check-code.py: Check for bare ^

Solaris sh interprets ^ as some kind of piping symbol.

contrib/check-code.py

@@ -1,168 +1,169
 #!/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.
 
 import sys, re, glob
 
 def repquote(m):
     t = re.sub(r"\w", "x", m.group(2))
     t = re.sub(r"[^\sx]", "o", t)
     return m.group(1) + t + m.group(1)
 
 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\$?\(\([^\)]*\)\)', "don't use (()) or $(()), use 'expr'"),
     (r'^function', "don't use 'function', use old style"),
     (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
     (r'echo.*\\n', "don't use 'echo \\n', use printf"),
     (r'^diff.*-\w*N', "don't use 'diff -N'"),
     (r'(^| )wc[^|]*$', "filter wc output"),
     (r'head -c', "don't use 'head -c', use 'dd'"),
     (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
     (r'printf.*\\\d\d\d', "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'\$PWD', "don't use $PWD, use `pwd`"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'export.*=', "don't export and assign at once"),
+    ('^([^"\']|("[^"]*")|(\'[^\']*\'))*\\^', "^ must be quoted"),
 ]
 
 testfilters = [
     (r"( *)(#([^\n]*\S)?)", repcomment),
     (r"<<(\S+)((.|\n)*?\n\1)", rephere),
 ]
 
 pypats = [
     (r'^\s*\t', "don't use tabs"),
     (r'\S;\s*\n', "semicolon"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'\w[+/*\-<>]\w', "missing whitespace in expression"),
     (r'^\s+\w+=\w+[^,)]$', "missing whitespace in assignment"),
     (r'.{85}', "line too long"),
     (r'[^\n]\Z', "no trailing newline"),
 #    (r'^\s+[^_ ][^_. ]+_[^_]+\s*=', "don't use underbars in identifiers"),
 #    (r'\w*[a-z][A-Z]\w*\s*=', "don't use camelcase in identifiers"),
     (r'^\s*(if|while|def|class|except|try)\s[^[]*:\s*[^\]#\s]+',
      "linebreak after :"),
     (r'class\s[^(]:', "old-style class, use class foo(object)"),
     (r'^\s+del\(', "del isn't a function"),
     (r'^\s+except\(', "except isn't 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() not available in Python 2.4"),
     (r'^\s*with\s+', "with not available in Python 2.4"),
     (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
     (r'([\(\[]\s\S)|(\S\s[\)\]])', "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'raise Exception', "don't raise generic exceptions"),
     (r'ui\.(status|progress|write|note)\([\'\"]x', "unwrapped ui message"),
 ]
 
 pyfilters = [
     (r"""(''')(([^']|\\'|'{1,2}(?!'))*)'''""", repquote),
     (r'''(""")(([^"]|\\"|"{1,2}(?!"))*)"""''', repquote),
     (r'''(?<!")(")(([^"\n]|\\")+)"(?!")''', repquote),
     (r"""(?<!')(')(([^'\n]|\\')+)'(?!')""", repquote),
     (r"( *)(#([^\n]*\S)?)", repcomment),
 ]
 
 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\s+|^\s+)\n', "trailing whitespace"),
     (r'.{85}', "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'\w+\* \w+', "use int *foo, not int* foo"),
     (r'\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
     (r'\S+ (\+\+|--)', "use foo++, not foo ++"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'\w[+/*]\w', "missing whitespace in expression"),
     (r'^#\s+\w', "use #foo, not # foo"),
     (r'[^\n]\Z', "no trailing newline"),
 ]
 
 cfilters = [
     (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
     (r'''(?<!")(")(([^"]|\\")+"(?!"))''', repquote),
     (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
     (r'(\()([^)]+\))', repcallspaces),
 ]
 
 checks = [
     ('python', r'.*\.(py|cgi)$', pyfilters, pypats),
     ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats),
     ('c', r'.*\.c$', cfilters, cpats),
 ]
 
 if len(sys.argv) == 1:
     check = glob.glob("*")
 else:
     check = sys.argv[1:]
 
 for f in check:
     for name, match, filters, pats in checks:
         fc = 0
         if not re.match(match, f):
             continue
         pre = post = open(f).read()
         if "no-" + "check-code" in pre:
             break
         for p, r in filters:
             post = re.sub(p, r, post)
         # print post # uncomment to show filtered version
         z = enumerate(zip(pre.splitlines(), post.splitlines(True)))
         for n, l in z:
             if "check-code" + "-ignore" in l[0]:
                 continue
             lc = 0
             for p, msg in pats:
                 if re.search(p, l[1]):
                     if not lc:
                         print "%s:%d:" % (f, n + 1)
                         print " > %s" % l[0]
                     print " %s" % msg
                     lc += 1
                     fc += 1
             if fc == 15:
                 print " (too many errors, giving up)"
                 break
         break

tests/test-convert-baz

@@ -1,83 +1,83
 #!/bin/sh
 
 "$TESTDIR/hghave" baz || exit 80
 
 mkdir do_not_use_HOME_baz
 cd do_not_use_HOME_baz
 HOME=`pwd`; export HOME
 cd ..
 baz my-id "mercurial <[e-mail]>"
 
 echo "[extensions]" >> $HGRCPATH
 echo "convert=" >> $HGRCPATH
 echo 'graphlog =' >> $HGRCPATH
 
 echo % create baz archive
 baz make-archive baz@mercurial--convert hg-test-convert-baz
 
 echo % initialize baz repo
 mkdir baz-repo
 cd baz-repo/
 baz init-tree baz@mercurial--convert/baz--test--0
 baz import
 
