py3: convert to next() function

next(..) was introduced in py2.6 and .next() is not available in py3

https://docs.python.org/2/library/functions.html#next

contrib/synthrepo.py

@@ -1,516 +1,516 b''
 # synthrepo.py - repo synthesis
 #
 # Copyright 2012 Facebook
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''synthesize structurally interesting change history
 
 This extension is useful for creating a repository with properties
 that are statistically similar to an existing repository. During
 analysis, a simple probability table is constructed from the history
 of an existing repository.  During synthesis, these properties are
 reconstructed.
 
 Properties that are analyzed and synthesized include the following:
 
 - Lines added or removed when an existing file is modified
 - Number and sizes of files added
 - Number of files removed
 - Line lengths
 - Topological distance to parent changeset(s)
 - Probability of a commit being a merge
 - Probability of a newly added file being added to a new directory
 - Interarrival time, and time zone, of commits
 - Number of files in each directory
 
 A few obvious properties that are not currently handled realistically:
 
 - Merges are treated as regular commits with two parents, which is not
   realistic
 - Modifications are not treated as operations on hunks of lines, but
   as insertions and deletions of randomly chosen single lines
 - Committer ID (always random)
 - Executability of files
 - Symlinks and binary files are ignored
 '''
 
 from __future__ import absolute_import
 import bisect
 import collections
 import itertools
 import json
 import os
 import random
 import sys
 import time
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     nullrev,
     short,
 )
 from mercurial import (
     cmdutil,
     context,
     error,
     hg,
     patch,
     scmutil,
     util,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 newfile = set(('new fi', 'rename', 'copy f', 'copy t'))
 
 def zerodict():
     return collections.defaultdict(lambda: 0)
 
 def roundto(x, k):
     if x > k * 2:
         return int(round(x / float(k)) * k)
     return int(round(x))
 
 def parsegitdiff(lines):
     filename, mar, lineadd, lineremove = None, None, zerodict(), 0
     binary = False
     for line in lines:
         start = line[:6]
         if start == 'diff -':
             if filename:
                 yield filename, mar, lineadd, lineremove, binary
             mar, lineadd, lineremove, binary = 'm', zerodict(), 0, False
             filename = patch.gitre.match(line).group(1)
         elif start in newfile:
             mar = 'a'
         elif start == 'GIT bi':
             binary = True
         elif start == 'delete':
             mar = 'r'
         elif start:
             s = start[0]
             if s == '-' and not line.startswith('--- '):
                 lineremove += 1
             elif s == '+' and not line.startswith('+++ '):
                 lineadd[roundto(len(line) - 1, 5)] += 1
     if filename:
         yield filename, mar, lineadd, lineremove, binary
 
 @command('analyze',
          [('o', 'output', '', _('write output to given file'), _('FILE')),
           ('r', 'rev', [], _('analyze specified revisions'), _('REV'))],
          _('hg analyze'), optionalrepo=True)
 def analyze(ui, repo, *revs, **opts):
     '''create a simple model of a repository to use for later synthesis
 
     This command examines every changeset in the given range (or all
     of history if none are specified) and creates a simple statistical
     model of the history of the repository. It also measures the directory
     structure of the repository as checked out.
 
     The model is written out to a JSON file, and can be used by
     :hg:`synthesize` to create or augment a repository with synthetic
     commits that have a structure that is statistically similar to the
     analyzed repository.
     '''
     root = repo.root
     if not root.endswith(os.path.sep):
         root += os.path.sep
 
     revs = list(revs)
     revs.extend(opts['rev'])
     if not revs:
         revs = [':']
 
     output = opts['output']
     if not output:
         output = os.path.basename(root) + '.json'
 
     if output == '-':
         fp = sys.stdout
     else:
         fp = open(output, 'w')
 
     # Always obtain file counts of each directory in the given root directory.
     def onerror(e):
         ui.warn(_('error walking directory structure: %s\n') % e)
 
     dirs = {}
     rootprefixlen = len(root)
     for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):
         dirpathfromroot = dirpath[rootprefixlen:]
         dirs[dirpathfromroot] = len(filenames)
         if '.hg' in dirnames:
             dirnames.remove('.hg')
 
     lineschanged = zerodict()
     children = zerodict()
     p1distance = zerodict()
     p2distance = zerodict()
     linesinfilesadded = zerodict()
     fileschanged = zerodict()
     filesadded = zerodict()
     filesremoved = zerodict()
     linelengths = zerodict()
     interarrival = zerodict()
     parents = zerodict()
     dirsadded = zerodict()
     tzoffset = zerodict()
 
     # If a mercurial repo is available, also model the commit history.
     if repo:
         revs = scmutil.revrange(repo, revs)
         revs.sort()
 
         progress = ui.progress
         _analyzing = _('analyzing')
         _changesets = _('changesets')
         _total = len(revs)
 
         for i, rev in enumerate(revs):
             progress(_analyzing, i, unit=_changesets, total=_total)
             ctx = repo[rev]
             pl = ctx.parents()
             pctx = pl[0]
             prev = pctx.rev()
             children[prev] += 1
             p1distance[rev - prev] += 1
             parents[len(pl)] += 1
             tzoffset[ctx.date()[1]] += 1
             if len(pl) > 1:
                 p2distance[rev - pl[1].rev()] += 1
             if prev == rev - 1:
                 lastctx = pctx
             else:
                 lastctx = repo[rev - 1]
             if lastctx.rev() != nullrev:
                 timedelta = ctx.date()[0] - lastctx.date()[0]
                 interarrival[roundto(timedelta, 300)] += 1
             diff = sum((d.splitlines() for d in ctx.diff(pctx, git=True)), [])
             fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0
             for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):
                 if isbin:
                     continue
                 added = sum(lineadd.itervalues(), 0)
                 if mar == 'm':
                     if added and lineremove:
                         lineschanged[roundto(added, 5),
                                      roundto(lineremove, 5)] += 1
                         filechanges += 1
                 elif mar == 'a':
                     fileadds += 1
                     if '/' in filename:
                         filedir = filename.rsplit('/', 1)[0]
                         if filedir not in pctx.dirs():
                             diradds += 1
                     linesinfilesadded[roundto(added, 5)] += 1
                 elif mar == 'r':
                     fileremoves += 1
                 for length, count in lineadd.iteritems():
                     linelengths[length] += count
             fileschanged[filechanges] += 1
             filesadded[fileadds] += 1
             dirsadded[diradds] += 1
             filesremoved[fileremoves] += 1
 
     invchildren = zerodict()
 
     for rev, count in children.iteritems():
         invchildren[count] += 1
 
     if output != '-':
         ui.status(_('writing output to %s\n') % output)
 
     def pronk(d):
         return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)
 
     json.dump({'revs': len(revs),
                'initdirs': pronk(dirs),
                'lineschanged': pronk(lineschanged),
                'children': pronk(invchildren),
                'fileschanged': pronk(fileschanged),
                'filesadded': pronk(filesadded),
                'linesinfilesadded': pronk(linesinfilesadded),
                'dirsadded': pronk(dirsadded),
                'filesremoved': pronk(filesremoved),
                'linelengths': pronk(linelengths),
                'parents': pronk(parents),
                'p1distance': pronk(p1distance),
                'p2distance': pronk(p2distance),
                'interarrival': pronk(interarrival),
                'tzoffset': pronk(tzoffset),
                },
               fp)
     fp.close()
 
 @command('synthesize',
          [('c', 'count', 0, _('create given number of commits'), _('COUNT')),
           ('', 'dict', '', _('path to a dictionary of words'), _('FILE')),
           ('', 'initfiles', 0, _('initial file count to create'), _('COUNT'))],
          _('hg synthesize [OPTION].. DESCFILE'))
 def synthesize(ui, repo, descpath, **opts):
     '''synthesize commits based on a model of an existing repository
 
     The model must have been generated by :hg:`analyze`. Commits will
     be generated randomly according to the probabilities described in
     the model. If --initfiles is set, the repository will be seeded with
     the given number files following the modeled repository's directory
     structure.
 
     When synthesizing new content, commit descriptions, and user
     names, words will be chosen randomly from a dictionary that is
     presumed to contain one word per line. Use --dict to specify the
     path to an alternate dictionary to use.
     '''
     try:
         fp = hg.openpath(ui, descpath)
     except Exception as err:
         raise error.Abort('%s: %s' % (descpath, err[0].strerror))
     desc = json.load(fp)
     fp.close()
 
     def cdf(l):
         if not l:
             return [], []
         vals, probs = zip(*sorted(l, key=lambda x: x[1], reverse=True))
         t = float(sum(probs, 0))
         s, cdfs = 0, []
         for v in probs:
             s += v
             cdfs.append(s / t)
         return vals, cdfs
 
     lineschanged = cdf(desc['lineschanged'])
     fileschanged = cdf(desc['fileschanged'])
     filesadded = cdf(desc['filesadded'])
     dirsadded = cdf(desc['dirsadded'])
     filesremoved = cdf(desc['filesremoved'])
     linelengths = cdf(desc['linelengths'])
     parents = cdf(desc['parents'])
     p1distance = cdf(desc['p1distance'])
     p2distance = cdf(desc['p2distance'])
     interarrival = cdf(desc['interarrival'])
     linesinfilesadded = cdf(desc['linesinfilesadded'])
     tzoffset = cdf(desc['tzoffset'])
 
     dictfile = opts.get('dict') or '/usr/share/dict/words'
     try:
         fp = open(dictfile, 'rU')
     except IOError as err:
         raise error.Abort('%s: %s' % (dictfile, err.strerror))
     words = fp.read().splitlines()
     fp.close()
 
     initdirs = {}
     if desc['initdirs']:
         for k, v in desc['initdirs']:
             initdirs[k.encode('utf-8').replace('.hg', '_hg')] = v
         initdirs = renamedirs(initdirs, words)
     initdirscdf = cdf(initdirs)
 
     def pick(cdf):
         return cdf[0][bisect.bisect_left(cdf[1], random.random())]
 
     def pickpath():
         return os.path.join(pick(initdirscdf), random.choice(words))
 
     def makeline(minimum=0):
         total = max(minimum, pick(linelengths))
         c, l = 0, []
         while c < total:
             w = random.choice(words)
             c += len(w) + 1
             l.append(w)
         return ' '.join(l)
 
     wlock = repo.wlock()
     lock = repo.lock()
 
     nevertouch = set(('.hgsub', '.hgignore', '.hgtags'))
 
     progress = ui.progress
     _synthesizing = _('synthesizing')
     _files = _('initial files')
     _changesets = _('changesets')
 
     # Synthesize a single initial revision adding files to the repo according
     # to the modeled directory structure.
     initcount = int(opts['initfiles'])
     if initcount and initdirs:
         pctx = repo[None].parents()[0]
         dirs = set(pctx.dirs())
         files = {}
 
         def validpath(path):
             # Don't pick filenames which are already directory names.
             if path in dirs:
                 return False
             # Don't pick directories which were used as file names.
             while path:
                 if path in files:
                     return False
                 path = os.path.dirname(path)
             return True
 
         for i in xrange(0, initcount):
             ui.progress(_synthesizing, i, unit=_files, total=initcount)
 
             path = pickpath()
             while not validpath(path):
                 path = pickpath()
             data = '%s contents\n' % path
             files[path] = context.memfilectx(repo, path, data)
             dir = os.path.dirname(path)
             while dir and dir not in dirs:
                 dirs.add(dir)
                 dir = os.path.dirname(dir)
 
         def filectxfn(repo, memctx, path):
             return files[path]
 
         ui.progress(_synthesizing, None)
         message = 'synthesized wide repo with %d files' % (len(files),)
         mc = context.memctx(repo, [pctx.node(), nullid], message,
                             files.iterkeys(), filectxfn, ui.username(),
                             '%d %d' % util.makedate())
         initnode = mc.commit()
         if ui.debugflag:
             hexfn = hex
         else:
             hexfn = short
         ui.status(_('added commit %s with %d files\n')
                   % (hexfn(initnode), len(files)))
 
     # Synthesize incremental revisions to the repository, adding repo depth.
     count = int(opts['count'])
     heads = set(map(repo.changelog.rev, repo.heads()))
     for i in xrange(count):
         progress(_synthesizing, i, unit=_changesets, total=count)
 
         node = repo.changelog.node
         revs = len(repo)
 
         def pickhead(heads, distance):
             if heads:
                 lheads = sorted(heads)
                 rev = revs - min(pick(distance), revs)
                 if rev < lheads[-1]:
                     rev = lheads[bisect.bisect_left(lheads, rev)]
                 else:
                     rev = lheads[-1]
                 return rev, node(rev)
             return nullrev, nullid
 
         r1 = revs - min(pick(p1distance), revs)
         p1 = node(r1)
 
         # the number of heads will grow without bound if we use a pure
         # model, so artificially constrain their proliferation
         toomanyheads = len(heads) > random.randint(1, 20)
         if p2distance[0] and (pick(parents) == 2 or toomanyheads):
             r2, p2 = pickhead(heads.difference([r1]), p2distance)
         else:
             r2, p2 = nullrev, nullid
 
         pl = [p1, p2]
         pctx = repo[r1]
         mf = pctx.manifest()
         mfk = mf.keys()
         changes = {}
         if mfk:
             for __ in xrange(pick(fileschanged)):
                 for __ in xrange(10):
                     fctx = pctx.filectx(random.choice(mfk))
                     path = fctx.path()
                     if not (path in nevertouch or fctx.isbinary() or
                             'l' in fctx.flags()):
                         break
                 lines = fctx.data().splitlines()
                 add, remove = pick(lineschanged)
                 for __ in xrange(remove):
                     if not lines:
                         break
                     del lines[random.randrange(0, len(lines))]
                 for __ in xrange(add):
                     lines.insert(random.randint(0, len(lines)), makeline())
                 path = fctx.path()
                 changes[path] = context.memfilectx(repo, path,
                                                    '\n'.join(lines) + '\n')
             for __ in xrange(pick(filesremoved)):
                 path = random.choice(mfk)
                 for __ in xrange(10):
                     path = random.choice(mfk)
                     if path not in changes:
                         changes[path] = None
                         break
         if filesadded:
             dirs = list(pctx.dirs())
             dirs.insert(0, '')
         for __ in xrange(pick(filesadded)):
             pathstr = ''
             while pathstr in dirs:
                 path = [random.choice(dirs)]
                 if pick(dirsadded):
                     path.append(random.choice(words))
                 path.append(random.choice(words))
                 pathstr = '/'.join(filter(None, path))
             data = '\n'.join(makeline()
                              for __ in xrange(pick(linesinfilesadded))) + '\n'
             changes[pathstr] = context.memfilectx(repo, pathstr, data)
         def filectxfn(repo, memctx, path):
             return changes[path]
         if not changes:
             continue
         if revs:
             date = repo['tip'].date()[0] + pick(interarrival)
         else:
             date = time.time() - (86400 * count)
         # dates in mercurial must be positive, fit in 32-bit signed integers.
         date = min(0x7fffffff, max(0, date))
         user = random.choice(words) + '@' + random.choice(words)
         mc = context.memctx(repo, pl, makeline(minimum=2),
                             sorted(changes.iterkeys()),
                             filectxfn, user, '%d %d' % (date, pick(tzoffset)))
         newnode = mc.commit()
         heads.add(repo.changelog.rev(newnode))
         heads.discard(r1)
         heads.discard(r2)
 
     lock.release()
     wlock.release()
 
 def renamedirs(dirs, words):
     '''Randomly rename the directory names in the per-dir file count dict.'''
     wordgen = itertools.cycle(words)
     replacements = {'': ''}
     def rename(dirpath):
         '''Recursively rename the directory and all path prefixes.
 
         The mapping from path to renamed path is stored for all path prefixes
         as in dynamic programming, ensuring linear runtime and consistent
         renaming regardless of iteration order through the model.
         '''
         if dirpath in replacements:
             return replacements[dirpath]
         head, _ = os.path.split(dirpath)
         if head:
             head = rename(head)
         else:
             head = ''
-        renamed = os.path.join(head, wordgen.next())
+        renamed = os.path.join(head, next(wordgen))
         replacements[dirpath] = renamed
         return renamed
     result = []
     for dirpath, count in dirs.iteritems():
         result.append([rename(dirpath.lstrip(os.sep)), count])
     return result

doc/hgmanpage.py

@@ -1,1115 +1,1115 b''
 # -*- coding: utf-8 -*-
 # $Id: manpage.py 6110 2009-08-31 14:40:33Z grubert $
 # Author: Engelbert Gruber <[e-mail]>
 # Copyright: This module is put into the public domain.
 
 """
 Simple man page writer for reStructuredText.
 
 Man pages (short for "manual pages") contain system documentation on unix-like
 systems. The pages are grouped in numbered sections:
 
  1 executable programs and shell commands
  2 system calls
  3 library functions
  4 special files
  5 file formats
  6 games
  7 miscellaneous
  8 system administration
 
 Man pages are written in *troff*, a text file formatting system.
 
 See http://www.tldp.org/HOWTO/Man-Page for a start.
 
 Man pages have no subsections only parts.
 Standard parts
 
   NAME ,
   SYNOPSIS ,
   DESCRIPTION ,
   OPTIONS ,
   FILES ,
   SEE ALSO ,
   BUGS ,
 
 and
 
   AUTHOR .
 
 A unix-like system keeps an index of the DESCRIPTIONs, which is accesable
 by the command whatis or apropos.
 
 """
 from __future__ import absolute_import
 
 __docformat__ = 'reStructuredText'
 
 import inspect
 import re
 
 from docutils import (
     languages,
     nodes,
     writers,
 )
 try:
     import roman
 except ImportError:
     from docutils.utils import roman
 import inspect
 
 FIELD_LIST_INDENT = 7
 DEFINITION_LIST_INDENT = 7
 OPTION_LIST_INDENT = 7
 BLOCKQOUTE_INDENT = 3.5
 
 # Define two macros so man/roff can calculate the
 # indent/unindent margins by itself
 MACRO_DEF = (r""".
 .nr rst2man-indent-level 0
 .
 .de1 rstReportMargin
 \\$1 \\n[an-margin]
 level \\n[rst2man-indent-level]
 level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
 -
 \\n[rst2man-indent0]
 \\n[rst2man-indent1]
 \\n[rst2man-indent2]
 ..
 .de1 INDENT
 .\" .rstReportMargin pre:
 . RS \\$1
 . nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
 . nr rst2man-indent-level +1
 .\" .rstReportMargin post:
 ..
 .de UNINDENT
 . RE
 .\" indent \\n[an-margin]
 .\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .nr rst2man-indent-level -1
 .\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .in \\n[rst2man-indent\\n[rst2man-indent-level]]u
 ..
 """)
 
 class Writer(writers.Writer):
 
     supported = ('manpage')
     """Formats this writer supports."""
 
     output = None
     """Final translated form of `document`."""
 
     def __init__(self):
         writers.Writer.__init__(self)
         self.translator_class = Translator
 
     def translate(self):
         visitor = self.translator_class(self.document)
         self.document.walkabout(visitor)
         self.output = visitor.astext()
 
 
 class Table(object):
     def __init__(self):
         self._rows = []
         self._options = ['center']
         self._tab_char = '\t'
         self._coldefs = []
     def new_row(self):
         self._rows.append([])
     def append_separator(self, separator):
         """Append the separator for table head."""
         self._rows.append([separator])
     def append_cell(self, cell_lines):
         """cell_lines is an array of lines"""
         start = 0
         if len(cell_lines) > 0 and cell_lines[0] == '.sp\n':
             start = 1
         self._rows[-1].append(cell_lines[start:])
         if len(self._coldefs) < len(self._rows[-1]):
             self._coldefs.append('l')
     def _minimize_cell(self, cell_lines):
         """Remove leading and trailing blank and ``.sp`` lines"""
         while (cell_lines and cell_lines[0] in ('\n', '.sp\n')):
             del cell_lines[0]
         while (cell_lines and cell_lines[-1] in ('\n', '.sp\n')):
             del cell_lines[-1]
     def as_list(self):
         text = ['.TS\n']
         text.append(' '.join(self._options) + ';\n')
         text.append('|%s|.\n' % ('|'.join(self._coldefs)))
         for row in self._rows:
             # row = array of cells. cell = array of lines.
             text.append('_\n')       # line above
             text.append('T{\n')
             for i in range(len(row)):
                 cell = row[i]
                 self._minimize_cell(cell)
                 text.extend(cell)
                 if not text[-1].endswith('\n'):
                     text[-1] += '\n'
                 if i < len(row) - 1:
                     text.append('T}'+self._tab_char+'T{\n')
                 else:
                     text.append('T}\n')
         text.append('_\n')
         text.append('.TE\n')
         return text
 
 class Translator(nodes.NodeVisitor):
     """"""
 
     words_and_spaces = re.compile(r'\S+| +|\n')
     document_start = """Man page generated from reStructuredText."""
 
     def __init__(self, document):
         nodes.NodeVisitor.__init__(self, document)
         self.settings = settings = document.settings
         lcode = settings.language_code
         arglen = len(inspect.getargspec(languages.get_language)[0])
         if arglen == 2:
             self.language = languages.get_language(lcode,
                                                    self.document.reporter)
         else:
             self.language = languages.get_language(lcode)
         self.head = []
         self.body = []
         self.foot = []
         self.section_level = 0
         self.context = []
         self.topic_class = ''
         self.colspecs = []
         self.compact_p = 1
         self.compact_simple = None
         # the list style "*" bullet or "#" numbered
         self._list_char = []
         # writing the header .TH and .SH NAME is postboned after
         # docinfo.
         self._docinfo = {
                 "title" : "", "title_upper": "",
                 "subtitle" : "",
                 "manual_section" : "", "manual_group" : "",
                 "author" : [],
                 "date" : "",
                 "copyright" : "",
                 "version" : "",
                     }
         self._docinfo_keys = []     # a list to keep the sequence as in source.
         self._docinfo_names = {}    # to get name from text not normalized.
         self._in_docinfo = None
         self._active_table = None
         self._in_literal = False
         self.header_written = 0
         self._line_block = 0
         self.authors = []
         self.section_level = 0
         self._indent = [0]
         # central definition of simple processing rules
         # what to output on : visit, depart
         # Do not use paragraph requests ``.PP`` because these set indentation.
         # use ``.sp``. Remove superfluous ``.sp`` in ``astext``.
         #
         # Fonts are put on a stack, the top one is used.
         # ``.ft P`` or ``\\fP`` pop from stack.
         # ``B`` bold, ``I`` italic, ``R`` roman should be available.
         # Hopefully ``C`` courier too.
         self.defs = {
                 'indent' : ('.INDENT %.1f\n', '.UNINDENT\n'),
                 'definition_list_item' : ('.TP', ''),
                 'field_name' : ('.TP\n.B ', '\n'),
                 'literal' : ('\\fB', '\\fP'),
                 'literal_block' : ('.sp\n.nf\n.ft C\n', '\n.ft P\n.fi\n'),
 
                 'option_list_item' : ('.TP\n', ''),
 
                 'reference' : (r'\%', r'\:'),
                 'emphasis': ('\\fI', '\\fP'),
                 'strong' : ('\\fB', '\\fP'),
                 'term' : ('\n.B ', '\n'),
                 'title_reference' : ('\\fI', '\\fP'),
 
                 'topic-title' : ('.SS ',),
                 'sidebar-title' : ('.SS ',),
 
                 'problematic' : ('\n.nf\n', '\n.fi\n'),
                     }
         # NOTE don't specify the newline before a dot-command, but ensure
         # it is there.
 
     def comment_begin(self, text):
         """Return commented version of the passed text WITHOUT end of
         line/comment."""
         prefix = '.\\" '
         out_text = ''.join(
             [(prefix + in_line + '\n')
             for in_line in text.split('\n')])
         return out_text
 
     def comment(self, text):
         """Return commented version of the passed text."""
         return self.comment_begin(text)+'.\n'
 
     def ensure_eol(self):
         """Ensure the last line in body is terminated by new line."""
         if self.body[-1][-1] != '\n':
             self.body.append('\n')
 
     def astext(self):
         """Return the final formatted document as a string."""
         if not self.header_written:
             # ensure we get a ".TH" as viewers require it.
             self.head.append(self.header())
         # filter body
         for i in xrange(len(self.body) - 1, 0, -1):
             # remove superfluous vertical gaps.
             if self.body[i] == '.sp\n':
                 if self.body[i - 1][:4] in ('.BI ','.IP '):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1][:3] == '.B ' and
                     self.body[i - 2][:4] == '.TP\n'):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1] == '\n' and
                     self.body[i - 2][0] != '.' and
                     (self.body[i - 3][:7] == '.TP\n.B '
                         or self.body[i - 3][:4] == '\n.B ')
                      ):
                     self.body[i] = '.\n'
         return ''.join(self.head + self.body + self.foot)
 
     def deunicode(self, text):
         text = text.replace(u'\xa0', '\\ ')
         text = text.replace(u'\u2020', '\\(dg')
         return text
 
     def visit_Text(self, node):
         text = node.astext()
         text = text.replace('\\','\\e')
         replace_pairs = [
             (u'-', ur'\-'),
             (u'\'', ur'\(aq'),
             (u'´', ur'\''),
             (u'`', ur'\(ga'),
             ]
         for (in_char, out_markup) in replace_pairs:
             text = text.replace(in_char, out_markup)
         # unicode
         text = self.deunicode(text)
         if self._in_literal:
             # prevent interpretation of "." at line start
             if text[0] == '.':
                 text = '\\&' + text
             text = text.replace('\n.', '\n\\&.')
         self.body.append(text)
 
     def depart_Text(self, node):
         pass
 
     def list_start(self, node):
         class enum_char(object):
             enum_style = {
                     'bullet'     : '\\(bu',
                     'emdash'     : '\\(em',
                      }
 
             def __init__(self, style):
                 self._style = style
                 if 'start' in node:
                     self._cnt = node['start'] - 1
                 else:
                     self._cnt = 0
                 self._indent = 2
                 if style == 'arabic':
                     # indentation depends on number of children
                     # and start value.
                     self._indent = len(str(len(node.children)))
                     self._indent += len(str(self._cnt)) + 1
                 elif style == 'loweralpha':
                     self._cnt += ord('a') - 1
                     self._indent = 3
                 elif style == 'upperalpha':
                     self._cnt += ord('A') - 1
                     self._indent = 3
                 elif style.endswith('roman'):
                     self._indent = 5
 
             def next(self):
                 if self._style == 'bullet':
                     return self.enum_style[self._style]
                 elif self._style == 'emdash':
                     return self.enum_style[self._style]
                 self._cnt += 1
                 # TODO add prefix postfix
                 if self._style == 'arabic':
                     return "%d." % self._cnt
                 elif self._style in ('loweralpha', 'upperalpha'):
                     return "%c." % self._cnt
                 elif self._style.endswith('roman'):
                     res = roman.toRoman(self._cnt) + '.'
                     if self._style.startswith('upper'):
                         return res.upper()
                     return res.lower()
                 else:
                     return "%d." % self._cnt
             def get_width(self):
                 return self._indent
             def __repr__(self):
                 return 'enum_style-%s' % list(self._style)
 
         if 'enumtype' in node:
             self._list_char.append(enum_char(node['enumtype']))
         else:
             self._list_char.append(enum_char('bullet'))
         if len(self._list_char) > 1:
             # indent nested lists
             self.indent(self._list_char[-2].get_width())
         else:
             self.indent(self._list_char[-1].get_width())
 
     def list_end(self):
         self.dedent()
         self._list_char.pop()
 
     def header(self):
         tmpl = (".TH %(title_upper)s %(manual_section)s"
                 " \"%(date)s\" \"%(version)s\" \"%(manual_group)s\"\n"
                 ".SH NAME\n"
                 "%(title)s \- %(subtitle)s\n")
         return tmpl % self._docinfo
 
     def append_header(self):
         """append header with .TH and .SH NAME"""
         # NOTE before everything
         # .TH title_upper section date source manual
         if self.header_written:
             return
         self.body.append(self.header())
         self.body.append(MACRO_DEF)
         self.header_written = 1
 
     def visit_address(self, node):
         self.visit_docinfo_item(node, 'address')
 
     def depart_address(self, node):
         pass
 
     def visit_admonition(self, node, name=None):
         if name:
             self.body.append('.IP %s\n' %
                         self.language.labels.get(name, name))
 
     def depart_admonition(self, node):
         self.body.append('.RE\n')
 
     def visit_attention(self, node):
         self.visit_admonition(node, 'attention')
 
     depart_attention = depart_admonition
 
     def visit_docinfo_item(self, node, name):
         if name == 'author':
             self._docinfo[name].append(node.astext())
         else:
             self._docinfo[name] = node.astext()
         self._docinfo_keys.append(name)
         raise nodes.SkipNode()
 
     def depart_docinfo_item(self, node):
         pass
 
     def visit_author(self, node):
         self.visit_docinfo_item(node, 'author')
 
     depart_author = depart_docinfo_item
 
     def visit_authors(self, node):
         # _author is called anyway.
         pass
 
     def depart_authors(self, node):
         pass
 
     def visit_block_quote(self, node):
         # BUG/HACK: indent always uses the _last_ indentation,
         # thus we need two of them.
         self.indent(BLOCKQOUTE_INDENT)
         self.indent(0)
 
     def depart_block_quote(self, node):
         self.dedent()
         self.dedent()
 
     def visit_bullet_list(self, node):
         self.list_start(node)
 
     def depart_bullet_list(self, node):
         self.list_end()
 
     def visit_caption(self, node):
         pass
 
     def depart_caption(self, node):
         pass
 
     def visit_caution(self, node):
         self.visit_admonition(node, 'caution')
 
     depart_caution = depart_admonition
 
     def visit_citation(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % num)
 
     def depart_citation(self, node):
         pass
 
     def visit_citation_reference(self, node):
         self.body.append('['+node.astext()+']')
         raise nodes.SkipNode()
 
     def visit_classifier(self, node):
         pass
 
     def depart_classifier(self, node):
         pass
 
     def visit_colspec(self, node):
         self.colspecs.append(node)
 
     def depart_colspec(self, node):
         pass
 
     def write_colspecs(self):
         self.body.append("%s.\n" % ('L '*len(self.colspecs)))
 
     def visit_comment(self, node,
                       sub=re.compile('-(?=-)').sub):
         self.body.append(self.comment(node.astext()))
         raise nodes.SkipNode()
 
     def visit_contact(self, node):
         self.visit_docinfo_item(node, 'contact')
 
     depart_contact = depart_docinfo_item
 
     def visit_container(self, node):
         pass
 
     def depart_container(self, node):
         pass
 
     def visit_compound(self, node):
         pass
 
     def depart_compound(self, node):
         pass
 
     def visit_copyright(self, node):
         self.visit_docinfo_item(node, 'copyright')
 
     def visit_danger(self, node):
         self.visit_admonition(node, 'danger')
 
     depart_danger = depart_admonition
 
     def visit_date(self, node):
         self.visit_docinfo_item(node, 'date')
 
     def visit_decoration(self, node):
         pass
 
     def depart_decoration(self, node):
         pass
 
     def visit_definition(self, node):
         pass
 
     def depart_definition(self, node):
         pass
 
     def visit_definition_list(self, node):
         self.indent(DEFINITION_LIST_INDENT)
 
     def depart_definition_list(self, node):
         self.dedent()
 
     def visit_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][0])
 
     def depart_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][1])
 
     def visit_description(self, node):
         pass
 
     def depart_description(self, node):
         pass
 
     def visit_docinfo(self, node):
         self._in_docinfo = 1
 
     def depart_docinfo(self, node):
         self._in_docinfo = None
         # NOTE nothing should be written before this
         self.append_header()
 
     def visit_doctest_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_doctest_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_document(self, node):
         # no blank line between comment and header.
         self.body.append(self.comment(self.document_start).rstrip()+'\n')
         # writing header is postboned
         self.header_written = 0
 
