view hgext/interhg.py @ 15462:2b1ec74c961f stable

mdiff/patch: fix bad hunk handling for unified diffs with zero context

Prior to this patch "hg diff -U0", i.e., zero lines of context, would
output hunk headers with a start line one greater than what GNU patch
and git output. Guido van Rossum documents the unified diff format[1]
as having a start line value "one lower than one would expect" for
zero length hunks.

Comparing the behaviour of the three systems prior to this patch in
transforming

  c1
  c3

to

  c1
  c2
  c3

- GNU "diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "git diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "hg diff -U0" reports the hunk as "@@ -2,0 +2,1 @@"

After this patch, "hg diff -U0" reports "@@ -1,0 +2,1 @@".

Since "hg export --config diff.unified=0" outputs zero-context unified
diffs, "hg import" has also been updated to account for start lines
one less than expected for zero length hunk ranges.

[1]: http://www.artima.com/weblogs/viewpost.jsp?thread=164293

# interhg.py - interhg
#
# Copyright 2007 OHASHI Hideya <[e-mail]>
#
# Contributor(s):
#   Edward Lee <[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.

'''expand expressions into changelog and summaries

This extension allows the use of a special syntax in summaries, which
will be automatically expanded into links or any other arbitrary
expression, much like InterWiki does.

A few example patterns (link to bug tracking, etc.) that may be used
in your hgrc::

  [interhg]
  issues = s!issue(\\d+)!<a href="http://bts/issue\\1">issue\\1</a>!
  bugzilla = s!((?:bug|b=|(?=#?\\d{4,}))(?:\\s*#?)(\\d+))!<a..=\\2">\\1</a>!i
  boldify = s!(^|\\s)#(\\d+)\\b! <b>#\\2</b>!
'''

import re
from mercurial.hgweb import hgweb_mod
from mercurial import templatefilters, extensions
from mercurial.i18n import _

interhg_table = []

def uisetup(ui):
    orig_escape = templatefilters.filters["escape"]

    def interhg_escape(x):
        escstr = orig_escape(x)
        for regexp, format in interhg_table:
            escstr = regexp.sub(format, escstr)
        return escstr

    templatefilters.filters["escape"] = interhg_escape

def interhg_refresh(orig, self, *args, **kwargs):
    interhg_table[:] = []
    for key, pattern in self.repo.ui.configitems('interhg'):
        # grab the delimiter from the character after the "s"
        unesc = pattern[1]
        delim = re.escape(unesc)

        # identify portions of the pattern, taking care to avoid escaped
        # delimiters. the replace format and flags are optional, but delimiters
        # are required.
        match = re.match(r'^s%s(.+)(?:(?<=\\\\)|(?<!\\))%s(.*)%s([ilmsux])*$'
                         % (delim, delim, delim), pattern)
        if not match:
            self.repo.ui.warn(_("interhg: invalid pattern for %s: %s\n")
                              % (key, pattern))
            continue

        # we need to unescape the delimiter for regexp and format
        delim_re = re.compile(r'(?<!\\)\\%s' % delim)
        regexp = delim_re.sub(unesc, match.group(1))
        format = delim_re.sub(unesc, match.group(2))

        # the pattern allows for 6 regexp flags, so set them if necessary
        flagin = match.group(3)
        flags = 0
        if flagin:
            for flag in flagin.upper():
                flags |= re.__dict__[flag]

        try:
            regexp = re.compile(regexp, flags)
            interhg_table.append((regexp, format))
        except re.error:
            self.repo.ui.warn(_("interhg: invalid regexp for %s: %s\n")
                              % (key, regexp))
    return orig(self, *args, **kwargs)

extensions.wrapfunction(hgweb_mod.hgweb, 'refresh', interhg_refresh)