i18n: fix "% inside _()" problems

Before this patch, "contrib/check-code.py" can't detect these
problems, because the regexp pattern to detect "% inside _()" doesn't
suppose the case that format string consists of multiple string
components concatenated implicitly or explicitly,

This patch does below for that regexp pattern to detect "% inside _()"
problems in such case.

  - put "+" into separator part ("[ \t\n]") for explicit concatenation
    ("...." + "...." style)

  - enclose "component and separator" part by "(?:....)+" for
    concatenation itself ("...." "...." or "...." + "....")

contrib/check-code.py

@@ -1,553 +1,553 b''
 #!/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.
 
 """style and portability checker for Mercurial
 
 when a rule triggers wrong, do one of the following (prefer one from top):
  * do the work-around the rule suggests
  * doublecheck that it is a false match
  * improve the rule pattern
  * add an ignore pattern to the rule (3rd arg) which matches your good line
    (you can append a short comment and match this, like: #re-raises, # no-py24)
  * change the pattern to a warning and list the exception in test-check-code-hg
  * ONLY use no--check-code for skipping entire files from external sources
 """
 
 import re, glob, os, sys
 import keyword
 import optparse
 try:
     import re2
 except ImportError:
     re2 = None
 
 def compilere(pat, multiline=False):
     if multiline:
         pat = '(?m)' + pat
     if re2:
         try:
             return re2.compile(pat)
         except re2.error:
             pass
     return re.compile(pat)
 
 def repquote(m):
     fromc = '.:'
     tochr = 'pq'
     def encodechr(i):
         if i > 255:
             return 'u'
         c = chr(i)
         if c in ' \n':
             return c
         if c.isalpha():
             return 'x'
         if c.isdigit():
             return 'n'
         try:
             return tochr[fromc.find(c)]
         except (ValueError, IndexError):
             return 'o'
     t = m.group('text')
     tt = ''.join(encodechr(i) for i in xrange(256))
     t = t.translate(tt)
     return m.group('quote') + t + m.group('quote')
 
 def reppython(m):
     comment = m.group('comment')
     if comment:
         l = len(comment.rstrip())
         return "#" * l + comment[l:]
     return repquote(m)
 
 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\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
     (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
     (r'(?<!hg )grep.*-a', "don't use 'grep -a', use in-line python"),
     (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
     (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
     (r'echo -n', "don't use 'echo -n', use printf"),
     (r'(^| )wc[^|]*$\n(?!.*\(re\))', "filter wc output"),
     (r'head -c', "don't use 'head -c', use 'dd'"),
     (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
     (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
     (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
     (r'printf.*[^\\]\\([1-9]|0\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'[^\n]\Z', "no trailing newline"),
     (r'export.*=', "don't export and assign at once"),
     (r'^source\b', "don't use 'source', use '.'"),
     (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
     (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
     (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
     (r'^stop\(\)', "don't use 'stop' as a shell function name"),
     (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
     (r'^alias\b.*=', "don't use alias, use a function"),
     (r'if\s*!', "don't use '!' to negate exit status"),
     (r'/dev/u?random', "don't use entropy, use /dev/zero"),
     (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
     (r'^( *)\t', "don't use tabs to indent"),
     (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
      "put a backslash-escaped newline after sed 'i' command"),
   ],
   # warnings
   [
     (r'^function', "don't use 'function', use old style"),
     (r'^diff.*-\w*N', "don't use 'diff -N'"),
     (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
     (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
     (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
   ]
 ]
 
 testfilters = [
     (r"( *)(#([^\n]*\S)?)", repcomment),
     (r"<<(\S+)((.|\n)*?\n\1)", rephere),
 ]
 
 winglobmsg = "use (glob) to match Windows paths too"
 uprefix = r"^  \$ "
 utestpats = [
   [
     (r'^(\S.*||  [$>] .*)[ \t]\n', "trailing whitespace on non-output"),
     (uprefix + r'.*\|\s*sed[^|>\n]*\n',
      "use regex test output patterns instead of sed"),
     (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
     (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
     (uprefix + r'.*\|\| echo.*(fail|error)',
      "explicit exit code checks unnecessary"),
     (uprefix + r'set -e', "don't use set -e"),
     (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
     (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
     (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
      winglobmsg),
     (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
      '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
     (r'^  reverting .*/.*[^)]$', winglobmsg),
     (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
     (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
     (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
     (r'^  moving \S+/.*[^)]$', winglobmsg),
     (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
     (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
   ],
   # warnings
   [
     (r'^  [^*?/\n]* \(glob\)$',
      "glob match with no glob character (?*/)"),
   ]
 ]
 
 for i in [0, 1]:
     for p, m in testpats[i]:
         if p.startswith(r'^'):
             p = r"^  [$>] (%s)" % p[1:]
         else:
             p = r"^  [$>] .*(%s)" % p
         utestpats[i].append((p, m))
 
 utestfilters = [
     (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
     (r"( *)(#([^\n]*\S)?)", repcomment),
 ]
 
 pypats = [
   [
     (r'^\s*def\s*\w+\s*\(.*,\s*\(',
      "tuple parameter unpacking not available in Python 3+"),
     (r'lambda\s*\(.*,.*\)',
      "tuple parameter unpacking not available in Python 3+"),
     (r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',
      '2to3 can\'t always rewrite "import qux, foo.bar", '
      'use "import foo.bar" on its own line instead.'),
     (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
     (r'\breduce\s*\(.*', "reduce is not available in Python 3+"),
     (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
     (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
     (r'^\s*\t', "don't use tabs"),
     (r'\S;\s*\n', "semicolon"),
-    (r'[^_]_\("[^"]+"[ \t\n]*%', "don't use % inside _()"),
-    (r"[^_]_\('[^']+'[ \t\n]*%", "don't use % inside _()"),
+    (r'[^_]_\((?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
+    (r"[^_]_\((?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
     (r'(\w|\)),\w', "missing whitespace after ,"),
     (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
     (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
     (r'(\s+)try:\n((?:\n|\1\s.*\n)+?)\1except.*?:\n'
      r'((?:\n|\1\s.*\n)+?)\1finally:', 'no try/except/finally in Python 2.4'),
     (r'(?<!def)(\s+|^|\()next\(.+\)',
      'no next(foo) in Python 2.4 and 2.5, use foo.next() instead'),
     (r'(\s+)try:\n((?:\n|\1\s.*\n)*?)\1\s*yield\b.*?'
      r'((?:\n|\1\s.*\n)+?)\1finally:',
      'no yield inside try/finally in Python 2.4'),
     (r'.{81}', "line too long"),
     (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),
     (r'[^\n]\Z', "no trailing newline"),
     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
 #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
 #     "don't use underbars in identifiers"),
     (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
      "don't use camelcase in identifiers"),
     (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
      "linebreak after :"),
     (r'class\s[^( \n]+:', "old-style class, use class foo(object)"),
     (r'class\s[^( \n]+\(\):',
      "class foo() not available in Python 2.4, use class foo(object)"),
     (r'\b(%s)\(' % '|'.join(keyword.kwlist),
      "Python keyword is not 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'\.isdisjoint\(', "set.isdisjoint not available in Python 2.4"),
     (r'^\s*except.* as .*:', "except as not available in Python 2.4"),
     (r'^\s*os\.path\.relpath', "relpath not available in Python 2.4"),
     (r'(?<!def)\s+(any|all|format)\(',
      "any/all/format not available in Python 2.4", 'no-py24'),
     (r'(?<!def)\s+(callable)\(',
      "callable not available in Python 3, use getattr(f, '__call__', None)"),
     (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
     (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
      "gratuitous whitespace after Python keyword"),
     (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "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'\([^()]*( =[^=]|[^<>!=]= )',
      "no whitespace around = for named parameters"),
     (r'raise Exception', "don't raise generic exceptions"),
     (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
      "don't use old-style two-argument raise, use Exception(message)"),
     (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
     (r' [=!]=\s+(True|False|None)',
      "comparison with singleton, use 'is' or 'is not' instead"),
     (r'^\s*(while|if) [01]:',
      "use True/False for constant Boolean expression"),
     (r'(?:(?<!def)\s+|\()hasattr',
      'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
     (r'opener\([^)]*\).read\(',
      "use opener.read() instead"),
     (r'BaseException', 'not in Python 2.4, use Exception'),
     (r'os\.path\.relpath', 'os.path.relpath is not in Python 2.5'),
     (r'opener\([^)]*\).write\(',
      "use opener.write() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.read\(',
      "use util.readfile() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.write\(',
      "use util.writefile() instead"),
     (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'[\s\(](open|file)\([^)]*\)\.',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'(?i)descendent', "the proper spelling is descendAnt"),
     (r'\.debug\(\_', "don't mark debug messages for translation"),
     (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
     (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
     (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
     (r'ui\.(status|progress|write|note|warn)\([\'\"]x',
      "missing _() in ui message (use () to hide false-positives)"),
     (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
   ],
   # warnings
   [
     (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
   ]
 ]
 
 pyfilters = [
     (r"""(?msx)(?P<comment>\#.*?$)|
          ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
           (?P<text>(([^\\]|\\.)*?))
           (?P=quote))""", reppython),
 ]
 
 txtfilters = []
 
 txtpats = [
   [
     ('\s$', 'trailing whitespace'),
   ],
   []
 ]
 
 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[ \t]+|^[ \t]+)\n', "trailing whitespace"),
     (r'.{81}', "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'[)][{]', "space between ) and {"),
     (r'\w+\* \w+', "use int *foo, not int* foo"),
     (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
     (r'\w+ (\+\+|--)', "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"),
     (r'^\s*#import\b', "use only #include in standard C code"),
   ],
   # warnings
   []
 ]
 
 cfilters = [
     (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
     (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
     (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
     (r'(\()([^)]+\))', repcallspaces),
 ]
 
 inutilpats = [
   [
     (r'\bui\.', "don't use ui in util"),
   ],
   # warnings
   []
 ]
 
 inrevlogpats = [
   [
     (r'\brepo\.', "don't use repo in revlog"),
   ],
   # warnings
   []
 ]
 
 checks = [
     ('python', r'.*\.(py|cgi)$', pyfilters, pypats),
     ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats),
     ('c', r'.*\.[ch]$', cfilters, cpats),
     ('unified test', r'.*\.t$', utestfilters, utestpats),
     ('layering violation repo in revlog', r'mercurial/revlog\.py', pyfilters,
      inrevlogpats),
     ('layering violation ui in util', r'mercurial/util\.py', pyfilters,
      inutilpats),
     ('txt', r'.*\.txt$', txtfilters, txtpats),
 ]
 
 def _preparepats():
     for c in checks:
         failandwarn = c[-1]
         for pats in failandwarn:
             for i, pseq in enumerate(pats):
                 # fix-up regexes for multi-line searches
                 p = pseq[0]
                 # \s doesn't match \n
                 p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                 # [^...] doesn't match newline
                 p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
 
                 pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
         filters = c[2]
         for i, flt in enumerate(filters):
             filters[i] = re.compile(flt[0]), flt[1]
 _preparepats()
 
 class norepeatlogger(object):
     def __init__(self):
         self._lastseen = None
 
     def log(self, fname, lineno, line, msg, blame):
         """print error related a to given line of a given file.
 
         The faulty line will also be printed but only once in the case
         of multiple errors.
 
         :fname: filename
         :lineno: line number
         :line: actual content of the line
         :msg: error message
         """
         msgid = fname, lineno, line
         if msgid != self._lastseen:
             if blame:
                 print "%s:%d (%s):" % (fname, lineno, blame)
             else:
                 print "%s:%d:" % (fname, lineno)
             print " > %s" % line
             self._lastseen = msgid
         print " " + msg
 
 _defaultlogger = norepeatlogger()
 
 def getblame(f):
     lines = []
     for l in os.popen('hg annotate -un %s' % f):
         start, line = l.split(':', 1)
         user, rev = start.split()
         lines.append((line[1:-1], user, rev))
     return lines
 
 def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
               blame=False, debug=False, lineno=True):
     """checks style and portability of a given file
 
     :f: filepath
     :logfunc: function used to report error
               logfunc(filename, linenumber, linecontent, errormessage)
     :maxerr: number of error to display before aborting.
              Set to false (default) to report all errors
 
     return True if no error is found, False otherwise.
     """
     blamecache = None
     result = True
     for name, match, filters, pats in checks:
         if debug:
             print name, f
         fc = 0
         if not re.match(match, f):
             if debug:
                 print "Skipping %s for %s it doesn't match %s" % (
                        name, match, f)
             continue
         try:
             fp = open(f)
         except IOError, e:
             print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])
             continue
         pre = post = fp.read()
         fp.close()
         if "no-" "check-code" in pre:
             print "Skipping %s it has no-" "check-code" % f
             return "Skip" # skip checking this file
         for p, r in filters:
             post = re.sub(p, r, post)
         nerrs = len(pats[0]) # nerr elements are errors
         if warnings:
             pats = pats[0] + pats[1]
         else:
             pats = pats[0]
         # print post # uncomment to show filtered version
 
         if debug:
             print "Checking %s for %s" % (name, f)
 
         prelines = None
         errors = []
         for i, pat in enumerate(pats):
             if len(pat) == 3:
                 p, msg, ignore = pat
             else:
                 p, msg = pat
                 ignore = None
             if i >= nerrs:
                 msg = "warning: " + msg
 
             pos = 0
             n = 0
             for m in p.finditer(post):
                 if prelines is None:
                     prelines = pre.splitlines()
                     postlines = post.splitlines(True)
 
                 start = m.start()
                 while n < len(postlines):
                     step = len(postlines[n])
                     if pos + step > start:
                         break
                     pos += step
                     n += 1
                 l = prelines[n]
 
                 if ignore and re.search(ignore, l, re.MULTILINE):
                     if debug:
                         print "Skipping %s for %s:%s (ignore pattern)" % (
                             name, f, n)
                     continue
                 bd = ""
                 if blame:
                     bd = 'working directory'
                     if not blamecache:
                         blamecache = getblame(f)
                     if n < len(blamecache):
                         bl, bu, br = blamecache[n]
                         if bl == l:
                             bd = '%s@%s' % (bu, br)
 
                 errors.append((f, lineno and n + 1, l, msg, bd))
                 result = False
 
         errors.sort()
         for e in errors:
             logfunc(*e)
             fc += 1
             if maxerr and fc >= maxerr:
                 print " (too many errors, giving up)"
                 break
 
     return result
 
 if __name__ == "__main__":
     parser = optparse.OptionParser("%prog [options] [files]")
     parser.add_option("-w", "--warnings", action="store_true",
                       help="include warning-level checks")
     parser.add_option("-p", "--per-file", type="int",
                       help="max warnings per file")
     parser.add_option("-b", "--blame", action="store_true",
                       help="use annotate to generate blame info")
     parser.add_option("", "--debug", action="store_true",
                       help="show debug information")
     parser.add_option("", "--nolineno", action="store_false",
                       dest='lineno', help="don't show line numbers")
 
     parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                         lineno=True)
     (options, args) = parser.parse_args()
 
     if len(args) == 0:
         check = glob.glob("*")
     else:
         check = args
 
     ret = 0
     for f in check:
         if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                          blame=options.blame, debug=options.debug,
                          lineno=options.lineno):
             ret = 1
     sys.exit(ret)

hgext/eol.py

@@ -1,350 +1,350 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 found in the root of the working copy. The
 ``.hgeol`` file use the same syntax as all other Mercurial
 configuration files. It uses two sections, ``[patterns]`` and
 ``[repository]``.
 