     def depart_document(self, node):
         if self._docinfo['author']:
             self.body.append('.SH AUTHOR\n%s\n'
                     % ', '.join(self._docinfo['author']))
         skip = ('author', 'copyright', 'date',
                 'manual_group', 'manual_section',
                 'subtitle',
                 'title', 'title_upper', 'version')
         for name in self._docinfo_keys:
             if name == 'address':
                 self.body.append("\n%s:\n%s%s.nf\n%s\n.fi\n%s%s" % (
                                     self.language.labels.get(name, name),
                                     self.defs['indent'][0] % 0,
                                     self.defs['indent'][0] % BLOCKQOUTE_INDENT,
                                     self._docinfo[name],
                                     self.defs['indent'][1],
                                     self.defs['indent'][1]))
             elif name not in skip:
                 if name in self._docinfo_names:
                     label = self._docinfo_names[name]
                 else:
                     label = self.language.labels.get(name, name)
                 self.body.append("\n%s: %s\n" % (label, self._docinfo[name]))
         if self._docinfo['copyright']:
             self.body.append('.SH COPYRIGHT\n%s\n'
                     % self._docinfo['copyright'])
         self.body.append(self.comment(
                         'Generated by docutils manpage writer.\n'))
 
     def visit_emphasis(self, node):
         self.body.append(self.defs['emphasis'][0])
 
     def depart_emphasis(self, node):
         self.body.append(self.defs['emphasis'][1])
 
     def visit_entry(self, node):
         # a cell in a table row
         if 'morerows' in node:
             self.document.reporter.warning('"table row spanning" not supported',
                     base_node=node)
         if 'morecols' in node:
             self.document.reporter.warning(
                     '"table cell spanning" not supported', base_node=node)
         self.context.append(len(self.body))
 
     def depart_entry(self, node):
         start = self.context.pop()
         self._active_table.append_cell(self.body[start:])
         del self.body[start:]
 
     def visit_enumerated_list(self, node):
         self.list_start(node)
 
     def depart_enumerated_list(self, node):
         self.list_end()
 
     def visit_error(self, node):
         self.visit_admonition(node, 'error')
 
     depart_error = depart_admonition
 
     def visit_field(self, node):
         pass
 
     def depart_field(self, node):
         pass
 
     def visit_field_body(self, node):
         if self._in_docinfo:
             name_normalized = self._field_name.lower().replace(" ","_")
             self._docinfo_names[name_normalized] = self._field_name
             self.visit_docinfo_item(node, name_normalized)
             raise nodes.SkipNode()
 
     def depart_field_body(self, node):
         pass
 
     def visit_field_list(self, node):
         self.indent(FIELD_LIST_INDENT)
 
     def depart_field_list(self, node):
         self.dedent()
 
     def visit_field_name(self, node):
         if self._in_docinfo:
             self._field_name = node.astext()
             raise nodes.SkipNode()
         else:
             self.body.append(self.defs['field_name'][0])
 
     def depart_field_name(self, node):
         self.body.append(self.defs['field_name'][1])
 
     def visit_figure(self, node):
         self.indent(2.5)
         self.indent(0)
 
     def depart_figure(self, node):
         self.dedent()
         self.dedent()
 
     def visit_footer(self, node):
         self.document.reporter.warning('"footer" not supported',
                 base_node=node)
 
     def depart_footer(self, node):
         pass
 
     def visit_footnote(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % self.deunicode(num))
 
     def depart_footnote(self, node):
         pass
 
     def footnote_backrefs(self, node):
         self.document.reporter.warning('"footnote_backrefs" not supported',
                 base_node=node)
 
     def visit_footnote_reference(self, node):
         self.body.append('['+self.deunicode(node.astext())+']')
         raise nodes.SkipNode()
 
     def depart_footnote_reference(self, node):
         pass
 
     def visit_generated(self, node):
         pass
 
     def depart_generated(self, node):
         pass
 
     def visit_header(self, node):
         raise NotImplementedError(node.astext())
 
     def depart_header(self, node):
         pass
 
     def visit_hint(self, node):
         self.visit_admonition(node, 'hint')
 
     depart_hint = depart_admonition
 
     def visit_subscript(self, node):
         self.body.append('\\s-2\\d')
 
     def depart_subscript(self, node):
         self.body.append('\\u\\s0')
 
     def visit_superscript(self, node):
         self.body.append('\\s-2\\u')
 
     def depart_superscript(self, node):
         self.body.append('\\d\\s0')
 
     def visit_attribution(self, node):
         self.body.append('\\(em ')
 
     def depart_attribution(self, node):
         self.body.append('\n')
 
     def visit_image(self, node):
         self.document.reporter.warning('"image" not supported',
                 base_node=node)
         text = []
         if 'alt' in node.attributes:
             text.append(node.attributes['alt'])
         if 'uri' in node.attributes:
             text.append(node.attributes['uri'])
         self.body.append('[image: %s]\n' % ('/'.join(text)))
         raise nodes.SkipNode()
 
     def visit_important(self, node):
         self.visit_admonition(node, 'important')
 
     depart_important = depart_admonition
 
     def visit_label(self, node):
         # footnote and citation
         if (isinstance(node.parent, nodes.footnote)
             or isinstance(node.parent, nodes.citation)):
             raise nodes.SkipNode()
         self.document.reporter.warning('"unsupported "label"',
                 base_node=node)
         self.body.append('[')
 
     def depart_label(self, node):
         self.body.append(']\n')
 
     def visit_legend(self, node):
         pass
 
     def depart_legend(self, node):
         pass
 
     # WHAT should we use .INDENT, .UNINDENT ?
     def visit_line_block(self, node):
         self._line_block += 1
         if self._line_block == 1:
             self.body.append('.sp\n')
             self.body.append('.nf\n')
         else:
             self.body.append('.in +2\n')
 
     def depart_line_block(self, node):
         self._line_block -= 1
         if self._line_block == 0:
             self.body.append('.fi\n')
             self.body.append('.sp\n')
         else:
             self.body.append('.in -2\n')
 
     def visit_line(self, node):
         pass
 
     def depart_line(self, node):
         self.body.append('\n')
 
     def visit_list_item(self, node):
         # man 7 man argues to use ".IP" instead of ".TP"
         self.body.append('.IP %s %d\n' % (
-                self._list_char[-1].next(),
+                next(self._list_char[-1]),
                 self._list_char[-1].get_width(),))
 
     def depart_list_item(self, node):
         pass
 
     def visit_literal(self, node):
         self.body.append(self.defs['literal'][0])
 
     def depart_literal(self, node):
         self.body.append(self.defs['literal'][1])
 
     def visit_literal_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_literal_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_meta(self, node):
         raise NotImplementedError(node.astext())
 
     def depart_meta(self, node):
         pass
 
     def visit_note(self, node):
         self.visit_admonition(node, 'note')
 
     depart_note = depart_admonition
 
     def indent(self, by=0.5):
         # if we are in a section ".SH" there already is a .RS
         step = self._indent[-1]
         self._indent.append(by)
         self.body.append(self.defs['indent'][0] % step)
 
     def dedent(self):
         self._indent.pop()
         self.body.append(self.defs['indent'][1])
 
     def visit_option_list(self, node):
         self.indent(OPTION_LIST_INDENT)
 
     def depart_option_list(self, node):
         self.dedent()
 
     def visit_option_list_item(self, node):
         # one item of the list
         self.body.append(self.defs['option_list_item'][0])
 
     def depart_option_list_item(self, node):
         self.body.append(self.defs['option_list_item'][1])
 
     def visit_option_group(self, node):
         # as one option could have several forms it is a group
         # options without parameter bold only, .B, -v
         # options with parameter bold italic, .BI, -f file
         #
         # we do not know if .B or .BI
         self.context.append('.B')           # blind guess
         self.context.append(len(self.body)) # to be able to insert later
         self.context.append(0)              # option counter
 
     def depart_option_group(self, node):
         self.context.pop()  # the counter
         start_position = self.context.pop()
         text = self.body[start_position:]
         del self.body[start_position:]
         self.body.append('%s%s\n' % (self.context.pop(), ''.join(text)))
 
     def visit_option(self, node):
         # each form of the option will be presented separately
         if self.context[-1] > 0:
             self.body.append(', ')
         if self.context[-3] == '.BI':
             self.body.append('\\')
         self.body.append(' ')
 
     def depart_option(self, node):
         self.context[-1] += 1
 
     def visit_option_string(self, node):
         # do not know if .B or .BI
         pass
 
     def depart_option_string(self, node):
         pass
 
     def visit_option_argument(self, node):
         self.context[-3] = '.BI' # bold/italic alternate
         if node['delimiter'] != ' ':
             self.body.append('\\fB%s ' % node['delimiter'])
         elif self.body[len(self.body) - 1].endswith('='):
             # a blank only means no blank in output, just changing font
             self.body.append(' ')
         else:
             # blank backslash blank, switch font then a blank
             self.body.append(' \\ ')
 
     def depart_option_argument(self, node):
         pass
 
     def visit_organization(self, node):
         self.visit_docinfo_item(node, 'organization')
 
     def depart_organization(self, node):
         pass
 
     def visit_paragraph(self, node):
         # ``.PP`` : Start standard indented paragraph.
         # ``.LP`` : Start block paragraph, all except the first.
         # ``.P [type]``  : Start paragraph type.
         # NOTE don't use paragraph starts because they reset indentation.
         # ``.sp`` is only vertical space
         self.ensure_eol()
         self.body.append('.sp\n')
 
     def depart_paragraph(self, node):
         self.body.append('\n')
 
     def visit_problematic(self, node):
         self.body.append(self.defs['problematic'][0])
 
     def depart_problematic(self, node):
         self.body.append(self.defs['problematic'][1])
 
     def visit_raw(self, node):
         if node.get('format') == 'manpage':
             self.body.append(node.astext() + "\n")
         # Keep non-manpage raw text out of output:
         raise nodes.SkipNode()
 
     def visit_reference(self, node):
         """E.g. link or email address."""
         self.body.append(self.defs['reference'][0])
 
     def depart_reference(self, node):
         self.body.append(self.defs['reference'][1])
 
     def visit_revision(self, node):
         self.visit_docinfo_item(node, 'revision')
 
     depart_revision = depart_docinfo_item
 
     def visit_row(self, node):
         self._active_table.new_row()
 
     def depart_row(self, node):
         pass
 
     def visit_section(self, node):
         self.section_level += 1
 
     def depart_section(self, node):
         self.section_level -= 1
 
     def visit_status(self, node):
         self.visit_docinfo_item(node, 'status')
 
     depart_status = depart_docinfo_item
 
     def visit_strong(self, node):
         self.body.append(self.defs['strong'][0])
 
     def depart_strong(self, node):
         self.body.append(self.defs['strong'][1])
 
     def visit_substitution_definition(self, node):
         """Internal only."""
         raise nodes.SkipNode()
 
     def visit_substitution_reference(self, node):
         self.document.reporter.warning('"substitution_reference" not supported',
                 base_node=node)
 
     def visit_subtitle(self, node):
         if isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['strong'][0])
         elif isinstance(node.parent, nodes.document):
             self.visit_docinfo_item(node, 'subtitle')
         elif isinstance(node.parent, nodes.section):
             self.body.append(self.defs['strong'][0])
 
     def depart_subtitle(self, node):
         # document subtitle calls SkipNode
         self.body.append(self.defs['strong'][1]+'\n.PP\n')
 
     def visit_system_message(self, node):
         # TODO add report_level
         #if node['level'] < self.document.reporter['writer'].report_level:
         #    Level is too low to display:
         #    raise nodes.SkipNode
         attr = {}
         if node.hasattr('id'):
             attr['name'] = node['id']
         if node.hasattr('line'):
             line = ', line %s' % node['line']
         else:
             line = ''
         self.body.append('.IP "System Message: %s/%s (%s:%s)"\n'
                          % (node['type'], node['level'], node['source'], line))
 
     def depart_system_message(self, node):
         pass
 
     def visit_table(self, node):
         self._active_table = Table()
 
     def depart_table(self, node):
         self.ensure_eol()
         self.body.extend(self._active_table.as_list())
         self._active_table = None
 
     def visit_target(self, node):
         # targets are in-document hyper targets, without any use for man-pages.
         raise nodes.SkipNode()
 
     def visit_tbody(self, node):
         pass
 
     def depart_tbody(self, node):
         pass
 
     def visit_term(self, node):
         self.body.append(self.defs['term'][0])
 
     def depart_term(self, node):
         self.body.append(self.defs['term'][1])
 
     def visit_tgroup(self, node):
         pass
 
     def depart_tgroup(self, node):
         pass
 
     def visit_thead(self, node):
         # MAYBE double line '='
         pass
 
     def depart_thead(self, node):
         # MAYBE double line '='
         pass
 
     def visit_tip(self, node):
         self.visit_admonition(node, 'tip')
 
     depart_tip = depart_admonition
 
     def visit_title(self, node):
         if isinstance(node.parent, nodes.topic):
             self.body.append(self.defs['topic-title'][0])
         elif isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['sidebar-title'][0])
         elif isinstance(node.parent, nodes.admonition):
             self.body.append('.IP "')
         elif self.section_level == 0:
             self._docinfo['title'] = node.astext()
             # document title for .TH
             self._docinfo['title_upper'] = node.astext().upper()
             raise nodes.SkipNode()
         elif self.section_level == 1:
             self.body.append('.SH ')
             for n in node.traverse(nodes.Text):
                 n.parent.replace(n, nodes.Text(n.astext().upper()))
         else:
             self.body.append('.SS ')
 
     def depart_title(self, node):
         if isinstance(node.parent, nodes.admonition):
             self.body.append('"')
         self.body.append('\n')
 
     def visit_title_reference(self, node):
         """inline citation reference"""
         self.body.append(self.defs['title_reference'][0])
 
     def depart_title_reference(self, node):
         self.body.append(self.defs['title_reference'][1])
 
     def visit_topic(self, node):
         pass
 
     def depart_topic(self, node):
         pass
 
     def visit_sidebar(self, node):
         pass
 
     def depart_sidebar(self, node):
         pass
 
     def visit_rubric(self, node):
         pass
 
     def depart_rubric(self, node):
         pass
 
     def visit_transition(self, node):
         # .PP      Begin a new paragraph and reset prevailing indent.
         # .sp N    leaves N lines of blank space.
         # .ce      centers the next line
         self.body.append('\n.sp\n.ce\n----\n')
 
     def depart_transition(self, node):
         self.body.append('\n.ce 0\n.sp\n')
 
     def visit_version(self, node):
         self.visit_docinfo_item(node, 'version')
 
     def visit_warning(self, node):
         self.visit_admonition(node, 'warning')
 
     depart_warning = depart_admonition
 
     def unimplemented_visit(self, node):
         raise NotImplementedError('visiting unimplemented node type: %s'
                                   % node.__class__.__name__)
 
 # vim: set fileencoding=utf-8 et ts=4 ai :

hgext/highlight/highlight.py

@@ -1,75 +1,75 b''
 # highlight.py - highlight extension implementation file
 #
 #  Copyright 2007-2009 Adam Hupp <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 #
 # The original module was split in an interface and an implementation
 # file to defer pygments loading and speedup extension setup.
 
 from mercurial import demandimport
 demandimport.ignore.extend(['pkgutil', 'pkg_resources', '__main__'])
 from mercurial import util, encoding
 
 from pygments import highlight
 from pygments.util import ClassNotFound
 from pygments.lexers import guess_lexer, guess_lexer_for_filename, TextLexer
 from pygments.formatters import HtmlFormatter
 
 SYNTAX_CSS = ('\n<link rel="stylesheet" href="{url}highlightcss" '
               'type="text/css" />')
 
 def pygmentize(field, fctx, style, tmpl, guessfilenameonly=False):
 
     # append a <link ...> to the syntax highlighting css
     old_header = tmpl.load('header')
     if SYNTAX_CSS not in old_header:
         new_header = old_header + SYNTAX_CSS
         tmpl.cache['header'] = new_header
 
     text = fctx.data()
     if util.binary(text):
         return
 
     # str.splitlines() != unicode.splitlines() because "reasons"
     for c in "\x0c\x1c\x1d\x1e":
         if c in text:
             text = text.replace(c, '')
 
     # Pygments is best used with Unicode strings:
     # <http://pygments.org/docs/unicode/>
     text = text.decode(encoding.encoding, 'replace')
 
     # To get multi-line strings right, we can't format line-by-line
     try:
         lexer = guess_lexer_for_filename(fctx.path(), text[:1024],
                                          stripnl=False)
     except (ClassNotFound, ValueError):
         # guess_lexer will return a lexer if *any* lexer matches. There is
         # no way to specify a minimum match score. This can give a high rate of
         # false positives on files with an unknown filename pattern.
         if guessfilenameonly:
             return
 
         try:
             lexer = guess_lexer(text[:1024], stripnl=False)
         except (ClassNotFound, ValueError):
             # Don't highlight unknown files
             return
 
     # Don't highlight text files
     if isinstance(lexer, TextLexer):
         return
 
     formatter = HtmlFormatter(nowrap=True, style=style)
 
     colorized = highlight(text, lexer, formatter)
     coloriter = (s.encode(encoding.encoding, 'replace')
                  for s in colorized.splitlines())
 
-    tmpl.filters['colorize'] = lambda x: coloriter.next()
+    tmpl.filters['colorize'] = lambda x: next(coloriter)
 
     oldl = tmpl.cache[field]
     newl = oldl.replace('line|escape', 'line|colorize')
     tmpl.cache[field] = newl

mercurial/ancestor.py

@@ -1,361 +1,361 b''
 # ancestor.py - generic DAG ancestor algorithm for mercurial
 #
 # Copyright 2006 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.
 
 from __future__ import absolute_import
 
 import collections
 import heapq
 
 from .node import nullrev
 
 def commonancestorsheads(pfunc, *nodes):
     """Returns a set with the heads of all common ancestors of all nodes,
     heads(::nodes[0] and ::nodes[1] and ...) .
 
     pfunc must return a list of parent vertices for a given vertex.
     """
     if not isinstance(nodes, set):
         nodes = set(nodes)
     if nullrev in nodes:
         return set()
     if len(nodes) <= 1:
         return nodes
 
     allseen = (1 << len(nodes)) - 1
     seen = [0] * (max(nodes) + 1)
     for i, n in enumerate(nodes):
         seen[n] = 1 << i
     poison = 1 << (i + 1)
 
     gca = set()
     interesting = len(nodes)
     nv = len(seen) - 1
     while nv >= 0 and interesting:
         v = nv
         nv -= 1
         if not seen[v]:
             continue
         sv = seen[v]
         if sv < poison:
             interesting -= 1
             if sv == allseen:
                 gca.add(v)
                 sv |= poison
                 if v in nodes:
                     # history is linear
                     return set([v])
         if sv < poison:
             for p in pfunc(v):
                 sp = seen[p]
                 if p == nullrev:
                     continue
                 if sp == 0:
                     seen[p] = sv
                     interesting += 1
                 elif sp != sv:
                     seen[p] |= sv
         else:
             for p in pfunc(v):
                 if p == nullrev:
                     continue
                 sp = seen[p]
                 if sp and sp < poison:
                     interesting -= 1
                 seen[p] = sv
     return gca
 
 def ancestors(pfunc, *orignodes):
     """
     Returns the common ancestors of a and b that are furthest from a
     root (as measured by longest path).
 
     pfunc must return a list of parent vertices for a given vertex.
     """
     def deepest(nodes):
         interesting = {}
         count = max(nodes) + 1
         depth = [0] * count
         seen = [0] * count
         mapping = []
         for (i, n) in enumerate(sorted(nodes)):
             depth[n] = 1
             b = 1 << i
             seen[n] = b
             interesting[b] = 1
             mapping.append((b, n))
         nv = count - 1
         while nv >= 0 and len(interesting) > 1:
             v = nv
             nv -= 1
             dv = depth[v]
             if dv == 0:
                 continue
             sv = seen[v]
             for p in pfunc(v):
                 if p == nullrev:
                     continue
                 dp = depth[p]
                 nsp = sp = seen[p]
                 if dp <= dv:
                     depth[p] = dv + 1
                     if sp != sv:
                         interesting[sv] += 1
                         nsp = seen[p] = sv
                         if sp:
                             interesting[sp] -= 1
                             if interesting[sp] == 0:
                                 del interesting[sp]
                 elif dv == dp - 1:
                     nsp = sp | sv
                     if nsp == sp:
                         continue
                     seen[p] = nsp
                     interesting.setdefault(nsp, 0)
                     interesting[nsp] += 1
                     interesting[sp] -= 1
                     if interesting[sp] == 0:
                         del interesting[sp]
             interesting[sv] -= 1
             if interesting[sv] == 0:
                 del interesting[sv]
 
         if len(interesting) != 1:
             return []
 
         k = 0
         for i in interesting:
             k |= i
         return set(n for (i, n) in mapping if k & i)
 
     gca = commonancestorsheads(pfunc, *orignodes)
 
     if len(gca) <= 1:
         return gca
     return deepest(gca)
 
 class incrementalmissingancestors(object):
     '''persistent state used to calculate missing ancestors incrementally
 
     Although similar in spirit to lazyancestors below, this is a separate class
     because trying to support contains and missingancestors operations with the
     same internal data structures adds needless complexity.'''
     def __init__(self, pfunc, bases):
         self.bases = set(bases)
         if not self.bases:
             self.bases.add(nullrev)
         self.pfunc = pfunc
 
     def hasbases(self):
         '''whether the common set has any non-trivial bases'''
         return self.bases and self.bases != set([nullrev])
 
     def addbases(self, newbases):
         '''grow the ancestor set by adding new bases'''
         self.bases.update(newbases)
 
     def removeancestorsfrom(self, revs):
         '''remove all ancestors of bases from the set revs (in place)'''
         bases = self.bases
         pfunc = self.pfunc
         revs.difference_update(bases)
         # nullrev is always an ancestor
         revs.discard(nullrev)
         if not revs:
             return
         # anything in revs > start is definitely not an ancestor of bases
         # revs <= start needs to be investigated
         start = max(bases)
         keepcount = sum(1 for r in revs if r > start)
         if len(revs) == keepcount:
             # no revs to consider
             return
 
         for curr in xrange(start, min(revs) - 1, -1):
             if curr not in bases:
                 continue
             revs.discard(curr)
             bases.update(pfunc(curr))
             if len(revs) == keepcount:
                 # no more potential revs to discard
                 break
 
     def missingancestors(self, revs):
         '''return all the ancestors of revs that are not ancestors of self.bases
 
         This may include elements from revs.
 
         Equivalent to the revset (::revs - ::self.bases). Revs are returned in
         revision number order, which is a topological order.'''
         revsvisit = set(revs)
         basesvisit = self.bases
         pfunc = self.pfunc
         bothvisit = revsvisit.intersection(basesvisit)
         revsvisit.difference_update(bothvisit)
         if not revsvisit:
             return []
 
         start = max(max(revsvisit), max(basesvisit))
         # At this point, we hold the invariants that:
         # - revsvisit is the set of nodes we know are an ancestor of at least
         #   one of the nodes in revs
         # - basesvisit is the same for bases
         # - bothvisit is the set of nodes we know are ancestors of at least one
         #   of the nodes in revs and one of the nodes in bases. bothvisit and
         #   revsvisit are mutually exclusive, but bothvisit is a subset of
         #   basesvisit.
         # Now we walk down in reverse topo order, adding parents of nodes
         # already visited to the sets while maintaining the invariants. When a
         # node is found in both revsvisit and basesvisit, it is removed from
         # revsvisit and added to bothvisit. When revsvisit becomes empty, there
         # are no more ancestors of revs that aren't also ancestors of bases, so
         # exit.
 
         missing = []
         for curr in xrange(start, nullrev, -1):
             if not revsvisit:
                 break
 
             if curr in bothvisit:
                 bothvisit.remove(curr)
                 # curr's parents might have made it into revsvisit through
                 # another path
                 for p in pfunc(curr):
                     revsvisit.discard(p)
                     basesvisit.add(p)
                     bothvisit.add(p)
                 continue
 
             if curr in revsvisit:
                 missing.append(curr)
                 revsvisit.remove(curr)
                 thisvisit = revsvisit
                 othervisit = basesvisit
             elif curr in basesvisit:
                 thisvisit = basesvisit
                 othervisit = revsvisit
             else:
                 # not an ancestor of revs or bases: ignore
                 continue
 
             for p in pfunc(curr):
                 if p == nullrev:
                     pass
                 elif p in othervisit or p in bothvisit:
                     # p is implicitly in thisvisit. This means p is or should be
                     # in bothvisit
                     revsvisit.discard(p)
                     basesvisit.add(p)
                     bothvisit.add(p)
                 else:
                     # visit later
                     thisvisit.add(p)
 
         missing.reverse()
         return missing
 
 class lazyancestors(object):
     def __init__(self, pfunc, revs, stoprev=0, inclusive=False):
         """Create a new object generating ancestors for the given revs. Does
         not generate revs lower than stoprev.
 
         This is computed lazily starting from revs. The object supports
         iteration and membership.
 
         cl should be a changelog and revs should be an iterable. inclusive is
         a boolean that indicates whether revs should be included. Revs lower
         than stoprev will not be generated.
 
         Result does not include the null revision."""
         self._parentrevs = pfunc
         self._initrevs = revs
         self._stoprev = stoprev
         self._inclusive = inclusive
 
         # Initialize data structures for __contains__.
         # For __contains__, we use a heap rather than a deque because
         # (a) it minimizes the number of parentrevs calls made
         # (b) it makes the loop termination condition obvious
         # Python's heap is a min-heap. Multiply all values by -1 to convert it
         # into a max-heap.
         self._containsvisit = [-rev for rev in revs]
         heapq.heapify(self._containsvisit)
         if inclusive:
             self._containsseen = set(revs)
         else:
             self._containsseen = set()
 
     def __nonzero__(self):
         """False if the set is empty, True otherwise."""
         try:
-            iter(self).next()
+            next(iter(self))
             return True
         except StopIteration:
             return False
 
     def __iter__(self):
         """Generate the ancestors of _initrevs in reverse topological order.
 
         If inclusive is False, yield a sequence of revision numbers starting
         with the parents of each revision in revs, i.e., each revision is *not*
         considered an ancestor of itself.  Results are in breadth-first order:
         parents of each rev in revs, then parents of those, etc.
 
         If inclusive is True, yield all the revs first (ignoring stoprev),
         then yield all the ancestors of revs as when inclusive is False.
         If an element in revs is an ancestor of a different rev it is not
         yielded again."""
         seen = set()
         revs = self._initrevs
         if self._inclusive:
             for rev in revs:
                 yield rev
             seen.update(revs)
 
         parentrevs = self._parentrevs
         stoprev = self._stoprev
         visit = collections.deque(revs)
 
         see = seen.add
         schedule = visit.append
 
         while visit:
             for parent in parentrevs(visit.popleft()):
                 if parent >= stoprev and parent not in seen:
                     schedule(parent)
                     see(parent)
                     yield parent
 
     def __contains__(self, target):
         """Test whether target is an ancestor of self._initrevs."""
         # Trying to do both __iter__ and __contains__ using the same visit
         # heap and seen set is complex enough that it slows down both. Keep
         # them separate.
         seen = self._containsseen
         if target in seen:
             return True
 
         parentrevs = self._parentrevs
         visit = self._containsvisit
         stoprev = self._stoprev
         heappop = heapq.heappop
         heappush = heapq.heappush
         see = seen.add
 
         targetseen = False
 
         while visit and -visit[0] > target and not targetseen:
             for parent in parentrevs(-heappop(visit)):
                 if parent < stoprev or parent in seen:
                     continue
                 # We need to make sure we push all parents into the heap so
                 # that we leave it in a consistent state for future calls.
                 heappush(visit, -parent)
                 see(parent)
                 if parent == target:
                     targetseen = True
 
         return targetseen

mercurial/cmdutil.py

@@ -1,3556 +1,3556 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 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.
 
 from __future__ import absolute_import
 
 import errno
 import os
 import re
 import sys
 import tempfile
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 
 from . import (
     bookmarks,
     changelog,
     copies,
     crecord as crecordmod,
     encoding,
     error,
     formatter,
     graphmod,
     lock as lockmod,
     match as matchmod,
     obsolete,
     patch,
     pathutil,
     phases,
     repair,
     revlog,
     revset,
     scmutil,
     templatekw,
     templater,
     util,
 )
 stringio = util.stringio
 
 def ishunk(x):
     hunkclasses = (crecordmod.uihunk, patch.recordhunk)
     return isinstance(x, hunkclasses)
 
 def newandmodified(chunks, originalchunks):
     newlyaddedandmodifiedfiles = set()
     for chunk in chunks:
         if ishunk(chunk) and chunk.header.isnewfile() and chunk not in \
             originalchunks:
             newlyaddedandmodifiedfiles.add(chunk.header.filename())
     return newlyaddedandmodifiedfiles
 
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 def setupwrapcolorwrite(ui):
     # wrap ui.write so diff output can be labeled/colorized
     def wrapwrite(orig, *args, **kw):
         label = kw.pop('label', '')
         for chunk, l in patch.difflabel(lambda: args):
             orig(chunk, label=label + l)
 
     oldwrite = ui.write
     def wrap(*args, **kwargs):
         return wrapwrite(oldwrite, *args, **kwargs)
     setattr(ui, 'write', wrap)
     return oldwrite
 
 def filterchunks(ui, originalhunks, usecurses, testfile, operation=None):
     if usecurses:
         if testfile:
             recordfn = crecordmod.testdecorator(testfile,
                                                 crecordmod.testchunkselector)
         else:
             recordfn = crecordmod.chunkselector
 
         return crecordmod.filterpatch(ui, originalhunks, recordfn, operation)
 
     else:
         return patch.filterpatch(ui, originalhunks, operation)
 
 def recordfilter(ui, originalhunks, operation=None):
     """ Prompts the user to filter the originalhunks and return a list of
     selected hunks.
     *operation* is used for ui purposes to indicate the user
     what kind of filtering they are doing: reverting, committing, shelving, etc.
     *operation* has to be a translated string.
     """
     usecurses = crecordmod.checkcurses(ui)
     testfile = ui.config('experimental', 'crecordtest', None)
     oldwrite = setupwrapcolorwrite(ui)
     try:
         newchunks, newopts = filterchunks(ui, originalhunks, usecurses,
                                           testfile, operation)
     finally:
         ui.write = oldwrite
     return newchunks, newopts
 
 def dorecord(ui, repo, commitfunc, cmdsuggest, backupall,
             filterfn, *pats, **opts):
     from . import merge as mergemod
     if not ui.interactive():
         if cmdsuggest:
             msg = _('running non-interactively, use %s instead') % cmdsuggest
         else:
             msg = _('running non-interactively')
         raise error.Abort(msg)
 
     # make sure username is set before going interactive
     if not opts.get('user'):
         ui.username() # raise exception, username not provided
 
     def recordfunc(ui, repo, message, match, opts):
         """This is generic record driver.
 
         Its job is to interactively filter local changes, and
         accordingly prepare working directory into a state in which the
         job can be delegated to a non-interactive commit command such as
         'commit' or 'qrefresh'.
 
         After the actual job is done by non-interactive command, the
         working directory is restored to its original state.
 
