merge default into stable for 4.0 code freeze

CONTRIBUTING

@@ -0,0 +1,13 b''
+Our full contribution guidelines are in our wiki, please see:
+
+https://www.mercurial-scm.org/wiki/ContributingChanges
+
+If you just want a checklist to follow, you can go straight to
+
+https://www.mercurial-scm.org/wiki/ContributingChanges#Submission_checklist
+
+If you can't run the entire testsuite for some reason (it can be
+difficult on Windows), please at least run `contrib/check-code.py` on
+any files you've modified and run `python contrib/check-commit` on any
+commits you've made (for example, `python contrib/check-commit
+273ce12ad8f1` will report some style violations on a very old commit).

Makefile

@@ -1,264 +1,266 b''
 # If you want to change PREFIX, do not just edit it below. The changed
 # value wont get passed on to recursive make calls. You should instead
 # override the variable on the command like:
 #
 # % make PREFIX=/opt/ install
 
 export PREFIX=/usr/local
 PYTHON=python
 $(eval HGROOT := $(shell pwd))
 HGPYTHONS ?= $(HGROOT)/build/pythons
 PURE=
 PYFILES:=$(shell find mercurial hgext doc -name '*.py')
 DOCFILES=mercurial/help/*.txt
 export LANGUAGE=C
 export LC_ALL=C
 TESTFLAGS ?= $(shell echo $$HGTESTFLAGS)
 
 # Set this to e.g. "mingw32" to use a non-default compiler.
 COMPILER=
 
 COMPILERFLAG_tmp_ =
 COMPILERFLAG_tmp_${COMPILER} ?= -c $(COMPILER)
 COMPILERFLAG=${COMPILERFLAG_tmp_${COMPILER}}
 
 help:
 	@echo 'Commonly used make targets:'
 	@echo '  all          - build program and documentation'
 	@echo '  install      - install program and man pages to $$PREFIX ($(PREFIX))'
 	@echo '  install-home - install with setup.py install --home=$$HOME ($(HOME))'
 	@echo '  local        - build for inplace usage'
 	@echo '  tests        - run all tests in the automatic test suite'
 	@echo '  test-foo     - run only specified tests (e.g. test-merge1.t)'
 	@echo '  dist         - run all tests and create a source tarball in dist/'
 	@echo '  clean        - remove files created by other targets'
 	@echo '                 (except installed files or dist source tarball)'
 	@echo '  update-pot   - update i18n/hg.pot'
 	@echo
 	@echo 'Example for a system-wide installation under /usr/local:'
 	@echo '  make all && su -c "make install" && hg version'
 	@echo
 	@echo 'Example for a local installation (usable in this directory):'
 	@echo '  make local && ./hg version'
 
 all: build doc
 
 local:
 	$(PYTHON) setup.py $(PURE) \
 	  build_py -c -d . \
 	  build_ext $(COMPILERFLAG) -i \
 	  build_hgexe $(COMPILERFLAG) -i \
 	  build_mo
 	env HGRCPATH= $(PYTHON) hg version
 
 build:
 	$(PYTHON) setup.py $(PURE) build $(COMPILERFLAG)
 
 wheel:
 	FORCE_SETUPTOOLS=1 $(PYTHON) setup.py $(PURE) bdist_wheel $(COMPILERFLAG)
 
 doc:
 	$(MAKE) -C doc
 
 cleanbutpackages:
 	-$(PYTHON) setup.py clean --all # ignore errors from this command
 	find contrib doc hgext hgext3rd i18n mercurial tests \
 		\( -name '*.py[cdo]' -o -name '*.so' \) -exec rm -f '{}' ';'
 	rm -f $(addprefix mercurial/,$(notdir $(wildcard mercurial/pure/[a-z]*.py)))
 	rm -f MANIFEST MANIFEST.in hgext/__index__.py tests/*.err
 	rm -f mercurial/__modulepolicy__.py
 	if test -d .hg; then rm -f mercurial/__version__.py; fi
 	rm -rf build mercurial/locale
 	$(MAKE) -C doc clean
 	$(MAKE) -C contrib/chg distclean
 
 clean: cleanbutpackages
 	rm -rf packages
 
 install: install-bin install-doc
 
 install-bin: build
 	$(PYTHON) setup.py $(PURE) install --root="$(DESTDIR)/" --prefix="$(PREFIX)" --force
 
 install-doc: doc
 	cd doc && $(MAKE) $(MFLAGS) install
 
 install-home: install-home-bin install-home-doc
 
 install-home-bin: build
 	$(PYTHON) setup.py $(PURE) install --home="$(HOME)" --prefix="" --force
 
 install-home-doc: doc
 	cd doc && $(MAKE) $(MFLAGS) PREFIX="$(HOME)" install
 
 MANIFEST-doc:
 	$(MAKE) -C doc MANIFEST
 
 MANIFEST.in: MANIFEST-doc
 	hg manifest | sed -e 's/^/include /' > MANIFEST.in
 	echo include mercurial/__version__.py >> MANIFEST.in
 	sed -e 's/^/include /' < doc/MANIFEST >> MANIFEST.in
 
 dist:	tests dist-notests
 
 dist-notests:	doc MANIFEST.in
 	TAR_OPTIONS="--owner=root --group=root --mode=u+w,go-w,a+rX-s" $(PYTHON) setup.py -q sdist
 
 check: tests
 
 tests:
 	cd tests && $(PYTHON) run-tests.py $(TESTFLAGS)
 
 test-%:
 	cd tests && $(PYTHON) run-tests.py $(TESTFLAGS) $@
 
 testpy-%:
 	@echo Looking for Python $* in $(HGPYTHONS)
 	[ -e $(HGPYTHONS)/$*/bin/python ] || ( \
 	cd $$(mktemp --directory --tmpdir) && \
         $(MAKE) -f $(HGROOT)/contrib/Makefile.python PYTHONVER=$* PREFIX=$(HGPYTHONS)/$* python )
 	cd tests && $(HGPYTHONS)/$*/bin/python run-tests.py $(TESTFLAGS)
 
 check-code:
 	hg manifest | xargs python contrib/check-code.py
 
 update-pot: i18n/hg.pot
 
 i18n/hg.pot: $(PYFILES) $(DOCFILES) i18n/posplit i18n/hggettext
 	$(PYTHON) i18n/hggettext mercurial/commands.py \
 	  hgext/*.py hgext/*/__init__.py \
 	  mercurial/fileset.py mercurial/revset.py \
 	  mercurial/templatefilters.py mercurial/templatekw.py \
 	  mercurial/templater.py \
 	  mercurial/filemerge.py \
 	  mercurial/hgweb/webcommands.py \
 	  $(DOCFILES) > i18n/hg.pot.tmp
         # All strings marked for translation in Mercurial contain
         # ASCII characters only. But some files contain string
         # literals like this '\037\213'. xgettext thinks it has to
         # parse them even though they are not marked for translation.
         # Extracting with an explicit encoding of ISO-8859-1 will make
         # xgettext "parse" and ignore them.
 	echo $(PYFILES) | xargs \
 	  xgettext --package-name "Mercurial" \
 	  --msgid-bugs-address "<[e-mail]>" \
 	  --copyright-holder "Matt Mackall <[e-mail]> and others" \
 	  --from-code ISO-8859-1 --join --sort-by-file --add-comments=i18n: \
 	  -d hg -p i18n -o hg.pot.tmp
 	$(PYTHON) i18n/posplit i18n/hg.pot.tmp
         # The target file is not created before the last step. So it never is in
         # an intermediate state.
 	mv -f i18n/hg.pot.tmp i18n/hg.pot
 
 %.po: i18n/hg.pot
         # work on a temporary copy for never having a half completed target
 	cp $@ $@.tmp
 	msgmerge --no-location --update $@.tmp $^
 	mv -f $@.tmp $@
 
 # Packaging targets
 
 osx:
 	/usr/bin/python2.7 setup.py install --optimize=1 \
 	  --root=build/mercurial/ --prefix=/usr/local/ \
 	  --install-lib=/Library/Python/2.7/site-packages/
 	make -C doc all install DESTDIR="$(PWD)/build/mercurial/"
 	mkdir -p $${OUTPUTDIR:-dist}
-	pkgbuild --root build/mercurial/ --identifier org.mercurial-scm.mercurial \
-	  build/mercurial.pkg
 	HGVER=$$((cat build/mercurial/Library/Python/2.7/site-packages/mercurial/__version__.py; echo 'print(version)') | python) && \
 	OSXVER=$$(sw_vers -productVersion | cut -d. -f1,2) && \
+	pkgbuild --root build/mercurial/ \
+	  --identifier org.mercurial-scm.mercurial \
+	  --version "$${HGVER}" \
+	  build/mercurial.pkg && \
 	productbuild --distribution contrib/macosx/distribution.xml \
 	  --package-path build/ \
 	  --version "$${HGVER}" \
 	  --resources contrib/macosx/ \
 	  "$${OUTPUTDIR:-dist/}"/Mercurial-"$${HGVER}"-macosx"$${OSXVER}".pkg
 
 deb:
 	contrib/builddeb
 
 ppa:
 	contrib/builddeb --source-only
 
 docker-debian-jessie:
 	mkdir -p packages/debian-jessie
 	contrib/dockerdeb debian jessie
 
 contrib/docker/ubuntu-%: contrib/docker/ubuntu.template
 	sed "s/__CODENAME__/$*/" $< > $@
 
 docker-ubuntu-trusty: contrib/docker/ubuntu-trusty
 	contrib/dockerdeb ubuntu trusty
 
 docker-ubuntu-trusty-ppa: contrib/docker/ubuntu-trusty
 	contrib/dockerdeb ubuntu trusty --source-only
 
 docker-ubuntu-wily: contrib/docker/ubuntu-wily
 	contrib/dockerdeb ubuntu wily
 
 docker-ubuntu-wily-ppa: contrib/docker/ubuntu-wily
 	contrib/dockerdeb ubuntu wily --source-only
 
 docker-ubuntu-xenial: contrib/docker/ubuntu-xenial
 	contrib/dockerdeb ubuntu xenial
 
 docker-ubuntu-xenial-ppa: contrib/docker/ubuntu-xenial
 	contrib/dockerdeb ubuntu xenial --source-only
 
 fedora20:
 	mkdir -p packages/fedora20
 	contrib/buildrpm
 	cp rpmbuild/RPMS/*/* packages/fedora20
 	cp rpmbuild/SRPMS/* packages/fedora20
 	rm -rf rpmbuild
 
 docker-fedora20:
 	mkdir -p packages/fedora20
 	contrib/dockerrpm fedora20
 
 fedora21:
 	mkdir -p packages/fedora21
 	contrib/buildrpm
 	cp rpmbuild/RPMS/*/* packages/fedora21
 	cp rpmbuild/SRPMS/* packages/fedora21
 	rm -rf rpmbuild
 
 docker-fedora21:
 	mkdir -p packages/fedora21
 	contrib/dockerrpm fedora21
 
 centos5:
 	mkdir -p packages/centos5
 	contrib/buildrpm --withpython
 	cp rpmbuild/RPMS/*/* packages/centos5
 	cp rpmbuild/SRPMS/* packages/centos5
 
 docker-centos5:
 	mkdir -p packages/centos5
 	contrib/dockerrpm centos5 --withpython
 
 centos6:
 	mkdir -p packages/centos6
 	contrib/buildrpm
 	cp rpmbuild/RPMS/*/* packages/centos6
 	cp rpmbuild/SRPMS/* packages/centos6
 
 docker-centos6:
 	mkdir -p packages/centos6
 	contrib/dockerrpm centos6
 
 centos7:
 	mkdir -p packages/centos7
 	contrib/buildrpm
 	cp rpmbuild/RPMS/*/* packages/centos7
 	cp rpmbuild/SRPMS/* packages/centos7
 
 docker-centos7:
 	mkdir -p packages/centos7
 	contrib/dockerrpm centos7
 
 .PHONY: help all local build doc cleanbutpackages clean install install-bin \
 	install-doc install-home install-home-bin install-home-doc \
 	dist dist-notests check tests check-code update-pot \
 	osx fedora20 docker-fedora20 fedora21 docker-fedora21 \
 	centos5 docker-centos5 centos6 docker-centos6 centos7 docker-centos7

contrib/bash_completion

@@ -1,642 +1,644 b''
 # bash completion for the Mercurial distributed SCM -*- sh -*-
 
 # Docs:
 #
 # If you source this file from your .bashrc, bash should be able to
 # complete a command line that uses hg with all the available commands
 # and options and sometimes even arguments.
 #
 # Mercurial allows you to define additional commands through extensions.
 # Bash should be able to automatically figure out the name of these new
 # commands and their options.  See below for how to define _hg_opt_foo
 # and _hg_cmd_foo functions to fine-tune the completion for option and
 # non-option arguments, respectively.
 #
 #
 # Notes about completion for specific commands:
 #
 # - the completion function for the email command from the patchbomb
 #   extension will try to call _hg_emails to get a list of e-mail
 #   addresses.  It's up to the user to define this function.  For
 #   example, put the addresses of the lists that you usually patchbomb
 #   in ~/.patchbomb-to and the addresses that you usually use to send
 #   the patchbombs in ~/.patchbomb-from and use something like this:
 #
 #      _hg_emails()
 #      {
 #          if [ -r ~/.patchbomb-$1 ]; then
 #              cat ~/.patchbomb-$1
 #          fi
 #      }
 #
 #
 # Writing completion functions for additional commands:
 #
 # If it exists, the function _hg_cmd_foo will be called without
 # arguments to generate the completion candidates for the hg command
 # "foo".  If the command receives some arguments that aren't options
 # even though they start with a "-", you can define a function called
 # _hg_opt_foo to generate the completion candidates.  If _hg_opt_foo
 # doesn't return 0, regular completion for options is attempted.
 #
 # In addition to the regular completion variables provided by bash,
 # the following variables are also set:
 # - $hg - the hg program being used (e.g. /usr/bin/hg)
 # - $cmd - the name of the hg command being completed
 # - $cmd_index - the index of $cmd in $COMP_WORDS
 # - $cur - the current argument being completed
 # - $prev - the argument before $cur
 # - $global_args - "|"-separated list of global options that accept
 #                  an argument (e.g. '--cwd|-R|--repository')
 # - $canonical - 1 if we canonicalized $cmd before calling the function
 #                0 otherwise
 #
 
 shopt -s extglob
 
 _hg_cmd()
 {
     HGPLAIN=1 "$hg" "$@" 2>/dev/null
 }
 
 _hg_commands()
 {
     local commands
     commands="$(HGPLAINEXCEPT=alias _hg_cmd debugcomplete "$cur")" || commands=""
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$commands' -- "$cur"))
 }
 
 _hg_paths()
 {
     local paths="$(_hg_cmd paths -q)"
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$paths' -- "$cur"))
 }
 
 _hg_repos()
 {
     local i
     for i in $(compgen -d -- "$cur"); do
         test ! -d "$i"/.hg || COMPREPLY=(${COMPREPLY[@]:-} "$i")
     done
 }
 
 _hg_debugpathcomplete()
 {
     local files="$(_hg_cmd debugpathcomplete $1 "$cur")"
     local IFS=$'\n'
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$files' -- "$cur"))
 }
 
 _hg_status()
 {
-    local files="$(_hg_cmd status -n$1 "glob:$cur**")"
-    local IFS=$'\n'
-    COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$files' -- "$cur"))
+    if [ -z "$HGCOMPLETE_NOSTATUS" ]; then
+        local files="$(_hg_cmd status -n$1 "glob:$cur**")"
+        local IFS=$'\n'
+        COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$files' -- "$cur"))
+    fi
 }
 
 _hg_branches()
 {
     local branches="$(_hg_cmd branches -q)"
     local IFS=$'\n'
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$branches' -- "$cur"))
 }
 
 _hg_bookmarks()
 {
     local bookmarks="$(_hg_cmd bookmarks -q)"
     local IFS=$'\n'
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$bookmarks' -- "$cur"))
 }
 
 _hg_labels()
 {
     local labels="$(_hg_cmd debugnamecomplete "$cur")"
     local IFS=$'\n'
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$labels' -- "$cur"))
 }
 
 # this is "kind of" ugly...
 _hg_count_non_option()
 {
     local i count=0
     local filters="$1"
 
     for ((i=1; $i<=$COMP_CWORD; i++)); do
         if [[ "${COMP_WORDS[i]}" != -* ]]; then
             if [[ ${COMP_WORDS[i-1]} == @($filters|$global_args) ]]; then
                 continue
             fi
             count=$(($count + 1))
         fi
     done
 
     echo $(($count - 1))
 }
 
 _hg_fix_wordlist()
 {
     local LASTCHAR=' '
     if [ ${#COMPREPLY[@]} = 1 ]; then
         [ -d "$COMPREPLY" ] && LASTCHAR=/
         COMPREPLY=$(printf %q%s "$COMPREPLY" "$LASTCHAR")
     else
         for ((i=0; i < ${#COMPREPLY[@]}; i++)); do
             [ -d "${COMPREPLY[$i]}" ] && COMPREPLY[$i]=${COMPREPLY[$i]}/
         done
     fi
 }
 
 _hg()
 {
     local cur prev cmd cmd_index opts i aliashg
     # global options that receive an argument
     local global_args='--cwd|-R|--repository'
     local hg="$1"
     local canonical=0
 
     aliashg=$(alias $hg 2>/dev/null)
     if [[ -n "$aliashg" ]]; then
       aliashg=${aliashg#"alias $hg='"}
       aliashg=${aliashg%"'"}
       hg=$aliashg
     fi
 
     COMPREPLY=()
     cur="$2"
     prev="$3"
 
     # searching for the command
     # (first non-option argument that doesn't follow a global option that
     #  receives an argument)
     for ((i=1; $i<=$COMP_CWORD; i++)); do
         if [[ ${COMP_WORDS[i]} != -* ]]; then
             if [[ ${COMP_WORDS[i-1]} != @($global_args) ]]; then
                 cmd="${COMP_WORDS[i]}"
                 cmd_index=$i
                 break
             fi
         fi
     done
 
     if [[ "$cur" == -* ]]; then
         if [ "$(type -t "_hg_opt_$cmd")" = function ] && "_hg_opt_$cmd"; then
             _hg_fix_wordlist
             return
         fi
 
         opts=$(HGPLAINEXCEPT=alias _hg_cmd debugcomplete --options "$cmd")
 
         COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$opts' -- "$cur"))
         _hg_fix_wordlist
         return
     fi
 
     # global options
     case "$prev" in
         -R|--repository)
             _hg_paths
             _hg_repos
             _hg_fix_wordlist
             return
         ;;
         --cwd)
             # Stick with default bash completion
             _hg_fix_wordlist
             return
         ;;
     esac
 
     if [ -z "$cmd" ] || [ $COMP_CWORD -eq $i ]; then
         _hg_commands
         _hg_fix_wordlist
         return
     fi
 
     # try to generate completion candidates for whatever command the user typed
     local help
     if _hg_command_specific; then
         _hg_fix_wordlist
         return
     fi
 
     # canonicalize the command name and try again
     help=$(_hg_cmd help "$cmd")
     if [ $? -ne 0 ]; then
         # Probably either the command doesn't exist or it's ambiguous
         return
     fi
     cmd=${help#hg }
     cmd=${cmd%%[$' \n']*}
     canonical=1
     _hg_command_specific
     _hg_fix_wordlist
 }
 
 _hg_command_specific()
 {
     if [ "$(type -t "_hg_cmd_$cmd")" = function ]; then
         "_hg_cmd_$cmd"
         return 0
     fi
 
     if [ "$cmd" != status ]; then
         case "$prev" in
             -r|--rev)
                 if [[ $canonical = 1 || status != "$cmd"* ]]; then
                     _hg_labels
                     return 0
                 fi
                 return 1
             ;;
             -B|--bookmark)
                 if [[ $canonical = 1 || status != "$cmd"* ]]; then
                     _hg_bookmarks
                     return 0
                 fi
                 return 1
             ;;
             -b|--branch)
                 if [[ $canonical = 1 || status != "$cmd"* ]]; then
                     _hg_branches
                     return 0
                 fi
                 return 1
             ;;
         esac
     fi
 
     local aliascmd=$(_hg_cmd showconfig alias.$cmd | awk '{print $1}')
     [ -n "$aliascmd" ] && cmd=$aliascmd
 
     case "$cmd" in
         help)
             _hg_commands
         ;;
         export)
             if _hg_ext_mq_patchlist qapplied && [ "${COMPREPLY[*]}" ]; then
                 return 0
             fi
             _hg_labels
         ;;
         manifest|update|up|checkout|co)
             _hg_labels
         ;;
         pull|push|outgoing|incoming)
             _hg_paths
             _hg_repos
         ;;
         paths)
             _hg_paths
         ;;
         add)
             _hg_status "u"
         ;;
         merge)
             _hg_labels
         ;;
         commit|ci|record)
             _hg_status "mar"
         ;;
         remove|rm)
             _hg_debugpathcomplete -n
         ;;
         forget)
             _hg_debugpathcomplete -fa
         ;;
         diff)
             _hg_status "mar"
         ;;
         revert)
             _hg_debugpathcomplete
         ;;
         clone)
             local count=$(_hg_count_non_option)
             if [ $count = 1 ]; then
                 _hg_paths
             fi
             _hg_repos
         ;;
         debugindex|debugindexdot)
             COMPREPLY=(${COMPREPLY[@]:-} $(compgen -f -X "!*.i" -- "$cur"))
         ;;
         debugdata)
             COMPREPLY=(${COMPREPLY[@]:-} $(compgen -f -X "!*.d" -- "$cur"))
         ;;
         *)
             return 1
         ;;
     esac
 
     return 0
 }
 
 complete -o bashdefault -o default -o nospace -F _hg hg \
     || complete -o default -o nospace -F _hg hg
 
 
 # Completion for commands provided by extensions
 
 # bookmarks
 _hg_cmd_bookmarks()
 {
     _hg_bookmarks
     return
 }
 
 # mq
 _hg_ext_mq_patchlist()
 {
     local patches
     patches=$(_hg_cmd $1)
     if [ $? -eq 0 ] && [ "$patches" ]; then
         COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$patches' -- "$cur"))
         return 0
     fi
     return 1
 }
 
 _hg_ext_mq_queues()
 {
     local root=$(_hg_cmd root)
     local n
     for n in $(cd "$root"/.hg && compgen -d -- "$cur"); do
         # I think we're usually not interested in the regular "patches" queue
         # so just filter it.
         if [ "$n" != patches ] && [ -e "$root/.hg/$n/series" ]; then
             COMPREPLY=(${COMPREPLY[@]:-} "$n")
         fi
     done
 }
 
 _hg_cmd_qpop()
 {
     if [[ "$prev" = @(-n|--name) ]]; then
         _hg_ext_mq_queues
         return
     fi
     _hg_ext_mq_patchlist qapplied
 }
 
 _hg_cmd_qpush()
 {
     if [[ "$prev" = @(-n|--name) ]]; then
         _hg_ext_mq_queues
         return
     fi
     _hg_ext_mq_patchlist qunapplied
 }
 
 _hg_cmd_qgoto()
 {
     if [[ "$prev" = @(-n|--name) ]]; then
         _hg_ext_mq_queues
         return
     fi
     _hg_ext_mq_patchlist qseries
 }
 
 _hg_cmd_qdelete()
 {
     local qcmd=qunapplied
     if [[ "$prev" = @(-r|--rev) ]]; then
         qcmd=qapplied
     fi
     _hg_ext_mq_patchlist $qcmd
 }
 
 _hg_cmd_qfinish()
 {
     if [[ "$prev" = @(-a|--applied) ]]; then
         return
     fi
     _hg_ext_mq_patchlist qapplied
 }
 
 _hg_cmd_qsave()
 {
     if [[ "$prev" = @(-n|--name) ]]; then
         _hg_ext_mq_queues
         return
     fi
 }
 
 _hg_cmd_rebase() {
    if [[ "$prev" = @(-s|--source|-d|--dest|-b|--base|-r|--rev) ]]; then
        _hg_labels
        return
    fi
 }
 
 _hg_cmd_strip()
 {
     if [[ "$prev" = @(-B|--bookmark) ]]; then
         _hg_bookmarks
         return
     fi
     _hg_labels
 }
 
 _hg_cmd_qcommit()
 {
     local root=$(_hg_cmd root)
     # this is run in a sub-shell, so we can't use _hg_status
     local files=$(cd "$root/.hg/patches" && _hg_cmd status -nmar)
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$files' -- "$cur"))
 }
 
 _hg_cmd_qfold()
 {
     _hg_ext_mq_patchlist qunapplied
 }
 
 _hg_cmd_qrename()
 {
     _hg_ext_mq_patchlist qseries
 }
 
 _hg_cmd_qheader()
 {
     _hg_ext_mq_patchlist qseries
 }
 
 _hg_cmd_qclone()
 {
     local count=$(_hg_count_non_option)
     if [ $count = 1 ]; then
         _hg_paths
     fi
     _hg_repos
 }
 
 _hg_ext_mq_guards()
 {
     _hg_cmd qselect --series | sed -e 's/^.//'
 }
 
 _hg_cmd_qselect()
 {
     local guards=$(_hg_ext_mq_guards)
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$guards' -- "$cur"))
 }
 
 _hg_cmd_qguard()
 {
     local prefix=''
 
     if [[ "$cur" == +* ]]; then
         prefix=+
     elif [[ "$cur" == -* ]]; then
         prefix=-
     fi
     local ncur=${cur#[-+]}
 
     if ! [ "$prefix" ]; then
         _hg_ext_mq_patchlist qseries
         return
     fi
 
     local guards=$(_hg_ext_mq_guards)
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -P $prefix -W '$guards' -- "$ncur"))
 }
 
 _hg_opt_qguard()
 {
     local i
     for ((i=cmd_index+1; i<=COMP_CWORD; i++)); do
         if [[ ${COMP_WORDS[i]} != -* ]]; then
             if [[ ${COMP_WORDS[i-1]} != @($global_args) ]]; then
                 _hg_cmd_qguard
                 return 0
             fi
         elif [ "${COMP_WORDS[i]}" = -- ]; then
             _hg_cmd_qguard
             return 0
         fi
     done
     return 1
 }
 
 _hg_cmd_qqueue()
 {
     local q
     local queues
     local opts="--list --create --rename --delete --purge"
 
     queues=$( _hg_cmd qqueue --quiet )
 
     COMPREPLY=( $( compgen -W "${opts} ${queues}" "${cur}" ) )
 }
 
 
 # hbisect
 _hg_cmd_bisect()
 {
     local i subcmd
 
     # find the sub-command
     for ((i=cmd_index+1; i<=COMP_CWORD; i++)); do
         if [[ ${COMP_WORDS[i]} != -* ]]; then
             if [[ ${COMP_WORDS[i-1]} != @($global_args) ]]; then
                 subcmd="${COMP_WORDS[i]}"
                 break
             fi
         fi
     done
 
     if [ -z "$subcmd" ] || [ $COMP_CWORD -eq $i ] || [ "$subcmd" = help ]; then
         COMPREPLY=(${COMPREPLY[@]:-}
                    $(compgen -W 'bad good help init next reset' -- "$cur"))
         return
     fi
 
     case "$subcmd" in
         good|bad)
             _hg_labels
             ;;
     esac
 
     return
 }
 
 
 # patchbomb
 _hg_cmd_email()
 {
     case "$prev" in
         -c|--cc|-t|--to|-f|--from|--bcc)
             # we need an e-mail address. let the user provide a function
             # to get them
             if [ "$(type -t _hg_emails)" = function ]; then
                 local arg=to
                 if [[ "$prev" == @(-f|--from) ]]; then
                     arg=from
                 fi
                 local addresses=$(_hg_emails $arg)
                 COMPREPLY=(${COMPREPLY[@]:-}
                            $(compgen -W '$addresses' -- "$cur"))
             fi
             return
             ;;
         -m|--mbox)
             # fallback to standard filename completion
             return
             ;;
         -s|--subject)
             # free form string
             return
             ;;
     esac
 
     _hg_labels
     return
 }
 
 
 # gpg
 _hg_cmd_sign()
 {
     _hg_labels
 }
 
 
 # transplant
 _hg_cmd_transplant()
 {
     case "$prev" in
         -s|--source)
             _hg_paths
             _hg_repos
             return
             ;;
         --filter)
             # standard filename completion
             return
             ;;
     esac
 
     # all other transplant options values and command parameters are revisions
     _hg_labels
     return
 }
 
 # shelve
 _hg_shelves()
 {
     local shelves="$(_hg_cmd shelve -ql)"
     local IFS=$'\n'
     COMPREPLY=(${COMPREPLY[@]:-} $(compgen -W '$shelves' -- "$cur"))
 }
 
 _hg_cmd_shelve()
 {
     if [[ "$prev" = @(-d|--delete|-l|--list|-p|--patch|--stat) ]]; then
         _hg_shelves
     else
         _hg_status "mard"
     fi
 }
 
 _hg_cmd_unshelve()
 {
     _hg_shelves
 }

contrib/check-code.py

@@ -1,657 +1,657 b''
 #!/usr/bin/env python
 #
 # check-code - a style and portability checker for Mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """style and portability checker for Mercurial
 
 when a rule triggers wrong, do one of the following (prefer one from top):
  * do the work-around the rule suggests
  * doublecheck that it is a false match
  * improve the rule pattern
  * add an ignore pattern to the rule (3rd arg) which matches your good line
    (you can append a short comment and match this, like: #re-raises)
  * change the pattern to a warning and list the exception in test-check-code-hg
  * ONLY use no--check-code for skipping entire files from external sources
 """
 
 from __future__ import absolute_import, print_function
 import glob
 import keyword
 import optparse
 import os
 import re
 import sys
 if sys.version_info[0] < 3:
     opentext = open
 else:
     def opentext(f):
         return open(f, encoding='ascii')
 try:
     xrange
 except NameError:
     xrange = range
 try:
     import re2
 except ImportError:
     re2 = None
 
 def compilere(pat, multiline=False):
     if multiline:
         pat = '(?m)' + pat
     if re2:
         try:
             return re2.compile(pat)
         except re2.error:
             pass
     return re.compile(pat)
 
 # check "rules depending on implementation of repquote()" in each
 # patterns (especially pypats), before changing around repquote()
 _repquotefixedmap = {' ': ' ', '\n': '\n', '.': 'p', ':': 'q',
                      '%': '%', '\\': 'b', '*': 'A', '+': 'P', '-': 'M'}
 def _repquoteencodechr(i):
     if i > 255:
         return 'u'
     c = chr(i)
     if c in _repquotefixedmap:
         return _repquotefixedmap[c]
     if c.isalpha():
         return 'x'
     if c.isdigit():
         return 'n'
     return 'o'
 _repquotett = ''.join(_repquoteencodechr(i) for i in xrange(256))
 
 def repquote(m):
     t = m.group('text')
     t = t.translate(_repquotett)
     return m.group('quote') + t + m.group('quote')
 
 def reppython(m):
     comment = m.group('comment')
     if comment:
         l = len(comment.rstrip())
         return "#" * l + comment[l:]
     return repquote(m)
 
 def repcomment(m):
     return m.group(1) + "#" * len(m.group(2))
 
 def repccomment(m):
     t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
     return m.group(1) + t + "*/"
 
 def repcallspaces(m):
     t = re.sub(r"\n\s+", "\n", m.group(2))
     return m.group(1) + t
 
 def repinclude(m):
     return m.group(1) + "<foo>"
 
 def rephere(m):
     t = re.sub(r"\S", "x", m.group(2))
     return m.group(1) + t
 
 
 testpats = [
   [
     (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),
     (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
     (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
     (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"),
     (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
     (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
     (r'echo -n', "don't use 'echo -n', use printf"),
     (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
     (r'head -c', "don't use 'head -c', use 'dd'"),
     (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
     (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
     (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
     (r'printf.*[^\\]\\([1-9]|0\d)', r"don't use 'printf \NNN', use Python"),
     (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
     (r'\$\(.*\)', "don't use $(expr), use `expr`"),
     (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
     (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
      "use egrep for extended grep syntax"),
     (r'/bin/', "don't use explicit paths for tools"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'export .*=', "don't export and assign at once"),
     (r'^source\b', "don't use 'source', use '.'"),
     (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
     (r'\bls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
     (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
     (r'^stop\(\)', "don't use 'stop' as a shell function name"),
     (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
     (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
     (r'^alias\b.*=', "don't use alias, use a function"),
     (r'if\s*!', "don't use '!' to negate exit status"),
     (r'/dev/u?random', "don't use entropy, use /dev/zero"),
     (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
     (r'^( *)\t', "don't use tabs to indent"),
     (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
      "put a backslash-escaped newline after sed 'i' command"),
     (r'^diff *-\w*[uU].*$\n(^  \$ |^$)', "prefix diff -u/-U with cmp"),
     (r'^\s+(if)? diff *-\w*[uU]', "prefix diff -u/-U with cmp"),
     (r'seq ', "don't use 'seq', use $TESTDIR/seq.py"),
     (r'\butil\.Abort\b', "directly use error.Abort"),
     (r'\|&', "don't use |&, use 2>&1"),
     (r'\w =  +\w', "only one space after = allowed"),
     (r'\bsed\b.*[^\\]\\n', "don't use 'sed ... \\n', use a \\ and a newline"),
     (r'env.*-u', "don't use 'env -u VAR', use 'unset VAR'")
   ],
   # warnings
   [
     (r'^function', "don't use 'function', use old style"),
     (r'^diff.*-\w*N', "don't use 'diff -N'"),
     (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
     (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
     (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
   ]
 ]
 
 testfilters = [
     (r"( *)(#([^\n]*\S)?)", repcomment),
     (r"<<(\S+)((.|\n)*?\n\1)", rephere),
 ]
 
 winglobmsg = "use (glob) to match Windows paths too"
 uprefix = r"^  \$ "
 utestpats = [
   [
     (r'^(\S.*||  [$>] \S.*)[ \t]\n', "trailing whitespace on non-output"),
     (uprefix + r'.*\|\s*sed[^|>\n]*\n',
      "use regex test output patterns instead of sed"),
     (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
     (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
     (uprefix + r'.*\|\| echo.*(fail|error)',
      "explicit exit code checks unnecessary"),
     (uprefix + r'set -e', "don't use set -e"),
     (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
     (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
      "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
      '# no-msys'), # in test-pull.t which is skipped on windows
     (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
     (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
      winglobmsg),
     (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
      '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
     (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
     (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
     (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
     (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
     (r'^  moving \S+/.*[^)]$', winglobmsg),
     (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
     (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
     (r'^  .*file://\$TESTTMP',
      'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
     (r'^  [^$>].*27\.0\.0\.1.*[^)]$',
      'use (glob) to match localhost IP on hosts without 127.0.0.1 too'),
     (r'^  (cat|find): .*: No such file or directory',
      'use test -f to test for file existence'),
     (r'^  diff -[^ -]*p',
      "don't use (external) diff with -p for portability"),
     (r'^  [-+][-+][-+] .* [-+]0000 \(glob\)',
      "glob timezone field in diff output for portability"),
     (r'^  @@ -[0-9]+ [+][0-9]+,[0-9]+ @@',
      "use '@@ -N* +N,n @@ (glob)' style chunk header for portability"),
     (r'^  @@ -[0-9]+,[0-9]+ [+][0-9]+ @@',
      "use '@@ -N,n +N* @@ (glob)' style chunk header for portability"),
     (r'^  @@ -[0-9]+ [+][0-9]+ @@',
      "use '@@ -N* +N* @@ (glob)' style chunk header for portability"),
     (uprefix + r'hg( +-[^ ]+( +[^ ]+)?)* +extdiff'
      r'( +(-[^ po-]+|--(?!program|option)[^ ]+|[^-][^ ]*))*$',
      "use $RUNTESTDIR/pdiff via extdiff (or -o/-p for false-positives)"),
   ],
   # warnings
   [
     (r'^  (?!.*127\.0\.0\.1)[^*?/\n]* \(glob\)$',
      "glob match with no glob string (?, *, /, and 127.0.0.1)"),
   ]
 ]
 
 for i in [0, 1]:
     for tp in testpats[i]:
         p = tp[0]
         m = tp[1]
         if p.startswith(r'^'):
             p = r"^  [$>] (%s)" % p[1:]
         else:
             p = r"^  [$>] .*(%s)" % p
         utestpats[i].append((p, m) + tp[2:])
 
 utestfilters = [
     (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
     (r"( +)(#([^\n]*\S)?)", repcomment),
 ]
 
 pypats = [
   [
     (r'^\s*def\s*\w+\s*\(.*,\s*\(',
      "tuple parameter unpacking not available in Python 3+"),
     (r'lambda\s*\(.*,.*\)',
      "tuple parameter unpacking not available in Python 3+"),
     (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
     (r'\breduce\s*\(.*', "reduce is not available in Python 3+"),
-    (r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
+    (r'\bdict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
      'dict-from-generator'),
     (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
     (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
     (r'^\s*\t', "don't use tabs"),
     (r'\S;\s*\n', "semicolon"),
     (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
     (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
     (r'(\w|\)),\w', "missing whitespace after ,"),
     (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
     (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
     (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
     (r'.{81}', "line too long"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
 #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
 #     "don't use underbars in identifiers"),
     (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
      "don't use camelcase in identifiers"),
     (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
      "linebreak after :"),
     (r'class\s[^( \n]+:', "old-style class, use class foo(object)",
      r'#.*old-style'),
     (r'class\s[^( \n]+\(\):',
      "class foo() creates old style object, use class foo(object)",
      r'#.*old-style'),
     (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                             if k not in ('print', 'exec')),
      "Python keyword is not a function"),
     (r',]', "unneeded trailing ',' in list"),
 #    (r'class\s[A-Z][^\(]*\((?!Exception)',
 #     "don't capitalize non-exception classes"),
 #    (r'in range\(', "use xrange"),
 #    (r'^\s*print\s+', "avoid using print in core and extensions"),
     (r'[\x80-\xff]', "non-ASCII character literal"),
     (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
     (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
      "gratuitous whitespace after Python keyword"),
     (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
 #    (r'\s\s=', "gratuitous whitespace before ="),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
      "missing whitespace around operator"),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
      "missing whitespace around operator"),
     (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
      "missing whitespace around operator"),
     (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
      "wrong whitespace around ="),
     (r'\([^()]*( =[^=]|[^<>!=]= )',
      "no whitespace around = for named parameters"),
     (r'raise Exception', "don't raise generic exceptions"),
     (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
      "don't use old-style two-argument raise, use Exception(message)"),
     (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
     (r' [=!]=\s+(True|False|None)',
      "comparison with singleton, use 'is' or 'is not' instead"),
     (r'^\s*(while|if) [01]:',
      "use True/False for constant Boolean expression"),
-    (r'(?:(?<!def)\s+|\()hasattr',
+    (r'(?:(?<!def)\s+|\()hasattr\(',
      'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
     (r'opener\([^)]*\).read\(',
      "use opener.read() instead"),
     (r'opener\([^)]*\).write\(',
      "use opener.write() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.read\(',
      "use util.readfile() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.write\(',
      "use util.writefile() instead"),
     (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'[\s\(](open|file)\([^)]*\)\.',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
     (r'\.debug\(\_', "don't mark debug messages for translation"),
     (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
     (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
     (r'^\s*except\s([^\(,]+|\([^\)]+\))\s*,',
      'legacy exception syntax; use "as" instead of ","'),
     (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
     (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
     (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
     (r'os\.path\.join\(.*, *(""|\'\')\)',
      "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
     (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
     # XXX only catch mutable arguments on the first line of the definition
     (r'def.*[( ]\w+=\{\}', "don't use mutable default arguments"),
     (r'\butil\.Abort\b', "directly use error.Abort"),
     (r'^import Queue', "don't use Queue, use util.queue + util.empty"),
     (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"),
     (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"),
     (r'^import SocketServer', "don't use SockerServer, use util.socketserver"),
     (r'^import urlparse', "don't use urlparse, use util.urlparse"),
     (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"),
     (r'^import cPickle', "don't use cPickle, use util.pickle"),
     (r'^import pickle', "don't use pickle, use util.pickle"),
     (r'^import httplib', "don't use httplib, use util.httplib"),
     (r'^import BaseHTTPServer', "use util.httpserver instead"),
     (r'\.next\(\)', "don't use .next(), use next(...)"),
 
     # rules depending on implementation of repquote()
     (r' x+[xpqo%APM][\'"]\n\s+[\'"]x',
      'string join across lines with no space'),
     (r'''(?x)ui\.(status|progress|write|note|warn)\(
          [ \t\n#]*
          (?# any strings/comments might precede a string, which
            # contains translatable message)
          ((['"]|\'\'\'|""")[ \npq%bAPMxno]*(['"]|\'\'\'|""")[ \t\n#]+)*
          (?# sequence consisting of below might precede translatable message
            # - formatting string: "% 10s", "%05d", "% -3.2f", "%*s", "%%" ...
            # - escaped character: "\\", "\n", "\0" ...
            # - character other than '%', 'b' as '\', and 'x' as alphabet)
          (['"]|\'\'\'|""")
          ((%([ n]?[PM]?([np]+|A))?x)|%%|b[bnx]|[ \nnpqAPMo])*x
          (?# this regexp can't use [^...] style,
            # because _preparepats forcibly adds "\n" into [^...],
            # even though this regexp wants match it against "\n")''',
      "missing _() in ui message (use () to hide false-positives)"),
   ],
   # warnings
   [
     # rules depending on implementation of repquote()
     (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
   ]
 ]
 
 pyfilters = [
     (r"""(?msx)(?P<comment>\#.*?$)|
          ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
           (?P<text>(([^\\]|\\.)*?))
           (?P=quote))""", reppython),
 ]
 
 txtfilters = []
 
 txtpats = [
   [
     ('\s$', 'trailing whitespace'),
     ('.. note::[ \n][^\n]', 'add two newlines after note::')
   ],
   []
 ]
 
 cpats = [
   [
     (r'//', "don't use //-style comments"),
     (r'^  ', "don't use spaces to indent"),
     (r'\S\t', "don't use tabs except for indent"),
     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
     (r'.{81}', "line too long"),
     (r'(while|if|do|for)\(', "use space after while/if/do/for"),
     (r'return\(', "return is not a function"),
     (r' ;', "no space before ;"),
     (r'[^;] \)', "no space before )"),
     (r'[)][{]', "space between ) and {"),
     (r'\w+\* \w+', "use int *foo, not int* foo"),
     (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
     (r'\w+ (\+\+|--)', "use foo++, not foo ++"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'^[^#]\w[+/*]\w', "missing whitespace in expression"),
     (r'\w\s=\s\s+\w', "gratuitous whitespace after ="),
     (r'^#\s+\w', "use #foo, not # foo"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'^\s*#import\b', "use only #include in standard C code"),
     (r'strcpy\(', "don't use strcpy, use strlcpy or memcpy"),
     (r'strcat\(', "don't use strcat"),
 
     # rules depending on implementation of repquote()
   ],
   # warnings
   [
     # rules depending on implementation of repquote()
   ]
 ]
 
 cfilters = [
     (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
     (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
     (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
     (r'(\()([^)]+\))', repcallspaces),
 ]
 
 inutilpats = [
   [
     (r'\bui\.', "don't use ui in util"),
   ],
   # warnings
   []
 ]
 
 inrevlogpats = [
   [
     (r'\brepo\.', "don't use repo in revlog"),
   ],
   # warnings
   []
 ]
 
 webtemplatefilters = []
 
 webtemplatepats = [
   [],
   [
     (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
      'follow desc keyword with either firstline or websub'),
   ]
 ]
 
 checks = [
     ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
     ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
     ('c', r'.*\.[ch]$', '', cfilters, cpats),
     ('unified test', r'.*\.t$', '', utestfilters, utestpats),
     ('layering violation repo in revlog', r'mercurial/revlog\.py', '',
      pyfilters, inrevlogpats),
     ('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,
      inutilpats),
     ('txt', r'.*\.txt$', '', txtfilters, txtpats),
     ('web template', r'mercurial/templates/.*\.tmpl', '',
      webtemplatefilters, webtemplatepats),
 ]
 
 def _preparepats():
     for c in checks:
         failandwarn = c[-1]
         for pats in failandwarn:
             for i, pseq in enumerate(pats):
                 # fix-up regexes for multi-line searches
                 p = pseq[0]
                 # \s doesn't match \n
                 p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                 # [^...] doesn't match newline
                 p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
 
                 pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
         filters = c[3]
         for i, flt in enumerate(filters):
             filters[i] = re.compile(flt[0]), flt[1]
 
 class norepeatlogger(object):
     def __init__(self):
         self._lastseen = None
 
     def log(self, fname, lineno, line, msg, blame):
         """print error related a to given line of a given file.
 
         The faulty line will also be printed but only once in the case
         of multiple errors.
 
         :fname: filename
         :lineno: line number
         :line: actual content of the line
         :msg: error message
         """
         msgid = fname, lineno, line
         if msgid != self._lastseen:
             if blame:
                 print("%s:%d (%s):" % (fname, lineno, blame))
             else:
                 print("%s:%d:" % (fname, lineno))
             print(" > %s" % line)
             self._lastseen = msgid
         print(" " + msg)
 
 _defaultlogger = norepeatlogger()
 
 def getblame(f):
     lines = []
     for l in os.popen('hg annotate -un %s' % f):
         start, line = l.split(':', 1)
         user, rev = start.split()
         lines.append((line[1:-1], user, rev))
     return lines
 
 def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
               blame=False, debug=False, lineno=True):
     """checks style and portability of a given file
 
     :f: filepath
     :logfunc: function used to report error
               logfunc(filename, linenumber, linecontent, errormessage)
     :maxerr: number of error to display before aborting.
              Set to false (default) to report all errors
 
     return True if no error is found, False otherwise.
     """
     blamecache = None
     result = True
 
     try:
         with opentext(f) as fp:
             try:
                 pre = post = fp.read()
             except UnicodeDecodeError as e:
                 print("%s while reading %s" % (e, f))
                 return result
     except IOError as e:
         print("Skipping %s, %s" % (f, str(e).split(':', 1)[0]))
         return result
 
     for name, match, magic, filters, pats in checks:
         if debug:
             print(name, f)
         fc = 0
         if not (re.match(match, f) or (magic and re.search(magic, pre))):
             if debug:
                 print("Skipping %s for %s it doesn't match %s" % (
                        name, match, f))
             continue
         if "no-" "check-code" in pre:
             # If you're looking at this line, it's because a file has:
             # no- check- code
             # but the reason to output skipping is to make life for
             # tests easier. So, instead of writing it with a normal
             # spelling, we write it with the expected spelling from
             # tests/test-check-code.t
             print("Skipping %s it has no-che?k-code (glob)" % f)
             return "Skip" # skip checking this file
         for p, r in filters:
             post = re.sub(p, r, post)
         nerrs = len(pats[0]) # nerr elements are errors
         if warnings:
             pats = pats[0] + pats[1]
         else:
             pats = pats[0]
         # print post # uncomment to show filtered version
 
         if debug:
             print("Checking %s for %s" % (name, f))
 
         prelines = None
         errors = []
         for i, pat in enumerate(pats):
             if len(pat) == 3:
                 p, msg, ignore = pat
             else:
                 p, msg = pat
                 ignore = None
             if i >= nerrs:
                 msg = "warning: " + msg
 
             pos = 0
             n = 0
             for m in p.finditer(post):
                 if prelines is None:
                     prelines = pre.splitlines()
                     postlines = post.splitlines(True)
 
                 start = m.start()
                 while n < len(postlines):
                     step = len(postlines[n])
                     if pos + step > start:
                         break
                     pos += step
                     n += 1
                 l = prelines[n]
 
                 if ignore and re.search(ignore, l, re.MULTILINE):
                     if debug:
                         print("Skipping %s for %s:%s (ignore pattern)" % (
                             name, f, n))
                     continue
                 bd = ""
                 if blame:
                     bd = 'working directory'
                     if not blamecache:
                         blamecache = getblame(f)
                     if n < len(blamecache):
                         bl, bu, br = blamecache[n]
                         if bl == l:
                             bd = '%s@%s' % (bu, br)
 
                 errors.append((f, lineno and n + 1, l, msg, bd))
                 result = False
 
         errors.sort()
         for e in errors:
             logfunc(*e)
             fc += 1
             if maxerr and fc >= maxerr:
                 print(" (too many errors, giving up)")
                 break
 
     return result
 
 def main():
     parser = optparse.OptionParser("%prog [options] [files]")
     parser.add_option("-w", "--warnings", action="store_true",
                       help="include warning-level checks")
     parser.add_option("-p", "--per-file", type="int",
                       help="max warnings per file")
     parser.add_option("-b", "--blame", action="store_true",
                       help="use annotate to generate blame info")
     parser.add_option("", "--debug", action="store_true",
                       help="show debug information")
     parser.add_option("", "--nolineno", action="store_false",
                       dest='lineno', help="don't show line numbers")
 
     parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                         lineno=True)
     (options, args) = parser.parse_args()
 
     if len(args) == 0:
         check = glob.glob("*")
     else:
         check = args
 
     _preparepats()
 
     ret = 0
     for f in check:
         if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                          blame=options.blame, debug=options.debug,
                          lineno=options.lineno):
             ret = 1
     return ret
 
 if __name__ == "__main__":
     sys.exit(main())

contrib/check-commit

@@ -1,102 +1,107 b''
 #!/usr/bin/env python
 #
 # Copyright 2014 Matt Mackall <[e-mail]>
 #
 # A tool/hook to run basic sanity checks on commits/patches for
 # submission to Mercurial. Install by adding the following to your
 # .hg/hgrc:
 #
 # [hooks]
 # pretxncommit = contrib/check-commit
 #
 # The hook can be temporarily bypassed with:
 #
 # $ BYPASS= hg commit
 #
 # See also: https://mercurial-scm.org/wiki/ContributingChanges
 
 from __future__ import absolute_import, print_function
 
 import os
 import re
 import sys
 
 commitheader = r"^(?:# [^\n]*\n)*"
 afterheader = commitheader + r"(?!#)"
 beforepatch = afterheader + r"(?!\n(?!@@))"
 
 errors = [
     (beforepatch + r".*[(]bc[)]", "(BC) needs to be uppercase"),
     (beforepatch + r".*[(]issue \d\d\d",
      "no space allowed between issue and number"),
     (beforepatch + r".*[(]bug(\d|\s)", "use (issueDDDD) instead of bug"),
     (commitheader + r"# User [^@\n]+\n", "username is not an email address"),
     (commitheader + r"(?!merge with )[^#]\S+[^:] ",
      "summary line doesn't start with 'topic: '"),
     (afterheader + r"[A-Z][a-z]\S+", "don't capitalize summary lines"),
     (afterheader + r"[^\n]*: *[A-Z][a-z]\S+", "don't capitalize summary lines"),
-    (afterheader + r"\S*[^A-Za-z0-9-]\S*: ",
+    (afterheader + r"\S*[^A-Za-z0-9-_]\S*: ",
      "summary keyword should be most user-relevant one-word command or topic"),
     (afterheader + r".*\.\s*\n", "don't add trailing period on summary line"),
     (afterheader + r".{79,}", "summary line too long (limit is 78)"),
     (r"\n\+\n( |\+)\n", "adds double empty line"),
     (r"\n \n\+\n", "adds double empty line"),
-    (r"\n\+[ \t]+def [a-z]+_[a-z]", "adds a function with foo_bar naming"),
+    # Forbid "_" in function name.
+    #
+    # We skip the check for cffi related functions. They use names mapping the
+    # name of the C function. C function names may contain "_".
+    (r"\n\+[ \t]+def (?!cffi)[a-z]+_[a-z]",
+     "adds a function with foo_bar naming"),
 ]
 
 word = re.compile('\S')
 def nonempty(first, second):
     if word.search(first):
         return first
     return second
 
 def checkcommit(commit, node=None):
     exitcode = 0
     printed = node is None
     hits = []
     for exp, msg in errors:
         for m in re.finditer(exp, commit):
             end = m.end()
             trailing = re.search(r'(\\n)+$', exp)
             if trailing:
                 end -= len(trailing.group()) / 2
             hits.append((end, exp, msg))
     if hits:
         hits.sort()
         pos = 0
         last = ''
         for n, l in enumerate(commit.splitlines(True)):
             pos += len(l)
             while len(hits):
                 end, exp, msg = hits[0]
                 if pos < end:
                     break
                 if not printed:
                     printed = True
                     print("node: %s" % node)
                 print("%d: %s" % (n, msg))
                 print(" %s" % nonempty(l, last)[:-1])
                 if "BYPASS" not in os.environ:
                     exitcode = 1
                 del hits[0]
             last = nonempty(l, last)
 
     return exitcode
 
 def readcommit(node):
     return os.popen("hg export %s" % node).read()
 
 if __name__ == "__main__":
     exitcode = 0
     node = os.environ.get("HG_NODE")
 
     if node:
         commit = readcommit(node)
         exitcode = checkcommit(commit)
     elif sys.argv[1:]:
         for node in sys.argv[1:]:
             exitcode |= checkcommit(readcommit(node), node)
     else:
         commit = sys.stdin.read()
         exitcode = checkcommit(commit)
     sys.exit(exitcode)

contrib/check-py3-compat.py

@@ -1,96 +1,95 b''
 #!/usr/bin/env python
 #
 # check-py3-compat - check Python 3 compatibility of Mercurial files
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import ast
-import imp
 import os
 import sys
 import traceback
 
 def check_compat_py2(f):
     """Check Python 3 compatibility for a file with Python 2"""
     with open(f, 'rb') as fh:
         content = fh.read()
     root = ast.parse(content)
 
     # Ignore empty files.
     if not root.body:
         return
 
     futures = set()
     haveprint = False
     for node in ast.walk(root):
         if isinstance(node, ast.ImportFrom):
             if node.module == '__future__':
                 futures |= set(n.name for n in node.names)
         elif isinstance(node, ast.Print):
             haveprint = True
 
     if 'absolute_import' not in futures:
         print('%s not using absolute_import' % f)
     if haveprint and 'print_function' not in futures:
         print('%s requires print_function' % f)
 
 def check_compat_py3(f):
     """Check Python 3 compatibility of a file with Python 3."""
+    import importlib  # not available on Python 2.6
     with open(f, 'rb') as fh:
         content = fh.read()
 
     try:
         ast.parse(content)
     except SyntaxError as e:
         print('%s: invalid syntax: %s' % (f, e))
         return
 
     # Try to import the module.
     # For now we only support mercurial.* and hgext.* modules because figuring
     # out module paths for things not in a package can be confusing.
     if f.startswith(('hgext/', 'mercurial/')) and not f.endswith('__init__.py'):
         assert f.endswith('.py')
-        name = f.replace('/', '.')[:-3]
-        with open(f, 'r') as fh:
-            try:
-                imp.load_module(name, fh, '', ('py', 'r', imp.PY_SOURCE))
-            except Exception as e:
-                exc_type, exc_value, tb = sys.exc_info()
-                # We walk the stack and ignore frames from our custom importer,
-                # import mechanisms, and stdlib modules. This kinda/sorta
-                # emulates CPython behavior in import.c while also attempting
-                # to pin blame on a Mercurial file.
-                for frame in reversed(traceback.extract_tb(tb)):
-                    if frame.name == '_call_with_frames_removed':
-                        continue
-                    if 'importlib' in frame.filename:
-                        continue
-                    if 'mercurial/__init__.py' in frame.filename:
-                        continue
-                    if frame.filename.startswith(sys.prefix):
-                        continue
-                    break
+        name = f.replace('/', '.')[:-3].replace('.pure.', '.')
+        try:
+            importlib.import_module(name)
+        except Exception as e:
+            exc_type, exc_value, tb = sys.exc_info()
+            # We walk the stack and ignore frames from our custom importer,
+            # import mechanisms, and stdlib modules. This kinda/sorta
+            # emulates CPython behavior in import.c while also attempting
+            # to pin blame on a Mercurial file.
+            for frame in reversed(traceback.extract_tb(tb)):
+                if frame.name == '_call_with_frames_removed':
+                    continue
+                if 'importlib' in frame.filename:
+                    continue
+                if 'mercurial/__init__.py' in frame.filename:
+                    continue
+                if frame.filename.startswith(sys.prefix):
+                    continue
+                break
 