 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 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 read from both the
 normal Mercurial configuration files and the ``.hgeol`` file, with the
 latter overriding the former. You can use that section to control the
 overall behavior. There are three 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.
 
 - ``eol.fix-trailing-newline`` (default False) can be set to True to
   ensure that converted files end with a EOL character (either ``\\n``
   or ``\\r\\n`` as per the configured patterns).
 
 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.checkheadshook``. 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. ``eol.checkheadshook`` only checks heads, intermediate
 invalid revisions will be pushed. To forbid them completely, use the
 ``eol.checkallhook`` hook. These hooks are best used as
 ``pretxnchangegroup`` hooks.
 
 See :hg:`help patterns` for more information about the glob patterns
 used.
 """
 
 from mercurial.i18n import _
 from mercurial import util, config, extensions, match, error
 import re, os
 
 testedwith = 'internal'
 
 # 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 Macintosh 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
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     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
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     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
 }
 
 class eolfile(object):
     def __init__(self, ui, root, data):
         self._decode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
         self._encode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
 
         self.cfg = config.config()
         # Our files should not be touched. The pattern must be
         # inserted first override a '** = native' pattern.
         self.cfg.set('patterns', '.hg*', 'BIN')
         # We can then parse the user's patterns.
         self.cfg.parse('.hgeol', data)
 
         isrepolf = self.cfg.get('repository', 'native') != 'CRLF'
         self._encode['NATIVE'] = isrepolf and 'to-lf' or 'to-crlf'
         iswdlf = ui.config('eol', 'native', os.linesep) in ('LF', '\n')
         self._decode['NATIVE'] = iswdlf and 'to-lf' or 'to-crlf'
 
         include = []
         exclude = []
         for pattern, style in self.cfg.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.
         self.match = match.match(root, '', [], include, exclude)
 
     def copytoui(self, ui):
         for pattern, style in self.cfg.items('patterns'):
             key = style.upper()
             try:
                 ui.setconfig('decode', pattern, self._decode[key])
                 ui.setconfig('encode', pattern, self._encode[key])
             except KeyError:
                 ui.warn(_("ignoring unknown EOL style '%s' from %s\n")
                         % (style, self.cfg.source('patterns', pattern)))
         # eol.only-consistent can be specified in ~/.hgrc or .hgeol
         for k, v in self.cfg.items('eol'):
             ui.setconfig('eol', k, v)
 
     def checkrev(self, repo, ctx, files):
         failed = []
         for f in (files or ctx.files()):
             if f not in ctx:
                 continue
             for pattern, style in self.cfg.items('patterns'):
                 if not match.match(repo.root, '', [pattern])(f):
                     continue
                 target = self._encode[style.upper()]
                 data = ctx[f].data()
                 if (target == "to-lf" and "\r\n" in data
                     or target == "to-crlf" and singlelf.search(data)):
                     failed.append((str(ctx), target, f))
                 break
         return failed
 
 def parseeol(ui, repo, nodes):
     try:
         for node in nodes:
             try:
                 if node is None:
                     # Cannot use workingctx.data() since it would load
                     # and cache the filters before we configure them.
                     data = repo.wfile('.hgeol').read()
                 else:
                     data = repo[node]['.hgeol'].data()
                 return eolfile(ui, repo.root, data)
             except (IOError, LookupError):
                 pass
     except error.ParseError, inst:
         ui.warn(_("warning: ignoring .hgeol file due to parse error "
                   "at %s: %s\n") % (inst.args[1], inst.args[0]))
     return None
 
 def _checkhook(ui, repo, node, headsonly):
     # Get revisions to check and touched files at the same time
     files = set()
     revs = set()
     for rev in xrange(repo[node].rev(), len(repo)):
         revs.add(rev)
         if headsonly:
             ctx = repo[rev]
             files.update(ctx.files())
             for pctx in ctx.parents():
                 revs.discard(pctx.rev())
     failed = []
     for rev in revs:
         ctx = repo[rev]
         eol = parseeol(ui, repo, [ctx.node()])
         if eol:
             failed.extend(eol.checkrev(repo, ctx, files))
 
     if failed:
         eols = {'to-lf': 'CRLF', 'to-crlf': 'LF'}
         msgs = []
         for node, target, f in failed:
             msgs.append(_("  %s in %s should not have %s line endings") %
                         (f, node, eols[target]))
         raise util.Abort(_("end-of-line check failed:\n") + "\n".join(msgs))
 
 def checkallhook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, False)
 
 def checkheadshook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, True)
 
 # "checkheadshook" used to be called "hook"
 hook = checkheadshook
 
 def preupdate(ui, repo, hooktype, parent1, parent2):
     repo.loadeol([parent1])
     return False
 
 def uisetup(ui):
     ui.setconfig('hooks', 'preupdate.eol', preupdate)
 
 def extsetup(ui):
     try:
         extensions.find('win32text')
         ui.warn(_("the eol extension is incompatible with the "
                   "win32text extension\n"))
     except KeyError:
         pass
 
 
 def reposetup(ui, repo):
     uisetup(repo.ui)
 
     if not repo.local():
         return
     for name, fn in filters.iteritems():
         repo.adddatafilter(name, fn)
 
     ui.setconfig('patch', 'eol', 'auto')
 
     class eolrepo(repo.__class__):
 
         def loadeol(self, nodes):
             eol = parseeol(self.ui, self, nodes)
             if eol is None:
                 return None
             eol.copytoui(self.ui)
             return eol.match
 
         def _hgcleardirstate(self):
             self._eolfile = self.loadeol([None, '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:
                 self.ui.debug("eol: detected change in .hgeol\n")
                 wlock = None
                 try:
                     wlock = self.wlock()
                     for f in self.dirstate:
                         if self.dirstate[f] == 'n':
                             # all normal files need to be looked at
                             # again since the new .hgeol file might no
                             # longer match a file it matched before
                             self.dirstate.normallookup(f)
                     # Create or touch the cache to update mtime
                     self.opener("eol.cache", "w").close()
                     wlock.release()
                 except error.LockUnavailable:
                     # If we cannot lock the repository and clear the
                     # dirstate, then a commit might not see all files
                     # as modified. But if we cannot lock the
                     # repository, then we can also not make a commit,
                     # so ignore the error.
                     pass
 
         def commitctx(self, ctx, error=False):
             for f in sorted(ctx.added() + ctx.modified()):
                 if not self._eolfile(f):
                     continue
                 try:
                     data = ctx[f].data()
                 except IOError:
                     continue
                 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))
+                                       "in %s\n") % f)
             return super(eolrepo, self).commitctx(ctx, error)
     repo.__class__ = eolrepo
     repo._hgcleardirstate()

mercurial/patch.py

@@ -1,1931 +1,1931 b''
 # patch.py - patch file parsing routines
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[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 cStringIO, email, os, errno, re, posixpath
 import tempfile, zlib, shutil
 # On python2.4 you have to import these by name or they fail to
 # load. This was not a problem on Python 2.7.
 import email.Generator
 import email.Parser
 
 from i18n import _
 from node import hex, short
 import base85, mdiff, scmutil, util, diffhelpers, copies, encoding, error
 
 gitre = re.compile('diff --git a/(.*) b/(.*)')
 
 class PatchError(Exception):
     pass
 
 
 # public functions
 
 def split(stream):
     '''return an iterator of individual patches from a stream'''
     def isheader(line, inheader):
         if inheader and line[0] in (' ', '\t'):
             # continuation
             return True
         if line[0] in (' ', '-', '+'):
             # diff line - don't check for header pattern in there
             return False
         l = line.split(': ', 1)
         return len(l) == 2 and ' ' not in l[0]
 
     def chunk(lines):
         return cStringIO.StringIO(''.join(lines))
 
     def hgsplit(stream, cur):
         inheader = True
 
         for line in stream:
             if not line.strip():
                 inheader = False
             if not inheader and line.startswith('# HG changeset patch'):
                 yield chunk(cur)
                 cur = []
                 inheader = True
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def mboxsplit(stream, cur):
         for line in stream:
             if line.startswith('From '):
                 for c in split(chunk(cur[1:])):
                     yield c
                 cur = []
 
             cur.append(line)
 
         if cur:
             for c in split(chunk(cur[1:])):
                 yield c
 
     def mimesplit(stream, cur):
         def msgfp(m):
             fp = cStringIO.StringIO()
             g = email.Generator.Generator(fp, mangle_from_=False)
             g.flatten(m)
             fp.seek(0)
             return fp
 
         for line in stream:
             cur.append(line)
         c = chunk(cur)
 
         m = email.Parser.Parser().parse(c)
         if not m.is_multipart():
             yield msgfp(m)
         else:
             ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
             for part in m.walk():
                 ct = part.get_content_type()
                 if ct not in ok_types:
                     continue
                 yield msgfp(part)
 
     def headersplit(stream, cur):
         inheader = False
 
         for line in stream:
             if not inheader and isheader(line, inheader):
                 yield chunk(cur)
                 cur = []
                 inheader = True
             if inheader and not isheader(line, inheader):
                 inheader = False
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def remainder(cur):
         yield chunk(cur)
 
     class fiter(object):
         def __init__(self, fp):
             self.fp = fp
 
         def __iter__(self):
             return self
 
         def next(self):
             l = self.fp.readline()
             if not l:
                 raise StopIteration
             return l
 
     inheader = False
     cur = []
 
     mimeheaders = ['content-type']
 
     if not util.safehasattr(stream, 'next'):
         # http responses, for example, have readline but not next
         stream = fiter(stream)
 
     for line in stream:
         cur.append(line)
         if line.startswith('# HG changeset patch'):
             return hgsplit(stream, cur)
         elif line.startswith('From '):
             return mboxsplit(stream, cur)
         elif isheader(line, inheader):
             inheader = True
             if line.split(':', 1)[0].lower() in mimeheaders:
                 # let email parser handle this
                 return mimesplit(stream, cur)
         elif line.startswith('--- ') and inheader:
             # No evil headers seen by diff start, split by hand
             return headersplit(stream, cur)
         # Not enough info, keep reading
 
     # if we are here, we have a very plain patch
     return remainder(cur)
 
 def extract(ui, fileobj):
     '''extract patch from data read from fileobj.
 
     patch can be a normal patch or contained in an email message.
 
     return tuple (filename, message, user, date, branch, node, p1, p2).
     Any item in the returned tuple can be None. If filename is None,
     fileobj did not contain a patch. Caller must unlink filename when done.'''
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(r'^(?:Index:[ \t]|diff[ \t]|RCS file: |'
                         r'retrieving revision [0-9]+(\.[0-9]+)*$|'
                         r'---[ \t].*?^\+\+\+[ \t]|'
                         r'\*\*\*[ \t].*?^---[ \t])', re.MULTILINE|re.DOTALL)
 
     fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
     tmpfp = os.fdopen(fd, 'w')
     try:
         msg = email.Parser.Parser().parse(fileobj)
 
         subject = msg['Subject']
         user = msg['From']
         if not subject and not user:
             # Not an email, restore parsed headers if any
             subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n'
 
         # should try to parse msg['Date']
         date = None
         nodeid = None
         branch = None
         parents = []
 
         if subject:
             if subject.startswith('[PATCH'):
                 pend = subject.find(']')
                 if pend >= 0:
                     subject = subject[pend + 1:].lstrip()
             subject = re.sub(r'\n[ \t]+', ' ', subject)
             ui.debug('Subject: %s\n' % subject)
         if user:
             ui.debug('From: %s\n' % user)
         diffs_seen = 0
         ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
         message = ''
         for part in msg.walk():
             content_type = part.get_content_type()
             ui.debug('Content-Type: %s\n' % content_type)
             if content_type not in ok_types:
                 continue
             payload = part.get_payload(decode=True)
             m = diffre.search(payload)
             if m:
                 hgpatch = False
                 hgpatchheader = False
                 ignoretext = False
 
                 ui.debug('found patch at byte %d\n' % m.start(0))
                 diffs_seen += 1
                 cfp = cStringIO.StringIO()
                 for line in payload[:m.start(0)].splitlines():
                     if line.startswith('# HG changeset patch') and not hgpatch:
                         ui.debug('patch generated by hg export\n')
                         hgpatch = True
                         hgpatchheader = True
                         # drop earlier commit message content
                         cfp.seek(0)
                         cfp.truncate()
                         subject = None
                     elif hgpatchheader:
                         if line.startswith('# User '):
                             user = line[7:]
                             ui.debug('From: %s\n' % user)
                         elif line.startswith("# Date "):
                             date = line[7:]
                         elif line.startswith("# Branch "):
                             branch = line[9:]
                         elif line.startswith("# Node ID "):
                             nodeid = line[10:]
                         elif line.startswith("# Parent "):
                             parents.append(line[9:].lstrip())
                         elif not line.startswith("# "):
                             hgpatchheader = False
                     elif line == '---':
                         ignoretext = True
                     if not hgpatchheader and not ignoretext:
                         cfp.write(line)
                         cfp.write('\n')
                 message = cfp.getvalue()
                 if tmpfp:
                     tmpfp.write(payload)
                     if not payload.endswith('\n'):
                         tmpfp.write('\n')
             elif not diffs_seen and message and content_type == 'text/plain':
                 message += '\n' + payload
     except: # re-raises
         tmpfp.close()
         os.unlink(tmpname)
         raise
 
     if subject and not message.startswith(subject):
         message = '%s\n%s' % (subject, message)
     tmpfp.close()
     if not diffs_seen:
         os.unlink(tmpname)
         return None, message, user, date, branch, None, None, None
     p1 = parents and parents.pop(0) or None
     p2 = parents and parents.pop(0) or None
     return tmpname, message, user, date, branch, nodeid, p1, p2
 
 class patchmeta(object):
     """Patched file metadata
 
     'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
     or COPY.  'path' is patched file path. 'oldpath' is set to the
     origin file when 'op' is either COPY or RENAME, None otherwise. If
     file mode is changed, 'mode' is a tuple (islink, isexec) where
     'islink' is True if the file is a symlink and 'isexec' is True if
     the file is executable. Otherwise, 'mode' is None.
     """
     def __init__(self, path):
         self.path = path
         self.oldpath = None
         self.mode = None
         self.op = 'MODIFY'
         self.binary = False
 
     def setmode(self, mode):
         islink = mode & 020000
         isexec = mode & 0100
         self.mode = (islink, isexec)
 
     def copy(self):
         other = patchmeta(self.path)
         other.oldpath = self.oldpath
         other.mode = self.mode
         other.op = self.op
         other.binary = self.binary
         return other
 
     def _ispatchinga(self, afile):
         if afile == '/dev/null':
             return self.op == 'ADD'
         return afile == 'a/' + (self.oldpath or self.path)
 
     def _ispatchingb(self, bfile):
         if bfile == '/dev/null':
             return self.op == 'DELETE'
         return bfile == 'b/' + self.path
 
     def ispatching(self, afile, bfile):
         return self._ispatchinga(afile) and self._ispatchingb(bfile)
 
     def __repr__(self):
         return "<patchmeta %s %r>" % (self.op, self.path)
 
 def readgitpatch(lr):
     """extract git-style metadata about patches from <patchname>"""
 