         In the end we'll record interesting changes, and everything else
         will be left in place, so the user can continue working.
         """
 
         checkunfinished(repo, commit=True)
         wctx = repo[None]
         merge = len(wctx.parents()) > 1
         if merge:
             raise error.Abort(_('cannot partially commit a merge '
                                '(use "hg commit" instead)'))
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         force = opts.get('force')
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         status = repo.status(match=match)
         if not force:
             repo.checkcommitpatterns(wctx, vdirs, match, status, fail)
         diffopts = patch.difffeatureopts(ui, opts=opts, whitespace=True)
         diffopts.nodates = True
         diffopts.git = True
         diffopts.showfunc = True
         originaldiff = patch.diff(repo, changes=status, opts=diffopts)
         originalchunks = patch.parsepatch(originaldiff)
 
         # 1. filter patch, since we are intending to apply subset of it
         try:
             chunks, newopts = filterfn(ui, originalchunks)
         except patch.PatchError as err:
             raise error.Abort(_('error parsing patch: %s') % err)
         opts.update(newopts)
 
         # We need to keep a backup of files that have been newly added and
         # modified during the recording process because there is a previous
         # version without the edit in the workdir
         newlyaddedandmodifiedfiles = newandmodified(chunks, originalchunks)
         contenders = set()
         for h in chunks:
             try:
                 contenders.update(set(h.files()))
             except AttributeError:
                 pass
 
         changed = status.modified + status.added + status.removed
         newfiles = [f for f in changed if f in contenders]
         if not newfiles:
             ui.status(_('no changes to record\n'))
             return 0
 
         modified = set(status.modified)
 
         # 2. backup changed files, so we can restore them in the end
 
         if backupall:
             tobackup = changed
         else:
             tobackup = [f for f in newfiles if f in modified or f in \
                     newlyaddedandmodifiedfiles]
         backups = {}
         if tobackup:
             backupdir = repo.join('record-backups')
             try:
                 os.mkdir(backupdir)
             except OSError as err:
                 if err.errno != errno.EEXIST:
                     raise
         try:
             # backup continues
             for f in tobackup:
                 fd, tmpname = tempfile.mkstemp(prefix=f.replace('/', '_')+'.',
                                                dir=backupdir)
                 os.close(fd)
                 ui.debug('backup %r as %r\n' % (f, tmpname))
                 util.copyfile(repo.wjoin(f), tmpname, copystat=True)
                 backups[f] = tmpname
 
             fp = stringio()
             for c in chunks:
                 fname = c.filename()
                 if fname in backups:
                     c.write(fp)
             dopatch = fp.tell()
             fp.seek(0)
 
             # 2.5 optionally review / modify patch in text editor
             if opts.get('review', False):
                 patchtext = (crecordmod.diffhelptext
                              + crecordmod.patchhelptext
                              + fp.read())
                 reviewedpatch = ui.edit(patchtext, "",
                                         extra={"suffix": ".diff"})
                 fp.truncate(0)
                 fp.write(reviewedpatch)
                 fp.seek(0)
 
             [os.unlink(repo.wjoin(c)) for c in newlyaddedandmodifiedfiles]
             # 3a. apply filtered patch to clean repo  (clean)
             if backups:
                 # Equivalent to hg.revert
                 m = scmutil.matchfiles(repo, backups.keys())
                 mergemod.update(repo, repo.dirstate.p1(),
                         False, True, matcher=m)
 
             # 3b. (apply)
             if dopatch:
                 try:
                     ui.debug('applying patch\n')
                     ui.debug(fp.getvalue())
                     patch.internalpatch(ui, repo, fp, 1, eolmode=None)
                 except patch.PatchError as err:
                     raise error.Abort(str(err))
             del fp
 
             # 4. We prepared working directory according to filtered
             #    patch. Now is the time to delegate the job to
             #    commit/qrefresh or the like!
 
             # Make all of the pathnames absolute.
             newfiles = [repo.wjoin(nf) for nf in newfiles]
             return commitfunc(ui, repo, *newfiles, **opts)
         finally:
             # 5. finally restore backed-up files
             try:
                 dirstate = repo.dirstate
                 for realname, tmpname in backups.iteritems():
                     ui.debug('restoring %r to %r\n' % (tmpname, realname))
 
                     if dirstate[realname] == 'n':
                         # without normallookup, restoring timestamp
                         # may cause partially committed files
                         # to be treated as unmodified
                         dirstate.normallookup(realname)
 
                     # copystat=True here and above are a hack to trick any
                     # editors that have f open that we haven't modified them.
                     #
                     # Also note that this racy as an editor could notice the
                     # file's mtime before we've finished writing it.
                     util.copyfile(tmpname, repo.wjoin(realname), copystat=True)
                     os.unlink(tmpname)
                 if tobackup:
                     os.rmdir(backupdir)
             except OSError:
                 pass
 
     def recordinwlock(ui, repo, message, match, opts):
         with repo.wlock():
             return recordfunc(ui, repo, message, match, opts)
 
     return commit(ui, repo, recordinwlock, pats, opts)
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "^log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     allcmds = []
     for e in keys:
         aliases = parsealiases(e)
         allcmds.extend(aliases)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith("debug") or found.startswith("debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice, allcmds
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice, allcmds = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = choice.keys()
         clist.sort()
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return choice.values()[0]
 
     raise error.UnknownCommand(cmd, allcmds)
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def bailifchanged(repo, merge=True):
     if merge and repo.dirstate.p2() != nullid:
         raise error.Abort(_('outstanding uncommitted merge'))
     modified, added, removed, deleted = repo.status()[:4]
     if modified or added or removed or deleted:
         raise error.Abort(_('uncommitted changes'))
     ctx = repo[None]
     for s in sorted(ctx.substate):
         ctx.sub(s).bailifchanged()
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
     message = opts.get('message')
     logfile = opts.get('logfile')
 
     if message and logfile:
         raise error.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if logfile == '-':
                 message = ui.fin.read()
             else:
                 message = '\n'.join(util.readfile(logfile).splitlines())
         except IOError as inst:
             raise error.Abort(_("can't read commit message '%s': %s") %
                              (logfile, inst.strerror))
     return message
 
 def mergeeditform(ctxorbool, baseformname):
     """return appropriate editform name (referencing a committemplate)
 
     'ctxorbool' is either a ctx to be committed, or a bool indicating whether
     merging is committed.
 
     This returns baseformname with '.merge' appended if it is a merge,
     otherwise '.normal' is appended.
     """
     if isinstance(ctxorbool, bool):
         if ctxorbool:
             return baseformname + ".merge"
     elif 1 < len(ctxorbool.parents()):
         return baseformname + ".merge"
 
     return baseformname + ".normal"
 
 def getcommiteditor(edit=False, finishdesc=None, extramsg=None,
                     editform='', **opts):
     """get appropriate commit message editor according to '--edit' option
 
     'finishdesc' is a function to be called with edited commit message
     (= 'description' of the new changeset) just after editing, but
     before checking empty-ness. It should return actual text to be
     stored into history. This allows to change description before
     storing.
 
     'extramsg' is a extra message to be shown in the editor instead of
     'Leave message empty to abort commit' line. 'HG: ' prefix and EOL
     is automatically added.
 
     'editform' is a dot-separated list of names, to distinguish
     the purpose of commit text editing.
 
     'getcommiteditor' returns 'commitforceeditor' regardless of
     'edit', if one of 'finishdesc' or 'extramsg' is specified, because
     they are specific for usage in MQ.
     """
     if edit or finishdesc or extramsg:
         return lambda r, c, s: commitforceeditor(r, c, s,
                                                  finishdesc=finishdesc,
                                                  extramsg=extramsg,
                                                  editform=editform)
     elif editform:
         return lambda r, c, s: commiteditor(r, c, s, editform=editform)
     else:
         return commiteditor
 
 def loglimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get('limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise error.Abort(_('limit must be a positive integer'))
         if limit <= 0:
             raise error.Abort(_('limit must be positive'))
     else:
         limit = None
     return limit
 
 def makefilename(repo, pat, node, desc=None,
                   total=None, seqno=None, revwidth=None, pathname=None):
     node_expander = {
         'H': lambda: hex(node),
         'R': lambda: str(repo.changelog.rev(node)),
         'h': lambda: short(node),
         'm': lambda: re.sub('[^\w]', '_', str(desc))
         }
     expander = {
         '%': lambda: '%',
         'b': lambda: os.path.basename(repo.root),
         }
 
     try:
         if node:
             expander.update(node_expander)
         if node:
             expander['r'] = (lambda:
                     str(repo.changelog.rev(node)).zfill(revwidth or 0))
         if total is not None:
             expander['N'] = lambda: str(total)
         if seqno is not None:
             expander['n'] = lambda: str(seqno)
         if total is not None and seqno is not None:
             expander['n'] = lambda: str(seqno).zfill(len(str(total)))
         if pathname is not None:
             expander['s'] = lambda: os.path.basename(pathname)
             expander['d'] = lambda: os.path.dirname(pathname) or '.'
             expander['p'] = lambda: pathname
 
         newname = []
         patlen = len(pat)
         i = 0
         while i < patlen:
             c = pat[i]
             if c == '%':
                 i += 1
                 c = pat[i]
                 c = expander[c]()
             newname.append(c)
             i += 1
         return ''.join(newname)
     except KeyError as inst:
         raise error.Abort(_("invalid format spec '%%%s' in output filename") %
                          inst.args[0])
 
 class _unclosablefile(object):
     def __init__(self, fp):
         self._fp = fp
 
     def close(self):
         pass
 
     def __iter__(self):
         return iter(self._fp)
 
     def __getattr__(self, attr):
         return getattr(self._fp, attr)
 
 def makefileobj(repo, pat, node=None, desc=None, total=None,
                 seqno=None, revwidth=None, mode='wb', modemap=None,
                 pathname=None):
 
     writable = mode not in ('r', 'rb')
 
     if not pat or pat == '-':
         if writable:
             fp = repo.ui.fout
         else:
             fp = repo.ui.fin
         return _unclosablefile(fp)
     if util.safehasattr(pat, 'write') and writable:
         return pat
     if util.safehasattr(pat, 'read') and 'r' in mode:
         return pat
     fn = makefilename(repo, pat, node, desc, total, seqno, revwidth, pathname)
     if modemap is not None:
         mode = modemap.get(fn, mode)
         if mode == 'wb':
             modemap[fn] = 'ab'
     return open(fn, mode)
 
 def openrevlog(repo, cmd, file_, opts):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts['changelog']
     mf = opts['manifest']
     dir = opts['dir']
     msg = None
     if cl and mf:
         msg = _('cannot specify --changelog and --manifest at the same time')
     elif cl and dir:
         msg = _('cannot specify --changelog and --dir at the same time')
     elif cl or mf:
         if file_:
             msg = _('cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _('cannot specify --changelog or --manifest or --dir '
                     'without a repository')
     if msg:
         raise error.Abort(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.unfiltered().changelog
         elif dir:
             if 'treemanifest' not in repo.requirements:
                 raise error.Abort(_("--dir can only be used on repos with "
                                    "treemanifest enabled"))
             dirlog = repo.dirlog(file_)
             if len(dirlog):
                 r = dirlog
         elif mf:
             r = repo.manifest
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
     if not r:
         if not file_:
             raise error.CommandError(cmd, _('invalid arguments'))
         if not os.path.isfile(file_):
             raise error.Abort(_("revlog '%s' not found") % file_)
         r = revlog.revlog(scmutil.opener(os.getcwd(), audit=False),
                           file_[:-2] + ".i")
     return r
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get("after")
     dryrun = opts.get("dry_run")
     wctx = repo[None]
 
     def walkpat(pat):
         srcs = []
         if after:
             badstates = '?'
         else:
             badstates = '?r'
         m = scmutil.match(repo[None], [pat], opts, globbed=True)
         for abs in repo.walk(m):
             state = repo.dirstate[abs]
             rel = m.rel(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
                 if exact and state == 'r':
                     ui.warn(_('%s: not copying - file has been marked for'
                               ' remove\n') % rel)
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if '/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit('/', 1)
             abstarget = repo.dirstate.normalize(abspath) + '/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(_('%s: not overwriting - %s collides with %s\n') %
                     (reltarget, repo.pathto(abssrc, cwd),
                      repo.pathto(prevsrc, cwd)))
             return
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if (repo.dirstate.normalize(abssrc) ==
                 repo.dirstate.normalize(abstarget)):
                 if not rename:
                     ui.warn(_("%s: can't copy - same file\n") % reltarget)
                     return
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in 'mn':
             if not opts['force']:
                 ui.warn(_('%s: not overwriting - file exists\n') %
                         reltarget)
                 return
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(_('%s: not recording move - %s does not exist\n') %
                             (relsrc, reltarget))
                 else:
                     ui.warn(_('%s: not recording copy - %s does not exist\n') %
                             (relsrc, reltarget))
                 return
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or '.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + "~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     util.copyfile(src, target)
                 srcexists = True
             except IOError as inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working directory\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, inst.strerror))
                     return True # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_('moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_('copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(ui, repo, wctx, abssrc, abstarget,
                              dryrun=dryrun, cwd=cwd)
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 util.unlinkpath(repo.wjoin(abssrc))
             wctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(os.sep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(os.sep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(os.sep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest,
                                              util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(dest,
                                         os.path.basename(util.localpath(p)))
                 else:
                     res = lambda p: dest
         return res
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise error.Abort(_('no source or destination specified'))
     if len(pats) == 1:
         raise error.Abort(_('no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise error.Abort(_('with multiple sources, destination must be an '
                                'existing directory'))
         if util.endswithsep(dest):
             raise error.Abort(_('destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise error.Abort(_('no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     if errors:
         ui.warn(_('(consider using --after)\n'))
 
     return errors != 0
 
 def service(opts, parentfn=None, initfn=None, runfn=None, logfile=None,
     runargs=None, appendpid=False):
     '''Run a command as a service.'''
 
     def writepid(pid):
         if opts['pid_file']:
             if appendpid:
                 mode = 'a'
             else:
                 mode = 'w'
             fp = open(opts['pid_file'], mode)
             fp.write(str(pid) + '\n')
             fp.close()
 
     if opts['daemon'] and not opts['daemon_postexec']:
         # Signal child process startup with file removal
         lockfd, lockpath = tempfile.mkstemp(prefix='hg-service-')
         os.close(lockfd)
         try:
             if not runargs:
                 runargs = util.hgcmd() + sys.argv[1:]
             runargs.append('--daemon-postexec=unlink:%s' % lockpath)
             # Don't pass --cwd to the child process, because we've already
             # changed directory.
             for i in xrange(1, len(runargs)):
                 if runargs[i].startswith('--cwd='):
                     del runargs[i]
                     break
                 elif runargs[i].startswith('--cwd'):
                     del runargs[i:i + 2]
                     break
             def condfn():
                 return not os.path.exists(lockpath)
             pid = util.rundetached(runargs, condfn)
             if pid < 0:
                 raise error.Abort(_('child process failed to start'))
             writepid(pid)
         finally:
             try:
                 os.unlink(lockpath)
             except OSError as e:
                 if e.errno != errno.ENOENT:
                     raise
         if parentfn:
             return parentfn(pid)
         else:
             return
 
     if initfn:
         initfn()
 
     if not opts['daemon']:
         writepid(util.getpid())
 
     if opts['daemon_postexec']:
         try:
             os.setsid()
         except AttributeError:
             pass
         for inst in opts['daemon_postexec']:
             if inst.startswith('unlink:'):
                 lockpath = inst[7:]
                 os.unlink(lockpath)
             elif inst.startswith('chdir:'):
                 os.chdir(inst[6:])
             elif inst != 'none':
                 raise error.Abort(_('invalid value for --daemon-postexec: %s')
                                   % inst)
         util.hidewindow()
         sys.stdout.flush()
         sys.stderr.flush()
 
         nullfd = os.open(os.devnull, os.O_RDWR)
         logfilefd = nullfd
         if logfile:
             logfilefd = os.open(logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND)
         os.dup2(nullfd, 0)
         os.dup2(logfilefd, 1)
         os.dup2(logfilefd, 2)
         if nullfd not in (0, 1, 2):
             os.close(nullfd)
         if logfile and logfilefd not in (0, 1, 2):
             os.close(logfilefd)
 
     if runfn:
         return runfn()
 
 ## facility to let extension process additional data into an import patch
 # list of identifier to be executed in order
 extrapreimport = []  # run before commit
 extrapostimport = [] # run after commit
 # mapping from identifier to actual import function
 #
 # 'preimport' are run before the commit is made and are provided the following
 # arguments:
 # - repo: the localrepository instance,
 # - patchdata: data extracted from patch header (cf m.patch.patchheadermap),
 # - extra: the future extra dictionary of the changeset, please mutate it,
 # - opts: the import options.
 # XXX ideally, we would just pass an ctx ready to be computed, that would allow
 # mutation of in memory commit and more. Feel free to rework the code to get
 # there.
 extrapreimportmap = {}
 # 'postimport' are run after the commit is made and are provided the following
 # argument:
 # - ctx: the changectx created by import.
 extrapostimportmap = {}
 
 def tryimportone(ui, repo, hunk, parents, opts, msgs, updatefunc):
     """Utility function used by commands.import to import a single patch
 
     This function is explicitly defined here to help the evolve extension to
     wrap this part of the import logic.
 
     The API is currently a bit ugly because it a simple code translation from
     the import command. Feel free to make it better.
 
     :hunk: a patch (as a binary string)
     :parents: nodes that will be parent of the created commit
     :opts: the full dict of option passed to the import command
     :msgs: list to save commit message to.
            (used in case we need to save it when failing)
     :updatefunc: a function that update a repo to a given node
                  updatefunc(<repo>, <node>)
     """
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
     extractdata = patch.extract(ui, hunk)
     tmpname = extractdata.get('filename')
     message = extractdata.get('message')
     user = opts.get('user') or extractdata.get('user')
     date = opts.get('date') or extractdata.get('date')
     branch = extractdata.get('branch')
     nodeid = extractdata.get('nodeid')
     p1 = extractdata.get('p1')
     p2 = extractdata.get('p2')
 
     nocommit = opts.get('no_commit')
     importbranch = opts.get('import_branch')
     update = not opts.get('bypass')
     strip = opts["strip"]
     prefix = opts["prefix"]
     sim = float(opts.get('similarity') or 0)
     if not tmpname:
         return (None, None, False)
 
     rejects = False
 
     try:
         cmdline_message = logmessage(ui, opts)
         if cmdline_message:
             # pickup the cmdline msg
             message = cmdline_message
         elif message:
             # pickup the patch msg
             message = message.strip()
         else:
             # launch the editor
             message = None
         ui.debug('message:\n%s\n' % message)
 
         if len(parents) == 1:
             parents.append(repo[nullid])
         if opts.get('exact'):
             if not nodeid or not p1:
                 raise error.Abort(_('not a Mercurial patch'))
             p1 = repo[p1]
             p2 = repo[p2 or nullid]
         elif p2:
             try:
                 p1 = repo[p1]
                 p2 = repo[p2]
                 # Without any options, consider p2 only if the
                 # patch is being applied on top of the recorded
                 # first parent.
                 if p1 != parents[0]:
                     p1 = parents[0]
                     p2 = repo[nullid]
             except error.RepoError:
                 p1, p2 = parents
             if p2.node() == nullid:
                 ui.warn(_("warning: import the patch as a normal revision\n"
                           "(use --exact to import the patch as a merge)\n"))
         else:
             p1, p2 = parents
 
         n = None
         if update:
             if p1 != parents[0]:
                 updatefunc(repo, p1.node())
             if p2 != parents[1]:
                 repo.setparents(p1.node(), p2.node())
 
             if opts.get('exact') or importbranch:
                 repo.dirstate.setbranch(branch or 'default')
 
             partial = opts.get('partial', False)
             files = set()
             try:
                 patch.patch(ui, repo, tmpname, strip=strip, prefix=prefix,
                             files=files, eolmode=None, similarity=sim / 100.0)
             except patch.PatchError as e:
                 if not partial:
                     raise error.Abort(str(e))
                 if partial:
                     rejects = True
 
             files = list(files)
             if nocommit:
                 if message:
                     msgs.append(message)
             else:
                 if opts.get('exact') or p2:
                     # If you got here, you either use --force and know what
                     # you are doing or used --exact or a merge patch while
                     # being updated to its first parent.
                     m = None
                 else:
                     m = scmutil.matchfiles(repo, files or [])
                 editform = mergeeditform(repo[None], 'import.normal')
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform=editform, **opts)
                 allowemptyback = repo.ui.backupconfig('ui', 'allowemptycommit')
                 extra = {}
                 for idfunc in extrapreimport:
                     extrapreimportmap[idfunc](repo, extractdata, extra, opts)
                 try:
                     if partial:
                         repo.ui.setconfig('ui', 'allowemptycommit', True)
                     n = repo.commit(message, user,
                                     date, match=m,
                                     editor=editor, extra=extra)
                     for idfunc in extrapostimport:
                         extrapostimportmap[idfunc](repo[n])
                 finally:
                     repo.ui.restoreconfig(allowemptyback)
         else:
             if opts.get('exact') or importbranch:
                 branch = branch or 'default'
             else:
                 branch = p1.branch()
             store = patch.filestore()
             try:
                 files = set()
                 try:
                     patch.patchrepo(ui, repo, p1, store, tmpname, strip, prefix,
                                     files, eolmode=None)
                 except patch.PatchError as e:
                     raise error.Abort(str(e))
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform='import.bypass')
                 memctx = context.makememctx(repo, (p1.node(), p2.node()),
                                             message,
                                             user,
                                             date,
                                             branch, files, store,
                                             editor=editor)
                 n = memctx.commit()
             finally:
                 store.close()
         if opts.get('exact') and nocommit:
             # --exact with --no-commit is still useful in that it does merge
             # and branch bits
             ui.warn(_("warning: can't check exact import with --no-commit\n"))
         elif opts.get('exact') and hex(n) != nodeid:
             raise error.Abort(_('patch is damaged or loses information'))
         msg = _('applied to working directory')
         if n:
             # i18n: refers to a short changeset id
             msg = _('created %s') % short(n)
         return (msg, n, rejects)
     finally:
         os.unlink(tmpname)
 
 # facility to let extensions include additional data in an exported patch
 # list of identifiers to be executed in order
 extraexport = []
 # mapping from identifier to actual export function
 # function as to return a string to be added to the header or None
 # it is given two arguments (sequencenumber, changectx)
 extraexportmap = {}
 
 def export(repo, revs, template='hg-%h.patch', fp=None, switch_parent=False,
            opts=None, match=None):
     '''export changesets as hg patches.'''
 
     total = len(revs)
     revwidth = max([len(str(rev)) for rev in revs])
     filemode = {}
 
     def single(rev, seqno, fp):
         ctx = repo[rev]
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()
         if switch_parent:
             parents.reverse()
 
         if parents:
             prev = parents[0]
         else:
             prev = nullid
 
         shouldclose = False
         if not fp and len(template) > 0:
             desc_lines = ctx.description().rstrip().split('\n')
             desc = desc_lines[0]    #Commit always has a first line.
             fp = makefileobj(repo, template, node, desc=desc, total=total,
                              seqno=seqno, revwidth=revwidth, mode='wb',
                              modemap=filemode)
             shouldclose = True
         if fp and not getattr(fp, 'name', '<unnamed>').startswith('<'):
             repo.ui.note("%s\n" % fp.name)
 
         if not fp:
             write = repo.ui.write
         else:
             def write(s, **kw):
                 fp.write(s)
 
         write("# HG changeset patch\n")
         write("# User %s\n" % ctx.user())
         write("# Date %d %d\n" % ctx.date())
         write("#      %s\n" % util.datestr(ctx.date()))
         if branch and branch != 'default':
             write("# Branch %s\n" % branch)
         write("# Node ID %s\n" % hex(node))
         write("# Parent  %s\n" % hex(prev))
         if len(parents) > 1:
             write("# Parent  %s\n" % hex(parents[1]))
 
         for headerid in extraexport:
             header = extraexportmap[headerid](seqno, ctx)
             if header is not None:
                 write('# %s\n' % header)
         write(ctx.description().rstrip())
         write("\n\n")
 
         for chunk, label in patch.diffui(repo, prev, node, match, opts=opts):
             write(chunk, label=label)
 
         if shouldclose:
             fp.close()
 
     for seqno, rev in enumerate(revs):
         single(rev, seqno + 1, fp)
 
 def diffordiffstat(ui, repo, diffopts, node1, node2, match,
                    changes=None, stat=False, fp=None, prefix='',
                    root='', listsubrepos=False):
     '''show diff or diffstat.'''
     if fp is None:
         write = ui.write
     else:
         def write(s, **kw):
             fp.write(s)
 
     if root:
         relroot = pathutil.canonpath(repo.root, repo.getcwd(), root)
     else:
         relroot = ''
     if relroot != '':
         # XXX relative roots currently don't work if the root is within a
         # subrepo
         uirelroot = match.uipath(relroot)
         relroot += '/'
         for matchroot in match.files():
             if not matchroot.startswith(relroot):
                 ui.warn(_('warning: %s not inside relative root %s\n') % (
                     match.uipath(matchroot), uirelroot))
 
     if stat:
         diffopts = diffopts.copy(context=0)
         width = 80
         if not ui.plain():
             width = ui.termwidth()
         chunks = patch.diff(repo, node1, node2, match, changes, diffopts,
                             prefix=prefix, relroot=relroot)
         for chunk, label in patch.diffstatui(util.iterlines(chunks),
                                              width=width,
                                              git=diffopts.git):
             write(chunk, label=label)
     else:
         for chunk, label in patch.diffui(repo, node1, node2, match,
                                          changes, diffopts, prefix=prefix,
                                          relroot=relroot):
             write(chunk, label=label)
 
     if listsubrepos:
         ctx1 = repo[node1]
         ctx2 = repo[node2]
         for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
             tempnode2 = node2
             try:
                 if node2 is not None:
                     tempnode2 = ctx2.substate[subpath][1]
             except KeyError:
                 # A subrepo that existed in node1 was deleted between node1 and
                 # node2 (inclusive). Thus, ctx2's substate won't contain that
                 # subpath. The best we can do is to ignore it.
                 tempnode2 = None
             submatch = matchmod.subdirmatcher(subpath, match)
             sub.diff(ui, diffopts, tempnode2, submatch, changes=changes,
                      stat=stat, fp=fp, prefix=prefix)
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, matchfn, diffopts, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.matchfn = matchfn
         self.diffopts = diffopts
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
 
     def flush(self, ctx):
         rev = ctx.rev()
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
             return 1
         return 0
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, matchfn=None, **props):
         if self.buffered:
             self.ui.pushbuffer(labeled=True)
             self._show(ctx, copies, matchfn, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer()
         else:
             self._show(ctx, copies, matchfn, props)
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         rev = ctx.rev()
         if self.ui.debugflag:
             hexfunc = hex
         else:
             hexfunc = short
         # as of now, wctx.node() and wctx.rev() return None, but we want to
         # show the same values as {node} and {rev} templatekw
         revnode = (scmutil.intrev(rev), hexfunc(bin(ctx.hex())))
 
         if self.ui.quiet:
             self.ui.write("%d:%s\n" % revnode, label='log.node')
             return
 
         date = util.datestr(ctx.date())
 
         # i18n: column positioning for "hg log"
         self.ui.write(_("changeset:   %d:%s\n") % revnode,
                       label='log.changeset changeset.%s' % ctx.phasestr())
 
         # branches are shown first before any other names due to backwards
         # compatibility
         branch = ctx.branch()
         # don't show the default branch name
         if branch != 'default':
             # i18n: column positioning for "hg log"
             self.ui.write(_("branch:      %s\n") % branch,
                           label='log.branch')
 
         for nsname, ns in self.repo.names.iteritems():
             # branches has special logic already handled above, so here we just
             # skip it
             if nsname == 'branches':
                 continue
             # we will use the templatename as the color name since those two
             # should be the same
             for name in ns.names(self.repo, changenode):
                 self.ui.write(ns.logfmt % name,
                               label='log.%s' % ns.colorname)
         if self.ui.debugflag:
             # i18n: column positioning for "hg log"
             self.ui.write(_("phase:       %s\n") % ctx.phasestr(),
                           label='log.phase')
         for pctx in scmutil.meaningfulparents(self.repo, ctx):
             label = 'log.parent changeset.%s' % pctx.phasestr()
             # i18n: column positioning for "hg log"
             self.ui.write(_("parent:      %d:%s\n")
                           % (pctx.rev(), hexfunc(pctx.node())),
                           label=label)
 
         if self.ui.debugflag and rev is not None:
             mnode = ctx.manifestnode()
             # i18n: column positioning for "hg log"
             self.ui.write(_("manifest:    %d:%s\n") %
                           (self.repo.manifest.rev(mnode), hex(mnode)),
                           label='ui.debug log.manifest')
         # i18n: column positioning for "hg log"
         self.ui.write(_("user:        %s\n") % ctx.user(),
                       label='log.user')
         # i18n: column positioning for "hg log"
         self.ui.write(_("date:        %s\n") % date,
                       label='log.date')
 
         if self.ui.debugflag:
             files = ctx.p1().status(ctx)[:3]
             for key, value in zip([# i18n: column positioning for "hg log"
                                    _("files:"),
                                    # i18n: column positioning for "hg log"
                                    _("files+:"),
                                    # i18n: column positioning for "hg log"
                                    _("files-:")], files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)),
                                   label='ui.debug log.files')
         elif ctx.files() and self.ui.verbose:
             # i18n: column positioning for "hg log"
             self.ui.write(_("files:       %s\n") % " ".join(ctx.files()),
                           label='ui.note log.files')
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             # i18n: column positioning for "hg log"
             self.ui.write(_("copies:      %s\n") % ' '.join(copies),
                           label='ui.note log.copies')
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')),
                               label='ui.debug log.extra')
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"),
                               label='ui.note log.description')
                 self.ui.write(description,
                               label='ui.note log.description')
                 self.ui.write("\n\n")
             else:
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0],
                               label='log.summary')
         self.ui.write("\n")
 
         self.showpatch(ctx, matchfn)
 
     def showpatch(self, ctx, matchfn):
         if not matchfn:
             matchfn = self.matchfn
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.diffallopts(self.ui, self.diffopts)
             node = ctx.node()
             prev = ctx.p1().node()
             if stat:
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
             if diff:
                 if stat:
                     self.ui.write("\n")
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
             self.ui.write("\n")
 
 class jsonchangeset(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, matchfn, diffopts, buffered):
         changeset_printer.__init__(self, ui, repo, matchfn, diffopts, buffered)
         self.cache = {}
         self._first = True
 
     def close(self):
         if not self._first:
             self.ui.write("\n]\n")
         else:
             self.ui.write("[]\n")
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         rev = ctx.rev()
         if rev is None:
             jrev = jnode = 'null'
         else:
             jrev = str(rev)
             jnode = '"%s"' % hex(ctx.node())
         j = encoding.jsonescape
 
         if self._first:
             self.ui.write("[\n {")
             self._first = False
         else:
             self.ui.write(",\n {")
 
         if self.ui.quiet:
             self.ui.write('\n  "rev": %s' % jrev)
             self.ui.write(',\n  "node": %s' % jnode)
             self.ui.write('\n }')
             return
 
         self.ui.write('\n  "rev": %s' % jrev)
         self.ui.write(',\n  "node": %s' % jnode)
         self.ui.write(',\n  "branch": "%s"' % j(ctx.branch()))
         self.ui.write(',\n  "phase": "%s"' % ctx.phasestr())
         self.ui.write(',\n  "user": "%s"' % j(ctx.user()))
         self.ui.write(',\n  "date": [%d, %d]' % ctx.date())
         self.ui.write(',\n  "desc": "%s"' % j(ctx.description()))
 
         self.ui.write(',\n  "bookmarks": [%s]' %
                       ", ".join('"%s"' % j(b) for b in ctx.bookmarks()))
         self.ui.write(',\n  "tags": [%s]' %
                       ", ".join('"%s"' % j(t) for t in ctx.tags()))
         self.ui.write(',\n  "parents": [%s]' %
                       ", ".join('"%s"' % c.hex() for c in ctx.parents()))
 
         if self.ui.debugflag:
             if rev is None:
                 jmanifestnode = 'null'
             else:
                 jmanifestnode = '"%s"' % hex(ctx.manifestnode())
             self.ui.write(',\n  "manifest": %s' % jmanifestnode)
 
             self.ui.write(',\n  "extra": {%s}' %
                           ", ".join('"%s": "%s"' % (j(k), j(v))
                                     for k, v in ctx.extra().items()))
 
             files = ctx.p1().status(ctx)
             self.ui.write(',\n  "modified": [%s]' %
                           ", ".join('"%s"' % j(f) for f in files[0]))
             self.ui.write(',\n  "added": [%s]' %
                           ", ".join('"%s"' % j(f) for f in files[1]))
             self.ui.write(',\n  "removed": [%s]' %
                           ", ".join('"%s"' % j(f) for f in files[2]))
 
         elif self.ui.verbose:
             self.ui.write(',\n  "files": [%s]' %
                           ", ".join('"%s"' % j(f) for f in ctx.files()))
 
             if copies:
                 self.ui.write(',\n  "copies": {%s}' %
                               ", ".join('"%s": "%s"' % (j(k), j(v))
                                                         for k, v in copies))
 
         matchfn = self.matchfn
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.difffeatureopts(self.ui, self.diffopts, git=True)
             node, prev = ctx.node(), ctx.p1().node()
             if stat:
                 self.ui.pushbuffer()
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
                 self.ui.write(',\n  "diffstat": "%s"' % j(self.ui.popbuffer()))
             if diff:
                 self.ui.pushbuffer()
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
                 self.ui.write(',\n  "diff": "%s"' % j(self.ui.popbuffer()))
 
         self.ui.write("\n }")
 
 class changeset_templater(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, matchfn, diffopts, tmpl, mapfile, buffered):
         changeset_printer.__init__(self, ui, repo, matchfn, diffopts, buffered)
         formatnode = ui.debugflag and (lambda x: x) or (lambda x: x[:12])
         filters = {'formatnode': formatnode}
         defaulttempl = {
             'parent': '{rev}:{node|formatnode} ',
             'manifest': '{rev}:{node|formatnode}',
             'file_copy': '{name} ({source})',
             'extra': '{key}={value|stringescape}'
             }
         # filecopy is preserved for compatibility reasons
         defaulttempl['filecopy'] = defaulttempl['file_copy']
         assert not (tmpl and mapfile)
         if mapfile:
             self.t = templater.templater.frommapfile(mapfile, filters=filters,
                                                      cache=defaulttempl)
         else:
             self.t = formatter.maketemplater(ui, 'changeset', tmpl,
                                              filters=filters,
                                              cache=defaulttempl)
 
         self.cache = {}
 
         # find correct templates for current mode
         tmplmodes = [
             (True, None),
             (self.ui.verbose, 'verbose'),
             (self.ui.quiet, 'quiet'),
             (self.ui.debugflag, 'debug'),
         ]
 
         self._parts = {'header': '', 'footer': '', 'changeset': 'changeset',
                        'docheader': '', 'docfooter': ''}
         for mode, postfix in tmplmodes:
             for t in self._parts:
                 cur = t
                 if postfix:
                     cur += "_" + postfix
                 if mode and cur in self.t:
                     self._parts[t] = cur
 
         if self._parts['docheader']:
             self.ui.write(templater.stringify(self.t(self._parts['docheader'])))
 
     def close(self):
         if self._parts['docfooter']:
             if not self.footer:
                 self.footer = ""
             self.footer += templater.stringify(self.t(self._parts['docfooter']))
         return super(changeset_templater, self).close()
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         props = props.copy()
         props.update(templatekw.keywords)
         props['templ'] = self.t
         props['ctx'] = ctx
         props['repo'] = self.repo
         props['ui'] = self.repo.ui
         props['revcache'] = {'copies': copies}
         props['cache'] = self.cache
 
