merge with stable

hgext/churn.py

@@ -1,197 +1,198 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 mercurial.i18n import _
 from mercurial import patch, cmdutil, util, templater, commands
 import os
 import time, datetime
 
 def maketemplater(ui, repo, tmpl):
     tmpl = templater.parsestring(tmpl, quoted=False)
     try:
         t = cmdutil.changeset_templater(ui, repo, False, None, None, False)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
     t.use_template(tmpl)
     return t
 
 def changedlines(ui, repo, ctx1, ctx2, fns):
     added, removed = 0, 0
     fmatch = cmdutil.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('template', '{author|email}')
         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 = cmdutil.match(repo, 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)
         key = amap.get(key, key) # alias remap
+        key = key.strip() # ignore leading and trailing spaces
         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))
 
     for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
         continue
 
     ui.progress(_('analyzing'), None)
 
     return rate
 
 
 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.
     '''
     def pad(s, l):
         return (s + " " * l)[:l]
 
     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.split('=' 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
 
     sortkey = ((not opts.get('sort')) and (lambda x: -sum(x[1])) or None)
     rate.sort(key=sortkey)
 
     # 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))
 
 
 cmdtable = {
     "churn":
         (churn,
          [('r', 'rev', [],
            _('count rate for the specified revision or range'), _('REV')),
           ('d', 'date', '',
            _('count rate for revisions matching date spec'), _('DATE')),
           ('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]")),
 }

hgext/eol.py

@@ -1,274 +1,280 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 every time you run an ``hg`` command. The
 ``.hgeol`` file use the same syntax as all other Mercurial
 configuration files. It uses two sections, ``[patterns]`` and
 ``[repository]``.
 
-The ``[patterns]`` section specifies the line endings used in the
-working directory. 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``.
+The ``[patterns]`` section specifies how line endings should be
+converted between the working copy 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 in that format and files declared to be binary (``BIN``)
-are left unchanged. Additionally, ``native`` is an alias for 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 behaviour; it is only needed if you
-need to override a later, more general pattern.
+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 behaviour; 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
+   copy, e.g. by updating to null and back to tip to touch all files.
+
 The extension uses an optional ``[eol]`` section in your hgrc file
 (not the ``.hgeol`` file) for settings that control the overall
 behavior. There are two 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.
 
 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.hook``. 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.
 
 See :hg:`help patterns` for more information about the glob patterns
 used.
 """
 
 from mercurial.i18n import _
 from mercurial import util, config, extensions, match
 import re, os
 
 # 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 Machintosh 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
     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
     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
 }
 
 
 def hook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     files = set()
     for rev in xrange(repo[node].rev(), len(repo)):
         files.update(repo[rev].files())
     tip = repo['tip']
     for f in files:
         if f not in tip:
             continue
         for pattern, target in ui.configitems('encode'):
             if match.match(repo.root, '', [pattern])(f):
                 data = tip[f].data()
                 if target == "to-lf" and "\r\n" in data:
                     raise util.Abort(_("%s should not have CRLF line endings")
                                      % f)
                 elif target == "to-crlf" and singlelf.search(data):
                     raise util.Abort(_("%s should not have LF line endings")
                                      % f)
 
 
 def preupdate(ui, repo, hooktype, parent1, parent2):
     #print "preupdate for %s: %s -> %s" % (repo.root, parent1, parent2)
     repo.readhgeol(parent1)
     return False
 
 def uisetup(ui):
     ui.setconfig('hooks', 'preupdate.eol', preupdate)
 
 def extsetup(ui):
     try:
         extensions.find('win32text')
         raise util.Abort(_("the eol extension is incompatible with the "
                            "win32text extension"))
     except KeyError:
         pass
 
 
 def reposetup(ui, repo):
     uisetup(repo.ui)
     #print "reposetup for", repo.root
 
     if not repo.local():
         return
     for name, fn in filters.iteritems():
         repo.adddatafilter(name, fn)
 
     ui.setconfig('patch', 'eol', 'auto')
 
     class eolrepo(repo.__class__):
 