     # Filter patch for git information
     gp = None
     gitpatches = []
     for line in lr:
         line = line.rstrip(' \r\n')
         if line.startswith('diff --git a/'):
             m = gitre.match(line)
             if m:
                 if gp:
                     gitpatches.append(gp)
                 dst = m.group(2)
                 gp = patchmeta(dst)
         elif gp:
             if line.startswith('--- '):
                 gitpatches.append(gp)
                 gp = None
                 continue
             if line.startswith('rename from '):
                 gp.op = 'RENAME'
                 gp.oldpath = line[12:]
             elif line.startswith('rename to '):
                 gp.path = line[10:]
             elif line.startswith('copy from '):
                 gp.op = 'COPY'
                 gp.oldpath = line[10:]
             elif line.startswith('copy to '):
                 gp.path = line[8:]
             elif line.startswith('deleted file'):
                 gp.op = 'DELETE'
             elif line.startswith('new file mode '):
                 gp.op = 'ADD'
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('new mode '):
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('GIT binary patch'):
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     return gitpatches
 
 class linereader(object):
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp):
         self.fp = fp
         self.buf = []
 
     def push(self, line):
         if line is not None:
             self.buf.append(line)
 
     def readline(self):
         if self.buf:
             l = self.buf[0]
             del self.buf[0]
             return l
         return self.fp.readline()
 
     def __iter__(self):
         while True:
             l = self.readline()
             if not l:
                 break
             yield l
 
 class abstractbackend(object):
     def __init__(self, ui):
         self.ui = ui
 
     def getfile(self, fname):
         """Return target file data and flags as a (data, (islink,
         isexec)) tuple.
         """
         raise NotImplementedError
 
     def setfile(self, fname, data, mode, copysource):
         """Write data to target file fname and set its mode. mode is a
         (islink, isexec) tuple. If data is None, the file content should
         be left unchanged. If the file is modified after being copied,
         copysource is set to the original file name.
         """
         raise NotImplementedError
 
     def unlink(self, fname):
         """Unlink target file."""
         raise NotImplementedError
 
     def writerej(self, fname, failed, total, lines):
         """Write rejected lines for fname. total is the number of hunks
         which failed to apply and total the total number of hunks for this
         files.
         """
         pass
 
     def exists(self, fname):
         raise NotImplementedError
 
 class fsbackend(abstractbackend):
     def __init__(self, ui, basedir):
         super(fsbackend, self).__init__(ui)
         self.opener = scmutil.opener(basedir)
 
     def _join(self, f):
         return os.path.join(self.opener.base, f)
 
     def getfile(self, fname):
         path = self._join(fname)
         if os.path.islink(path):
             return (os.readlink(path), (True, False))
         isexec = False
         try:
             isexec = os.lstat(path).st_mode & 0100 != 0
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
         return (self.opener.read(fname), (False, isexec))
 
     def setfile(self, fname, data, mode, copysource):
         islink, isexec = mode
         if data is None:
             util.setflags(self._join(fname), islink, isexec)
             return
         if islink:
             self.opener.symlink(data, fname)
         else:
             self.opener.write(fname, data)
             if isexec:
                 util.setflags(self._join(fname), False, True)
 
     def unlink(self, fname):
         util.unlinkpath(self._join(fname), ignoremissing=True)
 
     def writerej(self, fname, failed, total, lines):
         fname = fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
             (failed, total, fname))
         fp = self.opener(fname, 'w')
         fp.writelines(lines)
         fp.close()
 
     def exists(self, fname):
         return os.path.lexists(self._join(fname))
 
 class workingbackend(fsbackend):
     def __init__(self, ui, repo, similarity):
         super(workingbackend, self).__init__(ui, repo.root)
         self.repo = repo
         self.similarity = similarity
         self.removed = set()
         self.changed = set()
         self.copied = []
 
     def _checkknown(self, fname):
         if self.repo.dirstate[fname] == '?' and self.exists(fname):
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def setfile(self, fname, data, mode, copysource):
         self._checkknown(fname)
         super(workingbackend, self).setfile(fname, data, mode, copysource)
         if copysource is not None:
             self.copied.append((copysource, fname))
         self.changed.add(fname)
 
     def unlink(self, fname):
         self._checkknown(fname)
         super(workingbackend, self).unlink(fname)
         self.removed.add(fname)
         self.changed.add(fname)
 
     def close(self):
         wctx = self.repo[None]
         changed = set(self.changed)
         for src, dst in self.copied:
             scmutil.dirstatecopy(self.ui, self.repo, wctx, src, dst)
         if self.removed:
             wctx.forget(sorted(self.removed))
             for f in self.removed:
                 if f not in self.repo.dirstate:
                     # File was deleted and no longer belongs to the
                     # dirstate, it was probably marked added then
                     # deleted, and should not be considered by
                     # marktouched().
                     changed.discard(f)
         if changed:
             scmutil.marktouched(self.repo, changed, self.similarity)
         return sorted(self.changed)
 
 class filestore(object):
     def __init__(self, maxsize=None):
         self.opener = None
         self.files = {}
         self.created = 0
         self.maxsize = maxsize
         if self.maxsize is None:
             self.maxsize = 4*(2**20)
         self.size = 0
         self.data = {}
 
     def setfile(self, fname, data, mode, copied=None):
         if self.maxsize < 0 or (len(data) + self.size) <= self.maxsize:
             self.data[fname] = (data, mode, copied)
             self.size += len(data)
         else:
             if self.opener is None:
                 root = tempfile.mkdtemp(prefix='hg-patch-')
                 self.opener = scmutil.opener(root)
             # Avoid filename issues with these simple names
             fn = str(self.created)
             self.opener.write(fn, data)
             self.created += 1
             self.files[fname] = (fn, mode, copied)
 
     def getfile(self, fname):
         if fname in self.data:
             return self.data[fname]
         if not self.opener or fname not in self.files:
             raise IOError
         fn, mode, copied = self.files[fname]
         return self.opener.read(fn), mode, copied
 
     def close(self):
         if self.opener:
             shutil.rmtree(self.opener.base)
 
 class repobackend(abstractbackend):
     def __init__(self, ui, repo, ctx, store):
         super(repobackend, self).__init__(ui)
         self.repo = repo
         self.ctx = ctx
         self.store = store
         self.changed = set()
         self.removed = set()
         self.copied = {}
 
     def _checkknown(self, fname):
         if fname not in self.ctx:
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def getfile(self, fname):
         try:
             fctx = self.ctx[fname]
         except error.LookupError:
             raise IOError
         flags = fctx.flags()
         return fctx.data(), ('l' in flags, 'x' in flags)
 
     def setfile(self, fname, data, mode, copysource):
         if copysource:
             self._checkknown(copysource)
         if data is None:
             data = self.ctx[fname].data()
         self.store.setfile(fname, data, mode, copysource)
         self.changed.add(fname)
         if copysource:
             self.copied[fname] = copysource
 
     def unlink(self, fname):
         self._checkknown(fname)
         self.removed.add(fname)
 
     def exists(self, fname):
         return fname in self.ctx
 
     def close(self):
         return self.changed | self.removed
 
 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
 unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
 contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
 eolmodes = ['strict', 'crlf', 'lf', 'auto']
 
 class patchfile(object):
     def __init__(self, ui, gp, backend, store, eolmode='strict'):
         self.fname = gp.path
         self.eolmode = eolmode
         self.eol = None
         self.backend = backend
         self.ui = ui
         self.lines = []
         self.exists = False
         self.missing = True
         self.mode = gp.mode
         self.copysource = gp.oldpath
         self.create = gp.op in ('ADD', 'COPY', 'RENAME')
         self.remove = gp.op == 'DELETE'
         try:
             if self.copysource is None:
                 data, mode = backend.getfile(self.fname)
                 self.exists = True
             else:
                 data, mode = store.getfile(self.copysource)[:2]
                 self.exists = backend.exists(self.fname)
             self.missing = False
             if data:
                 self.lines = mdiff.splitnewlines(data)
             if self.mode is None:
                 self.mode = mode
             if self.lines:
                 # Normalize line endings
                 if self.lines[0].endswith('\r\n'):
                     self.eol = '\r\n'
                 elif self.lines[0].endswith('\n'):
                     self.eol = '\n'
                 if eolmode != 'strict':
                     nlines = []
                     for l in self.lines:
                         if l.endswith('\r\n'):
                             l = l[:-2] + '\n'
                         nlines.append(l)
                     self.lines = nlines
         except IOError:
             if self.create:
                 self.missing = False
             if self.mode is None:
                 self.mode = (False, False)
         if self.missing:
             self.ui.warn(_("unable to find '%s' for patching\n") % self.fname)
 
         self.hash = {}
         self.dirty = 0
         self.offset = 0
         self.skew = 0
         self.rej = []
         self.fileprinted = False
         self.printfile(False)
         self.hunks = 0
 
     def writelines(self, fname, lines, mode):
         if self.eolmode == 'auto':
             eol = self.eol
         elif self.eolmode == 'crlf':
             eol = '\r\n'
         else:
             eol = '\n'
 
         if self.eolmode != 'strict' and eol and eol != '\n':
             rawlines = []
             for l in lines:
                 if l and l[-1] == '\n':
                     l = l[:-1] + eol
                 rawlines.append(l)
             lines = rawlines
 
         self.backend.setfile(fname, ''.join(lines), mode, self.copysource)
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _("patching file %s\n") % self.fname
         if warn:
             self.ui.warn(s)
         else:
             self.ui.note(s)
 
 
     def findlines(self, l, linenum):
         # looks through the hash and finds candidate lines.  The
         # result is a list of line numbers sorted based on distance
         # from linenum
 
         cand = self.hash.get(l, [])
         if len(cand) > 1:
             # resort our list of potentials forward then back.
             cand.sort(key=lambda x: abs(x - linenum))
         return cand
 
     def write_rej(self):
         # our rejects are a little different from patch(1).  This always
         # creates rejects in the same form as the original patch.  A file
         # header is inserted so that you can run the reject through patch again
         # without having to type the filename.
         if not self.rej:
             return
         base = os.path.basename(self.fname)
         lines = ["--- %s\n+++ %s\n" % (base, base)]
         for x in self.rej:
             for l in x.hunk:
                 lines.append(l)
                 if l[-1] != '\n':
                     lines.append("\n\ No newline at end of file\n")
         self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)
 
     def apply(self, h):
         if not h.complete():
             raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                             (h.number, h.desc, len(h.a), h.lena, len(h.b),
                             h.lenb))
 
         self.hunks += 1
 
         if self.missing:
             self.rej.append(h)
             return -1
 
         if self.exists and self.create:
             if self.copysource:
                 self.ui.warn(_("cannot create %s: destination already "
-                               "exists\n" % self.fname))
+                               "exists\n") % self.fname)
             else:
                 self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 l = h.new(self.lines)
                 self.lines[:] = l
                 self.offset += len(l)
                 self.dirty = True
             return 0
 
         horig = h
         if (self.eolmode in ('crlf', 'lf')
             or self.eolmode == 'auto' and self.eol):
             # If new eols are going to be normalized, then normalize
             # hunk data before patching. Otherwise, preserve input
             # line-endings.
             h = h.getnormalized()
 
         # fast case first, no offsets, no fuzz
         old, oldstart, new, newstart = h.fuzzit(0, False)
         oldstart += self.offset
         orig_start = oldstart
         # if there's skew we want to emit the "(offset %d lines)" even
         # when the hunk cleanly applies at start + skew, so skip the
         # fast case code
         if (self.skew == 0 and
             diffhelpers.testhunk(old, self.lines, oldstart) == 0):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[oldstart:oldstart + len(old)] = new
                 self.offset += len(new) - len(old)
                 self.dirty = True
             return 0
 
         # ok, we couldn't match the hunk. Lets look for offsets and fuzz it
         self.hash = {}
         for x, s in enumerate(self.lines):
             self.hash.setdefault(s, []).append(x)
 
         for fuzzlen in xrange(3):
             for toponly in [True, False]:
                 old, oldstart, new, newstart = h.fuzzit(fuzzlen, toponly)
                 oldstart = oldstart + self.offset + self.skew
                 oldstart = min(oldstart, len(self.lines))
                 if old:
                     cand = self.findlines(old[0][1:], oldstart)
                 else:
                     # Only adding lines with no or fuzzed context, just
                     # take the skew in account
                     cand = [oldstart]
 
                 for l in cand:
                     if not old or diffhelpers.testhunk(old, self.lines, l) == 0:
                         self.lines[l : l + len(old)] = new
                         self.offset += len(new) - len(old)
                         self.skew = l - orig_start
                         self.dirty = True
                         offset = l - orig_start - fuzzlen
                         if fuzzlen:
                             msg = _("Hunk #%d succeeded at %d "
                                     "with fuzz %d "
                                     "(offset %d lines).\n")
                             self.printfile(True)
                             self.ui.warn(msg %
                                 (h.number, l + 1, fuzzlen, offset))
                         else:
                             msg = _("Hunk #%d succeeded at %d "
                                     "(offset %d lines).\n")
                             self.ui.note(msg % (h.number, l + 1, offset))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
         self.rej.append(horig)
         return -1
 
     def close(self):
         if self.dirty:
             self.writelines(self.fname, self.lines, self.mode)
         self.write_rej()
         return len(self.rej)
 
 class hunk(object):
     def __init__(self, desc, num, lr, context):
         self.number = num
         self.desc = desc
         self.hunk = [desc]
         self.a = []
         self.b = []
         self.starta = self.lena = None
         self.startb = self.lenb = None
         if lr is not None:
             if context:
                 self.read_context_hunk(lr)
             else:
                 self.read_unified_hunk(lr)
 
     def getnormalized(self):
         """Return a copy with line endings normalized to LF."""
 
         def normalize(lines):
             nlines = []
             for line in lines:
                 if line.endswith('\r\n'):
                     line = line[:-2] + '\n'
                 nlines.append(line)
             return nlines
 