-                if frame.filename:
-                    filename = os.path.basename(frame.filename)
-                    print('%s: error importing: <%s> %s (error at %s:%d)' % (
-                          f, type(e).__name__, e, filename, frame.lineno))
-                else:
-                    print('%s: error importing module: <%s> %s (line %d)' % (
-                          f, type(e).__name__, e, frame.lineno))
+            if frame.filename:
+                filename = os.path.basename(frame.filename)
+                print('%s: error importing: <%s> %s (error at %s:%d)' % (
+                      f, type(e).__name__, e, filename, frame.lineno))
+            else:
+                print('%s: error importing module: <%s> %s (line %d)' % (
+                      f, type(e).__name__, e, frame.lineno))
 
 if __name__ == '__main__':
     if sys.version_info[0] == 2:
         fn = check_compat_py2
     else:
         fn = check_compat_py3
 
     for f in sys.argv[1:]:
         fn(f)
 
     sys.exit(0)

contrib/chg/hgclient.c

@@ -1,590 +1,585 b''
 /*
  * A command server client that uses Unix domain socket
  *
  * Copyright (c) 2011 Yuya Nishihara <[e-mail]>
  *
  * This software may be used and distributed according to the terms of the
  * GNU General Public License version 2 or any later version.
  */
 
 #include <arpa/inet.h>  /* for ntohl(), htonl() */
 #include <assert.h>
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <signal.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
 #include <sys/un.h>
 #include <unistd.h>
 
 #include "hgclient.h"
 #include "util.h"
 
 enum {
 	CAP_GETENCODING = 0x0001,
 	CAP_RUNCOMMAND = 0x0002,
 	/* cHg extension: */
 	CAP_ATTACHIO = 0x0100,
 	CAP_CHDIR = 0x0200,
 	CAP_GETPAGER = 0x0400,
 	CAP_SETENV = 0x0800,
 	CAP_SETUMASK = 0x1000,
 	CAP_VALIDATE = 0x2000,
 };
 
 typedef struct {
 	const char *name;
 	unsigned int flag;
 } cappair_t;
 
 static const cappair_t captable[] = {
 	{"getencoding", CAP_GETENCODING},
 	{"runcommand", CAP_RUNCOMMAND},
 	{"attachio", CAP_ATTACHIO},
 	{"chdir", CAP_CHDIR},
 	{"getpager", CAP_GETPAGER},
 	{"setenv", CAP_SETENV},
 	{"setumask", CAP_SETUMASK},
 	{"validate", CAP_VALIDATE},
 	{NULL, 0},  /* terminator */
 };
 
 typedef struct {
 	char ch;
 	char *data;
 	size_t maxdatasize;
 	size_t datasize;
 } context_t;
 
 struct hgclient_tag_ {
 	int sockfd;
 	pid_t pgid;
 	pid_t pid;
 	context_t ctx;
 	unsigned int capflags;
 };
 
 static const size_t defaultdatasize = 4096;
 
 static void initcontext(context_t *ctx)
 {
 	ctx->ch = '\0';
 	ctx->data = malloc(defaultdatasize);
 	ctx->maxdatasize = (ctx->data) ? defaultdatasize : 0;
 	ctx->datasize = 0;
 	debugmsg("initialize context buffer with size %zu", ctx->maxdatasize);
 }
 
 static void enlargecontext(context_t *ctx, size_t newsize)
 {
 	if (newsize <= ctx->maxdatasize)
 		return;
 
 	newsize = defaultdatasize
 		* ((newsize + defaultdatasize - 1) / defaultdatasize);
 	ctx->data = reallocx(ctx->data, newsize);
 	ctx->maxdatasize = newsize;
 	debugmsg("enlarge context buffer to %zu", ctx->maxdatasize);
 }
 
 static void freecontext(context_t *ctx)
 {
 	debugmsg("free context buffer");
 	free(ctx->data);
 	ctx->data = NULL;
 	ctx->maxdatasize = 0;
 	ctx->datasize = 0;
 }
 
 /* Read channeled response from cmdserver */
 static void readchannel(hgclient_t *hgc)
 {
 	assert(hgc);
 
 	ssize_t rsize = recv(hgc->sockfd, &hgc->ctx.ch, sizeof(hgc->ctx.ch), 0);
 	if (rsize != sizeof(hgc->ctx.ch)) {
 		/* server would have exception and traceback would be printed */
 		debugmsg("failed to read channel");
 		exit(255);
 	}
 
 	uint32_t datasize_n;
 	rsize = recv(hgc->sockfd, &datasize_n, sizeof(datasize_n), 0);
 	if (rsize != sizeof(datasize_n))
 		abortmsg("failed to read data size");
 
 	/* datasize denotes the maximum size to write if input request */
 	hgc->ctx.datasize = ntohl(datasize_n);
 	enlargecontext(&hgc->ctx, hgc->ctx.datasize);
 
 	if (isupper(hgc->ctx.ch) && hgc->ctx.ch != 'S')
 		return;  /* assumes input request */
 
 	size_t cursize = 0;
-	int emptycount = 0;
 	while (cursize < hgc->ctx.datasize) {
 		rsize = recv(hgc->sockfd, hgc->ctx.data + cursize,
 			     hgc->ctx.datasize - cursize, 0);
-		/* rsize == 0 normally indicates EOF, while it's also a valid
-		 * packet size for unix socket. treat it as EOF and abort if
-		 * we get many empty responses in a row. */
-		emptycount = (rsize == 0 ? emptycount + 1 : 0);
-		if (rsize < 0 || emptycount > 20)
+		if (rsize < 1)
 			abortmsg("failed to read data block");
 		cursize += rsize;
 	}
 }
 
 static void sendall(int sockfd, const void *data, size_t datasize)
 {
 	const char *p = data;
 	const char *const endp = p + datasize;
 	while (p < endp) {
 		ssize_t r = send(sockfd, p, endp - p, 0);
 		if (r < 0)
 			abortmsgerrno("cannot communicate");
 		p += r;
 	}
 }
 
 /* Write lengh-data block to cmdserver */
 static void writeblock(const hgclient_t *hgc)
 {
 	assert(hgc);
 
 	const uint32_t datasize_n = htonl(hgc->ctx.datasize);
 	sendall(hgc->sockfd, &datasize_n, sizeof(datasize_n));
 
 	sendall(hgc->sockfd, hgc->ctx.data, hgc->ctx.datasize);
 }
 
 static void writeblockrequest(const hgclient_t *hgc, const char *chcmd)
 {
 	debugmsg("request %s, block size %zu", chcmd, hgc->ctx.datasize);
 
 	char buf[strlen(chcmd) + 1];
 	memcpy(buf, chcmd, sizeof(buf) - 1);
 	buf[sizeof(buf) - 1] = '\n';
 	sendall(hgc->sockfd, buf, sizeof(buf));
 
 	writeblock(hgc);
 }
 
 /* Build '\0'-separated list of args. argsize < 0 denotes that args are
  * terminated by NULL. */
 static void packcmdargs(context_t *ctx, const char *const args[],
 			ssize_t argsize)
 {
 	ctx->datasize = 0;
 	const char *const *const end = (argsize >= 0) ? args + argsize : NULL;
 	for (const char *const *it = args; it != end && *it; ++it) {
 		const size_t n = strlen(*it) + 1;  /* include '\0' */
 		enlargecontext(ctx, ctx->datasize + n);
 		memcpy(ctx->data + ctx->datasize, *it, n);
 		ctx->datasize += n;
 	}
 
 	if (ctx->datasize > 0)
 		--ctx->datasize;  /* strip last '\0' */
 }
 
 /* Extract '\0'-separated list of args to new buffer, terminated by NULL */
 static const char **unpackcmdargsnul(const context_t *ctx)
 {
 	const char **args = NULL;
 	size_t nargs = 0, maxnargs = 0;
 	const char *s = ctx->data;
 	const char *e = ctx->data + ctx->datasize;
 	for (;;) {
 		if (nargs + 1 >= maxnargs) {  /* including last NULL */
 			maxnargs += 256;
 			args = reallocx(args, maxnargs * sizeof(args[0]));
 		}
 		args[nargs] = s;
 		nargs++;
 		s = memchr(s, '\0', e - s);
 		if (!s)
 			break;
 		s++;
 	}
 	args[nargs] = NULL;
 	return args;
 }
 
 static void handlereadrequest(hgclient_t *hgc)
 {
 	context_t *ctx = &hgc->ctx;
 	size_t r = fread(ctx->data, sizeof(ctx->data[0]), ctx->datasize, stdin);
 	ctx->datasize = r;
 	writeblock(hgc);
 }
 
 /* Read single-line */
 static void handlereadlinerequest(hgclient_t *hgc)
 {
 	context_t *ctx = &hgc->ctx;
 	if (!fgets(ctx->data, ctx->datasize, stdin))
 		ctx->data[0] = '\0';
 	ctx->datasize = strlen(ctx->data);
 	writeblock(hgc);
 }
 
 /* Execute the requested command and write exit code */
 static void handlesystemrequest(hgclient_t *hgc)
 {
 	context_t *ctx = &hgc->ctx;
 	enlargecontext(ctx, ctx->datasize + 1);
 	ctx->data[ctx->datasize] = '\0';  /* terminate last string */
 
 	const char **args = unpackcmdargsnul(ctx);
 	if (!args[0] || !args[1])
 		abortmsg("missing command or cwd in system request");
 	debugmsg("run '%s' at '%s'", args[0], args[1]);
 	int32_t r = runshellcmd(args[0], args + 2, args[1]);
 	free(args);
 
 	uint32_t r_n = htonl(r);
 	memcpy(ctx->data, &r_n, sizeof(r_n));
 	ctx->datasize = sizeof(r_n);
 	writeblock(hgc);
 }
 
 /* Read response of command execution until receiving 'r'-esult */
 static void handleresponse(hgclient_t *hgc)
 {
 	for (;;) {
 		readchannel(hgc);
 		context_t *ctx = &hgc->ctx;
 		debugmsg("response read from channel %c, size %zu",
 			 ctx->ch, ctx->datasize);
 		switch (ctx->ch) {
 		case 'o':
 			fwrite(ctx->data, sizeof(ctx->data[0]), ctx->datasize,
 			       stdout);
 			break;
 		case 'e':
 			fwrite(ctx->data, sizeof(ctx->data[0]), ctx->datasize,
 			       stderr);
 			break;
 		case 'd':
 			/* assumes last char is '\n' */
 			ctx->data[ctx->datasize - 1] = '\0';
 			debugmsg("server: %s", ctx->data);
 			break;
 		case 'r':
 			return;
 		case 'I':
 			handlereadrequest(hgc);
 			break;
 		case 'L':
 			handlereadlinerequest(hgc);
 			break;
 		case 'S':
 			handlesystemrequest(hgc);
 			break;
 		default:
 			if (isupper(ctx->ch))
 				abortmsg("cannot handle response (ch = %c)",
 					 ctx->ch);
 		}
 	}
 }
 
 static unsigned int parsecapabilities(const char *s, const char *e)
 {
 	unsigned int flags = 0;
 	while (s < e) {
 		const char *t = strchr(s, ' ');
 		if (!t || t > e)
 			t = e;
 		const cappair_t *cap;
 		for (cap = captable; cap->flag; ++cap) {
 			size_t n = t - s;
 			if (strncmp(s, cap->name, n) == 0 &&
 			    strlen(cap->name) == n) {
 				flags |= cap->flag;
 				break;
 			}
 		}
 		s = t + 1;
 	}
 	return flags;
 }
 
 static void readhello(hgclient_t *hgc)
 {
 	readchannel(hgc);
 	context_t *ctx = &hgc->ctx;
 	if (ctx->ch != 'o') {
 		char ch = ctx->ch;
 		if (ch == 'e') {
 			/* write early error and will exit */
 			fwrite(ctx->data, sizeof(ctx->data[0]), ctx->datasize,
 			       stderr);
 			handleresponse(hgc);
 		}
 		abortmsg("unexpected channel of hello message (ch = %c)", ch);
 	}
 	enlargecontext(ctx, ctx->datasize + 1);
 	ctx->data[ctx->datasize] = '\0';
 	debugmsg("hello received: %s (size = %zu)", ctx->data, ctx->datasize);
 
 	const char *s = ctx->data;
 	const char *const dataend = ctx->data + ctx->datasize;
 	while (s < dataend) {
 		const char *t = strchr(s, ':');
 		if (!t || t[1] != ' ')
 			break;
 		const char *u = strchr(t + 2, '\n');
 		if (!u)
 			u = dataend;
 		if (strncmp(s, "capabilities:", t - s + 1) == 0) {
 			hgc->capflags = parsecapabilities(t + 2, u);
 		} else if (strncmp(s, "pgid:", t - s + 1) == 0) {
 			hgc->pgid = strtol(t + 2, NULL, 10);
 		} else if (strncmp(s, "pid:", t - s + 1) == 0) {
 			hgc->pid = strtol(t + 2, NULL, 10);
 		}
 		s = u + 1;
 	}
 	debugmsg("capflags=0x%04x, pid=%d", hgc->capflags, hgc->pid);
 }
 
 static void attachio(hgclient_t *hgc)
 {
 	debugmsg("request attachio");
 	static const char chcmd[] = "attachio\n";
 	sendall(hgc->sockfd, chcmd, sizeof(chcmd) - 1);
 	readchannel(hgc);
 	context_t *ctx = &hgc->ctx;
 	if (ctx->ch != 'I')
 		abortmsg("unexpected response for attachio (ch = %c)", ctx->ch);
 
 	static const int fds[3] = {STDIN_FILENO, STDOUT_FILENO, STDERR_FILENO};
 	struct msghdr msgh;
 	memset(&msgh, 0, sizeof(msgh));
 	struct iovec iov = {ctx->data, ctx->datasize};  /* dummy payload */
 	msgh.msg_iov = &iov;
 	msgh.msg_iovlen = 1;
 	char fdbuf[CMSG_SPACE(sizeof(fds))];
 	msgh.msg_control = fdbuf;
 	msgh.msg_controllen = sizeof(fdbuf);
 	struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msgh);
 	cmsg->cmsg_level = SOL_SOCKET;
 	cmsg->cmsg_type = SCM_RIGHTS;
 	cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
 	memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
 	msgh.msg_controllen = cmsg->cmsg_len;
 	ssize_t r = sendmsg(hgc->sockfd, &msgh, 0);
 	if (r < 0)
 		abortmsgerrno("sendmsg failed");
 
 	handleresponse(hgc);
 	int32_t n;
 	if (ctx->datasize != sizeof(n))
 		abortmsg("unexpected size of attachio result");
 	memcpy(&n, ctx->data, sizeof(n));
 	n = ntohl(n);
 	if (n != sizeof(fds) / sizeof(fds[0]))
 		abortmsg("failed to send fds (n = %d)", n);
 }
 
 static void chdirtocwd(hgclient_t *hgc)
 {
 	if (!getcwd(hgc->ctx.data, hgc->ctx.maxdatasize))
 		abortmsgerrno("failed to getcwd");
 	hgc->ctx.datasize = strlen(hgc->ctx.data);
 	writeblockrequest(hgc, "chdir");
 }
 
 static void forwardumask(hgclient_t *hgc)
 {
 	mode_t mask = umask(0);
 	umask(mask);
 
 	static const char command[] = "setumask\n";
 	sendall(hgc->sockfd, command, sizeof(command) - 1);
 	uint32_t data = htonl(mask);
 	sendall(hgc->sockfd, &data, sizeof(data));
 }
 
 /*!
  * Open connection to per-user cmdserver
  *
  * If no background server running, returns NULL.
  */
 hgclient_t *hgc_open(const char *sockname)
 {
 	int fd = socket(AF_UNIX, SOCK_STREAM, 0);
 	if (fd < 0)
 		abortmsgerrno("cannot create socket");
 
 	/* don't keep fd on fork(), so that it can be closed when the parent
 	 * process get terminated. */
 	fsetcloexec(fd);
 
 	struct sockaddr_un addr;
 	addr.sun_family = AF_UNIX;
 	strncpy(addr.sun_path, sockname, sizeof(addr.sun_path));
 	addr.sun_path[sizeof(addr.sun_path) - 1] = '\0';
 
 	int r = connect(fd, (struct sockaddr *)&addr, sizeof(addr));
 	if (r < 0) {
 		close(fd);
 		if (errno == ENOENT || errno == ECONNREFUSED)
 			return NULL;
 		abortmsgerrno("cannot connect to %s", addr.sun_path);
 	}
 	debugmsg("connected to %s", addr.sun_path);
 
 	hgclient_t *hgc = mallocx(sizeof(hgclient_t));
 	memset(hgc, 0, sizeof(*hgc));
 	hgc->sockfd = fd;
 	initcontext(&hgc->ctx);
 
 	readhello(hgc);
 	if (!(hgc->capflags & CAP_RUNCOMMAND))
 		abortmsg("insufficient capability: runcommand");
 	if (hgc->capflags & CAP_ATTACHIO)
 		attachio(hgc);
 	if (hgc->capflags & CAP_CHDIR)
 		chdirtocwd(hgc);
 	if (hgc->capflags & CAP_SETUMASK)
 		forwardumask(hgc);
 
 	return hgc;
 }
 
 /*!
  * Close connection and free allocated memory
  */
 void hgc_close(hgclient_t *hgc)
 {
 	assert(hgc);
 	freecontext(&hgc->ctx);
 	close(hgc->sockfd);
 	free(hgc);
 }
 
 pid_t hgc_peerpgid(const hgclient_t *hgc)
 {
 	assert(hgc);
 	return hgc->pgid;
 }
 
 pid_t hgc_peerpid(const hgclient_t *hgc)
 {
 	assert(hgc);
 	return hgc->pid;
 }
 
 /*!
  * Send command line arguments to let the server load the repo config and check
  * whether it can process our request directly or not.
  * Make sure hgc_setenv is called before calling this.
  *
  * @return - NULL, the server believes it can handle our request, or does not
  *           support "validate" command.
  *         - a list of strings, the server probably cannot handle our request
  *           and it sent instructions telling us what to do next. See
  *           chgserver.py for possible instruction formats.
  *           the list should be freed by the caller.
  *           the last string is guaranteed to be NULL.
  */
 const char **hgc_validate(hgclient_t *hgc, const char *const args[],
 			  size_t argsize)
 {
 	assert(hgc);
 	if (!(hgc->capflags & CAP_VALIDATE))
 		return NULL;
 
 	packcmdargs(&hgc->ctx, args, argsize);
 	writeblockrequest(hgc, "validate");
 	handleresponse(hgc);
 
 	/* the server returns '\0' if it can handle our request */
 	if (hgc->ctx.datasize <= 1)
 		return NULL;
 
 	/* make sure the buffer is '\0' terminated */
 	enlargecontext(&hgc->ctx, hgc->ctx.datasize + 1);
 	hgc->ctx.data[hgc->ctx.datasize] = '\0';
 	return unpackcmdargsnul(&hgc->ctx);
 }
 
 /*!
  * Execute the specified Mercurial command
  *
  * @return result code
  */
 int hgc_runcommand(hgclient_t *hgc, const char *const args[], size_t argsize)
 {
 	assert(hgc);
 
 	packcmdargs(&hgc->ctx, args, argsize);
 	writeblockrequest(hgc, "runcommand");
 	handleresponse(hgc);
 
 	int32_t exitcode_n;
 	if (hgc->ctx.datasize != sizeof(exitcode_n)) {
 		abortmsg("unexpected size of exitcode");
 	}
 	memcpy(&exitcode_n, hgc->ctx.data, sizeof(exitcode_n));
 	return ntohl(exitcode_n);
 }
 
 /*!
  * (Re-)send client's stdio channels so that the server can access to tty
  */
 void hgc_attachio(hgclient_t *hgc)
 {
 	assert(hgc);
 	if (!(hgc->capflags & CAP_ATTACHIO))
 		return;
 	attachio(hgc);
 }
 
 /*!
  * Get pager command for the given Mercurial command args
  *
  * If no pager enabled, returns NULL. The return value becomes invalid
  * once you run another request to hgc.
  */
 const char *hgc_getpager(hgclient_t *hgc, const char *const args[],
 			 size_t argsize)
 {
 	assert(hgc);
 
 	if (!(hgc->capflags & CAP_GETPAGER))
 		return NULL;
 
 	packcmdargs(&hgc->ctx, args, argsize);
 	writeblockrequest(hgc, "getpager");
 	handleresponse(hgc);
 
 	if (hgc->ctx.datasize < 1 || hgc->ctx.data[0] == '\0')
 		return NULL;
 	enlargecontext(&hgc->ctx, hgc->ctx.datasize + 1);
 	hgc->ctx.data[hgc->ctx.datasize] = '\0';
 	return hgc->ctx.data;
 }
 
 /*!
  * Update server's environment variables
  *
  * @param envp  list of environment variables in "NAME=VALUE" format,
  *              terminated by NULL.
  */
 void hgc_setenv(hgclient_t *hgc, const char *const envp[])
 {
 	assert(hgc && envp);
 	if (!(hgc->capflags & CAP_SETENV))
 		return;
 	packcmdargs(&hgc->ctx, envp, /*argsize*/ -1);
 	writeblockrequest(hgc, "setenv");
 }

contrib/perf.py

@@ -1,902 +1,1103 b''
 # perf.py - performance test routines
 '''helper extension to measure performance'''
 
 # "historical portability" policy of perf.py:
 #
 # We have to do:
 # - make perf.py "loadable" with as wide Mercurial version as possible
 #   This doesn't mean that perf commands work correctly with that Mercurial.
 #   BTW, perf.py itself has been available since 1.1 (or eb240755386d).
 # - make historical perf command work correctly with as wide Mercurial
 #   version as possible
 #
 # We have to do, if possible with reasonable cost:
 # - make recent perf command for historical feature work correctly
 #   with early Mercurial
 #
 # We don't have to do:
 # - make perf command for recent feature work correctly with early
 #   Mercurial
 
 from __future__ import absolute_import
 import functools
 import os
 import random
 import sys
 import time
 from mercurial import (
+    changegroup,
     cmdutil,
     commands,
     copies,
     error,
     extensions,
     mdiff,
     merge,
     revlog,
     util,
 )
 
 # for "historical portability":
 # try to import modules separately (in dict order), and ignore
 # failure, because these aren't available with early Mercurial
 try:
     from mercurial import branchmap # since 2.5 (or bcee63733aad)
 except ImportError:
     pass
 try:
     from mercurial import obsolete # since 2.3 (or ad0d6c2b3279)
 except ImportError:
     pass
 try:
     from mercurial import repoview # since 2.5 (or 3a6ddacb7198)
 except ImportError:
     pass
 try:
     from mercurial import scmutil # since 1.9 (or 8b252e826c68)
 except ImportError:
     pass
 
 # for "historical portability":
 # define util.safehasattr forcibly, because util.safehasattr has been
 # available since 1.9.3 (or 94b200a11cf7)
 _undefined = object()
 def safehasattr(thing, attr):
     return getattr(thing, attr, _undefined) is not _undefined
 setattr(util, 'safehasattr', safehasattr)
 
 # for "historical portability":
 # use locally defined empty option list, if formatteropts isn't
 # available, because commands.formatteropts has been available since
 # 3.2 (or 7a7eed5176a4), even though formatting itself has been
 # available since 2.2 (or ae5f92e154d3)
 formatteropts = getattr(commands, "formatteropts", [])
 
 # for "historical portability":
 # use locally defined option list, if debugrevlogopts isn't available,
 # because commands.debugrevlogopts has been available since 3.7 (or
 # 5606f7d0d063), even though cmdutil.openrevlog() has been available
 # since 1.9 (or a79fea6b3e77).
 revlogopts = getattr(commands, "debugrevlogopts", [
         ('c', 'changelog', False, ('open changelog')),
         ('m', 'manifest', False, ('open manifest')),
         ('', 'dir', False, ('open directory manifest')),
         ])
 
 cmdtable = {}
 
 # for "historical portability":
 # define parsealiases locally, because cmdutil.parsealiases has been
 # available since 1.5 (or 6252852b4332)
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 if safehasattr(cmdutil, 'command'):
     import inspect
     command = cmdutil.command(cmdtable)
     if 'norepo' not in inspect.getargspec(command)[0]:
         # for "historical portability":
         # wrap original cmdutil.command, because "norepo" option has
         # been available since 3.1 (or 75a96326cecb)
         _command = command
         def command(name, options=(), synopsis=None, norepo=False):
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return _command(name, list(options), synopsis)
 else:
     # for "historical portability":
     # define "@command" annotation locally, because cmdutil.command
     # has been available since 1.9 (or 2daa5179e73f)
     def command(name, options=(), synopsis=None, norepo=False):
         def decorator(func):
             if synopsis:
                 cmdtable[name] = func, list(options), synopsis
             else:
                 cmdtable[name] = func, list(options)
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return func
         return decorator
 
 def getlen(ui):
     if ui.configbool("perf", "stub"):
         return lambda x: 1
     return len
 
 def gettimer(ui, opts=None):
     """return a timer function and formatter: (timer, formatter)
 
     This function exists to gather the creation of formatter in a single
     place instead of duplicating it in all performance commands."""
 
     # enforce an idle period before execution to counteract power management
     # experimental config: perf.presleep
-    time.sleep(ui.configint("perf", "presleep", 1))
+    time.sleep(getint(ui, "perf", "presleep", 1))
 
     if opts is None:
         opts = {}
     # redirect all to stderr
     ui = ui.copy()
-    ui.fout = ui.ferr
+    uifout = safeattrsetter(ui, 'fout', ignoremissing=True)
+    if uifout:
+        # for "historical portability":
+        # ui.fout/ferr have been available since 1.9 (or 4e1ccd4c2b6d)
+        uifout.set(ui.ferr)
+
     # get a formatter
-    fm = ui.formatter('perf', opts)
+    uiformatter = getattr(ui, 'formatter', None)
+    if uiformatter:
+        fm = uiformatter('perf', opts)
+    else:
+        # for "historical portability":
+        # define formatter locally, because ui.formatter has been
+        # available since 2.2 (or ae5f92e154d3)
+        from mercurial import node
+        class defaultformatter(object):
+            """Minimized composition of baseformatter and plainformatter
+            """
+            def __init__(self, ui, topic, opts):
+                self._ui = ui
+                if ui.debugflag:
+                    self.hexfunc = node.hex
+                else:
+                    self.hexfunc = node.short
+            def __nonzero__(self):
+                return False
+            def startitem(self):
+                pass
+            def data(self, **data):
+                pass
+            def write(self, fields, deftext, *fielddata, **opts):
+                self._ui.write(deftext % fielddata, **opts)
+            def condwrite(self, cond, fields, deftext, *fielddata, **opts):
+                if cond:
+                    self._ui.write(deftext % fielddata, **opts)
+            def plain(self, text, **opts):
+                self._ui.write(text, **opts)
+            def end(self):
+                pass
+        fm = defaultformatter(ui, 'perf', opts)
+
     # stub function, runs code only once instead of in a loop
     # experimental config: perf.stub
     if ui.configbool("perf", "stub"):
         return functools.partial(stub_timer, fm), fm
     return functools.partial(_timer, fm), fm
 
 def stub_timer(fm, func, title=None):
     func()
 
 def _timer(fm, func, title=None):
     results = []
     begin = time.time()
     count = 0
     while True:
         ostart = os.times()
         cstart = time.time()
         r = func()
         cstop = time.time()
         ostop = os.times()
         count += 1
         a, b = ostart, ostop
         results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
         if cstop - begin > 3 and count >= 100:
             break
         if cstop - begin > 10 and count >= 3:
             break
 
     fm.startitem()
 
     if title:
         fm.write('title', '! %s\n', title)
     if r:
         fm.write('result', '! result: %s\n', r)
     m = min(results)
     fm.plain('!')
     fm.write('wall', ' wall %f', m[0])
     fm.write('comb', ' comb %f', m[1] + m[2])
     fm.write('user', ' user %f', m[1])
     fm.write('sys',  ' sys %f', m[2])
     fm.write('count',  ' (best of %d)', count)
     fm.plain('\n')
 
+# utilities for historical portability
+
+def getint(ui, section, name, default):
+    # for "historical portability":
+    # ui.configint has been available since 1.9 (or fa2b596db182)
+    v = ui.config(section, name, None)
+    if v is None:
+        return default
+    try:
+        return int(v)
+    except ValueError:
+        raise error.ConfigError(("%s.%s is not an integer ('%s')")
+                                % (section, name, v))
+
+def safeattrsetter(obj, name, ignoremissing=False):
+    """Ensure that 'obj' has 'name' attribute before subsequent setattr
+
+    This function is aborted, if 'obj' doesn't have 'name' attribute
+    at runtime. This avoids overlooking removal of an attribute, which
+    breaks assumption of performance measurement, in the future.
+
+    This function returns the object to (1) assign a new value, and
+    (2) restore an original value to the attribute.
+
+    If 'ignoremissing' is true, missing 'name' attribute doesn't cause
+    abortion, and this function returns None. This is useful to
+    examine an attribute, which isn't ensured in all Mercurial
+    versions.
+    """
+    if not util.safehasattr(obj, name):
+        if ignoremissing:
+            return None
+        raise error.Abort(("missing attribute %s of %s might break assumption"
+                           " of performance measurement") % (name, obj))
+
+    origvalue = getattr(obj, name)
+    class attrutil(object):
+        def set(self, newvalue):
+            setattr(obj, name, newvalue)
+        def restore(self):
+            setattr(obj, name, origvalue)
+
+    return attrutil()
+
+# utilities to examine each internal API changes
+
+def getbranchmapsubsettable():
+    # for "historical portability":
+    # subsettable is defined in:
+    # - branchmap since 2.9 (or 175c6fd8cacc)
+    # - repoview since 2.5 (or 59a9f18d4587)
+    for mod in (branchmap, repoview):
+        subsettable = getattr(mod, 'subsettable', None)
+        if subsettable:
+            return subsettable
+
+    # bisecting in bcee63733aad::59a9f18d4587 can reach here (both
+    # branchmap and repoview modules exist, but subsettable attribute
+    # doesn't)
+    raise error.Abort(("perfbranchmap not available with this Mercurial"),
+                      hint="use 2.5 or later")
+
+def getsvfs(repo):
+    """Return appropriate object to access files under .hg/store
+    """
+    # for "historical portability":
+    # repo.svfs has been available since 2.3 (or 7034365089bf)
+    svfs = getattr(repo, 'svfs', None)
+    if svfs:
+        return svfs
+    else:
+        return getattr(repo, 'sopener')
+
+def getvfs(repo):
+    """Return appropriate object to access files under .hg
+    """
+    # for "historical portability":
+    # repo.vfs has been available since 2.3 (or 7034365089bf)
+    vfs = getattr(repo, 'vfs', None)
+    if vfs:
+        return vfs
+    else:
+        return getattr(repo, 'opener')
+
+def repocleartagscachefunc(repo):
+    """Return the function to clear tags cache according to repo internal API
+    """
+    if util.safehasattr(repo, '_tagscache'): # since 2.0 (or 9dca7653b525)
+        # in this case, setattr(repo, '_tagscache', None) or so isn't
+        # correct way to clear tags cache, because existing code paths
+        # expect _tagscache to be a structured object.
+        def clearcache():
+            # _tagscache has been filteredpropertycache since 2.5 (or
+            # 98c867ac1330), and delattr() can't work in such case
+            if '_tagscache' in vars(repo):
+                del repo.__dict__['_tagscache']
+        return clearcache
+
+    repotags = safeattrsetter(repo, '_tags', ignoremissing=True)
+    if repotags: # since 1.4 (or 5614a628d173)
+        return lambda : repotags.set(None)
+
+    repotagscache = safeattrsetter(repo, 'tagscache', ignoremissing=True)
+    if repotagscache: # since 0.6 (or d7df759d0e97)
+        return lambda : repotagscache.set(None)
+
+    # Mercurial earlier than 0.6 (or d7df759d0e97) logically reaches
+    # this point, but it isn't so problematic, because:
+    # - repo.tags of such Mercurial isn't "callable", and repo.tags()
+    #   in perftags() causes failure soon
+    # - perf.py itself has been available since 1.1 (or eb240755386d)
+    raise error.Abort(("tags API of this hg command is unknown"))
+
+# perf commands
+
 @command('perfwalk', formatteropts)
 def perfwalk(ui, repo, *pats, **opts):
     timer, fm = gettimer(ui, opts)
     try:
         m = scmutil.match(repo[None], pats, {})
         timer(lambda: len(list(repo.dirstate.walk(m, [], True, False))))
     except Exception:
         try:
             m = scmutil.match(repo[None], pats, {})
             timer(lambda: len([b for a, b, c in repo.dirstate.statwalk([], m)]))
         except Exception:
             timer(lambda: len(list(cmdutil.walk(repo, pats, {}))))
     fm.end()
 
 @command('perfannotate', formatteropts)
 def perfannotate(ui, repo, f, **opts):
     timer, fm = gettimer(ui, opts)
     fc = repo['.'][f]
     timer(lambda: len(fc.annotate(True)))
     fm.end()
 
 @command('perfstatus',
          [('u', 'unknown', False,
            'ask status to look for unknown files')] + formatteropts)
 def perfstatus(ui, repo, **opts):
     #m = match.always(repo.root, repo.getcwd())
     #timer(lambda: sum(map(len, repo.dirstate.status(m, [], False, False,
     #                                                False))))
     timer, fm = gettimer(ui, opts)
     timer(lambda: sum(map(len, repo.status(unknown=opts['unknown']))))
     fm.end()
 
 @command('perfaddremove', formatteropts)
 def perfaddremove(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     try:
         oldquiet = repo.ui.quiet
         repo.ui.quiet = True
         matcher = scmutil.match(repo[None])
         timer(lambda: scmutil.addremove(repo, matcher, "", dry_run=True))
     finally:
         repo.ui.quiet = oldquiet
         fm.end()
 
 def clearcaches(cl):
     # behave somewhat consistently across internal API changes
     if util.safehasattr(cl, 'clearcaches'):
         cl.clearcaches()
     elif util.safehasattr(cl, '_nodecache'):
         from mercurial.node import nullid, nullrev
         cl._nodecache = {nullid: nullrev}
         cl._nodepos = None
 
 @command('perfheads', formatteropts)
 def perfheads(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.headrevs())
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perftags', formatteropts)
 def perftags(ui, repo, **opts):
     import mercurial.changelog
     import mercurial.manifest
     timer, fm = gettimer(ui, opts)
+    svfs = getsvfs(repo)
+    repocleartagscache = repocleartagscachefunc(repo)
     def t():
-        repo.changelog = mercurial.changelog.changelog(repo.svfs)
-        repo.manifest = mercurial.manifest.manifest(repo.svfs)
-        repo._tags = None
+        repo.changelog = mercurial.changelog.changelog(svfs)
+        repo.manifest = mercurial.manifest.manifest(svfs)
+        repocleartagscache()
         return len(repo.tags())
     timer(t)
     fm.end()
 
 @command('perfancestors', formatteropts)
 def perfancestors(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     heads = repo.changelog.headrevs()
     def d():
         for a in repo.changelog.ancestors(heads):
             pass
     timer(d)
     fm.end()
 
 @command('perfancestorset', formatteropts)
 def perfancestorset(ui, repo, revset, **opts):
     timer, fm = gettimer(ui, opts)
     revs = repo.revs(revset)
     heads = repo.changelog.headrevs()
     def d():
         s = repo.changelog.ancestors(heads)
         for rev in revs:
             rev in s
     timer(d)
     fm.end()
 
+@command('perfchangegroupchangelog', formatteropts +
+         [('', 'version', '02', 'changegroup version'),
+          ('r', 'rev', '', 'revisions to add to changegroup')])
+def perfchangegroupchangelog(ui, repo, version='02', rev=None, **opts):
+    """Benchmark producing a changelog group for a changegroup.
+
+    This measures the time spent processing the changelog during a
+    bundle operation. This occurs during `hg bundle` and on a server
+    processing a `getbundle` wire protocol request (handles clones
+    and pull requests).
+
+    By default, all revisions are added to the changegroup.
+    """
+    cl = repo.changelog
+    revs = [cl.lookup(r) for r in repo.revs(rev or 'all()')]
+    bundler = changegroup.getbundler(version, repo)
+
+    def lookup(node):
+        # The real bundler reads the revision in order to access the
+        # manifest node and files list. Do that here.
+        cl.read(node)
+        return node
+
+    def d():
+        for chunk in bundler.group(revs, cl, lookup):
+            pass
+
+    timer, fm = gettimer(ui, opts)
+    timer(d)
+    fm.end()
+
 @command('perfdirs', formatteropts)
 def perfdirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate.dirs()
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstate', formatteropts)
 def perfdirstate(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         repo.dirstate.invalidate()
         "a" in repo.dirstate
     timer(d)
     fm.end()
 
 @command('perfdirstatedirs', formatteropts)
 def perfdirstatedirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         "a" in repo.dirstate._dirs
         del repo.dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatefoldmap', formatteropts)
 def perfdirstatefoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._filefoldmap.get('a')
         del dirstate._filefoldmap
     timer(d)
     fm.end()
 
 @command('perfdirfoldmap', formatteropts)
 def perfdirfoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._dirfoldmap.get('a')
         del dirstate._dirfoldmap
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatewrite', formatteropts)
 def perfdirstatewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     ds = repo.dirstate
     "a" in ds
     def d():
         ds._dirty = True
         ds.write(repo.currenttransaction())
     timer(d)
     fm.end()
 
 @command('perfmergecalculate',
          [('r', 'rev', '.', 'rev to merge against')] + formatteropts)
 def perfmergecalculate(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     wctx = repo[None]
     rctx = scmutil.revsingle(repo, rev, rev)
     ancestor = wctx.ancestor(rctx)
     # we don't want working dir files to be stat'd in the benchmark, so prime
     # that cache
     wctx.dirty()
     def d():
         # acceptremote is True because we don't want prompts in the middle of
         # our benchmark
         merge.calculateupdates(repo, wctx, rctx, [ancestor], False, False,
                                acceptremote=True, followcopies=True)
     timer(d)
     fm.end()
 
 @command('perfpathcopies', [], "REV REV")
 def perfpathcopies(ui, repo, rev1, rev2, **opts):
     timer, fm = gettimer(ui, opts)
     ctx1 = scmutil.revsingle(repo, rev1, rev1)
     ctx2 = scmutil.revsingle(repo, rev2, rev2)
     def d():
         copies.pathcopies(ctx1, ctx2)
     timer(d)
     fm.end()
 
 @command('perfmanifest', [], 'REV')
 def perfmanifest(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     ctx = scmutil.revsingle(repo, rev, rev)
     t = ctx.manifestnode()
     def d():
         repo.manifest.clearcaches()
         repo.manifest.read(t)
     timer(d)
     fm.end()
 
 @command('perfchangeset', formatteropts)
 def perfchangeset(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     n = repo[rev].node()
     def d():
         repo.changelog.read(n)
         #repo.changelog._cache = None
     timer(d)
     fm.end()
 
 @command('perfindex', formatteropts)
 def perfindex(ui, repo, **opts):
     import mercurial.revlog
     timer, fm = gettimer(ui, opts)
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo["tip"].node()
+    svfs = getsvfs(repo)
     def d():
-        cl = mercurial.revlog.revlog(repo.svfs, "00changelog.i")
+        cl = mercurial.revlog.revlog(svfs, "00changelog.i")
         cl.rev(n)
     timer(d)
     fm.end()
 
 @command('perfstartup', formatteropts)
 def perfstartup(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cmd = sys.argv[0]
     def d():
         if os.name != 'nt':
             os.system("HGRCPATH= %s version -q > /dev/null" % cmd)
         else:
             os.environ['HGRCPATH'] = ''
             os.system("%s version -q > NUL" % cmd)
     timer(d)
     fm.end()
 
 @command('perfparents', formatteropts)
 def perfparents(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     # control the number of commits perfparents iterates over
     # experimental config: perf.parentscount
-    count = ui.configint("perf", "parentscount", 1000)
+    count = getint(ui, "perf", "parentscount", 1000)
     if len(repo.changelog) < count:
         raise error.Abort("repo needs %d commits for this test" % count)
     repo = repo.unfiltered()
     nl = [repo.changelog.node(i) for i in xrange(count)]
     def d():
         for n in nl:
             repo.changelog.parents(n)
     timer(d)
     fm.end()
 
 @command('perfctxfiles', formatteropts)
 def perfctxfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     def d():
         len(repo[x].files())
     timer(d)
     fm.end()
 
 @command('perfrawfiles', formatteropts)
 def perfrawfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.read(x)[3])
     timer(d)
     fm.end()
 
 @command('perflookup', formatteropts)
 def perflookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: len(repo.lookup(rev)))
     fm.end()
 
 @command('perfrevrange', formatteropts)
 def perfrevrange(ui, repo, *specs, **opts):
     timer, fm = gettimer(ui, opts)
     revrange = scmutil.revrange
     timer(lambda: len(revrange(repo, specs)))
     fm.end()
 
 @command('perfnodelookup', formatteropts)
 def perfnodelookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     import mercurial.revlog
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo[rev].node()
-    cl = mercurial.revlog.revlog(repo.svfs, "00changelog.i")
+    cl = mercurial.revlog.revlog(getsvfs(repo), "00changelog.i")
     def d():
         cl.rev(n)
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perflog',
          [('', 'rename', False, 'ask log to follow renames')] + formatteropts)
 def perflog(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                copies=opts.get('rename')))
     ui.popbuffer()
     fm.end()
 
 @command('perfmoonwalk', formatteropts)
 def perfmoonwalk(ui, repo, **opts):
     """benchmark walking the changelog backwards
 
     This also loads the changelog data for each revision in the changelog.
     """
     timer, fm = gettimer(ui, opts)
     def moonwalk():
         for i in xrange(len(repo), -1, -1):
             ctx = repo[i]
             ctx.branch() # read changelog data (in addition to the index)
     timer(moonwalk)
     fm.end()
 
 @command('perftemplating', formatteropts)
 def perftemplating(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                template='{date|shortdate} [{rev}:{node|short}]'
                                ' {author|person}: {desc|firstline}\n'))
     ui.popbuffer()
     fm.end()
 
 @command('perfcca', formatteropts)
 def perfcca(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: scmutil.casecollisionauditor(ui, False, repo.dirstate))
     fm.end()
 
 @command('perffncacheload', formatteropts)
 def perffncacheload(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     def d():
         s.fncache._load()
     timer(d)
     fm.end()
 
 @command('perffncachewrite', formatteropts)
 def perffncachewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     lock = repo.lock()
     tr = repo.transaction('perffncachewrite')
     def d():
         s.fncache._dirty = True
         s.fncache.write(tr)
     timer(d)
+    tr.close()
     lock.release()
-    tr.close()
     fm.end()
 
 @command('perffncacheencode', formatteropts)
 def perffncacheencode(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     def d():
         for p in s.fncache.entries:
             s.encode(p)
     timer(d)
     fm.end()
 
 @command('perfdiffwd', formatteropts)
 def perfdiffwd(ui, repo, **opts):
     """Profile diff of working directory changes"""
     timer, fm = gettimer(ui, opts)
     options = {
         'w': 'ignore_all_space',
         'b': 'ignore_space_change',
         'B': 'ignore_blank_lines',
         }
 
     for diffopt in ('', 'w', 'b', 'B', 'wB'):
         opts = dict((options[c], '1') for c in diffopt)
         def d():
             ui.pushbuffer()
             commands.diff(ui, repo, **opts)
             ui.popbuffer()
         title = 'diffopts: %s' % (diffopt and ('-' + diffopt) or 'none')
         timer(d, title)
     fm.end()
 
 @command('perfrevlog', revlogopts + formatteropts +
          [('d', 'dist', 100, 'distance between the revisions'),
-          ('s', 'startrev', 0, 'revision to start reading at')],
+          ('s', 'startrev', 0, 'revision to start reading at'),
+          ('', 'reverse', False, 'read in reverse')],
          '-c|-m|FILE')
-def perfrevlog(ui, repo, file_=None, startrev=0, **opts):
+def perfrevlog(ui, repo, file_=None, startrev=0, reverse=False, **opts):
     """Benchmark reading a series of revisions from a revlog.
 
     By default, we read every ``-d/--dist`` revision from 0 to tip of
     the specified revlog.
 
     The start revision can be defined via ``-s/--startrev``.
     """
     timer, fm = gettimer(ui, opts)
-    dist = opts['dist']
     _len = getlen(ui)
+
     def d():
         r = cmdutil.openrevlog(repo, 'perfrevlog', file_, opts)
-        for x in xrange(startrev, _len(r), dist):
+
+        startrev = 0
+        endrev = _len(r)
+        dist = opts['dist']
+
+        if reverse:
+            startrev, endrev = endrev, startrev
+            dist = -1 * dist
+
+        for x in xrange(startrev, endrev, dist):
             r.revision(r.node(x))
 
     timer(d)
     fm.end()
 
 @command('perfrevlogrevision', revlogopts + formatteropts +
          [('', 'cache', False, 'use caches instead of clearing')],
          '-c|-m|FILE REV')
 def perfrevlogrevision(ui, repo, file_, rev=None, cache=None, **opts):
     """Benchmark obtaining a revlog revision.
 
     Obtaining a revlog revision consists of roughly the following steps:
 
     1. Compute the delta chain
     2. Obtain the raw chunks for that delta chain
     3. Decompress each raw chunk
     4. Apply binary patches to obtain fulltext
     5. Verify hash of fulltext
 
     This command measures the time spent in each of these phases.
     """
     if opts.get('changelog') or opts.get('manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('perfrevlogrevision', 'invalid arguments')
 
     r = cmdutil.openrevlog(repo, 'perfrevlogrevision', file_, opts)
     node = r.lookup(rev)
     rev = r.rev(node)
 
     def dodeltachain(rev):
         if not cache:
             r.clearcaches()
         r._deltachain(rev)
 
     def doread(chain):
         if not cache:
             r.clearcaches()
         r._chunkraw(chain[0], chain[-1])
 
     def dodecompress(data, chain):
         if not cache:
             r.clearcaches()
 
         start = r.start
         length = r.length
         inline = r._inline
         iosize = r._io.size
         buffer = util.buffer
         offset = start(chain[0])
 
         for rev in chain:
             chunkstart = start(rev)
             if inline:
                 chunkstart += (rev + 1) * iosize
             chunklength = length(rev)
             b = buffer(data, chunkstart - offset, chunklength)
             revlog.decompress(b)
 
     def dopatch(text, bins):
         if not cache:
             r.clearcaches()
         mdiff.patches(text, bins)
 
     def dohash(text):
         if not cache:
             r.clearcaches()
         r._checkhash(text, node, rev)
 
     def dorevision():
         if not cache:
             r.clearcaches()
         r.revision(node)
 
     chain = r._deltachain(rev)[0]
     data = r._chunkraw(chain[0], chain[-1])[1]
     bins = r._chunks(chain)
     text = str(bins[0])
     bins = bins[1:]
     text = mdiff.patches(text, bins)
 
     benches = [
         (lambda: dorevision(), 'full'),
         (lambda: dodeltachain(rev), 'deltachain'),
         (lambda: doread(chain), 'read'),
         (lambda: dodecompress(data, chain), 'decompress'),
         (lambda: dopatch(text, bins), 'patch'),
         (lambda: dohash(text), 'hash'),
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevset',
          [('C', 'clear', False, 'clear volatile cache between each call.'),
           ('', 'contexts', False, 'obtain changectx for each revision')]
          + formatteropts, "REVSET")
 def perfrevset(ui, repo, expr, clear=False, contexts=False, **opts):
     """benchmark the execution time of a revset
 
     Use the --clean option if need to evaluate the impact of build volatile
     revisions set cache on the revset execution. Volatile cache hold filtered
     and obsolete related cache."""
     timer, fm = gettimer(ui, opts)
     def d():
         if clear:
             repo.invalidatevolatilesets()
         if contexts:
             for ctx in repo.set(expr): pass
         else:
             for r in repo.revs(expr): pass
     timer(d)
     fm.end()
 
 @command('perfvolatilesets', formatteropts)
 def perfvolatilesets(ui, repo, *names, **opts):
     """benchmark the computation of various volatile set
 
     Volatile set computes element related to filtering and obsolescence."""
     timer, fm = gettimer(ui, opts)
     repo = repo.unfiltered()
 
     def getobs(name):
         def d():
             repo.invalidatevolatilesets()
             obsolete.getrevs(repo, name)
         return d
 
     allobs = sorted(obsolete.cachefuncs)
     if names:
         allobs = [n for n in allobs if n in names]
 
     for name in allobs:
         timer(getobs(name), title=name)
 
     def getfiltered(name):
         def d():
             repo.invalidatevolatilesets()
             repoview.filterrevs(repo, name)
         return d
 
     allfilter = sorted(repoview.filtertable)
     if names:
         allfilter = [n for n in allfilter if n in names]
 
     for name in allfilter:
         timer(getfiltered(name), title=name)
     fm.end()
 
 @command('perfbranchmap',
          [('f', 'full', False,
            'Includes build time of subset'),
          ] + formatteropts)
 def perfbranchmap(ui, repo, full=False, **opts):
     """benchmark the update of a branchmap
 
     This benchmarks the full repo.branchmap() call with read and write disabled
     """
     timer, fm = gettimer(ui, opts)
     def getbranchmap(filtername):
         """generate a benchmark function for the filtername"""
         if filtername is None:
             view = repo
         else:
             view = repo.filtered(filtername)
         def d():
             if full:
                 view._branchcaches.clear()
             else:
                 view._branchcaches.pop(filtername, None)
             view.branchmap()
         return d
     # add filter in smaller subset to bigger subset
     possiblefilters = set(repoview.filtertable)
+    subsettable = getbranchmapsubsettable()
     allfilters = []
     while possiblefilters:
         for name in possiblefilters:
-            subset = branchmap.subsettable.get(name)
+            subset = subsettable.get(name)
             if subset not in possiblefilters:
                 break
         else:
             assert False, 'subset cycle %s!' % possiblefilters
         allfilters.append(name)
         possiblefilters.remove(name)
 
     # warm the cache
     if not full:
         for name in allfilters:
             repo.filtered(name).branchmap()
     # add unfiltered
     allfilters.append(None)
-    oldread = branchmap.read
-    oldwrite = branchmap.branchcache.write
+
+    branchcacheread = safeattrsetter(branchmap, 'read')
+    branchcachewrite = safeattrsetter(branchmap.branchcache, 'write')
+    branchcacheread.set(lambda repo: None)
+    branchcachewrite.set(lambda bc, repo: None)
     try:
-        branchmap.read = lambda repo: None
-        branchmap.write = lambda repo: None
         for name in allfilters:
             timer(getbranchmap(name), title=str(name))
     finally:
-        branchmap.read = oldread
-        branchmap.branchcache.write = oldwrite
+        branchcacheread.restore()
+        branchcachewrite.restore()
     fm.end()
 
 @command('perfloadmarkers')
 def perfloadmarkers(ui, repo):
     """benchmark the time to parse the on-disk markers for a repo
 
     Result is the number of markers in the repo."""
     timer, fm = gettimer(ui)
-    timer(lambda: len(obsolete.obsstore(repo.svfs)))
+    svfs = getsvfs(repo)
+    timer(lambda: len(obsolete.obsstore(svfs)))
     fm.end()
 
 @command('perflrucachedict', formatteropts +
     [('', 'size', 4, 'size of cache'),
      ('', 'gets', 10000, 'number of key lookups'),
      ('', 'sets', 10000, 'number of key sets'),
      ('', 'mixed', 10000, 'number of mixed mode operations'),
      ('', 'mixedgetfreq', 50, 'frequency of get vs set ops in mixed mode')],
     norepo=True)
 def perflrucache(ui, size=4, gets=10000, sets=10000, mixed=10000,
                  mixedgetfreq=50, **opts):
     def doinit():
         for i in xrange(10000):
             util.lrucachedict(size)
 
     values = []
     for i in xrange(size):
         values.append(random.randint(0, sys.maxint))
 
     # Get mode fills the cache and tests raw lookup performance with no
     # eviction.
     getseq = []
     for i in xrange(gets):
         getseq.append(random.choice(values))
 
     def dogets():
         d = util.lrucachedict(size)
         for v in values:
             d[v] = v
         for key in getseq:
             value = d[key]
             value # silence pyflakes warning
 
     # Set mode tests insertion speed with cache eviction.
     setseq = []
     for i in xrange(sets):
         setseq.append(random.randint(0, sys.maxint))
 
     def dosets():
         d = util.lrucachedict(size)
         for v in setseq:
             d[v] = v
 
     # Mixed mode randomly performs gets and sets with eviction.
     mixedops = []
     for i in xrange(mixed):
         r = random.randint(0, 100)
         if r < mixedgetfreq:
             op = 0
         else:
             op = 1
 
         mixedops.append((op, random.randint(0, size * 2)))
 
     def domixed():
         d = util.lrucachedict(size)
 
         for op, v in mixedops:
             if op == 0:
                 try:
                     d[v]
                 except KeyError:
                     pass
             else:
                 d[v] = v
 
     benches = [
         (doinit, 'init'),
         (dogets, 'gets'),
         (dosets, 'sets'),
         (domixed, 'mixed')
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 def uisetup(ui):
     if (util.safehasattr(cmdutil, 'openrevlog') and
         not util.safehasattr(commands, 'debugrevlogopts')):
         # for "historical portability":
         # In this case, Mercurial should be 1.9 (or a79fea6b3e77) -
         # 3.7 (or 5606f7d0d063). Therefore, '--dir' option for
         # openrevlog() should cause failure, because it has been
         # available since 3.5 (or 49c583ca48c4).
         def openrevlog(orig, repo, cmd, file_, opts):
             if opts.get('dir') and not util.safehasattr(repo, 'dirlog'):
                 raise error.Abort("This version doesn't support --dir option",
                                   hint="use 3.5 or later")
             return orig(repo, cmd, file_, opts)
         extensions.wrapfunction(cmdutil, 'openrevlog', openrevlog)

contrib/synthrepo.py

@@ -1,516 +1,516 b''
 # synthrepo.py - repo synthesis
 #
 # Copyright 2012 Facebook
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''synthesize structurally interesting change history
 
 This extension is useful for creating a repository with properties
 that are statistically similar to an existing repository. During
 analysis, a simple probability table is constructed from the history
 of an existing repository.  During synthesis, these properties are
 reconstructed.
 