         # write header
         if self._parts['header']:
             h = templater.stringify(self.t(self._parts['header'], **props))
             if self.buffered:
                 self.header[ctx.rev()] = h
             else:
                 if self.lastheader != h:
                     self.lastheader = h
                     self.ui.write(h)
 
         # write changeset metadata, then patch if requested
         key = self._parts['changeset']
         self.ui.write(templater.stringify(self.t(key, **props)))
         self.showpatch(ctx, matchfn)
 
         if self._parts['footer']:
             if not self.footer:
                 self.footer = templater.stringify(
                     self.t(self._parts['footer'], **props))
 
 def gettemplate(ui, tmpl, style):
     """
     Find the template matching the given template spec or style.
     """
 
     # ui settings
     if not tmpl and not style: # template are stronger than style
         tmpl = ui.config('ui', 'logtemplate')
         if tmpl:
             return templater.unquotestring(tmpl), None
         else:
             style = util.expandpath(ui.config('ui', 'style', ''))
 
     if not tmpl and style:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = (templater.templatepath('map-cmdline.' + mapfile)
                        or templater.templatepath(mapfile))
             if mapname:
                 mapfile = mapname
         return None, mapfile
 
     if not tmpl:
         return None, None
 
     return formatter.lookuptemplate(ui, 'changeset', tmpl)
 
 def show_changeset(ui, repo, opts, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changeset_printer() is done.
     """
     # options
     matchfn = None
     if opts.get('patch') or opts.get('stat'):
         matchfn = scmutil.matchall(repo)
 
     if opts.get('template') == 'json':
         return jsonchangeset(ui, repo, matchfn, opts, buffered)
 
     tmpl, mapfile = gettemplate(ui, opts.get('template'), opts.get('style'))
 
     if not tmpl and not mapfile:
         return changeset_printer(ui, repo, matchfn, opts, buffered)
 
     return changeset_templater(ui, repo, matchfn, opts, tmpl, mapfile, buffered)
 
 def showmarker(ui, marker, index=None):
     """utility function to display obsolescence marker in a readable way
 
     To be used by debug function."""
     if index is not None:
         ui.write("%i " % index)
     ui.write(hex(marker.precnode()))
     for repl in marker.succnodes():
         ui.write(' ')
         ui.write(hex(repl))
     ui.write(' %X ' % marker.flags())
     parents = marker.parentnodes()
     if parents is not None:
         ui.write('{%s} ' % ', '.join(hex(p) for p in parents))
     ui.write('(%s) ' % util.datestr(marker.date()))
     ui.write('{%s}' % (', '.join('%r: %r' % t for t in
                                  sorted(marker.metadata().items())
                                  if t[0] != 'date')))
     ui.write('\n')
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = util.matchdate(date)
     m = scmutil.matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(_("found revision %s from %s\n") %
                       (rev, util.datestr(results[rev])))
             return str(rev)
 
     raise error.Abort(_("revision matching date not found"))
 
 def increasingwindows(windowsize=8, sizelimit=512):
     while True:
         yield windowsize
         if windowsize < sizelimit:
             windowsize *= 2
 
 class FileWalkError(Exception):
     pass
 
 def walkfilerevs(repo, match, follow, revs, fncache):
     '''Walks the file history for the matched files.
 
     Returns the changeset revs that are involved in the file history.
 
     Throws FileWalkError if the file history can't be walked using
     filelogs alone.
     '''
     wanted = set()
     copies = []
     minrev, maxrev = min(revs), max(revs)
     def filerevgen(filelog, last):
         """
         Only files, no patterns.  Check the history of each file.
 
         Examines filelog entries within minrev, maxrev linkrev range
         Returns an iterator yielding (linkrev, parentlinkrevs, copied)
         tuples in backwards order
         """
         cl_count = len(repo)
         revs = []
         for j in xrange(0, last + 1):
             linkrev = filelog.linkrev(j)
             if linkrev < minrev:
                 continue
             # only yield rev for which we have the changelog, it can
             # happen while doing "hg log" during a pull or commit
             if linkrev >= cl_count:
                 break
 
             parentlinkrevs = []
             for p in filelog.parentrevs(j):
                 if p != nullrev:
                     parentlinkrevs.append(filelog.linkrev(p))
             n = filelog.node(j)
             revs.append((linkrev, parentlinkrevs,
                          follow and filelog.renamed(n)))
 
         return reversed(revs)
     def iterfiles():
         pctx = repo['.']
         for filename in match.files():
             if follow:
                 if filename not in pctx:
                     raise error.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % filename)
                 yield filename, pctx[filename].filenode()
             else:
                 yield filename, None
         for filename_node in copies:
             yield filename_node
 
     for file_, node in iterfiles():
         filelog = repo.file(file_)
         if not len(filelog):
             if node is None:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _('cannot follow nonexistent file: "%s"') % file_)
                 raise FileWalkError("Cannot walk via filelog")
             else:
                 continue
 
         if node is None:
             last = len(filelog) - 1
         else:
             last = filelog.rev(node)
 
         # keep track of all ancestors of the file
         ancestors = set([filelog.linkrev(last)])
 
         # iterate from latest to oldest revision
         for rev, flparentlinkrevs, copied in filerevgen(filelog, last):
             if not follow:
                 if rev > maxrev:
                     continue
             else:
                 # Note that last might not be the first interesting
                 # rev to us:
                 # if the file has been changed after maxrev, we'll
                 # have linkrev(last) > maxrev, and we still need
                 # to explore the file graph
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
             fncache.setdefault(rev, []).append(file_)
             wanted.add(rev)
             if copied:
                 copies.append(copied)
 
     return wanted
 
 class _followfilter(object):
     def __init__(self, repo, onlyfirst=False):
         self.repo = repo
         self.startrev = nullrev
         self.roots = set()
         self.onlyfirst = onlyfirst
 
     def match(self, rev):
         def realparents(rev):
             if self.onlyfirst:
                 return self.repo.changelog.parentrevs(rev)[0:1]
             else:
                 return filter(lambda x: x != nullrev,
                               self.repo.changelog.parentrevs(rev))
 
         if self.startrev == nullrev:
             self.startrev = rev
             return True
 
         if rev > self.startrev:
             # forward: all descendants
             if not self.roots:
                 self.roots.add(self.startrev)
             for parent in realparents(rev):
                 if parent in self.roots:
                     self.roots.add(rev)
                     return True
         else:
             # backwards: all parents
             if not self.roots:
                 self.roots.update(realparents(self.startrev))
             if rev in self.roots:
                 self.roots.remove(rev)
                 self.roots.update(realparents(rev))
                 return True
 
         return False
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     follow = opts.get('follow') or opts.get('follow_first')
     revs = _logrevs(repo, opts)
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or ((match.isexact() or match.prefix()) and
                                    opts.get('removed'))
     fncache = {}
     change = repo.changectx
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if match.always():
         # No files, no patterns.  Display all revs.
         wanted = revs
     elif not slowpath:
         # We only have to read through the filelog to find wanted revisions
 
         try:
             wanted = walkfilerevs(repo, match, follow, revs, fncache)
         except FileWalkError:
             slowpath = True
 
             # We decided to fall back to the slowpath because at least one
             # of the paths was not a file. Check to see if at least one of them
             # existed in history, otherwise simply return
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 return []
 
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise error.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
 
         # The slow path checks files modified in every changeset.
         # This is really slow on large repos, so compute the set lazily.
         class lazywantedset(object):
             def __init__(self):
                 self.set = set()
                 self.revs = set(revs)
 
             # No need to worry about locality here because it will be accessed
             # in the same order as the increasing window below.
             def __contains__(self, value):
                 if value in self.set:
                     return True
                 elif not value in self.revs:
                     return False
                 else:
                     self.revs.discard(value)
                     ctx = change(value)
                     matches = filter(match, ctx.files())
                     if matches:
                         fncache[value] = matches
                         self.set.add(value)
                         return True
                     return False
 
             def discard(self, value):
                 self.revs.discard(value)
                 self.set.discard(value)
 
         wanted = lazywantedset()
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get('prune', ()):
         rev = repo[rev].rev()
         ff = _followfilter(repo)
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted = wanted - [x]
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and match.always():
             ff = _followfilter(repo, onlyfirst=opts.get('follow_first'))
             def want(rev):
                 return ff.match(rev) and rev in wanted
         else:
             def want(rev):
                 return rev in wanted
 
         it = iter(revs)
         stopiteration = False
         for windowsize in increasingwindows():
             nrevs = []
             for i in xrange(windowsize):
                 rev = next(it, None)
                 if rev is None:
                     stopiteration = True
                     break
                 elif want(rev):
                     nrevs.append(rev)
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
                     def fns_generator():
                         for f in ctx.files():
                             if match(f):
                                 yield f
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
 
             if stopiteration:
                 break
 
     return iterate()
 
 def _makefollowlogfilematcher(repo, files, followfirst):
     # When displaying a revision with --patch --follow FILE, we have
     # to know which file of the revision must be diffed. With
     # --follow, we want the names of the ancestors of FILE in the
     # revision, stored in "fcache". "fcache" is populated by
     # reproducing the graph traversal already done by --follow revset
     # and relating linkrevs to file names (which is not "correct" but
     # good enough).
     fcache = {}
     fcacheready = [False]
     pctx = repo['.']
 
     def populate():
         for fn in files:
             for i in ((pctx[fn],), pctx[fn].ancestors(followfirst=followfirst)):
                 for c in i:
                     fcache.setdefault(c.linkrev(), set()).add(c.path())
 
     def filematcher(rev):
         if not fcacheready[0]:
             # Lazy initialization
             fcacheready[0] = True
             populate()
         return scmutil.matchfiles(repo, fcache.get(rev, []))
 
     return filematcher
 
 def _makenofollowlogfilematcher(repo, pats, opts):
     '''hook for extensions to override the filematcher for non-follow cases'''
     return None
 
 def _makelogrevset(repo, pats, opts, revs):
     """Return (expr, filematcher) where expr is a revset string built
     from log options and file patterns or None. If --stat or --patch
     are not passed filematcher is None. Otherwise it is a callable
     taking a revision number and returning a match objects filtering
     the files to be detailed when displaying the revision.
     """
     opt2revset = {
         'no_merges':        ('not merge()', None),
         'only_merges':      ('merge()', None),
         '_ancestors':       ('ancestors(%(val)s)', None),
         '_fancestors':      ('_firstancestors(%(val)s)', None),
         '_descendants':     ('descendants(%(val)s)', None),
         '_fdescendants':    ('_firstdescendants(%(val)s)', None),
         '_matchfiles':      ('_matchfiles(%(val)s)', None),
         'date':             ('date(%(val)r)', None),
         'branch':           ('branch(%(val)r)', ' or '),
         '_patslog':         ('filelog(%(val)r)', ' or '),
         '_patsfollow':      ('follow(%(val)r)', ' or '),
         '_patsfollowfirst': ('_followfirst(%(val)r)', ' or '),
         'keyword':          ('keyword(%(val)r)', ' or '),
         'prune':            ('not (%(val)r or ancestors(%(val)r))', ' and '),
         'user':             ('user(%(val)r)', ' or '),
         }
 
     opts = dict(opts)
     # follow or not follow?
     follow = opts.get('follow') or opts.get('follow_first')
     if opts.get('follow_first'):
         followfirst = 1
     else:
         followfirst = 0
     # --follow with FILE behavior depends on revs...
     it = iter(revs)
-    startrev = it.next()
+    startrev = next(it)
     followdescendants = startrev < next(it, startrev)
 
     # branch and only_branch are really aliases and must be handled at
     # the same time
     opts['branch'] = opts.get('branch', []) + opts.get('only_branch', [])
     opts['branch'] = [repo.lookupbranch(b) for b in opts['branch']]
     # pats/include/exclude are passed to match.match() directly in
     # _matchfiles() revset but walkchangerevs() builds its matcher with
     # scmutil.match(). The difference is input pats are globbed on
     # platforms without shell expansion (windows).
     wctx = repo[None]
     match, pats = scmutil.matchandpats(wctx, pats, opts)
     slowpath = match.anypats() or ((match.isexact() or match.prefix()) and
                                    opts.get('removed'))
     if not slowpath:
         for f in match.files():
             if follow and f not in wctx:
                 # If the file exists, it may be a directory, so let it
                 # take the slow path.
                 if os.path.exists(repo.wjoin(f)):
                     slowpath = True
                     continue
                 else:
                     raise error.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % f)
             filelog = repo.file(f)
             if not filelog:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _('cannot follow nonexistent file: "%s"') % f)
                 slowpath = True
 
         # We decided to fall back to the slowpath because at least one
         # of the paths was not a file. Check to see if at least one of them
         # existed in history - in that case, we'll continue down the
         # slowpath; otherwise, we can turn off the slowpath
         if slowpath:
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 slowpath = False
 
     fpats = ('_patsfollow', '_patsfollowfirst')
     fnopats = (('_ancestors', '_fancestors'),
                ('_descendants', '_fdescendants'))
     if slowpath:
         # See walkchangerevs() slow path.
         #
         # pats/include/exclude cannot be represented as separate
         # revset expressions as their filtering logic applies at file
         # level. For instance "-I a -X a" matches a revision touching
         # "a" and "b" while "file(a) and not file(b)" does
         # not. Besides, filesets are evaluated against the working
         # directory.
         matchargs = ['r:', 'd:relpath']
         for p in pats:
             matchargs.append('p:' + p)
         for p in opts.get('include', []):
             matchargs.append('i:' + p)
         for p in opts.get('exclude', []):
             matchargs.append('x:' + p)
         matchargs = ','.join(('%r' % p) for p in matchargs)
         opts['_matchfiles'] = matchargs
         if follow:
             opts[fnopats[0][followfirst]] = '.'
     else:
         if follow:
             if pats:
                 # follow() revset interprets its file argument as a
                 # manifest entry, so use match.files(), not pats.
                 opts[fpats[followfirst]] = list(match.files())
             else:
                 op = fnopats[followdescendants][followfirst]
                 opts[op] = 'rev(%d)' % startrev
         else:
             opts['_patslog'] = list(pats)
 
     filematcher = None
     if opts.get('patch') or opts.get('stat'):
         # When following files, track renames via a special matcher.
         # If we're forced to take the slowpath it means we're following
         # at least one pattern/directory, so don't bother with rename tracking.
         if follow and not match.always() and not slowpath:
             # _makefollowlogfilematcher expects its files argument to be
             # relative to the repo root, so use match.files(), not pats.
             filematcher = _makefollowlogfilematcher(repo, match.files(),
                                                     followfirst)
         else:
             filematcher = _makenofollowlogfilematcher(repo, pats, opts)
             if filematcher is None:
                 filematcher = lambda rev: match
 
     expr = []
     for op, val in sorted(opts.iteritems()):
         if not val:
             continue
         if op not in opt2revset:
             continue
         revop, andor = opt2revset[op]
         if '%(val)' not in revop:
             expr.append(revop)
         else:
             if not isinstance(val, list):
                 e = revop % {'val': val}
             else:
                 e = '(' + andor.join((revop % {'val': v}) for v in val) + ')'
             expr.append(e)
 
     if expr:
         expr = '(' + ' and '.join(expr) + ')'
     else:
         expr = None
     return expr, filematcher
 
 def _logrevs(repo, opts):
     # Default --rev value depends on --follow but --follow behavior
     # depends on revisions resolved from --rev...
     follow = opts.get('follow') or opts.get('follow_first')
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts['rev'])
     elif follow and repo.dirstate.p1() == nullid:
         revs = revset.baseset()
     elif follow:
         revs = repo.revs('reverse(:.)')
     else:
         revs = revset.spanset(repo)
         revs.reverse()
     return revs
 
 def getgraphlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     limit = loglimit(opts)
     revs = _logrevs(repo, opts)
     if not revs:
         return revset.baseset(), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if opts.get('rev'):
         # User-specified revs might be unsorted, but don't sort before
         # _makelogrevset because it might depend on the order of revs
         revs.sort(reverse=True)
     if expr:
         # Revset matchers often operate faster on revisions in changelog
         # order, because most filters deal with the changelog.
         revs.reverse()
         matcher = revset.match(repo.ui, expr)
         # Revset matches can reorder revisions. "A or B" typically returns
         # returns the revision matching A then the revision matching B. Sort
         # again to fix that.
         revs = matcher(repo, revs)
         revs.sort(reverse=True)
     if limit is not None:
         limitedrevs = []
         for idx, rev in enumerate(revs):
             if idx >= limit:
                 break
             limitedrevs.append(rev)
         revs = revset.baseset(limitedrevs)
 
     return revs, expr, filematcher
 
 def getlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     limit = loglimit(opts)
     revs = _logrevs(repo, opts)
     if not revs:
         return revset.baseset([]), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if expr:
         # Revset matchers often operate faster on revisions in changelog
         # order, because most filters deal with the changelog.
         if not opts.get('rev'):
             revs.reverse()
         matcher = revset.match(repo.ui, expr)
         # Revset matches can reorder revisions. "A or B" typically returns
         # returns the revision matching A then the revision matching B. Sort
         # again to fix that.
         fixopts = ['branch', 'only_branch', 'keyword', 'user']
         oldrevs = revs
         revs = matcher(repo, revs)
         if not opts.get('rev'):
             revs.sort(reverse=True)
         elif len(pats) > 1 or any(len(opts.get(op, [])) > 1 for op in fixopts):
             # XXX "A or B" is known to change the order; fix it by filtering
             # matched set again (issue5100)
             revs = oldrevs & revs
     if limit is not None:
         limitedrevs = []
         for idx, r in enumerate(revs):
             if limit <= idx:
                 break
             limitedrevs.append(r)
         revs = revset.baseset(limitedrevs)
 
     return revs, expr, filematcher
 
 def _graphnodeformatter(ui, displayer):
     spec = ui.config('ui', 'graphnodetemplate')
     if not spec:
         return templatekw.showgraphnode  # fast path for "{graphnode}"
 
     templ = formatter.gettemplater(ui, 'graphnode', spec)
     cache = {}
     if isinstance(displayer, changeset_templater):
         cache = displayer.cache  # reuse cache of slow templates
     props = templatekw.keywords.copy()
     props['templ'] = templ
     props['cache'] = cache
     def formatnode(repo, ctx):
         props['ctx'] = ctx
         props['repo'] = repo
         props['ui'] = repo.ui
         props['revcache'] = {}
         return templater.stringify(templ('graphnode', **props))
     return formatnode
 
 def displaygraph(ui, repo, dag, displayer, edgefn, getrenamed=None,
                  filematcher=None):
     formatnode = _graphnodeformatter(ui, displayer)
     state = graphmod.asciistate()
     styles = state['styles']
 
     # only set graph styling if HGPLAIN is not set.
     if ui.plain('graph'):
         # set all edge styles to |, the default pre-3.8 behaviour
         styles.update(dict.fromkeys(styles, '|'))
     else:
         edgetypes = {
             'parent': graphmod.PARENT,
             'grandparent': graphmod.GRANDPARENT,
             'missing': graphmod.MISSINGPARENT
         }
         for name, key in edgetypes.items():
             # experimental config: experimental.graphstyle.*
             styles[key] = ui.config('experimental', 'graphstyle.%s' % name,
                                     styles[key])
             if not styles[key]:
                 styles[key] = None
 
         # experimental config: experimental.graphshorten
         state['graphshorten'] = ui.configbool('experimental', 'graphshorten')
 
     for rev, type, ctx, parents in dag:
         char = formatnode(repo, ctx)
         copies = None
         if getrenamed and ctx.rev():
             copies = []
             for fn in ctx.files():
                 rename = getrenamed(fn, ctx.rev())
                 if rename:
                     copies.append((fn, rename[0]))
         revmatchfn = None
         if filematcher is not None:
             revmatchfn = filematcher(ctx.rev())
         displayer.show(ctx, copies=copies, matchfn=revmatchfn)
         lines = displayer.hunk.pop(rev).split('\n')
         if not lines[-1]:
             del lines[-1]
         displayer.flush(ctx)
         edges = edgefn(type, char, lines, state, rev, parents)
         for type, char, lines, coldata in edges:
             graphmod.ascii(ui, state, type, char, lines, coldata)
     displayer.close()
 
 def graphlog(ui, repo, *pats, **opts):
     # Parameters are identical to log command ones
     revs, expr, filematcher = getgraphlogrevs(repo, pats, opts)
     revdag = graphmod.dagwalker(repo, revs)
 
     getrenamed = None
     if opts.get('copies'):
         endrev = None
         if opts.get('rev'):
             endrev = scmutil.revrange(repo, opts.get('rev')).max() + 1
         getrenamed = templatekw.getrenamedfn(repo, endrev=endrev)
     displayer = show_changeset(ui, repo, opts, buffered=True)
     displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges, getrenamed,
                  filematcher)
 
 def checkunsupportedgraphflags(pats, opts):
     for op in ["newest_first"]:
         if op in opts and opts[op]:
             raise error.Abort(_("-G/--graph option is incompatible with --%s")
                              % op.replace("_", "-"))
 
 def graphrevs(repo, nodes, opts):
     limit = loglimit(opts)
     nodes.reverse()
     if limit is not None:
         nodes = nodes[:limit]
     return graphmod.nodes(repo, nodes)
 
 def add(ui, repo, match, prefix, explicitonly, **opts):
     join = lambda f: os.path.join(prefix, f)
     bad = []
 
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
 
     badmatch = matchmod.badmatch(match, badfn)
     dirstate = repo.dirstate
     # We don't want to just call wctx.walk here, since it would return a lot of
     # clean files, which we aren't interested in and takes time.
     for f in sorted(dirstate.walk(badmatch, sorted(wctx.substate),
                                   True, False, full=False)):
         exact = match.exact(f)
         if exact or not explicitonly and f not in wctx and repo.wvfs.lexists(f):
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(_('adding %s\n') % match.rel(f))
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             if opts.get('subrepos'):
                 bad.extend(sub.add(ui, submatch, prefix, False, **opts))
             else:
                 bad.extend(sub.add(ui, submatch, prefix, True, **opts))
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not opts.get('dry_run'):
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 def forget(ui, repo, match, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     wctx = repo[None]
     forgot = []
 
     s = repo.status(match=matchmod.badmatch(match, badfn), clean=True)
     forget = sorted(s[0] + s[1] + s[3] + s[6])
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             subbad, subforgot = sub.forget(submatch, prefix)
             bad.extend([subpath + '/' + f for f in subbad])
             forgot.extend([subpath + '/' + f for f in subforgot])
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not repo.wvfs.isdir(f):
                 if f not in forgot:
                     if repo.wvfs.exists(f):
                         # Don't complain if the exact case match wasn't given.
                         # But don't do this until after checking 'forgot', so
                         # that subrepo files aren't normalized, and this op is
                         # purely from data cached by the status walk above.
                         if repo.dirstate.normalize(f) in repo.dirstate:
                             continue
                         ui.warn(_('not removing %s: '
                                   'file is already untracked\n')
                                 % match.rel(f))
                     bad.append(f)
 
     for f in forget:
         if ui.verbose or not match.exact(f):
             ui.status(_('removing %s\n') % match.rel(f))
 
     rejected = wctx.forget(forget, prefix)
     bad.extend(f for f in rejected if f in match.files())
     forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 def files(ui, ctx, m, fm, fmt, subrepos):
     rev = ctx.rev()
     ret = 1
     ds = ctx.repo().dirstate
 
     for f in ctx.matches(m):
         if rev is None and ds[f] == 'r':
             continue
         fm.startitem()
         if ui.verbose:
             fc = ctx[f]
             fm.write('size flags', '% 10d % 1s ', fc.size(), fc.flags())
         fm.data(abspath=f)
         fm.write('path', fmt, m.rel(f))
         ret = 0
 
     for subpath in sorted(ctx.substate):
         def matchessubrepo(subpath):
             return (m.exact(subpath)
                     or any(f.startswith(subpath + '/') for f in m.files()))
 
         if subrepos or matchessubrepo(subpath):
             sub = ctx.sub(subpath)
             try:
                 submatch = matchmod.subdirmatcher(subpath, m)
                 recurse = m.exact(subpath) or subrepos
                 if sub.printfiles(ui, submatch, fm, fmt, recurse) == 0:
                     ret = 0
             except error.LookupError:
                 ui.status(_("skipping missing subrepository: %s\n")
                                % m.abs(subpath))
 
     return ret
 
 def remove(ui, repo, m, prefix, after, force, subrepos, warnings=None):
     join = lambda f: os.path.join(prefix, f)
     ret = 0
     s = repo.status(match=m, clean=True)
     modified, added, deleted, clean = s[0], s[1], s[3], s[6]
 
     wctx = repo[None]
 
     if warnings is None:
         warnings = []
         warn = True
     else:
         warn = False
 
     subs = sorted(wctx.substate)
     total = len(subs)
     count = 0
     for subpath in subs:
         def matchessubrepo(matcher, subpath):
             if matcher.exact(subpath):
                 return True
             for f in matcher.files():
                 if f.startswith(subpath):
                     return True
             return False
 
         count += 1
         if subrepos or matchessubrepo(m, subpath):
             ui.progress(_('searching'), count, total=total, unit=_('subrepos'))
 
             sub = wctx.sub(subpath)
             try:
                 submatch = matchmod.subdirmatcher(subpath, m)
                 if sub.removefiles(submatch, prefix, after, force, subrepos,
                                    warnings):
                     ret = 1
             except error.LookupError:
                 warnings.append(_("skipping missing subrepository: %s\n")
                                % join(subpath))
     ui.progress(_('searching'), None)
 
     # warn about failure to delete explicit files/dirs
     deleteddirs = util.dirs(deleted)
     files = m.files()
     total = len(files)
     count = 0
     for f in files:
         def insubrepo():
             for subpath in wctx.substate:
                 if f.startswith(subpath):
                     return True
             return False
 
         count += 1
         ui.progress(_('deleting'), count, total=total, unit=_('files'))
         isdir = f in deleteddirs or wctx.hasdir(f)
         if f in repo.dirstate or isdir or f == '.' or insubrepo():
             continue
 
         if repo.wvfs.exists(f):
             if repo.wvfs.isdir(f):
                 warnings.append(_('not removing %s: no tracked files\n')
                         % m.rel(f))
             else:
                 warnings.append(_('not removing %s: file is untracked\n')
                         % m.rel(f))
         # missing files will generate a warning elsewhere
         ret = 1
     ui.progress(_('deleting'), None)
 
     if force:
         list = modified + deleted + clean + added
     elif after:
         list = deleted
         remaining = modified + added + clean
         total = len(remaining)
         count = 0
         for f in remaining:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_('not removing %s: file still exists\n')
                     % m.rel(f))
             ret = 1
         ui.progress(_('skipping'), None)
     else:
         list = deleted + clean
         total = len(modified) + len(added)
         count = 0
         for f in modified:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_('not removing %s: file is modified (use -f'
                       ' to force removal)\n') % m.rel(f))
             ret = 1
         for f in added:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_('not removing %s: file has been marked for add'
                       ' (use forget to undo)\n') % m.rel(f))
             ret = 1
         ui.progress(_('skipping'), None)
 
     list = sorted(list)
     total = len(list)
     count = 0
     for f in list:
         count += 1
         if ui.verbose or not m.exact(f):
             ui.progress(_('deleting'), count, total=total, unit=_('files'))
             ui.status(_('removing %s\n') % m.rel(f))
     ui.progress(_('deleting'), None)
 
     with repo.wlock():
         if not after:
             for f in list:
                 if f in added:
                     continue # we never unlink added files on remove
                 util.unlinkpath(repo.wjoin(f), ignoremissing=True)
         repo[None].forget(list)
 
     if warn:
         for warning in warnings:
             ui.warn(warning)
 
     return ret
 
 def cat(ui, repo, ctx, matcher, prefix, **opts):
     err = 1
 
     def write(path):
         fp = makefileobj(repo, opts.get('output'), ctx.node(),
                          pathname=os.path.join(prefix, path))
         data = ctx[path].data()
         if opts.get('decode'):
             data = repo.wwritedata(path, data)
         fp.write(data)
         fp.close()
 