         # Dummy object, it is rebuilt manually
         nh = hunk(self.desc, self.number, None, None)
         nh.number = self.number
         nh.desc = self.desc
         nh.hunk = self.hunk
         nh.a = normalize(self.a)
         nh.b = normalize(self.b)
         nh.starta = self.starta
         nh.startb = self.startb
         nh.lena = self.lena
         nh.lenb = self.lenb
         return nh
 
     def read_unified_hunk(self, lr):
         m = unidesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, self.lena, self.startb, self.lenb = m.groups()
         if self.lena is None:
             self.lena = 1
         else:
             self.lena = int(self.lena)
         if self.lenb is None:
             self.lenb = 1
         else:
             self.lenb = int(self.lenb)
         self.starta = int(self.starta)
         self.startb = int(self.startb)
         diffhelpers.addlines(lr, self.hunk, self.lena, self.lenb, self.a,
                              self.b)
         # if we hit eof before finishing out the hunk, the last line will
         # be zero length.  Lets try to fix it up.
         while len(self.hunk[-1]) == 0:
             del self.hunk[-1]
             del self.a[-1]
             del self.b[-1]
             self.lena -= 1
             self.lenb -= 1
         self._fixnewline(lr)
 
     def read_context_hunk(self, lr):
         self.desc = lr.readline()
         m = contextdesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, aend = m.groups()
         self.starta = int(self.starta)
         if aend is None:
             aend = self.starta
         self.lena = int(aend) - self.starta
         if self.starta:
             self.lena += 1
         for x in xrange(self.lena):
             l = lr.readline()
             if l.startswith('---'):
                 # lines addition, old block is empty
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('- ') or l.startswith('! '):
                 u = '-' + s
             elif l.startswith('  '):
                 u = ' ' + s
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith('\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.startb, bend = m.groups()
         self.startb = int(self.startb)
         if bend is None:
             bend = self.startb
         self.lenb = int(bend) - self.startb
         if self.startb:
             self.lenb += 1
         hunki = 1
         for x in xrange(self.lenb):
             l = lr.readline()
             if l.startswith('\ '):
                 # XXX: the only way to hit this is with an invalid line range.
                 # The no-eol marker is not counted in the line range, but I
                 # guess there are diff(1) out there which behave differently.
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki - 1] = s
                 continue
             if not l:
                 # line deletions, new block is empty and we hit EOF
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('+ ') or l.startswith('! '):
                 u = '+' + s
             elif l.startswith('  '):
                 u = ' ' + s
             elif len(self.b) == 0:
                 # line deletions, new block is empty
                 lr.push(l)
                 break
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = ""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith('-'):
                     continue
                 else:
                     self.hunk.insert(hunki - 1, u)
                     break
 
         if not self.a:
             # this happens when lines were only added to the hunk
             for x in self.hunk:
                 if x.startswith('-') or x.startswith(' '):
                     self.a.append(x)
         if not self.b:
             # this happens when lines were only deleted from the hunk
             for x in self.hunk:
                 if x.startswith('+') or x.startswith(' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                              self.startb, self.lenb)
         self.hunk[0] = self.desc
         self._fixnewline(lr)
 
     def _fixnewline(self, lr):
         l = lr.readline()
         if l.startswith('\ '):
             diffhelpers.fix_newline(self.hunk, self.a, self.b)
         else:
             lr.push(l)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def _fuzzit(self, old, new, fuzz, toponly):
         # this removes context lines from the top and bottom of list 'l'.  It
         # checks the hunk to make sure only context lines are removed, and then
         # returns a new shortened list of lines.
         fuzz = min(fuzz, len(old))
         if fuzz:
             top = 0
             bot = 0
             hlen = len(self.hunk)
             for x in xrange(hlen - 1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x + 1][0] == ' ':
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in xrange(hlen - 1):
                     if self.hunk[hlen - bot - 1][0] == ' ':
                         bot += 1
                     else:
                         break
 
             bot = min(fuzz, bot)
             top = min(fuzz, top)
             return old[top:len(old) - bot], new[top:len(new) - bot], top
         return old, new, 0
 
     def fuzzit(self, fuzz, toponly):
         old, new, top = self._fuzzit(self.a, self.b, fuzz, toponly)
         oldstart = self.starta + top
         newstart = self.startb + top
         # zero length hunk ranges already have their start decremented
         if self.lena and oldstart > 0:
             oldstart -= 1
         if self.lenb and newstart > 0:
             newstart -= 1
         return old, oldstart, new, newstart
 
 class binhunk(object):
     'A binary patch file.'
     def __init__(self, lr, fname):
         self.text = None
         self.delta = False
         self.hunk = ['GIT binary patch\n']
         self._fname = fname
         self._read(lr)
 
     def complete(self):
         return self.text is not None
 
     def new(self, lines):
         if self.delta:
             return [applybindelta(self.text, ''.join(lines))]
         return [self.text]
 
     def _read(self, lr):
         def getline(lr, hunk):
             l = lr.readline()
             hunk.append(l)
             return l.rstrip('\r\n')
 
         size = 0
         while True:
             line = getline(lr, self.hunk)
             if not line:
                 raise PatchError(_('could not extract "%s" binary data')
                                  % self._fname)
             if line.startswith('literal '):
                 size = int(line[8:].rstrip())
                 break
             if line.startswith('delta '):
                 size = int(line[6:].rstrip())
                 self.delta = True
                 break
         dec = []
         line = getline(lr, self.hunk)
         while len(line) > 1:
             l = line[0]
             if l <= 'Z' and l >= 'A':
                 l = ord(l) - ord('A') + 1
             else:
                 l = ord(l) - ord('a') + 27
             try:
                 dec.append(base85.b85decode(line[1:])[:l])
             except ValueError, e:
                 raise PatchError(_('could not decode "%s" binary patch: %s')
                                  % (self._fname, str(e)))
             line = getline(lr, self.hunk)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('"%s" length is %d bytes, should be %d')
                              % (self._fname, len(text), size))
         self.text = text
 
 def parsefilename(str):
     # --- filename \t|space stuff
     s = str[4:].rstrip('\r\n')
     i = s.find('\t')
     if i < 0:
         i = s.find(' ')
         if i < 0:
             return s
     return s[:i]
 
 def pathstrip(path, strip):
     pathlen = len(path)
     i = 0
     if strip == 0:
         return '', path.rstrip()
     count = strip
     while count > 0:
         i = path.find('/', i)
         if i == -1:
             raise PatchError(_("unable to strip away %d of %d dirs from %s") %
                              (count, strip, path))
         i += 1
         # consume '//' in the path
         while i < pathlen - 1 and path[i] == '/':
             i += 1
         count -= 1
     return path[:i].lstrip(), path[i:].rstrip()
 
 def makepatchmeta(backend, afile_orig, bfile_orig, hunk, strip):
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     create = nulla and hunk.starta == 0 and hunk.lena == 0
     remove = nullb and hunk.startb == 0 and hunk.lenb == 0
     abase, afile = pathstrip(afile_orig, strip)
     gooda = not nulla and backend.exists(afile)
     bbase, bfile = pathstrip(bfile_orig, strip)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = not nullb and backend.exists(bfile)
     missing = not goodb and not gooda and not create
 
     # some diff programs apparently produce patches where the afile is
     # not /dev/null, but afile starts with bfile
     abasedir = afile[:afile.rfind('/') + 1]
     bbasedir = bfile[:bfile.rfind('/') + 1]
     if (missing and abasedir == bbasedir and afile.startswith(bfile)
         and hunk.starta == 0 and hunk.lena == 0):
         create = True
         missing = False
 
     # If afile is "a/b/foo" and bfile is "a/b/foo.orig" we assume the
     # diff is between a file and its backup. In this case, the original
     # file should be patched (see original mpatch code).
     isbackup = (abase == bbase and bfile.startswith(afile))
     fname = None
     if not missing:
         if gooda and goodb:
             fname = isbackup and afile or bfile
         elif gooda:
             fname = afile
 
     if not fname:
         if not nullb:
             fname = isbackup and afile or bfile
         elif not nulla:
             fname = afile
         else:
             raise PatchError(_("undefined source and destination files"))
 
     gp = patchmeta(fname)
     if create:
         gp.op = 'ADD'
     elif remove:
         gp.op = 'DELETE'
     return gp
 
 def scangitpatch(lr, firstline):
     """
     Git patches can emit:
     - rename a to b
     - change b
     - copy a to c
     - change c
 
     We cannot apply this sequence as-is, the renamed 'a' could not be
     found for it would have been renamed already. And we cannot copy
     from 'b' instead because 'b' would have been changed already. So
     we scan the git patch for copy and rename commands so we can
     perform the copies ahead of time.
     """
     pos = 0
     try:
         pos = lr.fp.tell()
         fp = lr.fp
     except IOError:
         fp = cStringIO.StringIO(lr.fp.read())
     gitlr = linereader(fp)
     gitlr.push(firstline)
     gitpatches = readgitpatch(gitlr)
     fp.seek(pos)
     return gitpatches
 
 def iterhunks(fp):
     """Read a patch and yield the following events:
     - ("file", afile, bfile, firsthunk): select a new target file.
     - ("hunk", hunk): a new hunk is ready to be applied, follows a
     "file" event.
     - ("git", gitchanges): current diff is in git format, gitchanges
     maps filenames to gitpatch records. Unique event.
     """
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
     emitfile = newfile = False
     gitpatches = None
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
 
     while True:
         x = lr.readline()
         if not x:
             break
         if state == BFILE and (
             (not context and x[0] == '@')
             or (context is not False and x.startswith('***************'))
             or x.startswith('GIT binary patch')):
             gp = None
             if (gitpatches and
                 gitpatches[-1].ispatching(afile, bfile)):
                 gp = gitpatches.pop()
             if x.startswith('GIT binary patch'):
                 h = binhunk(lr, gp.path)
             else:
                 if context is None and x.startswith('***************'):
                     context = True
                 h = hunk(x, hunknum + 1, lr, context)
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', (afile, bfile, h, gp and gp.copy() or None)
             yield 'hunk', h
         elif x.startswith('diff --git a/'):
             m = gitre.match(x.rstrip(' \r\n'))
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = scangitpatch(lr, x)
                 yield 'git', [g.copy() for g in gitpatches
                               if g.op in ('COPY', 'RENAME')]
                 gitpatches.reverse()
             afile = 'a/' + m.group(1)
             bfile = 'b/' + m.group(2)
             while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
                 yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
             if not gitpatches:
                 raise PatchError(_('failed to synchronize metadata for "%s"')
                                  % afile[2:])
             gp = gitpatches[-1]
             newfile = True
         elif x.startswith('---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith('+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith('***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith('---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith("***************"):
                 lr.push(l2)
                 continue
             newfile = True
             context = True
             afile = parsefilename(x)
             bfile = parsefilename(l2)
 
         if newfile:
             newfile = False
             emitfile = True
             state = BFILE
             hunknum = 0
 
     while gitpatches:
         gp = gitpatches.pop()
         yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
 
 def applybindelta(binchunk, data):
     """Apply a binary delta hunk
     The algorithm used is the algorithm from git's patch-delta.c
     """
     def deltahead(binchunk):
         i = 0
         for c in binchunk:
             i += 1
             if not (ord(c) & 0x80):
                 return i
         return i
     out = ""
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     i = 0
     while i < len(binchunk):
         cmd = ord(binchunk[i])
         i += 1
         if (cmd & 0x80):
             offset = 0
             size = 0
             if (cmd & 0x01):
                 offset = ord(binchunk[i])
                 i += 1
             if (cmd & 0x02):
                 offset |= ord(binchunk[i]) << 8
                 i += 1
             if (cmd & 0x04):
                 offset |= ord(binchunk[i]) << 16
                 i += 1
             if (cmd & 0x08):
                 offset |= ord(binchunk[i]) << 24
                 i += 1
             if (cmd & 0x10):
                 size = ord(binchunk[i])
                 i += 1
             if (cmd & 0x20):
                 size |= ord(binchunk[i]) << 8
                 i += 1
             if (cmd & 0x40):
                 size |= ord(binchunk[i]) << 16
                 i += 1
             if size == 0:
                 size = 0x10000
             offset_end = offset + size
             out += data[offset:offset_end]
         elif cmd != 0:
             offset_end = i + cmd
             out += binchunk[i:offset_end]
             i += cmd
         else:
             raise PatchError(_('unexpected delta opcode 0'))
     return out
 
 def applydiff(ui, fp, backend, store, strip=1, eolmode='strict'):
     """Reads a patch from fp and tries to apply it.
 
     Returns 0 for a clean patch, -1 if any rejects were found and 1 if
     there was any fuzz.
 
     If 'eolmode' is 'strict', the patch content and patched file are
     read in binary mode. Otherwise, line endings are ignored when
     patching then normalized according to 'eolmode'.
     """
     return _applydiff(ui, fp, patchfile, backend, store, strip=strip,
                       eolmode=eolmode)
 
 def _applydiff(ui, fp, patcher, backend, store, strip=1,
                eolmode='strict'):
 
     def pstrip(p):
         return pathstrip(p, strip - 1)[1]
 
     rejects = 0
     err = 0
     current_file = None
 
     for state, values in iterhunks(fp):
         if state == 'hunk':
             if not current_file:
                 continue
             ret = current_file.apply(values)
             if ret > 0:
                 err = 1
         elif state == 'file':
             if current_file:
                 rejects += current_file.close()
                 current_file = None
             afile, bfile, first_hunk, gp = values
             if gp:
                 gp.path = pstrip(gp.path)
                 if gp.oldpath:
                     gp.oldpath = pstrip(gp.oldpath)
             else:
                 gp = makepatchmeta(backend, afile, bfile, first_hunk, strip)
             if gp.op == 'RENAME':
                 backend.unlink(gp.oldpath)
             if not first_hunk:
                 if gp.op == 'DELETE':
                     backend.unlink(gp.path)
                     continue
                 data, mode = None, None
                 if gp.op in ('RENAME', 'COPY'):
                     data, mode = store.getfile(gp.oldpath)[:2]
                 if gp.mode:
                     mode = gp.mode
                     if gp.op == 'ADD':
                         # Added files without content have no hunk and
                         # must be created
                         data = ''
                 if data or mode:
                     if (gp.op in ('ADD', 'RENAME', 'COPY')
                         and backend.exists(gp.path)):
                         raise PatchError(_("cannot create %s: destination "
                                            "already exists") % gp.path)
                     backend.setfile(gp.path, data, mode, gp.oldpath)
                 continue
             try:
                 current_file = patcher(ui, gp, backend, store,
                                        eolmode=eolmode)
             except PatchError, inst:
                 ui.warn(str(inst) + '\n')
                 current_file = None
                 rejects += 1
                 continue
         elif state == 'git':
             for gp in values:
                 path = pstrip(gp.oldpath)
                 try:
                     data, mode = backend.getfile(path)
                 except IOError, e:
                     if e.errno != errno.ENOENT:
                         raise
                     # The error ignored here will trigger a getfile()
                     # error in a place more appropriate for error
                     # handling, and will not interrupt the patching
                     # process.
                 else:
                     store.setfile(path, data, mode)
         else:
             raise util.Abort(_('unsupported parser state: %s') % state)
 
     if current_file:
         rejects += current_file.close()
 
     if rejects:
         return -1
     return err
 
 def _externalpatch(ui, repo, patcher, patchname, strip, files,
                    similarity):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     args = []
     cwd = repo.root
     if cwd:
         args.append('-d %s' % util.shellquote(cwd))
     fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                        util.shellquote(patchname)))
     try:
         for line in fp:
             line = line.rstrip()
             ui.note(line + '\n')
             if line.startswith('patching file '):
                 pf = util.parsepatchoutput(line)
                 printed_file = False
                 files.add(pf)
             elif line.find('with fuzz') >= 0:
                 fuzz = True
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
             elif line.find('saving rejects to file') >= 0:
                 ui.warn(line + '\n')
             elif line.find('FAILED') >= 0:
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
     finally:
         if files:
             scmutil.marktouched(repo, files, similarity)
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          util.explainexit(code)[0])
     return fuzz
 
 def patchbackend(ui, backend, patchobj, strip, files=None, eolmode='strict'):
     if files is None:
         files = set()
     if eolmode is None:
         eolmode = ui.config('patch', 'eol', 'strict')
     if eolmode.lower() not in eolmodes:
         raise util.Abort(_('unsupported line endings type: %s') % eolmode)
     eolmode = eolmode.lower()
 
     store = filestore()
     try:
         fp = open(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     try:
         ret = applydiff(ui, fp, backend, store, strip=strip,
                         eolmode=eolmode)
     finally:
         if fp != patchobj:
             fp.close()
         files.update(backend.close())
         store.close()
     if ret < 0:
         raise PatchError(_('patch failed to apply'))
     return ret > 0
 
 def internalpatch(ui, repo, patchobj, strip, files=None, eolmode='strict',
                   similarity=0):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
     backend = workingbackend(ui, repo, similarity)
     return patchbackend(ui, backend, patchobj, strip, files, eolmode)
 
 def patchrepo(ui, repo, ctx, store, patchobj, strip, files=None,
               eolmode='strict'):
     backend = repobackend(ui, repo, ctx, store)
     return patchbackend(ui, backend, patchobj, strip, files, eolmode)
 
 def patch(ui, repo, patchname, strip=1, files=None, eolmode='strict',
           similarity=0):
     """Apply <patchname> to the working directory.
 