         _decode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
         _encode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
 
         def readhgeol(self, node=None, data=None):
             if data is None:
                 try:
                     if node is None:
                         data = self.wfile('.hgeol').read()
                     else:
                         data = self[node]['.hgeol'].data()
                 except (IOError, LookupError):
                     return None
 
             if self.ui.config('eol', 'native', os.linesep) in ('LF', '\n'):
                 self._decode['NATIVE'] = 'to-lf'
             else:
                 self._decode['NATIVE'] = 'to-crlf'
 
             eol = config.config()
             # Our files should not be touched. The pattern must be
             # inserted first override a '** = native' pattern.
             eol.set('patterns', '.hg*', 'BIN')
             # We can then parse the user's patterns.
             eol.parse('.hgeol', data)
 
             if eol.get('repository', 'native') == 'CRLF':
                 self._encode['NATIVE'] = 'to-crlf'
             else:
                 self._encode['NATIVE'] = 'to-lf'
 
             for pattern, style in eol.items('patterns'):
                 key = style.upper()
                 try:
                     self.ui.setconfig('decode', pattern, self._decode[key])
                     self.ui.setconfig('encode', pattern, self._encode[key])
                 except KeyError:
                     self.ui.warn(_("ignoring unknown EOL style '%s' from %s\n")
                                  % (style, eol.source('patterns', pattern)))
 
             include = []
             exclude = []
             for pattern, style in eol.items('patterns'):
                 key = style.upper()
                 if key == 'BIN':
                     exclude.append(pattern)
                 else:
                     include.append(pattern)
 
             # This will match the files for which we need to care
             # about inconsistent newlines.
             return match.match(self.root, '', [], include, exclude)
 
         def _hgcleardirstate(self):
             self._eolfile = self.readhgeol() or self.readhgeol('tip')
 
             if not self._eolfile:
                 self._eolfile = util.never
                 return
 
             try:
                 cachemtime = os.path.getmtime(self.join("eol.cache"))
             except OSError:
                 cachemtime = 0
 
             try:
                 eolmtime = os.path.getmtime(self.wjoin(".hgeol"))
             except OSError:
                 eolmtime = 0
 
             if eolmtime > cachemtime:
                 ui.debug("eol: detected change in .hgeol\n")
                 # TODO: we could introduce a method for this in dirstate.
                 wlock = None
                 try:
                     wlock = self.wlock()
                     for f, e in self.dirstate._map.iteritems():
                         self.dirstate._map[f] = (e[0], e[1], -1, 0)
                     self.dirstate._dirty = True
                     # Touch the cache to update mtime. TODO: are we sure this
                     # always enought to update the mtime, or should we write a
                     # bit to the file?
                     self.opener("eol.cache", "w").close()
                 finally:
                     if wlock is not None:
                         wlock.release()
 
         def commitctx(self, ctx, error=False):
             for f in sorted(ctx.added() + ctx.modified()):
                 if not self._eolfile(f):
                     continue
                 data = ctx[f].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 util.Abort(_("inconsistent newline style "
                                        "in %s\n" % f))
             return super(eolrepo, self).commitctx(ctx, error)
     repo.__class__ = eolrepo
     repo._hgcleardirstate()

tests/test-churn.t

@@ -1,141 +1,160 b''
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "churn=" >> $HGRCPATH
 
 create test repository
 
   $ hg init repo
   $ cd repo
   $ echo a > a
   $ hg ci -Am adda -u user1 -d 6:00
   adding a
   $ echo b >> a
   $ echo b > b
   $ hg ci -m changeba -u user2 -d 9:00 a
   $ hg ci -Am addb -u user2 -d 9:30
   adding b
   $ echo c >> a
   $ echo c >> b
   $ echo c > c
   $ hg ci -m changeca -u user3 -d 12:00 a
   $ hg ci -m changecb -u user3 -d 12:15 b
   $ hg ci -Am addc -u user3 -d 12:30
   adding c
   $ mkdir -p d/e
   $ echo abc > d/e/f1.txt
   $ hg ci -Am "add d/e/f1.txt" -u user1 -d 12:45 d/e/f1.txt
   $ mkdir -p d/g
   $ echo def > d/g/f2.txt
   $ hg ci -Am "add d/g/f2.txt" -u user1 -d 13:00 d/g/f2.txt
 