     # Automation often uses hg cat on single files, so special case it
     # for performance to avoid the cost of parsing the manifest.
     if len(matcher.files()) == 1 and not matcher.anypats():
         file = matcher.files()[0]
         mf = repo.manifest
         mfnode = ctx.manifestnode()
         if mfnode and mf.find(mfnode, file)[0]:
             write(file)
             return 0
 
     # Don't warn about "missing" files that are really in subrepos
     def badfn(path, msg):
         for subpath in ctx.substate:
             if path.startswith(subpath):
                 return
         matcher.bad(path, msg)
 
     for abs in ctx.walk(matchmod.badmatch(matcher, badfn)):
         write(abs)
         err = 0
 
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, matcher)
 
             if not sub.cat(submatch, os.path.join(prefix, sub._path),
                            **opts):
                 err = 0
         except error.RepoLookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % os.path.join(prefix, subpath))
 
     return err
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
     message = logmessage(ui, opts)
     matcher = scmutil.match(repo[None], pats, opts)
 
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         if scmutil.addremove(repo, matcher, "", opts) != 0:
             raise error.Abort(
                 _("failed to mark all new/missing files as added/removed"))
 
     return commitfunc(ui, repo, message, matcher, opts)
 
 def amend(ui, repo, commitfunc, old, extra, pats, opts):
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     # amend will reuse the existing user if not specified, but the obsolete
     # marker creation requires that the current user's name is specified.
     if obsolete.isenabled(repo, obsolete.createmarkersopt):
         ui.username() # raise exception if username not set
 
     ui.note(_('amending changeset %s\n') % old)
     base = old.p1()
     createmarkers = obsolete.isenabled(repo, obsolete.createmarkersopt)
 
     wlock = lock = newid = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         with repo.transaction('amend') as tr:
             # See if we got a message from -m or -l, if not, open the editor
             # with the message of the changeset to amend
             message = logmessage(ui, opts)
             # ensure logfile does not conflict with later enforcement of the
             # message. potential logfile content has been processed by
             # `logmessage` anyway.
             opts.pop('logfile')
             # First, do a regular commit to record all changes in the working
             # directory (if there are any)
             ui.callhooks = False
             activebookmark = repo._bookmarks.active
             try:
                 repo._bookmarks.active = None
                 opts['message'] = 'temporary amend commit for %s' % old
                 node = commit(ui, repo, commitfunc, pats, opts)
             finally:
                 repo._bookmarks.active = activebookmark
                 repo._bookmarks.recordchange(tr)
                 ui.callhooks = True
             ctx = repo[node]
 
             # Participating changesets:
             #
             # node/ctx o - new (intermediate) commit that contains changes
             #          |   from working dir to go into amending commit
             #          |   (or a workingctx if there were no changes)
             #          |
             # old      o - changeset to amend
             #          |
             # base     o - parent of amending changeset
 
             # Update extra dict from amended commit (e.g. to preserve graft
             # source)
             extra.update(old.extra())
 
             # Also update it from the intermediate commit or from the wctx
             extra.update(ctx.extra())
 
             if len(old.parents()) > 1:
                 # ctx.files() isn't reliable for merges, so fall back to the
                 # slower repo.status() method
                 files = set([fn for st in repo.status(base, old)[:3]
                              for fn in st])
             else:
                 files = set(old.files())
 
             # Second, we use either the commit we just did, or if there were no
             # changes the parent of the working directory as the version of the
             # files in the final amend commit
             if node:
                 ui.note(_('copying changeset %s to %s\n') % (ctx, base))
 
                 user = ctx.user()
                 date = ctx.date()
                 # Recompute copies (avoid recording a -> b -> a)
                 copied = copies.pathcopies(base, ctx)
                 if old.p2:
                     copied.update(copies.pathcopies(old.p2(), ctx))
 
                 # Prune files which were reverted by the updates: if old
                 # introduced file X and our intermediate commit, node,
                 # renamed that file, then those two files are the same and
                 # we can discard X from our list of files. Likewise if X
                 # was deleted, it's no longer relevant
                 files.update(ctx.files())
 
                 def samefile(f):
                     if f in ctx.manifest():
                         a = ctx.filectx(f)
                         if f in base.manifest():
                             b = base.filectx(f)
                             return (not a.cmp(b)
                                     and a.flags() == b.flags())
                         else:
                             return False
                     else:
                         return f not in base.manifest()
                 files = [f for f in files if not samefile(f)]
 
                 def filectxfn(repo, ctx_, path):
                     try:
                         fctx = ctx[path]
                         flags = fctx.flags()
                         mctx = context.memfilectx(repo,
                                                   fctx.path(), fctx.data(),
                                                   islink='l' in flags,
                                                   isexec='x' in flags,
                                                   copied=copied.get(path))
                         return mctx
                     except KeyError:
                         return None
             else:
                 ui.note(_('copying changeset %s to %s\n') % (old, base))
 
                 # Use version of files as in the old cset
                 def filectxfn(repo, ctx_, path):
                     try:
                         return old.filectx(path)
                     except KeyError:
                         return None
 
                 user = opts.get('user') or old.user()
                 date = opts.get('date') or old.date()
             editform = mergeeditform(old, 'commit.amend')
             editor = getcommiteditor(editform=editform, **opts)
             if not message:
                 editor = getcommiteditor(edit=True, editform=editform)
                 message = old.description()
 
             pureextra = extra.copy()
             extra['amend_source'] = old.hex()
 
             new = context.memctx(repo,
                                  parents=[base.node(), old.p2().node()],
                                  text=message,
                                  files=files,
                                  filectxfn=filectxfn,
                                  user=user,
                                  date=date,
                                  extra=extra,
                                  editor=editor)
 
             newdesc = changelog.stripdesc(new.description())
             if ((not node)
                 and newdesc == old.description()
                 and user == old.user()
                 and date == old.date()
                 and pureextra == old.extra()):
                 # nothing changed. continuing here would create a new node
                 # anyway because of the amend_source noise.
                 #
                 # This not what we expect from amend.
                 return old.node()
 
             ph = repo.ui.config('phases', 'new-commit', phases.draft)
             try:
                 if opts.get('secret'):
                     commitphase = 'secret'
                 else:
                     commitphase = old.phase()
                 repo.ui.setconfig('phases', 'new-commit', commitphase, 'amend')
                 newid = repo.commitctx(new)
             finally:
                 repo.ui.setconfig('phases', 'new-commit', ph, 'amend')
             if newid != old.node():
                 # Reroute the working copy parent to the new changeset
                 repo.setparents(newid, nullid)
 
                 # Move bookmarks from old parent to amend commit
                 bms = repo.nodebookmarks(old.node())
                 if bms:
                     marks = repo._bookmarks
                     for bm in bms:
                         ui.debug('moving bookmarks %r from %s to %s\n' %
                                  (marks, old.hex(), hex(newid)))
                         marks[bm] = newid
                     marks.recordchange(tr)
                 #commit the whole amend process
                 if createmarkers:
                     # mark the new changeset as successor of the rewritten one
                     new = repo[newid]
                     obs = [(old, (new,))]
                     if node:
                         obs.append((ctx, ()))
 
                     obsolete.createmarkers(repo, obs)
         if not createmarkers and newid != old.node():
             # Strip the intermediate commit (if there was one) and the amended
             # commit
             if node:
                 ui.note(_('stripping intermediate changeset %s\n') % ctx)
             ui.note(_('stripping amended changeset %s\n') % old)
             repair.strip(ui, repo, old.node(), topic='amend-backup')
     finally:
         lockmod.release(lock, wlock)
     return newid
 
 def commiteditor(repo, ctx, subs, editform=''):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(repo, ctx, subs, editform=editform,
                              unchangedmessagedetection=True)
 
 def commitforceeditor(repo, ctx, subs, finishdesc=None, extramsg=None,
                       editform='', unchangedmessagedetection=False):
     if not extramsg:
         extramsg = _("Leave message empty to abort commit.")
 
     forms = [e for e in editform.split('.') if e]
     forms.insert(0, 'changeset')
     templatetext = None
     while forms:
         tmpl = repo.ui.config('committemplate', '.'.join(forms))
         if tmpl:
             templatetext = committext = buildcommittemplate(
                 repo, ctx, subs, extramsg, tmpl)
             break
         forms.pop()
     else:
         committext = buildcommittext(repo, ctx, subs, extramsg)
 
     # run editor in the repository root
     olddir = os.getcwd()
     os.chdir(repo.root)
 
     # make in-memory changes visible to external process
     tr = repo.currenttransaction()
     repo.dirstate.write(tr)
     pending = tr and tr.writepending() and repo.root
 
     editortext = repo.ui.edit(committext, ctx.user(), ctx.extra(),
                         editform=editform, pending=pending)
     text = re.sub("(?m)^HG:.*(\n|$)", "", editortext)
     os.chdir(olddir)
 
     if finishdesc:
         text = finishdesc(text)
     if not text.strip():
         raise error.Abort(_("empty commit message"))
     if unchangedmessagedetection and editortext == templatetext:
         raise error.Abort(_("commit message unchanged"))
 
     return text
 
 def buildcommittemplate(repo, ctx, subs, extramsg, tmpl):
     ui = repo.ui
     tmpl, mapfile = gettemplate(ui, tmpl, None)
 
     t = changeset_templater(ui, repo, None, {}, tmpl, mapfile, False)
 
     for k, v in repo.ui.configitems('committemplate'):
         if k != 'changeset':
             t.t.cache[k] = v
 
     if not extramsg:
         extramsg = '' # ensure that extramsg is string
 
     ui.pushbuffer()
     t.show(ctx, extramsg=extramsg)
     return ui.popbuffer()
 
 def hgprefix(msg):
     return "\n".join(["HG: %s" % a for a in msg.split("\n") if a])
 
 def buildcommittext(repo, ctx, subs, extramsg):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append("")
     edittext.append("") # Empty line between message and comments.
     edittext.append(hgprefix(_("Enter commit message."
                       "  Lines beginning with 'HG:' are removed.")))
     edittext.append(hgprefix(extramsg))
     edittext.append("HG: --")
     edittext.append(hgprefix(_("user: %s") % ctx.user()))
     if ctx.p2():
         edittext.append(hgprefix(_("branch merge")))
     if ctx.branch():
         edittext.append(hgprefix(_("branch '%s'") % ctx.branch()))
     if bookmarks.isactivewdirparent(repo):
         edittext.append(hgprefix(_("bookmark '%s'") % repo._activebookmark))
     edittext.extend([hgprefix(_("subrepo %s") % s) for s in subs])
     edittext.extend([hgprefix(_("added %s") % f) for f in added])
     edittext.extend([hgprefix(_("changed %s") % f) for f in modified])
     edittext.extend([hgprefix(_("removed %s") % f) for f in removed])
     if not added and not modified and not removed:
         edittext.append(hgprefix(_("no files changed")))
     edittext.append("")
 
     return "\n".join(edittext)
 
 def commitstatus(repo, node, branch, bheads=None, opts=None):
     if opts is None:
         opts = {}
     ctx = repo[node]
     parents = ctx.parents()
 
     if (not opts.get('amend') and bheads and node not in bheads and not
         [x for x in parents if x.node() in bheads and x.branch() == branch]):
         repo.ui.status(_('created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get('close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(_('reopening closed branch head %d\n') % r)
 
     if repo.ui.debugflag:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx.hex()))
     elif repo.ui.verbose:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx))
 
 def postcommitstatus(repo, pats, opts):
     return repo.status(match=scmutil.match(repo[None], pats, opts))
 
 def revert(ui, repo, ctx, parents, *pats, **opts):
     parent, p2 = parents
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == p2:
         parent = p2
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other. in both cases, filesets should be evaluated against
     # workingctx to get consistent result (issue4497). this means 'set:**'
     # cannot be used to select missing files from target rev.
 
     # `names` is a mapping for all elements in working copy and target revision
     # The mapping is in the form:
     #   <asb path in repo> -> (<path from CWD>, <exactly specified by matcher?>)
     names = {}
 
     with repo.wlock():
         ## filling of the `names` mapping
         # walk dirstate to fill `names`
 
         interactive = opts.get('interactive', False)
         wctx = repo[None]
         m = scmutil.match(wctx, pats, opts)
 
         # we'll need this later
         targetsubs = sorted(s for s in wctx.substate if m(s))
 
         if not m.always():
             for abs in repo.walk(matchmod.badmatch(m, lambda x, y: False)):
                 names[abs] = m.rel(abs), m.exact(abs)
 
             # walk target manifest to fill `names`
 
             def badfn(path, msg):
                 if path in names:
                     return
                 if path in ctx.substate:
                     return
                 path_ = path + '/'
                 for f in names:
                     if f.startswith(path_):
                         return
                 ui.warn("%s: %s\n" % (m.rel(path), msg))
 
             for abs in ctx.walk(matchmod.badmatch(m, badfn)):
                 if abs not in names:
                     names[abs] = m.rel(abs), m.exact(abs)
 
             # Find status of all file in `names`.
             m = scmutil.matchfiles(repo, names)
 
             changes = repo.status(node1=node, match=m,
                                   unknown=True, ignored=True, clean=True)
         else:
             changes = repo.status(node1=node, match=m)
             for kind in changes:
                 for abs in kind:
                     names[abs] = m.rel(abs), m.exact(abs)
 
             m = scmutil.matchfiles(repo, names)
 
         modified = set(changes.modified)
         added    = set(changes.added)
         removed  = set(changes.removed)
         _deleted = set(changes.deleted)
         unknown  = set(changes.unknown)
         unknown.update(changes.ignored)
         clean    = set(changes.clean)
         modadded = set()
 
         # split between files known in target manifest and the others
         smf = set(mf)
 
         # determine the exact nature of the deleted changesets
         deladded = _deleted - smf
         deleted = _deleted - deladded
 
         # We need to account for the state of the file in the dirstate,
         # even when we revert against something else than parent. This will
         # slightly alter the behavior of revert (doing back up or not, delete
         # or just forget etc).
         if parent == node:
             dsmodified = modified
             dsadded = added
             dsremoved = removed
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
             modified, added, removed = set(), set(), set()
         else:
             changes = repo.status(node1=parent, match=m)
             dsmodified = set(changes.modified)
             dsadded    = set(changes.added)
             dsremoved  = set(changes.removed)
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
 
             # only take into account for removes between wc and target
             clean |= dsremoved - removed
             dsremoved &= removed
             # distinct between dirstate remove and other
             removed -= dsremoved
 
             modadded = added & dsmodified
             added -= modadded
 
             # tell newly modified apart.
             dsmodified &= modified
             dsmodified |= modified & dsadded # dirstate added may need backup
             modified -= dsmodified
 
             # We need to wait for some post-processing to update this set
             # before making the distinction. The dirstate will be used for
             # that purpose.
             dsadded = added
 
         # in case of merge, files that are actually added can be reported as
         # modified, we need to post process the result
         if p2 != nullid:
             mergeadd = dsmodified - smf
             dsadded |= mergeadd
             dsmodified -= mergeadd
 
         # if f is a rename, update `names` to also revert the source
         cwd = repo.getcwd()
         for f in localchanges:
             src = repo.dirstate.copied(f)
             # XXX should we check for rename down to target node?
             if src and src not in names and repo.dirstate[src] == 'r':
                 dsremoved.add(src)
                 names[src] = (repo.pathto(src, cwd), True)
 
         # distinguish between file to forget and the other
         added = set()
         for abs in dsadded:
             if repo.dirstate[abs] != 'a':
                 added.add(abs)
         dsadded -= added
 
         for abs in deladded:
             if repo.dirstate[abs] == 'a':
                 dsadded.add(abs)
         deladded -= dsadded
 
         # For files marked as removed, we check if an unknown file is present at
         # the same path. If a such file exists it may need to be backed up.
         # Making the distinction at this stage helps have simpler backup
         # logic.
         removunk = set()
         for abs in removed:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 removunk.add(abs)
         removed -= removunk
 
         dsremovunk = set()
         for abs in dsremoved:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 dsremovunk.add(abs)
         dsremoved -= dsremovunk
 
         # action to be actually performed by revert
         # (<list of file>, message>) tuple
         actions = {'revert': ([], _('reverting %s\n')),
                    'add': ([], _('adding %s\n')),
                    'remove': ([], _('removing %s\n')),
                    'drop': ([], _('removing %s\n')),
                    'forget': ([], _('forgetting %s\n')),
                    'undelete': ([], _('undeleting %s\n')),
                    'noop': (None, _('no changes needed to %s\n')),
                    'unknown': (None, _('file not managed: %s\n')),
                   }
 
         # "constant" that convey the backup strategy.
         # All set to `discard` if `no-backup` is set do avoid checking
         # no_backup lower in the code.
         # These values are ordered for comparison purposes
         backup = 2  # unconditionally do backup
         check = 1   # check if the existing file differs from target
         discard = 0 # never do backup
         if opts.get('no_backup'):
             backup = check = discard
 
         backupanddel = actions['remove']
         if not opts.get('no_backup'):
             backupanddel = actions['drop']
 
         disptable = (
             # dispatch table:
             #   file state
             #   action
             #   make backup
 
             ## Sets that results that will change file on disk
             # Modified compared to target, no local change
             (modified,      actions['revert'],   discard),
             # Modified compared to target, but local file is deleted
             (deleted,       actions['revert'],   discard),
             # Modified compared to target, local change
             (dsmodified,    actions['revert'],   backup),
             # Added since target
             (added,         actions['remove'],   discard),
             # Added in working directory
             (dsadded,       actions['forget'],   discard),
             # Added since target, have local modification
             (modadded,      backupanddel,        backup),
             # Added since target but file is missing in working directory
             (deladded,      actions['drop'],   discard),
             # Removed since  target, before working copy parent
             (removed,       actions['add'],      discard),
             # Same as `removed` but an unknown file exists at the same path
             (removunk,      actions['add'],      check),
             # Removed since targe, marked as such in working copy parent
             (dsremoved,     actions['undelete'], discard),
             # Same as `dsremoved` but an unknown file exists at the same path
             (dsremovunk,    actions['undelete'], check),
             ## the following sets does not result in any file changes
             # File with no modification
             (clean,         actions['noop'],     discard),
             # Existing file, not tracked anywhere
             (unknown,       actions['unknown'],  discard),
             )
 
         for abs, (rel, exact) in sorted(names.items()):
             # target file to be touch on disk (relative to cwd)
             target = repo.wjoin(abs)
             # search the entry in the dispatch table.
             # if the file is in any of these sets, it was touched in the working
             # directory parent and we are sure it needs to be reverted.
             for table, (xlist, msg), dobackup in disptable:
                 if abs not in table:
                     continue
                 if xlist is not None:
                     xlist.append(abs)
                     if dobackup and (backup <= dobackup
                                      or wctx[abs].cmp(ctx[abs])):
                             bakname = scmutil.origpath(ui, repo, rel)
                             ui.note(_('saving current version of %s as %s\n') %
                                     (rel, bakname))
                             if not opts.get('dry_run'):
                                 if interactive:
                                     util.copyfile(target, bakname)
                                 else:
                                     util.rename(target, bakname)
                     if ui.verbose or not exact:
                         if not isinstance(msg, basestring):
                             msg = msg(abs)
                         ui.status(msg % rel)
                 elif exact:
                     ui.warn(msg % rel)
                 break
 
         if not opts.get('dry_run'):
             needdata = ('revert', 'add', 'undelete')
             _revertprefetch(repo, ctx, *[actions[name][0] for name in needdata])
             _performrevert(repo, parents, ctx, actions, interactive)
 
         if targetsubs:
             # Revert the subrepos on the revert list
             for sub in targetsubs:
                 try:
                     wctx.sub(sub).revert(ctx.substate[sub], *pats, **opts)
                 except KeyError:
                     raise error.Abort("subrepository '%s' does not exist in %s!"
                                       % (sub, short(ctx.node())))
 
 def _revertprefetch(repo, ctx, *files):
     """Let extension changing the storage layer prefetch content"""
     pass
 
 def _performrevert(repo, parents, ctx, actions, interactive=False):
     """function that actually perform all the actions computed for revert
 
     This is an independent function to let extension to plug in and react to
     the imminent revert.
 
     Make sure you have the working directory locked when calling this function.
     """
     parent, p2 = parents
     node = ctx.node()
     excluded_files = []
     matcher_opts = {"exclude": excluded_files}
 
     def checkout(f):
         fc = ctx[f]
         repo.wwrite(f, fc.data(), fc.flags())
 
     audit_path = pathutil.pathauditor(repo.root)
     for f in actions['forget'][0]:
         if interactive:
             choice = \
                 repo.ui.promptchoice(
                     _("forget added file %s (yn)?$$ &Yes $$ &No")
                     % f)
             if choice == 0:
                 repo.dirstate.drop(f)
             else:
                 excluded_files.append(repo.wjoin(f))
         else:
             repo.dirstate.drop(f)
     for f in actions['remove'][0]:
         audit_path(f)
         try:
             util.unlinkpath(repo.wjoin(f))
         except OSError:
             pass
         repo.dirstate.remove(f)
     for f in actions['drop'][0]:
         audit_path(f)
         repo.dirstate.remove(f)
 
     normal = None
     if node == parent:
         # We're reverting to our parent. If possible, we'd like status
         # to report the file as clean. We have to use normallookup for
         # merges to avoid losing information about merged/dirty files.
         if p2 != nullid:
             normal = repo.dirstate.normallookup
         else:
             normal = repo.dirstate.normal
 
     newlyaddedandmodifiedfiles = set()
     if interactive:
         # Prompt the user for changes to revert
         torevert = [repo.wjoin(f) for f in actions['revert'][0]]
         m = scmutil.match(ctx, torevert, matcher_opts)
         diffopts = patch.difffeatureopts(repo.ui, whitespace=True)
         diffopts.nodates = True
         diffopts.git = True
         reversehunks = repo.ui.configbool('experimental',
                                           'revertalternateinteractivemode',
                                           True)
         if reversehunks:
             diff = patch.diff(repo, ctx.node(), None, m, opts=diffopts)
         else:
             diff = patch.diff(repo, None, ctx.node(), m, opts=diffopts)
         originalchunks = patch.parsepatch(diff)
 
         try:
 
             chunks, opts = recordfilter(repo.ui, originalchunks)
             if reversehunks:
                 chunks = patch.reversehunks(chunks)
 
         except patch.PatchError as err:
             raise error.Abort(_('error parsing patch: %s') % err)
 
         newlyaddedandmodifiedfiles = newandmodified(chunks, originalchunks)
         # Apply changes
         fp = stringio()
         for c in chunks:
             c.write(fp)
         dopatch = fp.tell()
         fp.seek(0)
         if dopatch:
             try:
                 patch.internalpatch(repo.ui, repo, fp, 1, eolmode=None)
             except patch.PatchError as err:
                 raise error.Abort(str(err))
         del fp
     else:
         for f in actions['revert'][0]:
             checkout(f)
             if normal:
                 normal(f)
 
     for f in actions['add'][0]:
         # Don't checkout modified files, they are already created by the diff
         if f not in newlyaddedandmodifiedfiles:
             checkout(f)
             repo.dirstate.add(f)
 
     normal = repo.dirstate.normallookup
     if node == parent and p2 == nullid:
         normal = repo.dirstate.normal
     for f in actions['undelete'][0]:
         checkout(f)
         normal(f)
 
     copied = copies.pathcopies(repo[parent], ctx)
 
     for f in actions['add'][0] + actions['undelete'][0] + actions['revert'][0]:
         if f in copied:
             repo.dirstate.copy(copied[f], f)
 
 def command(table):
     """Returns a function object to be used as a decorator for making commands.
 
     This function receives a command table as its argument. The table should
     be a dict.
 
     The returned function can be used as a decorator for adding commands
     to that command table. This function accepts multiple arguments to define
     a command.
 
     The first argument is the command name.
 
     The options argument is an iterable of tuples defining command arguments.
     See ``mercurial.fancyopts.fancyopts()`` for the format of each tuple.
 
     The synopsis argument defines a short, one line summary of how to use the
     command. This shows up in the help output.
 
     The norepo argument defines whether the command does not require a
     local repository. Most commands operate against a repository, thus the
     default is False.
 
     The optionalrepo argument defines whether the command optionally requires
     a local repository.
 
     The inferrepo argument defines whether to try to find a repository from the
     command line arguments. If True, arguments will be examined for potential
     repository locations. See ``findrepo()``. If a repository is found, it
     will be used.
     """
     def cmd(name, options=(), synopsis=None, norepo=False, optionalrepo=False,
             inferrepo=False):
         def decorator(func):
             func.norepo = norepo
             func.optionalrepo = optionalrepo
             func.inferrepo = inferrepo
             if synopsis:
                 table[name] = func, list(options), synopsis
             else:
                 table[name] = func, list(options)
             return func
         return decorator
 
     return cmd
 
 # a list of (ui, repo, otherpeer, opts, missing) functions called by
 # commands.outgoing.  "missing" is "missing" of the result of
 # "findcommonoutgoing()"
 outgoinghooks = util.hooks()
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # a list of (ui, repo, opts, changes) functions called by commands.summary.
 #
 # functions should return tuple of booleans below, if 'changes' is None:
 #  (whether-incomings-are-needed, whether-outgoings-are-needed)
 #
 # otherwise, 'changes' is a tuple of tuples below:
 #  - (sourceurl, sourcebranch, sourcepeer, incoming)
 #  - (desturl,   destbranch,   destpeer,   outgoing)
 summaryremotehooks = util.hooks()
 
 # A list of state files kept by multistep operations like graft.
 # Since graft cannot be aborted, it is considered 'clearable' by update.
 # note: bisect is intentionally excluded
 # (state file, clearable, allowcommit, error, hint)
 unfinishedstates = [
     ('graftstate', True, False, _('graft in progress'),
      _("use 'hg graft --continue' or 'hg update' to abort")),
     ('updatestate', True, False, _('last update was interrupted'),
      _("use 'hg update' to get a consistent checkout"))
     ]
 
 def checkunfinished(repo, commit=False):
     '''Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if commit and allowcommit:
             continue
         if repo.vfs.exists(f):
             raise error.Abort(msg, hint=hint)
 
 def clearunfinished(repo):
     '''Check for unfinished operations (as above), and clear the ones
     that are clearable.
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if not clearable and repo.vfs.exists(f):
             raise error.Abort(msg, hint=hint)
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if clearable and repo.vfs.exists(f):
             util.unlink(repo.join(f))
 
 afterresolvedstates = [
     ('graftstate',
      _('hg graft --continue')),
     ]
 
 def howtocontinue(repo):
     '''Check for an unfinished operation and return the command to finish
     it.
 
     afterresolvedstates tupples define a .hg/{file} and the corresponding
     command needed to finish it.
 
     Returns a (msg, warning) tuple. 'msg' is a string and 'warning' is
     a boolean.
     '''
     contmsg = _("continue: %s")
     for f, msg in afterresolvedstates:
         if repo.vfs.exists(f):
             return contmsg % msg, True
     workingctx = repo[None]
     dirty = any(repo.status()) or any(workingctx.sub(s).dirty()
                                          for s in workingctx.substate)
     if dirty:
         return contmsg % _("hg commit"), False
     return None, None
 
 def checkafterresolved(repo):
     '''Inform the user about the next action after completing hg resolve
 
     If there's a matching afterresolvedstates, howtocontinue will yield
     repo.ui.warn as the reporter.
 
     Otherwise, it will yield repo.ui.note.
     '''
     msg, warning = howtocontinue(repo)
     if msg is not None:
         if warning:
             repo.ui.warn("%s\n" % msg)
         else:
             repo.ui.note("%s\n" % msg)
 
 def wrongtooltocontinue(repo, task):
     '''Raise an abort suggesting how to properly continue if there is an
     active task.
 
     Uses howtocontinue() to find the active task.
 
     If there's no task (repo.ui.note for 'hg commit'), it does not offer
     a hint.
     '''
     after = howtocontinue(repo)
     hint = None
     if after[1]:
         hint = after[0]
     raise error.Abort(_('no %s in progress') % task, hint=hint)
 
 class dirstateguard(object):
     '''Restore dirstate at unexpected failure.
 
     At the construction, this class does:
 
     - write current ``repo.dirstate`` out, and
     - save ``.hg/dirstate`` into the backup file
 
     This restores ``.hg/dirstate`` from backup file, if ``release()``
     is invoked before ``close()``.
 
