churn: do not crash on malformed lines in alias file

hgext/churn.py

@@ -1,192 +1,196 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
         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"):
-            if not l.strip():
+            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
-            alias, actual = l.split('=' in l and '=' or None, 1)
-            amap[alias.strip()] = actual.strip()
 
     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 = util.termwidth()
     ui.debug("assuming %i character terminal\n" % ttywidth)
     width = ttywidth - maxname - 2 - 2 - 2
 
     if opts.get('diffstat'):
         width -= 15
         def format(name, (added, removed)):
             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]")),
 }

tests/test-churn

@@ -1,80 +1,81 b''
 #!/bin/sh
 
 echo "[extensions]" >> $HGRCPATH
 echo "churn=" >> $HGRCPATH
 
 echo % create test repository
 hg init repo
 cd repo
 echo a > a
 hg ci -Am adda -u user1 -d 6:00
 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
 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
 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
 
 echo % churn separate directories
 cd d
 hg churn e
 echo % churn all
 hg churn
 echo % churn excluding one dir
 hg churn -X e
 echo % churn up to rev 2
 hg churn -r :2
 cd ..
 echo % churn with aliases
 cat > ../aliases <<EOF
 user1 alias1
 
 user3 alias3
+not-an-alias
 EOF
 hg churn --aliases ../aliases
 echo % churn with .hgchurn
 mv ../aliases .hgchurn
 hg churn
 rm .hgchurn
 echo % churn with column specifier
 COLUMNS=40 hg churn
 echo % churn by hour
 hg churn -f '%H' -s
 
 echo % 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
 echo % churn --diffstat with color
 hg --config extensions.color= churn --config color.mode=ansi \
     --diffstat --color=always
 
 echo % changeset number churn
 hg churn -c
 
 echo 'with space = no-space' >> ../aliases
 echo a >> a
 hg commit -m a -u 'with space' -d 15:00
 echo % churn with space in alias
 hg churn --aliases ../aliases -r tip
 
 cd ..
 
 # issue 833: ZeroDivisionError
 hg init issue-833
 cd issue-833
 touch foo
 hg ci -Am foo
 # this was failing with a ZeroDivisionError
 hg churn
 cd ..

tests/test-churn.out

@@ -1,50 +1,52 b''
 % create test repository
 adding a
 adding b
 adding c
 % churn separate directories
 user1      1 ***************************************************************
 % churn all
 user3      3 ***************************************************************
 user1      3 ***************************************************************
 user2      2 ******************************************
 % churn excluding one dir
 user3      3 ***************************************************************
 user2      2 ******************************************
 user1      2 ******************************************
 % churn up to rev 2
 user2      2 ***************************************************************
 user1      1 ********************************
 % churn with aliases
+skipping malformed alias: not-an-alias
 alias3      3 **************************************************************
 alias1      3 **************************************************************
 user2       2 *****************************************
 % churn with .hgchurn
+skipping malformed alias: not-an-alias
 alias3      3 **************************************************************
 alias1      3 **************************************************************
 user2       2 *****************************************
 % churn with column specifier
 user3      3 ***********************
 user1      3 ***********************
 user2      2 ***************
 % churn by hour
 06      1 *****************
 09      2 *********************************
 12      4 ******************************************************************
 13      1 *****************
 % churn with separated added/removed lines
 user1           +3/-1 +++++++++++++++++++++++++++++++++++++++++--------------
 user3           +3/-0 +++++++++++++++++++++++++++++++++++++++++
 user2           +2/-0 +++++++++++++++++++++++++++
 % churn --diffstat with color
 user1           +3/-1 +++++++++++++++++++++++++++++++++++++++++--------------
 user3           +3/-0 +++++++++++++++++++++++++++++++++++++++++
 user2           +2/-0 +++++++++++++++++++++++++++
 % changeset number churn
 user1      4 ***************************************************************
 user3      3 ***********************************************
 user2      2 ********************************
 % churn with space in alias
 no-space      1 ************************************************************
 adding foo
 test      0