     'eolmode' specifies how end of lines should be handled. It can be:
     - 'strict': inputs are read in binary mode, EOLs are preserved
     - 'crlf': EOLs are ignored when patching and reset to CRLF
     - 'lf': EOLs are ignored when patching and reset to LF
     - None: get it from user settings, default to 'strict'
     'eolmode' is ignored when using an external patcher program.
 
     Returns whether patch was applied with fuzz factor.
     """
     patcher = ui.config('ui', 'patch')
     if files is None:
         files = set()
     try:
         if patcher:
             return _externalpatch(ui, repo, patcher, patchname, strip,
                                   files, similarity)
         return internalpatch(ui, repo, patchname, strip, files, eolmode,
                              similarity)
     except PatchError, err:
         raise util.Abort(str(err))
 
 def changedfiles(ui, repo, patchpath, strip=1):
     backend = fsbackend(ui, repo.root)
     fp = open(patchpath, 'rb')
     try:
         changed = set()
         for state, values in iterhunks(fp):
             if state == 'file':
                 afile, bfile, first_hunk, gp = values
                 if gp:
                     gp.path = pathstrip(gp.path, strip - 1)[1]
                     if gp.oldpath:
                         gp.oldpath = pathstrip(gp.oldpath, strip - 1)[1]
                 else:
                     gp = makepatchmeta(backend, afile, bfile, first_hunk, strip)
                 changed.add(gp.path)
                 if gp.op == 'RENAME':
                     changed.add(gp.oldpath)
             elif state not in ('hunk', 'git'):
                 raise util.Abort(_('unsupported parser state: %s') % state)
         return changed
     finally:
         fp.close()
 
 class GitDiffRequired(Exception):
     pass
 
 def diffopts(ui, opts=None, untrusted=False, section='diff'):
     def get(key, name=None, getter=ui.configbool):
         return ((opts and opts.get(key)) or
                 getter(section, name or key, None, untrusted=untrusted))
     return mdiff.diffopts(
         text=opts and opts.get('text'),
         git=get('git'),
         nodates=get('nodates'),
         showfunc=get('show_function', 'showfunc'),
         ignorews=get('ignore_all_space', 'ignorews'),
         ignorewsamount=get('ignore_space_change', 'ignorewsamount'),
         ignoreblanklines=get('ignore_blank_lines', 'ignoreblanklines'),
         context=get('unified', getter=ui.config))
 
 def diff(repo, node1=None, node2=None, match=None, changes=None, opts=None,
          losedatafn=None, prefix=''):
     '''yields diff of changes to files between two nodes, or node and
     working directory.
 
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.
 
     losedatafn(**kwarg) is a callable run when opts.upgrade=True and
     every time some change cannot be represented with the current
     patch format. Return False to upgrade to git patch format, True to
     accept the loss or raise an exception to abort the diff. It is
     called with the name of current file being diffed as 'fn'. If set
     to None, patches will always be upgraded to git format when
     necessary.
 
     prefix is a filename prefix that is prepended to all filenames on
     display (used for subrepos).
     '''
 
     if opts is None:
         opts = mdiff.defaultopts
 
     if not node1 and not node2:
         node1 = repo.dirstate.p1()
 
     def lrugetfilectx():
         cache = {}
         order = util.deque()
         def getfilectx(f, ctx):
             fctx = ctx.filectx(f, filelog=cache.get(f))
             if f not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[f] = fctx.filelog()
             else:
                 order.remove(f)
             order.append(f)
             return fctx
         return getfilectx
     getfilectx = lrugetfilectx()
 
     ctx1 = repo[node1]
     ctx2 = repo[node2]
 
     if not changes:
         changes = repo.status(ctx1, ctx2, match=match)
     modified, added, removed = changes[:3]
 
     if not modified and not added and not removed:
         return []
 
     revs = None
     hexfunc = repo.ui.debugflag and hex or short
     revs = [hexfunc(node) for node in [node1, node2] if node]
 
     copy = {}
     if opts.git or opts.upgrade:
         copy = copies.pathcopies(ctx1, ctx2)
 
     def difffn(opts, losedata):
         return trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
                        copy, getfilectx, opts, losedata, prefix)
     if opts.upgrade and not opts.git:
         try:
             def losedata(fn):
                 if not losedatafn or not losedatafn(fn=fn):
                     raise GitDiffRequired
             # Buffer the whole output until we are sure it can be generated
             return list(difffn(opts.copy(git=False), losedata))
         except GitDiffRequired:
             return difffn(opts.copy(git=True), None)
     else:
         return difffn(opts, None)
 
 def difflabel(func, *args, **kw):
     '''yields 2-tuples of (output, label) based on the output of func()'''
     headprefixes = [('diff', 'diff.diffline'),
                     ('copy', 'diff.extended'),
                     ('rename', 'diff.extended'),
                     ('old', 'diff.extended'),
                     ('new', 'diff.extended'),
                     ('deleted', 'diff.extended'),
                     ('---', 'diff.file_a'),
                     ('+++', 'diff.file_b')]
     textprefixes = [('@', 'diff.hunk'),
                     ('-', 'diff.deleted'),
                     ('+', 'diff.inserted')]
     head = False
     for chunk in func(*args, **kw):
         lines = chunk.split('\n')
         for i, line in enumerate(lines):
             if i != 0:
                 yield ('\n', '')
             if head:
                 if line.startswith('@'):
                     head = False
             else:
                 if line and line[0] not in ' +-@\\':
                     head = True
             stripline = line
             if not head and line and line[0] in '+-':
                 # highlight trailing whitespace, but only in changed lines
                 stripline = line.rstrip()
             prefixes = textprefixes
             if head:
                 prefixes = headprefixes
             for prefix, label in prefixes:
                 if stripline.startswith(prefix):
                     yield (stripline, label)
                     break
             else:
                 yield (line, '')
             if line != stripline:
                 yield (line[len(stripline):], 'diff.trailingwhitespace')
 
 def diffui(*args, **kw):
     '''like diff(), but yields 2-tuples of (output, label) for ui.write()'''
     return difflabel(diff, *args, **kw)
 
 def trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
             copy, getfilectx, opts, losedatafn, prefix):
 
     def join(f):
         return posixpath.join(prefix, f)
 
     def addmodehdr(header, omode, nmode):
         if omode != nmode:
             header.append('old mode %s\n' % omode)
             header.append('new mode %s\n' % nmode)
 
     def addindexmeta(meta, revs):
         if opts.git:
             i = len(revs)
             if i==2:
                 meta.append('index %s..%s\n' % tuple(revs))
             elif i==3:
                 meta.append('index %s,%s..%s\n' % tuple(revs))
 
     def gitindex(text):
         if not text:
             text = ""
         l = len(text)
         s = util.sha1('blob %d\0' % l)
         s.update(text)
         return s.hexdigest()
 
     def diffline(a, b, revs):
         if opts.git:
             line = 'diff --git a/%s b/%s\n' % (a, b)
         elif not repo.ui.quiet:
             if revs:
                 revinfo = ' '.join(["-r %s" % rev for rev in revs])
                 line = 'diff %s %s\n' % (revinfo, a)
             else:
                 line = 'diff %s\n' % a
         else:
             line = ''
         return line
 
     date1 = util.datestr(ctx1.date())
     man1 = ctx1.manifest()
 
     gone = set()
     gitmode = {'l': '120000', 'x': '100755', '': '100644'}
 
     copyto = dict([(v, k) for k, v in copy.items()])
 
     if opts.git:
         revs = None
 
     for f in sorted(modified + added + removed):
         to = None
         tn = None
         dodiff = True
         header = []
         if f in man1:
             to = getfilectx(f, ctx1).data()
         if f not in removed:
             tn = getfilectx(f, ctx2).data()
         a, b = f, f
         if opts.git or losedatafn:
             if f in added or (f in modified and to is None):
                 mode = gitmode[ctx2.flags(f)]
                 if f in copy or f in copyto:
                     if opts.git:
                         if f in copy:
                             a = copy[f]
                         else:
                             a = copyto[f]
                         omode = gitmode[man1.flags(a)]
                         addmodehdr(header, omode, mode)
                         if a in removed and a not in gone:
                             op = 'rename'
                             gone.add(a)
                         else:
                             op = 'copy'
                         header.append('%s from %s\n' % (op, join(a)))
                         header.append('%s to %s\n' % (op, join(f)))
                         to = getfilectx(a, ctx1).data()
                     else:
                         losedatafn(f)
                 else:
                     if opts.git:
                         header.append('new file mode %s\n' % mode)
                     elif ctx2.flags(f):
                         losedatafn(f)
                 # In theory, if tn was copied or renamed we should check
                 # if the source is binary too but the copy record already
                 # forces git mode.
                 if util.binary(tn):
                     if opts.git:
                         dodiff = 'binary'
                     else:
                         losedatafn(f)
                 if not opts.git and not tn:
                     # regular diffs cannot represent new empty file
                     losedatafn(f)
             elif f in removed or (f in modified and tn is None):
                 if opts.git:
                     # have we already reported a copy above?
                     if ((f in copy and copy[f] in added
                          and copyto[copy[f]] == f) or
                         (f in copyto and copyto[f] in added
                          and copy[copyto[f]] == f)):
                         dodiff = False
                     else:
                         header.append('deleted file mode %s\n' %
                                       gitmode[man1.flags(f)])
                         if util.binary(to):
                             dodiff = 'binary'
                 elif not to or util.binary(to):
                     # regular diffs cannot represent empty file deletion
                     losedatafn(f)
             else:
                 oflag = man1.flags(f)
                 nflag = ctx2.flags(f)
                 binary = util.binary(to) or util.binary(tn)
                 if opts.git:
                     addmodehdr(header, gitmode[oflag], gitmode[nflag])
                     if binary:
                         dodiff = 'binary'
                 elif binary or nflag != oflag:
                     losedatafn(f)
 
         if dodiff:
             if opts.git or revs:
                 header.insert(0, diffline(join(a), join(b), revs))
             if dodiff == 'binary':
                 text = mdiff.b85diff(to, tn)
                 if text:
                     addindexmeta(header, [gitindex(to), gitindex(tn)])
             else:
                 text = mdiff.unidiff(to, date1,
                                     # ctx2 date may be dynamic
                                     tn, util.datestr(ctx2.date()),
                                     join(a), join(b), opts=opts)
             if header and (text or len(header) > 1):
                 yield ''.join(header)
             if text:
                 yield text
 
 def diffstatsum(stats):
     maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
     for f, a, r, b in stats:
         maxfile = max(maxfile, encoding.colwidth(f))
         maxtotal = max(maxtotal, a + r)
         addtotal += a
         removetotal += r
         binary = binary or b
 
     return maxfile, maxtotal, addtotal, removetotal, binary
 
 def diffstatdata(lines):
     diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$')
 
     results = []
     filename, adds, removes, isbinary = None, 0, 0, False
 
     def addresult():
         if filename:
             results.append((filename, adds, removes, isbinary))
 
     for line in lines:
         if line.startswith('diff'):
             addresult()
             # set numbers to 0 anyway when starting new file
             adds, removes, isbinary = 0, 0, False
             if line.startswith('diff --git a/'):
                 filename = gitre.search(line).group(1)
             elif line.startswith('diff -r'):
                 # format: "diff -r ... -r ... filename"
                 filename = diffre.search(line).group(1)
         elif line.startswith('+') and not line.startswith('+++ '):
             adds += 1
         elif line.startswith('-') and not line.startswith('--- '):
             removes += 1
         elif (line.startswith('GIT binary patch') or
               line.startswith('Binary file')):
             isbinary = True
     addresult()
     return results
 
 def diffstat(lines, width=80, git=False):
     output = []
     stats = diffstatdata(lines)
     maxname, maxtotal, totaladds, totalremoves, hasbinary = diffstatsum(stats)
 
     countwidth = len(str(maxtotal))
     if hasbinary and countwidth < 3:
         countwidth = 3
     graphwidth = width - countwidth - maxname - 6
     if graphwidth < 10:
         graphwidth = 10
 
     def scale(i):
         if maxtotal <= graphwidth:
             return i
         # If diffstat runs out of room it doesn't print anything,
         # which isn't very useful, so always print at least one + or -
         # if there were at least some changes.
         return max(i * graphwidth // maxtotal, int(bool(i)))
 
     for filename, adds, removes, isbinary in stats:
         if isbinary:
             count = 'Bin'
         else:
             count = adds + removes
         pluses = '+' * scale(adds)
         minuses = '-' * scale(removes)
         output.append(' %s%s |  %*s %s%s\n' %
                       (filename, ' ' * (maxname - encoding.colwidth(filename)),
                        countwidth, count, pluses, minuses))
 
     if stats:
         output.append(_(' %d files changed, %d insertions(+), '
                         '%d deletions(-)\n')
                       % (len(stats), totaladds, totalremoves))
 
     return ''.join(output)
 
 def diffstatui(*args, **kw):
     '''like diffstat(), but yields 2-tuples of (output, label) for
     ui.write()
     '''
 
     for line in diffstat(*args, **kw).splitlines():
         if line and line[-1] in '+-':
             name, graph = line.rsplit(' ', 1)
             yield (name + ' ', '')
             m = re.search(r'\++', graph)
             if m:
                 yield (m.group(0), 'diffstat.inserted')
             m = re.search(r'-+', graph)
             if m:
                 yield (m.group(0), 'diffstat.deleted')
         else:
             yield (line, '')
         yield ('\n', '')

mercurial/subrepo.py

@@ -1,1537 +1,1537 b''
 # subrepo.py - sub-repository handling for Mercurial
 #
 # Copyright 2009-2010 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 errno, os, re, shutil, posixpath, sys
 import xml.dom.minidom
 import stat, subprocess, tarfile
 from i18n import _
 import config, util, node, error, cmdutil, bookmarks, match as matchmod
 import phases
 import pathutil
 hg = None
 propertycache = util.propertycache
 
 nullstate = ('', '', 'empty')
 
 def _expandedabspath(path):
     '''
     get a path or url and if it is a path expand it and return an absolute path
     '''
     expandedpath = util.urllocalpath(util.expandpath(path))
     u = util.url(expandedpath)
     if not u.scheme:
         path = util.normpath(os.path.abspath(u.path))
     return path
 
 def _getstorehashcachename(remotepath):
     '''get a unique filename for the store hash cache of a remote repository'''
     return util.sha1(_expandedabspath(remotepath)).hexdigest()[0:12]
 
 def _calcfilehash(filename):
     data = ''
     if os.path.exists(filename):
         fd = open(filename, 'rb')
         data = fd.read()
         fd.close()
     return util.sha1(data).hexdigest()
 
 class SubrepoAbort(error.Abort):
     """Exception class used to avoid handling a subrepo error more than once"""
     def __init__(self, *args, **kw):
         error.Abort.__init__(self, *args, **kw)
         self.subrepo = kw.get('subrepo')
         self.cause = kw.get('cause')
 