 Properties that are analyzed and synthesized include the following:
 
 - Lines added or removed when an existing file is modified
 - Number and sizes of files added
 - Number of files removed
 - Line lengths
 - Topological distance to parent changeset(s)
 - Probability of a commit being a merge
 - Probability of a newly added file being added to a new directory
 - Interarrival time, and time zone, of commits
 - Number of files in each directory
 
 A few obvious properties that are not currently handled realistically:
 
 - Merges are treated as regular commits with two parents, which is not
   realistic
 - Modifications are not treated as operations on hunks of lines, but
   as insertions and deletions of randomly chosen single lines
 - Committer ID (always random)
 - Executability of files
 - Symlinks and binary files are ignored
 '''
 
 from __future__ import absolute_import
 import bisect
 import collections
 import itertools
 import json
 import os
 import random
 import sys
 import time
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     nullrev,
     short,
 )
 from mercurial import (
     cmdutil,
     context,
     error,
     hg,
     patch,
     scmutil,
     util,
 )
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 newfile = set(('new fi', 'rename', 'copy f', 'copy t'))
 
 def zerodict():
     return collections.defaultdict(lambda: 0)
 
 def roundto(x, k):
     if x > k * 2:
         return int(round(x / float(k)) * k)
     return int(round(x))
 
 def parsegitdiff(lines):
     filename, mar, lineadd, lineremove = None, None, zerodict(), 0
     binary = False
     for line in lines:
         start = line[:6]
         if start == 'diff -':
             if filename:
                 yield filename, mar, lineadd, lineremove, binary
             mar, lineadd, lineremove, binary = 'm', zerodict(), 0, False
             filename = patch.gitre.match(line).group(1)
         elif start in newfile:
             mar = 'a'
         elif start == 'GIT bi':
             binary = True
         elif start == 'delete':
             mar = 'r'
         elif start:
             s = start[0]
             if s == '-' and not line.startswith('--- '):
                 lineremove += 1
             elif s == '+' and not line.startswith('+++ '):
                 lineadd[roundto(len(line) - 1, 5)] += 1
     if filename:
         yield filename, mar, lineadd, lineremove, binary
 
 @command('analyze',
          [('o', 'output', '', _('write output to given file'), _('FILE')),
           ('r', 'rev', [], _('analyze specified revisions'), _('REV'))],
          _('hg analyze'), optionalrepo=True)
 def analyze(ui, repo, *revs, **opts):
     '''create a simple model of a repository to use for later synthesis
 
     This command examines every changeset in the given range (or all
     of history if none are specified) and creates a simple statistical
     model of the history of the repository. It also measures the directory
     structure of the repository as checked out.
 
     The model is written out to a JSON file, and can be used by
     :hg:`synthesize` to create or augment a repository with synthetic
     commits that have a structure that is statistically similar to the
     analyzed repository.
     '''
     root = repo.root
     if not root.endswith(os.path.sep):
         root += os.path.sep
 
     revs = list(revs)
     revs.extend(opts['rev'])
     if not revs:
         revs = [':']
 
     output = opts['output']
     if not output:
         output = os.path.basename(root) + '.json'
 
     if output == '-':
         fp = sys.stdout
     else:
         fp = open(output, 'w')
 
     # Always obtain file counts of each directory in the given root directory.
     def onerror(e):
         ui.warn(_('error walking directory structure: %s\n') % e)
 
     dirs = {}
     rootprefixlen = len(root)
     for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):
         dirpathfromroot = dirpath[rootprefixlen:]
         dirs[dirpathfromroot] = len(filenames)
         if '.hg' in dirnames:
             dirnames.remove('.hg')
 
     lineschanged = zerodict()
     children = zerodict()
     p1distance = zerodict()
     p2distance = zerodict()
     linesinfilesadded = zerodict()
     fileschanged = zerodict()
     filesadded = zerodict()
     filesremoved = zerodict()
     linelengths = zerodict()
     interarrival = zerodict()
     parents = zerodict()
     dirsadded = zerodict()
     tzoffset = zerodict()
 
     # If a mercurial repo is available, also model the commit history.
     if repo:
         revs = scmutil.revrange(repo, revs)
         revs.sort()
 
         progress = ui.progress
         _analyzing = _('analyzing')
         _changesets = _('changesets')
         _total = len(revs)
 
         for i, rev in enumerate(revs):
             progress(_analyzing, i, unit=_changesets, total=_total)
             ctx = repo[rev]
             pl = ctx.parents()
             pctx = pl[0]
             prev = pctx.rev()
             children[prev] += 1
             p1distance[rev - prev] += 1
             parents[len(pl)] += 1
             tzoffset[ctx.date()[1]] += 1
             if len(pl) > 1:
                 p2distance[rev - pl[1].rev()] += 1
             if prev == rev - 1:
                 lastctx = pctx
             else:
                 lastctx = repo[rev - 1]
             if lastctx.rev() != nullrev:
                 timedelta = ctx.date()[0] - lastctx.date()[0]
                 interarrival[roundto(timedelta, 300)] += 1
             diff = sum((d.splitlines() for d in ctx.diff(pctx, git=True)), [])
             fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0
             for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):
                 if isbin:
                     continue
                 added = sum(lineadd.itervalues(), 0)
                 if mar == 'm':
                     if added and lineremove:
                         lineschanged[roundto(added, 5),
                                      roundto(lineremove, 5)] += 1
                         filechanges += 1
                 elif mar == 'a':
                     fileadds += 1
                     if '/' in filename:
                         filedir = filename.rsplit('/', 1)[0]
                         if filedir not in pctx.dirs():
                             diradds += 1
                     linesinfilesadded[roundto(added, 5)] += 1
                 elif mar == 'r':
                     fileremoves += 1
                 for length, count in lineadd.iteritems():
                     linelengths[length] += count
             fileschanged[filechanges] += 1
             filesadded[fileadds] += 1
             dirsadded[diradds] += 1
             filesremoved[fileremoves] += 1
 
     invchildren = zerodict()
 
     for rev, count in children.iteritems():
         invchildren[count] += 1
 
     if output != '-':
         ui.status(_('writing output to %s\n') % output)
 
     def pronk(d):
         return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)
 
     json.dump({'revs': len(revs),
                'initdirs': pronk(dirs),
                'lineschanged': pronk(lineschanged),
                'children': pronk(invchildren),
                'fileschanged': pronk(fileschanged),
                'filesadded': pronk(filesadded),
                'linesinfilesadded': pronk(linesinfilesadded),
                'dirsadded': pronk(dirsadded),
                'filesremoved': pronk(filesremoved),
                'linelengths': pronk(linelengths),
                'parents': pronk(parents),
                'p1distance': pronk(p1distance),
                'p2distance': pronk(p2distance),
                'interarrival': pronk(interarrival),
                'tzoffset': pronk(tzoffset),
                },
               fp)
     fp.close()
 
 @command('synthesize',
          [('c', 'count', 0, _('create given number of commits'), _('COUNT')),
           ('', 'dict', '', _('path to a dictionary of words'), _('FILE')),
           ('', 'initfiles', 0, _('initial file count to create'), _('COUNT'))],
          _('hg synthesize [OPTION].. DESCFILE'))
 def synthesize(ui, repo, descpath, **opts):
     '''synthesize commits based on a model of an existing repository
 
     The model must have been generated by :hg:`analyze`. Commits will
     be generated randomly according to the probabilities described in
     the model. If --initfiles is set, the repository will be seeded with
     the given number files following the modeled repository's directory
     structure.
 
     When synthesizing new content, commit descriptions, and user
     names, words will be chosen randomly from a dictionary that is
     presumed to contain one word per line. Use --dict to specify the
     path to an alternate dictionary to use.
     '''
     try:
         fp = hg.openpath(ui, descpath)
     except Exception as err:
         raise error.Abort('%s: %s' % (descpath, err[0].strerror))
     desc = json.load(fp)
     fp.close()
 
     def cdf(l):
         if not l:
             return [], []
         vals, probs = zip(*sorted(l, key=lambda x: x[1], reverse=True))
         t = float(sum(probs, 0))
         s, cdfs = 0, []
         for v in probs:
             s += v
             cdfs.append(s / t)
         return vals, cdfs
 
     lineschanged = cdf(desc['lineschanged'])
     fileschanged = cdf(desc['fileschanged'])
     filesadded = cdf(desc['filesadded'])
     dirsadded = cdf(desc['dirsadded'])
     filesremoved = cdf(desc['filesremoved'])
     linelengths = cdf(desc['linelengths'])
     parents = cdf(desc['parents'])
     p1distance = cdf(desc['p1distance'])
     p2distance = cdf(desc['p2distance'])
     interarrival = cdf(desc['interarrival'])
     linesinfilesadded = cdf(desc['linesinfilesadded'])
     tzoffset = cdf(desc['tzoffset'])
 
     dictfile = opts.get('dict') or '/usr/share/dict/words'
     try:
         fp = open(dictfile, 'rU')
     except IOError as err:
         raise error.Abort('%s: %s' % (dictfile, err.strerror))
     words = fp.read().splitlines()
     fp.close()
 
     initdirs = {}
     if desc['initdirs']:
         for k, v in desc['initdirs']:
             initdirs[k.encode('utf-8').replace('.hg', '_hg')] = v
         initdirs = renamedirs(initdirs, words)
     initdirscdf = cdf(initdirs)
 
     def pick(cdf):
         return cdf[0][bisect.bisect_left(cdf[1], random.random())]
 
     def pickpath():
         return os.path.join(pick(initdirscdf), random.choice(words))
 
     def makeline(minimum=0):
         total = max(minimum, pick(linelengths))
         c, l = 0, []
         while c < total:
             w = random.choice(words)
             c += len(w) + 1
             l.append(w)
         return ' '.join(l)
 
     wlock = repo.wlock()
     lock = repo.lock()
 
     nevertouch = set(('.hgsub', '.hgignore', '.hgtags'))
 
     progress = ui.progress
     _synthesizing = _('synthesizing')
     _files = _('initial files')
     _changesets = _('changesets')
 
     # Synthesize a single initial revision adding files to the repo according
     # to the modeled directory structure.
     initcount = int(opts['initfiles'])
     if initcount and initdirs:
         pctx = repo[None].parents()[0]
         dirs = set(pctx.dirs())
         files = {}
 
         def validpath(path):
             # Don't pick filenames which are already directory names.
             if path in dirs:
                 return False
             # Don't pick directories which were used as file names.
             while path:
                 if path in files:
                     return False
                 path = os.path.dirname(path)
             return True
 
         for i in xrange(0, initcount):
             ui.progress(_synthesizing, i, unit=_files, total=initcount)
 
             path = pickpath()
             while not validpath(path):
                 path = pickpath()
             data = '%s contents\n' % path
             files[path] = context.memfilectx(repo, path, data)
             dir = os.path.dirname(path)
             while dir and dir not in dirs:
                 dirs.add(dir)
                 dir = os.path.dirname(dir)
 
         def filectxfn(repo, memctx, path):
             return files[path]
 
         ui.progress(_synthesizing, None)
         message = 'synthesized wide repo with %d files' % (len(files),)
         mc = context.memctx(repo, [pctx.node(), nullid], message,
                             files.iterkeys(), filectxfn, ui.username(),
                             '%d %d' % util.makedate())
         initnode = mc.commit()
         if ui.debugflag:
             hexfn = hex
         else:
             hexfn = short
         ui.status(_('added commit %s with %d files\n')
                   % (hexfn(initnode), len(files)))
 
     # Synthesize incremental revisions to the repository, adding repo depth.
     count = int(opts['count'])
     heads = set(map(repo.changelog.rev, repo.heads()))
     for i in xrange(count):
         progress(_synthesizing, i, unit=_changesets, total=count)
 
         node = repo.changelog.node
         revs = len(repo)
 
         def pickhead(heads, distance):
             if heads:
                 lheads = sorted(heads)
                 rev = revs - min(pick(distance), revs)
                 if rev < lheads[-1]:
                     rev = lheads[bisect.bisect_left(lheads, rev)]
                 else:
                     rev = lheads[-1]
                 return rev, node(rev)
             return nullrev, nullid
 
         r1 = revs - min(pick(p1distance), revs)
         p1 = node(r1)
 
         # the number of heads will grow without bound if we use a pure
         # model, so artificially constrain their proliferation
         toomanyheads = len(heads) > random.randint(1, 20)
         if p2distance[0] and (pick(parents) == 2 or toomanyheads):
             r2, p2 = pickhead(heads.difference([r1]), p2distance)
         else:
             r2, p2 = nullrev, nullid
 
         pl = [p1, p2]
         pctx = repo[r1]
         mf = pctx.manifest()
         mfk = mf.keys()
         changes = {}
         if mfk:
             for __ in xrange(pick(fileschanged)):
                 for __ in xrange(10):
                     fctx = pctx.filectx(random.choice(mfk))
                     path = fctx.path()
                     if not (path in nevertouch or fctx.isbinary() or
                             'l' in fctx.flags()):
                         break
                 lines = fctx.data().splitlines()
                 add, remove = pick(lineschanged)
                 for __ in xrange(remove):
                     if not lines:
                         break
                     del lines[random.randrange(0, len(lines))]
                 for __ in xrange(add):
                     lines.insert(random.randint(0, len(lines)), makeline())
                 path = fctx.path()
                 changes[path] = context.memfilectx(repo, path,
                                                    '\n'.join(lines) + '\n')
             for __ in xrange(pick(filesremoved)):
                 path = random.choice(mfk)
                 for __ in xrange(10):
                     path = random.choice(mfk)
                     if path not in changes:
                         changes[path] = None
                         break
         if filesadded:
             dirs = list(pctx.dirs())
             dirs.insert(0, '')
         for __ in xrange(pick(filesadded)):
             pathstr = ''
             while pathstr in dirs:
                 path = [random.choice(dirs)]
                 if pick(dirsadded):
                     path.append(random.choice(words))
                 path.append(random.choice(words))
                 pathstr = '/'.join(filter(None, path))
             data = '\n'.join(makeline()
                              for __ in xrange(pick(linesinfilesadded))) + '\n'
             changes[pathstr] = context.memfilectx(repo, pathstr, data)
         def filectxfn(repo, memctx, path):
             return changes[path]
         if not changes:
             continue
         if revs:
             date = repo['tip'].date()[0] + pick(interarrival)
         else:
             date = time.time() - (86400 * count)
         # dates in mercurial must be positive, fit in 32-bit signed integers.
         date = min(0x7fffffff, max(0, date))
         user = random.choice(words) + '@' + random.choice(words)
         mc = context.memctx(repo, pl, makeline(minimum=2),
                             sorted(changes.iterkeys()),
                             filectxfn, user, '%d %d' % (date, pick(tzoffset)))
         newnode = mc.commit()
         heads.add(repo.changelog.rev(newnode))
         heads.discard(r1)
         heads.discard(r2)
 
     lock.release()
     wlock.release()
 
 def renamedirs(dirs, words):
     '''Randomly rename the directory names in the per-dir file count dict.'''
     wordgen = itertools.cycle(words)
     replacements = {'': ''}
     def rename(dirpath):
         '''Recursively rename the directory and all path prefixes.
 
         The mapping from path to renamed path is stored for all path prefixes
         as in dynamic programming, ensuring linear runtime and consistent
         renaming regardless of iteration order through the model.
         '''
         if dirpath in replacements:
             return replacements[dirpath]
         head, _ = os.path.split(dirpath)
         if head:
             head = rename(head)
         else:
             head = ''
         renamed = os.path.join(head, next(wordgen))
         replacements[dirpath] = renamed
         return renamed
     result = []
     for dirpath, count in dirs.iteritems():
         result.append([rename(dirpath.lstrip(os.sep)), count])
     return result

contrib/wix/help.wxs

@@ -1,52 +1,53 b''
 <?xml version="1.0" encoding="utf-8"?>
 <Wix xmlns="http://schemas.microsoft.com/wix/2006/wi">
 
   <?include guids.wxi ?>
   <?include defines.wxi ?>
 
   <Fragment>
     <ComponentGroup Id='helpFolder'>
       <ComponentRef Id='help.root' />
       <ComponentRef Id='help.internals' />
     </ComponentGroup>
   </Fragment>
 
   <Fragment>
     <DirectoryRef Id="INSTALLDIR">
       <Directory Id="helpdir" Name="help" FileSource="$(var.SourceDir)">
         <Component Id="help.root" Guid="$(var.help.root.guid)" Win64='$(var.IsX64)'>
           <File Name="config.txt" KeyPath="yes" />
           <File Name="dates.txt" />
           <File Name="diffs.txt" />
           <File Name="environment.txt" />
           <File Name="extensions.txt" />
           <File Name="filesets.txt" />
           <File Name="glossary.txt" />
           <File Name="hgignore.txt" />
           <File Name="hgweb.txt" />
           <File Name="merge-tools.txt" />
           <File Name="multirevs.txt" />
           <File Name="patterns.txt" />
           <File Name="phases.txt" />
           <File Name="revisions.txt" />
           <File Name="revsets.txt" />
           <File Name="scripting.txt" />
           <File Name="subrepos.txt" />
           <File Name="templates.txt" />
           <File Name="urls.txt" />
         </Component>
 
         <Directory Id="help.internaldir" Name="internals">
           <Component Id="help.internals" Guid="$(var.help.internals.guid)" Win64='$(var.IsX64)'>
             <File Id="internals.bundles.txt"      Name="bundles.txt" KeyPath="yes" />
             <File Id="internals.changegroups.txt" Name="changegroups.txt" />
             <File Id="internals.requirements.txt" Name="requirements.txt" />
             <File Id="internals.revlogs.txt"      Name="revlogs.txt" />
+            <File Id="internals.wireprotocol.txt" Name="wireprotocol.txt" />
           </Component>
         </Directory>
 
       </Directory>
     </DirectoryRef>
   </Fragment>
 
 </Wix>

contrib/zsh_completion

@@ -1,1222 +1,1222 b''
 #compdef hg
 
 # Zsh completion script for mercurial.  Rename this file to _hg and copy
 # it into your zsh function path (/usr/share/zsh/site-functions for
 # instance)
 #
 # If you do not want to install it globally, you can copy it somewhere
 # else and add that directory to $fpath. This must be done before
 # compinit is called. If the file is copied to ~/.zsh.d, your ~/.zshrc
 # file could look like this:
 #
 # fpath=("$HOME/.zsh.d" $fpath)
 # autoload -U compinit
 # compinit
 #
 # Copyright (C) 2005, 2006 Steve Borho <[e-mail]>
 # Copyright (C) 2006-10 Brendan Cully <[e-mail]>
 #
 # Permission is hereby granted, without written agreement and without
 # licence or royalty fees, to use, copy, modify, and distribute this
 # software and to distribute modified versions of this software for any
 # purpose, provided that the above copyright notice and the following
 # two paragraphs appear in all copies of this software.
 #
 # In no event shall the authors be liable to any party for direct,
 # indirect, special, incidental, or consequential damages arising out of
 # the use of this software and its documentation, even if the authors
 # have been advised of the possibility of such damage.
 #
 # The authors specifically disclaim any warranties, including, but not
 # limited to, the implied warranties of merchantability and fitness for
 # a particular purpose.  The software provided hereunder is on an "as
 # is" basis, and the authors have no obligation to provide maintenance,
 # support, updates, enhancements, or modifications.
 
 emulate -LR zsh
 setopt extendedglob
 
 local curcontext="$curcontext" state line
 typeset -A _hg_cmd_globals
 
 _hg() {
   local cmd _hg_root
   integer i=2
   _hg_cmd_globals=()
 
   while (( i < $#words ))
   do
     case "$words[$i]" in
       -R|--repository)
         eval _hg_root="$words[$i+1]"
         _hg_cmd_globals+=("$words[$i]" "$_hg_root")
         (( i += 2 ))
         continue
       ;;
       -R*)
         _hg_cmd_globals+="$words[$i]"
         eval _hg_root="${words[$i]#-R}"
        (( i++ ))
        continue
       ;;
       --cwd|--config)
         # pass along arguments to hg completer
         _hg_cmd_globals+=("$words[$i]" "$words[$i+1]")
         (( i += 2 ))
         continue
       ;;
       -*)
         # skip option
         (( i++ ))
         continue
       ;;
     esac
     if [[ -z "$cmd" ]]
     then
       cmd="$words[$i]"
       words[$i]=()
       (( CURRENT-- ))
     fi
     (( i++ ))
   done
 
   if [[ -z "$cmd" ]]
   then
     _arguments -s -w : $_hg_global_opts \
     ':mercurial command:_hg_commands'
     return
   fi
 
   # resolve abbreviations and aliases
   if ! (( $+functions[_hg_cmd_${cmd}] ))
   then
     local cmdexp
     (( $#_hg_cmd_list )) || _hg_get_commands
 
     cmdexp=$_hg_cmd_list[(r)${cmd}*]
     if [[ $cmdexp == $_hg_cmd_list[(R)${cmd}*] ]]
     then
       # might be nice to rewrite the command line with the expansion
       cmd="$cmdexp"
     fi
     if [[ -n $_hg_alias_list[$cmd] ]]
     then
       cmd=$_hg_alias_list[$cmd]
     fi
   fi
 
   curcontext="${curcontext%:*:*}:hg-${cmd}:"
 
   zstyle -s ":completion:$curcontext:" cache-policy update_policy
 
   if [[ -z "$update_policy" ]]
   then
     zstyle ":completion:$curcontext:" cache-policy _hg_cache_policy
   fi
 
   if (( $+functions[_hg_cmd_${cmd}] ))
   then
     _hg_cmd_${cmd}
   else
     # complete unknown commands normally
     _arguments -s -w : $_hg_global_opts \
       '*:files:_hg_files'
   fi
 }
 
 _hg_cache_policy() {
   typeset -a old
 
   # cache for a minute
   old=( "$1"(mm+10) )
   (( $#old )) && return 0
 
   return 1
 }
 
 _hg_get_commands() {
   typeset -ga _hg_cmd_list
   typeset -gA _hg_alias_list
   local hline cmd cmdalias
 
   _call_program hg hg debugcomplete -v | while read -A hline
   do
     cmd=$hline[1]
     _hg_cmd_list+=($cmd)
 
     for cmdalias in $hline[2,-1]
     do
       _hg_cmd_list+=($cmdalias)
       _hg_alias_list+=($cmdalias $cmd)
     done
   done
 }
 
 _hg_commands() {
   (( $#_hg_cmd_list )) || _hg_get_commands
   _describe -t commands 'mercurial command' _hg_cmd_list
 }
 
 _hg_revrange() {
   compset -P 1 '*:'
   _hg_labels "$@"
 }
 
 _hg_labels() {
   labels=("${(f)$(_hg_cmd debugnamecomplete)}")
   (( $#labels )) && _describe -t labels 'labels' labels
 }
 
 _hg_bookmarks() {
   typeset -a bookmark bookmarks
 
   _hg_cmd bookmarks | while read -A bookmark
   do
     if test -z ${bookmark[-1]:#[0-9]*}
     then
       bookmarks+=($bookmark[-2])
     fi
   done
   (( $#bookmarks )) && _describe -t bookmarks 'bookmarks' bookmarks
 }
 
 _hg_branches() {
   typeset -a branches
   local branch
 
   _hg_cmd branches | while read branch
   do
     branches+=(${branch/ #[0-9]#:*})
   done
   (( $#branches )) && _describe -t branches 'branches' branches
 }
 
 # likely merge candidates
 _hg_mergerevs() {
   typeset -a heads
   local myrev
 
   heads=(${(f)"$(_hg_cmd heads --template '{rev}:{branch}\\n')"})
   # exclude own revision
   myrev=$(_hg_cmd log -r . --template '{rev}:{branch}\\n')
   heads=(${heads:#$myrev})
 
   (( $#heads )) && _describe -t heads 'heads' heads
 
   branches=(${(f)"$(_hg_cmd heads --template '{branch}\\n')"})
   # exclude own revision
   myrev=$(_hg_cmd log -r . --template '{branch}\\n')
   branches=(${branches:#$myrev})
 
   (( $#branches )) && _describe -t branches 'branches' branches
 }
 
 _hg_files() {
   if [[ -n "$_hg_root" ]]
   then
     [[ -d "$_hg_root/.hg" ]] || return
     case "$_hg_root" in
       /*)
         _files -W $_hg_root
       ;;
       *)
         _files -W $PWD/$_hg_root
       ;;
     esac
   else
     _files
   fi
 }
 
 _hg_status() {
   [[ -d $PREFIX ]] || PREFIX=$PREFIX:h
   status_files=(${(ps:\0:)"$(_hg_cmd status -0n$1 ./$PREFIX)"})
 }
 
 _hg_unknown() {
   typeset -a status_files
   _hg_status u
   _wanted files expl 'unknown files' _multi_parts / status_files
 }
 
 _hg_missing() {
   typeset -a status_files
   _hg_status d
   _wanted files expl 'missing files' _multi_parts / status_files
 }
 
 _hg_modified() {
   typeset -a status_files
   _hg_status m
   _wanted files expl 'modified files' _multi_parts / status_files
 }
 
 _hg_resolve() {
   local rstate rpath
 
   [[ -d $PREFIX ]] || PREFIX=$PREFIX:h
 
   _hg_cmd resolve -l ./$PREFIX | while read rstate rpath
   do
     [[ $rstate == 'R' ]] && resolved_files+=($rpath)
     [[ $rstate == 'U' ]] && unresolved_files+=($rpath)
   done
 }
 
 _hg_resolved() {
   typeset -a resolved_files unresolved_files
   _hg_resolve
   _wanted files expl 'resolved files' _multi_parts / resolved_files
 }
 
 _hg_unresolved() {
   typeset -a resolved_files unresolved_files
   _hg_resolve
   _wanted files expl 'unresolved files' _multi_parts / unresolved_files
 }
 
 _hg_config() {
     typeset -a items
     items=(${${(%f)"$(_call_program hg hg showconfig)"}%%\=*})
     (( $#items )) && _describe -t config 'config item' items
 }
 
 _hg_addremove() {
   _alternative 'files:unknown files:_hg_unknown' \
     'files:missing files:_hg_missing'
 }
 
 _hg_ssh_urls() {
   if [[ -prefix */ ]]
   then
     if zstyle -T ":completion:${curcontext}:files" remote-access
     then
       local host=${PREFIX%%/*}
       typeset -a remdirs
       compset -p $(( $#host + 1 ))
       local rempath=${(M)PREFIX##*/}
       local cacheid="hg:${host}-${rempath//\//_}"
       cacheid=${cacheid%[-_]}
       compset -P '*/'
       if _cache_invalid "$cacheid" || ! _retrieve_cache "$cacheid"
       then
         remdirs=(${${(M)${(f)"$(_call_program files ssh -a -x $host ls -1FL "${(q)rempath}")"}##*/}%/})
         _store_cache "$cacheid" remdirs
       fi
       _describe -t directories 'remote directory' remdirs -S/
     else
       _message 'remote directory'
     fi
   else
     if compset -P '*@'
     then
       _hosts -S/
     else
       _alternative 'hosts:remote host name:_hosts -S/' \
         'users:user:_users -S@'
     fi
   fi
 }
 
 _hg_urls() {
   if compset -P bundle://
   then
     _files
   elif compset -P ssh://
   then
     _hg_ssh_urls
   elif [[ -prefix *: ]]
   then
     _urls
   else
     local expl
     compset -S '[^:]*'
     _wanted url-schemas expl 'URL schema' compadd -S '' - \
       http:// https:// ssh:// bundle://
   fi
 }
 
 _hg_paths() {
   typeset -a paths pnames
   _hg_cmd paths | while read -A pnames
   do
     paths+=($pnames[1])
   done
   (( $#paths )) && _describe -t path-aliases 'repository alias' paths
 }
 
 _hg_remote() {
   _alternative 'path-aliases:repository alias:_hg_paths' \
     'directories:directory:_files -/' \
     'urls:URL:_hg_urls'
 }
 
 _hg_clone_dest() {
   _alternative 'directories:directory:_files -/' \
     'urls:URL:_hg_urls'
 }
 
 _hg_add_help_topics=(
     config dates diffs environment extensions filesets glossary hgignore hgweb
     merge-tools multirevs obsolescence patterns phases revisions revsets
     subrepos templating urls
 )
 
 _hg_help_topics() {
     local topics
     (( $#_hg_cmd_list )) || _hg_get_commands
     topics=($_hg_cmd_list $_hg_add_help_topics)
     _describe -t help_topics 'help topics' topics
 }
 
 # Common options
 _hg_global_opts=(
-    '(--repository -R)'{-R+,--repository}'[repository root directory]:repository:_files -/'
+    '(--repository -R)'{-R+,--repository=}'[repository root directory]:repository:_files -/'
     '--cwd[change working directory]:new working directory:_files -/'
     '(--noninteractive -y)'{-y,--noninteractive}'[do not prompt, assume yes for any required answers]'
     '(--verbose -v)'{-v,--verbose}'[enable additional output]'
     '*--config[set/override config option]:defined config items:_hg_config'
     '(--quiet -q)'{-q,--quiet}'[suppress output]'
     '(--help -h)'{-h,--help}'[display help and exit]'
     '--debug[debug mode]'
     '--debugger[start debugger]'
     '--encoding[set the charset encoding]'
     '--encodingmode[set the charset encoding mode]'
     '--lsprof[print improved command execution profile]'
     '--traceback[print traceback on exception]'
     '--time[time how long the command takes]'
     '--profile[profile]'
     '--version[output version information and exit]'
 )
 
 _hg_pat_opts=(
-  '*'{-I+,--include}'[include names matching the given patterns]:dir:_files -W $(_hg_cmd root) -/'
-  '*'{-X+,--exclude}'[exclude names matching the given patterns]:dir:_files -W $(_hg_cmd root) -/')
+  '*'{-I+,--include=}'[include names matching the given patterns]:dir:_files -W $(_hg_cmd root) -/'
+  '*'{-X+,--exclude=}'[exclude names matching the given patterns]:dir:_files -W $(_hg_cmd root) -/')
 
 _hg_clone_opts=(
   $_hg_remote_opts
   '(--noupdate -U)'{-U,--noupdate}'[do not update the new working directory]'
   '--pull[use pull protocol to copy metadata]'
   '--uncompressed[use uncompressed transfer (fast over LAN)]')
 
 _hg_date_user_opts=(
   '(--currentdate -D)'{-D,--currentdate}'[record the current date as commit date]'
   '(--currentuser -U)'{-U,--currentuser}'[record the current user as committer]'
-  '(--date -d)'{-d+,--date}'[record the specified date as commit date]:date:'
-  '(--user -u)'{-u+,--user}'[record the specified user as committer]:user:')
+  '(--date -d)'{-d+,--date=}'[record the specified date as commit date]:date:'
+  '(--user -u)'{-u+,--user=}'[record the specified user as committer]:user:')
 
 _hg_gitlike_opts=(
   '(--git -g)'{-g,--git}'[use git extended diff format]')
 
 _hg_diff_opts=(
   $_hg_gitlike_opts
   '(--text -a)'{-a,--text}'[treat all files as text]'
   '--nodates[omit dates from diff headers]')
 
 _hg_mergetool_opts=(
-  '(--tool -t)'{-t+,--tool}'[specify merge tool]:tool:')
+  '(--tool -t)'{-t+,--tool=}'[specify merge tool]:tool:')
 
 _hg_dryrun_opts=(
   '(--dry-run -n)'{-n,--dry-run}'[do not perform actions, just print output]')
 
 _hg_ignore_space_opts=(
   '(--ignore-all-space -w)'{-w,--ignore-all-space}'[ignore white space when comparing lines]'
   '(--ignore-space-change -b)'{-b,--ignore-space-change}'[ignore changes in the amount of white space]'
   '(--ignore-blank-lines -B)'{-B,--ignore-blank-lines}'[ignore changes whose lines are all blank]')
 
 _hg_style_opts=(
   '--style[display using template map file]:'
   '--template[display with template]:')
 
 _hg_log_opts=(
   $_hg_global_opts $_hg_style_opts $_hg_gitlike_opts
-  '(--limit -l)'{-l+,--limit}'[limit number of changes displayed]:'
+  '(--limit -l)'{-l+,--limit=}'[limit number of changes displayed]:'
   '(--no-merges -M)'{-M,--no-merges}'[do not show merges]'
   '(--patch -p)'{-p,--patch}'[show patch]'
   '--stat[output diffstat-style summary of changes]'
 )
 
 _hg_commit_opts=(
   '(-m --message -l --logfile --edit -e)'{-e,--edit}'[edit commit message]'
-  '(-e --edit -l --logfile --message -m)'{-m+,--message}'[use <text> as commit message]:message:'
-  '(-e --edit -m --message --logfile -l)'{-l+,--logfile}'[read the commit message from <file>]:log file:_files')
+  '(-e --edit -l --logfile --message -m)'{-m+,--message=}'[use <text> as commit message]:message:'
+  '(-e --edit -m --message --logfile -l)'{-l+,--logfile=}'[read the commit message from <file>]:log file:_files')
 
 _hg_remote_opts=(
-  '(--ssh -e)'{-e+,--ssh}'[specify ssh command to use]:'
+  '(--ssh -e)'{-e+,--ssh=}'[specify ssh command to use]:'
   '--remotecmd[specify hg command to run on the remote side]:')
 
 _hg_branch_bmark_opts=(
-  '(--bookmark -B)'{-B+,--bookmark}'[specify bookmark(s)]:bookmark:_hg_bookmarks'
-  '(--branch -b)'{-b+,--branch}'[specify branch(es)]:branch:_hg_branches'
+  '(--bookmark -B)'{-B+,--bookmark=}'[specify bookmark(s)]:bookmark:_hg_bookmarks'
+  '(--branch -b)'{-b+,--branch=}'[specify branch(es)]:branch:_hg_branches'
 )
 
 _hg_subrepos_opts=(
   '(--subrepos -S)'{-S,--subrepos}'[recurse into subrepositories]')
 
 _hg_cmd() {
   _call_program hg HGPLAIN=1 hg "$_hg_cmd_globals[@]" "$@" 2> /dev/null
 }
 
 _hg_cmd_add() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_dryrun_opts $_hg_subrepos_opts \
   '*:unknown files:_hg_unknown'
 }
 
 _hg_cmd_addremove() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_dryrun_opts \
-  '(--similarity -s)'{-s+,--similarity}'[guess renamed files by similarity (0<=s<=100)]:' \
+  '(--similarity -s)'{-s+,--similarity=}'[guess renamed files by similarity (0<=s<=100)]:' \
   '*:unknown or missing files:_hg_addremove'
 }
 
 _hg_cmd_annotate() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts \
-  '(--rev -r)'{-r+,--rev}'[annotate the specified revision]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[annotate the specified revision]:revision:_hg_labels' \
   '(--follow -f)'{-f,--follow}'[follow file copies and renames]' \
   '(--text -a)'{-a,--text}'[treat all files as text]' \
   '(--user -u)'{-u,--user}'[list the author]' \
   '(--date -d)'{-d,--date}'[list the date]' \
   '(--number -n)'{-n,--number}'[list the revision number (default)]' \
   '(--changeset -c)'{-c,--changeset}'[list the changeset]' \
   '*:files:_hg_files'
 }
 
 _hg_cmd_archive() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_subrepos_opts \
   '--no-decode[do not pass files through decoders]' \
-  '(--prefix -p)'{-p+,--prefix}'[directory prefix for files in archive]:' \
-  '(--rev -r)'{-r+,--rev}'[revision to distribute]:revision:_hg_labels' \
-  '(--type -t)'{-t+,--type}'[type of distribution to create]:archive type:(files tar tbz2 tgz uzip zip)' \
+  '(--prefix -p)'{-p+,--prefix=}'[directory prefix for files in archive]:' \
+  '(--rev -r)'{-r+,--rev=}'[revision to distribute]:revision:_hg_labels' \
+  '(--type -t)'{-t+,--type=}'[type of distribution to create]:archive type:(files tar tbz2 tgz uzip zip)' \
   '*:destination:_files'
 }
 
 _hg_cmd_backout() {
   _arguments -s -w : $_hg_global_opts $_hg_mergetool_opts $_hg_pat_opts \
     '--merge[merge with old dirstate parent after backout]' \
-    '(--date -d)'{-d+,--date}'[record datecode as commit date]:date code:' \
+    '(--date -d)'{-d+,--date=}'[record datecode as commit date]:date code:' \
     '--parent[parent to choose when backing out merge]' \
-    '(--user -u)'{-u+,--user}'[record user as commiter]:user:' \
-    '(--rev -r)'{-r+,--rev}'[revision]:revision:_hg_labels' \
-    '(--message -m)'{-m+,--message}'[use <text> as commit message]:text:' \
-    '(--logfile -l)'{-l+,--logfile}'[read commit message from <file>]:log file:_files'
+    '(--user -u)'{-u+,--user=}'[record user as commiter]:user:' \
+    '(--rev -r)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
+    '(--message -m)'{-m+,--message=}'[use <text> as commit message]:text:' \
+    '(--logfile -l)'{-l+,--logfile=}'[read commit message from <file>]:log file:_files'
 }
 
 _hg_cmd_bisect() {
   _arguments -s -w : $_hg_global_opts \
   '(-)'{-r,--reset}'[reset bisect state]' \
   '(--extend -e)'{-e,--extend}'[extend the bisect range]' \
   '(--good -g --bad -b --skip -s --reset -r)'{-g,--good}'[mark changeset good]'::revision:_hg_labels \
   '(--good -g --bad -b --skip -s --reset -r)'{-b,--bad}'[mark changeset bad]'::revision:_hg_labels \
   '(--good -g --bad -b --skip -s --reset -r)'{-s,--skip}'[skip testing changeset]' \
-  '(--command -c --noupdate -U)'{-c+,--command}'[use command to check changeset state]':commands:_command_names \
+  '(--command -c --noupdate -U)'{-c+,--command=}'[use command to check changeset state]':commands:_command_names \
   '(--command -c --noupdate -U)'{-U,--noupdate}'[do not update to target]'
 }
 
 _hg_cmd_bookmarks() {
   _arguments -s -w : $_hg_global_opts \
   '(--force -f)'{-f,--force}'[force]' \
   '(--inactive -i)'{-i,--inactive}'[mark a bookmark inactive]' \
-  '(--rev -r --delete -d --rename -m)'{-r+,--rev}'[revision]:revision:_hg_labels' \
+  '(--rev -r --delete -d --rename -m)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
   '(--rev -r --delete -d --rename -m)'{-d,--delete}'[delete a given bookmark]' \
-  '(--rev -r --delete -d --rename -m)'{-m+,--rename}'[rename a given bookmark]:bookmark:_hg_bookmarks' \
+  '(--rev -r --delete -d --rename -m)'{-m+,--rename=}'[rename a given bookmark]:bookmark:_hg_bookmarks' \
   ':bookmark:_hg_bookmarks'
 }
 
 _hg_cmd_branch() {
   _arguments -s -w : $_hg_global_opts \
   '(--force -f)'{-f,--force}'[set branch name even if it shadows an existing branch]' \
   '(--clean -C)'{-C,--clean}'[reset branch name to parent branch name]'
 }
 
 _hg_cmd_branches() {
   _arguments -s -w : $_hg_global_opts \
   '(--active -a)'{-a,--active}'[show only branches that have unmerge heads]' \
   '(--closed -c)'{-c,--closed}'[show normal and closed branches]'
 }
 
 _hg_cmd_bundle() {
   _arguments -s -w : $_hg_global_opts $_hg_remote_opts \
   '(--force -f)'{-f,--force}'[run even when remote repository is unrelated]' \
   '(2)*--base[a base changeset to specify instead of a destination]:revision:_hg_labels' \
-  '(--branch -b)'{-b+,--branch}'[a specific branch to bundle]' \
-  '(--rev -r)'{-r+,--rev}'[changeset(s) to bundle]:' \
+  '(--branch -b)'{-b+,--branch=}'[a specific branch to bundle]:' \
+  '(--rev -r)'{-r+,--rev=}'[changeset(s) to bundle]:' \
   '--all[bundle all changesets in the repository]' \
   ':output file:_files' \
   ':destination repository:_files -/'
 }
 
 _hg_cmd_cat() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts \
-  '(--output -o)'{-o+,--output}'[print output to file with formatted name]:filespec:' \
-  '(--rev -r)'{-r+,--rev}'[revision]:revision:_hg_labels' \
+  '(--output -o)'{-o+,--output=}'[print output to file with formatted name]:filespec:' \
+  '(--rev -r)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
   '--decode[apply any matching decode filter]' \
   '*:file:_hg_files'
 }
 
 _hg_cmd_clone() {
   _arguments -s -w : $_hg_global_opts $_hg_clone_opts \
-  '(--rev -r)'{-r+,--rev}'[a changeset you would like to have after cloning]:' \
-  '(--updaterev -u)'{-u+,--updaterev}'[revision, tag or branch to check out]' \
-  '(--branch -b)'{-b+,--branch}'[clone only the specified branch]' \
+  '(--rev -r)'{-r+,--rev=}'[a changeset you would like to have after cloning]:' \
+  '(--updaterev -u)'{-u+,--updaterev=}'[revision, tag or branch to check out]:' \
+  '(--branch -b)'{-b+,--branch=}'[clone only the specified branch]:' \
   ':source repository:_hg_remote' \
   ':destination:_hg_clone_dest'
 }
 
 _hg_cmd_commit() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_subrepos_opts \
   '(--addremove -A)'{-A,--addremove}'[mark new/missing files as added/removed before committing]' \
-  '(--message -m)'{-m+,--message}'[use <text> as commit message]:text:' \
-  '(--logfile -l)'{-l+,--logfile}'[read commit message from <file>]:log file:_files' \
-  '(--date -d)'{-d+,--date}'[record datecode as commit date]:date code:' \
-  '(--user -u)'{-u+,--user}'[record user as commiter]:user:' \
+  '(--message -m)'{-m+,--message=}'[use <text> as commit message]:text:' \
+  '(--logfile -l)'{-l+,--logfile=}'[read commit message from <file>]:log file:_files' \
+  '(--date -d)'{-d+,--date=}'[record datecode as commit date]:date code:' \
+  '(--user -u)'{-u+,--user=}'[record user as commiter]:user:' \
   '--amend[amend the parent of the working dir]' \
   '--close-branch[mark a branch as closed]' \
   '*:file:_hg_files'
 }
 
 _hg_cmd_copy() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_dryrun_opts \
   '(--after -A)'{-A,--after}'[record a copy that has already occurred]' \
   '(--force -f)'{-f,--force}'[forcibly copy over an existing managed file]' \
   '*:file:_hg_files'
 }
 
 _hg_cmd_diff() {
   typeset -A opt_args
   _arguments -s -w : $_hg_global_opts $_hg_diff_opts $_hg_ignore_space_opts \
                      $_hg_pat_opts $_hg_subrepos_opts \
-  '*'{-r,--rev}'+[revision]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[revision]:revision:_hg_revrange' \
   '(--show-function -p)'{-p,--show-function}'[show which function each change is in]' \
-  '(--change -c)'{-c,--change}'[change made by revision]' \
+  '(--change -c)'{-c+,--change=}'[change made by revision]:' \
   '(--text -a)'{-a,--text}'[treat all files as text]' \
   '--reverse[produce a diff that undoes the changes]' \
-  '(--unified -U)'{-U,--unified}'[number of lines of context to show]' \
+  '(--unified -U)'{-U+,--unified=}'[number of lines of context to show]:' \
   '--stat[output diffstat-style summary of changes]' \
   '*:file:->diff_files'
 
   if [[ $state == 'diff_files' ]]
   then
     if [[ -n $opt_args[-r] ]]
     then
       _hg_files
     else
       _hg_modified
     fi
   fi
 }
 
 _hg_cmd_export() {
   _arguments -s -w : $_hg_global_opts $_hg_diff_opts \
-  '(--outout -o)'{-o+,--output}'[print output to file with formatted name]:filespec:' \
+  '(--outout -o)'{-o+,--output=}'[print output to file with formatted name]:filespec:' \
   '--switch-parent[diff against the second parent]' \
-  '(--rev -r)'{-r+,--rev}'[revision]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
   '*:revision:_hg_labels'
 }
 
 _hg_cmd_forget() {
   _arguments -s -w : $_hg_global_opts \
   '*:file:_hg_files'
 }
 
 _hg_cmd_graft() {
   _arguments -s -w : $_hg_global_opts $_hg_dryrun_opts \
                      $_hg_date_user_opts $_hg_mergetool_opts \
   '(--continue -c)'{-c,--continue}'[resume interrupted graft]' \
   '(--edit -e)'{-e,--edit}'[invoke editor on commit messages]' \
   '--log[append graft info to log message]' \
   '*:revision:_hg_labels'
 }
 
 _hg_cmd_grep() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts \
   '(--print0 -0)'{-0,--print0}'[end filenames with NUL]' \
   '--all[print all revisions with matches]' \
   '(--follow -f)'{-f,--follow}'[follow changeset or file history]' \
   '(--ignore-case -i)'{-i,--ignore-case}'[ignore case when matching]' \
   '(--files-with-matches -l)'{-l,--files-with-matches}'[print only filenames and revs that match]' \
   '(--line-number -n)'{-n,--line-number}'[print matching line numbers]' \
-  '*'{-r+,--rev}'[search in given revision range]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[search in given revision range]:revision:_hg_revrange' \
   '(--user -u)'{-u,--user}'[print user who committed change]' \
   '(--date -d)'{-d,--date}'[print date of a changeset]' \
   '1:search pattern:' \
   '*:files:_hg_files'
 }
 
 _hg_cmd_heads() {
   _arguments -s -w : $_hg_global_opts $_hg_style_opts \
   '(--topo -t)'{-t,--topo}'[show topological heads only]' \
   '(--closed -c)'{-c,--closed}'[show normal and closed branch heads]' \
-  '(--rev -r)'{-r+,--rev}'[show only heads which are descendants of rev]:revision:_hg_labels'
+  '(--rev -r)'{-r+,--rev=}'[show only heads which are descendants of rev]:revision:_hg_labels'
 }
 
 _hg_cmd_help() {
   _arguments -s -w : $_hg_global_opts \
   '(--extension -e)'{-e,--extension}'[show only help for extensions]' \
   '(--command -c)'{-c,--command}'[show only help for commands]' \
   '(--keyword -k)'{-k+,--keyword}'[show topics matching keyword]' \
   '*:mercurial help topic:_hg_help_topics'
 }
 
 _hg_cmd_identify() {
   _arguments -s -w : $_hg_global_opts $_hg_remote_opts \
-  '(--rev -r)'{-r+,--rev}'[identify the specified rev]:revision:_hg_labels' \
-  '(--num -n)'{-n+,--num}'[show local revision number]' \
-  '(--id -i)'{-i+,--id}'[show global revision id]' \
-  '(--branch -b)'{-b+,--branch}'[show branch]' \
-  '(--bookmark -B)'{-B+,--bookmark}'[show bookmarks]' \
-  '(--tags -t)'{-t+,--tags}'[show tags]'
+  '(--rev -r)'{-r+,--rev=}'[identify the specified rev]:revision:_hg_labels' \
+  '(--num -n)'{-n,--num}'[show local revision number]' \
+  '(--id -i)'{-i,--id}'[show global revision id]' \
+  '(--branch -b)'{-b,--branch}'[show branch]' \
+  '(--bookmark -B)'{-B,--bookmark}'[show bookmarks]' \
+  '(--tags -t)'{-t,--tags}'[show tags]'
 }
 
 _hg_cmd_import() {
   _arguments -s -w : $_hg_global_opts $_hg_commit_opts \
-  '(--strip -p)'{-p+,--strip}'[directory strip option for patch (default: 1)]:count:' \
+  '(--strip -p)'{-p+,--strip=}'[directory strip option for patch (default: 1)]:count:' \
   '(--force -f)'{-f,--force}'[skip check for outstanding uncommitted changes]' \
   '--bypass[apply patch without touching the working directory]' \
   '--no-commit[do not commit, just update the working directory]' \
   '--exact[apply patch to the nodes from which it was generated]' \
   '--import-branch[use any branch information in patch (implied by --exact)]' \
-  '(--date -d)'{-d+,--date}'[record datecode as commit date]:date code:' \
-  '(--user -u)'{-u+,--user}'[record user as commiter]:user:' \
-  '(--similarity -s)'{-s+,--similarity}'[guess renamed files by similarity (0<=s<=100)]:' \
+  '(--date -d)'{-d+,--date=}'[record datecode as commit date]:date code:' \
+  '(--user -u)'{-u+,--user=}'[record user as commiter]:user:' \
+  '(--similarity -s)'{-s+,--similarity=}'[guess renamed files by similarity (0<=s<=100)]:' \
   '*:patch:_files'
 }
 
 _hg_cmd_incoming() {
   _arguments -s -w : $_hg_log_opts $_hg_branch_bmark_opts $_hg_remote_opts \
                      $_hg_subrepos_opts \
   '(--force -f)'{-f,--force}'[run even when the remote repository is unrelated]' \
-  '(--rev -r)'{-r+,--rev}'[a specific revision up to which you would like to pull]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[a specific revision up to which you would like to pull]:revision:_hg_labels' \
   '(--newest-first -n)'{-n,--newest-first}'[show newest record first]' \
   '--bundle[file to store the bundles into]:bundle file:_files' \
   ':source:_hg_remote'
 }
 
 _hg_cmd_init() {
   _arguments -s -w : $_hg_global_opts $_hg_remote_opts \
   ':dir:_files -/'
 }
 
 _hg_cmd_locate() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts \
-  '(--rev -r)'{-r+,--rev}'[search repository as it stood at revision]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[search repository as it stood at revision]:revision:_hg_labels' \
   '(--print0 -0)'{-0,--print0}'[end filenames with NUL, for use with xargs]' \
   '(--fullpath -f)'{-f,--fullpath}'[print complete paths]' \
   '*:search pattern:_hg_files'
 }
 
 _hg_cmd_log() {
   _arguments -s -w : $_hg_log_opts $_hg_pat_opts \
   '(--follow --follow-first -f)'{-f,--follow}'[follow changeset or history]' \
   '(-f --follow)--follow-first[only follow the first parent of merge changesets]' \
   '(--copies -C)'{-C,--copies}'[show copied files]' \
   '(--keyword -k)'{-k+,--keyword}'[search for a keyword]:' \
-  '*'{-r,--rev}'[show the specified revision or revset]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[show the specified revision or revset]:revision:_hg_revrange' \
   '(--only-merges -m)'{-m,--only-merges}'[show only merges]' \
-  '(--prune -P)'{-P+,--prune}'[do not display revision or any of its ancestors]:revision:_hg_labels' \
-  '(--graph -G)'{-G+,--graph}'[show the revision DAG]' \
-  '(--branch -b)'{-b+,--branch}'[show changesets within the given named branch]:branch:_hg_branches' \
-  '(--user -u)'{-u+,--user}'[revisions committed by user]:user:' \
-  '(--date -d)'{-d+,--date}'[show revisions matching date spec]:date:' \
+  '(--prune -P)'{-P+,--prune=}'[do not display revision or any of its ancestors]:revision:_hg_labels' \
+  '(--graph -G)'{-G,--graph}'[show the revision DAG]' \
+  '(--branch -b)'{-b+,--branch=}'[show changesets within the given named branch]:branch:_hg_branches' \
+  '(--user -u)'{-u+,--user=}'[revisions committed by user]:user:' \
+  '(--date -d)'{-d+,--date=}'[show revisions matching date spec]:date:' \
   '*:files:_hg_files'
 }
 
 _hg_cmd_manifest() {
   _arguments -s -w : $_hg_global_opts \
   '--all[list files from all revisions]' \
-  '(--rev -r)'{-r+,--rev}'[revision to display]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[revision to display]:revision:_hg_labels' \
   ':revision:_hg_labels'
 }
 
 _hg_cmd_merge() {
   _arguments -s -w : $_hg_global_opts $_hg_mergetool_opts \
   '(--force -f)'{-f,--force}'[force a merge with outstanding changes]' \
-  '(--rev -r 1)'{-r,--rev}'[revision to merge]:revision:_hg_mergerevs' \
+  '(--rev -r 1)'{-r+,--rev=}'[revision to merge]:revision:_hg_mergerevs' \
   '(--preview -P)'{-P,--preview}'[review revisions to merge (no merge is performed)]' \
   ':revision:_hg_mergerevs'
 }
 
 _hg_cmd_outgoing() {
   _arguments -s -w : $_hg_log_opts $_hg_branch_bmark_opts $_hg_remote_opts \
                      $_hg_subrepos_opts \
   '(--force -f)'{-f,--force}'[run even when the remote repository is unrelated]' \
-  '*'{-r,--rev}'[a specific revision you would like to push]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[a specific revision you would like to push]:revision:_hg_revrange' \
   '(--newest-first -n)'{-n,--newest-first}'[show newest record first]' \
   ':destination:_hg_remote'
 }
 
 _hg_cmd_parents() {
   _arguments -s -w : $_hg_global_opts $_hg_style_opts \
-  '(--rev -r)'{-r+,--rev}'[show parents of the specified rev]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[show parents of the specified rev]:revision:_hg_labels' \
   ':last modified file:_hg_files'
 }
 
 _hg_cmd_paths() {
   _arguments -s -w : $_hg_global_opts \
   ':path:_hg_paths'
 }
 
 _hg_cmd_phase() {
   _arguments -s -w : $_hg_global_opts \
   '(--public -p)'{-p,--public}'[set changeset phase to public]' \
   '(--draft -d)'{-d,--draft}'[set changeset phase to draft]' \
   '(--secret -s)'{-s,--secret}'[set changeset phase to secret]' \
   '(--force -f)'{-f,--force}'[allow to move boundary backward]' \
-  '(--rev -r)'{-r+,--rev}'[target revision]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[target revision]:revision:_hg_labels' \
   ':revision:_hg_labels'
 }
 
 _hg_cmd_pull() {
   _arguments -s -w : $_hg_global_opts $_hg_branch_bmark_opts $_hg_remote_opts \
   '(--force -f)'{-f,--force}'[run even when the remote repository is unrelated]' \
   '(--update -u)'{-u,--update}'[update to new tip if changesets were pulled]' \
   '(--rev -r)'{-r+,--rev}'[a specific revision up to which you would like to pull]:revision:' \
   ':source:_hg_remote'
 }
 
 _hg_cmd_push() {
   _arguments -s -w : $_hg_global_opts $_hg_branch_bmark_opts $_hg_remote_opts \
   '(--force -f)'{-f,--force}'[force push]' \
-  '(--rev -r)'{-r+,--rev}'[a specific revision you would like to push]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[a specific revision you would like to push]:revision:_hg_labels' \
   '--new-branch[allow pushing a new branch]' \
   ':destination:_hg_remote'
 }
 
 _hg_cmd_remove() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts \
   '(--after -A)'{-A,--after}'[record remove that has already occurred]' \
   '(--force -f)'{-f,--force}'[remove file even if modified]' \
   '*:file:_hg_files'
 }
 
 _hg_cmd_rename() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_dryrun_opts \
   '(--after -A)'{-A,--after}'[record a rename that has already occurred]' \
   '(--force -f)'{-f,--force}'[forcibly copy over an existing managed file]' \
   '*:file:_hg_files'
 }
 
 _hg_cmd_resolve() {
   local context state line
   typeset -A opt_args
 
   _arguments -s -w : $_hg_global_opts $_hg_mergetool_opts $_hg_pat_opts \
   '(--all -a)'{-a,--all}'[select all unresolved files]' \
   '(--no-status -n)'{-n,--no-status}'[hide status prefix]' \
   '(--list -l --mark -m --unmark -u)'{-l,--list}'[list state of files needing merge]:*:merged files:->resolve_files' \
   '(--mark -m --list -l --unmark -u)'{-m,--mark}'[mark files as resolved]:*:unresolved files:_hg_unresolved' \
   '(--unmark -u --list -l --mark -m)'{-u,--unmark}'[unmark files as resolved]:*:resolved files:_hg_resolved' \
   '*:file:_hg_unresolved'
 
   if [[ $state == 'resolve_files' ]]
   then
     _alternative 'files:resolved files:_hg_resolved' \
       'files:unresolved files:_hg_unresolved'
   fi
 }
 
 _hg_cmd_revert() {
   local context state line
   typeset -A opt_args
 
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_dryrun_opts \
   '(--all -a :)'{-a,--all}'[revert all changes when no arguments given]' \
-  '(--rev -r)'{-r+,--rev}'[revision to revert to]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[revision to revert to]:revision:_hg_labels' \
   '(--no-backup -C)'{-C,--no-backup}'[do not save backup copies of files]' \
-  '(--date -d)'{-d+,--date}'[tipmost revision matching date]:date code:' \
+  '(--date -d)'{-d+,--date=}'[tipmost revision matching date]:date code:' \
   '*:file:->diff_files'
 
   if [[ $state == 'diff_files' ]]
   then
     if [[ -n $opt_args[-r] ]]
     then
       _hg_files
     else
       typeset -a status_files
       _hg_status mard
       _wanted files expl 'modified, added, removed or deleted file' _multi_parts / status_files
     fi
   fi
 }
 
