churn: count lines that look like diff headers but are not

Previously, churn cannot count added lines that start with "++ " or removed
lines that start with "-- ".

Differential Revision: https://phab.mercurial-scm.org/D9929

hgext/churn.py

@@ -1,259 +1,264
 # 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, division
 
 import datetime
 import os
 import time
 
 from mercurial.i18n import _
 from mercurial.pycompat import open
 from mercurial import (
     cmdutil,
     encoding,
     logcmdutil,
     patch,
     pycompat,
     registrar,
     scmutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # 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 = b'ships-with-hg-core'
 
 
 def changedlines(ui, repo, ctx1, ctx2, fmatch):
     added, removed = 0, 0
     diff = b''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
+    inhunk = False
     for l in diff.split(b'\n'):
-        if l.startswith(b"+") and not l.startswith(b"+++ "):
+        if inhunk and l.startswith(b"+"):
             added += 1
-        elif l.startswith(b"-") and not l.startswith(b"--- "):
+        elif inhunk and l.startswith(b"-"):
             removed += 1
+        elif l.startswith(b"@"):
+            inhunk = True
+        elif l.startswith(b"d"):
+            inhunk = False
     return (added, removed)
 
 
 def countrate(ui, repo, amap, *pats, **opts):
     """Calculate stats"""
     opts = pycompat.byteskwargs(opts)
     if opts.get(b'dateformat'):
 
         def getkey(ctx):
             t, tz = ctx.date()
             date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
             return encoding.strtolocal(
                 date.strftime(encoding.strfromlocal(opts[b'dateformat']))
             )
 
     else:
         tmpl = opts.get(b'oldtemplate') or opts.get(b'template')
         tmpl = logcmdutil.maketemplater(ui, repo, tmpl)
 
         def getkey(ctx):
             ui.pushbuffer()
             tmpl.show(ctx)
             return ui.popbuffer()
 
     progress = ui.makeprogress(
         _(b'analyzing'), unit=_(b'revisions'), total=len(repo)
     )
     rate = {}
 
     def prep(ctx, fmatch):
         rev = ctx.rev()
         key = getkey(ctx).strip()
         key = amap.get(key, key)  # alias remap
         if opts.get(b'changesets'):
             rate[key] = (rate.get(key, (0,))[0] + 1, 0)
         else:
             parents = ctx.parents()
             if len(parents) > 1:
                 ui.note(_(b'revision %d is a merge, ignoring...\n') % (rev,))
                 return
 
             ctx1 = parents[0]
             lines = changedlines(ui, repo, ctx1, ctx, fmatch)
             rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
 
         progress.increment()
 
     wopts = logcmdutil.walkopts(
         pats=pats,
         opts=opts,
         revspec=opts[b'rev'],
         date=opts[b'date'],
         include_pats=opts[b'include'],
         exclude_pats=opts[b'exclude'],
     )
     revs, makefilematcher = logcmdutil.makewalker(repo, wopts)
     for ctx in scmutil.walkchangerevs(repo, revs, makefilematcher, prep):
         continue
 
     progress.complete()
 
     return rate
 
 
 @command(
     b'churn',
     [
         (
             b'r',
             b'rev',
             [],
             _(b'count rate for the specified revision or revset'),
             _(b'REV'),
         ),
         (
             b'd',
             b'date',
             b'',
             _(b'count rate for revisions matching date spec'),
             _(b'DATE'),
         ),
         (
             b't',
             b'oldtemplate',
             b'',
             _(b'template to group changesets (DEPRECATED)'),
             _(b'TEMPLATE'),
         ),
         (
             b'T',
             b'template',
             b'{author|email}',
             _(b'template to group changesets'),
             _(b'TEMPLATE'),
         ),
         (
             b'f',
             b'dateformat',
             b'',
             _(b'strftime-compatible format for grouping by date'),
             _(b'FORMAT'),
         ),
         (b'c', b'changesets', False, _(b'count rate by number of changesets')),
         (b's', b'sort', False, _(b'sort by key (default: sort by count)')),
         (b'', b'diffstat', False, _(b'display added/removed lines separately')),
         (b'', b'aliases', b'', _(b'file with email aliases'), _(b'FILE')),
     ]
     + cmdutil.walkopts,
     _(b"hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
     helpcategory=command.CATEGORY_MAINTENANCE,
     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
 