 def annotatesubrepoerror(func):
     def decoratedmethod(self, *args, **kargs):
         try:
             res = func(self, *args, **kargs)
         except SubrepoAbort, ex:
             # This exception has already been handled
             raise ex
         except error.Abort, ex:
             subrepo = subrelpath(self)
             errormsg = str(ex) + ' ' + _('(in subrepo %s)') % subrepo
             # avoid handling this exception by raising a SubrepoAbort exception
             raise SubrepoAbort(errormsg, hint=ex.hint, subrepo=subrepo,
                                cause=sys.exc_info())
         return res
     return decoratedmethod
 
 def state(ctx, ui):
     """return a state dict, mapping subrepo paths configured in .hgsub
     to tuple: (source from .hgsub, revision from .hgsubstate, kind
     (key in types dict))
     """
     p = config.config()
     def read(f, sections=None, remap=None):
         if f in ctx:
             try:
                 data = ctx[f].data()
             except IOError, err:
                 if err.errno != errno.ENOENT:
                     raise
                 # handle missing subrepo spec files as removed
                 ui.warn(_("warning: subrepo spec file %s not found\n") % f)
                 return
             p.parse(f, data, sections, remap, read)
         else:
             raise util.Abort(_("subrepo spec file %s not found") % f)
 
     if '.hgsub' in ctx:
         read('.hgsub')
 
     for path, src in ui.configitems('subpaths'):
         p.set('subpaths', path, src, ui.configsource('subpaths', path))
 
     rev = {}
     if '.hgsubstate' in ctx:
         try:
             for i, l in enumerate(ctx['.hgsubstate'].data().splitlines()):
                 l = l.lstrip()
                 if not l:
                     continue
                 try:
                     revision, path = l.split(" ", 1)
                 except ValueError:
                     raise util.Abort(_("invalid subrepository revision "
                                        "specifier in .hgsubstate line %d")
                                      % (i + 1))
                 rev[path] = revision
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
 
     def remap(src):
         for pattern, repl in p.items('subpaths'):
             # Turn r'C:\foo\bar' into r'C:\\foo\\bar' since re.sub
             # does a string decode.
             repl = repl.encode('string-escape')
             # However, we still want to allow back references to go
             # through unharmed, so we turn r'\\1' into r'\1'. Again,
             # extra escapes are needed because re.sub string decodes.
             repl = re.sub(r'\\\\([0-9]+)', r'\\\1', repl)
             try:
                 src = re.sub(pattern, repl, src, 1)
             except re.error, e:
                 raise util.Abort(_("bad subrepository pattern in %s: %s")
                                  % (p.source('subpaths', pattern), e))
         return src
 
     state = {}
     for path, src in p[''].items():
         kind = 'hg'
         if src.startswith('['):
             if ']' not in src:
                 raise util.Abort(_('missing ] in subrepo source'))
             kind, src = src.split(']', 1)
             kind = kind[1:]
             src = src.lstrip() # strip any extra whitespace after ']'
 
         if not util.url(src).isabs():
             parent = _abssource(ctx._repo, abort=False)
             if parent:
                 parent = util.url(parent)
                 parent.path = posixpath.join(parent.path or '', src)
                 parent.path = posixpath.normpath(parent.path)
                 joined = str(parent)
                 # Remap the full joined path and use it if it changes,
                 # else remap the original source.
                 remapped = remap(joined)
                 if remapped == joined:
                     src = remap(src)
                 else:
                     src = remapped
 
         src = remap(src)
         state[util.pconvert(path)] = (src.strip(), rev.get(path, ''), kind)
 
     return state
 
 def writestate(repo, state):
     """rewrite .hgsubstate in (outer) repo with these subrepo states"""
     lines = ['%s %s\n' % (state[s][1], s) for s in sorted(state)]
     repo.wwrite('.hgsubstate', ''.join(lines), '')
 
 def submerge(repo, wctx, mctx, actx, overwrite):
     """delegated from merge.applyupdates: merging of .hgsubstate file
     in working context, merging context and ancestor context"""
     if mctx == actx: # backwards?
         actx = wctx.p1()
     s1 = wctx.substate
     s2 = mctx.substate
     sa = actx.substate
     sm = {}
 
     repo.ui.debug("subrepo merge %s %s %s\n" % (wctx, mctx, actx))
 
     def debug(s, msg, r=""):
         if r:
             r = "%s:%s:%s" % r
         repo.ui.debug("  subrepo %s: %s %s\n" % (s, msg, r))
 
     for s, l in sorted(s1.iteritems()):
         a = sa.get(s, nullstate)
         ld = l # local state with possible dirty flag for compares
         if wctx.sub(s).dirty():
             ld = (l[0], l[1] + "+")
         if wctx == actx: # overwrite
             a = ld
 
         if s in s2:
             r = s2[s]
             if ld == r or r == a: # no change or local is newer
                 sm[s] = l
                 continue
             elif ld == a: # other side changed
                 debug(s, "other changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             elif ld[0] != r[0]: # sources differ
                 if repo.ui.promptchoice(
                     _(' subrepository sources for %s differ\n'
                       'use (l)ocal source (%s) or (r)emote source (%s)?'
                       '$$ &Local $$ &Remote') % (s, l[0], r[0]), 0):
                     debug(s, "prompt changed, get", r)
                     wctx.sub(s).get(r, overwrite)
                     sm[s] = r
             elif ld[1] == a[1]: # local side is unchanged
                 debug(s, "other side changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             else:
                 debug(s, "both sides changed")
                 option = repo.ui.promptchoice(
                     _(' subrepository %s diverged (local revision: %s, '
                       'remote revision: %s)\n'
                       '(M)erge, keep (l)ocal or keep (r)emote?'
                       '$$ &Merge $$ &Local $$ &Remote')
                     % (s, l[1][:12], r[1][:12]), 0)
                 if option == 0:
                     wctx.sub(s).merge(r)
                     sm[s] = l
                     debug(s, "merge with", r)
                 elif option == 1:
                     sm[s] = l
                     debug(s, "keep local subrepo revision", l)
                 else:
                     wctx.sub(s).get(r, overwrite)
                     sm[s] = r
                     debug(s, "get remote subrepo revision", r)
         elif ld == a: # remote removed, local unchanged
             debug(s, "remote removed, remove")
             wctx.sub(s).remove()
         elif a == nullstate: # not present in remote or ancestor
             debug(s, "local added, keep")
             sm[s] = l
             continue
         else:
             if repo.ui.promptchoice(
                 _(' local changed subrepository %s which remote removed\n'
                   'use (c)hanged version or (d)elete?'
                   '$$ &Changed $$ &Delete') % s, 0):
                 debug(s, "prompt remove")
                 wctx.sub(s).remove()
 
     for s, r in sorted(s2.items()):
         if s in s1:
             continue
         elif s not in sa:
             debug(s, "remote added, get", r)
             mctx.sub(s).get(r)
             sm[s] = r
         elif r != sa[s]:
             if repo.ui.promptchoice(
                 _(' remote changed subrepository %s which local removed\n'
                   'use (c)hanged version or (d)elete?'
                   '$$ &Changed $$ &Delete') % s, 0) == 0:
                 debug(s, "prompt recreate", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
 
     # record merged .hgsubstate
     writestate(repo, sm)
     return sm
 
 def _updateprompt(ui, sub, dirty, local, remote):
     if dirty:
         msg = (_(' subrepository sources for %s differ\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     else:
         msg = (_(' subrepository sources for %s differ (in checked out '
                  'version)\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     return ui.promptchoice(msg, 0)
 
 def reporelpath(repo):
     """return path to this (sub)repo as seen from outermost repo"""
     parent = repo
     while util.safehasattr(parent, '_subparent'):
         parent = parent._subparent
     p = parent.root.rstrip(os.sep)
     return repo.root[len(p) + 1:]
 
 def subrelpath(sub):
     """return path to this subrepo as seen from outermost repo"""
     if util.safehasattr(sub, '_relpath'):
         return sub._relpath
     if not util.safehasattr(sub, '_repo'):
         return sub._path
     return reporelpath(sub._repo)
 
 def _abssource(repo, push=False, abort=True):
     """return pull/push path of repo - either based on parent repo .hgsub info
     or on the top repo config. Abort or return None if no source found."""
     if util.safehasattr(repo, '_subparent'):
         source = util.url(repo._subsource)
         if source.isabs():
             return str(source)
         source.path = posixpath.normpath(source.path)
         parent = _abssource(repo._subparent, push, abort=False)
         if parent:
             parent = util.url(util.pconvert(parent))
             parent.path = posixpath.join(parent.path or '', source.path)
             parent.path = posixpath.normpath(parent.path)
             return str(parent)
     else: # recursion reached top repo
         if util.safehasattr(repo, '_subtoppath'):
             return repo._subtoppath
         if push and repo.ui.config('paths', 'default-push'):
             return repo.ui.config('paths', 'default-push')
         if repo.ui.config('paths', 'default'):
             return repo.ui.config('paths', 'default')
         if repo.sharedpath != repo.path:
             # chop off the .hg component to get the default path form
             return os.path.dirname(repo.sharedpath)
     if abort:
         raise util.Abort(_("default path for subrepository not found"))
 
 def _sanitize(ui, path):
     def v(arg, dirname, names):
         if os.path.basename(dirname).lower() != '.hg':
             return
         for f in names:
             if f.lower() == 'hgrc':
                 ui.warn(
                     _("warning: removing potentially hostile .hg/hgrc in '%s'")
                       % path)
                 os.unlink(os.path.join(dirname, f))
     os.walk(path, v, None)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
 def subrepo(ctx, path):
     """return instance of the right subrepo class for subrepo in path"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     import hg as h
     hg = h
 
     pathutil.pathauditor(ctx._repo.root)(path)
     state = ctx.substate[path]
     if state[2] not in types:
         raise util.Abort(_('unknown subrepo type %s') % state[2])
     return types[state[2]](ctx, path, state[:2])
 
 def newcommitphase(ui, ctx):
     commitphase = phases.newcommitphase(ui)
     substate = getattr(ctx, "substate", None)
     if not substate:
         return commitphase
     check = ui.config('phases', 'checksubrepos', 'follow')
     if check not in ('ignore', 'follow', 'abort'):
         raise util.Abort(_('invalid phases.checksubrepos configuration: %s')
                          % (check))
     if check == 'ignore':
         return commitphase
     maxphase = phases.public
     maxsub = None
     for s in sorted(substate):
         sub = ctx.sub(s)
         subphase = sub.phase(substate[s][1])
         if maxphase < subphase:
             maxphase = subphase
             maxsub = s
     if commitphase < maxphase:
         if check == 'abort':
             raise util.Abort(_("can't commit in %s phase"
                                " conflicting %s from subrepository %s") %
                              (phases.phasenames[commitphase],
                               phases.phasenames[maxphase], maxsub))
         ui.warn(_("warning: changes are committed in"
                   " %s phase from subrepository %s\n") %
                 (phases.phasenames[maxphase], maxsub))
         return maxphase
     return commitphase
 
 # subrepo classes need to implement the following abstract class:
 
 class abstractsubrepo(object):
 
     def storeclean(self, path):
         """
         returns true if the repository has not changed since it was last
         cloned from or pushed to a given repository.
         """
         return False
 
     def dirty(self, ignoreupdate=False):
         """returns true if the dirstate of the subrepo is dirty or does not
         match current stored state. If ignoreupdate is true, only check
         whether the subrepo has uncommitted changes in its dirstate.
         """
         raise NotImplementedError
 
     def basestate(self):
         """current working directory base state, disregarding .hgsubstate
         state and working directory modifications"""
         raise NotImplementedError
 
     def checknested(self, path):
         """check if path is a subrepository within this repository"""
         return False
 
     def commit(self, text, user, date):
         """commit the current changes to the subrepo with the given
         log message. Use given user and date if possible. Return the
         new state of the subrepo.
         """
         raise NotImplementedError
 
     def phase(self, state):
         """returns phase of specified state in the subrepository.
         """
         return phases.public
 
     def remove(self):
         """remove the subrepo
 
         (should verify the dirstate is not dirty first)
         """
         raise NotImplementedError
 
     def get(self, state, overwrite=False):
         """run whatever commands are needed to put the subrepo into
         this state
         """
         raise NotImplementedError
 
     def merge(self, state):
         """merge currently-saved state with the new state."""
         raise NotImplementedError
 
     def push(self, opts):
         """perform whatever action is analogous to 'hg push'
 
         This may be a no-op on some systems.
         """
         raise NotImplementedError
 
     def add(self, ui, match, dryrun, listsubrepos, prefix, explicitonly):
         return []
 
     def status(self, rev2, **opts):
         return [], [], [], [], [], [], []
 
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         pass
 
     def outgoing(self, ui, dest, opts):
         return 1
 
     def incoming(self, ui, source, opts):
         return 1
 
     def files(self):
         """return filename iterator"""
         raise NotImplementedError
 
     def filedata(self, name):
         """return file data"""
         raise NotImplementedError
 
     def fileflags(self, name):
         """return file flags"""
         return ''
 
     def archive(self, ui, archiver, prefix, match=None):
         if match is not None:
             files = [f for f in self.files() if match(f)]
         else:
             files = self.files()
         total = len(files)
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0,
                     unit=_('files'), total=total)
         for i, name in enumerate(files):
             flags = self.fileflags(name)
             mode = 'x' in flags and 0755 or 0644
             symlink = 'l' in flags
             archiver.addfile(os.path.join(prefix, self._path, name),
                              mode, symlink, self.filedata(name))
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'), total=total)
         ui.progress(_('archiving (%s)') % relpath, None)
         return total
 
     def walk(self, match):
         '''
         walk recursively through the directory tree, finding all files
         matched by the match function
         '''
         pass
 
     def forget(self, ui, match, prefix):
         return ([], [])
 
     def revert(self, ui, substate, *pats, **opts):
         ui.warn('%s: reverting %s subrepos is unsupported\n' \
             % (substate[0], substate[2]))
         return []
 
 class hgsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         r = ctx._repo
         root = r.wjoin(path)
         create = False
         if not os.path.exists(os.path.join(root, '.hg')):
             create = True
             util.makedirs(root)
         self._repo = hg.repository(r.baseui, root, create=create)
         for s, k in [('ui', 'commitsubrepos')]:
             v = r.ui.config(s, k)
             if v:
                 self._repo.ui.setconfig(s, k, v)
         self._repo.ui.setconfig('ui', '_usedassubrepo', 'True')
         self._initrepo(r, state[0], create)
 
     def storeclean(self, path):
         clean = True
         lock = self._repo.lock()
         itercache = self._calcstorehash(path)
         try:
             for filehash in self._readstorehashcache(path):
                 if filehash != itercache.next():
                     clean = False
                     break
         except StopIteration:
             # the cached and current pull states have a different size
             clean = False
         if clean:
             try:
                 itercache.next()
                 # the cached and current pull states have a different size
                 clean = False
             except StopIteration:
                 pass
         lock.release()
         return clean
 
     def _calcstorehash(self, remotepath):
         '''calculate a unique "store hash"
 