 _hg_cmd_rollback() {
   _arguments -s -w : $_hg_global_opts $_hg_dryrun_opts \
   '(--force -f)'{-f,--force}'[ignore safety measures]' \
 }
 
 _hg_cmd_serve() {
   _arguments -s -w : $_hg_global_opts \
-  '(--accesslog -A)'{-A+,--accesslog}'[name of access log file]:log file:_files' \
-  '(--errorlog -E)'{-E+,--errorlog}'[name of error log file]:log file:_files' \
+  '(--accesslog -A)'{-A+,--accesslog=}'[name of access log file]:log file:_files' \
+  '(--errorlog -E)'{-E+,--errorlog=}'[name of error log file]:log file:_files' \
   '(--daemon -d)'{-d,--daemon}'[run server in background]' \
-  '(--port -p)'{-p+,--port}'[listen port]:listen port:' \
-  '(--address -a)'{-a+,--address}'[interface address]:interface address:' \
+  '(--port -p)'{-p+,--port=}'[listen port]:listen port:' \
+  '(--address -a)'{-a+,--address=}'[interface address]:interface address:' \
   '--prefix[prefix path to serve from]:directory:_files' \
-  '(--name -n)'{-n+,--name}'[name to show in web pages]:repository name:' \
+  '(--name -n)'{-n+,--name=}'[name to show in web pages]:repository name:' \
   '--web-conf[name of the hgweb config file]:webconf_file:_files' \
   '--pid-file[name of file to write process ID to]:pid_file:_files' \
   '--cmdserver[cmdserver mode]:mode:' \
   '(--templates -t)'{-t,--templates}'[web template directory]:template dir:_files -/' \
   '--style[web template style]:style' \
   '--stdio[for remote clients]' \
   '--certificate[certificate file]:cert_file:_files' \
   '(--ipv6 -6)'{-6,--ipv6}'[use IPv6 in addition to IPv4]'
 }
 
 _hg_cmd_showconfig() {
   _arguments -s -w : $_hg_global_opts \
-  '(--untrusted -u)'{-u+,--untrusted}'[show untrusted configuration options]' \
+  '(--untrusted -u)'{-u,--untrusted}'[show untrusted configuration options]' \
   ':config item:_hg_config'
 }
 
 _hg_cmd_status() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_subrepos_opts \
   '(--all -A)'{-A,--all}'[show status of all files]' \
   '(--modified -m)'{-m,--modified}'[show only modified files]' \
   '(--added -a)'{-a,--added}'[show only added files]' \
   '(--removed -r)'{-r,--removed}'[show only removed files]' \
   '(--deleted -d)'{-d,--deleted}'[show only deleted (but tracked) files]' \
   '(--clean -c)'{-c,--clean}'[show only files without changes]' \
   '(--unknown -u)'{-u,--unknown}'[show only unknown files]' \
   '(--ignored -i)'{-i,--ignored}'[show ignored files]' \
   '(--no-status -n)'{-n,--no-status}'[hide status prefix]' \
   '(--copies -C)'{-C,--copies}'[show source of copied files]' \
   '(--print0 -0)'{-0,--print0}'[end filenames with NUL, for use with xargs]' \
   '--rev[show difference from revision]:revision:_hg_labels' \
   '--change[list the changed files of a revision]:revision:_hg_labels' \
   '*:files:_files'
 }
 
 _hg_cmd_summary() {
   _arguments -s -w : $_hg_global_opts \
   '--remote[check for push and pull]'
 }
 
 _hg_cmd_tag() {
   _arguments -s -w : $_hg_global_opts \
   '(--local -l)'{-l,--local}'[make the tag local]' \
-  '(--message -m)'{-m+,--message}'[message for tag commit log entry]:message:' \
-  '(--date -d)'{-d+,--date}'[record datecode as commit date]:date code:' \
-  '(--user -u)'{-u+,--user}'[record user as commiter]:user:' \
-  '(--rev -r)'{-r+,--rev}'[revision to tag]:revision:_hg_labels' \
+  '(--message -m)'{-m+,--message=}'[message for tag commit log entry]:message:' \
+  '(--date -d)'{-d+,--date=}'[record datecode as commit date]:date code:' \
+  '(--user -u)'{-u+,--user=}'[record user as commiter]:user:' \
+  '(--rev -r)'{-r+,--rev=}'[revision to tag]:revision:_hg_labels' \
   '(--force -f)'{-f,--force}'[force tag]' \
   '--remove[remove a tag]' \
   '(--edit -e)'{-e,--edit}'[edit commit message]' \
   ':tag name:'
 }
 
 _hg_cmd_tip() {
   _arguments -s -w : $_hg_global_opts $_hg_gitlike_opts $_hg_style_opts \
   '(--patch -p)'{-p,--patch}'[show patch]'
 }
 
 _hg_cmd_unbundle() {
   _arguments -s -w : $_hg_global_opts \
   '(--update -u)'{-u,--update}'[update to new tip if changesets were unbundled]' \
   ':files:_files'
 }
 
 _hg_cmd_update() {
   _arguments -s -w : $_hg_global_opts \
   '(--clean -C)'{-C,--clean}'[overwrite locally modified files]' \
-  '(--rev -r)'{-r+,--rev}'[revision]:revision:_hg_labels' \
+  '(--rev -r)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
   '(--check -c)'{-c,--check}'[update across branches if no uncommitted changes]' \
-  '(--date -d)'{-d+,--date}'[tipmost revision matching date]' \
+  '(--date -d)'{-d+,--date=}'[tipmost revision matching date]:' \
   ':revision:_hg_labels'
 }
 
 ## extensions ##
 
 # HGK
 _hg_cmd_view() {
   _arguments -s -w : $_hg_global_opts \
-  '(--limit -l)'{-l+,--limit}'[limit number of changes displayed]:' \
+  '(--limit -l)'{-l+,--limit=}'[limit number of changes displayed]:' \
   ':revision range:_hg_labels'
 }
 
 # MQ
 _hg_qseries() {
   typeset -a patches
   patches=(${(f)"$(_hg_cmd qseries)"})
   (( $#patches )) && _describe -t hg-patches 'patches' patches
 }
 
 _hg_qapplied() {
   typeset -a patches
   patches=(${(f)"$(_hg_cmd qapplied)"})
   if (( $#patches ))
   then
     patches+=(qbase qtip)
     _describe -t hg-applied-patches 'applied patches' patches
   fi
 }
 
 _hg_qunapplied() {
   typeset -a patches
   patches=(${(f)"$(_hg_cmd qunapplied)"})
   (( $#patches )) && _describe -t hg-unapplied-patches 'unapplied patches' patches
 }
 
 # unapplied, including guarded patches
 _hg_qdeletable() {
   typeset -a unapplied
   unapplied=(${(f)"$(_hg_cmd qseries)"})
   for p in $(_hg_cmd qapplied)
   do
     unapplied=(${unapplied:#$p})
   done
 
   (( $#unapplied )) && _describe -t hg-allunapplied-patches 'all unapplied patches' unapplied
 }
 
 _hg_qguards() {
   typeset -a guards
   local guard
   compset -P "+|-"
   _hg_cmd qselect -s | while read guard
   do
     guards+=(${guard#(+|-)})
   done
   (( $#guards )) && _describe -t hg-guards 'guards' guards
 }
 
 _hg_qseries_opts=(
   '(--summary -s)'{-s,--summary}'[print first line of patch header]')
 
 _hg_cmd_qapplied() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts \
   '(--last -1)'{-1,--last}'[show only the preceding applied patch]' \
   '*:patch:_hg_qapplied'
 }
 
 _hg_cmd_qclone() {
   _arguments -s -w : $_hg_global_opts $_hg_remote_opts $_hg_clone_opts \
-  '(--patches -p)'{-p+,--patches}'[location of source patch repository]' \
+  '(--patches -p)'{-p+,--patches=}'[location of source patch repository]:' \
   ':source repository:_hg_remote' \
   ':destination:_hg_clone_dest'
 }
 
 _hg_cmd_qdelete() {
   _arguments -s -w : $_hg_global_opts \
   '(--keep -k)'{-k,--keep}'[keep patch file]' \
-  '*'{-r+,--rev}'[stop managing a revision]:applied patch:_hg_revrange' \
+  '*'{-r+,--rev=}'[stop managing a revision]:applied patch:_hg_revrange' \
   '*:unapplied patch:_hg_qdeletable'
 }
 
 _hg_cmd_qdiff() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_diff_opts \
                      $_hg_ignore_space_opts \
   '*:pattern:_hg_files'
 }
 
 _hg_cmd_qfinish() {
   _arguments -s -w : $_hg_global_opts \
   '(--applied -a)'{-a,--applied}'[finish all applied patches]' \
   '*:patch:_hg_qapplied'
 }
 
 _hg_cmd_qfold() {
   _arguments -s -w : $_hg_global_opts $_h_commit_opts \
   '(--keep,-k)'{-k,--keep}'[keep folded patch files]' \
   '(--force -f)'{-f,--force}'[overwrite any local changes]' \
   '--no-backup[do not save backup copies of files]' \
   '*:unapplied patch:_hg_qunapplied'
 }
 
 _hg_cmd_qgoto() {
   _arguments -s -w : $_hg_global_opts \
   '(--force -f)'{-f,--force}'[overwrite any local changes]' \
   '--keep-changes[tolerate non-conflicting local changes]' \
   ':patch:_hg_qseries'
 }
 
 _hg_cmd_qguard() {
   _arguments -s -w : $_hg_global_opts \
   '(--list -l)'{-l,--list}'[list all patches and guards]' \
   '(--none -n)'{-n,--none}'[drop all guards]' \
   ':patch:_hg_qseries' \
   '*:guards:_hg_qguards'
 }
 
 _hg_cmd_qheader() {
   _arguments -s -w : $_hg_global_opts \
   ':patch:_hg_qseries'
 }
 
 _hg_cmd_qimport() {
   _arguments -s -w : $_hg_global_opts $_hg_gitlike_opts \
   '(--existing -e)'{-e,--existing}'[import file in patch dir]' \
   '(--name -n 2)'{-n+,--name}'[patch file name]:name:' \
   '(--force -f)'{-f,--force}'[overwrite existing files]' \
-  '*'{-r+,--rev}'[place existing revisions under mq control]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[place existing revisions under mq control]:revision:_hg_revrange' \
   '(--push -P)'{-P,--push}'[qpush after importing]' \
   '*:patch:_files'
 }
 
 _hg_cmd_qnew() {
   _arguments -s -w : $_hg_global_opts $_hg_commit_opts $_hg_date_user_opts $_hg_gitlike_opts \
   ':patch:'
 }
 
 _hg_cmd_qnext() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts
 }
 
 _hg_cmd_qpop() {
   _arguments -s -w : $_hg_global_opts \
   '(--all -a :)'{-a,--all}'[pop all patches]' \
   '(--force -f)'{-f,--force}'[forget any local changes]' \
   '--keep-changes[tolerate non-conflicting local changes]' \
   '--no-backup[do not save backup copies of files]' \
   ':patch:_hg_qapplied'
 }
 
 _hg_cmd_qprev() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts
 }
 
 _hg_cmd_qpush() {
   _arguments -s -w : $_hg_global_opts \
   '(--all -a :)'{-a,--all}'[apply all patches]' \
   '(--list -l)'{-l,--list}'[list patch name in commit text]' \
   '(--force -f)'{-f,--force}'[apply if the patch has rejects]' \
   '(--exact -e)'{-e,--exact}'[apply the target patch to its recorded parent]' \
   '--move[reorder patch series and apply only the patch]' \
   '--keep-changes[tolerate non-conflicting local changes]' \
   '--no-backup[do not save backup copies of files]' \
   ':patch:_hg_qunapplied'
 }
 
 _hg_cmd_qrefresh() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_commit_opts $_hg_gitlike_opts \
   '(--short -s)'{-s,--short}'[short refresh]' \
   '*:files:_hg_files'
 }
 
 _hg_cmd_qrename() {
   _arguments -s -w : $_hg_global_opts \
   ':patch:_hg_qunapplied' \
   ':destination:'
 }
 
 _hg_cmd_qselect() {
   _arguments -s -w : $_hg_global_opts \
   '(--none -n :)'{-n,--none}'[disable all guards]' \
   '(--series -s :)'{-s,--series}'[list all guards in series file]' \
   '--pop[pop to before first guarded applied patch]' \
   '--reapply[pop and reapply patches]' \
   '*:guards:_hg_qguards'
 }
 
 _hg_cmd_qseries() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts \
   '(--missing -m)'{-m,--missing}'[print patches not in series]'
 }
 
 _hg_cmd_qunapplied() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts \
   '(--first -1)'{-1,--first}'[show only the first patch]'
 }
 
 _hg_cmd_qtop() {
   _arguments -s -w : $_hg_global_opts $_hg_qseries_opts
 }
 
 _hg_cmd_strip() {
   _arguments -s -w : $_hg_global_opts \
   '(--force -f)'{-f,--force}'[force removal, discard uncommitted changes, no backup]' \
   '(--no-backup -n)'{-n,--no-backup}'[no backups]' \
   '(--keep -k)'{-k,--keep}'[do not modify working copy during strip]' \
-  '(--bookmark -B)'{-B+,--bookmark}'[remove revs only reachable from given bookmark]:bookmark:_hg_bookmarks' \
-  '(--rev -r)'{-r+,--rev}'[revision]:revision:_hg_labels' \
+  '(--bookmark -B)'{-B+,--bookmark=}'[remove revs only reachable from given bookmark]:bookmark:_hg_bookmarks' \
+  '(--rev -r)'{-r+,--rev=}'[revision]:revision:_hg_labels' \
   ':revision:_hg_labels'
 }
 
 # Patchbomb
 _hg_cmd_email() {
   _arguments -s -w : $_hg_global_opts $_hg_remote_opts $_hg_gitlike_opts \
   '--plain[omit hg patch header]' \
   '--body[send patches as inline message text (default)]' \
   '(--outgoing -o)'{-o,--outgoing}'[send changes not found in the target repository]' \
   '(--bundle -b)'{-b,--bundle}'[send changes not in target as a binary bundle]' \
   '--bundlename[name of the bundle attachment file (default: bundle)]:' \
-  '*'{-r+,--rev}'[search in given revision range]:revision:_hg_revrange' \
+  '*'{-r+,--rev=}'[search in given revision range]:revision:_hg_revrange' \
   '--force[run even when remote repository is unrelated (with -b/--bundle)]' \
   '*--base[a base changeset to specify instead of a destination (with -b/--bundle)]:revision:_hg_labels' \
   '--intro[send an introduction email for a single patch]' \
   '(--inline -i --attach -a)'{-a,--attach}'[send patches as attachments]' \
   '(--attach -a --inline -i)'{-i,--inline}'[send patches as inline attachments]' \
   '*--bcc[email addresses of blind carbon copy recipients]:email:' \
   '*'{-c+,--cc}'[email addresses of copy recipients]:email:' \
   '(--diffstat -d)'{-d,--diffstat}'[add diffstat output to messages]' \
   '--date[use the given date as the sending date]:date:' \
   '--desc[use the given file as the series description]:files:_files' \
   '(--from -f)'{-f,--from}'[email address of sender]:email:' \
   '(--test -n)'{-n,--test}'[print messages that would be sent]' \
   '(--mbox -m)'{-m,--mbox}'[write messages to mbox file instead of sending them]:file:' \
   '*--reply-to[email addresses replies should be sent to]:email:' \
   '(--subject -s)'{-s,--subject}'[subject of first message (intro or single patch)]:subject:' \
   '--in-reply-to[message identifier to reply to]:msgid:' \
   '*--flag[flags to add in subject prefixes]:flag:' \
   '*'{-t,--to}'[email addresses of recipients]:email:' \
   ':revision:_hg_revrange'
 }
 
 # Rebase
 _hg_cmd_rebase() {
   _arguments -s -w : $_hg_global_opts $_hg_commit_opts $_hg_mergetool_opts \
-  '*'{-r,--rev}'[rebase these revisions]:revision:_hg_revrange' \
-  '(--source -s)'{-s+,--source}'[rebase from the specified changeset]:revision:_hg_labels' \
-  '(--base -b)'{-b+,--base}'[rebase from the base of the specified changeset]:revision:_hg_labels' \
-  '(--dest -d)'{-d+,--dest}'[rebase onto the specified changeset]:revision:_hg_labels' \
+  '*'{-r+,--rev=}'[rebase these revisions]:revision:_hg_revrange' \
+  '(--source -s)'{-s+,--source=}'[rebase from the specified changeset]:revision:_hg_labels' \
+  '(--base -b)'{-b+,--base=}'[rebase from the base of the specified changeset]:revision:_hg_labels' \
+  '(--dest -d)'{-d+,--dest=}'[rebase onto the specified changeset]:revision:_hg_labels' \
   '--collapse[collapse the rebased changeset]' \
   '--keep[keep original changeset]' \
   '--keepbranches[keep original branch name]' \
   '(--continue -c)'{-c,--continue}'[continue an interrupted rebase]' \
   '(--abort -a)'{-a,--abort}'[abort an interrupted rebase]' \
 }
 
 # Record
 _hg_cmd_record() {
   _arguments -s -w : $_hg_global_opts $_hg_commit_opts $_hg_pat_opts \
                      $_hg_ignore_space_opts $_hg_subrepos_opts \
   '(--addremove -A)'{-A,--addremove}'[mark new/missing files as added/removed before committing]' \
   '--close-branch[mark a branch as closed, hiding it from the branch list]' \
   '--amend[amend the parent of the working dir]' \
-  '(--date -d)'{-d+,--date}'[record the specified date as commit date]:date:' \
-  '(--user -u)'{-u+,--user}'[record the specified user as committer]:user:'
+  '(--date -d)'{-d+,--date=}'[record the specified date as commit date]:date:' \
+  '(--user -u)'{-u+,--user=}'[record the specified user as committer]:user:'
 }
 
 _hg_cmd_qrecord() {
   _arguments -s -w : $_hg_global_opts $_hg_commit_opts $_hg_date_user_opts $_hg_gitlike_opts \
                      $_hg_pat_opts $_hg_ignore_space_opts $_hg_subrepos_opts
 }
 
 # Convert
 _hg_cmd_convert() {
 _arguments -s -w : $_hg_global_opts \
   '(--source-type -s)'{-s,--source-type}'[source repository type]' \
   '(--dest-type -d)'{-d,--dest-type}'[destination repository type]' \
-  '(--rev -r)'{-r+,--rev}'[import up to target revision]:revision:' \
-  '(--authormap -A)'{-A+,--authormap}'[remap usernames using this file]:file:_files' \
+  '(--rev -r)'{-r+,--rev=}'[import up to target revision]:revision:' \
+  '(--authormap -A)'{-A+,--authormap=}'[remap usernames using this file]:file:_files' \
   '--filemap[remap file names using contents of file]:file:_files' \
   '--splicemap[splice synthesized history into place]:file:_files' \
   '--branchmap[change branch names while converting]:file:_files' \
   '--branchsort[try to sort changesets by branches]' \
   '--datesort[try to sort changesets by date]' \
   '--sourcesort[preserve source changesets order]'
 }
 
 # Graphlog
 _hg_cmd_glog() {
   _hg_cmd_log $@
 }
 
 # Purge
 _hg_cmd_purge() {
   _arguments -s -w : $_hg_global_opts $_hg_pat_opts $_hg_subrepos_opts \
   '(--abort-on-err -a)'{-a,--abort-on-err}'[abort if an error occurs]' \
   '--all[purge ignored files too]' \
   '(--print -p)'{-p,--print}'[print filenames instead of deleting them]' \
   '(--print0 -0)'{-0,--print0}'[end filenames with NUL, for use with xargs (implies -p/--print)]'
 }
 
 _hg "$@"

doc/hgmanpage.py

@@ -1,1115 +1,1114 b''
 # -*- coding: utf-8 -*-
 # $Id: manpage.py 6110 2009-08-31 14:40:33Z grubert $
 # Author: Engelbert Gruber <[e-mail]>
 # Copyright: This module is put into the public domain.
 
 """
 Simple man page writer for reStructuredText.
 
 Man pages (short for "manual pages") contain system documentation on unix-like
 systems. The pages are grouped in numbered sections:
 
  1 executable programs and shell commands
  2 system calls
  3 library functions
  4 special files
  5 file formats
  6 games
  7 miscellaneous
  8 system administration
 
 Man pages are written in *troff*, a text file formatting system.
 
 See http://www.tldp.org/HOWTO/Man-Page for a start.
 
 Man pages have no subsections only parts.
 Standard parts
 
   NAME ,
   SYNOPSIS ,
   DESCRIPTION ,
   OPTIONS ,
   FILES ,
   SEE ALSO ,
   BUGS ,
 
 and
 
   AUTHOR .
 
 A unix-like system keeps an index of the DESCRIPTIONs, which is accesable
 by the command whatis or apropos.
 
 """
 from __future__ import absolute_import
 
 __docformat__ = 'reStructuredText'
 
 import inspect
 import re
 
 from docutils import (
     languages,
     nodes,
     writers,
 )
 try:
     import roman
 except ImportError:
     from docutils.utils import roman
-import inspect
 
 FIELD_LIST_INDENT = 7
 DEFINITION_LIST_INDENT = 7
 OPTION_LIST_INDENT = 7
 BLOCKQOUTE_INDENT = 3.5
 
 # Define two macros so man/roff can calculate the
 # indent/unindent margins by itself
 MACRO_DEF = (r""".
 .nr rst2man-indent-level 0
 .
 .de1 rstReportMargin
 \\$1 \\n[an-margin]
 level \\n[rst2man-indent-level]
 level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
 -
 \\n[rst2man-indent0]
 \\n[rst2man-indent1]
 \\n[rst2man-indent2]
 ..
 .de1 INDENT
 .\" .rstReportMargin pre:
 . RS \\$1
 . nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
 . nr rst2man-indent-level +1
 .\" .rstReportMargin post:
 ..
 .de UNINDENT
 . RE
 .\" indent \\n[an-margin]
 .\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .nr rst2man-indent-level -1
 .\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .in \\n[rst2man-indent\\n[rst2man-indent-level]]u
 ..
 """)
 
 class Writer(writers.Writer):
 
     supported = ('manpage')
     """Formats this writer supports."""
 
     output = None
     """Final translated form of `document`."""
 
     def __init__(self):
         writers.Writer.__init__(self)
         self.translator_class = Translator
 
     def translate(self):
         visitor = self.translator_class(self.document)
         self.document.walkabout(visitor)
         self.output = visitor.astext()
 
 
 class Table(object):
     def __init__(self):
         self._rows = []
         self._options = ['center']
         self._tab_char = '\t'
         self._coldefs = []
     def new_row(self):
         self._rows.append([])
     def append_separator(self, separator):
         """Append the separator for table head."""
         self._rows.append([separator])
     def append_cell(self, cell_lines):
         """cell_lines is an array of lines"""
         start = 0
         if len(cell_lines) > 0 and cell_lines[0] == '.sp\n':
             start = 1
         self._rows[-1].append(cell_lines[start:])
         if len(self._coldefs) < len(self._rows[-1]):
             self._coldefs.append('l')
     def _minimize_cell(self, cell_lines):
         """Remove leading and trailing blank and ``.sp`` lines"""
         while (cell_lines and cell_lines[0] in ('\n', '.sp\n')):
             del cell_lines[0]
         while (cell_lines and cell_lines[-1] in ('\n', '.sp\n')):
             del cell_lines[-1]
     def as_list(self):
         text = ['.TS\n']
         text.append(' '.join(self._options) + ';\n')
         text.append('|%s|.\n' % ('|'.join(self._coldefs)))
         for row in self._rows:
             # row = array of cells. cell = array of lines.
             text.append('_\n')       # line above
             text.append('T{\n')
             for i in range(len(row)):
                 cell = row[i]
                 self._minimize_cell(cell)
                 text.extend(cell)
                 if not text[-1].endswith('\n'):
                     text[-1] += '\n'
                 if i < len(row) - 1:
                     text.append('T}'+self._tab_char+'T{\n')
                 else:
                     text.append('T}\n')
         text.append('_\n')
         text.append('.TE\n')
         return text
 
 class Translator(nodes.NodeVisitor):
     """"""
 
     words_and_spaces = re.compile(r'\S+| +|\n')
     document_start = """Man page generated from reStructuredText."""
 
     def __init__(self, document):
         nodes.NodeVisitor.__init__(self, document)
         self.settings = settings = document.settings
         lcode = settings.language_code
         arglen = len(inspect.getargspec(languages.get_language)[0])
         if arglen == 2:
             self.language = languages.get_language(lcode,
                                                    self.document.reporter)
         else:
             self.language = languages.get_language(lcode)
         self.head = []
         self.body = []
         self.foot = []
         self.section_level = 0
         self.context = []
         self.topic_class = ''
         self.colspecs = []
         self.compact_p = 1
         self.compact_simple = None
         # the list style "*" bullet or "#" numbered
         self._list_char = []
         # writing the header .TH and .SH NAME is postboned after
         # docinfo.
         self._docinfo = {
                 "title" : "", "title_upper": "",
                 "subtitle" : "",
                 "manual_section" : "", "manual_group" : "",
                 "author" : [],
                 "date" : "",
                 "copyright" : "",
                 "version" : "",
                     }
         self._docinfo_keys = []     # a list to keep the sequence as in source.
         self._docinfo_names = {}    # to get name from text not normalized.
         self._in_docinfo = None
         self._active_table = None
         self._in_literal = False
         self.header_written = 0
         self._line_block = 0
         self.authors = []
         self.section_level = 0
         self._indent = [0]
         # central definition of simple processing rules
         # what to output on : visit, depart
         # Do not use paragraph requests ``.PP`` because these set indentation.
         # use ``.sp``. Remove superfluous ``.sp`` in ``astext``.
         #
         # Fonts are put on a stack, the top one is used.
         # ``.ft P`` or ``\\fP`` pop from stack.
         # ``B`` bold, ``I`` italic, ``R`` roman should be available.
         # Hopefully ``C`` courier too.
         self.defs = {
                 'indent' : ('.INDENT %.1f\n', '.UNINDENT\n'),
                 'definition_list_item' : ('.TP', ''),
                 'field_name' : ('.TP\n.B ', '\n'),
                 'literal' : ('\\fB', '\\fP'),
                 'literal_block' : ('.sp\n.nf\n.ft C\n', '\n.ft P\n.fi\n'),
 
                 'option_list_item' : ('.TP\n', ''),
 
                 'reference' : (r'\%', r'\:'),
                 'emphasis': ('\\fI', '\\fP'),
                 'strong' : ('\\fB', '\\fP'),
                 'term' : ('\n.B ', '\n'),
                 'title_reference' : ('\\fI', '\\fP'),
 
                 'topic-title' : ('.SS ',),
                 'sidebar-title' : ('.SS ',),
 
                 'problematic' : ('\n.nf\n', '\n.fi\n'),
                     }
         # NOTE don't specify the newline before a dot-command, but ensure
         # it is there.
 
     def comment_begin(self, text):
         """Return commented version of the passed text WITHOUT end of
         line/comment."""
         prefix = '.\\" '
         out_text = ''.join(
             [(prefix + in_line + '\n')
             for in_line in text.split('\n')])
         return out_text
 
     def comment(self, text):
         """Return commented version of the passed text."""
         return self.comment_begin(text)+'.\n'
 
     def ensure_eol(self):
         """Ensure the last line in body is terminated by new line."""
         if self.body[-1][-1] != '\n':
             self.body.append('\n')
 
     def astext(self):
         """Return the final formatted document as a string."""
         if not self.header_written:
             # ensure we get a ".TH" as viewers require it.
             self.head.append(self.header())
         # filter body
         for i in xrange(len(self.body) - 1, 0, -1):
             # remove superfluous vertical gaps.
             if self.body[i] == '.sp\n':
                 if self.body[i - 1][:4] in ('.BI ','.IP '):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1][:3] == '.B ' and
                     self.body[i - 2][:4] == '.TP\n'):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1] == '\n' and
                     self.body[i - 2][0] != '.' and
                     (self.body[i - 3][:7] == '.TP\n.B '
                         or self.body[i - 3][:4] == '\n.B ')
                      ):
                     self.body[i] = '.\n'
         return ''.join(self.head + self.body + self.foot)
 
     def deunicode(self, text):
         text = text.replace(u'\xa0', '\\ ')
         text = text.replace(u'\u2020', '\\(dg')
         return text
 
     def visit_Text(self, node):
         text = node.astext()
         text = text.replace('\\','\\e')
         replace_pairs = [
-            (u'-', ur'\-'),
-            (u'\'', ur'\(aq'),
-            (u'´', ur'\''),
-            (u'`', ur'\(ga'),
+            (u'-', u'\\-'),
+            (u"'", u'\\(aq'),
+            (u'´', u"\\'"),
+            (u'`', u'\\(ga'),
             ]
         for (in_char, out_markup) in replace_pairs:
             text = text.replace(in_char, out_markup)
         # unicode
         text = self.deunicode(text)
         if self._in_literal:
             # prevent interpretation of "." at line start
             if text[0] == '.':
                 text = '\\&' + text
             text = text.replace('\n.', '\n\\&.')
         self.body.append(text)
 
     def depart_Text(self, node):
         pass
 
     def list_start(self, node):
         class enum_char(object):
             enum_style = {
                     'bullet'     : '\\(bu',
                     'emdash'     : '\\(em',
                      }
 
             def __init__(self, style):
                 self._style = style
                 if 'start' in node:
                     self._cnt = node['start'] - 1
                 else:
                     self._cnt = 0
                 self._indent = 2
                 if style == 'arabic':
                     # indentation depends on number of children
                     # and start value.
                     self._indent = len(str(len(node.children)))
                     self._indent += len(str(self._cnt)) + 1
                 elif style == 'loweralpha':
                     self._cnt += ord('a') - 1
                     self._indent = 3
                 elif style == 'upperalpha':
                     self._cnt += ord('A') - 1
                     self._indent = 3
                 elif style.endswith('roman'):
                     self._indent = 5
 
             def next(self):
                 if self._style == 'bullet':
                     return self.enum_style[self._style]
                 elif self._style == 'emdash':
                     return self.enum_style[self._style]
                 self._cnt += 1
                 # TODO add prefix postfix
                 if self._style == 'arabic':
                     return "%d." % self._cnt
                 elif self._style in ('loweralpha', 'upperalpha'):
                     return "%c." % self._cnt
                 elif self._style.endswith('roman'):
                     res = roman.toRoman(self._cnt) + '.'
                     if self._style.startswith('upper'):
                         return res.upper()
                     return res.lower()
                 else:
                     return "%d." % self._cnt
             def get_width(self):
                 return self._indent
             def __repr__(self):
                 return 'enum_style-%s' % list(self._style)
 
         if 'enumtype' in node:
             self._list_char.append(enum_char(node['enumtype']))
         else:
             self._list_char.append(enum_char('bullet'))
         if len(self._list_char) > 1:
             # indent nested lists
             self.indent(self._list_char[-2].get_width())
         else:
             self.indent(self._list_char[-1].get_width())
 
     def list_end(self):
         self.dedent()
         self._list_char.pop()
 
     def header(self):
         tmpl = (".TH %(title_upper)s %(manual_section)s"
                 " \"%(date)s\" \"%(version)s\" \"%(manual_group)s\"\n"
                 ".SH NAME\n"
                 "%(title)s \- %(subtitle)s\n")
         return tmpl % self._docinfo
 
     def append_header(self):
         """append header with .TH and .SH NAME"""
         # NOTE before everything
         # .TH title_upper section date source manual
         if self.header_written:
             return
         self.body.append(self.header())
         self.body.append(MACRO_DEF)
         self.header_written = 1
 
     def visit_address(self, node):
         self.visit_docinfo_item(node, 'address')
 
     def depart_address(self, node):
         pass
 
     def visit_admonition(self, node, name=None):
         if name:
             self.body.append('.IP %s\n' %
                         self.language.labels.get(name, name))
 
     def depart_admonition(self, node):
         self.body.append('.RE\n')
 
     def visit_attention(self, node):
         self.visit_admonition(node, 'attention')
 
     depart_attention = depart_admonition
 
     def visit_docinfo_item(self, node, name):
         if name == 'author':
             self._docinfo[name].append(node.astext())
         else:
             self._docinfo[name] = node.astext()
         self._docinfo_keys.append(name)
         raise nodes.SkipNode()
 
     def depart_docinfo_item(self, node):
         pass
 
     def visit_author(self, node):
         self.visit_docinfo_item(node, 'author')
 
     depart_author = depart_docinfo_item
 
     def visit_authors(self, node):
         # _author is called anyway.
         pass
 
     def depart_authors(self, node):
         pass
 
     def visit_block_quote(self, node):
         # BUG/HACK: indent always uses the _last_ indentation,
         # thus we need two of them.
         self.indent(BLOCKQOUTE_INDENT)
         self.indent(0)
 
     def depart_block_quote(self, node):
         self.dedent()
         self.dedent()
 
     def visit_bullet_list(self, node):
         self.list_start(node)
 
     def depart_bullet_list(self, node):
         self.list_end()
 
     def visit_caption(self, node):
         pass
 
     def depart_caption(self, node):
         pass
 
     def visit_caution(self, node):
         self.visit_admonition(node, 'caution')
 
     depart_caution = depart_admonition
 
     def visit_citation(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % num)
 
     def depart_citation(self, node):
         pass
 
     def visit_citation_reference(self, node):
         self.body.append('['+node.astext()+']')
         raise nodes.SkipNode()
 
     def visit_classifier(self, node):
         pass
 
     def depart_classifier(self, node):
         pass
 
     def visit_colspec(self, node):
         self.colspecs.append(node)
 
     def depart_colspec(self, node):
         pass
 
     def write_colspecs(self):
         self.body.append("%s.\n" % ('L '*len(self.colspecs)))
 
     def visit_comment(self, node,
                       sub=re.compile('-(?=-)').sub):
         self.body.append(self.comment(node.astext()))
         raise nodes.SkipNode()
 
     def visit_contact(self, node):
         self.visit_docinfo_item(node, 'contact')
 
     depart_contact = depart_docinfo_item
 
     def visit_container(self, node):
         pass
 
     def depart_container(self, node):
         pass
 
     def visit_compound(self, node):
         pass
 
     def depart_compound(self, node):
         pass
 
     def visit_copyright(self, node):
         self.visit_docinfo_item(node, 'copyright')
 
     def visit_danger(self, node):
         self.visit_admonition(node, 'danger')
 
     depart_danger = depart_admonition
 
     def visit_date(self, node):
         self.visit_docinfo_item(node, 'date')
 
     def visit_decoration(self, node):
         pass
 
     def depart_decoration(self, node):
         pass
 
     def visit_definition(self, node):
         pass
 
     def depart_definition(self, node):
         pass
 
     def visit_definition_list(self, node):
         self.indent(DEFINITION_LIST_INDENT)
 
     def depart_definition_list(self, node):
         self.dedent()
 
     def visit_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][0])
 
     def depart_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][1])
 
     def visit_description(self, node):
         pass
 
     def depart_description(self, node):
         pass
 
     def visit_docinfo(self, node):
         self._in_docinfo = 1
 
     def depart_docinfo(self, node):
         self._in_docinfo = None
         # NOTE nothing should be written before this
         self.append_header()
 
     def visit_doctest_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_doctest_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_document(self, node):
         # no blank line between comment and header.
         self.body.append(self.comment(self.document_start).rstrip()+'\n')
         # writing header is postboned
         self.header_written = 0
 
     def depart_document(self, node):
         if self._docinfo['author']:
             self.body.append('.SH AUTHOR\n%s\n'
                     % ', '.join(self._docinfo['author']))
         skip = ('author', 'copyright', 'date',
                 'manual_group', 'manual_section',
                 'subtitle',
                 'title', 'title_upper', 'version')
         for name in self._docinfo_keys:
             if name == 'address':
                 self.body.append("\n%s:\n%s%s.nf\n%s\n.fi\n%s%s" % (
                                     self.language.labels.get(name, name),
                                     self.defs['indent'][0] % 0,
                                     self.defs['indent'][0] % BLOCKQOUTE_INDENT,
                                     self._docinfo[name],
                                     self.defs['indent'][1],
                                     self.defs['indent'][1]))
             elif name not in skip:
                 if name in self._docinfo_names:
                     label = self._docinfo_names[name]
                 else:
                     label = self.language.labels.get(name, name)
                 self.body.append("\n%s: %s\n" % (label, self._docinfo[name]))
         if self._docinfo['copyright']:
             self.body.append('.SH COPYRIGHT\n%s\n'
                     % self._docinfo['copyright'])
         self.body.append(self.comment(
                         'Generated by docutils manpage writer.\n'))
 
     def visit_emphasis(self, node):
         self.body.append(self.defs['emphasis'][0])
 
     def depart_emphasis(self, node):
         self.body.append(self.defs['emphasis'][1])
 
     def visit_entry(self, node):
         # a cell in a table row
         if 'morerows' in node:
             self.document.reporter.warning('"table row spanning" not supported',
                     base_node=node)
         if 'morecols' in node:
             self.document.reporter.warning(
                     '"table cell spanning" not supported', base_node=node)
         self.context.append(len(self.body))
 
     def depart_entry(self, node):
         start = self.context.pop()
         self._active_table.append_cell(self.body[start:])
         del self.body[start:]
 
     def visit_enumerated_list(self, node):
         self.list_start(node)
 
     def depart_enumerated_list(self, node):
         self.list_end()
 
     def visit_error(self, node):
         self.visit_admonition(node, 'error')
 
     depart_error = depart_admonition
 
     def visit_field(self, node):
         pass
 
     def depart_field(self, node):
         pass
 
     def visit_field_body(self, node):
         if self._in_docinfo:
             name_normalized = self._field_name.lower().replace(" ","_")
             self._docinfo_names[name_normalized] = self._field_name
             self.visit_docinfo_item(node, name_normalized)
             raise nodes.SkipNode()
 
     def depart_field_body(self, node):
         pass
 
     def visit_field_list(self, node):
         self.indent(FIELD_LIST_INDENT)
 
     def depart_field_list(self, node):
         self.dedent()
 
     def visit_field_name(self, node):
         if self._in_docinfo:
             self._field_name = node.astext()
             raise nodes.SkipNode()
         else:
             self.body.append(self.defs['field_name'][0])
 
     def depart_field_name(self, node):
         self.body.append(self.defs['field_name'][1])
 
     def visit_figure(self, node):
         self.indent(2.5)
         self.indent(0)
 
     def depart_figure(self, node):
         self.dedent()
         self.dedent()
 
     def visit_footer(self, node):
         self.document.reporter.warning('"footer" not supported',
                 base_node=node)
 
     def depart_footer(self, node):
         pass
 
     def visit_footnote(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % self.deunicode(num))
 
     def depart_footnote(self, node):
         pass
 
     def footnote_backrefs(self, node):
         self.document.reporter.warning('"footnote_backrefs" not supported',
                 base_node=node)
 
     def visit_footnote_reference(self, node):
         self.body.append('['+self.deunicode(node.astext())+']')
         raise nodes.SkipNode()
 
     def depart_footnote_reference(self, node):
         pass
 
     def visit_generated(self, node):
         pass
 
     def depart_generated(self, node):
         pass
 
     def visit_header(self, node):
         raise NotImplementedError(node.astext())
 
     def depart_header(self, node):
         pass
 
     def visit_hint(self, node):
         self.visit_admonition(node, 'hint')
 
     depart_hint = depart_admonition
 
     def visit_subscript(self, node):
         self.body.append('\\s-2\\d')
 
     def depart_subscript(self, node):
         self.body.append('\\u\\s0')
 
     def visit_superscript(self, node):
         self.body.append('\\s-2\\u')
 
     def depart_superscript(self, node):
         self.body.append('\\d\\s0')
 
     def visit_attribution(self, node):
         self.body.append('\\(em ')
 
     def depart_attribution(self, node):
         self.body.append('\n')
 
     def visit_image(self, node):
         self.document.reporter.warning('"image" not supported',
                 base_node=node)
         text = []
         if 'alt' in node.attributes:
             text.append(node.attributes['alt'])
         if 'uri' in node.attributes:
             text.append(node.attributes['uri'])
         self.body.append('[image: %s]\n' % ('/'.join(text)))
         raise nodes.SkipNode()
 
     def visit_important(self, node):
         self.visit_admonition(node, 'important')
 
     depart_important = depart_admonition
 
     def visit_label(self, node):
         # footnote and citation
         if (isinstance(node.parent, nodes.footnote)
             or isinstance(node.parent, nodes.citation)):
             raise nodes.SkipNode()
         self.document.reporter.warning('"unsupported "label"',
                 base_node=node)
         self.body.append('[')
 
     def depart_label(self, node):
         self.body.append(']\n')
 
     def visit_legend(self, node):
         pass
 
     def depart_legend(self, node):
         pass
 
     # WHAT should we use .INDENT, .UNINDENT ?
     def visit_line_block(self, node):
         self._line_block += 1
         if self._line_block == 1:
             self.body.append('.sp\n')
             self.body.append('.nf\n')
         else:
             self.body.append('.in +2\n')
 
     def depart_line_block(self, node):
         self._line_block -= 1
         if self._line_block == 0:
             self.body.append('.fi\n')
             self.body.append('.sp\n')
         else:
             self.body.append('.in -2\n')
 
     def visit_line(self, node):
         pass
 
     def depart_line(self, node):
         self.body.append('\n')
 
     def visit_list_item(self, node):
         # man 7 man argues to use ".IP" instead of ".TP"
         self.body.append('.IP %s %d\n' % (
                 next(self._list_char[-1]),
                 self._list_char[-1].get_width(),))
 
     def depart_list_item(self, node):
         pass
 
     def visit_literal(self, node):
         self.body.append(self.defs['literal'][0])
 
     def depart_literal(self, node):
         self.body.append(self.defs['literal'][1])
 
     def visit_literal_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_literal_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_meta(self, node):
         raise NotImplementedError(node.astext())
 
     def depart_meta(self, node):
         pass
 
     def visit_note(self, node):
         self.visit_admonition(node, 'note')
 
     depart_note = depart_admonition
 
     def indent(self, by=0.5):
         # if we are in a section ".SH" there already is a .RS
         step = self._indent[-1]
         self._indent.append(by)
         self.body.append(self.defs['indent'][0] % step)
 
     def dedent(self):
         self._indent.pop()
         self.body.append(self.defs['indent'][1])
 
     def visit_option_list(self, node):
         self.indent(OPTION_LIST_INDENT)
 
     def depart_option_list(self, node):
         self.dedent()
 
     def visit_option_list_item(self, node):
         # one item of the list
         self.body.append(self.defs['option_list_item'][0])
 
     def depart_option_list_item(self, node):
         self.body.append(self.defs['option_list_item'][1])
 
     def visit_option_group(self, node):
         # as one option could have several forms it is a group
         # options without parameter bold only, .B, -v
         # options with parameter bold italic, .BI, -f file
         #
         # we do not know if .B or .BI
         self.context.append('.B')           # blind guess
         self.context.append(len(self.body)) # to be able to insert later
         self.context.append(0)              # option counter
 
     def depart_option_group(self, node):
         self.context.pop()  # the counter
         start_position = self.context.pop()
         text = self.body[start_position:]
         del self.body[start_position:]
         self.body.append('%s%s\n' % (self.context.pop(), ''.join(text)))
 
     def visit_option(self, node):
         # each form of the option will be presented separately
         if self.context[-1] > 0:
             self.body.append(', ')
         if self.context[-3] == '.BI':
             self.body.append('\\')
         self.body.append(' ')
 
     def depart_option(self, node):
         self.context[-1] += 1
 
     def visit_option_string(self, node):
         # do not know if .B or .BI
         pass
 
     def depart_option_string(self, node):
         pass
 
     def visit_option_argument(self, node):
         self.context[-3] = '.BI' # bold/italic alternate
         if node['delimiter'] != ' ':
             self.body.append('\\fB%s ' % node['delimiter'])
         elif self.body[len(self.body) - 1].endswith('='):
             # a blank only means no blank in output, just changing font
             self.body.append(' ')
         else:
             # blank backslash blank, switch font then a blank
             self.body.append(' \\ ')
 
     def depart_option_argument(self, node):
         pass
 
     def visit_organization(self, node):
         self.visit_docinfo_item(node, 'organization')
 
     def depart_organization(self, node):
         pass
 
     def visit_paragraph(self, node):
         # ``.PP`` : Start standard indented paragraph.
         # ``.LP`` : Start block paragraph, all except the first.
         # ``.P [type]``  : Start paragraph type.
         # NOTE don't use paragraph starts because they reset indentation.
         # ``.sp`` is only vertical space
         self.ensure_eol()
         self.body.append('.sp\n')
 
     def depart_paragraph(self, node):
         self.body.append('\n')
 
     def visit_problematic(self, node):
         self.body.append(self.defs['problematic'][0])
 
     def depart_problematic(self, node):
         self.body.append(self.defs['problematic'][1])
 
     def visit_raw(self, node):
         if node.get('format') == 'manpage':
             self.body.append(node.astext() + "\n")
         # Keep non-manpage raw text out of output:
         raise nodes.SkipNode()
 
     def visit_reference(self, node):
         """E.g. link or email address."""
         self.body.append(self.defs['reference'][0])
 
     def depart_reference(self, node):
         self.body.append(self.defs['reference'][1])
 
     def visit_revision(self, node):
         self.visit_docinfo_item(node, 'revision')
 
     depart_revision = depart_docinfo_item
 
     def visit_row(self, node):
         self._active_table.new_row()
 
     def depart_row(self, node):
         pass
 
     def visit_section(self, node):
         self.section_level += 1
 
     def depart_section(self, node):
         self.section_level -= 1
 
     def visit_status(self, node):
         self.visit_docinfo_item(node, 'status')
 
     depart_status = depart_docinfo_item
 
     def visit_strong(self, node):
         self.body.append(self.defs['strong'][0])
 
     def depart_strong(self, node):
         self.body.append(self.defs['strong'][1])
 
     def visit_substitution_definition(self, node):
         """Internal only."""
         raise nodes.SkipNode()
 
     def visit_substitution_reference(self, node):
         self.document.reporter.warning('"substitution_reference" not supported',
                 base_node=node)
 
     def visit_subtitle(self, node):
         if isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['strong'][0])
         elif isinstance(node.parent, nodes.document):
             self.visit_docinfo_item(node, 'subtitle')
         elif isinstance(node.parent, nodes.section):
             self.body.append(self.defs['strong'][0])
 
     def depart_subtitle(self, node):
         # document subtitle calls SkipNode
         self.body.append(self.defs['strong'][1]+'\n.PP\n')
 
     def visit_system_message(self, node):
         # TODO add report_level
         #if node['level'] < self.document.reporter['writer'].report_level:
         #    Level is too low to display:
         #    raise nodes.SkipNode
         attr = {}
         if node.hasattr('id'):
             attr['name'] = node['id']
         if node.hasattr('line'):
             line = ', line %s' % node['line']
         else:
             line = ''
         self.body.append('.IP "System Message: %s/%s (%s:%s)"\n'
                          % (node['type'], node['level'], node['source'], line))
 
     def depart_system_message(self, node):
         pass
 
     def visit_table(self, node):
         self._active_table = Table()
 
     def depart_table(self, node):
         self.ensure_eol()
         self.body.extend(self._active_table.as_list())
         self._active_table = None
 
     def visit_target(self, node):
         # targets are in-document hyper targets, without any use for man-pages.
         raise nodes.SkipNode()
 
     def visit_tbody(self, node):
         pass
 
     def depart_tbody(self, node):
         pass
 
     def visit_term(self, node):
         self.body.append(self.defs['term'][0])
 
     def depart_term(self, node):
         self.body.append(self.defs['term'][1])
 
     def visit_tgroup(self, node):
         pass
 
     def depart_tgroup(self, node):
         pass
 
     def visit_thead(self, node):
         # MAYBE double line '='
         pass
 
     def depart_thead(self, node):
         # MAYBE double line '='
         pass
 
     def visit_tip(self, node):
         self.visit_admonition(node, 'tip')
 
     depart_tip = depart_admonition
 
     def visit_title(self, node):
         if isinstance(node.parent, nodes.topic):
             self.body.append(self.defs['topic-title'][0])
         elif isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['sidebar-title'][0])
         elif isinstance(node.parent, nodes.admonition):
             self.body.append('.IP "')
         elif self.section_level == 0:
             self._docinfo['title'] = node.astext()
             # document title for .TH
             self._docinfo['title_upper'] = node.astext().upper()
             raise nodes.SkipNode()
         elif self.section_level == 1:
             self.body.append('.SH ')
             for n in node.traverse(nodes.Text):
                 n.parent.replace(n, nodes.Text(n.astext().upper()))
         else:
             self.body.append('.SS ')
 
     def depart_title(self, node):
         if isinstance(node.parent, nodes.admonition):
             self.body.append('"')
         self.body.append('\n')
 
     def visit_title_reference(self, node):
         """inline citation reference"""
         self.body.append(self.defs['title_reference'][0])
 
     def depart_title_reference(self, node):
         self.body.append(self.defs['title_reference'][1])
 
     def visit_topic(self, node):
         pass
 
     def depart_topic(self, node):
         pass
 
     def visit_sidebar(self, node):
         pass
 
     def depart_sidebar(self, node):
         pass
 
     def visit_rubric(self, node):
         pass
 
     def depart_rubric(self, node):
         pass
 
     def visit_transition(self, node):
         # .PP      Begin a new paragraph and reset prevailing indent.
         # .sp N    leaves N lines of blank space.
         # .ce      centers the next line
         self.body.append('\n.sp\n.ce\n----\n')
 
     def depart_transition(self, node):
         self.body.append('\n.ce 0\n.sp\n')
 
     def visit_version(self, node):
         self.visit_docinfo_item(node, 'version')
 
     def visit_warning(self, node):
         self.visit_admonition(node, 'warning')
 
     depart_warning = depart_admonition
 
     def unimplemented_visit(self, node):
         raise NotImplementedError('visiting unimplemented node type: %s'
                                   % node.__class__.__name__)
 
 # vim: set fileencoding=utf-8 et ts=4 ai :

hgext/acl.py

@@ -1,330 +1,330 b''
 # acl.py - changeset access control for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''hooks for controlling repository access
 
 This hook makes it possible to allow or deny write access to given
 branches and paths of a repository when receiving incoming changesets
 via pretxnchangegroup and pretxncommit.
 
 The authorization is matched based on the local user name on the
 system where the hook runs, and not the committer of the original
 changeset (since the latter is merely informative).
 
 The acl hook is best used along with a restricted shell like hgsh,
 preventing authenticating users from doing anything other than pushing
 or pulling. The hook is not safe to use if users have interactive
 shell access, as they can then disable the hook. Nor is it safe if
 remote users share an account, because then there is no way to
 distinguish them.
 
 The order in which access checks are performed is:
 
 1) Deny  list for branches (section ``acl.deny.branches``)
 2) Allow list for branches (section ``acl.allow.branches``)
 3) Deny  list for paths    (section ``acl.deny``)
 4) Allow list for paths    (section ``acl.allow``)
 
 The allow and deny sections take key-value pairs.
 
 Branch-based Access Control
 ---------------------------
 
 Use the ``acl.deny.branches`` and ``acl.allow.branches`` sections to
 have branch-based access control. Keys in these sections can be
 either:
 
 - a branch name, or
 - an asterisk, to match any branch;
 
 The corresponding values can be either:
 
 - a comma-separated list containing users and groups, or
 - an asterisk, to match anyone;
 
 You can add the "!" prefix to a user or group name to invert the sense
 of the match.
 
 Path-based Access Control
 -------------------------
 
 Use the ``acl.deny`` and ``acl.allow`` sections to have path-based
 access control. Keys in these sections accept a subtree pattern (with
 a glob syntax by default). The corresponding values follow the same
 syntax as the other sections above.
 
 Groups
 ------
 
 Group names must be prefixed with an ``@`` symbol. Specifying a group
 name has the same effect as specifying all the users in that group.
 
 You can define group members in the ``acl.groups`` section.
 If a group name is not defined there, and Mercurial is running under
 a Unix-like system, the list of users will be taken from the OS.
 Otherwise, an exception will be raised.
 
 Example Configuration
 ---------------------
 
 ::
 
   [hooks]
 
   # Use this if you want to check access restrictions at commit time
   pretxncommit.acl = python:hgext.acl.hook
 
   # Use this if you want to check access restrictions for pull, push,
   # bundle and serve.
   pretxnchangegroup.acl = python:hgext.acl.hook
 
   [acl]
   # Allow or deny access for incoming changes only if their source is
   # listed here, let them pass otherwise. Source is "serve" for all
   # remote access (http or ssh), "push", "pull" or "bundle" when the
   # related commands are run locally.
   # Default: serve
   sources = serve
 
   [acl.deny.branches]
 
   # Everyone is denied to the frozen branch:
   frozen-branch = *
 
   # A bad user is denied on all branches:
   * = bad-user
 
   [acl.allow.branches]
 
   # A few users are allowed on branch-a:
   branch-a = user-1, user-2, user-3
 
   # Only one user is allowed on branch-b:
   branch-b = user-1
 
   # The super user is allowed on any branch:
   * = super-user
 
   # Everyone is allowed on branch-for-tests:
   branch-for-tests = *
 
   [acl.deny]
   # This list is checked first. If a match is found, acl.allow is not
   # checked. All users are granted access if acl.deny is not present.
   # Format for both lists: glob pattern = user, ..., @group, ...
 
   # To match everyone, use an asterisk for the user:
   # my/glob/pattern = *
 
   # user6 will not have write access to any file:
   ** = user6
 
   # Group "hg-denied" will not have write access to any file:
   ** = @hg-denied
 
   # Nobody will be able to change "DONT-TOUCH-THIS.txt", despite
   # everyone being able to change all other files. See below.
   src/main/resources/DONT-TOUCH-THIS.txt = *
 
   [acl.allow]
   # if acl.allow is not present, all users are allowed by default
   # empty acl.allow = no users allowed
 
   # User "doc_writer" has write access to any file under the "docs"
   # folder:
   docs/** = doc_writer
 
   # User "jack" and group "designers" have write access to any file
   # under the "images" folder:
   images/** = jack, @designers
 
   # Everyone (except for "user6" and "@hg-denied" - see acl.deny above)
   # will have write access to any file under the "resources" folder
   # (except for 1 file. See acl.deny):
   src/main/resources/** = *
 
   .hgtags = release_engineer
 
 Examples using the "!" prefix
 .............................
 
 Suppose there's a branch that only a given user (or group) should be able to
 push to, and you don't want to restrict access to any other branch that may
 be created.
 
 The "!" prefix allows you to prevent anyone except a given user or group to
 push changesets in a given branch or path.
 