     This just removes the backup file at ``close()`` before ``release()``.
     '''
 
     def __init__(self, repo, name):
         self._repo = repo
         self._suffix = '.backup.%s.%d' % (name, id(self))
         repo.dirstate.savebackup(repo.currenttransaction(), self._suffix)
         self._active = True
         self._closed = False
 
     def __del__(self):
         if self._active: # still active
             # this may occur, even if this class is used correctly:
             # for example, releasing other resources like transaction
             # may raise exception before ``dirstateguard.release`` in
             # ``release(tr, ....)``.
             self._abort()
 
     def close(self):
         if not self._active: # already inactivated
             msg = (_("can't close already inactivated backup: dirstate%s")
                    % self._suffix)
             raise error.Abort(msg)
 
         self._repo.dirstate.clearbackup(self._repo.currenttransaction(),
                                          self._suffix)
         self._active = False
         self._closed = True
 
     def _abort(self):
         self._repo.dirstate.restorebackup(self._repo.currenttransaction(),
                                            self._suffix)
         self._active = False
 
     def release(self):
         if not self._closed:
             if not self._active: # already inactivated
                 msg = (_("can't release already inactivated backup:"
                          " dirstate%s")
                        % self._suffix)
                 raise error.Abort(msg)
             self._abort()

mercurial/copies.py

@@ -1,553 +1,553 b''
 # copies.py - copy detection for Mercurial
 #
 # Copyright 2008 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.
 
 from __future__ import absolute_import
 
 import heapq
 
 from . import (
     node,
     pathutil,
     scmutil,
     util,
 )
 
 def _findlimit(repo, a, b):
     """
     Find the last revision that needs to be checked to ensure that a full
     transitive closure for file copies can be properly calculated.
     Generally, this means finding the earliest revision number that's an
     ancestor of a or b but not both, except when a or b is a direct descendent
     of the other, in which case we can return the minimum revnum of a and b.
     None if no such revision exists.
     """
 
     # basic idea:
     # - mark a and b with different sides
     # - if a parent's children are all on the same side, the parent is
     #   on that side, otherwise it is on no side
     # - walk the graph in topological order with the help of a heap;
     #   - add unseen parents to side map
     #   - clear side of any parent that has children on different sides
     #   - track number of interesting revs that might still be on a side
     #   - track the lowest interesting rev seen
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
     working = len(cl) # pseudo rev for the working directory
     if a is None:
         a = working
     if b is None:
         b = working
 
     side = {a: -1, b: 1}
     visit = [-a, -b]
     heapq.heapify(visit)
     interesting = len(visit)
     hascommonancestor = False
     limit = working
 
     while interesting:
         r = -heapq.heappop(visit)
         if r == working:
             parents = [cl.rev(p) for p in repo.dirstate.parents()]
         else:
             parents = cl.parentrevs(r)
         for p in parents:
             if p < 0:
                 continue
             if p not in side:
                 # first time we see p; add it to visit
                 side[p] = side[r]
                 if side[p]:
                     interesting += 1
                 heapq.heappush(visit, -p)
             elif side[p] and side[p] != side[r]:
                 # p was interesting but now we know better
                 side[p] = 0
                 interesting -= 1
                 hascommonancestor = True
         if side[r]:
             limit = r # lowest rev visited
             interesting -= 1
 
     if not hascommonancestor:
         return None
 
     # Consider the following flow (see test-commit-amend.t under issue4405):
     # 1/ File 'a0' committed
     # 2/ File renamed from 'a0' to 'a1' in a new commit (call it 'a1')
     # 3/ Move back to first commit
     # 4/ Create a new commit via revert to contents of 'a1' (call it 'a1-amend')
     # 5/ Rename file from 'a1' to 'a2' and commit --amend 'a1-msg'
     #
     # During the amend in step five, we will be in this state:
     #
     # @  3 temporary amend commit for a1-amend
     # |
     # o  2 a1-amend
     # |
     # | o  1 a1
     # |/
     # o  0 a0
     #
     # When _findlimit is called, a and b are revs 3 and 0, so limit will be 2,
     # yet the filelog has the copy information in rev 1 and we will not look
     # back far enough unless we also look at the a and b as candidates.
     # This only occurs when a is a descendent of b or visa-versa.
     return min(limit, a, b)
 
 def _chain(src, dst, a, b):
     '''chain two sets of copies a->b'''
     t = a.copy()
     for k, v in b.iteritems():
         if v in t:
             # found a chain
             if t[v] != k:
                 # file wasn't renamed back to itself
                 t[k] = t[v]
             if v not in dst:
                 # chain was a rename, not a copy
                 del t[v]
         if v in src:
             # file is a copy of an existing file
             t[k] = v
 
     # remove criss-crossed copies
     for k, v in t.items():
         if k in src and v in dst:
             del t[k]
 
     return t
 
 def _tracefile(fctx, am, limit=-1):
     '''return file context that is the ancestor of fctx present in ancestor
     manifest am, stopping after the first ancestor lower than limit'''
 
     for f in fctx.ancestors():
         if am.get(f.path(), None) == f.filenode():
             return f
         if limit >= 0 and f.linkrev() < limit and f.rev() < limit:
             return None
 
 def _dirstatecopies(d):
     ds = d._repo.dirstate
     c = ds.copies().copy()
     for k in c.keys():
         if ds[k] not in 'anm':
             del c[k]
     return c
 
 def _computeforwardmissing(a, b, match=None):
     """Computes which files are in b but not a.
     This is its own function so extensions can easily wrap this call to see what
     files _forwardcopies is about to process.
     """
     ma = a.manifest()
     mb = b.manifest()
     if match:
         ma = ma.matches(match)
         mb = mb.matches(match)
     return mb.filesnotin(ma)
 
 def _forwardcopies(a, b, match=None):
     '''find {dst@b: src@a} copy mapping where a is an ancestor of b'''
 
     # check for working copy
     w = None
     if b.rev() is None:
         w = b
         b = w.p1()
         if a == b:
             # short-circuit to avoid issues with merge states
             return _dirstatecopies(w)
 
     # files might have to be traced back to the fctx parent of the last
     # one-side-only changeset, but not further back than that
     limit = _findlimit(a._repo, a.rev(), b.rev())
     if limit is None:
         limit = -1
     am = a.manifest()
 
     # find where new files came from
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
 
     # Computing the forward missing is quite expensive on large manifests, since
     # it compares the entire manifests. We can optimize it in the common use
     # case of computing what copies are in a commit versus its parent (like
     # during a rebase or histedit). Note, we exclude merge commits from this
     # optimization, since the ctx.files() for a merge commit is not correct for
     # this comparison.
     forwardmissingmatch = match
     if not match and b.p1() == a and b.p2().node() == node.nullid:
         forwardmissingmatch = scmutil.matchfiles(a._repo, b.files())
     missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
     for f in missing:
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
         ofctx = _tracefile(fctx, am, limit)
         if ofctx:
             cm[f] = ofctx.path()
 
     # combine copies from dirstate if necessary
     if w is not None:
         cm = _chain(a, w, cm, _dirstatecopies(w))
 
     return cm
 
 def _backwardrenames(a, b):
     if a._repo.ui.configbool('experimental', 'disablecopytrace'):
         return {}
 
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(f.iteritems()):
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 def pathcopies(x, y, match=None):
     '''find {dst@y: src@x} copy mapping for directed compare'''
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
         return _forwardcopies(x, y, match=match)
     if a == y:
         return _backwardrenames(x, y)
     return _chain(x, y, _backwardrenames(x, a),
                   _forwardcopies(a, y, match=match))
 
 def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2):
     """Computes, based on addedinm1 and addedinm2, the files exclusive to c1
     and c2. This is its own function so extensions can easily wrap this call
     to see what files mergecopies is about to process.
 
     Even though c1 and c2 are not used in this function, they are useful in
     other extensions for being able to read the file nodes of the changed files.
     """
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
     if u1:
         repo.ui.debug("  unmatched files in local:\n   %s\n"
                       % "\n   ".join(u1))
     if u2:
         repo.ui.debug("  unmatched files in other:\n   %s\n"
                       % "\n   ".join(u2))
     return u1, u2
 
 def _makegetfctx(ctx):
     """return a 'getfctx' function suitable for checkcopies usage
 
     We have to re-setup the function building 'filectx' for each
     'checkcopies' to ensure the linkrev adjustment is properly setup for
     each. Linkrev adjustment is important to avoid bug in rename
     detection. Moreover, having a proper '_ancestrycontext' setup ensures
     the performance impact of this adjustment is kept limited. Without it,
     each file could do a full dag traversal making the time complexity of
     the operation explode (see issue4537).
 
     This function exists here mostly to limit the impact on stable. Feel
     free to refactor on default.
     """
     rev = ctx.rev()
     repo = ctx._repo
     ac = getattr(ctx, '_ancestrycontext', None)
     if ac is None:
         revs = [rev]
         if rev is None:
             revs = [p.rev() for p in ctx.parents()]
         ac = repo.changelog.ancestors(revs, inclusive=True)
         ctx._ancestrycontext = ac
     def makectx(f, n):
         if len(n) != 20:  # in a working context?
             if ctx.rev() is None:
                 return ctx.filectx(f)
             return repo[None][f]
         fctx = repo.filectx(f, fileid=n)
         # setup only needed for filectx not create from a changectx
         fctx._ancestrycontext = ac
         fctx._descendantrev = rev
         return fctx
     return util.lrucachefunc(makectx)
 
 def mergecopies(repo, c1, c2, ca):
     """
     Find moves and copies between context c1 and c2 that are relevant
     for merging.
 
     Returns four dicts: "copy", "movewithdir", "diverge", and
     "renamedelete".
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return {}, {}, {}, {}
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return repo.dirstate.copies(), {}, {}, {}
 
     # Copy trace disabling is explicitly below the node == p1 logic above
     # because the logic above is required for a simple copy to be kept across a
     # rebase.
     if repo.ui.configbool('experimental', 'disablecopytrace'):
         return {}, {}, {}, {}
 
     limit = _findlimit(repo, c1.rev(), c2.rev())
     if limit is None:
         # no common ancestor, no copies
         return {}, {}, {}, {}
     repo.ui.debug("  searching for copies back to rev %d\n" % limit)
 
     m1 = c1.manifest()
     m2 = c2.manifest()
     ma = ca.manifest()
 
     copy1, copy2, = {}, {}
     movewithdir1, movewithdir2 = {}, {}
     fullcopy1, fullcopy2 = {}, {}
     diverge = {}
 
     # find interesting file sets from manifests
     addedinm1 = m1.filesnotin(ma)
     addedinm2 = m2.filesnotin(ma)
     u1, u2 = _computenonoverlap(repo, c1, c2, addedinm1, addedinm2)
     bothnew = sorted(addedinm1 & addedinm2)
 
     for f in u1:
         checkcopies(c1, f, m1, m2, ca, limit, diverge, copy1, fullcopy1)
 
     for f in u2:
         checkcopies(c2, f, m2, m1, ca, limit, diverge, copy2, fullcopy2)
 
     copy = dict(copy1.items() + copy2.items())
     movewithdir = dict(movewithdir1.items() + movewithdir2.items())
     fullcopy = dict(fullcopy1.items() + fullcopy2.items())
 
     renamedelete = {}
     renamedeleteset = set()
     divergeset = set()
     for of, fl in diverge.items():
         if len(fl) == 1 or of in c1 or of in c2:
             del diverge[of] # not actually divergent, or not a rename
             if of not in c1 and of not in c2:
                 # renamed on one side, deleted on the other side, but filter
                 # out files that have been renamed and then deleted
                 renamedelete[of] = [f for f in fl if f in c1 or f in c2]
                 renamedeleteset.update(fl) # reverse map for below
         else:
             divergeset.update(fl) # reverse map for below
 
     if bothnew:
         repo.ui.debug("  unmatched files new in both:\n   %s\n"
                       % "\n   ".join(bothnew))
     bothdiverge, _copy, _fullcopy = {}, {}, {}
     for f in bothnew:
         checkcopies(c1, f, m1, m2, ca, limit, bothdiverge, _copy, _fullcopy)
         checkcopies(c2, f, m2, m1, ca, limit, bothdiverge, _copy, _fullcopy)
     for of, fl in bothdiverge.items():
         if len(fl) == 2 and fl[0] == fl[1]:
             copy[fl[0]] = of # not actually divergent, just matching renames
 
     if fullcopy and repo.ui.debugflag:
         repo.ui.debug("  all copies found (* = to merge, ! = divergent, "
                       "% = renamed and deleted):\n")
         for f in sorted(fullcopy):
             note = ""
             if f in copy:
                 note += "*"
             if f in divergeset:
                 note += "!"
             if f in renamedeleteset:
                 note += "%"
             repo.ui.debug("   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f,
                                                               note))
     del divergeset
 
     if not fullcopy:
         return copy, movewithdir, diverge, renamedelete
 
     repo.ui.debug("  checking for directory renames\n")
 
     # generate a directory move map
     d1, d2 = c1.dirs(), c2.dirs()
     # Hack for adding '', which is not otherwise added, to d1 and d2
     d1.addpath('/')
     d2.addpath('/')
     invalid = set()
     dirmove = {}
 
     # examine each file copy for a potential directory move, which is
     # when all the files in a directory are moved to a new directory
     for dst, src in fullcopy.iteritems():
         dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif dsrc in d1 and ddst in d1:
             # directory wasn't entirely moved locally
             invalid.add(dsrc + "/")
         elif dsrc in d2 and ddst in d2:
             # directory wasn't entirely moved remotely
             invalid.add(dsrc + "/")
         elif dsrc + "/" in dirmove and dirmove[dsrc + "/"] != ddst + "/":
             # files from the same directory moved to two different places
             invalid.add(dsrc + "/")
         else:
             # looks good so far
             dirmove[dsrc + "/"] = ddst + "/"
 
     for i in invalid:
         if i in dirmove:
             del dirmove[i]
     del d1, d2, invalid
 
     if not dirmove:
         return copy, movewithdir, diverge, renamedelete
 
     for d in dirmove:
         repo.ui.debug("   discovered dir src: '%s' -> dst: '%s'\n" %
                       (d, dirmove[d]))
 
     # check unaccounted nonoverlapping files against directory moves
     for f in u1 + u2:
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
                     # new file added in a directory that was moved, move it
                     df = dirmove[d] + f[len(d):]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(("   pending file src: '%s' -> "
                                        "dst: '%s'\n") % (f, df))
                     break
 
     return copy, movewithdir, diverge, renamedelete
 
 def checkcopies(ctx, f, m1, m2, ca, limit, diverge, copy, fullcopy):
     """
     check possible copies of f from m1 to m2
 
     ctx = starting context for f in m1
     f = the filename to check
     m1 = the source manifest
     m2 = the destination manifest
     ca = the changectx of the common ancestor
     limit = the rev number to not search beyond
     diverge = record all diverges in this dict
     copy = record all non-divergent copies in this dict
     fullcopy = record all copies in this dict
     """
 
     ma = ca.manifest()
     getfctx = _makegetfctx(ctx)
 
     def _related(f1, f2, limit):
         # Walk back to common ancestor to see if the two files originate
         # from the same file. Since workingfilectx's rev() is None it messes
         # up the integer comparison logic, hence the pre-step check for
         # None (f1 and f2 can only be workingfilectx's initially).
 
         if f1 == f2:
             return f1 # a match
 
         g1, g2 = f1.ancestors(), f2.ancestors()
         try:
             f1r, f2r = f1.linkrev(), f2.linkrev()
 
             if f1r is None:
-                f1 = g1.next()
+                f1 = next(g1)
             if f2r is None:
-                f2 = g2.next()
+                f2 = next(g2)
 
             while True:
                 f1r, f2r = f1.linkrev(), f2.linkrev()
                 if f1r > f2r:
-                    f1 = g1.next()
+                    f1 = next(g1)
                 elif f2r > f1r:
-                    f2 = g2.next()
+                    f2 = next(g2)
                 elif f1 == f2:
                     return f1 # a match
                 elif f1r == f2r or f1r < limit or f2r < limit:
                     return False # copy no longer relevant
         except StopIteration:
             return False
 
     of = None
     seen = set([f])
     for oc in getfctx(f, m1[f]).ancestors():
         ocr = oc.linkrev()
         of = oc.path()
         if of in seen:
             # check limit late - grab last rename before
             if ocr < limit:
                 break
             continue
         seen.add(of)
 
         fullcopy[f] = of # remember for dir rename detection
         if of not in m2:
             continue # no match, keep looking
         if m2[of] == ma.get(of):
             break # no merge needed, quit early
         c2 = getfctx(of, m2[of])
         cr = _related(oc, c2, ca.rev())
         if cr and (of == f or of == c2.path()): # non-divergent
             copy[f] = of
             of = None
             break
 
     if of in ma:
         diverge.setdefault(of, []).append(f)
 
 def duplicatecopies(repo, rev, fromrev, skiprev=None):
     '''reproduce copies from fromrev to rev in the dirstate
 
     If skiprev is specified, it's a revision that should be used to
     filter copy records. Any copies that occur between fromrev and
     skiprev will not be duplicated, even if they appear in the set of
     copies between fromrev and rev.
     '''
     exclude = {}
     if (skiprev is not None and
         not repo.ui.configbool('experimental', 'disablecopytrace')):
         # disablecopytrace skips this line, but not the entire function because
         # the line below is O(size of the repo) during a rebase, while the rest
         # of the function is much faster (and is required for carrying copy
         # metadata across the rebase anyway).
         exclude = pathcopies(repo[fromrev], repo[skiprev])
     for dst, src in pathcopies(repo[fromrev], repo[rev]).iteritems():
         # copies.pathcopies returns backward renames, so dst might not
         # actually be in the dirstate
         if dst in exclude:
             continue
         if repo.dirstate[dst] in "nma":
             repo.dirstate.copy(src, dst)

mercurial/hgweb/webcommands.py

@@ -1,1304 +1,1304 b''
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 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.
 
 from __future__ import absolute_import
 
 import cgi
 import copy
 import mimetypes
 import os
 import re
 
 from ..i18n import _
 from ..node import hex, short
 
 from .common import (
     ErrorResponse,
     HTTP_FORBIDDEN,
     HTTP_NOT_FOUND,
     HTTP_OK,
     get_contact,
     paritygen,
     staticfile,
 )
 
 from .. import (
     archival,
     encoding,
     error,
     graphmod,
     patch,
     revset,
     scmutil,
     templatefilters,
     templater,
     util,
 )
 
 from . import (
     webutil,
 )
 
 __all__ = []
 commands = {}
 
 class webcommand(object):
     """Decorator used to register a web command handler.
 
     The decorator takes as its positional arguments the name/path the
     command should be accessible under.
 
     Usage:
 
     @webcommand('mycommand')
     def mycommand(web, req, tmpl):
         pass
     """
 
     def __init__(self, name):
         self.name = name
 
     def __call__(self, func):
         __all__.append(self.name)
         commands[self.name] = func
         return func
 
 @webcommand('log')
 def log(web, req, tmpl):
     """
     /log[/{revision}[/{path}]]
     --------------------------
 
     Show repository or file history.
 
     For URLs of the form ``/log/{revision}``, a list of changesets starting at
     the specified changeset identifier is shown. If ``{revision}`` is not
     defined, the default is ``tip``. This form is equivalent to the
     ``changelog`` handler.
 
     For URLs of the form ``/log/{revision}/{file}``, the history for a specific
     file will be shown. This form is equivalent to the ``filelog`` handler.
     """
 
     if 'file' in req.form and req.form['file'][0]:
         return filelog(web, req, tmpl)
     else:
         return changelog(web, req, tmpl)
 
 @webcommand('rawfile')
 def rawfile(web, req, tmpl):
     guessmime = web.configbool('web', 'guessmime', False)
 
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
         content = manifest(web, req, tmpl)
         req.respond(HTTP_OK, web.ctype)
         return content
 
     try:
         fctx = webutil.filectx(web.repo, req)
     except error.LookupError as inst:
         try:
             content = manifest(web, req, tmpl)
             req.respond(HTTP_OK, web.ctype)
             return content
         except ErrorResponse:
             raise inst
 
     path = fctx.path()
     text = fctx.data()
     mt = 'application/binary'
     if guessmime:
         mt = mimetypes.guess_type(path)[0]
         if mt is None:
             if util.binary(text):
                 mt = 'application/binary'
             else:
                 mt = 'text/plain'
     if mt.startswith('text/'):
         mt += '; charset="%s"' % encoding.encoding
 
     req.respond(HTTP_OK, mt, path, body=text)
     return []
 
 def _filerevision(web, req, tmpl, fctx):
     f = fctx.path()
     text = fctx.data()
     parity = paritygen(web.stripecount)
 
     if util.binary(text):
         mt = mimetypes.guess_type(f)[0] or 'application/octet-stream'
         text = '(binary:%s)' % mt
 
     def lines():
         for lineno, t in enumerate(text.splitlines(True)):
             yield {"line": t,
                    "lineid": "l%d" % (lineno + 1),
                    "linenumber": "% 6d" % (lineno + 1),
-                   "parity": parity.next()}
+                   "parity": next(parity)}
 
     return tmpl("filerevision",
                 file=f,
                 path=webutil.up(f),
                 text=lines(),
                 symrev=webutil.symrevorshortnode(req, fctx),
                 rename=webutil.renamelink(fctx),
                 permissions=fctx.manifest().flags(f),
                 **webutil.commonentry(web.repo, fctx))
 
 @webcommand('file')
 def file(web, req, tmpl):
     """
     /file/{revision}[/{path}]
     -------------------------
 
     Show information about a directory or file in the repository.
 
     Info about the ``path`` given as a URL parameter will be rendered.
 
     If ``path`` is a directory, information about the entries in that
     directory will be rendered. This form is equivalent to the ``manifest``
     handler.
 
     If ``path`` is a file, information about that file will be shown via
     the ``filerevision`` template.
 
     If ``path`` is not defined, information about the root directory will
     be rendered.
     """
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
         return manifest(web, req, tmpl)
     try:
         return _filerevision(web, req, tmpl, webutil.filectx(web.repo, req))
     except error.LookupError as inst:
         try:
             return manifest(web, req, tmpl)
         except ErrorResponse:
             raise inst
 
 def _search(web, req, tmpl):
     MODE_REVISION = 'rev'
     MODE_KEYWORD = 'keyword'
     MODE_REVSET = 'revset'
 
     def revsearch(ctx):
         yield ctx
 
     def keywordsearch(query):
         lower = encoding.lower
         qw = lower(query).split()
 
         def revgen():
             cl = web.repo.changelog
             for i in xrange(len(web.repo) - 1, 0, -100):
                 l = []
                 for j in cl.revs(max(0, i - 99), i):
                     ctx = web.repo[j]
                     l.append(ctx)
                 l.reverse()
                 for e in l:
                     yield e
 
         for ctx in revgen():
             miss = 0
             for q in qw:
                 if not (q in lower(ctx.user()) or
                         q in lower(ctx.description()) or
                         q in lower(" ".join(ctx.files()))):
                     miss = 1
                     break
             if miss:
                 continue
 
             yield ctx
 
     def revsetsearch(revs):
         for r in revs:
             yield web.repo[r]
 
     searchfuncs = {
         MODE_REVISION: (revsearch, 'exact revision search'),
         MODE_KEYWORD: (keywordsearch, 'literal keyword search'),
         MODE_REVSET: (revsetsearch, 'revset expression search'),
     }
 
     def getsearchmode(query):
         try:
             ctx = web.repo[query]
         except (error.RepoError, error.LookupError):
             # query is not an exact revision pointer, need to
             # decide if it's a revset expression or keywords
             pass
         else:
             return MODE_REVISION, ctx
 
         revdef = 'reverse(%s)' % query
         try:
             tree = revset.parse(revdef)
         except error.ParseError:
             # can't parse to a revset tree
             return MODE_KEYWORD, query
 
         if revset.depth(tree) <= 2:
             # no revset syntax used
             return MODE_KEYWORD, query
 
         if any((token, (value or '')[:3]) == ('string', 're:')
                     for token, value, pos in revset.tokenize(revdef)):
             return MODE_KEYWORD, query
 
         funcsused = revset.funcsused(tree)
         if not funcsused.issubset(revset.safesymbols):
             return MODE_KEYWORD, query
 
         mfunc = revset.match(web.repo.ui, revdef)
         try:
             revs = mfunc(web.repo)
             return MODE_REVSET, revs
             # ParseError: wrongly placed tokens, wrongs arguments, etc
             # RepoLookupError: no such revision, e.g. in 'revision:'
             # Abort: bookmark/tag not exists
             # LookupError: ambiguous identifier, e.g. in '(bc)' on a large repo
         except (error.ParseError, error.RepoLookupError, error.Abort,
                 LookupError):
             return MODE_KEYWORD, query
 
     def changelist(**map):
         count = 0
 
         for ctx in searchfunc[0](funcarg):
             count += 1
             n = ctx.node()
             showtags = webutil.showtag(web.repo, tmpl, 'changelogtag', n)
             files = webutil.listfilediffs(tmpl, ctx.files(), n, web.maxfiles)
 
             yield tmpl('searchentry',
-                       parity=parity.next(),
+                       parity=next(parity),
                        changelogtag=showtags,
                        files=files,
                        **webutil.commonentry(web.repo, ctx))
 
             if count >= revcount:
                 break
 
     query = req.form['rev'][0]
     revcount = web.maxchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     lessvars['rev'] = query
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
     morevars['rev'] = query
 
     mode, funcarg = getsearchmode(query)
 
     if 'forcekw' in req.form:
         showforcekw = ''
         showunforcekw = searchfuncs[mode][1]
         mode = MODE_KEYWORD
         funcarg = query
     else:
         if mode != MODE_KEYWORD:
             showforcekw = searchfuncs[MODE_KEYWORD][1]
         else:
             showforcekw = ''
         showunforcekw = ''
 
     searchfunc = searchfuncs[mode]
 
     tip = web.repo['tip']
     parity = paritygen(web.stripecount)
 
     return tmpl('search', query=query, node=tip.hex(), symrev='tip',
                 entries=changelist, archives=web.archivelist("tip"),
                 morevars=morevars, lessvars=lessvars,
                 modedesc=searchfunc[1],
                 showforcekw=showforcekw, showunforcekw=showunforcekw)
 
 @webcommand('changelog')
 def changelog(web, req, tmpl, shortlog=False):
     """
     /changelog[/{revision}]
     -----------------------
 
     Show information about multiple changesets.
 
     If the optional ``revision`` URL argument is absent, information about
     all changesets starting at ``tip`` will be rendered. If the ``revision``
     argument is present, changesets will be shown starting from the specified
     revision.
 
     If ``revision`` is absent, the ``rev`` query string argument may be
     defined. This will perform a search for changesets.
 
     The argument for ``rev`` can be a single revision, a revision set,
     or a literal keyword to search for in changeset data (equivalent to
     :hg:`log -k`).
 
     The ``revcount`` query string argument defines the maximum numbers of
     changesets to render.
 
     For non-searches, the ``changelog`` template will be rendered.
     """
 
     query = ''
     if 'node' in req.form:
         ctx = webutil.changectx(web.repo, req)
         symrev = webutil.symrevorshortnode(req, ctx)
     elif 'rev' in req.form:
         return _search(web, req, tmpl)
     else:
         ctx = web.repo['tip']
         symrev = 'tip'
 
     def changelist():
         revs = []
         if pos != -1:
             revs = web.repo.changelog.revs(pos, 0)
         curcount = 0
         for rev in revs:
             curcount += 1
             if curcount > revcount + 1:
                 break
 
             entry = webutil.changelistentry(web, web.repo[rev], tmpl)
-            entry['parity'] = parity.next()
+            entry['parity'] = next(parity)
             yield entry
 
     if shortlog:
         revcount = web.maxshortchanges
     else:
         revcount = web.maxchanges
 
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = len(web.repo)
     pos = ctx.rev()
     parity = paritygen(web.stripecount)
 
     changenav = webutil.revnav(web.repo).gen(pos, revcount, count)
 
     entries = list(changelist())
     latestentry = entries[:1]
     if len(entries) > revcount:
         nextentry = entries[-1:]
         entries = entries[:-1]
     else:
         nextentry = []
 
     return tmpl(shortlog and 'shortlog' or 'changelog', changenav=changenav,
                 node=ctx.hex(), rev=pos, symrev=symrev, changesets=count,
                 entries=entries,
                 latestentry=latestentry, nextentry=nextentry,
                 archives=web.archivelist("tip"), revcount=revcount,
                 morevars=morevars, lessvars=lessvars, query=query)
 
 @webcommand('shortlog')
 def shortlog(web, req, tmpl):
     """
     /shortlog
     ---------
 
     Show basic information about a set of changesets.
 
     This accepts the same parameters as the ``changelog`` handler. The only
     difference is the ``shortlog`` template will be rendered instead of the
     ``changelog`` template.
     """
     return changelog(web, req, tmpl, shortlog=True)
 
 @webcommand('changeset')
 def changeset(web, req, tmpl):
     """
     /changeset[/{revision}]
     -----------------------
 
     Show information about a single changeset.
 
     A URL path argument is the changeset identifier to show. See ``hg help
     revisions`` for possible values. If not defined, the ``tip`` changeset
     will be shown.
 
     The ``changeset`` template is rendered. Contents of the ``changesettag``,
     ``changesetbookmark``, ``filenodelink``, ``filenolink``, and the many
     templates related to diffs may all be used to produce the output.
     """
     ctx = webutil.changectx(web.repo, req)
 
     return tmpl('changeset', **webutil.changesetentry(web, req, tmpl, ctx))
 
 rev = webcommand('rev')(changeset)
 
 def decodepath(path):
     """Hook for mapping a path in the repository to a path in the
     working copy.
 
     Extensions (e.g., largefiles) can override this to remap files in
     the virtual file system presented by the manifest command below."""
     return path
 
 @webcommand('manifest')
 def manifest(web, req, tmpl):
     """
     /manifest[/{revision}[/{path}]]
     -------------------------------
 
     Show information about a directory.
 
     If the URL path arguments are omitted, information about the root
     directory for the ``tip`` changeset will be shown.
 
     Because this handler can only show information for directories, it
     is recommended to use the ``file`` handler instead, as it can handle both
     directories and files.
 
     The ``manifest`` template will be rendered for this handler.
     """
     if 'node' in req.form:
         ctx = webutil.changectx(web.repo, req)
         symrev = webutil.symrevorshortnode(req, ctx)
     else:
         ctx = web.repo['tip']
         symrev = 'tip'
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     mf = ctx.manifest()
     node = ctx.node()
 
     files = {}
     dirs = {}
     parity = paritygen(web.stripecount)
 
     if path and path[-1] != "/":
         path += "/"
     l = len(path)
     abspath = "/" + path
 
     for full, n in mf.iteritems():
         # the virtual path (working copy path) used for the full
         # (repository) path
         f = decodepath(full)
 
         if f[:l] != path:
             continue
         remain = f[l:]
         elements = remain.split('/')
         if len(elements) == 1:
             files[remain] = full
         else:
             h = dirs # need to retain ref to dirs (root)
             for elem in elements[0:-1]:
                 if elem not in h:
                     h[elem] = {}
                 h = h[elem]
                 if len(h) > 1:
                     break
             h[None] = None # denotes files present
 
     if mf and not files and not dirs:
         raise ErrorResponse(HTTP_NOT_FOUND, 'path not found: ' + path)
 
     def filelist(**map):
         for f in sorted(files):
             full = files[f]
 
             fctx = ctx.filectx(full)
             yield {"file": full,
-                   "parity": parity.next(),
+                   "parity": next(parity),
                    "basename": f,
                    "date": fctx.date(),
                    "size": fctx.size(),
                    "permissions": mf.flags(full)}
 
     def dirlist(**map):
         for d in sorted(dirs):
 
             emptydirs = []
             h = dirs[d]
             while isinstance(h, dict) and len(h) == 1:
                 k, v = h.items()[0]
                 if v:
                     emptydirs.append(k)
                 h = v
 
             path = "%s%s" % (abspath, d)
-            yield {"parity": parity.next(),
+            yield {"parity": next(parity),
                    "path": path,
                    "emptydirs": "/".join(emptydirs),
                    "basename": d}
 
     return tmpl("manifest",
                 symrev=symrev,
                 path=abspath,
                 up=webutil.up(abspath),
-                upparity=parity.next(),
+                upparity=next(parity),
                 fentries=filelist,
                 dentries=dirlist,
                 archives=web.archivelist(hex(node)),
                 **webutil.commonentry(web.repo, ctx))
 
 @webcommand('tags')
 def tags(web, req, tmpl):
     """
     /tags
     -----
 
     Show information about tags.
 
     No arguments are accepted.
 
     The ``tags`` template is rendered.
     """
     i = list(reversed(web.repo.tagslist()))
     parity = paritygen(web.stripecount)
 
     def entries(notip, latestonly, **map):
         t = i
         if notip:
             t = [(k, n) for k, n in i if k != "tip"]
         if latestonly:
             t = t[:1]
         for k, n in t:
-            yield {"parity": parity.next(),
+            yield {"parity": next(parity),
                    "tag": k,
                    "date": web.repo[n].date(),
                    "node": hex(n)}
 
     return tmpl("tags",
                 node=hex(web.repo.changelog.tip()),
                 entries=lambda **x: entries(False, False, **x),
                 entriesnotip=lambda **x: entries(True, False, **x),
                 latestentry=lambda **x: entries(True, True, **x))
 
 @webcommand('bookmarks')
 def bookmarks(web, req, tmpl):
     """
     /bookmarks
     ----------
 
     Show information about bookmarks.
 
     No arguments are accepted.
 
     The ``bookmarks`` template is rendered.
     """
     i = [b for b in web.repo._bookmarks.items() if b[1] in web.repo]
     sortkey = lambda b: (web.repo[b[1]].rev(), b[0])
     i = sorted(i, key=sortkey, reverse=True)
     parity = paritygen(web.stripecount)
 
     def entries(latestonly, **map):
         t = i
         if latestonly:
             t = i[:1]
         for k, n in t:
-            yield {"parity": parity.next(),
+            yield {"parity": next(parity),
                    "bookmark": k,
                    "date": web.repo[n].date(),
                    "node": hex(n)}
 
     if i:
         latestrev = i[0][1]
     else:
         latestrev = -1
 
     return tmpl("bookmarks",
                 node=hex(web.repo.changelog.tip()),
                 lastchange=[{"date": web.repo[latestrev].date()}],
                 entries=lambda **x: entries(latestonly=False, **x),
                 latestentry=lambda **x: entries(latestonly=True, **x))
 
 @webcommand('branches')
 def branches(web, req, tmpl):
     """
     /branches
     ---------
 
     Show information about branches.
 
     All known branches are contained in the output, even closed branches.
 
     No arguments are accepted.
 
     The ``branches`` template is rendered.
     """
     entries = webutil.branchentries(web.repo, web.stripecount)
     latestentry = webutil.branchentries(web.repo, web.stripecount, 1)
     return tmpl('branches', node=hex(web.repo.changelog.tip()),
                 entries=entries, latestentry=latestentry)
 
 @webcommand('summary')
 def summary(web, req, tmpl):
     """
     /summary
     --------
 
     Show a summary of repository state.
 
     Information about the latest changesets, bookmarks, tags, and branches
     is captured by this handler.
 