         This method is used to to detect when there are changes that may
         require a push to a given remote path.'''
         # sort the files that will be hashed in increasing (likely) file size
         filelist = ('bookmarks', 'store/phaseroots', 'store/00changelog.i')
         yield '# %s\n' % _expandedabspath(remotepath)
         for relname in filelist:
             absname = os.path.normpath(self._repo.join(relname))
             yield '%s = %s\n' % (relname, _calcfilehash(absname))
 
     def _getstorehashcachepath(self, remotepath):
         '''get a unique path for the store hash cache'''
         return self._repo.join(os.path.join(
             'cache', 'storehash', _getstorehashcachename(remotepath)))
 
     def _readstorehashcache(self, remotepath):
         '''read the store hash cache for a given remote repository'''
         cachefile = self._getstorehashcachepath(remotepath)
         if not os.path.exists(cachefile):
             return ''
         fd = open(cachefile, 'r')
         pullstate = fd.readlines()
         fd.close()
         return pullstate
 
     def _cachestorehash(self, remotepath):
         '''cache the current store hash
 
         Each remote repo requires its own store hash cache, because a subrepo
         store may be "clean" versus a given remote repo, but not versus another
         '''
         cachefile = self._getstorehashcachepath(remotepath)
         lock = self._repo.lock()
         storehash = list(self._calcstorehash(remotepath))
         cachedir = os.path.dirname(cachefile)
         if not os.path.exists(cachedir):
             util.makedirs(cachedir, notindexed=True)
         fd = open(cachefile, 'w')
         fd.writelines(storehash)
         fd.close()
         lock.release()
 
     @annotatesubrepoerror
     def _initrepo(self, parentrepo, source, create):
         self._repo._subparent = parentrepo
         self._repo._subsource = source
 
         if create:
             fp = self._repo.opener("hgrc", "w", text=True)
             fp.write('[paths]\n')
 
             def addpathconfig(key, value):
                 if value:
                     fp.write('%s = %s\n' % (key, value))
                     self._repo.ui.setconfig('paths', key, value)
 
             defpath = _abssource(self._repo, abort=False)
             defpushpath = _abssource(self._repo, True, abort=False)
             addpathconfig('default', defpath)
             if defpath != defpushpath:
                 addpathconfig('default-push', defpushpath)
             fp.close()
 
     @annotatesubrepoerror
     def add(self, ui, match, dryrun, listsubrepos, prefix, explicitonly):
         return cmdutil.add(ui, self._repo, match, dryrun, listsubrepos,
                            os.path.join(prefix, self._path), explicitonly)
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         try:
             rev1 = self._state[1]
             ctx1 = self._repo[rev1]
             ctx2 = self._repo[rev2]
             return self._repo.status(ctx1, ctx2, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
             return [], [], [], [], [], [], []
 
     @annotatesubrepoerror
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         try:
             node1 = node.bin(self._state[1])
             # We currently expect node2 to come from substate and be
             # in hex format
             if node2 is not None:
                 node2 = node.bin(node2)
             cmdutil.diffordiffstat(ui, self._repo, diffopts,
                                    node1, node2, match,
                                    prefix=posixpath.join(prefix, self._path),
                                    listsubrepos=True, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
 
     @annotatesubrepoerror
     def archive(self, ui, archiver, prefix, match=None):
         self._get(self._state + ('hg',))
         total = abstractsubrepo.archive(self, ui, archiver, prefix, match)
         rev = self._state[1]
         ctx = self._repo[rev]
         for subpath in ctx.substate:
             s = subrepo(ctx, subpath)
             submatch = matchmod.narrowmatcher(subpath, match)
             total += s.archive(
                 ui, archiver, os.path.join(prefix, self._path), submatch)
         return total
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False):
         r = self._state[1]
         if r == '' and not ignoreupdate: # no state recorded
             return True
         w = self._repo[None]
         if r != w.p1().hex() and not ignoreupdate:
             # different version checked out
             return True
         return w.dirty() # working directory changed
 
     def basestate(self):
         return self._repo['.'].hex()
 
     def checknested(self, path):
         return self._repo._checknested(self._repo.wjoin(path))
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # don't bother committing in the subrepo if it's only been
         # updated
         if not self.dirty(True):
             return self._repo['.'].hex()
         self._repo.ui.debug("committing subrepo %s\n" % subrelpath(self))
         n = self._repo.commit(text, user, date)
         if not n:
             return self._repo['.'].hex() # different version checked out
         return node.hex(n)
 
     @annotatesubrepoerror
     def phase(self, state):
         return self._repo[state].phase()
 
     @annotatesubrepoerror
     def remove(self):
         # we can't fully delete the repository as it may contain
         # local-only history
         self._repo.ui.note(_('removing subrepo %s\n') % subrelpath(self))
         hg.clean(self._repo, node.nullid, False)
 
     def _get(self, state):
         source, revision, kind = state
         if revision in self._repo.unfiltered():
             return True
         self._repo._subsource = source
         srcurl = _abssource(self._repo)
         other = hg.peer(self._repo, {}, srcurl)
         if len(self._repo) == 0:
             self._repo.ui.status(_('cloning subrepo %s from %s\n')
                                  % (subrelpath(self), srcurl))
             parentrepo = self._repo._subparent
             shutil.rmtree(self._repo.path)
             other, cloned = hg.clone(self._repo._subparent.baseui, {},
                                      other, self._repo.root,
                                      update=False)
             self._repo = cloned.local()
             self._initrepo(parentrepo, source, create=True)
             self._cachestorehash(srcurl)
         else:
             self._repo.ui.status(_('pulling subrepo %s from %s\n')
                                  % (subrelpath(self), srcurl))
             cleansub = self.storeclean(srcurl)
             remotebookmarks = other.listkeys('bookmarks')
             self._repo.pull(other)
             bookmarks.updatefromremote(self._repo.ui, self._repo,
                                        remotebookmarks, srcurl)
             if cleansub:
                 # keep the repo clean after pull
                 self._cachestorehash(srcurl)
         return False
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         inrepo = self._get(state)
         source, revision, kind = state
         repo = self._repo
         repo.ui.debug("getting subrepo %s\n" % self._path)
         if inrepo:
             urepo = repo.unfiltered()
             ctx = urepo[revision]
             if ctx.hidden():
                 urepo.ui.warn(
                     _('revision %s in subrepo %s is hidden\n') \
                     % (revision[0:12], self._path))
                 repo = urepo
         hg.updaterepo(repo, revision, overwrite)
 
     @annotatesubrepoerror
     def merge(self, state):
         self._get(state)
         cur = self._repo['.']
         dst = self._repo[state[1]]
         anc = dst.ancestor(cur)
 
         def mergefunc():
             if anc == cur and dst.branch() == cur.branch():
                 self._repo.ui.debug("updating subrepo %s\n" % subrelpath(self))
                 hg.update(self._repo, state[1])
             elif anc == dst:
                 self._repo.ui.debug("skipping subrepo %s\n" % subrelpath(self))
             else:
                 self._repo.ui.debug("merging subrepo %s\n" % subrelpath(self))
                 hg.merge(self._repo, state[1], remind=False)
 
         wctx = self._repo[None]
         if self.dirty():
             if anc != dst:
                 if _updateprompt(self._repo.ui, self, wctx.dirty(), cur, dst):
                     mergefunc()
             else:
                 mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
         newbranch = opts.get('new_branch')
         ssh = opts.get('ssh')
 
         # push subrepos depth-first for coherent ordering
         c = self._repo['']
         subs = c.substate # only repos that are committed
         for s in sorted(subs):
             if c.sub(s).push(opts) == 0:
                 return False
 
         dsturl = _abssource(self._repo, True)
         if not force:
             if self.storeclean(dsturl):
                 self._repo.ui.status(
                     _('no changes made to subrepo %s since last push to %s\n')
                     % (subrelpath(self), dsturl))
                 return None
         self._repo.ui.status(_('pushing subrepo %s to %s\n') %
             (subrelpath(self), dsturl))
         other = hg.peer(self._repo, {'ssh': ssh}, dsturl)
         res = self._repo.push(other, force, newbranch=newbranch)
 
         # the repo is now clean
         self._cachestorehash(dsturl)
         return res
 
     @annotatesubrepoerror
     def outgoing(self, ui, dest, opts):
         return hg.outgoing(ui, self._repo, _abssource(self._repo, True), opts)
 
     @annotatesubrepoerror
     def incoming(self, ui, source, opts):
         return hg.incoming(ui, self._repo, _abssource(self._repo, False), opts)
 
     @annotatesubrepoerror
     def files(self):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.manifest()
 
     def filedata(self, name):
         rev = self._state[1]
         return self._repo[rev][name].data()
 
     def fileflags(self, name):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.flags(name)
 
     def walk(self, match):
         ctx = self._repo[None]
         return ctx.walk(match)
 
     @annotatesubrepoerror
     def forget(self, ui, match, prefix):
         return cmdutil.forget(ui, self._repo, match,
                               os.path.join(prefix, self._path), True)
 
     @annotatesubrepoerror
     def revert(self, ui, substate, *pats, **opts):
         # reverting a subrepo is a 2 step process:
         # 1. if the no_backup is not set, revert all modified
         #    files inside the subrepo
         # 2. update the subrepo to the revision specified in
         #    the corresponding substate dictionary
         ui.status(_('reverting subrepo %s\n') % substate[0])
         if not opts.get('no_backup'):
             # Revert all files on the subrepo, creating backups
             # Note that this will not recursively revert subrepos
             # We could do it if there was a set:subrepos() predicate
             opts = opts.copy()
             opts['date'] = None
             opts['rev'] = substate[1]
 
             pats = []
             if not opts.get('all'):
                 pats = ['set:modified()']
             self.filerevert(ui, *pats, **opts)
 
         # Update the repo to the revision specified in the given substate
         self.get(substate, overwrite=True)
 
     def filerevert(self, ui, *pats, **opts):
         ctx = self._repo[opts['rev']]
         parents = self._repo.dirstate.parents()
         if opts.get('all'):
             pats = ['set:modified()']
         else:
             pats = []
         cmdutil.revert(ui, self._repo, ctx, parents, *pats, **opts)
 
 class svnsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         self._ctx = ctx
         self._ui = ctx._repo.ui
         self._exe = util.findexe('svn')
         if not self._exe:
             raise util.Abort(_("'svn' executable not found for subrepo '%s'")
                              % self._path)
 
     def _svncommand(self, commands, filename='', failok=False):
         cmd = [self._exe]
         extrakw = {}
         if not self._ui.interactive():
             # Making stdin be a pipe should prevent svn from behaving
             # interactively even if we can't pass --non-interactive.
             extrakw['stdin'] = subprocess.PIPE
             # Starting in svn 1.5 --non-interactive is a global flag
             # instead of being per-command, but we need to support 1.4 so
             # we have to be intelligent about what commands take
             # --non-interactive.
             if commands[0] in ('update', 'checkout', 'commit'):
                 cmd.append('--non-interactive')
         cmd.extend(commands)
         if filename is not None:
             path = os.path.join(self._ctx._repo.origroot, self._path, filename)
             cmd.append(path)
         env = dict(os.environ)
         # Avoid localized output, preserve current locale for everything else.
         lc_all = env.get('LC_ALL')
         if lc_all:
             env['LANG'] = lc_all
             del env['LC_ALL']
         env['LC_MESSAGES'] = 'C'
         p = subprocess.Popen(cmd, bufsize=-1, close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                               universal_newlines=True, env=env, **extrakw)
         stdout, stderr = p.communicate()
         stderr = stderr.strip()
         if not failok:
             if p.returncode:
                 raise util.Abort(stderr or 'exited with code %d' % p.returncode)
             if stderr:
                 self._ui.warn(stderr + '\n')
         return stdout, stderr
 
     @propertycache
     def _svnversion(self):
         output, err = self._svncommand(['--version', '--quiet'], filename=None)
         m = re.search(r'^(\d+)\.(\d+)', output)
         if not m:
             raise util.Abort(_('cannot retrieve svn tool version'))
         return (int(m.group(1)), int(m.group(2)))
 
     def _wcrevs(self):
         # Get the working directory revision as well as the last
         # commit revision so we can compare the subrepo state with
         # both. We used to store the working directory one.
         output, err = self._svncommand(['info', '--xml'])
         doc = xml.dom.minidom.parseString(output)
         entries = doc.getElementsByTagName('entry')
         lastrev, rev = '0', '0'
         if entries:
             rev = str(entries[0].getAttribute('revision')) or '0'
             commits = entries[0].getElementsByTagName('commit')
             if commits:
                 lastrev = str(commits[0].getAttribute('revision')) or '0'
         return (lastrev, rev)
 
     def _wcrev(self):
         return self._wcrevs()[0]
 
     def _wcchanged(self):
         """Return (changes, extchanges, missing) where changes is True
         if the working directory was changed, extchanges is
         True if any of these changes concern an external entry and missing
         is True if any change is a missing entry.
         """
         output, err = self._svncommand(['status', '--xml'])
         externals, changes, missing = [], [], []
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             s = e.getElementsByTagName('wc-status')
             if not s:
                 continue
             item = s[0].getAttribute('item')
             props = s[0].getAttribute('props')
             path = e.getAttribute('path')
             if item == 'external':
                 externals.append(path)
             elif item == 'missing':
                 missing.append(path)
             if (item not in ('', 'normal', 'unversioned', 'external')
                 or props not in ('', 'none', 'normal')):
                 changes.append(path)
         for path in changes:
             for ext in externals:
                 if path == ext or path.startswith(ext + os.sep):
                     return True, True, bool(missing)
         return bool(changes), False, bool(missing)
 
     def dirty(self, ignoreupdate=False):
         if not self._wcchanged()[0]:
             if self._state[1] in self._wcrevs() or ignoreupdate:
                 return False
         return True
 
     def basestate(self):
         lastrev, rev = self._wcrevs()
         if lastrev != rev:
             # Last committed rev is not the same than rev. We would
             # like to take lastrev but we do not know if the subrepo
             # URL exists at lastrev.  Test it and fallback to rev it
             # is not there.
             try:
                 self._svncommand(['list', '%s@%s' % (self._state[0], lastrev)])
                 return lastrev
             except error.Abort:
                 pass
         return rev
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # user and date are out of our hands since svn is centralized
         changed, extchanged, missing = self._wcchanged()
         if not changed:
             return self.basestate()
         if extchanged:
             # Do not try to commit externals
             raise util.Abort(_('cannot commit svn externals'))
         if missing:
             # svn can commit with missing entries but aborting like hg
             # seems a better approach.
             raise util.Abort(_('cannot commit missing svn entries'))
         commitinfo, err = self._svncommand(['commit', '-m', text])
         self._ui.status(commitinfo)
         newrev = re.search('Committed revision ([0-9]+).', commitinfo)
         if not newrev:
             if not commitinfo.strip():
                 # Sometimes, our definition of "changed" differs from
                 # svn one. For instance, svn ignores missing files
                 # when committing. If there are only missing files, no
                 # commit is made, no output and no error code.
                 raise util.Abort(_('failed to commit svn changes'))
             raise util.Abort(commitinfo.splitlines()[-1])
         newrev = newrev.groups()[0]
         self._ui.status(self._svncommand(['update', '-r', newrev])[0])
         return newrev
 