 In the examples below, we will:
 1) Deny access to branch "ring" to anyone but user "gollum"
 2) Deny access to branch "lake" to anyone but members of the group "hobbit"
 3) Deny access to a file to anyone but user "gollum"
 
 ::
 
   [acl.allow.branches]
   # Empty
 
   [acl.deny.branches]
 
   # 1) only 'gollum' can commit to branch 'ring';
   # 'gollum' and anyone else can still commit to any other branch.
   ring = !gollum
 
   # 2) only members of the group 'hobbit' can commit to branch 'lake';
   # 'hobbit' members and anyone else can still commit to any other branch.
   lake = !@hobbit
 
   # You can also deny access based on file paths:
 
   [acl.allow]
   # Empty
 
   [acl.deny]
   # 3) only 'gollum' can change the file below;
   # 'gollum' and anyone else can still change any other file.
   /misty/mountains/cave/ring = !gollum
 
 '''
 
 from __future__ import absolute_import
 
 import getpass
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     match,
     util,
 )
 
 urlreq = util.urlreq
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 def _getusers(ui, group):
 
     # First, try to use group definition from section [acl.groups]
     hgrcusers = ui.configlist('acl.groups', group)
     if hgrcusers:
         return hgrcusers
 
     ui.debug('acl: "%s" not defined in [acl.groups]\n' % group)
     # If no users found in group definition, get users from OS-level group
     try:
         return util.groupmembers(group)
     except KeyError:
         raise error.Abort(_("group '%s' is undefined") % group)
 
 def _usermatch(ui, user, usersorgroups):
 
     if usersorgroups == '*':
         return True
 
     for ug in usersorgroups.replace(',', ' ').split():
 
         if ug.startswith('!'):
             # Test for excluded user or group. Format:
             # if ug is a user  name: !username
             # if ug is a group name: !@groupname
             ug = ug[1:]
             if not ug.startswith('@') and user != ug \
                 or ug.startswith('@') and user not in _getusers(ui, ug[1:]):
                 return True
 
         # Test for user or group. Format:
         # if ug is a user  name: username
         # if ug is a group name: @groupname
         elif user == ug \
              or ug.startswith('@') and user in _getusers(ui, ug[1:]):
             return True
 
     return False
 
 def buildmatch(ui, repo, user, key):
     '''return tuple of (match function, list enabled).'''
     if not ui.has_section(key):
         ui.debug('acl: %s not enabled\n' % key)
         return None
 
     pats = [pat for pat, users in ui.configitems(key)
             if _usermatch(ui, user, users)]
     ui.debug('acl: %s enabled, %d entries for user %s\n' %
              (key, len(pats), user))
 
     # Branch-based ACL
     if not repo:
         if pats:
             # If there's an asterisk (meaning "any branch"), always return True;
             # Otherwise, test if b is in pats
             if '*' in pats:
                 return util.always
             return lambda b: b in pats
         return util.never
 
     # Path-based ACL
     if pats:
         return match.match(repo.root, '', pats)
     return util.never
 
 def hook(ui, repo, hooktype, node=None, source=None, **kwargs):
     if hooktype not in ['pretxnchangegroup', 'pretxncommit']:
         raise error.Abort(_('config error - hook type "%s" cannot stop '
                            'incoming changesets nor commits') % hooktype)
     if (hooktype == 'pretxnchangegroup' and
         source not in ui.config('acl', 'sources', 'serve').split()):
         ui.debug('acl: changes have source "%s" - skipping\n' % source)
         return
 
     user = None
     if source == 'serve' and 'url' in kwargs:
         url = kwargs['url'].split(':')
         if url[0] == 'remote' and url[1].startswith('http'):
             user = urlreq.unquote(url[3])
 
     if user is None:
         user = getpass.getuser()
 
     ui.debug('acl: checking access for user "%s"\n' % user)
 
     # deprecated config: acl.config
     cfg = ui.config('acl', 'config')
     if cfg:
         ui.readconfig(cfg, sections=['acl.groups', 'acl.allow.branches',
             'acl.deny.branches', 'acl.allow', 'acl.deny'])
 
     allowbranches = buildmatch(ui, None, user, 'acl.allow.branches')
     denybranches = buildmatch(ui, None, user, 'acl.deny.branches')
     allow = buildmatch(ui, repo, user, 'acl.allow')
     deny = buildmatch(ui, repo, user, 'acl.deny')
 
     for rev in xrange(repo[node], len(repo)):
         ctx = repo[rev]
         branch = ctx.branch()
         if denybranches and denybranches(branch):
             raise error.Abort(_('acl: user "%s" denied on branch "%s"'
                                ' (changeset "%s")')
                                % (user, branch, ctx))
         if allowbranches and not allowbranches(branch):
             raise error.Abort(_('acl: user "%s" not allowed on branch "%s"'
                                ' (changeset "%s")')
                                % (user, branch, ctx))
         ui.debug('acl: branch access granted: "%s" on branch "%s"\n'
         % (ctx, branch))
 
         for f in ctx.files():
             if deny and deny(f):
                 raise error.Abort(_('acl: user "%s" denied on "%s"'
                 ' (changeset "%s")') % (user, f, ctx))
             if allow and not allow(f):
                 raise error.Abort(_('acl: user "%s" not allowed on "%s"'
                 ' (changeset "%s")') % (user, f, ctx))
         ui.debug('acl: path access granted: "%s"\n' % ctx)

hgext/blackbox.py

@@ -1,250 +1,250 b''
 # blackbox.py - log repository events to a file for post-mortem debugging
 #
 # Copyright 2010 Nicolas Dumazet
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """log repository events to a blackbox for debugging
 
 Logs event information to .hg/blackbox.log to help debug and diagnose problems.
 The events that get logged can be configured via the blackbox.track config key.
 
 Examples::
 
   [blackbox]
   track = *
   # dirty is *EXPENSIVE* (slow);
   # each log entry indicates `+` if the repository is dirty, like :hg:`id`.
   dirty = True
   # record the source of log messages
   logsource = True
 
   [blackbox]
   track = command, commandfinish, commandexception, exthook, pythonhook
 
   [blackbox]
   track = incoming
 
   [blackbox]
   # limit the size of a log file
   maxsize = 1.5 MB
   # rotate up to N log files when the current one gets too big
   maxfiles = 3
 
 """
 
 from __future__ import absolute_import
 
 import errno
 import re
 
 from mercurial.i18n import _
 from mercurial.node import hex
 
 from mercurial import (
     cmdutil,
     ui as uimod,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 lastui = None
 
 filehandles = {}
 
 def _openlog(vfs):
     path = vfs.join('blackbox.log')
     if path in filehandles:
         return filehandles[path]
     filehandles[path] = fp = vfs('blackbox.log', 'a')
     return fp
 
 def _closelog(vfs):
     path = vfs.join('blackbox.log')
     fp = filehandles[path]
     del filehandles[path]
     fp.close()
 
 def wrapui(ui):
     class blackboxui(ui.__class__):
         def __init__(self, src=None):
             super(blackboxui, self).__init__(src)
             if src is None:
                 self._partialinit()
             else:
                 self._bbfp = getattr(src, '_bbfp', None)
                 self._bbinlog = False
                 self._bbrepo = getattr(src, '_bbrepo', None)
                 self._bbvfs = getattr(src, '_bbvfs', None)
 
         def _partialinit(self):
             if util.safehasattr(self, '_bbvfs'):
                 return
             self._bbfp = None
             self._bbinlog = False
             self._bbrepo = None
             self._bbvfs = None
 
         def copy(self):
             self._partialinit()
             return self.__class__(self)
 
         @util.propertycache
         def track(self):
             return self.configlist('blackbox', 'track', ['*'])
 
         def _openlogfile(self):
             def rotate(oldpath, newpath):
                 try:
                     self._bbvfs.unlink(newpath)
                 except OSError as err:
                     if err.errno != errno.ENOENT:
                         self.debug("warning: cannot remove '%s': %s\n" %
                                    (newpath, err.strerror))
                 try:
                     if newpath:
                         self._bbvfs.rename(oldpath, newpath)
                 except OSError as err:
                     if err.errno != errno.ENOENT:
                         self.debug("warning: cannot rename '%s' to '%s': %s\n" %
                                    (newpath, oldpath, err.strerror))
 
             fp = _openlog(self._bbvfs)
             maxsize = self.configbytes('blackbox', 'maxsize', 1048576)
             if maxsize > 0:
                 st = self._bbvfs.fstat(fp)
                 if st.st_size >= maxsize:
                     path = fp.name
                     _closelog(self._bbvfs)
                     maxfiles = self.configint('blackbox', 'maxfiles', 7)
                     for i in xrange(maxfiles - 1, 1, -1):
                         rotate(oldpath='%s.%d' % (path, i - 1),
                                newpath='%s.%d' % (path, i))
                     rotate(oldpath=path,
                            newpath=maxfiles > 0 and path + '.1')
                     fp = _openlog(self._bbvfs)
             return fp
 
         def _bbwrite(self, fmt, *args):
             self._bbfp.write(fmt % args)
             self._bbfp.flush()
 
         def log(self, event, *msg, **opts):
             global lastui
             super(blackboxui, self).log(event, *msg, **opts)
             self._partialinit()
 
             if not '*' in self.track and not event in self.track:
                 return
 
             if self._bbfp:
                 ui = self
             elif self._bbvfs:
                 try:
                     self._bbfp = self._openlogfile()
                 except (IOError, OSError) as err:
                     self.debug('warning: cannot write to blackbox.log: %s\n' %
                                err.strerror)
                     del self._bbvfs
                     self._bbfp = None
                 ui = self
             else:
                 # certain ui instances exist outside the context of
                 # a repo, so just default to the last blackbox that
                 # was seen.
                 ui = lastui
 
             if not ui or not ui._bbfp:
                 return
             if not lastui or ui._bbrepo:
                 lastui = ui
             if ui._bbinlog:
                 # recursion guard
                 return
             try:
                 ui._bbinlog = True
                 date = util.datestr(None, '%Y/%m/%d %H:%M:%S')
                 user = util.getuser()
                 pid = str(util.getpid())
                 formattedmsg = msg[0] % msg[1:]
                 rev = '(unknown)'
                 changed = ''
                 if ui._bbrepo:
                     ctx = ui._bbrepo[None]
                     parents = ctx.parents()
                     rev = ('+'.join([hex(p.node()) for p in parents]))
                     if (ui.configbool('blackbox', 'dirty', False) and (
                         any(ui._bbrepo.status()) or
                         any(ctx.sub(s).dirty() for s in ctx.substate)
                     )):
                         changed = '+'
                 if ui.configbool('blackbox', 'logsource', False):
                     src = ' [%s]' % event
                 else:
                     src = ''
                 try:
                     ui._bbwrite('%s %s @%s%s (%s)%s> %s',
                         date, user, rev, changed, pid, src, formattedmsg)
                 except IOError as err:
                     self.debug('warning: cannot write to blackbox.log: %s\n' %
                                err.strerror)
             finally:
                 ui._bbinlog = False
 
         def setrepo(self, repo):
             self._bbfp = None
             self._bbinlog = False
             self._bbrepo = repo
             self._bbvfs = repo.vfs
 
     ui.__class__ = blackboxui
     uimod.ui = blackboxui
 
 def uisetup(ui):
     wrapui(ui)
 
 def reposetup(ui, repo):
     # During 'hg pull' a httppeer repo is created to represent the remote repo.
     # It doesn't have a .hg directory to put a blackbox in, so we don't do
     # the blackbox setup for it.
     if not repo.local():
         return
 
     if util.safehasattr(ui, 'setrepo'):
         ui.setrepo(repo)
 
 @command('^blackbox',
     [('l', 'limit', 10, _('the number of events to show')),
     ],
     _('hg blackbox [OPTION]...'))
 def blackbox(ui, repo, *revs, **opts):
     '''view the recent repository events
     '''
 
     if not repo.vfs.exists('blackbox.log'):
         return
 
     limit = opts.get('limit')
     fp = repo.vfs('blackbox.log', 'r')
     lines = fp.read().split('\n')
 
     count = 0
     output = []
     for line in reversed(lines):
         if count >= limit:
             break
 
         # count the commands by matching lines like: 2013/01/23 19:13:36 root>
         if re.match('^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
             count += 1
         output.append(line)
 
     ui.status('\n'.join(reversed(output)))

hgext/bugzilla.py

@@ -1,928 +1,928 b''
 # bugzilla.py - bugzilla integration for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 # Copyright 2011-4 Jim Hague <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''hooks for integrating with the Bugzilla bug tracker
 
 This hook extension adds comments on bugs in Bugzilla when changesets
 that refer to bugs by Bugzilla ID are seen. The comment is formatted using
 the Mercurial template mechanism.
 
 The bug references can optionally include an update for Bugzilla of the
 hours spent working on the bug. Bugs can also be marked fixed.
 
 Three basic modes of access to Bugzilla are provided:
 
 1. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later.
 
 2. Check data via the Bugzilla XMLRPC interface and submit bug change
    via email to Bugzilla email interface. Requires Bugzilla 3.4 or later.
 
 3. Writing directly to the Bugzilla database. Only Bugzilla installations
    using MySQL are supported. Requires Python MySQLdb.
 
 Writing directly to the database is susceptible to schema changes, and
 relies on a Bugzilla contrib script to send out bug change
 notification emails. This script runs as the user running Mercurial,
 must be run on the host with the Bugzilla install, and requires
 permission to read Bugzilla configuration details and the necessary
 MySQL user and password to have full access rights to the Bugzilla
 database. For these reasons this access mode is now considered
 deprecated, and will not be updated for new Bugzilla versions going
 forward. Only adding comments is supported in this access mode.
 
 Access via XMLRPC needs a Bugzilla username and password to be specified
 in the configuration. Comments are added under that username. Since the
 configuration must be readable by all Mercurial users, it is recommended
 that the rights of that user are restricted in Bugzilla to the minimum
 necessary to add comments. Marking bugs fixed requires Bugzilla 4.0 and later.
 
 Access via XMLRPC/email uses XMLRPC to query Bugzilla, but sends
 email to the Bugzilla email interface to submit comments to bugs.
 The From: address in the email is set to the email address of the Mercurial
 user, so the comment appears to come from the Mercurial user. In the event
 that the Mercurial user email is not recognized by Bugzilla as a Bugzilla
 user, the email associated with the Bugzilla username used to log into
 Bugzilla is used instead as the source of the comment. Marking bugs fixed
 works on all supported Bugzilla versions.
 
 Configuration items common to all access modes:
 
 bugzilla.version
   The access type to use. Values recognized are:
 
   :``xmlrpc``:       Bugzilla XMLRPC interface.
   :``xmlrpc+email``: Bugzilla XMLRPC and email interfaces.
   :``3.0``:          MySQL access, Bugzilla 3.0 and later.
   :``2.18``:         MySQL access, Bugzilla 2.18 and up to but not
                      including 3.0.
   :``2.16``:         MySQL access, Bugzilla 2.16 and up to but not
                      including 2.18.
 
 bugzilla.regexp
   Regular expression to match bug IDs for update in changeset commit message.
   It must contain one "()" named group ``<ids>`` containing the bug
   IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Bug 1234``, ``Bug no. 1234``,
   ``Bug number 1234``, ``Bugs 1234,5678``, ``Bug 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixregexp
   Regular expression to match bug IDs for marking fixed in changeset
   commit message. This must contain a "()" named group ``<ids>` containing
   the bug IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Fixes 1234``, ``Fixes bug 1234``,
   ``Fixes bugs 1234,5678``, ``Fixes 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixstatus
   The status to set a bug to when marking fixed. Default ``RESOLVED``.
 
 bugzilla.fixresolution
   The resolution to set a bug to when marking fixed. Default ``FIXED``.
 
 bugzilla.style
   The style file to use when formatting comments.
 
 bugzilla.template
   Template to use when formatting comments. Overrides style if
   specified. In addition to the usual Mercurial keywords, the
   extension specifies:
 
   :``{bug}``:     The Bugzilla bug ID.
   :``{root}``:    The full pathname of the Mercurial repository.
   :``{webroot}``: Stripped pathname of the Mercurial repository.
   :``{hgweb}``:   Base URL for browsing Mercurial repositories.
 
   Default ``changeset {node|short} in repo {root} refers to bug
   {bug}.\\ndetails:\\n\\t{desc|tabindent}``
 
 bugzilla.strip
   The number of path separator characters to strip from the front of
   the Mercurial repository path (``{root}`` in templates) to produce
   ``{webroot}``. For example, a repository with ``{root}``
   ``/var/local/my-project`` with a strip of 2 gives a value for
   ``{webroot}`` of ``my-project``. Default 0.
 
 web.baseurl
   Base URL for browsing Mercurial repositories. Referenced from
   templates as ``{hgweb}``.
 
 Configuration items common to XMLRPC+email and MySQL access modes:
 
 bugzilla.usermap
   Path of file containing Mercurial committer email to Bugzilla user email
   mappings. If specified, the file should contain one mapping per
   line::
 
     committer = Bugzilla user
 
   See also the ``[usermap]`` section.
 
 The ``[usermap]`` section is used to specify mappings of Mercurial
 committer email to Bugzilla user email. See also ``bugzilla.usermap``.
 Contains entries of the form ``committer = Bugzilla user``.
 
 XMLRPC access mode configuration:
 
 bugzilla.bzurl
   The base URL for the Bugzilla installation.
   Default ``http://localhost/bugzilla``.
 
 bugzilla.user
   The username to use to log into Bugzilla via XMLRPC. Default
   ``bugs``.
 
 bugzilla.password
   The password for Bugzilla login.
 
 XMLRPC+email access mode uses the XMLRPC access mode configuration items,
 and also:
 
 bugzilla.bzemail
   The Bugzilla email address.
 
 In addition, the Mercurial email settings must be configured. See the
 documentation in hgrc(5), sections ``[email]`` and ``[smtp]``.
 
 MySQL access mode configuration:
 
 bugzilla.host
   Hostname of the MySQL server holding the Bugzilla database.
   Default ``localhost``.
 
 bugzilla.db
   Name of the Bugzilla database in MySQL. Default ``bugs``.
 
 bugzilla.user
   Username to use to access MySQL server. Default ``bugs``.
 
 bugzilla.password
   Password to use to access MySQL server.
 
 bugzilla.timeout
   Database connection timeout (seconds). Default 5.
 
 bugzilla.bzuser
   Fallback Bugzilla user name to record comments with, if changeset
   committer cannot be found as a Bugzilla user.
 
 bugzilla.bzdir
    Bugzilla install directory. Used by default notify. Default
    ``/var/www/html/bugzilla``.
 
 bugzilla.notify
   The command to run to get Bugzilla to send bug change notification
   emails. Substitutes from a map with 3 keys, ``bzdir``, ``id`` (bug
   id) and ``user`` (committer bugzilla email). Default depends on
   version; from 2.18 it is "cd %(bzdir)s && perl -T
   contrib/sendbugmail.pl %(id)s %(user)s".
 
 Activating the extension::
 
     [extensions]
     bugzilla =
 
     [hooks]
     # run bugzilla hook on every change pulled or pushed in here
     incoming.bugzilla = python:hgext.bugzilla.hook
 
 Example configurations:
 
 XMLRPC example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
 XMLRPC+email example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. Bug comments
 are sent to the Bugzilla email address
 ``[e-mail]``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc+email
     bzemail=[e-mail]
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 MySQL example configuration. This has a local Bugzilla 3.2 installation
 in ``/opt/bugzilla-3.2``. The MySQL database is on ``localhost``,
 the Bugzilla database name is ``bugs`` and MySQL is
 accessed with MySQL username ``bugs`` password ``XYZZY``. It is used
 with a collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     host=localhost
     password=XYZZY
     version=3.0
     bzuser=[e-mail]
     bzdir=/opt/bugzilla-3.2
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 All the above add a comment to the Bugzilla bug record of the form::
 
     Changeset 3b16791d6642 in repository-name.
     http://my-project.org/hg/repository-name/rev/3b16791d6642
 
     Changeset commit comment. Bug 1234.
 '''
 
 from __future__ import absolute_import
 
 import re
 import time
 
 from mercurial.i18n import _
 from mercurial.node import short
 from mercurial import (
     cmdutil,
     error,
     mail,
     util,
 )
 
 urlparse = util.urlparse
 xmlrpclib = util.xmlrpclib
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 class bzaccess(object):
     '''Base class for access to Bugzilla.'''
 
     def __init__(self, ui):
         self.ui = ui
         usermap = self.ui.config('bugzilla', 'usermap')
         if usermap:
             self.ui.readconfig(usermap, sections=['usermap'])
 
     def map_committer(self, user):
         '''map name of committer to Bugzilla user name.'''
         for committer, bzuser in self.ui.configitems('usermap'):
             if committer.lower() == user.lower():
                 return bzuser
         return user
 
     # Methods to be implemented by access classes.
     #
     # 'bugs' is a dict keyed on bug id, where values are a dict holding
     # updates to bug state. Recognized dict keys are:
     #
     # 'hours': Value, float containing work hours to be updated.
     # 'fix':   If key present, bug is to be marked fixed. Value ignored.
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
         pass
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
         pass
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
         pass
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
         pass
 
 # Bugzilla via direct access to MySQL database.
 class bzmysql(bzaccess):
     '''Support for direct MySQL access to Bugzilla.
 
     The earliest Bugzilla version this is tested with is version 2.16.
 
     If your Bugzilla is version 3.4 or above, you are strongly
     recommended to use the XMLRPC access method instead.
     '''
 
     @staticmethod
     def sql_buglist(ids):
         '''return SQL-friendly list of bug ids'''
         return '(' + ','.join(map(str, ids)) + ')'
 
     _MySQLdb = None
 
     def __init__(self, ui):
         try:
             import MySQLdb as mysql
             bzmysql._MySQLdb = mysql
         except ImportError as err:
             raise error.Abort(_('python mysql support not available: %s') % err)
 
         bzaccess.__init__(self, ui)
 
         host = self.ui.config('bugzilla', 'host', 'localhost')
         user = self.ui.config('bugzilla', 'user', 'bugs')
         passwd = self.ui.config('bugzilla', 'password')
         db = self.ui.config('bugzilla', 'db', 'bugs')
         timeout = int(self.ui.config('bugzilla', 'timeout', 5))
         self.ui.note(_('connecting to %s:%s as %s, password %s\n') %
                      (host, db, user, '*' * len(passwd)))
         self.conn = bzmysql._MySQLdb.connect(host=host,
                                                    user=user, passwd=passwd,
                                                    db=db,
                                                    connect_timeout=timeout)
         self.cursor = self.conn.cursor()
         self.longdesc_id = self.get_longdesc_id()
         self.user_ids = {}
         self.default_notify = "cd %(bzdir)s && ./processmail %(id)s %(user)s"
 
     def run(self, *args, **kwargs):
         '''run a query.'''
         self.ui.note(_('query: %s %s\n') % (args, kwargs))
         try:
             self.cursor.execute(*args, **kwargs)
         except bzmysql._MySQLdb.MySQLError:
             self.ui.note(_('failed query: %s %s\n') % (args, kwargs))
             raise
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select fieldid from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_('unknown database schema'))
         return ids[0][0]
 
     def filter_real_bug_ids(self, bugs):
         '''filter not-existing bugs from set.'''
         self.run('select bug_id from bugs where bug_id in %s' %
                  bzmysql.sql_buglist(bugs.keys()))
         existing = [id for (id,) in self.cursor.fetchall()]
         for id in bugs.keys():
             if id not in existing:
                 self.ui.status(_('bug %d does not exist\n') % id)
                 del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''filter bug ids that already refer to this changeset from set.'''
         self.run('''select bug_id from longdescs where
                     bug_id in %s and thetext like "%%%s%%"''' %
                  (bzmysql.sql_buglist(bugs.keys()), short(node)))
         for (id,) in self.cursor.fetchall():
             self.ui.status(_('bug %d already knows about changeset %s\n') %
                            (id, short(node)))
             del bugs[id]
 
     def notify(self, bugs, committer):
         '''tell bugzilla to send mail.'''
         self.ui.status(_('telling bugzilla to send mail:\n'))
         (user, userid) = self.get_bugzilla_user(committer)
         for id in bugs.keys():
             self.ui.status(_('  bug %s\n') % id)
             cmdfmt = self.ui.config('bugzilla', 'notify', self.default_notify)
             bzdir = self.ui.config('bugzilla', 'bzdir',
                                    '/var/www/html/bugzilla')
             try:
                 # Backwards-compatible with old notify string, which
                 # took one string. This will throw with a new format
                 # string.
                 cmd = cmdfmt % id
             except TypeError:
                 cmd = cmdfmt % {'bzdir': bzdir, 'id': id, 'user': user}
             self.ui.note(_('running notify command %s\n') % cmd)
             fp = util.popen('(%s) 2>&1' % cmd)
             out = fp.read()
             ret = fp.close()
             if ret:
                 self.ui.warn(out)
                 raise error.Abort(_('bugzilla notify command %s') %
                                  util.explainexit(ret)[0])
         self.ui.status(_('done\n'))
 
     def get_user_id(self, user):
         '''look up numeric bugzilla user id.'''
         try:
             return self.user_ids[user]
         except KeyError:
             try:
                 userid = int(user)
             except ValueError:
                 self.ui.note(_('looking up user %s\n') % user)
                 self.run('''select userid from profiles
                             where login_name like %s''', user)
                 all = self.cursor.fetchall()
                 if len(all) != 1:
                     raise KeyError(user)
                 userid = int(all[0][0])
             self.user_ids[user] = userid
             return userid
 
     def get_bugzilla_user(self, committer):
         '''See if committer is a registered bugzilla user. Return
         bugzilla username and userid if so. If not, return default
         bugzilla username and userid.'''
         user = self.map_committer(committer)
         try:
             userid = self.get_user_id(user)
         except KeyError:
             try:
                 defaultuser = self.ui.config('bugzilla', 'bzuser')
                 if not defaultuser:
                     raise error.Abort(_('cannot find bugzilla user id for %s') %
                                      user)
                 userid = self.get_user_id(defaultuser)
                 user = defaultuser
             except KeyError:
                 raise error.Abort(_('cannot find bugzilla user id for %s or %s')
                                  % (user, defaultuser))
         return (user, userid)
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update bug state with comment text.
 
         Try adding comment as committer of changeset, otherwise as
         default bugzilla user.'''
         if len(newstate) > 0:
             self.ui.warn(_("Bugzilla/MySQL cannot update bug state\n"))
 
         (user, userid) = self.get_bugzilla_user(committer)
         now = time.strftime('%Y-%m-%d %H:%M:%S')
         self.run('''insert into longdescs
                     (bug_id, who, bug_when, thetext)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, text))
         self.run('''insert into bugs_activity (bug_id, who, bug_when, fieldid)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, self.longdesc_id))
         self.conn.commit()
 
 class bzmysql_2_18(bzmysql):
     '''support for bugzilla 2.18 series.'''
 
     def __init__(self, ui):
         bzmysql.__init__(self, ui)
         self.default_notify = \
             "cd %(bzdir)s && perl -T contrib/sendbugmail.pl %(id)s %(user)s"
 
 class bzmysql_3_0(bzmysql_2_18):
     '''support for bugzilla 3.0 series.'''
 
     def __init__(self, ui):
         bzmysql_2_18.__init__(self, ui)
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select id from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_('unknown database schema'))
         return ids[0][0]
 
 # Bugzilla via XMLRPC interface.
 
 class cookietransportrequest(object):
     """A Transport request method that retains cookies over its lifetime.
 
     The regular xmlrpclib transports ignore cookies. Which causes
     a bit of a problem when you need a cookie-based login, as with
     the Bugzilla XMLRPC interface prior to 4.4.3.
 
     So this is a helper for defining a Transport which looks for
     cookies being set in responses and saves them to add to all future
     requests.
     """
 
     # Inspiration drawn from
     # http://blog.godson.in/2010/09/how-to-make-python-xmlrpclib-client.html
     # http://www.itkovian.net/base/transport-class-for-pythons-xml-rpc-lib/
 
     cookies = []
     def send_cookies(self, connection):
         if self.cookies:
             for cookie in self.cookies:
                 connection.putheader("Cookie", cookie)
 
     def request(self, host, handler, request_body, verbose=0):
         self.verbose = verbose
         self.accept_gzip_encoding = False
 
         # issue XML-RPC request
         h = self.make_connection(host)
         if verbose:
             h.set_debuglevel(1)
 
         self.send_request(h, handler, request_body)
         self.send_host(h, host)
         self.send_cookies(h)
         self.send_user_agent(h)
         self.send_content(h, request_body)
 
         # Deal with differences between Python 2.4-2.6 and 2.7.
         # In the former h is a HTTP(S). In the latter it's a
         # HTTP(S)Connection. Luckily, the 2.4-2.6 implementation of
         # HTTP(S) has an underlying HTTP(S)Connection, so extract
         # that and use it.
         try:
             response = h.getresponse()
         except AttributeError:
             response = h._conn.getresponse()
 
         # Add any cookie definitions to our list.
         for header in response.msg.getallmatchingheaders("Set-Cookie"):
             val = header.split(": ", 1)[1]
             cookie = val.split(";", 1)[0]
             self.cookies.append(cookie)
 
         if response.status != 200:
             raise xmlrpclib.ProtocolError(host + handler, response.status,
                                           response.reason, response.msg.headers)
 
         payload = response.read()
         parser, unmarshaller = self.getparser()
         parser.feed(payload)
         parser.close()
 
         return unmarshaller.close()
 
 # The explicit calls to the underlying xmlrpclib __init__() methods are
 # necessary. The xmlrpclib.Transport classes are old-style classes, and
 # it turns out their __init__() doesn't get called when doing multiple
 # inheritance with a new-style class.
 class cookietransport(cookietransportrequest, xmlrpclib.Transport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.Transport.__init__(self, use_datetime)
 
 class cookiesafetransport(cookietransportrequest, xmlrpclib.SafeTransport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.SafeTransport.__init__(self, use_datetime)
 
 class bzxmlrpc(bzaccess):
     """Support for access to Bugzilla via the Bugzilla XMLRPC API.
 
     Requires a minimum Bugzilla version 3.4.
     """
 
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
 
         bzweb = self.ui.config('bugzilla', 'bzurl',
                                'http://localhost/bugzilla/')
         bzweb = bzweb.rstrip("/") + "/xmlrpc.cgi"
 
         user = self.ui.config('bugzilla', 'user', 'bugs')
         passwd = self.ui.config('bugzilla', 'password')
 
         self.fixstatus = self.ui.config('bugzilla', 'fixstatus', 'RESOLVED')
         self.fixresolution = self.ui.config('bugzilla', 'fixresolution',
                                             'FIXED')
 
         self.bzproxy = xmlrpclib.ServerProxy(bzweb, self.transport(bzweb))
         ver = self.bzproxy.Bugzilla.version()['version'].split('.')
         self.bzvermajor = int(ver[0])
         self.bzverminor = int(ver[1])
         login = self.bzproxy.User.login({'login': user, 'password': passwd,
                                          'restrict_login': True})
         self.bztoken = login.get('token', '')
 
     def transport(self, uri):
         if urlparse.urlparse(uri, "http")[0] == "https":
             return cookiesafetransport()
         else:
             return cookietransport()
 
     def get_bug_comments(self, id):
         """Return a string with all comment text for a bug."""
         c = self.bzproxy.Bug.comments({'ids': [id],
                                        'include_fields': ['text'],
                                        'token': self.bztoken})
         return ''.join([t['text'] for t in c['bugs'][str(id)]['comments']])
 
     def filter_real_bug_ids(self, bugs):
         probe = self.bzproxy.Bug.get({'ids': sorted(bugs.keys()),
                                       'include_fields': [],
                                       'permissive': True,
                                       'token': self.bztoken,
                                       })
         for badbug in probe['faults']:
             id = badbug['id']
             self.ui.status(_('bug %d does not exist\n') % id)
             del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         for id in sorted(bugs.keys()):
             if self.get_bug_comments(id).find(short(node)) != -1:
                 self.ui.status(_('bug %d already knows about changeset %s\n') %
                                (id, short(node)))
                 del bugs[id]
 
     def updatebug(self, bugid, newstate, text, committer):
         args = {}
         if 'hours' in newstate:
             args['work_time'] = newstate['hours']
 
         if self.bzvermajor >= 4:
             args['ids'] = [bugid]
             args['comment'] = {'body' : text}
             if 'fix' in newstate:
                 args['status'] = self.fixstatus
                 args['resolution'] = self.fixresolution
             args['token'] = self.bztoken
             self.bzproxy.Bug.update(args)
         else:
             if 'fix' in newstate:
                 self.ui.warn(_("Bugzilla/XMLRPC needs Bugzilla 4.0 or later "
                                "to mark bugs fixed\n"))
             args['id'] = bugid
             args['comment'] = text
             self.bzproxy.Bug.add_comment(args)
 
 class bzxmlrpcemail(bzxmlrpc):
     """Read data from Bugzilla via XMLRPC, send updates via email.
 
     Advantages of sending updates via email:
       1. Comments can be added as any user, not just logged in user.
       2. Bug statuses or other fields not accessible via XMLRPC can
          potentially be updated.
 
     There is no XMLRPC function to change bug status before Bugzilla
     4.0, so bugs cannot be marked fixed via XMLRPC before Bugzilla 4.0.
     But bugs can be marked fixed via email from 3.4 onwards.
     """
 
     # The email interface changes subtly between 3.4 and 3.6. In 3.4,
     # in-email fields are specified as '@<fieldname> = <value>'. In
     # 3.6 this becomes '@<fieldname> <value>'. And fieldname @bug_id
     # in 3.4 becomes @id in 3.6. 3.6 and 4.0 both maintain backwards
     # compatibility, but rather than rely on this use the new format for
     # 4.0 onwards.
 
     def __init__(self, ui):
         bzxmlrpc.__init__(self, ui)
 
         self.bzemail = self.ui.config('bugzilla', 'bzemail')
         if not self.bzemail:
             raise error.Abort(_("configuration 'bzemail' missing"))
         mail.validateconfig(self.ui)
 
     def makecommandline(self, fieldname, value):
         if self.bzvermajor >= 4:
             return "@%s %s" % (fieldname, str(value))
         else:
             if fieldname == "id":
                 fieldname = "bug_id"
             return "@%s = %s" % (fieldname, str(value))
 
     def send_bug_modify_email(self, bugid, commands, comment, committer):
         '''send modification message to Bugzilla bug via email.
 
         The message format is documented in the Bugzilla email_in.pl
         specification. commands is a list of command lines, comment is the
         comment text.
 
         To stop users from crafting commit comments with
         Bugzilla commands, specify the bug ID via the message body, rather
         than the subject line, and leave a blank line after it.
         '''
         user = self.map_committer(committer)
         matches = self.bzproxy.User.get({'match': [user],
                                          'token': self.bztoken})
         if not matches['users']:
             user = self.ui.config('bugzilla', 'user', 'bugs')
             matches = self.bzproxy.User.get({'match': [user],
                                              'token': self.bztoken})
             if not matches['users']:
                 raise error.Abort(_("default bugzilla user %s email not found")
                                   % user)
         user = matches['users'][0]['email']
         commands.append(self.makecommandline("id", bugid))
 
         text = "\n".join(commands) + "\n\n" + comment
 
         _charsets = mail._charsets(self.ui)
         user = mail.addressencode(self.ui, user, _charsets)
         bzemail = mail.addressencode(self.ui, self.bzemail, _charsets)
         msg = mail.mimeencode(self.ui, text, _charsets)
         msg['From'] = user
         msg['To'] = bzemail
         msg['Subject'] = mail.headencode(self.ui, "Bug modification", _charsets)
         sendmail = mail.connect(self.ui)
         sendmail(user, bzemail, msg.as_string())
 
     def updatebug(self, bugid, newstate, text, committer):
         cmds = []
         if 'hours' in newstate:
             cmds.append(self.makecommandline("work_time", newstate['hours']))
         if 'fix' in newstate:
             cmds.append(self.makecommandline("bug_status", self.fixstatus))
             cmds.append(self.makecommandline("resolution", self.fixresolution))
         self.send_bug_modify_email(bugid, cmds, text, committer)
 
 class bugzilla(object):
     # supported versions of bugzilla. different versions have
     # different schemas.
     _versions = {
         '2.16': bzmysql,
         '2.18': bzmysql_2_18,
         '3.0':  bzmysql_3_0,
         'xmlrpc': bzxmlrpc,
         'xmlrpc+email': bzxmlrpcemail
         }
 
     _default_bug_re = (r'bugs?\s*,?\s*(?:#|nos?\.?|num(?:ber)?s?)?\s*'
                        r'(?P<ids>(?:\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
                        r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 
     _default_fix_re = (r'fix(?:es)?\s*(?:bugs?\s*)?,?\s*'
                        r'(?:nos?\.?|num(?:ber)?s?)?\s*'
                        r'(?P<ids>(?:#?\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
                        r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
 
         bzversion = self.ui.config('bugzilla', 'version')
         try:
             bzclass = bugzilla._versions[bzversion]
         except KeyError:
             raise error.Abort(_('bugzilla version %s not supported') %
                              bzversion)
         self.bzdriver = bzclass(self.ui)
 
         self.bug_re = re.compile(
             self.ui.config('bugzilla', 'regexp',
                            bugzilla._default_bug_re), re.IGNORECASE)
         self.fix_re = re.compile(
             self.ui.config('bugzilla', 'fixregexp',
                            bugzilla._default_fix_re), re.IGNORECASE)
         self.split_re = re.compile(r'\D+')
 
     def find_bugs(self, ctx):
         '''return bugs dictionary created from commit comment.
 
         Extract bug info from changeset comments. Filter out any that are
         not known to Bugzilla, and any that already have a reference to
         the given changeset in their comments.
         '''
         start = 0
         hours = 0.0
         bugs = {}
         bugmatch = self.bug_re.search(ctx.description(), start)
         fixmatch = self.fix_re.search(ctx.description(), start)
         while True:
             bugattribs = {}
             if not bugmatch and not fixmatch:
                 break
             if not bugmatch:
                 m = fixmatch
             elif not fixmatch:
                 m = bugmatch
             else:
                 if bugmatch.start() < fixmatch.start():
                     m = bugmatch
                 else:
                     m = fixmatch
             start = m.end()
             if m is bugmatch:
                 bugmatch = self.bug_re.search(ctx.description(), start)
                 if 'fix' in bugattribs:
                     del bugattribs['fix']
             else:
                 fixmatch = self.fix_re.search(ctx.description(), start)
                 bugattribs['fix'] = None
 
             try:
                 ids = m.group('ids')
             except IndexError:
                 ids = m.group(1)
             try:
                 hours = float(m.group('hours'))
                 bugattribs['hours'] = hours
             except IndexError:
                 pass
             except TypeError:
                 pass
             except ValueError:
                 self.ui.status(_("%s: invalid hours\n") % m.group('hours'))
 
             for id in self.split_re.split(ids):
                 if not id:
                     continue
                 bugs[int(id)] = bugattribs
         if bugs:
             self.bzdriver.filter_real_bug_ids(bugs)
         if bugs:
             self.bzdriver.filter_cset_known_bug_ids(ctx.node(), bugs)
         return bugs
 
     def update(self, bugid, newstate, ctx):
         '''update bugzilla bug with reference to changeset.'''
 
         def webroot(root):
             '''strip leading prefix of repo root and turn into
             url-safe path.'''
             count = int(self.ui.config('bugzilla', 'strip', 0))
             root = util.pconvert(root)
             while count > 0:
                 c = root.find('/')
                 if c == -1:
                     break
                 root = root[c + 1:]
                 count -= 1
             return root
 
         mapfile = None
         tmpl = self.ui.config('bugzilla', 'template')
         if not tmpl:
             mapfile = self.ui.config('bugzilla', 'style')
         if not mapfile and not tmpl:
             tmpl = _('changeset {node|short} in repo {root} refers '
                      'to bug {bug}.\ndetails:\n\t{desc|tabindent}')
         t = cmdutil.changeset_templater(self.ui, self.repo,
                                         False, None, tmpl, mapfile, False)
         self.ui.pushbuffer()
         t.show(ctx, changes=ctx.changeset(),
                bug=str(bugid),
                hgweb=self.ui.config('web', 'baseurl'),
                root=self.repo.root,
                webroot=webroot(self.repo.root))
         data = self.ui.popbuffer()
         self.bzdriver.updatebug(bugid, newstate, data, util.email(ctx.user()))
 
     def notify(self, bugs, committer):
         '''ensure Bugzilla users are notified of bug change.'''
         self.bzdriver.notify(bugs, committer)
 
 def hook(ui, repo, hooktype, node=None, **kwargs):
     '''add comment to bugzilla for each changeset that refers to a
     bugzilla bug id. only add a comment once per bug, so same change
     seen multiple times does not fill bug with duplicate data.'''
     if node is None:
         raise error.Abort(_('hook type %s does not pass a changeset id') %
                          hooktype)
     try:
         bz = bugzilla(ui, repo)
         ctx = repo[node]
         bugs = bz.find_bugs(ctx)
         if bugs:
             for bug in bugs:
                 bz.update(bug, bugs[bug], ctx)
             bz.notify(bugs, util.email(ctx.user()))
     except Exception as e:
         raise error.Abort(_('Bugzilla error: %s') % e)

hgext/censor.py

@@ -1,190 +1,190 b''
 # Copyright (C) 2015 - Mike Edgar <[e-mail]>
 #
 # This extension enables removal of file content at a given revision,
 # rewriting the data/metadata of successive revisions to preserve revision log
 # integrity.
 
 """erase file content at a given revision
 
 The censor command instructs Mercurial to erase all content of a file at a given
 revision *without updating the changeset hash.* This allows existing history to
 remain valid while preventing future clones/pulls from receiving the erased
 data.
 
 Typical uses for censor are due to security or legal requirements, including::
 
  * Passwords, private keys, cryptographic material
  * Licensed data/code/libraries for which the license has expired
  * Personally Identifiable Information or other private data
 
 Censored nodes can interrupt mercurial's typical operation whenever the excised
 data needs to be materialized. Some commands, like ``hg cat``/``hg revert``,
 simply fail when asked to produce censored data. Others, like ``hg verify`` and
 ``hg update``, must be capable of tolerating censored data to continue to
 function in a meaningful way. Such commands only tolerate censored file
 revisions if they are allowed by the "censor.policy=ignore" config option.
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial.node import short
 
 from mercurial import (
     cmdutil,
     error,
     filelog,
     lock as lockmod,
     revlog,
     scmutil,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 @command('censor',
     [('r', 'rev', '', _('censor file from specified revision'), _('REV')),
      ('t', 'tombstone', '', _('replacement tombstone data'), _('TEXT'))],
     _('-r REV [-t TEXT] [FILE]'))
 def censor(ui, repo, path, rev='', tombstone='', **opts):
     wlock = lock = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         return _docensor(ui, repo, path, rev, tombstone, **opts)
     finally:
         lockmod.release(lock, wlock)
 
 def _docensor(ui, repo, path, rev='', tombstone='', **opts):
     if not path:
         raise error.Abort(_('must specify file path to censor'))
     if not rev:
         raise error.Abort(_('must specify revision to censor'))
 
     wctx = repo[None]
 
     m = scmutil.match(wctx, (path,))
     if m.anypats() or len(m.files()) != 1:
         raise error.Abort(_('can only specify an explicit filename'))
     path = m.files()[0]
     flog = repo.file(path)
     if not len(flog):
         raise error.Abort(_('cannot censor file with no history'))
 
     rev = scmutil.revsingle(repo, rev, rev).rev()
     try:
         ctx = repo[rev]
     except KeyError:
         raise error.Abort(_('invalid revision identifier %s') % rev)
 
     try:
         fctx = ctx.filectx(path)
     except error.LookupError:
         raise error.Abort(_('file does not exist at revision %s') % rev)
 
     fnode = fctx.filenode()
     headctxs = [repo[c] for c in repo.heads()]
     heads = [c for c in headctxs if path in c and c.filenode(path) == fnode]
     if heads:
         headlist = ', '.join([short(c.node()) for c in heads])
         raise error.Abort(_('cannot censor file in heads (%s)') % headlist,
             hint=_('clean/delete and commit first'))
 
     wp = wctx.parents()
     if ctx.node() in [p.node() for p in wp]:
         raise error.Abort(_('cannot censor working directory'),
             hint=_('clean/delete/update first'))
 
     flogv = flog.version & 0xFFFF
     if flogv != revlog.REVLOGNG:
         raise error.Abort(
             _('censor does not support revlog version %d') % (flogv,))
 
     tombstone = filelog.packmeta({"censored": tombstone}, "")
 
     crev = fctx.filerev()
 
     if len(tombstone) > flog.rawsize(crev):
         raise error.Abort(_(
             'censor tombstone must be no longer than censored data'))
 
     # Using two files instead of one makes it easy to rewrite entry-by-entry
     idxread = repo.svfs(flog.indexfile, 'r')
     idxwrite = repo.svfs(flog.indexfile, 'wb', atomictemp=True)
     if flog.version & revlog.REVLOGNGINLINEDATA:
         dataread, datawrite = idxread, idxwrite
     else:
         dataread = repo.svfs(flog.datafile, 'r')
         datawrite = repo.svfs(flog.datafile, 'wb', atomictemp=True)
 
     # Copy all revlog data up to the entry to be censored.
     rio = revlog.revlogio()
     offset = flog.start(crev)
 
     for chunk in util.filechunkiter(idxread, limit=crev * rio.size):
         idxwrite.write(chunk)
     for chunk in util.filechunkiter(dataread, limit=offset):
         datawrite.write(chunk)
 
     def rewriteindex(r, newoffs, newdata=None):
         """Rewrite the index entry with a new data offset and optional new data.
 
         The newdata argument, if given, is a tuple of three positive integers:
         (new compressed, new uncompressed, added flag bits).
         """
         offlags, comp, uncomp, base, link, p1, p2, nodeid = flog.index[r]
         flags = revlog.gettype(offlags)
         if newdata:
             comp, uncomp, nflags = newdata
             flags |= nflags
         offlags = revlog.offset_type(newoffs, flags)
         e = (offlags, comp, uncomp, r, link, p1, p2, nodeid)
         idxwrite.write(rio.packentry(e, None, flog.version, r))
         idxread.seek(rio.size, 1)
 
     def rewrite(r, offs, data, nflags=revlog.REVIDX_DEFAULT_FLAGS):
         """Write the given full text to the filelog with the given data offset.
 
         Returns:
             The integer number of data bytes written, for tracking data offsets.
         """
         flag, compdata = flog.compress(data)
         newcomp = len(flag) + len(compdata)
         rewriteindex(r, offs, (newcomp, len(data), nflags))
         datawrite.write(flag)
         datawrite.write(compdata)
         dataread.seek(flog.length(r), 1)
         return newcomp
 
     # Rewrite censored revlog entry with (padded) tombstone data.
     pad = ' ' * (flog.rawsize(crev) - len(tombstone))
     offset += rewrite(crev, offset, tombstone + pad, revlog.REVIDX_ISCENSORED)
 
     # Rewrite all following filelog revisions fixing up offsets and deltas.
     for srev in xrange(crev + 1, len(flog)):
         if crev in flog.parentrevs(srev):
             # Immediate children of censored node must be re-added as fulltext.
             try:
                 revdata = flog.revision(srev)
             except error.CensoredNodeError as e:
                 revdata = e.tombstone
             dlen = rewrite(srev, offset, revdata)
         else:
             # Copy any other revision data verbatim after fixing up the offset.
             rewriteindex(srev, offset)
             dlen = flog.length(srev)
             for chunk in util.filechunkiter(dataread, limit=dlen):
                 datawrite.write(chunk)
         offset += dlen
 
     idxread.close()
     idxwrite.close()
     if dataread is not idxread:
         dataread.close()
         datawrite.close()

hgext/chgserver.py

@@ -1,643 +1,643 b''
 # chgserver.py - command server extension for cHg
 #
 # Copyright 2011 Yuya Nishihara <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """command server extension for cHg (EXPERIMENTAL)
 
 'S' channel (read/write)
     propagate ui.system() request to client
 
 'attachio' command
     attach client's stdio passed by sendmsg()
 
 'chdir' command
     change current directory
 
 'getpager' command
     checks if pager is enabled and which pager should be executed
 
 'setenv' command
     replace os.environ completely
 
 'setumask' command
     set umask
 
 'validate' command
     reload the config and check if the server is up to date
 
 Config
 ------
 
 ::
 
   [chgserver]
   idletimeout = 3600 # seconds, after which an idle server will exit
   skiphash = False   # whether to skip config or env change checks
 """
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import inspect
 import os
 import re
 import signal
 import struct
 import sys
 import time
 
 from mercurial.i18n import _
 
 from mercurial import (
     cmdutil,
     commands,
     commandserver,
     dispatch,
     error,
     extensions,
     osutil,
     util,
 )
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 _log = commandserver.log
 
 def _hashlist(items):
     """return sha1 hexdigest for a list"""
     return hashlib.sha1(str(items)).hexdigest()
 
 # sensitive config sections affecting confighash
 _configsections = [
     'alias',  # affects global state commands.table
     'extdiff',  # uisetup will register new commands
     'extensions',
 ]
 
 # sensitive environment variables affecting confighash
 _envre = re.compile(r'''\A(?:
                     CHGHG
                     |HG.*
                     |LANG(?:UAGE)?
                     |LC_.*
                     |LD_.*
                     |PATH
                     |PYTHON.*
                     |TERM(?:INFO)?
                     |TZ
                     )\Z''', re.X)
 
 def _confighash(ui):
     """return a quick hash for detecting config/env changes
 
     confighash is the hash of sensitive config items and environment variables.
 
     for chgserver, it is designed that once confighash changes, the server is
     not qualified to serve its client and should redirect the client to a new
     server. different from mtimehash, confighash change will not mark the
     server outdated and exit since the user can have different configs at the
     same time.
     """
     sectionitems = []
     for section in _configsections:
         sectionitems.append(ui.configitems(section))
     sectionhash = _hashlist(sectionitems)
     envitems = [(k, v) for k, v in os.environ.iteritems() if _envre.match(k)]
     envhash = _hashlist(sorted(envitems))
     return sectionhash[:6] + envhash[:6]
 
 def _getmtimepaths(ui):
     """get a list of paths that should be checked to detect change
 
     The list will include:
     - extensions (will not cover all files for complex extensions)
     - mercurial/__version__.py
     - python binary
     """
     modules = [m for n, m in extensions.extensions(ui)]
     try:
         from mercurial import __version__
         modules.append(__version__)
     except ImportError:
         pass
     files = [sys.executable]
     for m in modules:
         try:
             files.append(inspect.getabsfile(m))
         except TypeError:
             pass
     return sorted(set(files))
 
 def _mtimehash(paths):
     """return a quick hash for detecting file changes
 
     mtimehash calls stat on given paths and calculate a hash based on size and
     mtime of each file. mtimehash does not read file content because reading is
     expensive. therefore it's not 100% reliable for detecting content changes.
     it's possible to return different hashes for same file contents.
     it's also possible to return a same hash for different file contents for
     some carefully crafted situation.
 
     for chgserver, it is designed that once mtimehash changes, the server is
     considered outdated immediately and should no longer provide service.
 
     mtimehash is not included in confighash because we only know the paths of
     extensions after importing them (there is imp.find_module but that faces
     race conditions). We need to calculate confighash without importing.
     """
     def trystat(path):
         try:
             st = os.stat(path)
             return (st.st_mtime, st.st_size)
         except OSError:
             # could be ENOENT, EPERM etc. not fatal in any case
             pass
     return _hashlist(map(trystat, paths))[:12]
 
 class hashstate(object):
     """a structure storing confighash, mtimehash, paths used for mtimehash"""
     def __init__(self, confighash, mtimehash, mtimepaths):
         self.confighash = confighash
         self.mtimehash = mtimehash
         self.mtimepaths = mtimepaths
 
     @staticmethod
     def fromui(ui, mtimepaths=None):
         if mtimepaths is None:
             mtimepaths = _getmtimepaths(ui)
         confighash = _confighash(ui)
         mtimehash = _mtimehash(mtimepaths)
         _log('confighash = %s mtimehash = %s\n' % (confighash, mtimehash))
         return hashstate(confighash, mtimehash, mtimepaths)
 
 # copied from hgext/pager.py:uisetup()
 def _setuppagercmd(ui, options, cmd):
     if not ui.formatted():
         return
 
     p = ui.config("pager", "pager", os.environ.get("PAGER"))
     usepager = False
     always = util.parsebool(options['pager'])
     auto = options['pager'] == 'auto'
 
     if not p:
         pass
     elif always:
         usepager = True
     elif not auto:
         usepager = False
     else:
         attended = ['annotate', 'cat', 'diff', 'export', 'glog', 'log', 'qdiff']
         attend = ui.configlist('pager', 'attend', attended)
         ignore = ui.configlist('pager', 'ignore')
         cmds, _ = cmdutil.findcmd(cmd, commands.table)
 
         for cmd in cmds:
             var = 'attend-%s' % cmd
             if ui.config('pager', var):
                 usepager = ui.configbool('pager', var)
                 break
             if (cmd in attend or
                 (cmd not in ignore and not attend)):
                 usepager = True
                 break
 
     if usepager:
         ui.setconfig('ui', 'formatted', ui.formatted(), 'pager')
         ui.setconfig('ui', 'interactive', False, 'pager')
         return p
 
 def _newchgui(srcui, csystem):
     class chgui(srcui.__class__):
         def __init__(self, src=None):
             super(chgui, self).__init__(src)
             if src:
                 self._csystem = getattr(src, '_csystem', csystem)
             else:
                 self._csystem = csystem
 
         def system(self, cmd, environ=None, cwd=None, onerr=None,
                    errprefix=None):
             # fallback to the original system method if the output needs to be
             # captured (to self._buffers), or the output stream is not stdout
             # (e.g. stderr, cStringIO), because the chg client is not aware of
             # these situations and will behave differently (write to stdout).
             if (any(s[1] for s in self._bufferstates)
                 or not util.safehasattr(self.fout, 'fileno')
                 or self.fout.fileno() != sys.stdout.fileno()):
                 return super(chgui, self).system(cmd, environ, cwd, onerr,
                                                  errprefix)
             # copied from mercurial/util.py:system()
             self.flush()
             def py2shell(val):
                 if val is None or val is False:
                     return '0'
                 if val is True:
                     return '1'
                 return str(val)
             env = os.environ.copy()
             if environ:
                 env.update((k, py2shell(v)) for k, v in environ.iteritems())
             env['HG'] = util.hgexecutable()
             rc = self._csystem(cmd, env, cwd)
             if rc and onerr:
                 errmsg = '%s %s' % (os.path.basename(cmd.split(None, 1)[0]),
                                     util.explainexit(rc)[0])
                 if errprefix:
                     errmsg = '%s: %s' % (errprefix, errmsg)
                 raise onerr(errmsg)
             return rc
 
     return chgui(srcui)
 
 def _loadnewui(srcui, args):
     newui = srcui.__class__()
     for a in ['fin', 'fout', 'ferr', 'environ']:
         setattr(newui, a, getattr(srcui, a))
     if util.safehasattr(srcui, '_csystem'):
         newui._csystem = srcui._csystem
 
     # internal config: extensions.chgserver
     newui.setconfig('extensions', 'chgserver',
                     srcui.config('extensions', 'chgserver'), '--config')
 
     # command line args
     args = args[:]
     dispatch._parseconfig(newui, dispatch._earlygetopt(['--config'], args))
 
     # stolen from tortoisehg.util.copydynamicconfig()
     for section, name, value in srcui.walkconfig():
         source = srcui.configsource(section, name)
         if ':' in source or source == '--config':
             # path:line or command line
             continue
         if source == 'none':
             # ui.configsource returns 'none' by default
             source = ''
         newui.setconfig(section, name, value, source)
 
     # load wd and repo config, copied from dispatch.py
     cwds = dispatch._earlygetopt(['--cwd'], args)
     cwd = cwds and os.path.realpath(cwds[-1]) or None
     rpath = dispatch._earlygetopt(["-R", "--repository", "--repo"], args)
     path, newlui = dispatch._getlocal(newui, rpath, wd=cwd)
 
     return (newui, newlui)
 
 class channeledsystem(object):
     """Propagate ui.system() request in the following format:
 
     payload length (unsigned int),
     cmd, '\0',
     cwd, '\0',
     envkey, '=', val, '\0',
     ...
     envkey, '=', val
 
     and waits:
 
     exitcode length (unsigned int),
     exitcode (int)
     """
     def __init__(self, in_, out, channel):
         self.in_ = in_
         self.out = out
         self.channel = channel
 
     def __call__(self, cmd, environ, cwd):
         args = [util.quotecommand(cmd), os.path.abspath(cwd or '.')]
         args.extend('%s=%s' % (k, v) for k, v in environ.iteritems())
         data = '\0'.join(args)
         self.out.write(struct.pack('>cI', self.channel, len(data)))
         self.out.write(data)
         self.out.flush()
 
         length = self.in_.read(4)
         length, = struct.unpack('>I', length)
         if length != 4:
             raise error.Abort(_('invalid response'))
         rc, = struct.unpack('>i', self.in_.read(4))
         return rc
 