     The ``summary`` template is rendered.
     """
     i = reversed(web.repo.tagslist())
 
     def tagentries(**map):
         parity = paritygen(web.stripecount)
         count = 0
         for k, n in i:
             if k == "tip": # skip tip
                 continue
 
             count += 1
             if count > 10: # limit to 10 tags
                 break
 
             yield tmpl("tagentry",
-                       parity=parity.next(),
+                       parity=next(parity),
                        tag=k,
                        node=hex(n),
                        date=web.repo[n].date())
 
     def bookmarks(**map):
         parity = paritygen(web.stripecount)
         marks = [b for b in web.repo._bookmarks.items() if b[1] in web.repo]
         sortkey = lambda b: (web.repo[b[1]].rev(), b[0])
         marks = sorted(marks, key=sortkey, reverse=True)
         for k, n in marks[:10]:  # limit to 10 bookmarks
-            yield {'parity': parity.next(),
+            yield {'parity': next(parity),
                    'bookmark': k,
                    'date': web.repo[n].date(),
                    'node': hex(n)}
 
     def changelist(**map):
         parity = paritygen(web.stripecount, offset=start - end)
         l = [] # build a list in forward order for efficiency
         revs = []
         if start < end:
             revs = web.repo.changelog.revs(start, end - 1)
         for i in revs:
             ctx = web.repo[i]
 
             l.append(tmpl(
                 'shortlogentry',
-                parity=parity.next(),
+                parity=next(parity),
                 **webutil.commonentry(web.repo, ctx)))
 
         l.reverse()
         yield l
 
     tip = web.repo['tip']
     count = len(web.repo)
     start = max(0, count - web.maxchanges)
     end = min(count, start + web.maxchanges)
 
     return tmpl("summary",
                 desc=web.config("web", "description", "unknown"),
                 owner=get_contact(web.config) or "unknown",
                 lastchange=tip.date(),
                 tags=tagentries,
                 bookmarks=bookmarks,
                 branches=webutil.branchentries(web.repo, web.stripecount, 10),
                 shortlog=changelist,
                 node=tip.hex(),
                 symrev='tip',
                 archives=web.archivelist("tip"))
 
 @webcommand('filediff')
 def filediff(web, req, tmpl):
     """
     /diff/{revision}/{path}
     -----------------------
 
     Show how a file changed in a particular commit.
 
     The ``filediff`` template is rendered.
 
     This handler is registered under both the ``/diff`` and ``/filediff``
     paths. ``/diff`` is used in modern code.
     """
     fctx, ctx = None, None
     try:
         fctx = webutil.filectx(web.repo, req)
     except LookupError:
         ctx = webutil.changectx(web.repo, req)
         path = webutil.cleanpath(web.repo, req.form['file'][0])
         if path not in ctx.files():
             raise
 
     if fctx is not None:
         path = fctx.path()
         ctx = fctx.changectx()
 
     parity = paritygen(web.stripecount)
     style = web.config('web', 'style', 'paper')
     if 'style' in req.form:
         style = req.form['style'][0]
 
     diffs = webutil.diffs(web.repo, tmpl, ctx, None, [path], parity, style)
     if fctx is not None:
         rename = webutil.renamelink(fctx)
         ctx = fctx
     else:
         rename = []
         ctx = ctx
     return tmpl("filediff",
                 file=path,
                 symrev=webutil.symrevorshortnode(req, ctx),
                 rename=rename,
                 diff=diffs,
                 **webutil.commonentry(web.repo, ctx))
 
 diff = webcommand('diff')(filediff)
 
 @webcommand('comparison')
 def comparison(web, req, tmpl):
     """
     /comparison/{revision}/{path}
     -----------------------------
 
     Show a comparison between the old and new versions of a file from changes
     made on a particular revision.
 
     This is similar to the ``diff`` handler. However, this form features
     a split or side-by-side diff rather than a unified diff.
 
     The ``context`` query string argument can be used to control the lines of
     context in the diff.
 
     The ``filecomparison`` template is rendered.
     """
     ctx = webutil.changectx(web.repo, req)
     if 'file' not in req.form:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = webutil.cleanpath(web.repo, req.form['file'][0])
 
     parsecontext = lambda v: v == 'full' and -1 or int(v)
     if 'context' in req.form:
         context = parsecontext(req.form['context'][0])
     else:
         context = parsecontext(web.config('web', 'comparisoncontext', '5'))
 
     def filelines(f):
         if util.binary(f.data()):
             mt = mimetypes.guess_type(f.path())[0]
             if not mt:
                 mt = 'application/octet-stream'
             return [_('(binary file %s, hash: %s)') % (mt, hex(f.filenode()))]
         return f.data().splitlines()
 
     fctx = None
     parent = ctx.p1()
     leftrev = parent.rev()
     leftnode = parent.node()
     rightrev = ctx.rev()
     rightnode = ctx.node()
     if path in ctx:
         fctx = ctx[path]
         rightlines = filelines(fctx)
         if path not in parent:
             leftlines = ()
         else:
             pfctx = parent[path]
             leftlines = filelines(pfctx)
     else:
         rightlines = ()
         pfctx = ctx.parents()[0][path]
         leftlines = filelines(pfctx)
 
     comparison = webutil.compare(tmpl, context, leftlines, rightlines)
     if fctx is not None:
         rename = webutil.renamelink(fctx)
         ctx = fctx
     else:
         rename = []
         ctx = ctx
     return tmpl('filecomparison',
                 file=path,
                 symrev=webutil.symrevorshortnode(req, ctx),
                 rename=rename,
                 leftrev=leftrev,
                 leftnode=hex(leftnode),
                 rightrev=rightrev,
                 rightnode=hex(rightnode),
                 comparison=comparison,
                 **webutil.commonentry(web.repo, ctx))
 
 @webcommand('annotate')
 def annotate(web, req, tmpl):
     """
     /annotate/{revision}/{path}
     ---------------------------
 
     Show changeset information for each line in a file.
 
     The ``fileannotate`` template is rendered.
     """
     fctx = webutil.filectx(web.repo, req)
     f = fctx.path()
     parity = paritygen(web.stripecount)
     diffopts = patch.difffeatureopts(web.repo.ui, untrusted=True,
                                      section='annotate', whitespace=True)
 
     def annotate(**map):
         last = None
         if util.binary(fctx.data()):
             mt = (mimetypes.guess_type(fctx.path())[0]
                   or 'application/octet-stream')
             lines = enumerate([((fctx.filectx(fctx.filerev()), 1),
                                 '(binary:%s)' % mt)])
         else:
             lines = enumerate(fctx.annotate(follow=True, linenumber=True,
                                             diffopts=diffopts))
         for lineno, ((f, targetline), l) in lines:
             fnode = f.filenode()
 
             if last != fnode:
                 last = fnode
 
-            yield {"parity": parity.next(),
+            yield {"parity": next(parity),
                    "node": f.hex(),
                    "rev": f.rev(),
                    "author": f.user(),
                    "desc": f.description(),
                    "extra": f.extra(),
                    "file": f.path(),
                    "targetline": targetline,
                    "line": l,
                    "lineno": lineno + 1,
                    "lineid": "l%d" % (lineno + 1),
                    "linenumber": "% 6d" % (lineno + 1),
                    "revdate": f.date()}
 
     return tmpl("fileannotate",
                 file=f,
                 annotate=annotate,
                 path=webutil.up(f),
                 symrev=webutil.symrevorshortnode(req, fctx),
                 rename=webutil.renamelink(fctx),
                 permissions=fctx.manifest().flags(f),
                 **webutil.commonentry(web.repo, fctx))
 
 @webcommand('filelog')
 def filelog(web, req, tmpl):
     """
     /filelog/{revision}/{path}
     --------------------------
 
     Show information about the history of a file in the repository.
 
     The ``revcount`` query string argument can be defined to control the
     maximum number of entries to show.
 
     The ``filelog`` template will be rendered.
     """
 
     try:
         fctx = webutil.filectx(web.repo, req)
         f = fctx.path()
         fl = fctx.filelog()
     except error.LookupError:
         f = webutil.cleanpath(web.repo, req.form['file'][0])
         fl = web.repo.file(f)
         numrevs = len(fl)
         if not numrevs: # file doesn't exist at all
             raise
         rev = webutil.changectx(web.repo, req).rev()
         first = fl.linkrev(0)
         if rev < first: # current rev is from before file existed
             raise
         frev = numrevs - 1
         while fl.linkrev(frev) > rev:
             frev -= 1
         fctx = web.repo.filectx(f, fl.linkrev(frev))
 
     revcount = web.maxshortchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = fctx.filerev() + 1
     start = max(0, fctx.filerev() - revcount + 1) # first rev on this page
     end = min(count, start + revcount) # last rev on this page
     parity = paritygen(web.stripecount, offset=start - end)
 
     def entries():
         l = []
 
         repo = web.repo
         revs = fctx.filelog().revs(start, end - 1)
         for i in revs:
             iterfctx = fctx.filectx(i)
 
             l.append(dict(
-                parity=parity.next(),
+                parity=next(parity),
                 filerev=i,
                 file=f,
                 rename=webutil.renamelink(iterfctx),
                 **webutil.commonentry(repo, iterfctx)))
         for e in reversed(l):
             yield e
 
     entries = list(entries())
     latestentry = entries[:1]
 
     revnav = webutil.filerevnav(web.repo, fctx.path())
     nav = revnav.gen(end - 1, revcount, count)
     return tmpl("filelog",
                 file=f,
                 nav=nav,
                 symrev=webutil.symrevorshortnode(req, fctx),
                 entries=entries,
                 latestentry=latestentry,
                 revcount=revcount,
                 morevars=morevars,
                 lessvars=lessvars,
                 **webutil.commonentry(web.repo, fctx))
 
 @webcommand('archive')
 def archive(web, req, tmpl):
     """
     /archive/{revision}.{format}[/{path}]
     -------------------------------------
 
     Obtain an archive of repository content.
 
     The content and type of the archive is defined by a URL path parameter.
     ``format`` is the file extension of the archive type to be generated. e.g.
     ``zip`` or ``tar.bz2``. Not all archive types may be allowed by your
     server configuration.
 
     The optional ``path`` URL parameter controls content to include in the
     archive. If omitted, every file in the specified revision is present in the
     archive. If included, only the specified file or contents of the specified
     directory will be included in the archive.
 
     No template is used for this handler. Raw, binary content is generated.
     """
 
     type_ = req.form.get('type', [None])[0]
     allowed = web.configlist("web", "allow_archive")
     key = req.form['node'][0]
 
     if type_ not in web.archives:
         msg = 'Unsupported archive type: %s' % type_
         raise ErrorResponse(HTTP_NOT_FOUND, msg)
 
     if not ((type_ in allowed or
         web.configbool("web", "allow" + type_, False))):
         msg = 'Archive type not allowed: %s' % type_
         raise ErrorResponse(HTTP_FORBIDDEN, msg)
 
     reponame = re.sub(r"\W+", "-", os.path.basename(web.reponame))
     cnode = web.repo.lookup(key)
     arch_version = key
     if cnode == key or key == 'tip':
         arch_version = short(cnode)
     name = "%s-%s" % (reponame, arch_version)
 
     ctx = webutil.changectx(web.repo, req)
     pats = []
     matchfn = scmutil.match(ctx, [])
     file = req.form.get('file', None)
     if file:
         pats = ['path:' + file[0]]
         matchfn = scmutil.match(ctx, pats, default='path')
         if pats:
             files = [f for f in ctx.manifest().keys() if matchfn(f)]
             if not files:
                 raise ErrorResponse(HTTP_NOT_FOUND,
                     'file(s) not found: %s' % file[0])
 
     mimetype, artype, extension, encoding = web.archivespecs[type_]
     headers = [
         ('Content-Disposition', 'attachment; filename=%s%s' % (name, extension))
         ]
     if encoding:
         headers.append(('Content-Encoding', encoding))
     req.headers.extend(headers)
     req.respond(HTTP_OK, mimetype)
 
     archival.archive(web.repo, req, cnode, artype, prefix=name,
                      matchfn=matchfn,
                      subrepos=web.configbool("web", "archivesubrepos"))
     return []
 
 
 @webcommand('static')
 def static(web, req, tmpl):
     fname = req.form['file'][0]
     # a repo owner may set web.static in .hg/hgrc to get any file
     # readable by the user running the CGI script
     static = web.config("web", "static", None, untrusted=False)
     if not static:
         tp = web.templatepath or templater.templatepaths()
         if isinstance(tp, str):
             tp = [tp]
         static = [os.path.join(p, 'static') for p in tp]
     staticfile(static, fname, req)
     return []
 
 @webcommand('graph')
 def graph(web, req, tmpl):
     """
     /graph[/{revision}]
     -------------------
 
     Show information about the graphical topology of the repository.
 
     Information rendered by this handler can be used to create visual
     representations of repository topology.
 
     The ``revision`` URL parameter controls the starting changeset.
 
     The ``revcount`` query string argument can define the number of changesets
     to show information for.
 
     This handler will render the ``graph`` template.
     """
 
     if 'node' in req.form:
         ctx = webutil.changectx(web.repo, req)
         symrev = webutil.symrevorshortnode(req, ctx)
     else:
         ctx = web.repo['tip']
         symrev = 'tip'
     rev = ctx.rev()
 
     bg_height = 39
     revcount = web.maxshortchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = len(web.repo)
     pos = rev
 
     uprev = min(max(0, count - 1), rev + revcount)
     downrev = max(0, rev - revcount)
     changenav = webutil.revnav(web.repo).gen(pos, revcount, count)
 
     tree = []
     if pos != -1:
         allrevs = web.repo.changelog.revs(pos, 0)
         revs = []
         for i in allrevs:
             revs.append(i)
             if len(revs) >= revcount:
                 break
 
         # We have to feed a baseset to dagwalker as it is expecting smartset
         # object. This does not have a big impact on hgweb performance itself
         # since hgweb graphing code is not itself lazy yet.
         dag = graphmod.dagwalker(web.repo, revset.baseset(revs))
         # As we said one line above... not lazy.
         tree = list(graphmod.colored(dag, web.repo))
 
     def getcolumns(tree):
         cols = 0
         for (id, type, ctx, vtx, edges) in tree:
             if type != graphmod.CHANGESET:
                 continue
             cols = max(cols, max([edge[0] for edge in edges] or [0]),
                              max([edge[1] for edge in edges] or [0]))
         return cols
 
     def graphdata(usetuples, encodestr):
         data = []
 
         row = 0
         for (id, type, ctx, vtx, edges) in tree:
             if type != graphmod.CHANGESET:
                 continue
             node = str(ctx)
             age = encodestr(templatefilters.age(ctx.date()))
             desc = templatefilters.firstline(encodestr(ctx.description()))
             desc = cgi.escape(templatefilters.nonempty(desc))
             user = cgi.escape(templatefilters.person(encodestr(ctx.user())))
             branch = cgi.escape(encodestr(ctx.branch()))
             try:
                 branchnode = web.repo.branchtip(branch)
             except error.RepoLookupError:
                 branchnode = None
             branch = branch, branchnode == ctx.node()
 
             if usetuples:
                 data.append((node, vtx, edges, desc, user, age, branch,
                              [cgi.escape(encodestr(x)) for x in ctx.tags()],
                              [cgi.escape(encodestr(x))
                               for x in ctx.bookmarks()]))
             else:
                 edgedata = [{'col': edge[0], 'nextcol': edge[1],
                              'color': (edge[2] - 1) % 6 + 1,
                              'width': edge[3], 'bcolor': edge[4]}
                             for edge in edges]
 
                 data.append(
                     {'node': node,
                      'col': vtx[0],
                      'color': (vtx[1] - 1) % 6 + 1,
                      'edges': edgedata,
                      'row': row,
                      'nextrow': row + 1,
                      'desc': desc,
                      'user': user,
                      'age': age,
                      'bookmarks': webutil.nodebookmarksdict(
                          web.repo, ctx.node()),
                      'branches': webutil.nodebranchdict(web.repo, ctx),
                      'inbranch': webutil.nodeinbranch(web.repo, ctx),
                      'tags': webutil.nodetagsdict(web.repo, ctx.node())})
 
             row += 1
 
         return data
 
     cols = getcolumns(tree)
     rows = len(tree)
     canvasheight = (rows + 1) * bg_height - 27
 
     return tmpl('graph', rev=rev, symrev=symrev, revcount=revcount,
                 uprev=uprev,
                 lessvars=lessvars, morevars=morevars, downrev=downrev,
                 cols=cols, rows=rows,
                 canvaswidth=(cols + 1) * bg_height,
                 truecanvasheight=rows * bg_height,
                 canvasheight=canvasheight, bg_height=bg_height,
                 # {jsdata} will be passed to |json, so it must be in utf-8
                 jsdata=lambda **x: graphdata(True, encoding.fromlocal),
                 nodes=lambda **x: graphdata(False, str),
                 node=ctx.hex(), changenav=changenav)
 
 def _getdoc(e):
     doc = e[0].__doc__
     if doc:
         doc = _(doc).partition('\n')[0]
     else:
         doc = _('(no help text available)')
     return doc
 
 @webcommand('help')
 def help(web, req, tmpl):
     """
     /help[/{topic}]
     ---------------
 
     Render help documentation.
 
     This web command is roughly equivalent to :hg:`help`. If a ``topic``
     is defined, that help topic will be rendered. If not, an index of
     available help topics will be rendered.
 
     The ``help`` template will be rendered when requesting help for a topic.
     ``helptopics`` will be rendered for the index of help topics.
     """
     from .. import commands, help as helpmod  # avoid cycle
 
     topicname = req.form.get('node', [None])[0]
     if not topicname:
         def topics(**map):
             for entries, summary, _doc in helpmod.helptable:
                 yield {'topic': entries[0], 'summary': summary}
 
         early, other = [], []
         primary = lambda s: s.partition('|')[0]
         for c, e in commands.table.iteritems():
             doc = _getdoc(e)
             if 'DEPRECATED' in doc or c.startswith('debug'):
                 continue
             cmd = primary(c)
             if cmd.startswith('^'):
                 early.append((cmd[1:], doc))
             else:
                 other.append((cmd, doc))
 
         early.sort()
         other.sort()
 
         def earlycommands(**map):
             for c, doc in early:
                 yield {'topic': c, 'summary': doc}
 
         def othercommands(**map):
             for c, doc in other:
                 yield {'topic': c, 'summary': doc}
 
         return tmpl('helptopics', topics=topics, earlycommands=earlycommands,
                     othercommands=othercommands, title='Index')
 
     # Render an index of sub-topics.
     if topicname in helpmod.subtopics:
         topics = []
         for entries, summary, _doc in helpmod.subtopics[topicname]:
             topics.append({
                 'topic': '%s.%s' % (topicname, entries[0]),
                 'basename': entries[0],
                 'summary': summary,
             })
 
         return tmpl('helptopics', topics=topics, title=topicname,
                     subindex=True)
 
     u = webutil.wsgiui()
     u.verbose = True
 
     # Render a page from a sub-topic.
     if '.' in topicname:
         # TODO implement support for rendering sections, like
         # `hg help` works.
         topic, subtopic = topicname.split('.', 1)
         if topic not in helpmod.subtopics:
             raise ErrorResponse(HTTP_NOT_FOUND)
     else:
         topic = topicname
         subtopic = None
 
     try:
         doc = helpmod.help_(u, topic, subtopic=subtopic)
     except error.UnknownCommand:
         raise ErrorResponse(HTTP_NOT_FOUND)
     return tmpl('help', topic=topicname, doc=doc)
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = commands.values()

mercurial/hgweb/webutil.py

@@ -1,608 +1,608 b''
 # hgweb/webutil.py - utility library for the web interface.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 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.
 
 from __future__ import absolute_import
 
 import copy
 import difflib
 import os
 import re
 
 from ..i18n import _
 from ..node import hex, nullid, short
 
 from .common import (
     ErrorResponse,
     HTTP_NOT_FOUND,
     paritygen,
 )
 
 from .. import (
     context,
     error,
     match,
     patch,
     pathutil,
     templatefilters,
     ui as uimod,
     util,
 )
 
 def up(p):
     if p[0] != "/":
         p = "/" + p
     if p[-1] == "/":
         p = p[:-1]
     up = os.path.dirname(p)
     if up == "/":
         return "/"
     return up + "/"
 
 def _navseq(step, firststep=None):
     if firststep:
         yield firststep
         if firststep >= 20 and firststep <= 40:
             firststep = 50
             yield firststep
         assert step > 0
         assert firststep > 0
         while step <= firststep:
             step *= 10
     while True:
         yield 1 * step
         yield 3 * step
         step *= 10
 
 class revnav(object):
 
     def __init__(self, repo):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         """
         # used for hex generation
         self._revlog = repo.changelog
 
     def __nonzero__(self):
         """return True if any revision to navigate over"""
         return self._first() is not None
 
     def _first(self):
         """return the minimum non-filtered changeset or None"""
         try:
-            return iter(self._revlog).next()
+            return next(iter(self._revlog))
         except StopIteration:
             return None
 
     def hex(self, rev):
         return hex(self._revlog.node(rev))
 
     def gen(self, pos, pagelen, limit):
         """computes label and revision id for navigation link
 
         :pos: is the revision relative to which we generate navigation.
         :pagelen: the size of each navigation page
         :limit: how far shall we link
 
         The return is:
             - a single element tuple
             - containing a dictionary with a `before` and `after` key
             - values are generator functions taking arbitrary number of kwargs
             - yield items are dictionaries with `label` and `node` keys
         """
         if not self:
             # empty repo
             return ({'before': (), 'after': ()},)
 
         targets = []
         for f in _navseq(1, pagelen):
             if f > limit:
                 break
             targets.append(pos + f)
             targets.append(pos - f)
         targets.sort()
 
         first = self._first()
         navbefore = [("(%i)" % first, self.hex(first))]
         navafter = []
         for rev in targets:
             if rev not in self._revlog:
                 continue
             if pos < rev < limit:
                 navafter.append(("+%d" % abs(rev - pos), self.hex(rev)))
             if 0 < rev < pos:
                 navbefore.append(("-%d" % abs(rev - pos), self.hex(rev)))
 
 
         navafter.append(("tip", "tip"))
 
         data = lambda i: {"label": i[0], "node": i[1]}
         return ({'before': lambda **map: (data(i) for i in navbefore),
                  'after':  lambda **map: (data(i) for i in navafter)},)
 
 class filerevnav(revnav):
 
     def __init__(self, repo, path):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         :path: path of the file we generate nav for
         """
         # used for iteration
         self._changelog = repo.unfiltered().changelog
         # used for hex generation
         self._revlog = repo.file(path)
 
     def hex(self, rev):
         return hex(self._changelog.node(self._revlog.linkrev(rev)))
 
 class _siblings(object):
     def __init__(self, siblings=[], hiderev=None):
         self.siblings = [s for s in siblings if s.node() != nullid]
         if len(self.siblings) == 1 and self.siblings[0].rev() == hiderev:
             self.siblings = []
 
     def __iter__(self):
         for s in self.siblings:
             d = {
                 'node': s.hex(),
                 'rev': s.rev(),
                 'user': s.user(),
                 'date': s.date(),
                 'description': s.description(),
                 'branch': s.branch(),
             }
             if util.safehasattr(s, 'path'):
                 d['file'] = s.path()
             yield d
 
     def __len__(self):
         return len(self.siblings)
 
 def parents(ctx, hide=None):
     if isinstance(ctx, context.basefilectx):
         introrev = ctx.introrev()
         if ctx.changectx().rev() != introrev:
             return _siblings([ctx.repo()[introrev]], hide)
     return _siblings(ctx.parents(), hide)
 
 def children(ctx, hide=None):
     return _siblings(ctx.children(), hide)
 
 def renamelink(fctx):
     r = fctx.renamed()
     if r:
         return [{'file': r[0], 'node': hex(r[1])}]
     return []
 
 def nodetagsdict(repo, node):
     return [{"name": i} for i in repo.nodetags(node)]
 
 def nodebookmarksdict(repo, node):
     return [{"name": i} for i in repo.nodebookmarks(node)]
 
 def nodebranchdict(repo, ctx):
     branches = []
     branch = ctx.branch()
     # If this is an empty repo, ctx.node() == nullid,
     # ctx.branch() == 'default'.
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branchnode == ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodeinbranch(repo, ctx):
     branches = []
     branch = ctx.branch()
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branch != 'default' and branchnode != ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodebranchnodefault(ctx):
     branches = []
     branch = ctx.branch()
     if branch != 'default':
         branches.append({"name": branch})
     return branches
 
 def showtag(repo, tmpl, t1, node=nullid, **args):
     for t in repo.nodetags(node):
         yield tmpl(t1, tag=t, **args)
 
 def showbookmark(repo, tmpl, t1, node=nullid, **args):
     for t in repo.nodebookmarks(node):
         yield tmpl(t1, bookmark=t, **args)
 
 def branchentries(repo, stripecount, limit=0):
     tips = []
     heads = repo.heads()
     parity = paritygen(stripecount)
     sortkey = lambda item: (not item[1], item[0].rev())
 
     def entries(**map):
         count = 0
         if not tips:
             for tag, hs, tip, closed in repo.branchmap().iterbranches():
                 tips.append((repo[tip], closed))
         for ctx, closed in sorted(tips, key=sortkey, reverse=True):
             if limit > 0 and count >= limit:
                 return
             count += 1
             if closed:
                 status = 'closed'
             elif ctx.node() not in heads:
                 status = 'inactive'
             else:
                 status = 'open'
             yield {
-                'parity': parity.next(),
+                'parity': next(parity),
                 'branch': ctx.branch(),
                 'status': status,
                 'node': ctx.hex(),
                 'date': ctx.date()
             }
 
     return entries
 
 def cleanpath(repo, path):
     path = path.lstrip('/')
     return pathutil.canonpath(repo.root, '', path)
 
 def changeidctx(repo, changeid):
     try:
         ctx = repo[changeid]
     except error.RepoError:
         man = repo.manifest
         ctx = repo[man.linkrev(man.rev(man.lookup(changeid)))]
 
     return ctx
 
 def changectx(repo, req):
     changeid = "tip"
     if 'node' in req.form:
         changeid = req.form['node'][0]
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[(ipos + 1):]
     elif 'manifest' in req.form:
         changeid = req.form['manifest'][0]
 
     return changeidctx(repo, changeid)
 
 def basechangectx(repo, req):
     if 'node' in req.form:
         changeid = req.form['node'][0]
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[:ipos]
             return changeidctx(repo, changeid)
 
     return None
 
 def filectx(repo, req):
     if 'file' not in req.form:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = cleanpath(repo, req.form['file'][0])
     if 'node' in req.form:
         changeid = req.form['node'][0]
     elif 'filenode' in req.form:
         changeid = req.form['filenode'][0]
     else:
         raise ErrorResponse(HTTP_NOT_FOUND, 'node or filenode not given')
     try:
         fctx = repo[changeid][path]
     except error.RepoError:
         fctx = repo.filectx(path, fileid=changeid)
 
     return fctx
 
 def commonentry(repo, ctx):
     node = ctx.node()
     return {
         'rev': ctx.rev(),
         'node': hex(node),
         'author': ctx.user(),
         'desc': ctx.description(),
         'date': ctx.date(),
         'extra': ctx.extra(),
         'phase': ctx.phasestr(),
         'branch': nodebranchnodefault(ctx),
         'inbranch': nodeinbranch(repo, ctx),
         'branches': nodebranchdict(repo, ctx),
         'tags': nodetagsdict(repo, node),
         'bookmarks': nodebookmarksdict(repo, node),
         'parent': lambda **x: parents(ctx),
         'child': lambda **x: children(ctx),
     }
 
 def changelistentry(web, ctx, tmpl):
     '''Obtain a dictionary to be used for entries in a changelist.
 
     This function is called when producing items for the "entries" list passed
     to the "shortlog" and "changelog" templates.
     '''
     repo = web.repo
     rev = ctx.rev()
     n = ctx.node()
     showtags = showtag(repo, tmpl, 'changelogtag', n)
     files = listfilediffs(tmpl, ctx.files(), n, web.maxfiles)
 
     entry = commonentry(repo, ctx)
     entry.update(
         allparents=lambda **x: parents(ctx),
         parent=lambda **x: parents(ctx, rev - 1),
         child=lambda **x: children(ctx, rev + 1),
         changelogtag=showtags,
         files=files,
     )
     return entry
 
 def symrevorshortnode(req, ctx):
     if 'node' in req.form:
         return templatefilters.revescape(req.form['node'][0])
     else:
         return short(ctx.node())
 
 def changesetentry(web, req, tmpl, ctx):
     '''Obtain a dictionary to be used to render the "changeset" template.'''
 
     showtags = showtag(web.repo, tmpl, 'changesettag', ctx.node())
     showbookmarks = showbookmark(web.repo, tmpl, 'changesetbookmark',
                                  ctx.node())
     showbranch = nodebranchnodefault(ctx)
 
     files = []
     parity = paritygen(web.stripecount)
     for blockno, f in enumerate(ctx.files()):
         template = f in ctx and 'filenodelink' or 'filenolink'
         files.append(tmpl(template,
                           node=ctx.hex(), file=f, blockno=blockno + 1,
-                          parity=parity.next()))
+                          parity=next(parity)))
 
     basectx = basechangectx(web.repo, req)
     if basectx is None:
         basectx = ctx.p1()
 
     style = web.config('web', 'style', 'paper')
     if 'style' in req.form:
         style = req.form['style'][0]
 
     parity = paritygen(web.stripecount)
     diff = diffs(web.repo, tmpl, ctx, basectx, None, parity, style)
 
     parity = paritygen(web.stripecount)
     diffstatsgen = diffstatgen(ctx, basectx)
     diffstats = diffstat(tmpl, ctx, diffstatsgen, parity)
 
     return dict(
         diff=diff,
         symrev=symrevorshortnode(req, ctx),
         basenode=basectx.hex(),
         changesettag=showtags,
         changesetbookmark=showbookmarks,
         changesetbranch=showbranch,
         files=files,
         diffsummary=lambda **x: diffsummary(diffstatsgen),
         diffstat=diffstats,
         archives=web.archivelist(ctx.hex()),
         **commonentry(web.repo, ctx))
 
 def listfilediffs(tmpl, files, node, max):
     for f in files[:max]:
         yield tmpl('filedifflink', node=hex(node), file=f)
     if len(files) > max:
         yield tmpl('fileellipses')
 
 def diffs(repo, tmpl, ctx, basectx, files, parity, style):
 
     def countgen():
         start = 1
         while True:
             yield start
             start += 1
 
     blockcount = countgen()
     def prettyprintlines(diff, blockno):
         for lineno, l in enumerate(diff.splitlines(True)):
             difflineno = "%d.%d" % (blockno, lineno + 1)
             if l.startswith('+'):
                 ltype = "difflineplus"
             elif l.startswith('-'):
                 ltype = "difflineminus"
             elif l.startswith('@'):
                 ltype = "difflineat"
             else:
                 ltype = "diffline"
             yield tmpl(ltype,
                        line=l,
                        lineno=lineno + 1,
                        lineid="l%s" % difflineno,
                        linenumber="% 8s" % difflineno)
 
     if files:
         m = match.exact(repo.root, repo.getcwd(), files)
     else:
         m = match.always(repo.root, repo.getcwd())
 
     diffopts = patch.diffopts(repo.ui, untrusted=True)
     if basectx is None:
         parents = ctx.parents()
         if parents:
             node1 = parents[0].node()
         else:
             node1 = nullid
     else:
         node1 = basectx.node()
     node2 = ctx.node()
 
     block = []
     for chunk in patch.diff(repo, node1, node2, m, opts=diffopts):
         if chunk.startswith('diff') and block:
-            blockno = blockcount.next()
-            yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
+            blockno = next(blockcount)
+            yield tmpl('diffblock', parity=next(parity), blockno=blockno,
                        lines=prettyprintlines(''.join(block), blockno))
             block = []
         if chunk.startswith('diff') and style != 'raw':
             chunk = ''.join(chunk.splitlines(True)[1:])
         block.append(chunk)
-    blockno = blockcount.next()
-    yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
+    blockno = next(blockcount)
+    yield tmpl('diffblock', parity=next(parity), blockno=blockno,
                lines=prettyprintlines(''.join(block), blockno))
 
 def compare(tmpl, context, leftlines, rightlines):
     '''Generator function that provides side-by-side comparison data.'''
 
     def compline(type, leftlineno, leftline, rightlineno, rightline):
         lineid = leftlineno and ("l%s" % leftlineno) or ''
         lineid += rightlineno and ("r%s" % rightlineno) or ''
         return tmpl('comparisonline',
                     type=type,
                     lineid=lineid,
                     leftlineno=leftlineno,
                     leftlinenumber="% 6s" % (leftlineno or ''),
                     leftline=leftline or '',
                     rightlineno=rightlineno,
                     rightlinenumber="% 6s" % (rightlineno or ''),
                     rightline=rightline or '')
 
     def getblock(opcodes):
         for type, llo, lhi, rlo, rhi in opcodes:
             len1 = lhi - llo
             len2 = rhi - rlo
             count = min(len1, len2)
             for i in xrange(count):
                 yield compline(type=type,
                                leftlineno=llo + i + 1,
                                leftline=leftlines[llo + i],
                                rightlineno=rlo + i + 1,
                                rightline=rightlines[rlo + i])
             if len1 > len2:
                 for i in xrange(llo + count, lhi):
                     yield compline(type=type,
                                    leftlineno=i + 1,
                                    leftline=leftlines[i],
                                    rightlineno=None,
                                    rightline=None)
             elif len2 > len1:
                 for i in xrange(rlo + count, rhi):
                     yield compline(type=type,
                                    leftlineno=None,
                                    leftline=None,
                                    rightlineno=i + 1,
                                    rightline=rightlines[i])
 
     s = difflib.SequenceMatcher(None, leftlines, rightlines)
     if context < 0:
         yield tmpl('comparisonblock', lines=getblock(s.get_opcodes()))
     else:
         for oc in s.get_grouped_opcodes(n=context):
             yield tmpl('comparisonblock', lines=getblock(oc))
 
 def diffstatgen(ctx, basectx):
     '''Generator function that provides the diffstat data.'''
 
     stats = patch.diffstatdata(util.iterlines(ctx.diff(basectx)))
     maxname, maxtotal, addtotal, removetotal, binary = patch.diffstatsum(stats)
     while True:
         yield stats, maxname, maxtotal, addtotal, removetotal, binary
 
 def diffsummary(statgen):
     '''Return a short summary of the diff.'''
 