 
 churn separate directories
 
   $ cd d
   $ hg churn e
   user1      1 ***************************************************************
 
 churn all
 
   $ hg churn
   user3      3 ***************************************************************
   user1      3 ***************************************************************
   user2      2 ******************************************
 
 churn excluding one dir
 
   $ hg churn -X e
   user3      3 ***************************************************************
   user2      2 ******************************************
   user1      2 ******************************************
 
 churn up to rev 2
 
   $ hg churn -r :2
   user2      2 ***************************************************************
   user1      1 ********************************
   $ cd ..
 
 churn with aliases
 
   $ cat > ../aliases <<EOF
   > user1 alias1
   > user3 alias3
   > not-an-alias
   > EOF
 
 churn with .hgchurn
 
   $ mv ../aliases .hgchurn
   $ hg churn
   skipping malformed alias: not-an-alias
   alias3      3 **************************************************************
   alias1      3 **************************************************************
   user2       2 *****************************************
   $ rm .hgchurn
 
 churn with column specifier
 
   $ COLUMNS=40 hg churn
   user3      3 ***********************
   user1      3 ***********************
   user2      2 ***************
 
 churn by hour
 
   $ hg churn -f '%H' -s
   06      1 *****************
   09      2 *********************************
   12      4 ******************************************************************
   13      1 *****************
 
 
 churn with separated added/removed lines
 
   $ hg rm d/g/f2.txt
   $ hg ci -Am "removed d/g/f2.txt" -u user1 -d 14:00 d/g/f2.txt
   $ hg churn --diffstat
   user1           +3/-1 +++++++++++++++++++++++++++++++++++++++++--------------
   user3           +3/-0 +++++++++++++++++++++++++++++++++++++++++
   user2           +2/-0 +++++++++++++++++++++++++++
 
 churn --diffstat with color
 
   $ hg --config extensions.color= churn --config color.mode=ansi \
   >     --diffstat --color=always
   user1           +3/-1 \x1b[0;32m+++++++++++++++++++++++++++++++++++++++++\x1b[0m\x1b[0;31m--------------\x1b[0m (esc)
   user3           +3/-0 \x1b[0;32m+++++++++++++++++++++++++++++++++++++++++\x1b[0m (esc)
   user2           +2/-0 \x1b[0;32m+++++++++++++++++++++++++++\x1b[0m (esc)
 
 
 changeset number churn
 
   $ hg churn -c
   user1      4 ***************************************************************
   user3      3 ***********************************************
   user2      2 ********************************
 
   $ echo 'with space = no-space' >> ../aliases
   $ echo a >> a
   $ hg commit -m a -u 'with space' -d 15:00
 
 churn with space in alias
 
   $ hg churn --aliases ../aliases -r tip
   no-space      1 ************************************************************
 
   $ cd ..
 
 
 Issue833: ZeroDivisionError
 
   $ hg init issue-833
   $ cd issue-833
   $ touch foo
   $ hg ci -Am foo
   adding foo
 
 this was failing with a ZeroDivisionError
 
   $ hg churn
   test      0 
   $ cd ..
+
+Ignore trailing or leading spaces in emails
+
+  $ cd repo
+  $ touch bar
+  $ hg ci -Am'bar' -u 'user4 <[e-mail]>'
+  adding bar
+  $ touch foo
+  $ hg ci -Am'foo' -u 'user4 < [e-mail] >'
+  adding foo
+  $ hg log -l2 --template '[{author|email}]\n'
+  [ [e-mail] ]
+  [[e-mail]]
+  $ hg churn -c
+  user1            4 *********************************************************
+  user3            3 *******************************************
+  [e-mail]      2 *****************************
+  user2            2 *****************************
+  with space       1 **************