 _iochannels = [
     # server.ch, ui.fp, mode
     ('cin', 'fin', 'rb'),
     ('cout', 'fout', 'wb'),
     ('cerr', 'ferr', 'wb'),
 ]
 
 class chgcmdserver(commandserver.server):
     def __init__(self, ui, repo, fin, fout, sock, hashstate, baseaddress):
         super(chgcmdserver, self).__init__(
             _newchgui(ui, channeledsystem(fin, fout, 'S')), repo, fin, fout)
         self.clientsock = sock
         self._oldios = []  # original (self.ch, ui.fp, fd) before "attachio"
         self.hashstate = hashstate
         self.baseaddress = baseaddress
         if hashstate is not None:
             self.capabilities = self.capabilities.copy()
             self.capabilities['validate'] = chgcmdserver.validate
 
     def cleanup(self):
         super(chgcmdserver, self).cleanup()
         # dispatch._runcatch() does not flush outputs if exception is not
         # handled by dispatch._dispatch()
         self.ui.flush()
         self._restoreio()
 
     def attachio(self):
         """Attach to client's stdio passed via unix domain socket; all
         channels except cresult will no longer be used
         """
         # tell client to sendmsg() with 1-byte payload, which makes it
         # distinctive from "attachio\n" command consumed by client.read()
         self.clientsock.sendall(struct.pack('>cI', 'I', 1))
         clientfds = osutil.recvfds(self.clientsock.fileno())
         _log('received fds: %r\n' % clientfds)
 
         ui = self.ui
         ui.flush()
         first = self._saveio()
         for fd, (cn, fn, mode) in zip(clientfds, _iochannels):
             assert fd > 0
             fp = getattr(ui, fn)
             os.dup2(fd, fp.fileno())
             os.close(fd)
             if not first:
                 continue
             # reset buffering mode when client is first attached. as we want
             # to see output immediately on pager, the mode stays unchanged
             # when client re-attached. ferr is unchanged because it should
             # be unbuffered no matter if it is a tty or not.
             if fn == 'ferr':
                 newfp = fp
             else:
                 # make it line buffered explicitly because the default is
                 # decided on first write(), where fout could be a pager.
                 if fp.isatty():
                     bufsize = 1  # line buffered
                 else:
                     bufsize = -1  # system default
                 newfp = os.fdopen(fp.fileno(), mode, bufsize)
                 setattr(ui, fn, newfp)
             setattr(self, cn, newfp)
 
         self.cresult.write(struct.pack('>i', len(clientfds)))
 
     def _saveio(self):
         if self._oldios:
             return False
         ui = self.ui
         for cn, fn, _mode in _iochannels:
             ch = getattr(self, cn)
             fp = getattr(ui, fn)
             fd = os.dup(fp.fileno())
             self._oldios.append((ch, fp, fd))
         return True
 
     def _restoreio(self):
         ui = self.ui
         for (ch, fp, fd), (cn, fn, _mode) in zip(self._oldios, _iochannels):
             newfp = getattr(ui, fn)
             # close newfp while it's associated with client; otherwise it
             # would be closed when newfp is deleted
             if newfp is not fp:
                 newfp.close()
             # restore original fd: fp is open again
             os.dup2(fd, fp.fileno())
             os.close(fd)
             setattr(self, cn, ch)
             setattr(ui, fn, fp)
         del self._oldios[:]
 
     def validate(self):
         """Reload the config and check if the server is up to date
 
         Read a list of '\0' separated arguments.
         Write a non-empty list of '\0' separated instruction strings or '\0'
         if the list is empty.
         An instruction string could be either:
             - "unlink $path", the client should unlink the path to stop the
               outdated server.
             - "redirect $path", the client should attempt to connect to $path
               first. If it does not work, start a new server. It implies
               "reconnect".
             - "exit $n", the client should exit directly with code n.
               This may happen if we cannot parse the config.
             - "reconnect", the client should close the connection and
               reconnect.
         If neither "reconnect" nor "redirect" is included in the instruction
         list, the client can continue with this server after completing all
         the instructions.
         """
         args = self._readlist()
         try:
             self.ui, lui = _loadnewui(self.ui, args)
         except error.ParseError as inst:
             dispatch._formatparse(self.ui.warn, inst)
             self.ui.flush()
             self.cresult.write('exit 255')
             return
         newhash = hashstate.fromui(lui, self.hashstate.mtimepaths)
         insts = []
         if newhash.mtimehash != self.hashstate.mtimehash:
             addr = _hashaddress(self.baseaddress, self.hashstate.confighash)
             insts.append('unlink %s' % addr)
             # mtimehash is empty if one or more extensions fail to load.
             # to be compatible with hg, still serve the client this time.
             if self.hashstate.mtimehash:
                 insts.append('reconnect')
         if newhash.confighash != self.hashstate.confighash:
             addr = _hashaddress(self.baseaddress, newhash.confighash)
             insts.append('redirect %s' % addr)
         _log('validate: %s\n' % insts)
         self.cresult.write('\0'.join(insts) or '\0')
 
     def chdir(self):
         """Change current directory
 
         Note that the behavior of --cwd option is bit different from this.
         It does not affect --config parameter.
         """
         path = self._readstr()
         if not path:
             return
         _log('chdir to %r\n' % path)
         os.chdir(path)
 
     def setumask(self):
         """Change umask"""
         mask = struct.unpack('>I', self._read(4))[0]
         _log('setumask %r\n' % mask)
         os.umask(mask)
 
     def getpager(self):
         """Read cmdargs and write pager command to r-channel if enabled
 
         If pager isn't enabled, this writes '\0' because channeledoutput
         does not allow to write empty data.
         """
         args = self._readlist()
         try:
             cmd, _func, args, options, _cmdoptions = dispatch._parse(self.ui,
                                                                      args)
         except (error.Abort, error.AmbiguousCommand, error.CommandError,
                 error.UnknownCommand):
             cmd = None
             options = {}
         if not cmd or 'pager' not in options:
             self.cresult.write('\0')
             return
 
         pagercmd = _setuppagercmd(self.ui, options, cmd)
         if pagercmd:
             # Python's SIGPIPE is SIG_IGN by default. change to SIG_DFL so
             # we can exit if the pipe to the pager is closed
             if util.safehasattr(signal, 'SIGPIPE') and \
                     signal.getsignal(signal.SIGPIPE) == signal.SIG_IGN:
                 signal.signal(signal.SIGPIPE, signal.SIG_DFL)
             self.cresult.write(pagercmd)
         else:
             self.cresult.write('\0')
 
     def setenv(self):
         """Clear and update os.environ
 
         Note that not all variables can make an effect on the running process.
         """
         l = self._readlist()
         try:
             newenv = dict(s.split('=', 1) for s in l)
         except ValueError:
             raise ValueError('unexpected value in setenv request')
         _log('setenv: %r\n' % sorted(newenv.keys()))
         os.environ.clear()
         os.environ.update(newenv)
 
     capabilities = commandserver.server.capabilities.copy()
     capabilities.update({'attachio': attachio,
                          'chdir': chdir,
                          'getpager': getpager,
                          'setenv': setenv,
                          'setumask': setumask})
 
 def _tempaddress(address):
     return '%s.%d.tmp' % (address, os.getpid())
 
 def _hashaddress(address, hashstr):
     return '%s-%s' % (address, hashstr)
 
 class chgunixservicehandler(object):
     """Set of operations for chg services"""
 
     pollinterval = 1  # [sec]
 
     def __init__(self, ui):
         self.ui = ui
         self._idletimeout = ui.configint('chgserver', 'idletimeout', 3600)
         self._lastactive = time.time()
 
     def bindsocket(self, sock, address):
         self._inithashstate(address)
         self._checkextensions()
         self._bind(sock)
         self._createsymlink()
 
     def _inithashstate(self, address):
         self._baseaddress = address
         if self.ui.configbool('chgserver', 'skiphash', False):
             self._hashstate = None
             self._realaddress = address
             return
         self._hashstate = hashstate.fromui(self.ui)
         self._realaddress = _hashaddress(address, self._hashstate.confighash)
 
     def _checkextensions(self):
         if not self._hashstate:
             return
         if extensions.notloaded():
             # one or more extensions failed to load. mtimehash becomes
             # meaningless because we do not know the paths of those extensions.
             # set mtimehash to an illegal hash value to invalidate the server.
             self._hashstate.mtimehash = ''
 
     def _bind(self, sock):
         # use a unique temp address so we can stat the file and do ownership
         # check later
         tempaddress = _tempaddress(self._realaddress)
         util.bindunixsocket(sock, tempaddress)
         self._socketstat = os.stat(tempaddress)
         # rename will replace the old socket file if exists atomically. the
         # old server will detect ownership change and exit.
         util.rename(tempaddress, self._realaddress)
 
     def _createsymlink(self):
         if self._baseaddress == self._realaddress:
             return
         tempaddress = _tempaddress(self._baseaddress)
         os.symlink(os.path.basename(self._realaddress), tempaddress)
         util.rename(tempaddress, self._baseaddress)
 
     def _issocketowner(self):
         try:
             stat = os.stat(self._realaddress)
             return (stat.st_ino == self._socketstat.st_ino and
                     stat.st_mtime == self._socketstat.st_mtime)
         except OSError:
             return False
 
     def unlinksocket(self, address):
         if not self._issocketowner():
             return
         # it is possible to have a race condition here that we may
         # remove another server's socket file. but that's okay
         # since that server will detect and exit automatically and
         # the client will start a new server on demand.
         try:
             os.unlink(self._realaddress)
         except OSError as exc:
             if exc.errno != errno.ENOENT:
                 raise
 
     def printbanner(self, address):
         # no "listening at" message should be printed to simulate hg behavior
         pass
 
     def shouldexit(self):
         if not self._issocketowner():
             self.ui.debug('%s is not owned, exiting.\n' % self._realaddress)
             return True
         if time.time() - self._lastactive > self._idletimeout:
             self.ui.debug('being idle too long. exiting.\n')
             return True
         return False
 
     def newconnection(self):
         self._lastactive = time.time()
 
     def createcmdserver(self, repo, conn, fin, fout):
         return chgcmdserver(self.ui, repo, fin, fout, conn,
                             self._hashstate, self._baseaddress)
 
 def chgunixservice(ui, repo, opts):
     if repo:
         # one chgserver can serve multiple repos. drop repo infomation
         ui.setconfig('bundle', 'mainreporoot', '', 'repo')
     h = chgunixservicehandler(ui)
     return commandserver.unixforkingservice(ui, repo=None, opts=opts, handler=h)
 
 def uisetup(ui):
     commandserver._servicemap['chgunix'] = chgunixservice
 
     # CHGINTERNALMARK is temporarily set by chg client to detect if chg will
     # start another chg. drop it to avoid possible side effects.
     if 'CHGINTERNALMARK' in os.environ:
         del os.environ['CHGINTERNALMARK']

hgext/children.py

@@ -1,69 +1,69 b''
 # Mercurial extension to provide the 'hg children' command
 #
 # Copyright 2007 by Intevation GmbH <[e-mail]>
 #
 # Author(s):
 # Thomas Arendsen Hein <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to display child changesets (DEPRECATED)
 
 This extension is deprecated. You should use :hg:`log -r
 "children(REV)"` instead.
 '''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
 )
 
 templateopts = commands.templateopts
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 @command('children',
     [('r', 'rev', '',
      _('show children of the specified revision'), _('REV')),
     ] + templateopts,
     _('hg children [-r REV] [FILE]'),
     inferrepo=True)
 def children(ui, repo, file_=None, **opts):
     """show the children of the given or working directory revision
 
     Print the children of the working directory's revisions. If a
     revision is given via -r/--rev, the children of that revision will
     be printed. If a file argument is given, revision in which the
     file was last changed (after the working directory revision or the
     argument to --rev if given) is printed.
 
     Please use :hg:`log` instead::
 
         hg children => hg log -r "children()"
         hg children -r REV => hg log -r "children(REV)"
 
     See :hg:`help log` and :hg:`help revsets.children`.
 
     """
     rev = opts.get('rev')
     if file_:
         fctx = repo.filectx(file_, changeid=rev)
         childctxs = [fcctx.changectx() for fcctx in fctx.children()]
     else:
         ctx = repo[rev]
         childctxs = ctx.children()
 
     displayer = cmdutil.show_changeset(ui, repo, opts)
     for cctx in childctxs:
         displayer.show(cctx)
     displayer.close()

hgext/churn.py

@@ -1,211 +1,211 b''
 # churn.py - create a graph of revisions count grouped by template
 #
 # Copyright 2006 Josef "Jeff" Sipek <[e-mail]>
 # Copyright 2008 Alexander Solovyov <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to display statistics about repository history'''
 
 from __future__ import absolute_import
 
 import datetime
 import os
 import time
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     encoding,
     patch,
     scmutil,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 def maketemplater(ui, repo, tmpl):
     return cmdutil.changeset_templater(ui, repo, False, None, tmpl, None, False)
 
 def changedlines(ui, repo, ctx1, ctx2, fns):
     added, removed = 0, 0
     fmatch = scmutil.matchfiles(repo, fns)
     diff = ''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
     for l in diff.split('\n'):
         if l.startswith("+") and not l.startswith("+++ "):
             added += 1
         elif l.startswith("-") and not l.startswith("--- "):
             removed += 1
     return (added, removed)
 
 def countrate(ui, repo, amap, *pats, **opts):
     """Calculate stats"""
     if opts.get('dateformat'):
         def getkey(ctx):
             t, tz = ctx.date()
             date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
             return date.strftime(opts['dateformat'])
     else:
         tmpl = opts.get('oldtemplate') or opts.get('template')
         tmpl = maketemplater(ui, repo, tmpl)
         def getkey(ctx):
             ui.pushbuffer()
             tmpl.show(ctx)
             return ui.popbuffer()
 
     state = {'count': 0}
     rate = {}
     df = False
     if opts.get('date'):
         df = util.matchdate(opts['date'])
 
     m = scmutil.match(repo[None], pats, opts)
     def prep(ctx, fns):
         rev = ctx.rev()
         if df and not df(ctx.date()[0]): # doesn't match date format
             return
 
         key = getkey(ctx).strip()
         key = amap.get(key, key) # alias remap
         if opts.get('changesets'):
             rate[key] = (rate.get(key, (0,))[0] + 1, 0)
         else:
             parents = ctx.parents()
             if len(parents) > 1:
                 ui.note(_('revision %d is a merge, ignoring...\n') % (rev,))
                 return
 
             ctx1 = parents[0]
             lines = changedlines(ui, repo, ctx1, ctx, fns)
             rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
 
         state['count'] += 1
         ui.progress(_('analyzing'), state['count'], total=len(repo),
                     unit=_('revisions'))
 
     for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
         continue
 
     ui.progress(_('analyzing'), None)
 
     return rate
 
 
 @command('churn',
     [('r', 'rev', [],
      _('count rate for the specified revision or revset'), _('REV')),
     ('d', 'date', '',
      _('count rate for revisions matching date spec'), _('DATE')),
     ('t', 'oldtemplate', '',
      _('template to group changesets (DEPRECATED)'), _('TEMPLATE')),
     ('T', 'template', '{author|email}',
      _('template to group changesets'), _('TEMPLATE')),
     ('f', 'dateformat', '',
      _('strftime-compatible format for grouping by date'), _('FORMAT')),
     ('c', 'changesets', False, _('count rate by number of changesets')),
     ('s', 'sort', False, _('sort by key (default: sort by count)')),
     ('', 'diffstat', False, _('display added/removed lines separately')),
     ('', 'aliases', '', _('file with email aliases'), _('FILE')),
     ] + commands.walkopts,
     _("hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
     inferrepo=True)
 def churn(ui, repo, *pats, **opts):
     '''histogram of changes to the repository
 
     This command will display a histogram representing the number
     of changed lines or revisions, grouped according to the given
     template. The default template will group changes by author.
     The --dateformat option may be used to group the results by
     date instead.
 
     Statistics are based on the number of changed lines, or
     alternatively the number of matching revisions if the
     --changesets option is specified.
 
     Examples::
 
       # display count of changed lines for every committer
       hg churn -t "{author|email}"
 
       # display daily activity graph
       hg churn -f "%H" -s -c
 
       # display activity of developers by month
       hg churn -f "%Y-%m" -s -c
 
       # display count of lines changed in every year
       hg churn -f "%Y" -s
 
     It is possible to map alternate email addresses to a main address
     by providing a file using the following format::
 
       <alias email> = <actual email>
 
     Such a file may be specified with the --aliases option, otherwise
     a .hgchurn file will be looked for in the working directory root.
     Aliases will be split from the rightmost "=".
     '''
     def pad(s, l):
         return s + " " * (l - encoding.colwidth(s))
 
     amap = {}
     aliases = opts.get('aliases')
     if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
         aliases = repo.wjoin('.hgchurn')
     if aliases:
         for l in open(aliases, "r"):
             try:
                 alias, actual = l.rsplit('=' in l and '=' or None, 1)
                 amap[alias.strip()] = actual.strip()
             except ValueError:
                 l = l.strip()
                 if l:
                     ui.warn(_("skipping malformed alias: %s\n") % l)
                 continue
 
     rate = countrate(ui, repo, amap, *pats, **opts).items()
     if not rate:
         return
 
     if opts.get('sort'):
         rate.sort()
     else:
         rate.sort(key=lambda x: (-sum(x[1]), x))
 
     # Be careful not to have a zero maxcount (issue833)
     maxcount = float(max(sum(v) for k, v in rate)) or 1.0
     maxname = max(len(k) for k, v in rate)
 
     ttywidth = ui.termwidth()
     ui.debug("assuming %i character terminal\n" % ttywidth)
     width = ttywidth - maxname - 2 - 2 - 2
 
     if opts.get('diffstat'):
         width -= 15
         def format(name, diffstat):
             added, removed = diffstat
             return "%s %15s %s%s\n" % (pad(name, maxname),
                                        '+%d/-%d' % (added, removed),
                                        ui.label('+' * charnum(added),
                                                 'diffstat.inserted'),
                                        ui.label('-' * charnum(removed),
                                                 'diffstat.deleted'))
     else:
         width -= 6
         def format(name, count):
             return "%s %6d %s\n" % (pad(name, maxname), sum(count),
                                     '*' * charnum(sum(count)))
 
     def charnum(count):
         return int(round(count * width / maxcount))
 
     for name, count in rate:
         ui.write(format(name, count))

hgext/clonebundles.py

@@ -1,186 +1,186 b''
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """advertise pre-generated bundles to seed clones
 
 "clonebundles" is a server-side extension used to advertise the existence
 of pre-generated, externally hosted bundle files to clients that are
 cloning so that cloning can be faster, more reliable, and require less
 resources on the server.
 
 Cloning can be a CPU and I/O intensive operation on servers. Traditionally,
 the server, in response to a client's request to clone, dynamically generates
 a bundle containing the entire repository content and sends it to the client.
 There is no caching on the server and the server will have to redundantly
 generate the same outgoing bundle in response to each clone request. For
 servers with large repositories or with high clone volume, the load from
 clones can make scaling the server challenging and costly.
 
 This extension provides server operators the ability to offload potentially
 expensive clone load to an external service. Here's how it works.
 
 1. A server operator establishes a mechanism for making bundle files available
    on a hosting service where Mercurial clients can fetch them.
 2. A manifest file listing available bundle URLs and some optional metadata
    is added to the Mercurial repository on the server.
 3. A client initiates a clone against a clone bundles aware server.
 4. The client sees the server is advertising clone bundles and fetches the
    manifest listing available bundles.
 5. The client filters and sorts the available bundles based on what it
    supports and prefers.
 6. The client downloads and applies an available bundle from the
    server-specified URL.
 7. The client reconnects to the original server and performs the equivalent
    of :hg:`pull` to retrieve all repository data not in the bundle. (The
    repository could have been updated between when the bundle was created
    and when the client started the clone.)
 
 Instead of the server generating full repository bundles for every clone
 request, it generates full bundles once and they are subsequently reused to
 bootstrap new clones. The server may still transfer data at clone time.
 However, this is only data that has been added/changed since the bundle was
 created. For large, established repositories, this can reduce server load for
 clones to less than 1% of original.
 
 To work, this extension requires the following of server operators:
 
 * Generating bundle files of repository content (typically periodically,
   such as once per day).
 * A file server that clients have network access to and that Python knows
   how to talk to through its normal URL handling facility (typically an
   HTTP server).
 * A process for keeping the bundles manifest in sync with available bundle
   files.
 
 Strictly speaking, using a static file hosting server isn't required: a server
 operator could use a dynamic service for retrieving bundle data. However,
 static file hosting services are simple and scalable and should be sufficient
 for most needs.
 
 Bundle files can be generated with the :hg:`bundle` command. Typically
 :hg:`bundle --all` is used to produce a bundle of the entire repository.
 
 :hg:`debugcreatestreamclonebundle` can be used to produce a special
 *streaming clone bundle*. These are bundle files that are extremely efficient
 to produce and consume (read: fast). However, they are larger than
 traditional bundle formats and require that clients support the exact set
 of repository data store formats in use by the repository that created them.
 Typically, a newer server can serve data that is compatible with older clients.
 However, *streaming clone bundles* don't have this guarantee. **Server
 operators need to be aware that newer versions of Mercurial may produce
 streaming clone bundles incompatible with older Mercurial versions.**
 
 A server operator is responsible for creating a ``.hg/clonebundles.manifest``
 file containing the list of available bundle files suitable for seeding
 clones. If this file does not exist, the repository will not advertise the
 existence of clone bundles when clients connect.
 
 The manifest file contains a newline (\n) delimited list of entries.
 
 Each line in this file defines an available bundle. Lines have the format:
 
     <URL> [<key>=<value>[ <key>=<value>]]
 
 That is, a URL followed by an optional, space-delimited list of key=value
 pairs describing additional properties of this bundle. Both keys and values
 are URI encoded.
 
 Keys in UPPERCASE are reserved for use by Mercurial and are defined below.
 All non-uppercase keys can be used by site installations. An example use
 for custom properties is to use the *datacenter* attribute to define which
 data center a file is hosted in. Clients could then prefer a server in the
 data center closest to them.
 
 The following reserved keys are currently defined:
 
 BUNDLESPEC
    A "bundle specification" string that describes the type of the bundle.
 
    These are string values that are accepted by the "--type" argument of
    :hg:`bundle`.
 
    The values are parsed in strict mode, which means they must be of the
    "<compression>-<type>" form. See
    mercurial.exchange.parsebundlespec() for more details.
 
    :hg:`debugbundle --spec` can be used to print the bundle specification
    string for a bundle file. The output of this command can be used verbatim
    for the value of ``BUNDLESPEC`` (it is already escaped).
 
    Clients will automatically filter out specifications that are unknown or
    unsupported so they won't attempt to download something that likely won't
    apply.
 
    The actual value doesn't impact client behavior beyond filtering:
    clients will still sniff the bundle type from the header of downloaded
    files.
 
    **Use of this key is highly recommended**, as it allows clients to
    easily skip unsupported bundles. If this key is not defined, an old
    client may attempt to apply a bundle that it is incapable of reading.
 
 REQUIRESNI
    Whether Server Name Indication (SNI) is required to connect to the URL.
    SNI allows servers to use multiple certificates on the same IP. It is
    somewhat common in CDNs and other hosting providers. Older Python
    versions do not support SNI. Defining this attribute enables clients
    with older Python versions to filter this entry without experiencing
    an opaque SSL failure at connection time.
 
    If this is defined, it is important to advertise a non-SNI fallback
    URL or clients running old Python releases may not be able to clone
    with the clonebundles facility.
 
    Value should be "true".
 
 Manifests can contain multiple entries. Assuming metadata is defined, clients
 will filter entries from the manifest that they don't support. The remaining
 entries are optionally sorted by client preferences
 (``experimental.clonebundleprefers`` config option). The client then attempts
 to fetch the bundle at the first URL in the remaining list.
 
 **Errors when downloading a bundle will fail the entire clone operation:
 clients do not automatically fall back to a traditional clone.** The reason
 for this is that if a server is using clone bundles, it is probably doing so
 because the feature is necessary to help it scale. In other words, there
 is an assumption that clone load will be offloaded to another service and
 that the Mercurial server isn't responsible for serving this clone load.
 If that other service experiences issues and clients start mass falling back to
 the original Mercurial server, the added clone load could overwhelm the server
 due to unexpected load and effectively take it offline. Not having clients
 automatically fall back to cloning from the original server mitigates this
 scenario.
 
 Because there is no automatic Mercurial server fallback on failure of the
 bundle hosting service, it is important for server operators to view the bundle
 hosting service as an extension of the Mercurial server in terms of
 availability and service level agreements: if the bundle hosting service goes
 down, so does the ability for clients to clone. Note: clients will see a
 message informing them how to bypass the clone bundles facility when a failure
 occurs. So server operators should prepare for some people to follow these
 instructions when a failure occurs, thus driving more load to the original
 Mercurial server when the bundle hosting service fails.
 """
 
 from __future__ import absolute_import
 
 from mercurial import (
     extensions,
     wireproto,
 )
 
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 def capabilities(orig, repo, proto):
     caps = orig(repo, proto)
 
     # Only advertise if a manifest exists. This does add some I/O to requests.
     # But this should be cheaper than a wasted network round trip due to
     # missing file.
     if repo.opener.exists('clonebundles.manifest'):
         caps.append('clonebundles')
 
     return caps
 
 def extsetup(ui):
     extensions.wrapfunction(wireproto, '_capabilities', capabilities)

hgext/color.py

@@ -1,665 +1,689 b''
 # color.py color output for Mercurial commands
 #
 # Copyright (C) 2007 Kevin Christen <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''colorize output from some commands
 
 The color extension colorizes output from several Mercurial commands.
 For example, the diff command shows additions in green and deletions
 in red, while the status command shows modified files in magenta. Many
 other commands have analogous colors. It is possible to customize
 these colors.
 
 Effects
 -------
 
 Other effects in addition to color, like bold and underlined text, are
 also available. By default, the terminfo database is used to find the
 terminal codes used to change color and effect.  If terminfo is not
 available, then effects are rendered with the ECMA-48 SGR control
 function (aka ANSI escape codes).
 
 The available effects in terminfo mode are 'blink', 'bold', 'dim',
 'inverse', 'invisible', 'italic', 'standout', and 'underline'; in
 ECMA-48 mode, the options are 'bold', 'inverse', 'italic', and
 'underline'.  How each is rendered depends on the terminal emulator.
 Some may not be available for a given terminal type, and will be
 silently ignored.
 
+If the terminfo entry for your terminal is missing codes for an effect
+or has the wrong codes, you can add or override those codes in your
+configuration::
+
+  [color]
+  terminfo.dim = \E[2m
+
+where '\E' is substituted with an escape character.
+
 Labels
 ------
 
 Text receives color effects depending on the labels that it has. Many
 default Mercurial commands emit labelled text. You can also define
 your own labels in templates using the label function, see :hg:`help
 templates`. A single portion of text may have more than one label. In
 that case, effects given to the last label will override any other
 effects. This includes the special "none" effect, which nullifies
 other effects.
 
 Labels are normally invisible. In order to see these labels and their
 position in the text, use the global --color=debug option. The same
 anchor text may be associated to multiple labels, e.g.
 
   [log.changeset changeset.secret|changeset:   22611:6f0a53c8f587]
 
 The following are the default effects for some default labels. Default
 effects may be overridden from your configuration file::
 
   [color]
   status.modified = blue bold underline red_background
   status.added = green bold
   status.removed = red bold blue_background
   status.deleted = cyan bold underline
   status.unknown = magenta bold underline
   status.ignored = black bold
 
   # 'none' turns off all effects
   status.clean = none
   status.copied = none
 
   qseries.applied = blue bold underline
   qseries.unapplied = black bold
   qseries.missing = red bold
 
   diff.diffline = bold
   diff.extended = cyan bold
   diff.file_a = red bold
   diff.file_b = green bold
   diff.hunk = magenta
   diff.deleted = red
   diff.inserted = green
   diff.changed = white
   diff.tab =
   diff.trailingwhitespace = bold red_background
 
   # Blank so it inherits the style of the surrounding label
   changeset.public =
   changeset.draft =
   changeset.secret =
 
   resolve.unresolved = red bold
   resolve.resolved = green bold
 
   bookmarks.active = green
 
   branches.active = none
   branches.closed = black bold
   branches.current = green
   branches.inactive = none
 
   tags.normal = green
   tags.local = black bold
 
   rebase.rebased = blue
   rebase.remaining = red bold
 
   shelve.age = cyan
   shelve.newest = green bold
   shelve.name = blue bold
 
   histedit.remaining = red bold
 
 Custom colors
 -------------
 
 Because there are only eight standard colors, this module allows you
 to define color names for other color slots which might be available
 for your terminal type, assuming terminfo mode.  For instance::
 
   color.brightblue = 12
   color.pink = 207
   color.orange = 202
 
 to set 'brightblue' to color slot 12 (useful for 16 color terminals
 that have brighter colors defined in the upper eight) and, 'pink' and
 'orange' to colors in 256-color xterm's default color cube.  These
 defined colors may then be used as any of the pre-defined eight,
 including appending '_background' to set the background to that color.
 
 Modes
 -----
 
 By default, the color extension will use ANSI mode (or win32 mode on
 Windows) if it detects a terminal. To override auto mode (to enable
 terminfo mode, for example), set the following configuration option::
 
   [color]
   mode = terminfo
 
 Any value other than 'ansi', 'win32', 'terminfo', or 'auto' will
 disable color.
 
 Note that on some systems, terminfo mode may cause problems when using
 color with the pager extension and less -R. less with the -R option
 will only display ECMA-48 color codes, and terminfo mode may sometimes
 emit codes that less doesn't understand. You can work around this by
 either using ansi mode (or auto mode), or by using less -r (which will
 pass through all terminal control codes, not just color control
 codes).
 
 On some systems (such as MSYS in Windows), the terminal may support
 a different color mode than the pager (activated via the "pager"
 extension). It is possible to define separate modes depending on whether
 the pager is active::
 
   [color]
   mode = auto
   pagermode = ansi
 
 If ``pagermode`` is not defined, the ``mode`` will be used.
 '''
 
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     dispatch,
     extensions,
     subrepo,
     ui as uimod,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 # start and stop parameters for effects
 _effects = {'none': 0, 'black': 30, 'red': 31, 'green': 32, 'yellow': 33,
             'blue': 34, 'magenta': 35, 'cyan': 36, 'white': 37, 'bold': 1,
             'italic': 3, 'underline': 4, 'inverse': 7, 'dim': 2,
             'black_background': 40, 'red_background': 41,
             'green_background': 42, 'yellow_background': 43,
             'blue_background': 44, 'purple_background': 45,
             'cyan_background': 46, 'white_background': 47}
 
 def _terminfosetup(ui, mode):
     '''Initialize terminfo data and the terminal if we're in terminfo mode.'''
 
     global _terminfo_params
     # If we failed to load curses, we go ahead and return.
     if not _terminfo_params:
         return
     # Otherwise, see what the config file says.
     if mode not in ('auto', 'terminfo'):
         return
 
-    _terminfo_params.update((key[6:], (False, int(val)))
+    _terminfo_params.update((key[6:], (False, int(val), ''))
         for key, val in ui.configitems('color')
         if key.startswith('color.'))
+    _terminfo_params.update((key[9:], (True, '', val.replace('\\E', '\x1b')))
+        for key, val in ui.configitems('color')
+        if key.startswith('terminfo.'))
 
     try:
         curses.setupterm()
     except curses.error as e:
         _terminfo_params = {}
         return
 
-    for key, (b, e) in _terminfo_params.items():
+    for key, (b, e, c) in _terminfo_params.items():
         if not b:
             continue
-        if not curses.tigetstr(e):
+        if not c and not curses.tigetstr(e):
             # Most terminals don't support dim, invis, etc, so don't be
             # noisy and use ui.debug().
             ui.debug("no terminfo entry for %s\n" % e)
             del _terminfo_params[key]
     if not curses.tigetstr('setaf') or not curses.tigetstr('setab'):
         # Only warn about missing terminfo entries if we explicitly asked for
         # terminfo mode.
         if mode == "terminfo":
             ui.warn(_("no terminfo entry for setab/setaf: reverting to "
               "ECMA-48 color\n"))
         _terminfo_params = {}
 
 def _modesetup(ui, coloropt):
     global _terminfo_params
 
     if coloropt == 'debug':
         return 'debug'
 
     auto = (coloropt == 'auto')
     always = not auto and util.parsebool(coloropt)
     if not always and not auto:
         return None
 
     formatted = always or (os.environ.get('TERM') != 'dumb' and ui.formatted())
 
     mode = ui.config('color', 'mode', 'auto')
 
     # If pager is active, color.pagermode overrides color.mode.
     if getattr(ui, 'pageractive', False):
         mode = ui.config('color', 'pagermode', mode)
 
     realmode = mode
     if mode == 'auto':
         if os.name == 'nt':
             term = os.environ.get('TERM')
             # TERM won't be defined in a vanilla cmd.exe environment.
 
             # UNIX-like environments on Windows such as Cygwin and MSYS will
             # set TERM. They appear to make a best effort attempt at setting it
             # to something appropriate. However, not all environments with TERM
             # defined support ANSI. Since "ansi" could result in terminal
             # gibberish, we error on the side of selecting "win32". However, if
             # w32effects is not defined, we almost certainly don't support
             # "win32", so don't even try.
             if (term and 'xterm' in term) or not w32effects:
                 realmode = 'ansi'
             else:
                 realmode = 'win32'
         else:
             realmode = 'ansi'
 
     def modewarn():
         # only warn if color.mode was explicitly set and we're in
         # an interactive terminal
         if mode == realmode and ui.interactive():
             ui.warn(_('warning: failed to set color mode to %s\n') % mode)
 
     if realmode == 'win32':
         _terminfo_params = {}
         if not w32effects:
             modewarn()
             return None
         _effects.update(w32effects)
     elif realmode == 'ansi':
         _terminfo_params = {}
     elif realmode == 'terminfo':
         _terminfosetup(ui, mode)
         if not _terminfo_params:
             ## FIXME Shouldn't we return None in this case too?
             modewarn()
             realmode = 'ansi'
     else:
         return None
 
     if always or (auto and formatted):
         return realmode
     return None
 
 try:
     import curses
-    # Mapping from effect name to terminfo attribute name or color number.
-    # This will also force-load the curses module.
-    _terminfo_params = {'none': (True, 'sgr0'),
-                        'standout': (True, 'smso'),
-                        'underline': (True, 'smul'),
-                        'reverse': (True, 'rev'),
-                        'inverse': (True, 'rev'),
-                        'blink': (True, 'blink'),
-                        'dim': (True, 'dim'),
-                        'bold': (True, 'bold'),
-                        'invisible': (True, 'invis'),
-                        'italic': (True, 'sitm'),
-                        'black': (False, curses.COLOR_BLACK),
-                        'red': (False, curses.COLOR_RED),
-                        'green': (False, curses.COLOR_GREEN),
-                        'yellow': (False, curses.COLOR_YELLOW),
-                        'blue': (False, curses.COLOR_BLUE),
-                        'magenta': (False, curses.COLOR_MAGENTA),
-                        'cyan': (False, curses.COLOR_CYAN),
-                        'white': (False, curses.COLOR_WHITE)}
+    # Mapping from effect name to terminfo attribute name (or raw code) or
+    # color number.  This will also force-load the curses module.
+    _terminfo_params = {'none': (True, 'sgr0', ''),
+                        'standout': (True, 'smso', ''),
+                        'underline': (True, 'smul', ''),
+                        'reverse': (True, 'rev', ''),
+                        'inverse': (True, 'rev', ''),
+                        'blink': (True, 'blink', ''),
+                        'dim': (True, 'dim', ''),
+                        'bold': (True, 'bold', ''),
+                        'invisible': (True, 'invis', ''),
+                        'italic': (True, 'sitm', ''),
+                        'black': (False, curses.COLOR_BLACK, ''),
+                        'red': (False, curses.COLOR_RED, ''),
+                        'green': (False, curses.COLOR_GREEN, ''),
+                        'yellow': (False, curses.COLOR_YELLOW, ''),
+                        'blue': (False, curses.COLOR_BLUE, ''),
+                        'magenta': (False, curses.COLOR_MAGENTA, ''),
+                        'cyan': (False, curses.COLOR_CYAN, ''),
+                        'white': (False, curses.COLOR_WHITE, '')}
 except ImportError:
     _terminfo_params = {}
 
 _styles = {'grep.match': 'red bold',
            'grep.linenumber': 'green',
            'grep.rev': 'green',
            'grep.change': 'green',
            'grep.sep': 'cyan',
            'grep.filename': 'magenta',
            'grep.user': 'magenta',
            'grep.date': 'magenta',
            'bookmarks.active': 'green',
            'branches.active': 'none',
            'branches.closed': 'black bold',
            'branches.current': 'green',
            'branches.inactive': 'none',
            'diff.changed': 'white',
            'diff.deleted': 'red',
            'diff.diffline': 'bold',
            'diff.extended': 'cyan bold',
            'diff.file_a': 'red bold',
            'diff.file_b': 'green bold',
            'diff.hunk': 'magenta',
            'diff.inserted': 'green',
            'diff.tab': '',
            'diff.trailingwhitespace': 'bold red_background',
            'changeset.public' : '',
            'changeset.draft' : '',
            'changeset.secret' : '',
            'diffstat.deleted': 'red',
            'diffstat.inserted': 'green',
            'histedit.remaining': 'red bold',
            'ui.prompt': 'yellow',
            'log.changeset': 'yellow',
            'patchbomb.finalsummary': '',
            'patchbomb.from': 'magenta',
            'patchbomb.to': 'cyan',
            'patchbomb.subject': 'green',
            'patchbomb.diffstats': '',
            'rebase.rebased': 'blue',
            'rebase.remaining': 'red bold',
            'resolve.resolved': 'green bold',
            'resolve.unresolved': 'red bold',
            'shelve.age': 'cyan',
            'shelve.newest': 'green bold',
            'shelve.name': 'blue bold',
            'status.added': 'green bold',
            'status.clean': 'none',
            'status.copied': 'none',
            'status.deleted': 'cyan bold underline',
            'status.ignored': 'black bold',
            'status.modified': 'blue bold',
            'status.removed': 'red bold',
            'status.unknown': 'magenta bold underline',
            'tags.normal': 'green',
            'tags.local': 'black bold'}
 
 
 def _effect_str(effect):
     '''Helper function for render_effects().'''
 
     bg = False
     if effect.endswith('_background'):
         bg = True
         effect = effect[:-11]
-    attr, val = _terminfo_params[effect]
+    try:
+        attr, val, termcode = _terminfo_params[effect]
+    except KeyError:
+        return ''
     if attr:
-        return curses.tigetstr(val)
+        if termcode:
+            return termcode
+        else:
+            return curses.tigetstr(val)
     elif bg:
         return curses.tparm(curses.tigetstr('setab'), val)
     else:
         return curses.tparm(curses.tigetstr('setaf'), val)
 
 def render_effects(text, effects):
     'Wrap text in commands to turn on each effect.'
     if not text:
         return text
     if not _terminfo_params:
         start = [str(_effects[e]) for e in ['none'] + effects.split()]
         start = '\033[' + ';'.join(start) + 'm'
         stop = '\033[' + str(_effects['none']) + 'm'
     else:
         start = ''.join(_effect_str(effect)
                         for effect in ['none'] + effects.split())
         stop = _effect_str('none')
     return ''.join([start, text, stop])
 
 def extstyles():
     for name, ext in extensions.extensions():
         _styles.update(getattr(ext, 'colortable', {}))
 
 def valideffect(effect):
     'Determine if the effect is valid or not.'
     good = False
     if not _terminfo_params and effect in _effects:
         good = True
     elif effect in _terminfo_params or effect[:-11] in _terminfo_params:
         good = True
     return good
 
 def configstyles(ui):
     for status, cfgeffects in ui.configitems('color'):
-        if '.' not in status or status.startswith('color.'):
+        if '.' not in status or status.startswith(('color.', 'terminfo.')):
             continue
         cfgeffects = ui.configlist('color', status)
         if cfgeffects:
             good = []
             for e in cfgeffects:
                 if valideffect(e):
                     good.append(e)
                 else:
                     ui.warn(_("ignoring unknown color/effect %r "
                               "(configured in color.%s)\n")
                             % (e, status))
             _styles[status] = ' '.join(good)
 
 class colorui(uimod.ui):
     _colormode = 'ansi'
     def write(self, *args, **opts):
         if self._colormode is None:
             return super(colorui, self).write(*args, **opts)
 
         label = opts.get('label', '')
         if self._buffers and not opts.get('prompt', False):
             if self._bufferapplylabels:
                 self._buffers[-1].extend(self.label(a, label) for a in args)
             else:
                 self._buffers[-1].extend(args)
         elif self._colormode == 'win32':
             for a in args:
                 win32print(a, super(colorui, self).write, **opts)
         else:
             return super(colorui, self).write(
                 *[self.label(a, label) for a in args], **opts)
 
     def write_err(self, *args, **opts):
         if self._colormode is None:
             return super(colorui, self).write_err(*args, **opts)
 
         label = opts.get('label', '')
         if self._bufferstates and self._bufferstates[-1][0]:
             return self.write(*args, **opts)
         if self._colormode == 'win32':
             for a in args:
                 win32print(a, super(colorui, self).write_err, **opts)
         else:
             return super(colorui, self).write_err(
                 *[self.label(a, label) for a in args], **opts)
 
     def showlabel(self, msg, label):
         if label and msg:
             if msg[-1] == '\n':
                 return "[%s|%s]\n" % (label, msg[:-1])
             else:
                 return "[%s|%s]" % (label, msg)
         else:
             return msg
 
     def label(self, msg, label):
         if self._colormode is None:
             return super(colorui, self).label(msg, label)
 
         if self._colormode == 'debug':
             return self.showlabel(msg, label)
 
         effects = []
         for l in label.split():
             s = _styles.get(l, '')
             if s:
                 effects.append(s)
             elif valideffect(l):
                 effects.append(l)
         effects = ' '.join(effects)
         if effects:
             return '\n'.join([render_effects(s, effects)
                               for s in msg.split('\n')])
         return msg
 
 def uisetup(ui):
     if ui.plain():
         return
     if not isinstance(ui, colorui):
         colorui.__bases__ = (ui.__class__,)
         ui.__class__ = colorui
     def colorcmd(orig, ui_, opts, cmd, cmdfunc):
         mode = _modesetup(ui_, opts['color'])
         colorui._colormode = mode
         if mode and mode != 'debug':
             extstyles()
             configstyles(ui_)
         return orig(ui_, opts, cmd, cmdfunc)
     def colorgit(orig, gitsub, commands, env=None, stream=False, cwd=None):
         if gitsub.ui._colormode and len(commands) and commands[0] == "diff":
                 # insert the argument in the front,
                 # the end of git diff arguments is used for paths
                 commands.insert(1, '--color')
         return orig(gitsub, commands, env, stream, cwd)
     extensions.wrapfunction(dispatch, '_runcommand', colorcmd)
     extensions.wrapfunction(subrepo.gitsubrepo, '_gitnodir', colorgit)
 
 def extsetup(ui):
     commands.globalopts.append(
         ('', 'color', 'auto',
          # i18n: 'always', 'auto', 'never', and 'debug' are keywords
          # and should not be translated
          _("when to colorize (boolean, always, auto, never, or debug)"),
          _('TYPE')))
 
 @command('debugcolor', [], 'hg debugcolor')
 def debugcolor(ui, repo, **opts):
     global _styles
     _styles = {}
     for effect in _effects.keys():
         _styles[effect] = effect
+    if _terminfo_params:
+        for k, v in ui.configitems('color'):
+            if k.startswith('color.'):
+                _styles[k] = k[6:]
+            elif k.startswith('terminfo.'):
+                _styles[k] = k[9:]
     ui.write(('color mode: %s\n') % ui._colormode)
     ui.write(_('available colors:\n'))
-    for label, colors in _styles.items():
-        ui.write(('%s\n') % colors, label=label)
+    for colorname, label in _styles.items():
+        ui.write(('%s\n') % colorname, label=label)
 
 if os.name != 'nt':
     w32effects = None
 else:
     import ctypes
     import re
 
     _kernel32 = ctypes.windll.kernel32
 
     _WORD = ctypes.c_ushort
 
     _INVALID_HANDLE_VALUE = -1
 
     class _COORD(ctypes.Structure):
         _fields_ = [('X', ctypes.c_short),
                     ('Y', ctypes.c_short)]
 
     class _SMALL_RECT(ctypes.Structure):
         _fields_ = [('Left', ctypes.c_short),
                     ('Top', ctypes.c_short),
                     ('Right', ctypes.c_short),
                     ('Bottom', ctypes.c_short)]
 
     class _CONSOLE_SCREEN_BUFFER_INFO(ctypes.Structure):
         _fields_ = [('dwSize', _COORD),
                     ('dwCursorPosition', _COORD),
                     ('wAttributes', _WORD),
                     ('srWindow', _SMALL_RECT),
                     ('dwMaximumWindowSize', _COORD)]
 
-    _STD_OUTPUT_HANDLE = 0xfffffff5L # (DWORD)-11
-    _STD_ERROR_HANDLE = 0xfffffff4L  # (DWORD)-12
+    _STD_OUTPUT_HANDLE = 0xfffffff5 # (DWORD)-11
+    _STD_ERROR_HANDLE = 0xfffffff4  # (DWORD)-12
 
     _FOREGROUND_BLUE = 0x0001
     _FOREGROUND_GREEN = 0x0002
     _FOREGROUND_RED = 0x0004
     _FOREGROUND_INTENSITY = 0x0008
 
     _BACKGROUND_BLUE = 0x0010
     _BACKGROUND_GREEN = 0x0020
     _BACKGROUND_RED = 0x0040
     _BACKGROUND_INTENSITY = 0x0080
 
     _COMMON_LVB_REVERSE_VIDEO = 0x4000
     _COMMON_LVB_UNDERSCORE = 0x8000
 
     # http://msdn.microsoft.com/en-us/library/ms682088%28VS.85%29.aspx
     w32effects = {
         'none': -1,
         'black': 0,
         'red': _FOREGROUND_RED,
         'green': _FOREGROUND_GREEN,
         'yellow': _FOREGROUND_RED | _FOREGROUND_GREEN,
         'blue': _FOREGROUND_BLUE,
         'magenta': _FOREGROUND_BLUE | _FOREGROUND_RED,
         'cyan': _FOREGROUND_BLUE | _FOREGROUND_GREEN,
         'white': _FOREGROUND_RED | _FOREGROUND_GREEN | _FOREGROUND_BLUE,
         'bold': _FOREGROUND_INTENSITY,
         'black_background': 0x100,                  # unused value > 0x0f
         'red_background': _BACKGROUND_RED,
         'green_background': _BACKGROUND_GREEN,
         'yellow_background': _BACKGROUND_RED | _BACKGROUND_GREEN,
         'blue_background': _BACKGROUND_BLUE,
         'purple_background': _BACKGROUND_BLUE | _BACKGROUND_RED,
         'cyan_background': _BACKGROUND_BLUE | _BACKGROUND_GREEN,
         'white_background': (_BACKGROUND_RED | _BACKGROUND_GREEN |
                              _BACKGROUND_BLUE),
         'bold_background': _BACKGROUND_INTENSITY,
         'underline': _COMMON_LVB_UNDERSCORE,  # double-byte charsets only
         'inverse': _COMMON_LVB_REVERSE_VIDEO, # double-byte charsets only
     }
 
     passthrough = set([_FOREGROUND_INTENSITY,
                        _BACKGROUND_INTENSITY,
                        _COMMON_LVB_UNDERSCORE,
                        _COMMON_LVB_REVERSE_VIDEO])
 
     stdout = _kernel32.GetStdHandle(
                   _STD_OUTPUT_HANDLE)  # don't close the handle returned
     if stdout is None or stdout == _INVALID_HANDLE_VALUE:
         w32effects = None
     else:
         csbi = _CONSOLE_SCREEN_BUFFER_INFO()
         if not _kernel32.GetConsoleScreenBufferInfo(
                     stdout, ctypes.byref(csbi)):
             # stdout may not support GetConsoleScreenBufferInfo()
             # when called from subprocess or redirected
             w32effects = None
         else:
             origattr = csbi.wAttributes
             ansire = re.compile('\033\[([^m]*)m([^\033]*)(.*)',
                                 re.MULTILINE | re.DOTALL)
 
     def win32print(text, orig, **opts):
         label = opts.get('label', '')
         attr = origattr
 
         def mapcolor(val, attr):
             if val == -1:
                 return origattr
             elif val in passthrough:
                 return attr | val
             elif val > 0x0f:
                 return (val & 0x70) | (attr & 0x8f)
             else:
                 return (val & 0x07) | (attr & 0xf8)
 
         # determine console attributes based on labels
         for l in label.split():
             style = _styles.get(l, '')
             for effect in style.split():
                 try:
                     attr = mapcolor(w32effects[effect], attr)
                 except KeyError:
                     # w32effects could not have certain attributes so we skip
                     # them if not found
                     pass
         # hack to ensure regexp finds data
         if not text.startswith('\033['):
             text = '\033[m' + text
 
         # Look for ANSI-like codes embedded in text
         m = re.match(ansire, text)
 
         try:
             while m:
                 for sattr in m.group(1).split(';'):
                     if sattr:
                         attr = mapcolor(int(sattr), attr)
                 _kernel32.SetConsoleTextAttribute(stdout, attr)
                 orig(m.group(2), **opts)
                 m = re.match(ansire, m.group(3))
         finally:
             # Explicitly reset original attributes
             _kernel32.SetConsoleTextAttribute(stdout, origattr)

hgext/convert/__init__.py

@@ -1,458 +1,458 b''
 # convert.py Foreign SCM converter
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''import revisions from foreign VCS repositories into Mercurial'''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     registrar,
 )
 
 from . import (
     convcmd,
     cvsps,
     subversion,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 @command('convert',
     [('', 'authors', '',
       _('username mapping filename (DEPRECATED) (use --authormap instead)'),
       _('FILE')),
     ('s', 'source-type', '', _('source repository type'), _('TYPE')),
     ('d', 'dest-type', '', _('destination repository type'), _('TYPE')),
     ('r', 'rev', [], _('import up to source revision REV'), _('REV')),
     ('A', 'authormap', '', _('remap usernames using this file'), _('FILE')),
     ('', 'filemap', '', _('remap file names using contents of file'),
      _('FILE')),
     ('', 'full', None,
      _('apply filemap changes by converting all files again')),
     ('', 'splicemap', '', _('splice synthesized history into place'),
      _('FILE')),
     ('', 'branchmap', '', _('change branch names while converting'),
      _('FILE')),
     ('', 'branchsort', None, _('try to sort changesets by branches')),
     ('', 'datesort', None, _('try to sort changesets by date')),
     ('', 'sourcesort', None, _('preserve source changesets order')),
     ('', 'closesort', None, _('try to reorder closed revisions'))],
    _('hg convert [OPTION]... SOURCE [DEST [REVMAP]]'),
    norepo=True)
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
 
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
     - Perforce [p4]
 
     Accepted destination formats [identifiers]:
 
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted.
     Otherwise, convert will only import up to the named revision
     (given in a format understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with ``-hg`` appended. If the destination
     repository doesn't exist, it will be created.
 
     By default, all sources except Mercurial will use --branchsort.
     Mercurial uses --sourcesort to preserve original revision numbers
     order. Sort modes have the following effects:
 
     --branchsort  convert from parent to child revision when possible,
                   which means branches are usually converted one after
                   the other. It generates more compact repositories.
 
     --datesort    sort revisions by date. Converted repositories have
                   good-looking changelogs but are often an order of
                   magnitude larger than the same ones generated by
                   --branchsort.
 
     --sourcesort  try to preserve source revisions order, only
                   supported by Mercurial sources.
 
     --closesort   try to move closed revisions as close as possible
                   to parent branches, only supported by Mercurial
                   sources.
 
     If ``REVMAP`` isn't given, it will be put in a default location
     (``<dest>/.hg/shamap`` by default). The ``REVMAP`` is a simple
     text file that maps each source commit ID to the destination ID
     for that revision, like so::
 
       <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created. It's
     updated on each commit copied, so :hg:`convert` can be interrupted
     and can be run repeatedly to copy new commits.
 
     The authormap is a simple text file that maps each source commit
     author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (e.g.: CVS). One line per
     author mapping and the line format is::
 
       source author = destination author
 
     Empty lines and lines starting with a ``#`` are ignored.
 
     The filemap is a file that allows filtering and remapping of files
     and directories. Each line can contain one of the following
     directives::
 
       include path/to/file-or-dir
 
       exclude path/to/file-or-dir
 
       rename path/to/source path/to/destination
 
     Comment lines start with ``#``. A specified path matches if it
     equals the full relative name of a file or one of its parent
     directories. The ``include`` or ``exclude`` directive with the
     longest matching path applies, so line order does not matter.
 
     The ``include`` directive causes a file, or all files under a
     directory, to be included in the destination repository. The default
     if there are no ``include`` statements is to include everything.
     If there are any ``include`` statements, nothing else is included.
     The ``exclude`` directive causes files or directories to
     be omitted. The ``rename`` directive renames a file or directory if
     it is converted. To rename from a subdirectory into the root of
     the repository, use ``.`` as the path to rename to.
 
     ``--full`` will make sure the converted changesets contain exactly
     the right files with the right content. It will make a full
     conversion of all files, not just the ones that have
     changed. Files that already are correct will not be changed. This
     can be used to apply filemap changes when converting
     incrementally. This is currently only supported for Mercurial and
     Subversion.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision. This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together. Each entry
     contains a key, followed by a space, followed by one or two
     comma-separated values::
 
       key parent1, parent2
 
     The key is the revision ID in the source
     revision control system whose parents should be modified (same
     format as a key in .hg/shamap). The values are the revision IDs
     (in either the source or destination revision control system) that
     should be used as the new parents for that node. For example, if
     you have merged "release-1.0" into "trunk", then you should
     specify the revision on "trunk" as the first parent and the one on
     the "release-1.0" branch as the second.
 
     The branchmap is a file that allows you to rename a branch when it is
     being brought in from whatever external repository. When used in
     conjunction with a splicemap, it allows for a powerful combination
     to help fix even the most badly mismanaged repositories and turn them
     into nicely structured Mercurial repositories. The branchmap contains
     lines of the form::
 
       original_branch_name new_branch_name
 
     where "original_branch_name" is the name of the branch in the
     source repository, and "new_branch_name" is the name of the branch
     is the destination repository. No whitespace is allowed in the
     branch names. This can be used to (for instance) move code in one
     repository from "default" to a named branch.
 
     Mercurial Source
     ################
 
     The Mercurial source recognizes the following configuration
     options, which you can set on the command line with ``--config``:
 
     :convert.hg.ignoreerrors: ignore integrity errors when reading.
         Use it to fix Mercurial repositories with missing revlogs, by
         converting from and to Mercurial. Default is False.
 
     :convert.hg.saverev: store original revision ID in changeset
         (forces target IDs to change). It takes a boolean argument and
         defaults to False.
 