     @annotatesubrepoerror
     def remove(self):
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
-                            'it has changes.\n' % self._path))
+                            'it has changes.\n') % self._path)
             return
         self._ui.note(_('removing subrepo %s\n') % self._path)
 
         def onerror(function, path, excinfo):
             if function is not os.remove:
                 raise
             # read-only files cannot be unlinked under Windows
             s = os.stat(path)
             if (s.st_mode & stat.S_IWRITE) != 0:
                 raise
             os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
             os.remove(path)
 
         path = self._ctx._repo.wjoin(self._path)
         shutil.rmtree(path, onerror=onerror)
         try:
             os.removedirs(os.path.dirname(path))
         except OSError:
             pass
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         if overwrite:
             self._svncommand(['revert', '--recursive'])
         args = ['checkout']
         if self._svnversion >= (1, 5):
             args.append('--force')
         # The revision must be specified at the end of the URL to properly
         # update to a directory which has since been deleted and recreated.
         args.append('%s@%s' % (state[0], state[1]))
         status, err = self._svncommand(args, failok=True)
         _sanitize(self._ui, self._path)
         if not re.search('Checked out revision [0-9]+.', status):
             if ('is already a working copy for a different URL' in err
                 and (self._wcchanged()[:2] == (False, False))):
                 # obstructed but clean working copy, so just blow it away.
                 self.remove()
                 self.get(state, overwrite=False)
                 return
             raise util.Abort((status or err).splitlines()[-1])
         self._ui.status(status)
 
     @annotatesubrepoerror
     def merge(self, state):
         old = self._state[1]
         new = state[1]
         wcrev = self._wcrev()
         if new != wcrev:
             dirty = old == wcrev or self._wcchanged()[0]
             if _updateprompt(self._ui, self, dirty, wcrev, new):
                 self.get(state, False)
 
     def push(self, opts):
         # push is a no-op for SVN
         return True
 
     @annotatesubrepoerror
     def files(self):
         output = self._svncommand(['list', '--recursive', '--xml'])[0]
         doc = xml.dom.minidom.parseString(output)
         paths = []
         for e in doc.getElementsByTagName('entry'):
             kind = str(e.getAttribute('kind'))
             if kind != 'file':
                 continue
             name = ''.join(c.data for c
                            in e.getElementsByTagName('name')[0].childNodes
                            if c.nodeType == c.TEXT_NODE)
             paths.append(name.encode('utf-8'))
         return paths
 
     def filedata(self, name):
         return self._svncommand(['cat'], name)[0]
 
 
 class gitsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._state = state
         self._ctx = ctx
         self._path = path
         self._relpath = os.path.join(reporelpath(ctx._repo), path)
         self._abspath = ctx._repo.wjoin(path)
         self._subparent = ctx._repo
         self._ui = ctx._repo.ui
         self._ensuregit()
 
     def _ensuregit(self):
         try:
             self._gitexecutable = 'git'
             out, err = self._gitnodir(['--version'])
         except OSError, e:
             if e.errno != 2 or os.name != 'nt':
                 raise
             self._gitexecutable = 'git.cmd'
             out, err = self._gitnodir(['--version'])
         m = re.search(r'^git version (\d+)\.(\d+)', out)
         if not m:
             self._ui.warn(_('cannot retrieve git version\n'))
             return
         version = (int(m.group(1)), int(m.group(2)))
         # git 1.4.0 can't work at all, but 1.5.X can in at least some cases,
         # despite the docstring comment.  For now, error on 1.4.0, warn on
         # 1.5.0 but attempt to continue.
         if version < (1, 5):
             raise util.Abort(_('git subrepo requires at least 1.6.0 or later'))
         elif version < (1, 6):
             self._ui.warn(_('git subrepo requires at least 1.6.0 or later\n'))
 
     def _gitcommand(self, commands, env=None, stream=False):
         return self._gitdir(commands, env=env, stream=stream)[0]
 
     def _gitdir(self, commands, env=None, stream=False):
         return self._gitnodir(commands, env=env, stream=stream,
                               cwd=self._abspath)
 
     def _gitnodir(self, commands, env=None, stream=False, cwd=None):
         """Calls the git command
 
         The methods tries to call the git command. versions prior to 1.6.0
         are not supported and very probably fail.
         """
         self._ui.debug('%s: git %s\n' % (self._relpath, ' '.join(commands)))
         # unless ui.quiet is set, print git's stderr,
         # which is mostly progress and useful info
         errpipe = None
         if self._ui.quiet:
             errpipe = open(os.devnull, 'w')
         p = subprocess.Popen([self._gitexecutable] + commands, bufsize=-1,
                              cwd=cwd, env=env, close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=errpipe)
         if stream:
             return p.stdout, None
 
         retdata = p.stdout.read().strip()
         # wait for the child to exit to avoid race condition.
         p.wait()
 
         if p.returncode != 0 and p.returncode != 1:
             # there are certain error codes that are ok
             command = commands[0]
             if command in ('cat-file', 'symbolic-ref'):
                 return retdata, p.returncode
             # for all others, abort
             raise util.Abort('git %s error %d in %s' %
                              (command, p.returncode, self._relpath))
 
         return retdata, p.returncode
 
     def _gitmissing(self):
         return not os.path.exists(os.path.join(self._abspath, '.git'))
 
     def _gitstate(self):
         return self._gitcommand(['rev-parse', 'HEAD'])
 
     def _gitcurrentbranch(self):
         current, err = self._gitdir(['symbolic-ref', 'HEAD', '--quiet'])
         if err:
             current = None
         return current
 
     def _gitremote(self, remote):
         out = self._gitcommand(['remote', 'show', '-n', remote])
         line = out.split('\n')[1]
         i = line.index('URL: ') + len('URL: ')
         return line[i:]
 
     def _githavelocally(self, revision):
         out, code = self._gitdir(['cat-file', '-e', revision])
         return code == 0
 
     def _gitisancestor(self, r1, r2):
         base = self._gitcommand(['merge-base', r1, r2])
         return base == r1
 
     def _gitisbare(self):
         return self._gitcommand(['config', '--bool', 'core.bare']) == 'true'
 
     def _gitupdatestat(self):
         """This must be run before git diff-index.
         diff-index only looks at changes to file stat;
         this command looks at file contents and updates the stat."""
         self._gitcommand(['update-index', '-q', '--refresh'])
 
     def _gitbranchmap(self):
         '''returns 2 things:
         a map from git branch to revision
         a map from revision to branches'''
         branch2rev = {}
         rev2branch = {}
 
         out = self._gitcommand(['for-each-ref', '--format',
                                 '%(objectname) %(refname)'])
         for line in out.split('\n'):
             revision, ref = line.split(' ')
             if (not ref.startswith('refs/heads/') and
                 not ref.startswith('refs/remotes/')):
                 continue
             if ref.startswith('refs/remotes/') and ref.endswith('/HEAD'):
                 continue # ignore remote/HEAD redirects
             branch2rev[ref] = revision
             rev2branch.setdefault(revision, []).append(ref)
         return branch2rev, rev2branch
 
     def _gittracking(self, branches):
         'return map of remote branch to local tracking branch'
         # assumes no more than one local tracking branch for each remote
         tracking = {}
         for b in branches:
             if b.startswith('refs/remotes/'):
                 continue
             bname = b.split('/', 2)[2]
             remote = self._gitcommand(['config', 'branch.%s.remote' % bname])
             if remote:
                 ref = self._gitcommand(['config', 'branch.%s.merge' % bname])
                 tracking['refs/remotes/%s/%s' %
                          (remote, ref.split('/', 2)[2])] = b
         return tracking
 
     def _abssource(self, source):
         if '://' not in source:
             # recognize the scp syntax as an absolute source
             colon = source.find(':')
             if colon != -1 and '/' not in source[:colon]:
                 return source
         self._subsource = source
         return _abssource(self)
 
     def _fetch(self, source, revision):
         if self._gitmissing():
             source = self._abssource(source)
             self._ui.status(_('cloning subrepo %s from %s\n') %
                             (self._relpath, source))
             self._gitnodir(['clone', source, self._abspath])
         if self._githavelocally(revision):
             return
         self._ui.status(_('pulling subrepo %s from %s\n') %
                         (self._relpath, self._gitremote('origin')))
         # try only origin: the originally cloned repo
         self._gitcommand(['fetch'])
         if not self._githavelocally(revision):
             raise util.Abort(_("revision %s does not exist in subrepo %s\n") %
                                (revision, self._relpath))
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False):
         if self._gitmissing():
             return self._state[1] != ''
         if self._gitisbare():
             return True
         if not ignoreupdate and self._state[1] != self._gitstate():
             # different version checked out
             return True
         # check for staged changes or modified files; ignore untracked files
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
         return code == 1
 
     def basestate(self):
         return self._gitstate()
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         source, revision, kind = state
         if not revision:
             self.remove()
             return
         self._fetch(source, revision)
         # if the repo was set to be bare, unbare it
         if self._gitisbare():
             self._gitcommand(['config', 'core.bare', 'false'])
             if self._gitstate() == revision:
                 self._gitcommand(['reset', '--hard', 'HEAD'])
                 return
         elif self._gitstate() == revision:
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # reset --hard will otherwise throw away files added for commit,
                 # not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 self._gitcommand(['reset', '--hard', 'HEAD'])
             return
         branch2rev, rev2branch = self._gitbranchmap()
 
         def checkout(args):
             cmd = ['checkout']
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # the -f option will otherwise throw away files added for
                 # commit, not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 cmd.append('-f')
             self._gitcommand(cmd + args)
             _sanitize(self._ui, self._path)
 
         def rawcheckout():
             # no branch to checkout, check it out with no branch
             self._ui.warn(_('checking out detached HEAD in subrepo %s\n') %
                           self._relpath)
             self._ui.warn(_('check out a git branch if you intend '
                             'to make changes\n'))
             checkout(['-q', revision])
 
         if revision not in rev2branch:
             rawcheckout()
             return
         branches = rev2branch[revision]
         firstlocalbranch = None
         for b in branches:
             if b == 'refs/heads/master':
                 # master trumps all other branches
                 checkout(['refs/heads/master'])
                 return
             if not firstlocalbranch and not b.startswith('refs/remotes/'):
                 firstlocalbranch = b
         if firstlocalbranch:
             checkout([firstlocalbranch])
             return
 
         tracking = self._gittracking(branch2rev.keys())
         # choose a remote branch already tracked if possible
         remote = branches[0]
         if remote not in tracking:
             for b in branches:
                 if b in tracking:
                     remote = b
                     break
 
         if remote not in tracking:
             # create a new local tracking branch
             local = remote.split('/', 3)[3]
             checkout(['-b', local, remote])
         elif self._gitisancestor(branch2rev[tracking[remote]], remote):
             # When updating to a tracked remote branch,
             # if the local tracking branch is downstream of it,
             # a normal `git pull` would have performed a "fast-forward merge"
             # which is equivalent to updating the local branch to the remote.
             # Since we are only looking at branching at update, we need to
             # detect this situation and perform this action lazily.
             if tracking[remote] != self._gitcurrentbranch():
                 checkout([tracking[remote]])
             self._gitcommand(['merge', '--ff', remote])
         else:
             # a real merge would be required, just checkout the revision
             rawcheckout()
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         cmd = ['commit', '-a', '-m', text]
         env = os.environ.copy()
         if user:
             cmd += ['--author', user]
         if date:
             # git's date parser silently ignores when seconds < 1e9
             # convert to ISO8601
             env['GIT_AUTHOR_DATE'] = util.datestr(date,
                                                   '%Y-%m-%dT%H:%M:%S %1%2')
         self._gitcommand(cmd, env=env)
         # make sure commit works otherwise HEAD might not exist under certain
         # circumstances
         return self._gitstate()
 
     @annotatesubrepoerror
     def merge(self, state):
         source, revision, kind = state
         self._fetch(source, revision)
         base = self._gitcommand(['merge-base', revision, self._state[1]])
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
 
         def mergefunc():
             if base == revision:
                 self.get(state) # fast forward merge
             elif base != self._state[1]:
                 self._gitcommand(['merge', '--no-commit', revision])
             _sanitize(self._ui, self._path)
 
         if self.dirty():
             if self._gitstate() != revision:
                 dirty = self._gitstate() == self._state[1] or code != 0
                 if _updateprompt(self._ui, self, dirty,
                                  self._state[1][:7], revision[:7]):
                     mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
 
         if not self._state[1]:
             return True
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         # if a branch in origin contains the revision, nothing to do
         branch2rev, rev2branch = self._gitbranchmap()
         if self._state[1] in rev2branch:
             for b in rev2branch[self._state[1]]:
                 if b.startswith('refs/remotes/origin/'):
                     return True
         for b, revision in branch2rev.iteritems():
             if b.startswith('refs/remotes/origin/'):
                 if self._gitisancestor(self._state[1], revision):
                     return True
         # otherwise, try to push the currently checked out branch
         cmd = ['push']
         if force:
             cmd.append('--force')
 
         current = self._gitcurrentbranch()
         if current:
             # determine if the current branch is even useful
             if not self._gitisancestor(self._state[1], current):
                 self._ui.warn(_('unrelated git branch checked out '
                                 'in subrepo %s\n') % self._relpath)
                 return False
             self._ui.status(_('pushing branch %s of subrepo %s\n') %
                             (current.split('/', 2)[2], self._relpath))
             self._gitcommand(cmd + ['origin', current])
             return True
         else:
             self._ui.warn(_('no branch checked out in subrepo %s\n'
                             'cannot push revision %s\n') %
                           (self._relpath, self._state[1]))
             return False
 
     @annotatesubrepoerror
     def remove(self):
         if self._gitmissing():
             return
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n') % self._relpath)
             return
         # we can't fully delete the repository as it may contain
         # local-only history
         self._ui.note(_('removing subrepo %s\n') % self._relpath)
         self._gitcommand(['config', 'core.bare', 'true'])
         for f in os.listdir(self._abspath):
             if f == '.git':
                 continue
             path = os.path.join(self._abspath, f)
             if os.path.isdir(path) and not os.path.islink(path):
                 shutil.rmtree(path)
             else:
                 os.remove(path)
 
     def archive(self, ui, archiver, prefix, match=None):
         total = 0
         source, revision = self._state
         if not revision:
             return total
         self._fetch(source, revision)
 
         # Parse git's native archive command.
         # This should be much faster than manually traversing the trees
         # and objects with many subprocess calls.
         tarstream = self._gitcommand(['archive', revision], stream=True)
         tar = tarfile.open(fileobj=tarstream, mode='r|')
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0, unit=_('files'))
         for i, info in enumerate(tar):
             if info.isdir():
                 continue
             if match and not match(info.name):
                 continue
             if info.issym():
                 data = info.linkname
             else:
                 data = tar.extractfile(info).read()
             archiver.addfile(os.path.join(prefix, self._path, info.name),
                              info.mode, info.issym(), data)
             total += 1
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'))
         ui.progress(_('archiving (%s)') % relpath, None)
         return total
 
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         rev1 = self._state[1]
         if self._gitmissing() or not rev1:
             # if the repo is missing, return no results
             return [], [], [], [], [], [], []
         modified, added, removed = [], [], []
         self._gitupdatestat()
         if rev2:
             command = ['diff-tree', rev1, rev2]
         else:
             command = ['diff-index', rev1]
         out = self._gitcommand(command)
         for line in out.split('\n'):
             tab = line.find('\t')
             if tab == -1:
                 continue
             status, f = line[tab - 1], line[tab + 1:]
             if status == 'M':
                 modified.append(f)
             elif status == 'A':
                 added.append(f)
             elif status == 'D':
                 removed.append(f)
 
         deleted = unknown = ignored = clean = []
         return modified, added, removed, deleted, unknown, ignored, clean
 
 types = {
     'hg': hgsubrepo,
     'svn': svnsubrepo,
     'git': gitsubrepo,
     }