       # display count of lines changed in a time range
       hg churn -d "2020-04 to 2020-09"
 
     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 + b" " * (l - encoding.colwidth(s))
 
     amap = {}
     aliases = opts.get('aliases')
     if not aliases and os.path.exists(repo.wjoin(b'.hgchurn')):
         aliases = repo.wjoin(b'.hgchurn')
     if aliases:
         for l in open(aliases, b"rb"):
             try:
                 alias, actual = l.rsplit(b'=' in l and b'=' or None, 1)
                 amap[alias.strip()] = actual.strip()
             except ValueError:
                 l = l.strip()
                 if l:
                     ui.warn(_(b"skipping malformed alias: %s\n") % l)
                 continue
 
     rate = list(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(b"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 b"%s %15s %s%s\n" % (
                 pad(name, maxname),
                 b'+%d/-%d' % (added, removed),
                 ui.label(b'+' * charnum(added), b'diffstat.inserted'),
                 ui.label(b'-' * charnum(removed), b'diffstat.deleted'),
             )
 
     else:
         width -= 6
 
         def format(name, count):
             return b"%s %6d %s\n" % (
                 pad(name, maxname),
                 sum(count),
                 b'*' * charnum(sum(count)),
             )
 
     def charnum(count):
         return int(count * width // maxcount)
 
     for name, count in rate:
         ui.write(format(name, count))

tests/test-churn.t

@@ -1,197 +1,216
   $ 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
   user1      3 ***************************************************************
   user3      3 ***************************************************************
   user2      2 ******************************************
 
 churn excluding one dir
 
   $ hg churn -X e
   user3      3 ***************************************************************
   user1      2 ******************************************
   user2      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
   alias1      3 **************************************************************
   alias3      3 **************************************************************
   user2       2 *****************************************
   $ rm .hgchurn
 
 churn with column specifier
 
   $ COLUMNS=40 hg churn
   user1      3 ***********************
   user3      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 ******************************************
   user2            2 ****************************
   [e-mail]      2 ****************************
   with space       1 **************
 
 Test multibyte sequences in names
 
   $ echo bar >> bar
   $ hg --encoding utf-8 ci -m'changed bar' -u 'El Niño <[e-mail]>'
   $ hg --encoding utf-8 churn -ct '{author|person}'
   user1           4 **********************************************************
   user3           3 *******************************************
   user2           2 *****************************
   user4           2 *****************************
   El Ni\xc3\xb1o         1 ************** (esc)
   with space      1 **************
 
 Test --template argument, with backwards compatibility
 
   $ hg churn -t '{author|user}'
   user1      4 ***************************************************************
   user3      3 ***********************************************
   user2      2 *******************************
   nino       1 ***************
   with       1 ***************
              0 
   user4      0 
   $ hg churn -T '{author|user}'
   user1      4 ***************************************************************
   user3      3 ***********************************************
   user2      2 *******************************
   nino       1 ***************
   with       1 ***************
              0 
   user4      0 
   $ hg churn -t 'alltogether'
   alltogether     11 *********************************************************
   $ hg churn -T 'alltogether'
   alltogether     11 *********************************************************
 
   $ cd ..
+
+count lines that look like headings but are not
+
+  $ hg init not-headers
+  $ cd not-headers
+  $ cat > a <<EOF
+  > diff
+  > @@ -195,3 +195,21 @@
+  > -- a/tests/test-churn.t
+  > ++ b/tests/test-churn.t
+  > EOF
+  $ hg ci -Am adda -u user1
+  adding a
+  $ hg churn --diffstat
+  user1           +4/-0 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
+  $ hg rm a
+  $ hg ci -Am removea -u user1
+  $ hg churn --diffstat
+  user1           +4/-4 +++++++++++++++++++++++++++---------------------------