     :convert.hg.startrev: specify the initial Mercurial revision.
         The default is 0.
 
     :convert.hg.revs: revset specifying the source revisions to convert.
 
     CVS Source
     ##########
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course the
     repository is ``:local:``. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganization in the CVS
     sandbox is ignored.
 
     The following options can be used with ``--config``:
 
     :convert.cvsps.cache: Set to False to disable remote log caching,
         for testing and debugging purposes. Default is True.
 
     :convert.cvsps.fuzz: Specify the maximum time (in seconds) that is
         allowed between commits with identical user and log message in
         a single changeset. When very large files were checked in as
         part of a changeset then the default may not be long enough.
         The default is 60.
 
     :convert.cvsps.mergeto: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will insert a dummy revision merging the
         branch on which this log message occurs to the branch
         indicated in the regex. Default is ``{{mergetobranch
         ([-\\w]+)}}``
 
     :convert.cvsps.mergefrom: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will add the most recent revision on the
         branch indicated in the regex as the second parent of the
         changeset. Default is ``{{mergefrombranch ([-\\w]+)}}``
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     :hooks.cvslog: Specify a Python function to be called at the end of
         gathering the CVS log. The function is passed a list with the
         log entries, and can modify the entries in-place, or add or
         delete them.
 
     :hooks.cvschangesets: Specify a Python function to be called after
         the changesets are calculated from the CVS log. The
         function is passed a list with the changeset entries, and can
         modify the changesets in-place, or add or delete them.
 
     An additional "debugcvsps" Mercurial command allows the builtin
     changeset merging code to be run without doing a conversion. Its
     parameters and output are similar to that of cvsps 2.1. Please see
     the command help for more details.
 
     Subversion Source
     #################
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied ``svn://repo/path/`` source URL is
     converted as a single branch. If ``svn://repo/path/trunk`` exists
     it replaces the default branch. If ``svn://repo/path/branches``
     exists, its subdirectories are listed as possible branches. If
     ``svn://repo/path/tags`` exists, it is looked for tags referencing
     converted branches. Default ``trunk``, ``branches`` and ``tags``
     values can be overridden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable auto
     detection.
 
     The following options can be set with ``--config``:
 
     :convert.svn.branches: specify the directory containing branches.
         The default is ``branches``.
 
     :convert.svn.tags: specify the directory containing tags. The
         default is ``tags``.
 
     :convert.svn.trunk: specify the name of the trunk branch. The
         default is ``trunk``.
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     :convert.svn.startrev: specify start Subversion revision number.
         The default is 0.
 
     Git Source
     ##########
 
     The Git importer converts commits from all reachable branches (refs
     in refs/heads) and remotes (refs in refs/remotes) to Mercurial.
     Branches are converted to bookmarks with the same name, with the
     leading 'refs/heads' stripped. Git submodules are converted to Git
     subrepos in Mercurial.
 
     The following options can be set with ``--config``:
 
     :convert.git.similarity: specify how similar files modified in a
         commit must be to be imported as renames or copies, as a
         percentage between ``0`` (disabled) and ``100`` (files must be
         identical). For example, ``90`` means that a delete/add pair will
         be imported as a rename if more than 90% of the file hasn't
         changed. The default is ``50``.
 
     :convert.git.findcopiesharder: while detecting copies, look at all
         files in the working copy instead of just changed ones. This
         is very expensive for large projects, and is only effective when
         ``convert.git.similarity`` is greater than 0. The default is False.
 
     :convert.git.remoteprefix: remote refs are converted as bookmarks with
         ``convert.git.remoteprefix`` as a prefix followed by a /. The default
         is 'remote'.
 
     :convert.git.skipsubmodules: does not convert root level .gitmodules files
         or files with 160000 mode indicating a submodule. Default is False.
 
     Perforce Source
     ###############
 
     The Perforce (P4) importer can be given a p4 depot path or a
     client specification as source. It will convert all files in the
     source to a flat Mercurial repository, ignoring labels, branches
     and integrations. Note that when a depot path is given you then
     usually should specify a target directory, because otherwise the
     target may be named ``...-hg``.
 
     The following options can be set with ``--config``:
 
     :convert.p4.encoding: specify the encoding to use when decoding standard
         output of the Perforce command line tool. The default is default system
         encoding.
 
     :convert.p4.startrev: specify initial Perforce revision (a
         Perforce changelist number).
 
     Mercurial Destination
     #####################
 
     The Mercurial destination will recognize Mercurial subrepositories in the
     destination directory, and update the .hgsubstate file automatically if the
     destination subrepositories contain the <dest>/<sub>/.hg/shamap file.
     Converting a repository with subrepositories requires converting a single
     repository at a time, from the bottom up.
 
     .. container:: verbose
 
        An example showing how to convert a repository with subrepositories::
 
          # so convert knows the type when it sees a non empty destination
          $ hg init converted
 
          $ hg convert orig/sub1 converted/sub1
          $ hg convert orig/sub2 converted/sub2
          $ hg convert orig converted
 
     The following options are supported:
 
     :convert.hg.clonebranches: dispatch source branches in separate
         clones. The default is False.
 
     :convert.hg.tagsbranch: branch name for tag revisions, defaults to
         ``default``.
 
     :convert.hg.usebranchnames: preserve branch names. The default is
         True.
 
     :convert.hg.sourcename: records the given string as a 'convert_source' extra
         value on each commit made in the target repository. The default is None.
 
     All Destinations
     ################
 
     All destination types accept the following options:
 
     :convert.skiptags: does not convert tags from the source repo to the target
         repo. The default is False.
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 @command('debugsvnlog', [], 'hg debugsvnlog', norepo=True)
 def debugsvnlog(ui, **opts):
     return subversion.debugsvnlog(ui, **opts)
 
 @command('debugcvsps',
     [
     # Main options shared with cvsps-2.1
     ('b', 'branches', [], _('only return changes on specified branches')),
     ('p', 'prefix', '', _('prefix to remove from file names')),
     ('r', 'revisions', [],
      _('only return changes after or between specified tags')),
     ('u', 'update-cache', None, _("update cvs log cache")),
     ('x', 'new-cache', None, _("create new cvs log cache")),
     ('z', 'fuzz', 60, _('set commit time fuzz in seconds')),
     ('', 'root', '', _('specify cvsroot')),
     # Options specific to builtin cvsps
     ('', 'parents', '', _('show parent changesets')),
     ('', 'ancestors', '', _('show current changeset in ancestor branches')),
     # Options that are ignored for compatibility with cvsps-2.1
     ('A', 'cvs-direct', None, _('ignored for compatibility')),
     ],
     _('hg debugcvsps [OPTION]... [PATH]...'),
     norepo=True)
 def debugcvsps(ui, *args, **opts):
     '''create changeset information from CVS
 
     This command is intended as a debugging tool for the CVS to
     Mercurial converter, and can be used as a direct replacement for
     cvsps.
 
     Hg debugcvsps reads the CVS rlog for current directory (or any
     named directory) in the CVS repository, and converts the log to a
     series of changesets based on matching commit log entries and
     dates.'''
     return cvsps.debugcvsps(ui, *args, **opts)
 
 def kwconverted(ctx, name):
     rev = ctx.extra().get('convert_revision', '')
     if rev.startswith('svn:'):
         if name == 'svnrev':
             return str(subversion.revsplit(rev)[2])
         elif name == 'svnpath':
             return subversion.revsplit(rev)[1]
         elif name == 'svnuuid':
             return subversion.revsplit(rev)[0]
     return rev
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('svnrev')
 def kwsvnrev(repo, ctx, **args):
     """String. Converted subversion revision number."""
     return kwconverted(ctx, 'svnrev')
 
 @templatekeyword('svnpath')
 def kwsvnpath(repo, ctx, **args):
     """String. Converted subversion revision project path."""
     return kwconverted(ctx, 'svnpath')
 
 @templatekeyword('svnuuid')
 def kwsvnuuid(repo, ctx, **args):
     """String. Converted subversion revision repository identifier."""
     return kwconverted(ctx, 'svnuuid')
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [kwsvnrev, kwsvnpath, kwsvnuuid]

hgext/convert/subversion.py

@@ -1,1354 +1,1354 b''
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 from __future__ import absolute_import
 
 import os
 import re
 import sys
 import tempfile
 import xml.dom.minidom
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     scmutil,
     strutil,
     util,
 )
 
 from . import common
 
 pickle = util.pickle
 stringio = util.stringio
 propertycache = util.propertycache
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 commandline = common.commandline
 commit = common.commit
 converter_sink = common.converter_sink
 converter_source = common.converter_source
 decodeargs = common.decodeargs
 encodeargs = common.encodeargs
 makedatetimestamp = common.makedatetimestamp
 mapfile = common.mapfile
 MissingTool = common.MissingTool
 NoRepo = common.NoRepo
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 try:
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     from . import transport
     import warnings
     warnings.filterwarnings('ignore',
             module='svn.core',
             category=DeprecationWarning)
     svn.core.SubversionException # trigger import to catch error
 
 except ImportError:
     svn = None
 
 class SvnPathNotFound(Exception):
     pass
 
 def revsplit(rev):
     """Parse a revision string and return (uuid, path, revnum).
     >>> revsplit('svn:a2147622-4a9f-4db4-a8d3-13562ff547b2'
     ...          '/proj%20B/mytrunk/mytrunk@1')
     ('a2147622-4a9f-4db4-a8d3-13562ff547b2', '/proj%20B/mytrunk/mytrunk', 1)
     >>> revsplit('svn:8af66a51-67f5-4354-b62c-98d67cc7be1d@1')
     ('', '', 1)
     >>> revsplit('@7')
     ('', '', 7)
     >>> revsplit('7')
     ('', '', 0)
     >>> revsplit('bad')
     ('', '', 0)
     """
     parts = rev.rsplit('@', 1)
     revnum = 0
     if len(parts) > 1:
         revnum = int(parts[1])
     parts = parts[0].split('/', 1)
     uuid = ''
     mod = ''
     if len(parts) > 1 and parts[0].startswith('svn:'):
         uuid = parts[0][4:]
         mod = '/' + parts[1]
     return uuid, mod, revnum
 
 def quote(s):
     # As of svn 1.7, many svn calls expect "canonical" paths. In
     # theory, we should call svn.core.*canonicalize() on all paths
     # before passing them to the API.  Instead, we assume the base url
     # is canonical and copy the behaviour of svn URL encoding function
     # so we can extend it safely with new components. The "safe"
     # characters were taken from the "svn_uri__char_validity" table in
     # libsvn_subr/path.c.
     return urlreq.quote(s, "!$&'()*+,-./:=@_~")
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except svn.core.SubversionException:
         # svn.client.url_from_path() fails with local repositories
         pass
     if os.path.isdir(path):
         path = os.path.normpath(os.path.abspath(path))
         if os.name == 'nt':
             path = '/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
         path = encoding.tolocal(path)
         path = 'file://%s' % quote(path)
     return svn.core.svn_path_canonicalize(path)
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         paths = {}
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 paths[k] = changedpath(v)
         pickle.dump((paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except IOError:
         # Caller may interrupt the iteration
         pickle.dump(None, fp, protocol)
     except Exception as inst:
         pickle.dump(str(inst), fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.close()
     # With large history, cleanup process goes crazy and suddenly
     # consumes *huge* amount of memory. The output file being closed,
     # there is no need for clean termination.
     os._exit(0)
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     if svn is None:
         raise error.Abort(_('debugsvnlog could not load Subversion python '
                            'bindings'))
 
     util.setbinary(sys.stdin)
     util.setbinary(sys.stdout)
     args = decodeargs(sys.stdin.read())
     get_log_child(sys.stdout, *args)
 
 class logstream(object):
     """Interruptible revision log iterator."""
     def __init__(self, stdout):
         self._stdout = stdout
 
     def __iter__(self):
         while True:
             try:
                 entry = pickle.load(self._stdout)
             except EOFError:
                 raise error.Abort(_('Mercurial failed to run itself, check'
                                    ' hg executable is in PATH'))
             try:
                 orig_paths, revnum, author, date, message = entry
             except (TypeError, ValueError):
                 if entry is None:
                     break
                 raise error.Abort(_("log stream exception '%s'") % entry)
             yield entry
 
     def close(self):
         if self._stdout:
             self._stdout.close()
             self._stdout = None
 
 class directlogstream(list):
     """Direct revision log iterator.
     This can be used for debugging and development but it will probably leak
     memory and is not suitable for real conversions."""
     def __init__(self, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
 
         def receiver(orig_paths, revnum, author, date, message, pool):
             paths = {}
             if orig_paths is not None:
                 for k, v in orig_paths.iteritems():
                     paths[k] = changedpath(v)
             self.append((paths, revnum, author, date, message))
 
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
 
     def close(self):
         pass
 
 # Check to see if the given path is a local Subversion repo. Verify this by
 # looking for several svn-specific files and directories in the given
 # directory.
 def filecheck(ui, path, proto):
     for x in ('locks', 'hooks', 'format', 'db'):
         if not os.path.exists(os.path.join(path, x)):
             return False
     return True
 
 # Check to see if a given path is the root of an svn repo over http. We verify
 # this by requesting a version-controlled URL we know can't exist and looking
 # for the svn-specific "not found" XML.
 def httpcheck(ui, path, proto):
     try:
         opener = urlreq.buildopener()
         rsp = opener.open('%s://%s/!svn/ver/0/.svn' % (proto, path))
         data = rsp.read()
     except urlerr.httperror as inst:
         if inst.code != 404:
             # Except for 404 we cannot know for sure this is not an svn repo
             ui.warn(_('svn: cannot probe remote repository, assume it could '
                       'be a subversion repository. Use --source-type if you '
                       'know better.\n'))
             return True
         data = inst.fp.read()
     except Exception:
         # Could be urlerr.urlerror if the URL is invalid or anything else.
         return False
     return '<m:human-readable errcode="160013">' in data
 
 protomap = {'http': httpcheck,
             'https': httpcheck,
             'file': filecheck,
             }
 def issvnurl(ui, url):
     try:
         proto, path = url.split('://', 1)
         if proto == 'file':
             if (os.name == 'nt' and path[:1] == '/' and path[1:2].isalpha()
                 and path[2:6].lower() == '%3a/'):
                 path = path[:2] + ':/' + path[6:]
             path = urlreq.url2pathname(path)
     except ValueError:
         proto = 'file'
         path = os.path.abspath(url)
     if proto == 'file':
         path = util.pconvert(path)
     check = protomap.get(proto, lambda *args: False)
     while '/' in path:
         if check(ui, path, proto):
             return True
         path = path.rsplit('/', 1)[0]
     return False
 
 # SVN conversion code stolen from bzr-svn and tailor
 #
 # Subversion looks like a versioned filesystem, branches structures
 # are defined by conventions and not enforced by the tool. First,
 # we define the potential branches (modules) as "trunk" and "branches"
 # children directories. Revisions are then identified by their
 # module and revision number (and a repository identifier).
 #
 # The revision graph is really a tree (or a forest). By default, a
 # revision parent is the previous revision in the same module. If the
 # module directory is copied/moved from another module then the
 # revision is the module root and its parent the source revision in
 # the parent module. A revision has at most one parent.
 #
 class svn_source(converter_source):
     def __init__(self, ui, url, revs=None):
         super(svn_source, self).__init__(ui, url, revs=revs)
 
         if not (url.startswith('svn://') or url.startswith('svn+ssh://') or
                 (os.path.exists(url) and
                  os.path.exists(os.path.join(url, '.svn'))) or
                 issvnurl(ui, url)):
             raise NoRepo(_("%s does not look like a Subversion repository")
                          % url)
         if svn is None:
             raise MissingTool(_('could not load Subversion python bindings'))
 
         try:
             version = svn.core.SVN_VER_MAJOR, svn.core.SVN_VER_MINOR
             if version < (1, 4):
                 raise MissingTool(_('Subversion python bindings %d.%d found, '
                                     '1.4 or later required') % version)
         except AttributeError:
             raise MissingTool(_('Subversion python bindings are too old, 1.4 '
                                 'or later required'))
 
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at + 1:])
                 url = url[:at]
         except ValueError:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.baseurl = svn.ra.get_repos_root(self.ra)
             # Module is either empty or a repository path starting with
             # a slash and not ending with a slash.
             self.module = urlreq.unquote(self.url[len(self.baseurl):])
             self.prevmodule = None
             self.rootmodule = self.module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra)
         except svn.core.SubversionException:
             ui.traceback()
             svnversion = '%d.%d.%d' % (svn.core.SVN_VER_MAJOR,
                                        svn.core.SVN_VER_MINOR,
                                        svn.core.SVN_VER_MICRO)
             raise NoRepo(_("%s does not look like a Subversion repository "
                            "to libsvn version %s")
                          % (self.url, svnversion))
 
         if revs:
             if len(revs) > 1:
                 raise error.Abort(_('subversion source does not support '
                                    'specifying multiple revisions'))
             try:
                 latest = int(revs[0])
             except ValueError:
                 raise error.Abort(_('svn: revision %s is not an integer') %
                                  revs[0])
 
         self.trunkname = self.ui.config('convert', 'svn.trunk',
                                         'trunk').strip('/')
         self.startrev = self.ui.config('convert', 'svn.startrev', default=0)
         try:
             self.startrev = int(self.startrev)
             if self.startrev < 0:
                 self.startrev = 0
         except ValueError:
             raise error.Abort(_('svn: start revision %s is not an integer')
                              % self.startrev)
 
         try:
             self.head = self.latest(self.module, latest)
         except SvnPathNotFound:
             self.head = None
         if not self.head:
             raise error.Abort(_('no revision found in module %s')
                              % self.module)
         self.last_changed = self.revnum(self.head)
 
         self._changescache = (None, None)
 
         if os.path.exists(os.path.join(url, '.svn/entries')):
             self.wc = url
         else:
             self.wc = None
         self.convertfp = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.iterkeys():
             uuid, module, revnum = revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + quote(path),
                                  optrev, False, self.ctx)
             return True
         except svn.core.SubversionException:
             return False
 
     def getheads(self):
 
         def isdir(path, revnum):
             kind = self._checkpath(path, revnum)
             return kind == svn.core.svn_node_dir
 
         def getcfgpath(name, rev):
             cfgpath = self.ui.config('convert', 'svn.' + name)
             if cfgpath is not None and cfgpath.strip() == '':
                 return None
             path = (cfgpath or name).strip('/')
             if not self.exists(path, rev):
                 if self.module.endswith(path) and name == 'trunk':
                     # we are converting from inside this directory
                     return None
                 if cfgpath:
                     raise error.Abort(_('expected %s to be at %r, but not found'
                                        ) % (name, path))
                 return None
             self.ui.note(_('found %s at %r\n') % (name, path))
             return path
 
         rev = optrev(self.last_changed)
         oldmodule = ''
         trunk = getcfgpath('trunk', rev)
         self.tags = getcfgpath('tags', rev)
         branches = getcfgpath('branches', rev)
 
         # If the project has a trunk or branches, we will extract heads
         # from them. We keep the project root otherwise.
         if trunk:
             oldmodule = self.module or ''
             self.module += '/' + trunk
             self.head = self.latest(self.module, self.last_changed)
             if not self.head:
                 raise error.Abort(_('no revision found in module %s')
                                  % self.module)
 
         # First head in the list is the module's head
         self.heads = [self.head]
         if self.tags is not None:
             self.tags = '%s/%s' % (oldmodule , (self.tags or 'tags'))
 
         # Check if branches bring a few more heads to the list
         if branches:
             rpath = self.url.strip('/')
             branchnames = svn.client.ls(rpath + '/' + quote(branches),
                                         rev, False, self.ctx)
             for branch in sorted(branchnames):
                 module = '%s/%s/%s' % (oldmodule, branches, branch)
                 if not isdir(module, self.last_changed):
                     continue
                 brevid = self.latest(module, self.last_changed)
                 if not brevid:
                     self.ui.note(_('ignoring empty branch %s\n') % branch)
                     continue
                 self.ui.note(_('found branch %s at %d\n') %
                              (branch, self.revnum(brevid)))
                 self.heads.append(brevid)
 
         if self.startrev and self.heads:
             if len(self.heads) > 1:
                 raise error.Abort(_('svn: start revision is not supported '
                                    'with more than one branch'))
             revnum = self.revnum(self.heads[0])
             if revnum < self.startrev:
                 raise error.Abort(
                     _('svn: no revision found after start revision %d')
                                  % self.startrev)
 
         return self.heads
 
     def _getchanges(self, rev, full):
         (paths, parents) = self.paths[rev]
         copies = {}
         if parents:
             files, self.removed, copies = self.expandpaths(rev, paths, parents)
         if full or not parents:
             # Perform a full checkout on roots
             uuid, module, revnum = revsplit(rev)
             entries = svn.client.ls(self.baseurl + quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
             self.removed = set()
 
         files.sort()
         files = zip(files, [rev] * len(files))
         return (files, copies)
 
     def getchanges(self, rev, full):
         # reuse cache from getchangedfiles
         if self._changescache[0] == rev and not full:
             (files, copies) = self._changescache[1]
         else:
             (files, copies) = self._getchanges(rev, full)
             # caller caches the result, so free it here to release memory
             del self.paths[rev]
         return (files, copies, set())
 
     def getchangedfiles(self, rev, i):
         # called from filemap - cache computed values for reuse in getchanges
         (files, copies) = self._getchanges(rev, False)
         self._changescache = (rev, (files, copies))
         return [f[0] for f in files]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = revsplit(rev)
             self.module = module
             self.reparent(module)
             # We assume that:
             # - requests for revisions after "stop" come from the
             # revision graph backward traversal. Cache all of them
             # down to stop, they will be used eventually.
             # - requests for revisions before "stop" come to get
             # isolated branches parents. Just fetch what is needed.
             stop = self.lastrevs.get(module, 0)
             if revnum < stop:
                 stop = revnum + 1
             self._fetch_revisions(revnum, stop)
             if rev not in self.commits:
                 raise error.Abort(_('svn: revision %s not found') % revnum)
         revcommit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return revcommit
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ fails if revision format does not match the correct format"""
         if not re.match(r'svn:[0-9a-f]{8,8}-[0-9a-f]{4,4}-'
-                              '[0-9a-f]{4,4}-[0-9a-f]{4,4}-[0-9a-f]'
-                              '{12,12}(.*)\@[0-9]+$',revstr):
+                              r'[0-9a-f]{4,4}-[0-9a-f]{4,4}-[0-9a-f]'
+                              r'{12,12}(.*)\@[0-9]+$',revstr):
             raise error.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def numcommits(self):
         return int(self.head.rsplit('@', 1)[1]) - self.startrev
 
     def gettags(self):
         tags = {}
         if self.tags is None:
             return tags
 
         # svn tags are just a convention, project branches left in a
         # 'tags' directory. There is no other relationship than
         # ancestry, which is expensive to discover and makes them hard
         # to update incrementally.  Worse, past revisions may be
         # referenced by tags far away in the future, requiring a deep
         # history traversal on every calculation.  Current code
         # performs a single backward traversal, tracking moves within
         # the tags directory (tag renaming) and recording a new tag
         # everytime a project is copied from outside the tags
         # directory. It also lists deleted tags, this behaviour may
         # change in the future.
         pendings = []
         tagspath = self.tags
         start = svn.ra.get_latest_revnum(self.ra)
         stream = self._getlog([self.tags], start, self.startrev)
         try:
             for entry in stream:
                 origpaths, revnum, author, date, message = entry
                 if not origpaths:
                     origpaths = []
                 copies = [(e.copyfrom_path, e.copyfrom_rev, p) for p, e
                           in origpaths.iteritems() if e.copyfrom_path]
                 # Apply moves/copies from more specific to general
                 copies.sort(reverse=True)
 
                 srctagspath = tagspath
                 if copies and copies[-1][2] == tagspath:
                     # Track tags directory moves
                     srctagspath = copies.pop()[0]
 
                 for source, sourcerev, dest in copies:
                     if not dest.startswith(tagspath + '/'):
                         continue
                     for tag in pendings:
                         if tag[0].startswith(dest):
                             tagpath = source + tag[0][len(dest):]
                             tag[:2] = [tagpath, sourcerev]
                             break
                     else:
                         pendings.append([source, sourcerev, dest])
 
                 # Filter out tags with children coming from different
                 # parts of the repository like:
                 # /tags/tag.1 (from /trunk:10)
                 # /tags/tag.1/foo (from /branches/foo:12)
                 # Here/tags/tag.1 discarded as well as its children.
                 # It happens with tools like cvs2svn. Such tags cannot
                 # be represented in mercurial.
                 addeds = dict((p, e.copyfrom_path) for p, e
                               in origpaths.iteritems()
                               if e.action == 'A' and e.copyfrom_path)
                 badroots = set()
                 for destroot in addeds:
                     for source, sourcerev, dest in pendings:
                         if (not dest.startswith(destroot + '/')
                             or source.startswith(addeds[destroot] + '/')):
                             continue
                         badroots.add(destroot)
                         break
 
                 for badroot in badroots:
                     pendings = [p for p in pendings if p[2] != badroot
                                 and not p[2].startswith(badroot + '/')]
 
                 # Tell tag renamings from tag creations
                 renamings = []
                 for source, sourcerev, dest in pendings:
                     tagname = dest.split('/')[-1]
                     if source.startswith(srctagspath):
                         renamings.append([source, sourcerev, tagname])
                         continue
                     if tagname in tags:
                         # Keep the latest tag value
                         continue
                     # From revision may be fake, get one with changes
                     try:
                         tagid = self.latest(source, sourcerev)
                         if tagid and tagname not in tags:
                             tags[tagname] = tagid
                     except SvnPathNotFound:
                         # It happens when we are following directories
                         # we assumed were copied with their parents
                         # but were really created in the tag
                         # directory.
                         pass
                 pendings = renamings
                 tagspath = srctagspath
         finally:
             stream.close()
         return tags
 
     def converted(self, rev, destrev):
         if not self.wc:
             return
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.wc, '.svn', 'hg-shamap'),
                                   'a')
         self.convertfp.write('%s %d\n' % (destrev, self.revnum(rev)))
         self.convertfp.flush()
 
     def revid(self, revnum, module=None):
         return 'svn:%s%s@%s' % (self.uuid, module or self.module, revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def latest(self, path, stop=None):
         """Find the latest revid affecting path, up to stop revision
         number. If stop is None, default to repository latest
         revision. It may return a revision in a different module,
         since a branch may be moved without a change being
         reported. Return None if computed module does not belong to
         rootmodule subtree.
         """
         def findchanges(path, start, stop=None):
             stream = self._getlog([path], start, stop or 1)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if stop is None and paths:
                         # We do not know the latest changed revision,
                         # keep the first one with changed paths.
                         break
                     if revnum <= stop:
                         break
 
                     for p in paths:
                         if (not path.startswith(p) or
                             not paths[p].copyfrom_path):
                             continue
                         newpath = paths[p].copyfrom_path + path[len(p):]
                         self.ui.debug("branch renamed from %s to %s at %d\n" %
                                       (path, newpath, revnum))
                         path = newpath
                         break
                 if not paths:
                     revnum = None
                 return revnum, path
             finally:
                 stream.close()
 
         if not path.startswith(self.rootmodule):
             # Requests on foreign branches may be forbidden at server level
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
 
         if stop is None:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             prevmodule = self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(prevmodule)
         except svn.core.SubversionException:
             dirent = None
         if not dirent:
             raise SvnPathNotFound(_('%s not found up to revision %d')
                                   % (path, stop))
 
         # stat() gives us the previous revision on this line of
         # development, but it might be in *another module*. Fetch the
         # log and detect renames down to the latest revision.
         revnum, realpath = findchanges(path, stop, dirent.created_rev)
         if revnum is None:
             # Tools like svnsync can create empty revision, when
             # synchronizing only a subtree for instance. These empty
             # revisions created_rev still have their original values
             # despite all changes having disappeared and can be
             # returned by ra.stat(), at least when stating the root
             # module. In that case, do not trust created_rev and scan
             # the whole history.
             revnum, realpath = findchanges(path, stop)
             if revnum is None:
                 self.ui.debug('ignoring empty branch %r\n' % realpath)
                 return None
 
         if not realpath.startswith(self.rootmodule):
             self.ui.debug('ignoring foreign branch %r\n' % realpath)
             return None
         return self.revid(revnum, realpath)
 
     def reparent(self, module):
         """Reparent the svn transport and return the previous parent."""
         if self.prevmodule == module:
             return module
         svnurl = self.baseurl + quote(module)
         prevmodule = self.prevmodule
         if prevmodule is None:
             prevmodule = ''
         self.ui.debug("reparent to %s\n" % svnurl)
         svn.ra.reparent(self.ra, svnurl)
         self.prevmodule = module
         return prevmodule
 
     def expandpaths(self, rev, paths, parents):
         changed, removed = set(), set()
         copies = {}
 
         new_module, revnum = revsplit(rev)[1:]
         if new_module != self.module:
             self.module = new_module
             self.reparent(self.module)
 
         for i, (path, ent) in enumerate(paths):
             self.ui.progress(_('scanning paths'), i, item=path,
                              total=len(paths), unit=_('paths'))
             entrypath = self.getrelpath(path)
 
             kind = self._checkpath(entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 changed.add(self.recode(entrypath))
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrom_path = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrom_path:
                     continue
                 self.ui.debug("copied to %s from %s@%s\n" %
                               (entrypath, copyfrom_path, ent.copyfrom_rev))
                 copies[self.recode(entrypath)] = self.recode(copyfrom_path)
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 parentpath = pmodule + "/" + entrypath
                 fromkind = self._checkpath(entrypath, prevnum, pmodule)
 
                 if fromkind == svn.core.svn_node_file:
                     removed.add(self.recode(entrypath))
                 elif fromkind == svn.core.svn_node_dir:
                     oroot = parentpath.strip('/')
                     nroot = path.strip('/')
                     children = self._iterfiles(oroot, prevnum)
                     for childpath in children:
                         childpath = childpath.replace(oroot, nroot)
                         childpath = self.getrelpath("/" + childpath, pmodule)
                         if childpath:
                             removed.add(self.recode(childpath))
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 if ent.action == 'M':
                     # If the directory just had a prop change,
                     # then we shouldn't need to look for its children.
                     continue
                 if ent.action == 'R' and parents:
                     # If a directory is replacing a file, mark the previous
                     # file as deleted
                     pmodule, prevnum = revsplit(parents[0])[1:]
                     pkind = self._checkpath(entrypath, prevnum, pmodule)
                     if pkind == svn.core.svn_node_file:
                         removed.add(self.recode(entrypath))
                     elif pkind == svn.core.svn_node_dir:
                         # We do not know what files were kept or removed,
                         # mark them all as changed.
                         for childpath in self._iterfiles(pmodule, prevnum):
                             childpath = self.getrelpath("/" + childpath)
                             if childpath:
                                 changed.add(self.recode(childpath))
 
                 for childpath in self._iterfiles(path, revnum):
                     childpath = self.getrelpath("/" + childpath)
                     if childpath:
                         changed.add(self.recode(childpath))
 
                 # Handle directory copies
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrompath = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrompath:
                     continue
                 self.ui.debug("mark %s came from %s:%d\n"
                               % (path, copyfrompath, ent.copyfrom_rev))
                 children = self._iterfiles(ent.copyfrom_path, ent.copyfrom_rev)
                 for childpath in children:
                     childpath = self.getrelpath("/" + childpath, pmodule)
                     if not childpath:
                         continue
                     copytopath = path + childpath[len(copyfrompath):]
                     copytopath = self.getrelpath(copytopath)
                     copies[self.recode(copytopath)] = self.recode(childpath)
 
         self.ui.progress(_('scanning paths'), None)
         changed.update(removed)
         return (list(changed), removed, copies)
 
     def _fetch_revisions(self, from_revnum, to_revnum):
         if from_revnum < to_revnum:
             from_revnum, to_revnum = to_revnum, from_revnum
 
         self.child_cset = None
 
         def parselogentry(orig_paths, revnum, author, date, message):
             """Return the parsed commit object or None, and True if
             the revision is a branch root.
             """
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             branched = False
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
 
             if rev in self.commits or revnum < to_revnum:
                 return None, branched
 
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
             orig_paths = sorted(orig_paths.iteritems())
             root_paths = [(p, e) for p, e in orig_paths
                           if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
                 if ent.copyfrom_path:
                     branched = True
                     newpath = ent.copyfrom_path + self.module[len(path):]
                     # ent.copyfrom_rev may not be the actual last revision
                     previd = self.latest(newpath, ent.copyfrom_rev)
                     if previd is not None:
                         prevmodule, prevnum = revsplit(previd)[1:]
                         if prevnum >= self.startrev:
                             parents = [previd]
                             self.ui.note(
                                 _('found parent of branch %s at %d: %s\n') %
                                 (self.module, prevnum, prevmodule))
                 else:
                     self.ui.debug("no copyfrom path, don't know what to do.\n")
 
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if self.getrelpath(path) is None:
                     continue
                 paths.append((path, ent))
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = util.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
             if self.ui.configbool('convert', 'localtimezone'):
                 date = makedatetimestamp(date[0])
 
             if message:
                 log = self.recode(message)
             else:
                 log = ''
 
             if author:
                 author = self.recode(author)
             else:
                 author = ''
 
             try:
                 branch = self.module.split("/")[-1]
                 if branch == self.trunkname:
                     branch = None
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev)
 
             self.commits[rev] = cset
             # The parents list is *shared* among self.paths and the
             # commit object. Both will be updated below.
             self.paths[rev] = (paths, cset.parents)
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents[:] = [rev]
             self.child_cset = cset
             return cset, branched
 
         self.ui.note(_('fetching revision log for "%s" from %d to %d\n') %
                      (self.module, from_revnum, to_revnum))
 
         try:
             firstcset = None
             lastonbranch = False
             stream = self._getlog([self.module], from_revnum, to_revnum)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if revnum < self.startrev:
                         lastonbranch = True
                         break
                     if not paths:
                         self.ui.debug('revision %d has no entries\n' % revnum)
                         # If we ever leave the loop on an empty
                         # revision, do not try to get a parent branch
                         lastonbranch = lastonbranch or revnum == 0
                         continue
                     cset, lastonbranch = parselogentry(paths, revnum, author,
                                                        date, message)
                     if cset:
                         firstcset = cset
                     if lastonbranch:
                         break
             finally:
                 stream.close()
 
             if not lastonbranch and firstcset and not firstcset.parents:
                 # The first revision of the sequence (the last fetched one)
                 # has invalid parents if not a branch root. Find the parent
                 # revision now, if any.
                 try:
                     firstrevnum = self.revnum(firstcset.rev)
                     if firstrevnum > 1:
                         latest = self.latest(self.module, firstrevnum - 1)
                         if latest:
                             firstcset.parents.append(latest)
                 except SvnPathNotFound:
                     pass
         except svn.core.SubversionException as xxx_todo_changeme:
             (inst, num) = xxx_todo_changeme.args
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise error.Abort(_('svn: branch has no revision %s')
                                  % to_revnum)
             raise
 
     def getfile(self, file, rev):
         # TODO: ra.get_file transmits the whole file instead of diffs.
         if file in self.removed:
             return None, None
         mode = ''
         try:
             new_module, revnum = revsplit(rev)[1:]
             if self.module != new_module:
                 self.module = new_module
                 self.reparent(self.module)
             io = stringio()
             info = svn.ra.get_file(self.ra, file, revnum, io)
             data = io.getvalue()
             # ra.get_file() seems to keep a reference on the input buffer
             # preventing collection. Release it explicitly.
             io.close()
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
         except svn.core.SubversionException as e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
                 return None, None
             raise
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _iterfiles(self, path, revnum):
         """Enumerate all files in path at revnum, recursively."""
         path = path.strip('/')
         pool = svn.core.Pool()
         rpath = '/'.join([self.baseurl, quote(path)]).strip('/')
         entries = svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool)
         if path:
             path += '/'
         return ((path + p) for p, e in entries.iteritems()
                 if e.kind == svn.core.svn_node_file)
 
     def getrelpath(self, path, module=None):
         if module is None:
             module = self.module
         # Given the repository url of this wc, say
         #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
         # extract the "entry" portion (a relative path) from what
         # svn log --xml says, i.e.
         #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
         # that is to say "tests/PloneTestCase.py"
         if path.startswith(module):
             relative = path.rstrip('/')[len(module):]
             if relative.startswith('/'):
                 return relative[1:]
             elif relative == '':
                 return relative
 
         # The path is outside our tracked tree...
         self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
         return None
 
     def _checkpath(self, path, revnum, module=None):
         if module is not None:
             prevmodule = self.reparent('')
             path = module + '/' + path
         try:
             # ra.check_path does not like leading slashes very much, it leads
             # to PROPFIND subversion errors
             return svn.ra.check_path(self.ra, path.strip('/'), revnum)
         finally:
             if module is not None:
                 self.reparent(prevmodule)
 
     def _getlog(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
         # Normalize path names, svn >= 1.5 only wants paths relative to
         # supplied URL
         relpaths = []
         for p in paths:
             if not p.startswith('/'):
                 p = self.module + '/' + p
             relpaths.append(p.strip('/'))
         args = [self.baseurl, relpaths, start, end, limit,
                 discover_changed_paths, strict_node_history]
         # developer config: convert.svn.debugsvnlog
         if not self.ui.configbool('convert', 'svn.debugsvnlog', True):
             return directlogstream(*args)
         arg = encodeargs(args)
         hgexe = util.hgexecutable()
         cmd = '%s debugsvnlog' % util.shellquote(hgexe)
         stdin, stdout = util.popen2(util.quotecommand(cmd))
         stdin.write(arg)
         try:
             stdin.close()
         except IOError:
             raise error.Abort(_('Mercurial failed to run itself, check'
                                ' hg executable is in PATH'))
         return logstream(stdout)
 
 pre_revprop_change = '''#!/bin/sh
 
 REPOS="$1"
 REV="$2"
 USER="$3"
 PROPNAME="$4"
 ACTION="$5"
 
 if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
 
 echo "Changing prohibited revision property" >&2
 exit 1
 '''
 
 class svn_sink(converter_sink, commandline):
     commit_re = re.compile(r'Committed revision (\d+).', re.M)
     uuid_re = re.compile(r'Repository UUID:\s*(\S+)', re.M)
 
     def prerun(self):
         if self.wc:
             os.chdir(self.wc)
 
     def postrun(self):
         if self.wc:
             os.chdir(self.cwd)
 
     def join(self, name):
         return os.path.join(self.wc, '.svn', name)
 
     def revmapfile(self):
         return self.join('hg-shamap')
 
     def authorfile(self):
         return self.join('hg-authormap')
 
     def __init__(self, ui, path):
 
         converter_sink.__init__(self, ui, path)
         commandline.__init__(self, ui, 'svn')
         self.delete = []
         self.setexec = []
         self.delexec = []
         self.copies = []
         self.wc = None
         self.cwd = os.getcwd()
 
         created = False
         if os.path.isfile(os.path.join(path, '.svn', 'entries')):
             self.wc = os.path.realpath(path)
             self.run0('update')
         else:
             if not re.search(r'^(file|http|https|svn|svn\+ssh)\://', path):
                 path = os.path.realpath(path)
                 if os.path.isdir(os.path.dirname(path)):
                     if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
                         ui.status(_('initializing svn repository %r\n') %
                                   os.path.basename(path))
                         commandline(ui, 'svnadmin').run0('create', path)
                         created = path
                     path = util.normpath(path)
                     if not path.startswith('/'):
                         path = '/' + path
                     path = 'file://' + path
 
             wcpath = os.path.join(os.getcwd(), os.path.basename(path) + '-wc')
             ui.status(_('initializing svn working copy %r\n')
                       % os.path.basename(wcpath))
             self.run0('checkout', path, wcpath)
 
             self.wc = wcpath
         self.opener = scmutil.opener(self.wc)
         self.wopener = scmutil.opener(self.wc)
         self.childmap = mapfile(ui, self.join('hg-childmap'))
         if util.checkexec(self.wc):
             self.is_exec = util.isexec
         else:
             self.is_exec = None
 
         if created:
             hook = os.path.join(created, 'hooks', 'pre-revprop-change')
             fp = open(hook, 'w')
             fp.write(pre_revprop_change)
             fp.close()
             util.setflags(hook, False, True)
 
         output = self.run0('info')
         self.uuid = self.uuid_re.search(output).group(1).strip()
 
     def wjoin(self, *names):
         return os.path.join(self.wc, *names)
 
     @propertycache
     def manifest(self):
         # As of svn 1.7, the "add" command fails when receiving
         # already tracked entries, so we have to track and filter them
         # ourselves.
         m = set()
         output = self.run0('ls', recursive=True, xml=True)
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             for n in e.childNodes:
                 if n.nodeType != n.ELEMENT_NODE or n.tagName != 'name':
                     continue
                 name = ''.join(c.data for c in n.childNodes
                                if c.nodeType == c.TEXT_NODE)
                 # Entries are compared with names coming from
                 # mercurial, so bytes with undefined encoding. Our
                 # best bet is to assume they are in local
                 # encoding. They will be passed to command line calls
                 # later anyway, so they better be.
                 m.add(encoding.tolocal(name.encode('utf-8')))
                 break
         return m
 
     def putfile(self, filename, flags, data):
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             try:
                 if os.path.islink(self.wjoin(filename)):
                     os.unlink(filename)
             except OSError:
                 pass
             self.wopener.write(filename, data)
 
             if self.is_exec:
                 if self.is_exec(self.wjoin(filename)):
                     if 'x' not in flags:
                         self.delexec.append(filename)
                 else:
                     if 'x' in flags:
                         self.setexec.append(filename)
                 util.setflags(self.wjoin(filename), False, 'x' in flags)
 
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
         # already occurred.  Cross the semantic gap.
         wdest = self.wjoin(dest)
         exists = os.path.lexists(wdest)
         if exists:
             fd, tempname = tempfile.mkstemp(
                 prefix='hg-copy-', dir=os.path.dirname(wdest))
             os.close(fd)
             os.unlink(tempname)
             os.rename(wdest, tempname)
         try:
             self.run0('copy', source, dest)
         finally:
             self.manifest.add(dest)
             if exists:
                 try:
                     os.unlink(wdest)
                 except OSError:
                     pass
                 os.rename(tempname, wdest)
 
     def dirs_of(self, files):
         dirs = set()
         for f in files:
             if os.path.isdir(self.wjoin(f)):
                 dirs.add(f)
             for i in strutil.rfindall(f, '/'):
                 dirs.add(f[:i])
         return dirs
 
     def add_dirs(self, files):
         add_dirs = [d for d in sorted(self.dirs_of(files))
                     if d not in self.manifest]
         if add_dirs:
             self.manifest.update(add_dirs)
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
     def add_files(self, files):
         files = [f for f in files if f not in self.manifest]
         if files:
             self.manifest.update(files)
             self.xargs(files, 'add', quiet=True)
         return files
 
     def addchild(self, parent, child):
         self.childmap[parent] = child
 
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
             except KeyError:
                 pass
 
         # Apply changes to working copy
         for f, v in files:
             data, mode = source.getfile(f, v)
             if data is None:
                 self.delete.append(f)
             else:
                 self.putfile(f, mode, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
         if full:
             self.delete.extend(sorted(self.manifest.difference(files)))
         files = [f[0] for f in files]
 
         entries = set(self.delete)
         files = frozenset(files)
         entries.update(self.add_dirs(files.difference(entries)))
         if self.copies:
             for s, d in self.copies:
                 self._copyfile(s, d)
             self.copies = []
         if self.delete:
             self.xargs(self.delete, 'delete')
             for f in self.delete:
                 self.manifest.remove(f)
             self.delete = []
         entries.update(self.add_files(files.difference(entries)))
         if self.delexec:
             self.xargs(self.delexec, 'propdel', 'svn:executable')
             self.delexec = []
         if self.setexec:
             self.xargs(self.setexec, 'propset', 'svn:executable', '*')
             self.setexec = []
 
         fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
         fp = os.fdopen(fd, 'w')
         fp.write(commit.desc)
         fp.close()
         try:
             output = self.run0('commit',
                                username=util.shortuser(commit.author),
                                file=messagefile,
                                encoding='utf-8')
             try:
                 rev = self.commit_re.search(output).group(1)
             except AttributeError:
                 if parents and not files:
                     return parents[0]
                 self.ui.warn(_('unexpected svn output:\n'))
                 self.ui.warn(output)
                 raise error.Abort(_('unable to cope with svn output'))
             if commit.rev:
                 self.run('propset', 'hg:convert-rev', commit.rev,
                          revprop=True, revision=rev)
             if commit.branch and commit.branch != 'default':
                 self.run('propset', 'hg:convert-branch', commit.branch,
                          revprop=True, revision=rev)
             for parent in parents:
                 self.addchild(parent, rev)
             return self.revid(rev)
         finally:
             os.unlink(messagefile)
 
     def puttags(self, tags):
         self.ui.warn(_('writing Subversion tags is not yet implemented\n'))
         return None, None
 
     def hascommitfrommap(self, rev):
         # We trust that revisions referenced in a map still is present
         # TODO: implement something better if necessary and feasible
         return True
 
     def hascommitforsplicemap(self, rev):
         # This is not correct as one can convert to an existing subversion
         # repository and childmap would not list all revisions. Too bad.
         if rev in self.childmap:
             return True
         raise error.Abort(_('splice map revision %s not found in subversion '
                            'child map (revision lookups are not implemented)')
                          % rev)

hgext/eol.py

@@ -1,363 +1,392 b''
 """automatically manage newlines in repository files
 
 This extension allows you to manage the type of line endings (CRLF or
 LF) that are used in the repository and in the local working
 directory. That way you can get CRLF line endings on Windows and LF on
 Unix/Mac, thereby letting everybody use their OS native line endings.
 
 The extension reads its configuration from a versioned ``.hgeol``
 configuration file found in the root of the working directory. The
 ``.hgeol`` file use the same syntax as all other Mercurial
 configuration files. It uses two sections, ``[patterns]`` and
 ``[repository]``.
 
 The ``[patterns]`` section specifies how line endings should be
 converted between the working directory and the repository. The format is
 specified by a file pattern. The first match is used, so put more
 specific patterns first. The available line endings are ``LF``,
 ``CRLF``, and ``BIN``.
 
 Files with the declared format of ``CRLF`` or ``LF`` are always
 checked out and stored in the repository in that format and files
 declared to be binary (``BIN``) are left unchanged. Additionally,
 ``native`` is an alias for checking out in the platform's default line
 ending: ``LF`` on Unix (including Mac OS X) and ``CRLF`` on
 Windows. Note that ``BIN`` (do nothing to line endings) is Mercurial's
 default behavior; it is only needed if you need to override a later,
 more general pattern.
 
 The optional ``[repository]`` section specifies the line endings to
 use for files stored in the repository. It has a single setting,
 ``native``, which determines the storage line endings for files
 declared as ``native`` in the ``[patterns]`` section. It can be set to
 ``LF`` or ``CRLF``. The default is ``LF``. For example, this means
 that on Windows, files configured as ``native`` (``CRLF`` by default)
 will be converted to ``LF`` when stored in the repository. Files
 declared as ``LF``, ``CRLF``, or ``BIN`` in the ``[patterns]`` section
 are always stored as-is in the repository.
 
 Example versioned ``.hgeol`` file::
 
   [patterns]
   **.py = native
   **.vcproj = CRLF
   **.txt = native
   Makefile = LF
   **.jpg = BIN
 
   [repository]
   native = LF
 
 .. note::
 
    The rules will first apply when files are touched in the working
    directory, e.g. by updating to null and back to tip to touch all files.
 
 The extension uses an optional ``[eol]`` section read from both the
 normal Mercurial configuration files and the ``.hgeol`` file, with the
 latter overriding the former. You can use that section to control the
 overall behavior. There are three settings:
 
 - ``eol.native`` (default ``os.linesep``) can be set to ``LF`` or
   ``CRLF`` to override the default interpretation of ``native`` for
   checkout. This can be used with :hg:`archive` on Unix, say, to
   generate an archive where files have line endings for Windows.
 
 - ``eol.only-consistent`` (default True) can be set to False to make
   the extension convert files with inconsistent EOLs. Inconsistent
   means that there is both ``CRLF`` and ``LF`` present in the file.
   Such files are normally not touched under the assumption that they
   have mixed EOLs on purpose.
 
 - ``eol.fix-trailing-newline`` (default False) can be set to True to
   ensure that converted files end with a EOL character (either ``\\n``
   or ``\\r\\n`` as per the configured patterns).
 
 The extension provides ``cleverencode:`` and ``cleverdecode:`` filters
 like the deprecated win32text extension does. This means that you can
 disable win32text and enable eol and your filters will still work. You
 only need to these filters until you have prepared a ``.hgeol`` file.
 
 The ``win32text.forbid*`` hooks provided by the win32text extension
 have been unified into a single hook named ``eol.checkheadshook``. The
 hook will lookup the expected line endings from the ``.hgeol`` file,
 which means you must migrate to a ``.hgeol`` file first before using
 the hook. ``eol.checkheadshook`` only checks heads, intermediate
 invalid revisions will be pushed. To forbid them completely, use the
 ``eol.checkallhook`` hook. These hooks are best used as
 ``pretxnchangegroup`` hooks.
 
 See :hg:`help patterns` for more information about the glob patterns
 used.
 """
 
 from __future__ import absolute_import
 
 import os
 import re
 from mercurial.i18n import _
 from mercurial import (
     config,
     error,
     extensions,
     match,
     util,
 )
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 # Matches a lone LF, i.e., one that is not part of CRLF.
 singlelf = re.compile('(^|[^\r])\n')
 # Matches a single EOL which can either be a CRLF where repeated CR
 # are removed or a LF. We do not care about old Macintosh files, so a
 # stray CR is an error.
 eolre = re.compile('\r*\n')
 
 
 def inconsistenteol(data):
     return '\r\n' in data and singlelf.search(data)
 
 def tolf(s, params, ui, **kwargs):
     """Filter to convert to LF EOLs."""
     if util.binary(s):
         return s
     if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s):
         return s
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     return eolre.sub('\n', s)
 
 def tocrlf(s, params, ui, **kwargs):
     """Filter to convert to CRLF EOLs."""
     if util.binary(s):
         return s
     if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s):
         return s
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     return eolre.sub('\r\n', s)
 
 def isbinary(s, params):
     """Filter to do nothing with the file."""
     return s
 
 filters = {
     'to-lf': tolf,
     'to-crlf': tocrlf,
     'is-binary': isbinary,
     # The following provide backwards compatibility with win32text
     'cleverencode:': tolf,
     'cleverdecode:': tocrlf
 }
 
 class eolfile(object):
     def __init__(self, ui, root, data):
         self._decode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
         self._encode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
 
         self.cfg = config.config()
         # Our files should not be touched. The pattern must be
         # inserted first override a '** = native' pattern.
         self.cfg.set('patterns', '.hg*', 'BIN', 'eol')
         # We can then parse the user's patterns.
         self.cfg.parse('.hgeol', data)
 
         isrepolf = self.cfg.get('repository', 'native') != 'CRLF'
         self._encode['NATIVE'] = isrepolf and 'to-lf' or 'to-crlf'
         iswdlf = ui.config('eol', 'native', os.linesep) in ('LF', '\n')
         self._decode['NATIVE'] = iswdlf and 'to-lf' or 'to-crlf'
 
         include = []
         exclude = []
+        self.patterns = []
         for pattern, style in self.cfg.items('patterns'):
             key = style.upper()
             if key == 'BIN':
                 exclude.append(pattern)
             else:
                 include.append(pattern)
+            m = match.match(root, '', [pattern])
+            self.patterns.append((pattern, key, m))
         # This will match the files for which we need to care
         # about inconsistent newlines.
         self.match = match.match(root, '', [], include, exclude)
 
     def copytoui(self, ui):
-        for pattern, style in self.cfg.items('patterns'):
-            key = style.upper()
+        for pattern, key, m in self.patterns:
             try:
                 ui.setconfig('decode', pattern, self._decode[key], 'eol')
                 ui.setconfig('encode', pattern, self._encode[key], 'eol')
             except KeyError:
                 ui.warn(_("ignoring unknown EOL style '%s' from %s\n")
-                        % (style, self.cfg.source('patterns', pattern)))
+                        % (key, self.cfg.source('patterns', pattern)))
         # eol.only-consistent can be specified in ~/.hgrc or .hgeol
         for k, v in self.cfg.items('eol'):
             ui.setconfig('eol', k, v, 'eol')
 
     def checkrev(self, repo, ctx, files):
         failed = []
         for f in (files or ctx.files()):
             if f not in ctx:
                 continue
-            for pattern, style in self.cfg.items('patterns'):
-                if not match.match(repo.root, '', [pattern])(f):
+            for pattern, key, m in self.patterns:
+                if not m(f):
                     continue
-                target = self._encode[style.upper()]
+                target = self._encode[key]
                 data = ctx[f].data()
                 if (target == "to-lf" and "\r\n" in data
                     or target == "to-crlf" and singlelf.search(data)):
                     failed.append((f, target, str(ctx)))
                 break
         return failed
 
 def parseeol(ui, repo, nodes):
     try:
         for node in nodes:
             try:
                 if node is None:
                     # Cannot use workingctx.data() since it would load
                     # and cache the filters before we configure them.
                     data = repo.wfile('.hgeol').read()
                 else:
                     data = repo[node]['.hgeol'].data()
                 return eolfile(ui, repo.root, data)
             except (IOError, LookupError):
                 pass
     except error.ParseError as inst:
         ui.warn(_("warning: ignoring .hgeol file due to parse error "
                   "at %s: %s\n") % (inst.args[1], inst.args[0]))
     return None
 
 def _checkhook(ui, repo, node, headsonly):
     # Get revisions to check and touched files at the same time
     files = set()
     revs = set()
     for rev in xrange(repo[node].rev(), len(repo)):
         revs.add(rev)
         if headsonly:
             ctx = repo[rev]
             files.update(ctx.files())
             for pctx in ctx.parents():
                 revs.discard(pctx.rev())
     failed = []
     for rev in revs:
         ctx = repo[rev]
         eol = parseeol(ui, repo, [ctx.node()])
         if eol:
             failed.extend(eol.checkrev(repo, ctx, files))
 
     if failed:
         eols = {'to-lf': 'CRLF', 'to-crlf': 'LF'}
         msgs = []
         for f, target, node in sorted(failed):
             msgs.append(_("  %s in %s should not have %s line endings") %
                         (f, node, eols[target]))
         raise error.Abort(_("end-of-line check failed:\n") + "\n".join(msgs))
 
 def checkallhook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, False)
 
 def checkheadshook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, True)
 
 # "checkheadshook" used to be called "hook"
 hook = checkheadshook
 
 def preupdate(ui, repo, hooktype, parent1, parent2):
     repo.loadeol([parent1])
     return False
 
 def uisetup(ui):
     ui.setconfig('hooks', 'preupdate.eol', preupdate, 'eol')
 
 def extsetup(ui):
     try:
         extensions.find('win32text')
         ui.warn(_("the eol extension is incompatible with the "
                   "win32text extension\n"))
     except KeyError:
         pass
 
 
 def reposetup(ui, repo):
     uisetup(repo.ui)
 
     if not repo.local():
         return
     for name, fn in filters.iteritems():
         repo.adddatafilter(name, fn)
 
     ui.setconfig('patch', 'eol', 'auto', 'eol')
 
     class eolrepo(repo.__class__):
 
         def loadeol(self, nodes):
             eol = parseeol(self.ui, self, nodes)
             if eol is None:
                 return None
             eol.copytoui(self.ui)
             return eol.match
 
         def _hgcleardirstate(self):
-            self._eolfile = self.loadeol([None, 'tip'])
-            if not self._eolfile:
-                self._eolfile = util.never
+            self._eolmatch = self.loadeol([None, 'tip'])
+            if not self._eolmatch:
+                self._eolmatch = util.never
                 return
 
+            oldeol = None
             try:
                 cachemtime = os.path.getmtime(self.join("eol.cache"))
             except OSError:
                 cachemtime = 0
+            else:
+                olddata = self.vfs.read("eol.cache")
+                if olddata:
+                    oldeol = eolfile(self.ui, self.root, olddata)
 
             try:
                 eolmtime = os.path.getmtime(self.wjoin(".hgeol"))
             except OSError:
                 eolmtime = 0
 
             if eolmtime > cachemtime:
                 self.ui.debug("eol: detected change in .hgeol\n")
+
+                hgeoldata = self.wvfs.read('.hgeol')
+                neweol = eolfile(self.ui, self.root, hgeoldata)
+
                 wlock = None
                 try:
                     wlock = self.wlock()
                     for f in self.dirstate:
-                        if self.dirstate[f] == 'n':
-                            # all normal files need to be looked at
-                            # again since the new .hgeol file might no
-                            # longer match a file it matched before
-                            self.dirstate.normallookup(f)
-                    # Create or touch the cache to update mtime
-                    self.vfs("eol.cache", "w").close()
-                    wlock.release()
+                        if self.dirstate[f] != 'n':
+                            continue
+                        if oldeol is not None:
+                            if not oldeol.match(f) and not neweol.match(f):
+                                continue
+                            oldkey = None
+                            for pattern, key, m in oldeol.patterns:
+                                if m(f):
+                                    oldkey = key
+                                    break
+                            newkey = None
+                            for pattern, key, m in neweol.patterns:
+                                if m(f):
+                                    newkey = key
+                                    break
+                            if oldkey == newkey:
+                                continue
+                        # all normal files need to be looked at again since
+                        # the new .hgeol file specify a different filter
+                        self.dirstate.normallookup(f)
+                    # Write the cache to update mtime and cache .hgeol
+                    with self.vfs("eol.cache", "w") as f:
+                        f.write(hgeoldata)
                 except error.LockUnavailable:
                     # If we cannot lock the repository and clear the
                     # dirstate, then a commit might not see all files
                     # as modified. But if we cannot lock the
                     # repository, then we can also not make a commit,
                     # so ignore the error.
                     pass
+                finally:
+                    if wlock is not None:
+                        wlock.release()
 
         def commitctx(self, ctx, haserror=False):
             for f in sorted(ctx.added() + ctx.modified()):
-                if not self._eolfile(f):
+                if not self._eolmatch(f):
                     continue
                 fctx = ctx[f]
                 if fctx is None:
                     continue
                 data = fctx.data()
                 if util.binary(data):
                     # We should not abort here, since the user should
                     # be able to say "** = native" to automatically
                     # have all non-binary files taken care of.
                     continue
                 if inconsistenteol(data):
                     raise error.Abort(_("inconsistent newline style "
                                        "in %s\n") % f)
             return super(eolrepo, self).commitctx(ctx, haserror)
     repo.__class__ = eolrepo
     repo._hgcleardirstate()

hgext/extdiff.py

@@ -1,384 +1,392 b''
 # extdiff.py - external diff program support for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to allow external programs to compare revisions
 
 The extdiff Mercurial extension allows you to use external programs
 to compare revisions, or revision with working directory. The external
 diff programs are called with a configurable set of options and two
 non-option arguments: paths to directories containing snapshots of
 files to compare.
 