 echo % create initial files
 echo 'this is a file' > a
 baz add a
 mkdir src
 baz add src
 cd src
 dd count=1 if=/dev/zero of=b > /dev/null 2> /dev/null
 baz add b
 # HACK: hide GNU tar-1.22 "tar: The --preserve option is deprecated, use --preserve-permissions --preserve-order instead"
-baz commit -s "added a file, src and src/b (binary)" 2>&1 | grep -v ^tar
+baz commit -s "added a file, src and src/b (binary)" 2>&1 | grep -v '^tar'
 
 echo % create link file and modify a
 ln -s ../a a-link
 baz add a-link
 echo 'this a modification to a' >> ../a
 baz commit -s "added link to a and modify a"
 
 echo % create second link and modify b
 ln -s ../a a-link-2
 baz add a-link-2
 dd count=1 seek=1 if=/dev/zero of=b > /dev/null 2> /dev/null
 baz commit -s "added second link and modify b"
 
 echo % b file to link and a-link-2 to regular file
 rm -f a-link-2
 echo 'this is now a regular file' > a-link-2
 ln -sf ../a b
 baz commit -s "file to link and link to file test"
 
 echo % move a-link-2 file and src directory
 cd ..
 baz mv src/a-link-2 c
 baz mv src test
 baz commit -s "move and rename a-link-2 file and src directory"
 
 echo % move and add the moved file again
 echo e > e
 baz add e
 baz commit -s "add e"
 baz mv e f
 echo ee > e
 baz add e
 baz commit -s "move e and recreate it again"
 cd ..
 
 echo % converting baz repo to Mercurial
 hg convert baz-repo baz-repo-hg
 
 baz register-archive -d baz@mercurial--convert
 
 glog()
 {
     hg glog --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
 }
 
 echo % show graph log
 glog -R baz-repo-hg
 hg up -q -R baz-repo-hg
 hg -R baz-repo-hg manifest --debug
 hg -R baz-repo-hg log -r 5 -r 7 -C --debug | grep copies

tests/test-convert-cvs-synthetic

@@ -1,118 +1,118
 #!/bin/sh
 
 # This feature requires use of builtin cvsps!
 "$TESTDIR/hghave" cvs || exit 80
 
 set -e
 
 echo "[extensions]" >> $HGRCPATH
 echo "convert = " >> $HGRCPATH
 echo "graphlog = " >> $HGRCPATH
 
 echo % create cvs repository with one project
 mkdir cvsrepo
 cd cvsrepo
 CVSROOT=`pwd`
 export CVSROOT
 CVS_OPTIONS=-f
 export CVS_OPTIONS
 cd ..
 
 filterpath()
 {
     eval "$@" | sed "s:$CVSROOT:*REPO*:g"
 }
 
 cvscall()
 {
     echo cvs -f "$@"
     cvs -f "$@" 2>&1
 }
 
 # output of 'cvs ci' varies unpredictably, so just discard it
 cvsci()
 {
     echo cvs -f ci "$@"
     cvs -f ci "$@" >/dev/null 2>&1
 }
 
 filterpath cvscall -d "$CVSROOT" init
 mkdir cvsrepo/proj
 
 cvscall -q co proj
 
 echo % create file1 on the trunk
 cd proj
 touch file1
 cvscall -Q add file1
 cvsci -m"add file1 on trunk" file1
 
 echo % create two branches
 cvscall -q tag -b v1_0
 cvscall -q tag -b v1_1
 
 echo % create file2 on branch v1_0
 cvscall -Q up -rv1_0
 touch file2
 cvscall -Q add file2
 cvsci -m"add file2" file2
 
 echo % create file3, file4 on branch v1_1
 cvscall -Q up -rv1_1
 touch file3
 touch file4
 cvscall -Q add file3 file4
 cvsci -m"add file3, file4 on branch v1_1" file3 file4
 
 echo % merge file2 from v1_0 to v1_1
 cvscall -Q up -jv1_0
 cvsci -m"MERGE from v1_0: add file2"
 
 # Step things up a notch: now we make the history really hairy, with
 # changes bouncing back and forth between trunk and v1_2 and merges
 # going both ways.  (I.e., try to model the real world.)
 
 echo "% create branch v1_2"
 cvscall -Q up -A
 cvscall -q tag -b v1_2
 
 echo "% create file5 on branch v1_2"
 cvscall -Q up -rv1_2
 touch file5
 cvs -Q add file5
 cvsci -m"add file5 on v1_2"
 
 echo "% create file6 on trunk post-v1_2"
 cvscall -Q up -A
 touch file6
 cvscall -Q add file6
 cvsci -m"add file6 on trunk post-v1_2"
 
 echo "% merge file5 from v1_2 to trunk"
 cvscall -Q up -A
 cvscall -Q up -jv1_2 file5
 cvsci -m"MERGE from v1_2: add file5"
 
 echo "% merge file6 from trunk to v1_2"
 cvscall -Q up -rv1_2
 cvscall up -jHEAD file6
 cvsci -m"MERGE from HEAD: add file6"
 
 echo % cvs rlog output
 filterpath cvscall -q rlog proj | egrep '^(RCS file|revision)'
 
 echo "% convert to hg (#1)"
 cd ..
 filterpath hg convert --datesort proj proj.hg
 
 echo "% hg glog output (#1)"
 hg -R proj.hg glog --template "{rev} {desc}\n"
 
 echo "% convert to hg (#2: with merge detection)"
 filterpath hg convert \
-  --config convert.cvsps.mergefrom="\"^MERGE from (\S+):\"" \
+  --config convert.cvsps.mergefrom='"^MERGE from (\S+):"' \
   --datesort \
   proj proj.hg2
 
 echo "% hg glog output (#2)"
 hg -R proj.hg2 glog --template "{rev} {desc}\n"