 The extdiff extension also allows you to configure new diff commands, so
 you do not need to type :hg:`extdiff -p kdiff3` always. ::
 
   [extdiff]
   # add new command that runs GNU diff(1) in 'context diff' mode
   cdiff = gdiff -Nprc5
   ## or the old way:
   #cmd.cdiff = gdiff
   #opts.cdiff = -Nprc5
 
   # add new command called meld, runs meld (no need to name twice).  If
   # the meld executable is not available, the meld tool in [merge-tools]
   # will be used, if available
   meld =
 
   # add new command called vimdiff, runs gvimdiff with DirDiff plugin
   # (see http://www.vim.org/scripts/script.php?script_id=102) Non
   # English user, be sure to put "let g:DirDiffDynamicDiffText = 1" in
   # your .vimrc
   vimdiff = gvim -f "+next" \\
             "+execute 'DirDiff' fnameescape(argv(0)) fnameescape(argv(1))"
 
 Tool arguments can include variables that are expanded at runtime::
 
   $parent1, $plabel1 - filename, descriptive label of first parent
   $child,   $clabel  - filename, descriptive label of child revision
   $parent2, $plabel2 - filename, descriptive label of second parent
   $root              - repository root
   $parent is an alias for $parent1.
 
 The extdiff extension will look in your [diff-tools] and [merge-tools]
 sections for diff tool arguments, when none are specified in [extdiff].
 
 ::
 
   [extdiff]
   kdiff3 =
 
   [diff-tools]
   kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
 
 You can use -I/-X and list of file or directory names like normal
 :hg:`diff` command. The extdiff extension makes snapshots of only
 needed files, so running the external diff program will actually be
 pretty fast (at least faster than having to compare the entire tree).
 '''
 
 from __future__ import absolute_import
 
 import os
 import re
 import shlex
 import shutil
 import tempfile
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     short,
 )
 from mercurial import (
     archival,
     cmdutil,
     commands,
     error,
     filemerge,
     scmutil,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 def snapshot(ui, repo, files, node, tmproot, listsubrepos):
     '''snapshot files as of some revision
     if not using snapshot, -I/-X does not work and recursive diff
     in tools like kdiff3 and meld displays too many files.'''
     dirname = os.path.basename(repo.root)
     if dirname == "":
         dirname = "root"
     if node is not None:
         dirname = '%s.%s' % (dirname, short(node))
     base = os.path.join(tmproot, dirname)
     os.mkdir(base)
     fns_and_mtime = []
 
     if node is not None:
         ui.note(_('making snapshot of %d files from rev %s\n') %
                 (len(files), short(node)))
     else:
         ui.note(_('making snapshot of %d files from working directory\n') %
             (len(files)))
 
     if files:
         repo.ui.setconfig("ui", "archivemeta", False)
 
         archival.archive(repo, base, node, 'files',
                          matchfn=scmutil.matchfiles(repo, files),
                          subrepos=listsubrepos)
 
         for fn in sorted(files):
             wfn = util.pconvert(fn)
             ui.note('  %s\n' % wfn)
 
             if node is None:
                 dest = os.path.join(base, wfn)
 
                 fns_and_mtime.append((dest, repo.wjoin(fn),
                                       os.lstat(dest).st_mtime))
     return dirname, fns_and_mtime
 
 def dodiff(ui, repo, cmdline, pats, opts):
     '''Do the actual diff:
 
     - copy to a temp structure if diffing 2 internal revisions
     - copy to a temp structure if diffing working revision with
       another one and more than 1 file is changed
     - just invoke the diff for a single file in the working dir
     '''
 
     revs = opts.get('rev')
     change = opts.get('change')
     do3way = '$parent2' in cmdline
 
     if revs and change:
         msg = _('cannot specify --rev and --change at the same time')
         raise error.Abort(msg)
     elif change:
         node2 = scmutil.revsingle(repo, change, None).node()
         node1a, node1b = repo.changelog.parents(node2)
     else:
         node1a, node2 = scmutil.revpair(repo, revs)
         if not revs:
             node1b = repo.dirstate.p2()
         else:
             node1b = nullid
 
     # Disable 3-way merge if there is only one parent
     if do3way:
         if node1b == nullid:
             do3way = False
 
     subrepos=opts.get('subrepos')
 
     matcher = scmutil.match(repo[node2], pats, opts)
 
     if opts.get('patch'):
         if subrepos:
             raise error.Abort(_('--patch cannot be used with --subrepos'))
         if node2 is None:
             raise error.Abort(_('--patch requires two revisions'))
     else:
         mod_a, add_a, rem_a = map(set, repo.status(node1a, node2, matcher,
                                                    listsubrepos=subrepos)[:3])
         if do3way:
             mod_b, add_b, rem_b = map(set,
                                       repo.status(node1b, node2, matcher,
                                                   listsubrepos=subrepos)[:3])
         else:
             mod_b, add_b, rem_b = set(), set(), set()
         modadd = mod_a | add_a | mod_b | add_b
         common = modadd | rem_a | rem_b
         if not common:
             return 0
 
     tmproot = tempfile.mkdtemp(prefix='extdiff.')
     try:
         if not opts.get('patch'):
             # Always make a copy of node1a (and node1b, if applicable)
             dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a)
             dir1a = snapshot(ui, repo, dir1a_files, node1a, tmproot,
                              subrepos)[0]
             rev1a = '@%d' % repo[node1a].rev()
             if do3way:
                 dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b)
                 dir1b = snapshot(ui, repo, dir1b_files, node1b, tmproot,
                                  subrepos)[0]
                 rev1b = '@%d' % repo[node1b].rev()
             else:
                 dir1b = None
                 rev1b = ''
 
             fns_and_mtime = []
 
             # If node2 in not the wc or there is >1 change, copy it
             dir2root = ''
             rev2 = ''
             if node2:
                 dir2 = snapshot(ui, repo, modadd, node2, tmproot, subrepos)[0]
                 rev2 = '@%d' % repo[node2].rev()
             elif len(common) > 1:
                 #we only actually need to get the files to copy back to
                 #the working dir in this case (because the other cases
                 #are: diffing 2 revisions or single file -- in which case
                 #the file is already directly passed to the diff tool).
                 dir2, fns_and_mtime = snapshot(ui, repo, modadd, None, tmproot,
                                                subrepos)
             else:
                 # This lets the diff tool open the changed file directly
                 dir2 = ''
                 dir2root = repo.root
 
             label1a = rev1a
             label1b = rev1b
             label2 = rev2
 
             # If only one change, diff the files instead of the directories
             # Handle bogus modifies correctly by checking if the files exist
             if len(common) == 1:
                 common_file = util.localpath(common.pop())
                 dir1a = os.path.join(tmproot, dir1a, common_file)
                 label1a = common_file + rev1a
                 if not os.path.isfile(dir1a):
                     dir1a = os.devnull
                 if do3way:
                     dir1b = os.path.join(tmproot, dir1b, common_file)
                     label1b = common_file + rev1b
                     if not os.path.isfile(dir1b):
                         dir1b = os.devnull
                 dir2 = os.path.join(dir2root, dir2, common_file)
                 label2 = common_file + rev2
         else:
             template = 'hg-%h.patch'
             cmdutil.export(repo, [repo[node1a].rev(), repo[node2].rev()],
                            template=repo.vfs.reljoin(tmproot, template),
                            match=matcher)
             label1a = cmdutil.makefilename(repo, template, node1a)
             label2 = cmdutil.makefilename(repo, template, node2)
             dir1a = repo.vfs.reljoin(tmproot, label1a)
             dir2 = repo.vfs.reljoin(tmproot, label2)
             dir1b = None
             label1b = None
             fns_and_mtime = []
 
         # Function to quote file/dir names in the argument string.
         # When not operating in 3-way mode, an empty string is
         # returned for parent2
         replace = {'parent': dir1a, 'parent1': dir1a, 'parent2': dir1b,
                    'plabel1': label1a, 'plabel2': label1b,
                    'clabel': label2, 'child': dir2,
                    'root': repo.root}
         def quote(match):
             pre = match.group(2)
             key = match.group(3)
             if not do3way and key == 'parent2':
                 return pre
             return pre + util.shellquote(replace[key])
 
         # Match parent2 first, so 'parent1?' will match both parent1 and parent
         regex = (r'''(['"]?)([^\s'"$]*)'''
                  r'\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)\1')
         if not do3way and not re.search(regex, cmdline):
             cmdline += ' $parent1 $child'
         cmdline = re.sub(regex, quote, cmdline)
 
         ui.debug('running %r in %s\n' % (cmdline, tmproot))
         ui.system(cmdline, cwd=tmproot)
 
         for copy_fn, working_fn, mtime in fns_and_mtime:
             if os.lstat(copy_fn).st_mtime != mtime:
                 ui.debug('file changed while diffing. '
                          'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn))
                 util.copyfile(copy_fn, working_fn)
 
         return 1
     finally:
         ui.note(_('cleaning up temp directory\n'))
         shutil.rmtree(tmproot)
 
 extdiffopts = [
     ('o', 'option', [],
      _('pass option to comparison program'), _('OPT')),
     ('r', 'rev', [], _('revision'), _('REV')),
     ('c', 'change', '', _('change made by revision'), _('REV')),
     ('', 'patch', None, _('compare patches for two revisions'))
     ] + commands.walkopts + commands.subrepoopts
 
 @command('extdiff',
     [('p', 'program', '', _('comparison program to run'), _('CMD')),
      ] + extdiffopts,
     _('hg extdiff [OPT]... [FILE]...'),
     inferrepo=True)
 def extdiff(ui, repo, *pats, **opts):
     '''use external program to diff repository (or selected files)
 
     Show differences between revisions for the specified files, using
     an external program. The default program used is diff, with
     default options "-Npru".
 
     To select a different program, use the -p/--program option. The
     program will be passed the names of two directories to compare. To
     pass additional options to the program, use -o/--option. These
     will be passed before the names of the directories to compare.
 
     When two revision arguments are given, then changes are shown
     between those revisions. If only one revision is specified then
     that revision is compared to the working directory, and, when no
     revisions are specified, the working directory files are compared
     to its parent.'''
     program = opts.get('program')
     option = opts.get('option')
     if not program:
         program = 'diff'
         option = option or ['-Npru']
     cmdline = ' '.join(map(util.shellquote, [program] + option))
     return dodiff(ui, repo, cmdline, pats, opts)
 
+class savedcmd(object):
+    """use external program to diff repository (or selected files)
+
+    Show differences between revisions for the specified files, using
+    the following program::
+
+        %(path)s
+
+    When two revision arguments are given, then changes are shown
+    between those revisions. If only one revision is specified then
+    that revision is compared to the working directory, and, when no
+    revisions are specified, the working directory files are compared
+    to its parent.
+    """
+
+    def __init__(self, path, cmdline):
+        # We can't pass non-ASCII through docstrings (and path is
+        # in an unknown encoding anyway)
+        docpath = path.encode("string-escape")
+        self.__doc__ = self.__doc__ % {'path': util.uirepr(docpath)}
+        self._cmdline = cmdline
+
+    def __call__(self, ui, repo, *pats, **opts):
+        options = ' '.join(map(util.shellquote, opts['option']))
+        if options:
+            options = ' ' + options
+        return dodiff(ui, repo, self._cmdline + options, pats, opts)
+
 def uisetup(ui):
     for cmd, path in ui.configitems('extdiff'):
         path = util.expandpath(path)
         if cmd.startswith('cmd.'):
             cmd = cmd[4:]
             if not path:
                 path = util.findexe(cmd)
                 if path is None:
                     path = filemerge.findexternaltool(ui, cmd) or cmd
             diffopts = ui.config('extdiff', 'opts.' + cmd, '')
             cmdline = util.shellquote(path)
             if diffopts:
                 cmdline += ' ' + diffopts
         elif cmd.startswith('opts.'):
             continue
         else:
             if path:
                 # case "cmd = path opts"
                 cmdline = path
                 diffopts = len(shlex.split(cmdline)) > 1
             else:
                 # case "cmd ="
                 path = util.findexe(cmd)
                 if path is None:
                     path = filemerge.findexternaltool(ui, cmd) or cmd
                 cmdline = util.shellquote(path)
                 diffopts = False
         # look for diff arguments in [diff-tools] then [merge-tools]
         if not diffopts:
             args = ui.config('diff-tools', cmd+'.diffargs') or \
                    ui.config('merge-tools', cmd+'.diffargs')
             if args:
                 cmdline += ' ' + args
-        def save(cmdline):
-            '''use closure to save diff command to use'''
-            def mydiff(ui, repo, *pats, **opts):
-                options = ' '.join(map(util.shellquote, opts['option']))
-                if options:
-                    options = ' ' + options
-                return dodiff(ui, repo, cmdline + options, pats, opts)
-            # We can't pass non-ASCII through docstrings (and path is
-            # in an unknown encoding anyway)
-            docpath = path.encode("string-escape")
-            mydiff.__doc__ = '''\
-use %(path)s to diff repository (or selected files)
+        command(cmd, extdiffopts[:], _('hg %s [OPTION]... [FILE]...') % cmd,
+                inferrepo=True)(savedcmd(path, cmdline))
 
-    Show differences between revisions for the specified files, using
-    the %(path)s program.
-
-    When two revision arguments are given, then changes are shown
-    between those revisions. If only one revision is specified then
-    that revision is compared to the working directory, and, when no
-    revisions are specified, the working directory files are compared
-    to its parent.\
-''' % {'path': util.uirepr(docpath)}
-            return mydiff
-        command(cmd, extdiffopts[:], _('hg %s [OPTION]... [FILE]...') % cmd,
-                inferrepo=True)(save(cmdline))
+# tell hggettext to extract docstrings from these functions:
+i18nfunctions = [savedcmd]

hgext/fetch.py

@@ -1,165 +1,165 b''
 # fetch.py - pull and merge remote changes
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''pull, update and merge in one command (DEPRECATED)'''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial.node import (
     short,
 )
 from mercurial import (
     cmdutil,
     commands,
     error,
     exchange,
     hg,
     lock,
     util,
 )
 
 release = lock.release
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 @command('fetch',
     [('r', 'rev', [],
      _('a specific revision you would like to pull'), _('REV')),
     ('e', 'edit', None, _('invoke editor on commit messages')),
     ('', 'force-editor', None, _('edit commit message (DEPRECATED)')),
     ('', 'switch-parent', None, _('switch parents when merging')),
     ] + commands.commitopts + commands.commitopts2 + commands.remoteopts,
     _('hg fetch [SOURCE]'))
 def fetch(ui, repo, source='default', **opts):
     '''pull changes from a remote repository, merge new changes if needed.
 
     This finds all changes from the repository at the specified path
     or URL and adds them to the local repository.
 
     If the pulled changes add a new branch head, the head is
     automatically merged, and the result of the merge is committed.
     Otherwise, the working directory is updated to include the new
     changes.
 
     When a merge is needed, the working directory is first updated to
     the newly pulled changes. Local changes are then merged into the
     pulled changes. To switch the merge order, use --switch-parent.
 
     See :hg:`help dates` for a list of formats valid for -d/--date.
 
     Returns 0 on success.
     '''
 
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
 
     parent, _p2 = repo.dirstate.parents()
     branch = repo.dirstate.branch()
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if parent != branchnode:
         raise error.Abort(_('working directory not at branch tip'),
                          hint=_("use 'hg update' to check out branch tip"))
 
     wlock = lock = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
 
         cmdutil.bailifchanged(repo)
 
         bheads = repo.branchheads(branch)
         bheads = [head for head in bheads if len(repo[head].children()) == 0]
         if len(bheads) > 1:
             raise error.Abort(_('multiple heads in this branch '
                                '(use "hg heads ." and "hg merge" to merge)'))
 
         other = hg.peer(repo, opts, ui.expandpath(source))
         ui.status(_('pulling from %s\n') %
                   util.hidepassword(ui.expandpath(source)))
         revs = None
         if opts['rev']:
             try:
                 revs = [other.lookup(rev) for rev in opts['rev']]
             except error.CapabilityError:
                 err = _("other repository doesn't support revision lookup, "
                         "so a rev cannot be specified.")
                 raise error.Abort(err)
 
         # Are there any changes at all?
         modheads = exchange.pull(repo, other, heads=revs).cgresult
         if modheads == 0:
             return 0
 
         # Is this a simple fast-forward along the current branch?
         newheads = repo.branchheads(branch)
         newchildren = repo.changelog.nodesbetween([parent], newheads)[2]
         if len(newheads) == 1 and len(newchildren):
             if newchildren[0] != parent:
                 return hg.update(repo, newchildren[0])
             else:
                 return 0
 
         # Are there more than one additional branch heads?
         newchildren = [n for n in newchildren if n != parent]
         newparent = parent
         if newchildren:
             newparent = newchildren[0]
             hg.clean(repo, newparent)
         newheads = [n for n in newheads if n != newparent]
         if len(newheads) > 1:
             ui.status(_('not merging with %d other new branch heads '
                         '(use "hg heads ." and "hg merge" to merge them)\n') %
                       (len(newheads) - 1))
             return 1
 
         if not newheads:
             return 0
 
         # Otherwise, let's merge.
         err = False
         if newheads:
             # By default, we consider the repository we're pulling
             # *from* as authoritative, so we merge our changes into
             # theirs.
             if opts['switch_parent']:
                 firstparent, secondparent = newparent, newheads[0]
             else:
                 firstparent, secondparent = newheads[0], newparent
                 ui.status(_('updating to %d:%s\n') %
                           (repo.changelog.rev(firstparent),
                            short(firstparent)))
             hg.clean(repo, firstparent)
             ui.status(_('merging with %d:%s\n') %
                       (repo.changelog.rev(secondparent), short(secondparent)))
             err = hg.merge(repo, secondparent, remind=False)
 
         if not err:
             # we don't translate commit messages
             message = (cmdutil.logmessage(ui, opts) or
                        ('Automated merge with %s' %
                         util.removeauth(other.url())))
             editopt = opts.get('edit') or opts.get('force_editor')
             editor = cmdutil.getcommiteditor(edit=editopt, editform='fetch')
             n = repo.commit(message, opts['user'], opts['date'], editor=editor)
             ui.status(_('new changeset %d:%s merges remote changes '
                         'with local\n') % (repo.changelog.rev(n),
                                            short(n)))
 
         return err
 
     finally:
         release(lock, wlock)

hgext/fsmonitor/__init__.py

@@ -1,695 +1,695 b''
 # __init__.py - fsmonitor initialization and overrides
 #
 # Copyright 2013-2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''Faster status operations with the Watchman file monitor (EXPERIMENTAL)
 
 Integrates the file-watching program Watchman with Mercurial to produce faster
 status results.
 
 On a particular Linux system, for a real-world repository with over 400,000
 files hosted on ext4, vanilla `hg status` takes 1.3 seconds. On the same
 system, with fsmonitor it takes about 0.3 seconds.
 
 fsmonitor requires no configuration -- it will tell Watchman about your
 repository as necessary. You'll need to install Watchman from
 https://facebook.github.io/watchman/ and make sure it is in your PATH.
 
 The following configuration options exist:
 
 ::
 
     [fsmonitor]
     mode = {off, on, paranoid}
 
 When `mode = off`, fsmonitor will disable itself (similar to not loading the
 extension at all). When `mode = on`, fsmonitor will be enabled (the default).
 When `mode = paranoid`, fsmonitor will query both Watchman and the filesystem,
 and ensure that the results are consistent.
 
 ::
 
     [fsmonitor]
     timeout = (float)
 
 A value, in seconds, that determines how long fsmonitor will wait for Watchman
 to return results. Defaults to `2.0`.
 
 ::
 
     [fsmonitor]
     blacklistusers = (list of userids)
 
 A list of usernames for which fsmonitor will disable itself altogether.
 
 ::
 
     [fsmonitor]
     walk_on_invalidate = (boolean)
 
 Whether or not to walk the whole repo ourselves when our cached state has been
 invalidated, for example when Watchman has been restarted or .hgignore rules
 have been changed. Walking the repo in that case can result in competing for
 I/O with Watchman. For large repos it is recommended to set this value to
 false. You may wish to set this to true if you have a very fast filesystem
 that can outpace the IPC overhead of getting the result data for the full repo
 from Watchman. Defaults to false.
 
 fsmonitor is incompatible with the largefiles and eol extensions, and
 will disable itself if any of those are active.
 
 '''
 
 # Platforms Supported
 # ===================
 #
 # **Linux:** *Stable*. Watchman and fsmonitor are both known to work reliably,
 #   even under severe loads.
 #
 # **Mac OS X:** *Stable*. The Mercurial test suite passes with fsmonitor
 #   turned on, on case-insensitive HFS+. There has been a reasonable amount of
 #   user testing under normal loads.
 #
 # **Solaris, BSD:** *Alpha*. watchman and fsmonitor are believed to work, but
 #   very little testing has been done.
 #
 # **Windows:** *Alpha*. Not in a release version of watchman or fsmonitor yet.
 #
 # Known Issues
 # ============
 #
 # * fsmonitor will disable itself if any of the following extensions are
 #   enabled: largefiles, inotify, eol; or if the repository has subrepos.
 # * fsmonitor will produce incorrect results if nested repos that are not
 #   subrepos exist. *Workaround*: add nested repo paths to your `.hgignore`.
 #
 # The issues related to nested repos and subrepos are probably not fundamental
 # ones. Patches to fix them are welcome.
 
 from __future__ import absolute_import
 
 import hashlib
 import os
 import stat
 import sys
 
 from mercurial.i18n import _
 from mercurial import (
     context,
     extensions,
     localrepo,
     merge,
     pathutil,
     scmutil,
     util,
 )
 from mercurial import match as matchmod
 
 from . import (
     state,
     watchmanclient,
 )
 
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 # This extension is incompatible with the following blacklisted extensions
 # and will disable itself when encountering one of these:
 _blacklist = ['largefiles', 'eol']
 
 def _handleunavailable(ui, state, ex):
     """Exception handler for Watchman interaction exceptions"""
     if isinstance(ex, watchmanclient.Unavailable):
         if ex.warn:
             ui.warn(str(ex) + '\n')
         if ex.invalidate:
             state.invalidate()
         ui.log('fsmonitor', 'Watchman unavailable: %s\n', ex.msg)
     else:
         ui.log('fsmonitor', 'Watchman exception: %s\n', ex)
 
 def _hashignore(ignore):
     """Calculate hash for ignore patterns and filenames
 
     If this information changes between Mercurial invocations, we can't
     rely on Watchman information anymore and have to re-scan the working
     copy.
 
     """
     sha1 = hashlib.sha1()
     if util.safehasattr(ignore, 'includepat'):
         sha1.update(ignore.includepat)
     sha1.update('\0\0')
     if util.safehasattr(ignore, 'excludepat'):
         sha1.update(ignore.excludepat)
     sha1.update('\0\0')
     if util.safehasattr(ignore, 'patternspat'):
         sha1.update(ignore.patternspat)
     sha1.update('\0\0')
     if util.safehasattr(ignore, '_files'):
         for f in ignore._files:
             sha1.update(f)
     sha1.update('\0')
     return sha1.hexdigest()
 
 def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True):
     '''Replacement for dirstate.walk, hooking into Watchman.
 
     Whenever full is False, ignored is False, and the Watchman client is
     available, use Watchman combined with saved state to possibly return only a
     subset of files.'''
     def bail():
         return orig(match, subrepos, unknown, ignored, full=True)
 
     if full or ignored or not self._watchmanclient.available():
         return bail()
     state = self._fsmonitorstate
     clock, ignorehash, notefiles = state.get()
     if not clock:
         if state.walk_on_invalidate:
             return bail()
         # Initial NULL clock value, see
         # https://facebook.github.io/watchman/docs/clockspec.html
         clock = 'c:0:0'
         notefiles = []
 
     def fwarn(f, msg):
         self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
         return False
 
     def badtype(mode):
         kind = _('unknown')
         if stat.S_ISCHR(mode):
             kind = _('character device')
         elif stat.S_ISBLK(mode):
             kind = _('block device')
         elif stat.S_ISFIFO(mode):
             kind = _('fifo')
         elif stat.S_ISSOCK(mode):
             kind = _('socket')
         elif stat.S_ISDIR(mode):
             kind = _('directory')
         return _('unsupported file type (type is %s)') % kind
 
     ignore = self._ignore
     dirignore = self._dirignore
     if unknown:
         if _hashignore(ignore) != ignorehash and clock != 'c:0:0':
             # ignore list changed -- can't rely on Watchman state any more
             if state.walk_on_invalidate:
                 return bail()
             notefiles = []
             clock = 'c:0:0'
     else:
         # always ignore
         ignore = util.always
         dirignore = util.always
 
     matchfn = match.matchfn
     matchalways = match.always()
     dmap = self._map
     nonnormalset = getattr(self, '_nonnormalset', None)
 
     copymap = self._copymap
     getkind = stat.S_IFMT
     dirkind = stat.S_IFDIR
     regkind = stat.S_IFREG
     lnkkind = stat.S_IFLNK
     join = self._join
     normcase = util.normcase
     fresh_instance = False
 
     exact = skipstep3 = False
     if matchfn == match.exact:  # match.exact
         exact = True
         dirignore = util.always  # skip step 2
     elif match.files() and not match.anypats():  # match.match, no patterns
         skipstep3 = True
 
     if not exact and self._checkcase:
         # note that even though we could receive directory entries, we're only
         # interested in checking if a file with the same name exists. So only
         # normalize files if possible.
         normalize = self._normalizefile
         skipstep3 = False
     else:
         normalize = None
 
     # step 1: find all explicit files
     results, work, dirsnotfound = self._walkexplicit(match, subrepos)
 
     skipstep3 = skipstep3 and not (work or dirsnotfound)
     work = [d for d in work if not dirignore(d[0])]
 
     if not work and (exact or skipstep3):
         for s in subrepos:
             del results[s]
         del results['.hg']
         return results
 
     # step 2: query Watchman
     try:
         # Use the user-configured timeout for the query.
         # Add a little slack over the top of the user query to allow for
         # overheads while transferring the data
         self._watchmanclient.settimeout(state.timeout + 0.1)
         result = self._watchmanclient.command('query', {
             'fields': ['mode', 'mtime', 'size', 'exists', 'name'],
             'since': clock,
             'expression': [
                 'not', [
                     'anyof', ['dirname', '.hg'],
                     ['name', '.hg', 'wholename']
                 ]
             ],
             'sync_timeout': int(state.timeout * 1000),
             'empty_on_fresh_instance': state.walk_on_invalidate,
         })
     except Exception as ex:
         _handleunavailable(self._ui, state, ex)
         self._watchmanclient.clearconnection()
         return bail()
     else:
         # We need to propagate the last observed clock up so that we
         # can use it for our next query
         state.setlastclock(result['clock'])
         if result['is_fresh_instance']:
             if state.walk_on_invalidate:
                 state.invalidate()
                 return bail()
             fresh_instance = True
             # Ignore any prior noteable files from the state info
             notefiles = []
 
     # for file paths which require normalization and we encounter a case
     # collision, we store our own foldmap
     if normalize:
         foldmap = dict((normcase(k), k) for k in results)
 
     switch_slashes = os.sep == '\\'
     # The order of the results is, strictly speaking, undefined.
     # For case changes on a case insensitive filesystem we may receive
     # two entries, one with exists=True and another with exists=False.
     # The exists=True entries in the same response should be interpreted
     # as being happens-after the exists=False entries due to the way that
     # Watchman tracks files.  We use this property to reconcile deletes
     # for name case changes.
     for entry in result['files']:
         fname = entry['name']
         if switch_slashes:
             fname = fname.replace('\\', '/')
         if normalize:
             normed = normcase(fname)
             fname = normalize(fname, True, True)
             foldmap[normed] = fname
         fmode = entry['mode']
         fexists = entry['exists']
         kind = getkind(fmode)
 
         if not fexists:
             # if marked as deleted and we don't already have a change
             # record, mark it as deleted.  If we already have an entry
             # for fname then it was either part of walkexplicit or was
             # an earlier result that was a case change
             if fname not in results and fname in dmap and (
                     matchalways or matchfn(fname)):
                 results[fname] = None
         elif kind == dirkind:
             if fname in dmap and (matchalways or matchfn(fname)):
                 results[fname] = None
         elif kind == regkind or kind == lnkkind:
             if fname in dmap:
                 if matchalways or matchfn(fname):
                     results[fname] = entry
             elif (matchalways or matchfn(fname)) and not ignore(fname):
                 results[fname] = entry
         elif fname in dmap and (matchalways or matchfn(fname)):
             results[fname] = None
 
     # step 3: query notable files we don't already know about
     # XXX try not to iterate over the entire dmap
     if normalize:
         # any notable files that have changed case will already be handled
         # above, so just check membership in the foldmap
         notefiles = set((normalize(f, True, True) for f in notefiles
                          if normcase(f) not in foldmap))
     visit = set((f for f in notefiles if (f not in results and matchfn(f)
                                           and (f in dmap or not ignore(f)))))
 
     if nonnormalset is not None and not fresh_instance:
         if matchalways:
             visit.update(f for f in nonnormalset if f not in results)
             visit.update(f for f in copymap if f not in results)
         else:
             visit.update(f for f in nonnormalset
                          if f not in results and matchfn(f))
             visit.update(f for f in copymap
                          if f not in results and matchfn(f))
     else:
         if matchalways:
             visit.update(f for f, st in dmap.iteritems()
                          if (f not in results and
                              (st[2] < 0 or st[0] != 'n' or fresh_instance)))
             visit.update(f for f in copymap if f not in results)
         else:
             visit.update(f for f, st in dmap.iteritems()
                          if (f not in results and
                              (st[2] < 0 or st[0] != 'n' or fresh_instance)
                              and matchfn(f)))
             visit.update(f for f in copymap
                          if f not in results and matchfn(f))
 
     audit = pathutil.pathauditor(self._root).check
     auditpass = [f for f in visit if audit(f)]
     auditpass.sort()
     auditfail = visit.difference(auditpass)
     for f in auditfail:
         results[f] = None
 
     nf = iter(auditpass).next
     for st in util.statfiles([join(f) for f in auditpass]):
         f = nf()
         if st or f in dmap:
             results[f] = st
 
     for s in subrepos:
         del results[s]
     del results['.hg']
     return results
 
 def overridestatus(
         orig, self, node1='.', node2=None, match=None, ignored=False,
         clean=False, unknown=False, listsubrepos=False):
     listignored = ignored
     listclean = clean
     listunknown = unknown
 
     def _cmpsets(l1, l2):
         try:
             if 'FSMONITOR_LOG_FILE' in os.environ:
                 fn = os.environ['FSMONITOR_LOG_FILE']
                 f = open(fn, 'wb')
             else:
                 fn = 'fsmonitorfail.log'
                 f = self.opener(fn, 'wb')
         except (IOError, OSError):
             self.ui.warn(_('warning: unable to write to %s\n') % fn)
             return
 
         try:
             for i, (s1, s2) in enumerate(zip(l1, l2)):
                 if set(s1) != set(s2):
                     f.write('sets at position %d are unequal\n' % i)
                     f.write('watchman returned: %s\n' % s1)
                     f.write('stat returned: %s\n' % s2)
         finally:
             f.close()
 
     if isinstance(node1, context.changectx):
         ctx1 = node1
     else:
         ctx1 = self[node1]
     if isinstance(node2, context.changectx):
         ctx2 = node2
     else:
         ctx2 = self[node2]
 
     working = ctx2.rev() is None
     parentworking = working and ctx1 == self['.']
     match = match or matchmod.always(self.root, self.getcwd())
 
     # Maybe we can use this opportunity to update Watchman's state.
     # Mercurial uses workingcommitctx and/or memctx to represent the part of
     # the workingctx that is to be committed. So don't update the state in
     # that case.
     # HG_PENDING is set in the environment when the dirstate is being updated
     # in the middle of a transaction; we must not update our state in that
     # case, or we risk forgetting about changes in the working copy.
     updatestate = (parentworking and match.always() and
                    not isinstance(ctx2, (context.workingcommitctx,
                                          context.memctx)) and
                    'HG_PENDING' not in os.environ)
 
     try:
         if self._fsmonitorstate.walk_on_invalidate:
             # Use a short timeout to query the current clock.  If that
             # takes too long then we assume that the service will be slow
             # to answer our query.
             # walk_on_invalidate indicates that we prefer to walk the
             # tree ourselves because we can ignore portions that Watchman
             # cannot and we tend to be faster in the warmer buffer cache
             # cases.
             self._watchmanclient.settimeout(0.1)
         else:
             # Give Watchman more time to potentially complete its walk
             # and return the initial clock.  In this mode we assume that
             # the filesystem will be slower than parsing a potentially
             # very large Watchman result set.
             self._watchmanclient.settimeout(
                 self._fsmonitorstate.timeout + 0.1)
         startclock = self._watchmanclient.getcurrentclock()
     except Exception as ex:
         self._watchmanclient.clearconnection()
         _handleunavailable(self.ui, self._fsmonitorstate, ex)
         # boo, Watchman failed. bail
         return orig(node1, node2, match, listignored, listclean,
                     listunknown, listsubrepos)
 
     if updatestate:
         # We need info about unknown files. This may make things slower the
         # first time, but whatever.
         stateunknown = True
     else:
         stateunknown = listunknown
 
     r = orig(node1, node2, match, listignored, listclean, stateunknown,
              listsubrepos)
     modified, added, removed, deleted, unknown, ignored, clean = r
 
     if updatestate:
         notefiles = modified + added + removed + deleted + unknown
         self._fsmonitorstate.set(
             self._fsmonitorstate.getlastclock() or startclock,
             _hashignore(self.dirstate._ignore),
             notefiles)
 
     if not listunknown:
         unknown = []
 
     # don't do paranoid checks if we're not going to query Watchman anyway
     full = listclean or match.traversedir is not None
     if self._fsmonitorstate.mode == 'paranoid' and not full:
         # run status again and fall back to the old walk this time
         self.dirstate._fsmonitordisable = True
 
         # shut the UI up
         quiet = self.ui.quiet
         self.ui.quiet = True
         fout, ferr = self.ui.fout, self.ui.ferr
         self.ui.fout = self.ui.ferr = open(os.devnull, 'wb')
 
         try:
             rv2 = orig(
                 node1, node2, match, listignored, listclean, listunknown,
                 listsubrepos)
         finally:
             self.dirstate._fsmonitordisable = False
             self.ui.quiet = quiet
             self.ui.fout, self.ui.ferr = fout, ferr
 
         # clean isn't tested since it's set to True above
         _cmpsets([modified, added, removed, deleted, unknown, ignored, clean],
                  rv2)
         modified, added, removed, deleted, unknown, ignored, clean = rv2
 
     return scmutil.status(
         modified, added, removed, deleted, unknown, ignored, clean)
 
 def makedirstate(cls):
     class fsmonitordirstate(cls):
         def _fsmonitorinit(self, fsmonitorstate, watchmanclient):
             # _fsmonitordisable is used in paranoid mode
             self._fsmonitordisable = False
             self._fsmonitorstate = fsmonitorstate
             self._watchmanclient = watchmanclient
 
         def walk(self, *args, **kwargs):
             orig = super(fsmonitordirstate, self).walk
             if self._fsmonitordisable:
                 return orig(*args, **kwargs)
             return overridewalk(orig, self, *args, **kwargs)
 
         def rebuild(self, *args, **kwargs):
             self._fsmonitorstate.invalidate()
             return super(fsmonitordirstate, self).rebuild(*args, **kwargs)
 
         def invalidate(self, *args, **kwargs):
             self._fsmonitorstate.invalidate()
             return super(fsmonitordirstate, self).invalidate(*args, **kwargs)
 
     return fsmonitordirstate
 
 def wrapdirstate(orig, self):
     ds = orig(self)
     # only override the dirstate when Watchman is available for the repo
     if util.safehasattr(self, '_fsmonitorstate'):
         ds.__class__ = makedirstate(ds.__class__)
         ds._fsmonitorinit(self._fsmonitorstate, self._watchmanclient)
     return ds
 
 def extsetup(ui):
     wrapfilecache(localrepo.localrepository, 'dirstate', wrapdirstate)
     if sys.platform == 'darwin':
         # An assist for avoiding the dangling-symlink fsevents bug
         extensions.wrapfunction(os, 'symlink', wrapsymlink)
 
     extensions.wrapfunction(merge, 'update', wrapupdate)
 
 def wrapsymlink(orig, source, link_name):
     ''' if we create a dangling symlink, also touch the parent dir
     to encourage fsevents notifications to work more correctly '''
     try:
         return orig(source, link_name)
     finally:
         try:
             os.utime(os.path.dirname(link_name), None)
         except OSError:
             pass
 
 class state_update(object):
     ''' This context mananger is responsible for dispatching the state-enter
         and state-leave signals to the watchman service '''
 
     def __init__(self, repo, node, distance, partial):
         self.repo = repo
         self.node = node
         self.distance = distance
         self.partial = partial
 
     def __enter__(self):
         self._state('state-enter')
         return self
 
     def __exit__(self, type_, value, tb):
         status = 'ok' if type_ is None else 'failed'
         self._state('state-leave', status=status)
 
     def _state(self, cmd, status='ok'):
         if not util.safehasattr(self.repo, '_watchmanclient'):
             return
         try:
             commithash = self.repo[self.node].hex()
             self.repo._watchmanclient.command(cmd, {
                 'name': 'hg.update',
                 'metadata': {
                     # the target revision
                     'rev': commithash,
                     # approximate number of commits between current and target
                     'distance': self.distance,
                     # success/failure (only really meaningful for state-leave)
                     'status': status,
                     # whether the working copy parent is changing
                     'partial': self.partial,
             }})
         except Exception as e:
             # Swallow any errors; fire and forget
             self.repo.ui.log(
                 'watchman', 'Exception %s while running %s\n', e, cmd)
 
 # Bracket working copy updates with calls to the watchman state-enter
 # and state-leave commands.  This allows clients to perform more intelligent
 # settling during bulk file change scenarios
 # https://facebook.github.io/watchman/docs/cmd/subscribe.html#advanced-settling
 def wrapupdate(orig, repo, node, branchmerge, force, ancestor=None,
                mergeancestor=False, labels=None, matcher=None, **kwargs):
 
     distance = 0
     partial = True
     if matcher is None or matcher.always():
         partial = False
         wc = repo[None]
         parents = wc.parents()
         if len(parents) == 2:
             anc = repo.changelog.ancestor(parents[0].node(), parents[1].node())
             ancrev = repo[anc].rev()
             distance = abs(repo[node].rev() - ancrev)
         elif len(parents) == 1:
             distance = abs(repo[node].rev() - parents[0].rev())
 
     with state_update(repo, node, distance, partial):
         return orig(
             repo, node, branchmerge, force, ancestor, mergeancestor,
             labels, matcher, *kwargs)
 
 def reposetup(ui, repo):
     # We don't work with largefiles or inotify
     exts = extensions.enabled()
     for ext in _blacklist:
         if ext in exts:
             ui.warn(_('The fsmonitor extension is incompatible with the %s '
                       'extension and has been disabled.\n') % ext)
             return
 
     if util.safehasattr(repo, 'dirstate'):
         # We don't work with subrepos either. Note that we can get passed in
         # e.g. a statichttprepo, which throws on trying to access the substate.
         # XXX This sucks.
         try:
             # if repo[None].substate can cause a dirstate parse, which is too
             # slow. Instead, look for a file called hgsubstate,
             if repo.wvfs.exists('.hgsubstate') or repo.wvfs.exists('.hgsub'):
                 return
         except AttributeError:
             return
 
         fsmonitorstate = state.state(repo)
         if fsmonitorstate.mode == 'off':
             return
 
         try:
             client = watchmanclient.client(repo)
         except Exception as ex:
             _handleunavailable(ui, fsmonitorstate, ex)
             return
 
         repo._fsmonitorstate = fsmonitorstate
         repo._watchmanclient = client
 
         # at this point since fsmonitorstate wasn't present, repo.dirstate is
         # not a fsmonitordirstate
         repo.dirstate.__class__ = makedirstate(repo.dirstate.__class__)
         # nuke the dirstate so that _fsmonitorinit and subsequent configuration
         # changes take effect on it
         del repo._filecache['dirstate']
         delattr(repo.unfiltered(), 'dirstate')
 
         class fsmonitorrepo(repo.__class__):
             def status(self, *args, **kwargs):
                 orig = super(fsmonitorrepo, self).status
                 return overridestatus(orig, self, *args, **kwargs)
 
         repo.__class__ = fsmonitorrepo
 
 def wrapfilecache(cls, propname, wrapper):
     """Wraps a filecache property. These can't be wrapped using the normal
     wrapfunction. This should eventually go into upstream Mercurial.
     """
     assert callable(wrapper)
     for currcls in cls.__mro__:
         if propname in currcls.__dict__:
             origfn = currcls.__dict__[propname].func
             assert callable(origfn)
             def wrap(*args, **kwargs):
                 return wrapper(origfn, *args, **kwargs)
             currcls.__dict__[propname].func = wrap
             break
 
     if currcls is object:
         raise AttributeError(
             _("type '%s' has no property '%s'") % (cls, propname))

hgext/gpg.py

@@ -1,318 +1,318 b''
 # Copyright 2005, 2006 Benoit Boissinot <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''commands to sign and verify changesets'''
 
 from __future__ import absolute_import
 
 import binascii
 import os
 import tempfile
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     error,
     match,
     node as hgnode,
     util,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 class gpg(object):
     def __init__(self, path, key=None):
         self.path = path
         self.key = (key and " --local-user \"%s\"" % key) or ""
 
     def sign(self, data):
         gpgcmd = "%s --sign --detach-sign%s" % (self.path, self.key)
         return util.filter(data, gpgcmd)
 
     def verify(self, data, sig):
         """ returns of the good and bad signatures"""
         sigfile = datafile = None
         try:
             # create temporary files
             fd, sigfile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".sig")
             fp = os.fdopen(fd, 'wb')
             fp.write(sig)
             fp.close()
             fd, datafile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".txt")
             fp = os.fdopen(fd, 'wb')
             fp.write(data)
             fp.close()
             gpgcmd = ("%s --logger-fd 1 --status-fd 1 --verify "
                       "\"%s\" \"%s\"" % (self.path, sigfile, datafile))
             ret = util.filter("", gpgcmd)
         finally:
             for f in (sigfile, datafile):
                 try:
                     if f:
                         os.unlink(f)
                 except OSError:
                     pass
         keys = []
         key, fingerprint = None, None
         for l in ret.splitlines():
             # see DETAILS in the gnupg documentation
             # filter the logger output
             if not l.startswith("[GNUPG:]"):
                 continue
             l = l[9:]
             if l.startswith("VALIDSIG"):
                 # fingerprint of the primary key
                 fingerprint = l.split()[10]
             elif l.startswith("ERRSIG"):
                 key = l.split(" ", 3)[:2]
                 key.append("")
                 fingerprint = None
             elif (l.startswith("GOODSIG") or
                   l.startswith("EXPSIG") or
                   l.startswith("EXPKEYSIG") or
                   l.startswith("BADSIG")):
                 if key is not None:
                     keys.append(key + [fingerprint])
                 key = l.split(" ", 2)
                 fingerprint = None
         if key is not None:
             keys.append(key + [fingerprint])
         return keys
 
 def newgpg(ui, **opts):
     """create a new gpg instance"""
     gpgpath = ui.config("gpg", "cmd", "gpg")
     gpgkey = opts.get('key')
     if not gpgkey:
         gpgkey = ui.config("gpg", "key", None)
     return gpg(gpgpath, gpgkey)
 
 def sigwalk(repo):
     """
     walk over every sigs, yields a couple
     ((node, version, sig), (filename, linenumber))
     """
     def parsefile(fileiter, context):
         ln = 1
         for l in fileiter:
             if not l:
                 continue
             yield (l.split(" ", 2), (context, ln))
             ln += 1
 
     # read the heads
     fl = repo.file(".hgsigs")
     for r in reversed(fl.heads()):
         fn = ".hgsigs|%s" % hgnode.short(r)
         for item in parsefile(fl.read(r).splitlines(), fn):
             yield item
     try:
         # read local signatures
         fn = "localsigs"
         for item in parsefile(repo.vfs(fn), fn):
             yield item
     except IOError:
         pass
 
 def getkeys(ui, repo, mygpg, sigdata, context):
     """get the keys who signed a data"""
     fn, ln = context
     node, version, sig = sigdata
     prefix = "%s:%d" % (fn, ln)
     node = hgnode.bin(node)
 
     data = node2txt(repo, node, version)
     sig = binascii.a2b_base64(sig)
     keys = mygpg.verify(data, sig)
 
     validkeys = []
     # warn for expired key and/or sigs
     for key in keys:
         if key[0] == "ERRSIG":
             ui.write(_("%s Unknown key ID \"%s\"\n")
                      % (prefix, shortkey(ui, key[1][:15])))
             continue
         if key[0] == "BADSIG":
             ui.write(_("%s Bad signature from \"%s\"\n") % (prefix, key[2]))
             continue
         if key[0] == "EXPSIG":
             ui.write(_("%s Note: Signature has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         elif key[0] == "EXPKEYSIG":
             ui.write(_("%s Note: This key has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         validkeys.append((key[1], key[2], key[3]))
     return validkeys
 
 @command("sigs", [], _('hg sigs'))
 def sigs(ui, repo):
     """list signed changesets"""
     mygpg = newgpg(ui)
     revs = {}
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         fn, ln = context
         try:
             n = repo.lookup(node)
         except KeyError:
             ui.warn(_("%s:%d node does not exist\n") % (fn, ln))
             continue
         r = repo.changelog.rev(n)
         keys = getkeys(ui, repo, mygpg, data, context)
         if not keys:
             continue
         revs.setdefault(r, [])
         revs[r].extend(keys)
     for rev in sorted(revs, reverse=True):
         for k in revs[rev]:
             r = "%5d:%s" % (rev, hgnode.hex(repo.changelog.node(rev)))
             ui.write("%-30s %s\n" % (keystr(ui, k), r))
 
 @command("sigcheck", [], _('hg sigcheck REV'))
 def sigcheck(ui, repo, rev):
     """verify all the signatures there may be for a particular revision"""
     mygpg = newgpg(ui)
     rev = repo.lookup(rev)
     hexrev = hgnode.hex(rev)
     keys = []
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         if node == hexrev:
             k = getkeys(ui, repo, mygpg, data, context)
             if k:
                 keys.extend(k)
 
     if not keys:
         ui.write(_("no valid signature for %s\n") % hgnode.short(rev))
         return
 
     # print summary
     ui.write(_("%s is signed by:\n") % hgnode.short(rev))
     for key in keys:
         ui.write(" %s\n" % keystr(ui, key))
 
 def keystr(ui, key):
     """associate a string to a key (username, comment)"""
     keyid, user, fingerprint = key
     comment = ui.config("gpg", fingerprint, None)
     if comment:
         return "%s (%s)" % (user, comment)
     else:
         return user
 
 @command("sign",
          [('l', 'local', None, _('make the signature local')),
           ('f', 'force', None, _('sign even if the sigfile is modified')),
           ('', 'no-commit', None, _('do not commit the sigfile after signing')),
           ('k', 'key', '',
            _('the key id to sign with'), _('ID')),
           ('m', 'message', '',
            _('use text as commit message'), _('TEXT')),
           ('e', 'edit', False, _('invoke editor on commit messages')),
          ] + commands.commitopts2,
          _('hg sign [OPTION]... [REV]...'))
 def sign(ui, repo, *revs, **opts):
     """add a signature for the current or given revision
 
     If no revision is given, the parent of the working directory is used,
     or tip if no revision is checked out.
 
     The ``gpg.cmd`` config setting can be used to specify the command
     to run. A default key can be specified with ``gpg.key``.
 
     See :hg:`help dates` for a list of formats valid for -d/--date.
     """
     with repo.wlock():
         return _dosign(ui, repo, *revs, **opts)
 
 def _dosign(ui, repo, *revs, **opts):
     mygpg = newgpg(ui, **opts)
     sigver = "0"
     sigmessage = ""
 
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
 
     if revs:
         nodes = [repo.lookup(n) for n in revs]
     else:
         nodes = [node for node in repo.dirstate.parents()
                  if node != hgnode.nullid]
         if len(nodes) > 1:
             raise error.Abort(_('uncommitted merge - please provide a '
                                'specific revision'))
         if not nodes:
             nodes = [repo.changelog.tip()]
 
     for n in nodes:
         hexnode = hgnode.hex(n)
         ui.write(_("signing %d:%s\n") % (repo.changelog.rev(n),
                                          hgnode.short(n)))
         # build data
         data = node2txt(repo, n, sigver)
         sig = mygpg.sign(data)
         if not sig:
             raise error.Abort(_("error while signing"))
         sig = binascii.b2a_base64(sig)
         sig = sig.replace("\n", "")
         sigmessage += "%s %s %s\n" % (hexnode, sigver, sig)
 
     # write it
     if opts['local']:
         repo.vfs.append("localsigs", sigmessage)
         return
 
     if not opts["force"]:
         msigs = match.exact(repo.root, '', ['.hgsigs'])
         if any(repo.status(match=msigs, unknown=True, ignored=True)):
             raise error.Abort(_("working copy of .hgsigs is changed "),
                              hint=_("please commit .hgsigs manually"))
 
     sigsfile = repo.wfile(".hgsigs", "ab")
     sigsfile.write(sigmessage)
     sigsfile.close()
 
     if '.hgsigs' not in repo.dirstate:
         repo[None].add([".hgsigs"])
 
     if opts["no_commit"]:
         return
 
     message = opts['message']
     if not message:
         # we don't translate commit messages
         message = "\n".join(["Added signature for changeset %s"
                              % hgnode.short(n)
                              for n in nodes])
     try:
         editor = cmdutil.getcommiteditor(editform='gpg.sign', **opts)
         repo.commit(message, opts['user'], opts['date'], match=msigs,
                     editor=editor)
     except ValueError as inst:
         raise error.Abort(str(inst))
 
 def shortkey(ui, key):
     if len(key) != 16:
         ui.debug("key ID \"%s\" format error\n" % key)
         return key
 
     return key[-8:]
 
 def node2txt(repo, node, ver):
     """map a manifest into some text"""
     if ver == "0":
         return "%s\n" % hgnode.hex(node)
     else:
         raise error.Abort(_("unknown signature version"))

hgext/graphlog.py

@@ -1,69 +1,69 b''
 # ASCII graph log extension for Mercurial
 #
 # Copyright 2007 Joel Rosdahl <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to view revision graphs from a shell (DEPRECATED)
 
 The functionality of this extension has been include in core Mercurial
 since version 2.3. Please use :hg:`log -G ...` instead.
 
 This extension adds a --graph option to the incoming, outgoing and log
 commands. When this options is given, an ASCII representation of the
 revision graph is also shown.
 '''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
 )
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
-# Note for extension authors: ONLY specify testedwith = 'internal' for
+# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
-testedwith = 'internal'
+testedwith = 'ships-with-hg-core'
 
 @command('glog',
     [('f', 'follow', None,
      _('follow changeset history, or file history across copies and renames')),
     ('', 'follow-first', None,
      _('only follow the first parent of merge changesets (DEPRECATED)')),
     ('d', 'date', '', _('show revisions matching date spec'), _('DATE')),
     ('C', 'copies', None, _('show copied files')),
     ('k', 'keyword', [],
      _('do case-insensitive search for a given text'), _('TEXT')),
     ('r', 'rev', [], _('show the specified revision or revset'), _('REV')),
     ('', 'removed', None, _('include revisions where files were removed')),
     ('m', 'only-merges', None, _('show only merges (DEPRECATED)')),
     ('u', 'user', [], _('revisions committed by user'), _('USER')),
     ('', 'only-branch', [],
      _('show only changesets within the given named branch (DEPRECATED)'),
      _('BRANCH')),
     ('b', 'branch', [],
      _('show changesets within the given named branch'), _('BRANCH')),
     ('P', 'prune', [],
      _('do not display revision or any of its ancestors'), _('REV')),
     ] + commands.logopts + commands.walkopts,
     _('[OPTION]... [FILE]'),
     inferrepo=True)
 def glog(ui, repo, *pats, **opts):
     """show revision history alongside an ASCII revision graph
 
     Print a revision history alongside a revision graph drawn with
     ASCII characters.
 
     Nodes printed as an @ character are parents of the working
     directory.
 
     This is an alias to :hg:`log -G`.
     """
     opts['graph'] = True
     return commands.log(ui, repo, *pats, **opts)