-    stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
+    stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     return _(' %d files changed, %d insertions(+), %d deletions(-)\n') % (
              len(stats), addtotal, removetotal)
 
 def diffstat(tmpl, ctx, statgen, parity):
     '''Return a diffstat template for each file in the diff.'''
 
-    stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
+    stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     files = ctx.files()
 
     def pct(i):
         if maxtotal == 0:
             return 0
         return (float(i) / maxtotal) * 100
 
     fileno = 0
     for filename, adds, removes, isbinary in stats:
         template = filename in files and 'diffstatlink' or 'diffstatnolink'
         total = adds + removes
         fileno += 1
         yield tmpl(template, node=ctx.hex(), file=filename, fileno=fileno,
                    total=total, addpct=pct(adds), removepct=pct(removes),
-                   parity=parity.next())
+                   parity=next(parity))
 
 class sessionvars(object):
     def __init__(self, vars, start='?'):
         self.start = start
         self.vars = vars
     def __getitem__(self, key):
         return self.vars[key]
     def __setitem__(self, key, value):
         self.vars[key] = value
     def __copy__(self):
         return sessionvars(copy.copy(self.vars), self.start)
     def __iter__(self):
         separator = self.start
         for key, value in sorted(self.vars.iteritems()):
             yield {'name': key, 'value': str(value), 'separator': separator}
             separator = '&'
 
 class wsgiui(uimod.ui):
     # default termwidth breaks under mod_wsgi
     def termwidth(self):
         return 80
 
 def getwebsubs(repo):
     websubtable = []
     websubdefs = repo.ui.configitems('websub')
     # we must maintain interhg backwards compatibility
     websubdefs += repo.ui.configitems('interhg')
     for key, pattern in websubdefs:
         # grab the delimiter from the character after the "s"
         unesc = pattern[1]
         delim = re.escape(unesc)
 
         # identify portions of the pattern, taking care to avoid escaped
         # delimiters. the replace format and flags are optional, but
         # delimiters are required.
         match = re.match(
             r'^s%s(.+)(?:(?<=\\\\)|(?<!\\))%s(.*)%s([ilmsux])*$'
             % (delim, delim, delim), pattern)
         if not match:
             repo.ui.warn(_("websub: invalid pattern for %s: %s\n")
                               % (key, pattern))
             continue
 
         # we need to unescape the delimiter for regexp and format
         delim_re = re.compile(r'(?<!\\)\\%s' % delim)
         regexp = delim_re.sub(unesc, match.group(1))
         format = delim_re.sub(unesc, match.group(2))
 
         # the pattern allows for 6 regexp flags, so set them if necessary
         flagin = match.group(3)
         flags = 0
         if flagin:
             for flag in flagin.upper():
                 flags |= re.__dict__[flag]
 
         try:
             regexp = re.compile(regexp, flags)
             websubtable.append((regexp, format))
         except re.error:
             repo.ui.warn(_("websub: invalid regexp for %s: %s\n")
                          % (key, regexp))
     return websubtable

mercurial/merge.py

@@ -1,1651 +1,1651 b''
 # merge.py - directory-level update/merge handling for Mercurial
 #
 # Copyright 2006, 2007 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.
 
 from __future__ import absolute_import
 
 import errno
 import os
 import shutil
 import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullhex,
     nullid,
     nullrev,
 )
 from . import (
     copies,
     destutil,
     error,
     filemerge,
     obsolete,
     scmutil,
     subrepo,
     util,
     worker,
 )
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 def _droponode(data):
     # used for compatibility for v1
     bits = data.split('\0')
     bits = bits[:-2] + bits[-1:]
     return '\0'.join(bits)
 
 class mergestate(object):
     '''track 3-way merge state of individual files
 
     The merge state is stored on disk when needed. Two files are used: one with
     an old format (version 1), and one with a new format (version 2). Version 2
     stores a superset of the data in version 1, including new kinds of records
     in the future. For more about the new format, see the documentation for
     `_readrecordsv2`.
 
     Each record can contain arbitrary content, and has an associated type. This
     `type` should be a letter. If `type` is uppercase, the record is mandatory:
     versions of Mercurial that don't support it should abort. If `type` is
     lowercase, the record can be safely ignored.
 
     Currently known records:
 
     L: the node of the "local" part of the merge (hexified version)
     O: the node of the "other" part of the merge (hexified version)
     F: a file to be merged entry
     C: a change/delete or delete/change conflict
     D: a file that the external merge driver will merge internally
        (experimental)
     m: the external merge driver defined for this merge plus its run state
        (experimental)
     f: a (filename, dictonary) tuple of optional values for a given file
     X: unsupported mandatory record type (used in tests)
     x: unsupported advisory record type (used in tests)
     l: the labels for the parts of the merge.
 
     Merge driver run states (experimental):
     u: driver-resolved files unmarked -- needs to be run next time we're about
        to resolve or commit
     m: driver-resolved files marked -- only needs to be run before commit
     s: success/skipped -- does not need to be run any more
 
     '''
     statepathv1 = 'merge/state'
     statepathv2 = 'merge/state2'
 
     @staticmethod
     def clean(repo, node=None, other=None, labels=None):
         """Initialize a brand new merge state, removing any existing state on
         disk."""
         ms = mergestate(repo)
         ms.reset(node, other, labels)
         return ms
 
     @staticmethod
     def read(repo):
         """Initialize the merge state, reading it from disk."""
         ms = mergestate(repo)
         ms._read()
         return ms
 
     def __init__(self, repo):
         """Initialize the merge state.
 
         Do not use this directly! Instead call read() or clean()."""
         self._repo = repo
         self._dirty = False
         self._labels = None
 
     def reset(self, node=None, other=None, labels=None):
         self._state = {}
         self._stateextras = {}
         self._local = None
         self._other = None
         self._labels = labels
         for var in ('localctx', 'otherctx'):
             if var in vars(self):
                 delattr(self, var)
         if node:
             self._local = node
             self._other = other
         self._readmergedriver = None
         if self.mergedriver:
             self._mdstate = 's'
         else:
             self._mdstate = 'u'
         shutil.rmtree(self._repo.join('merge'), True)
         self._results = {}
         self._dirty = False
 
     def _read(self):
         """Analyse each record content to restore a serialized state from disk
 
         This function process "record" entry produced by the de-serialization
         of on disk file.
         """
         self._state = {}
         self._stateextras = {}
         self._local = None
         self._other = None
         for var in ('localctx', 'otherctx'):
             if var in vars(self):
                 delattr(self, var)
         self._readmergedriver = None
         self._mdstate = 's'
         unsupported = set()
         records = self._readrecords()
         for rtype, record in records:
             if rtype == 'L':
                 self._local = bin(record)
             elif rtype == 'O':
                 self._other = bin(record)
             elif rtype == 'm':
                 bits = record.split('\0', 1)
                 mdstate = bits[1]
                 if len(mdstate) != 1 or mdstate not in 'ums':
                     # the merge driver should be idempotent, so just rerun it
                     mdstate = 'u'
 
                 self._readmergedriver = bits[0]
                 self._mdstate = mdstate
             elif rtype in 'FDC':
                 bits = record.split('\0')
                 self._state[bits[0]] = bits[1:]
             elif rtype == 'f':
                 filename, rawextras = record.split('\0', 1)
                 extraparts = rawextras.split('\0')
                 extras = {}
                 i = 0
                 while i < len(extraparts):
                     extras[extraparts[i]] = extraparts[i + 1]
                     i += 2
 
                 self._stateextras[filename] = extras
             elif rtype == 'l':
                 labels = record.split('\0', 2)
                 self._labels = [l for l in labels if len(l) > 0]
             elif not rtype.islower():
                 unsupported.add(rtype)
         self._results = {}
         self._dirty = False
 
         if unsupported:
             raise error.UnsupportedMergeRecords(unsupported)
 
     def _readrecords(self):
         """Read merge state from disk and return a list of record (TYPE, data)
 
         We read data from both v1 and v2 files and decide which one to use.
 
         V1 has been used by version prior to 2.9.1 and contains less data than
         v2. We read both versions and check if no data in v2 contradicts
         v1. If there is not contradiction we can safely assume that both v1
         and v2 were written at the same time and use the extract data in v2. If
         there is contradiction we ignore v2 content as we assume an old version
         of Mercurial has overwritten the mergestate file and left an old v2
         file around.
 
         returns list of record [(TYPE, data), ...]"""
         v1records = self._readrecordsv1()
         v2records = self._readrecordsv2()
         if self._v1v2match(v1records, v2records):
             return v2records
         else:
             # v1 file is newer than v2 file, use it
             # we have to infer the "other" changeset of the merge
             # we cannot do better than that with v1 of the format
             mctx = self._repo[None].parents()[-1]
             v1records.append(('O', mctx.hex()))
             # add place holder "other" file node information
             # nobody is using it yet so we do no need to fetch the data
             # if mctx was wrong `mctx[bits[-2]]` may fails.
             for idx, r in enumerate(v1records):
                 if r[0] == 'F':
                     bits = r[1].split('\0')
                     bits.insert(-2, '')
                     v1records[idx] = (r[0], '\0'.join(bits))
             return v1records
 
     def _v1v2match(self, v1records, v2records):
         oldv2 = set() # old format version of v2 record
         for rec in v2records:
             if rec[0] == 'L':
                 oldv2.add(rec)
             elif rec[0] == 'F':
                 # drop the onode data (not contained in v1)
                 oldv2.add(('F', _droponode(rec[1])))
         for rec in v1records:
             if rec not in oldv2:
                 return False
         else:
             return True
 
     def _readrecordsv1(self):
         """read on disk merge state for version 1 file
 
         returns list of record [(TYPE, data), ...]
 
         Note: the "F" data from this file are one entry short
               (no "other file node" entry)
         """
         records = []
         try:
             f = self._repo.vfs(self.statepathv1)
             for i, l in enumerate(f):
                 if i == 0:
                     records.append(('L', l[:-1]))
                 else:
                     records.append(('F', l[:-1]))
             f.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
         return records
 
     def _readrecordsv2(self):
         """read on disk merge state for version 2 file
 
         This format is a list of arbitrary records of the form:
 
           [type][length][content]
 
         `type` is a single character, `length` is a 4 byte integer, and
         `content` is an arbitrary byte sequence of length `length`.
 
         Mercurial versions prior to 3.7 have a bug where if there are
         unsupported mandatory merge records, attempting to clear out the merge
         state with hg update --clean or similar aborts. The 't' record type
         works around that by writing out what those versions treat as an
         advisory record, but later versions interpret as special: the first
         character is the 'real' record type and everything onwards is the data.
 
         Returns list of records [(TYPE, data), ...]."""
         records = []
         try:
             f = self._repo.vfs(self.statepathv2)
             data = f.read()
             off = 0
             end = len(data)
             while off < end:
                 rtype = data[off]
                 off += 1
                 length = _unpack('>I', data[off:(off + 4)])[0]
                 off += 4
                 record = data[off:(off + length)]
                 off += length
                 if rtype == 't':
                     rtype, record = record[0], record[1:]
                 records.append((rtype, record))
             f.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
         return records
 
     @util.propertycache
     def mergedriver(self):
         # protect against the following:
         # - A configures a malicious merge driver in their hgrc, then
         #   pauses the merge
         # - A edits their hgrc to remove references to the merge driver
         # - A gives a copy of their entire repo, including .hg, to B
         # - B inspects .hgrc and finds it to be clean
         # - B then continues the merge and the malicious merge driver
         #  gets invoked
         configmergedriver = self._repo.ui.config('experimental', 'mergedriver')
         if (self._readmergedriver is not None
             and self._readmergedriver != configmergedriver):
             raise error.ConfigError(
                 _("merge driver changed since merge started"),
                 hint=_("revert merge driver change or abort merge"))
 
         return configmergedriver
 
     @util.propertycache
     def localctx(self):
         if self._local is None:
             raise RuntimeError("localctx accessed but self._local isn't set")
         return self._repo[self._local]
 
     @util.propertycache
     def otherctx(self):
         if self._other is None:
             raise RuntimeError("otherctx accessed but self._other isn't set")
         return self._repo[self._other]
 
     def active(self):
         """Whether mergestate is active.
 
         Returns True if there appears to be mergestate. This is a rough proxy
         for "is a merge in progress."
         """
         # Check local variables before looking at filesystem for performance
         # reasons.
         return bool(self._local) or bool(self._state) or \
                self._repo.vfs.exists(self.statepathv1) or \
                self._repo.vfs.exists(self.statepathv2)
 
     def commit(self):
         """Write current state on disk (if necessary)"""
         if self._dirty:
             records = self._makerecords()
             self._writerecords(records)
             self._dirty = False
 
     def _makerecords(self):
         records = []
         records.append(('L', hex(self._local)))
         records.append(('O', hex(self._other)))
         if self.mergedriver:
             records.append(('m', '\0'.join([
                 self.mergedriver, self._mdstate])))
         for d, v in self._state.iteritems():
             if v[0] == 'd':
                 records.append(('D', '\0'.join([d] + v)))
             # v[1] == local ('cd'), v[6] == other ('dc') -- not supported by
             # older versions of Mercurial
             elif v[1] == nullhex or v[6] == nullhex:
                 records.append(('C', '\0'.join([d] + v)))
             else:
                 records.append(('F', '\0'.join([d] + v)))
         for filename, extras in sorted(self._stateextras.iteritems()):
             rawextras = '\0'.join('%s\0%s' % (k, v) for k, v in
                                   extras.iteritems())
             records.append(('f', '%s\0%s' % (filename, rawextras)))
         if self._labels is not None:
             labels = '\0'.join(self._labels)
             records.append(('l', labels))
         return records
 
     def _writerecords(self, records):
         """Write current state on disk (both v1 and v2)"""
         self._writerecordsv1(records)
         self._writerecordsv2(records)
 
     def _writerecordsv1(self, records):
         """Write current state on disk in a version 1 file"""
         f = self._repo.vfs(self.statepathv1, 'w')
         irecords = iter(records)
-        lrecords = irecords.next()
+        lrecords = next(irecords)
         assert lrecords[0] == 'L'
         f.write(hex(self._local) + '\n')
         for rtype, data in irecords:
             if rtype == 'F':
                 f.write('%s\n' % _droponode(data))
         f.close()
 
     def _writerecordsv2(self, records):
         """Write current state on disk in a version 2 file
 
         See the docstring for _readrecordsv2 for why we use 't'."""
         # these are the records that all version 2 clients can read
         whitelist = 'LOF'
         f = self._repo.vfs(self.statepathv2, 'w')
         for key, data in records:
             assert len(key) == 1
             if key not in whitelist:
                 key, data = 't', '%s%s' % (key, data)
             format = '>sI%is' % len(data)
             f.write(_pack(format, key, len(data), data))
         f.close()
 
     def add(self, fcl, fco, fca, fd):
         """add a new (potentially?) conflicting file the merge state
         fcl: file context for local,
         fco: file context for remote,
         fca: file context for ancestors,
         fd:  file path of the resulting merge.
 
         note: also write the local version to the `.hg/merge` directory.
         """
         if fcl.isabsent():
             hash = nullhex
         else:
             hash = util.sha1(fcl.path()).hexdigest()
             self._repo.vfs.write('merge/' + hash, fcl.data())
         self._state[fd] = ['u', hash, fcl.path(),
                            fca.path(), hex(fca.filenode()),
                            fco.path(), hex(fco.filenode()),
                            fcl.flags()]
         self._stateextras[fd] = { 'ancestorlinknode' : hex(fca.node()) }
         self._dirty = True
 
     def __contains__(self, dfile):
         return dfile in self._state
 
     def __getitem__(self, dfile):
         return self._state[dfile][0]
 
     def __iter__(self):
         return iter(sorted(self._state))
 
     def files(self):
         return self._state.keys()
 
     def mark(self, dfile, state):
         self._state[dfile][0] = state
         self._dirty = True
 
     def mdstate(self):
         return self._mdstate
 
     def unresolved(self):
         """Obtain the paths of unresolved files."""
 
         for f, entry in self._state.items():
             if entry[0] == 'u':
                 yield f
 
     def driverresolved(self):
         """Obtain the paths of driver-resolved files."""
 
         for f, entry in self._state.items():
             if entry[0] == 'd':
                 yield f
 
     def extras(self, filename):
         return self._stateextras.setdefault(filename, {})
 
     def _resolve(self, preresolve, dfile, wctx):
         """rerun merge process for file path `dfile`"""
         if self[dfile] in 'rd':
             return True, 0
         stateentry = self._state[dfile]
         state, hash, lfile, afile, anode, ofile, onode, flags = stateentry
         octx = self._repo[self._other]
         extras = self.extras(dfile)
         anccommitnode = extras.get('ancestorlinknode')
         if anccommitnode:
             actx = self._repo[anccommitnode]
         else:
             actx = None
         fcd = self._filectxorabsent(hash, wctx, dfile)
         fco = self._filectxorabsent(onode, octx, ofile)
         # TODO: move this to filectxorabsent
         fca = self._repo.filectx(afile, fileid=anode, changeid=actx)
         # "premerge" x flags
         flo = fco.flags()
         fla = fca.flags()
         if 'x' in flags + flo + fla and 'l' not in flags + flo + fla:
             if fca.node() == nullid:
                 if preresolve:
                     self._repo.ui.warn(
                         _('warning: cannot merge flags for %s\n') % afile)
             elif flags == fla:
                 flags = flo
         if preresolve:
             # restore local
             if hash != nullhex:
                 f = self._repo.vfs('merge/' + hash)
                 self._repo.wwrite(dfile, f.read(), flags)
                 f.close()
             else:
                 self._repo.wvfs.unlinkpath(dfile, ignoremissing=True)
             complete, r, deleted = filemerge.premerge(self._repo, self._local,
                                                       lfile, fcd, fco, fca,
                                                       labels=self._labels)
         else:
             complete, r, deleted = filemerge.filemerge(self._repo, self._local,
                                                        lfile, fcd, fco, fca,
                                                        labels=self._labels)
         if r is None:
             # no real conflict
             del self._state[dfile]
             self._stateextras.pop(dfile, None)
             self._dirty = True
         elif not r:
             self.mark(dfile, 'r')
 
         if complete:
             action = None
             if deleted:
                 if fcd.isabsent():
                     # dc: local picked. Need to drop if present, which may
                     # happen on re-resolves.
                     action = 'f'
                 else:
                     # cd: remote picked (or otherwise deleted)
                     action = 'r'
             else:
                 if fcd.isabsent(): # dc: remote picked
                     action = 'g'
                 elif fco.isabsent(): # cd: local picked
                     if dfile in self.localctx:
                         action = 'am'
                     else:
                         action = 'a'
                 # else: regular merges (no action necessary)
             self._results[dfile] = r, action
 
         return complete, r
 
     def _filectxorabsent(self, hexnode, ctx, f):
         if hexnode == nullhex:
             return filemerge.absentfilectx(ctx, f)
         else:
             return ctx[f]
 
     def preresolve(self, dfile, wctx):
         """run premerge process for dfile
 
         Returns whether the merge is complete, and the exit code."""
         return self._resolve(True, dfile, wctx)
 
     def resolve(self, dfile, wctx):
         """run merge process (assuming premerge was run) for dfile
 
         Returns the exit code of the merge."""
         return self._resolve(False, dfile, wctx)[1]
 
     def counts(self):
         """return counts for updated, merged and removed files in this
         session"""
         updated, merged, removed = 0, 0, 0
         for r, action in self._results.itervalues():
             if r is None:
                 updated += 1
             elif r == 0:
                 if action == 'r':
                     removed += 1
                 else:
                     merged += 1
         return updated, merged, removed
 
     def unresolvedcount(self):
         """get unresolved count for this merge (persistent)"""
         return len([True for f, entry in self._state.iteritems()
                     if entry[0] == 'u'])
 
     def actions(self):
         """return lists of actions to perform on the dirstate"""
         actions = {'r': [], 'f': [], 'a': [], 'am': [], 'g': []}
         for f, (r, action) in self._results.iteritems():
             if action is not None:
                 actions[action].append((f, None, "merge result"))
         return actions
 
     def recordactions(self):
         """record remove/add/get actions in the dirstate"""
         branchmerge = self._repo.dirstate.p2() != nullid
         recordupdates(self._repo, self.actions(), branchmerge)
 
     def queueremove(self, f):
         """queues a file to be removed from the dirstate
 
         Meant for use by custom merge drivers."""
         self._results[f] = 0, 'r'
 
     def queueadd(self, f):
         """queues a file to be added to the dirstate
 
         Meant for use by custom merge drivers."""
         self._results[f] = 0, 'a'
 
     def queueget(self, f):
         """queues a file to be marked modified in the dirstate
 
         Meant for use by custom merge drivers."""
         self._results[f] = 0, 'g'
 
 def _getcheckunknownconfig(repo, section, name):
     config = repo.ui.config(section, name, default='abort')
     valid = ['abort', 'ignore', 'warn']
     if config not in valid:
         validstr = ', '.join(["'" + v + "'" for v in valid])
         raise error.ConfigError(_("%s.%s not valid "
                                   "('%s' is none of %s)")
                                 % (section, name, config, validstr))
     return config
 
 def _checkunknownfile(repo, wctx, mctx, f, f2=None):
     if f2 is None:
         f2 = f
     return (repo.wvfs.audit.check(f)
         and repo.wvfs.isfileorlink(f)
         and repo.dirstate.normalize(f) not in repo.dirstate
         and mctx[f2].cmp(wctx[f]))
 
 def _checkunknownfiles(repo, wctx, mctx, force, actions, mergeforce):
     """
     Considers any actions that care about the presence of conflicting unknown
     files. For some actions, the result is to abort; for others, it is to
     choose a different action.
     """
     conflicts = set()
     warnconflicts = set()
     abortconflicts = set()
     unknownconfig = _getcheckunknownconfig(repo, 'merge', 'checkunknown')
     ignoredconfig = _getcheckunknownconfig(repo, 'merge', 'checkignored')
     if not force:
         def collectconflicts(conflicts, config):
             if config == 'abort':
                 abortconflicts.update(conflicts)
             elif config == 'warn':
                 warnconflicts.update(conflicts)
 
         for f, (m, args, msg) in actions.iteritems():
             if m in ('c', 'dc'):
                 if _checkunknownfile(repo, wctx, mctx, f):
                     conflicts.add(f)
             elif m == 'dg':
                 if _checkunknownfile(repo, wctx, mctx, f, args[0]):
                     conflicts.add(f)
 
         ignoredconflicts = set([c for c in conflicts
                                 if repo.dirstate._ignore(c)])
         unknownconflicts = conflicts - ignoredconflicts
         collectconflicts(ignoredconflicts, ignoredconfig)
         collectconflicts(unknownconflicts, unknownconfig)
     else:
         for f, (m, args, msg) in actions.iteritems():
             if m == 'cm':
                 fl2, anc = args
                 different = _checkunknownfile(repo, wctx, mctx, f)
                 if repo.dirstate._ignore(f):
                     config = ignoredconfig
                 else:
                     config = unknownconfig
 
                 # The behavior when force is True is described by this table:
                 #  config  different  mergeforce  |    action    backup
                 #    *         n          *       |      get        n
                 #    *         y          y       |     merge       -
                 #   abort      y          n       |     merge       -   (1)
                 #   warn       y          n       |  warn + get     y
                 #  ignore      y          n       |      get        y
                 #
                 # (1) this is probably the wrong behavior here -- we should
                 #     probably abort, but some actions like rebases currently
                 #     don't like an abort happening in the middle of
                 #     merge.update.
                 if not different:
                     actions[f] = ('g', (fl2, False), "remote created")
                 elif mergeforce or config == 'abort':
                     actions[f] = ('m', (f, f, None, False, anc),
                                   "remote differs from untracked local")
                 elif config == 'abort':
                     abortconflicts.add(f)
                 else:
                     if config == 'warn':
                         warnconflicts.add(f)
                     actions[f] = ('g', (fl2, True), "remote created")
 
     for f in sorted(abortconflicts):
         repo.ui.warn(_("%s: untracked file differs\n") % f)
     if abortconflicts:
         raise error.Abort(_("untracked files in working directory "
                             "differ from files in requested revision"))
 
     for f in sorted(warnconflicts):
         repo.ui.warn(_("%s: replacing untracked file\n") % f)
 
     for f, (m, args, msg) in actions.iteritems():
         backup = f in conflicts
         if m == 'c':
             flags, = args
             actions[f] = ('g', (flags, backup), msg)
 
 def _forgetremoved(wctx, mctx, branchmerge):
     """
     Forget removed files
 
     If we're jumping between revisions (as opposed to merging), and if
     neither the working directory nor the target rev has the file,
     then we need to remove it from the dirstate, to prevent the
     dirstate from listing the file when it is no longer in the
     manifest.
 
     If we're merging, and the other revision has removed a file
     that is not present in the working directory, we need to mark it
     as removed.
     """
 
     actions = {}
     m = 'f'
     if branchmerge:
         m = 'r'
     for f in wctx.deleted():
         if f not in mctx:
             actions[f] = m, None, "forget deleted"
 
     if not branchmerge:
         for f in wctx.removed():
             if f not in mctx:
                 actions[f] = 'f', None, "forget removed"
 
     return actions
 
 def _checkcollision(repo, wmf, actions):
     # build provisional merged manifest up
     pmmf = set(wmf)
 
     if actions:
         # k, dr, e and rd are no-op
         for m in 'a', 'am', 'f', 'g', 'cd', 'dc':
             for f, args, msg in actions[m]:
                 pmmf.add(f)
         for f, args, msg in actions['r']:
             pmmf.discard(f)
         for f, args, msg in actions['dm']:
             f2, flags = args
             pmmf.discard(f2)
             pmmf.add(f)
         for f, args, msg in actions['dg']:
             pmmf.add(f)
         for f, args, msg in actions['m']:
             f1, f2, fa, move, anc = args
             if move:
                 pmmf.discard(f1)
             pmmf.add(f)
 
     # check case-folding collision in provisional merged manifest
     foldmap = {}
     for f in sorted(pmmf):
         fold = util.normcase(f)
         if fold in foldmap:
             raise error.Abort(_("case-folding collision between %s and %s")
                              % (f, foldmap[fold]))
         foldmap[fold] = f
 
     # check case-folding of directories
     foldprefix = unfoldprefix = lastfull = ''
     for fold, f in sorted(foldmap.items()):
         if fold.startswith(foldprefix) and not f.startswith(unfoldprefix):
             # the folded prefix matches but actual casing is different
             raise error.Abort(_("case-folding collision between "
                                 "%s and directory of %s") % (lastfull, f))
         foldprefix = fold + '/'
         unfoldprefix = f + '/'
         lastfull = f
 
 def driverpreprocess(repo, ms, wctx, labels=None):
     """run the preprocess step of the merge driver, if any
 
     This is currently not implemented -- it's an extension point."""
     return True
 
 def driverconclude(repo, ms, wctx, labels=None):
     """run the conclude step of the merge driver, if any
 
     This is currently not implemented -- it's an extension point."""
     return True
 
 def manifestmerge(repo, wctx, p2, pa, branchmerge, force, matcher,
                   acceptremote, followcopies):
     """
     Merge p1 and p2 with ancestor pa and generate merge action list
 
     branchmerge and force are as passed in to update
     matcher = matcher to filter file lists
     acceptremote = accept the incoming changes without prompting
     """
     if matcher is not None and matcher.always():
         matcher = None
 
     copy, movewithdir, diverge, renamedelete = {}, {}, {}, {}
 
     # manifests fetched in order are going to be faster, so prime the caches
     [x.manifest() for x in
      sorted(wctx.parents() + [p2, pa], key=lambda x: x.rev())]
 
     if followcopies:
         ret = copies.mergecopies(repo, wctx, p2, pa)
         copy, movewithdir, diverge, renamedelete = ret
 
     repo.ui.note(_("resolving manifests\n"))
     repo.ui.debug(" branchmerge: %s, force: %s, partial: %s\n"
                   % (bool(branchmerge), bool(force), bool(matcher)))
     repo.ui.debug(" ancestor: %s, local: %s, remote: %s\n" % (pa, wctx, p2))
 
     m1, m2, ma = wctx.manifest(), p2.manifest(), pa.manifest()
     copied = set(copy.values())
     copied.update(movewithdir.values())
 
     if '.hgsubstate' in m1:
         # check whether sub state is modified
         if any(wctx.sub(s).dirty() for s in wctx.substate):
             m1['.hgsubstate'] += '+'
 
     # Compare manifests
     if matcher is not None:
         m1 = m1.matches(matcher)
         m2 = m2.matches(matcher)
     diff = m1.diff(m2)
 
     actions = {}
     for f, ((n1, fl1), (n2, fl2)) in diff.iteritems():
         if n1 and n2: # file exists on both local and remote side
             if f not in ma:
                 fa = copy.get(f, None)
                 if fa is not None:
                     actions[f] = ('m', (f, f, fa, False, pa.node()),
                                   "both renamed from " + fa)
                 else:
                     actions[f] = ('m', (f, f, None, False, pa.node()),
                                   "both created")
             else:
                 a = ma[f]
                 fla = ma.flags(f)
                 nol = 'l' not in fl1 + fl2 + fla
                 if n2 == a and fl2 == fla:
                     actions[f] = ('k' , (), "remote unchanged")
                 elif n1 == a and fl1 == fla: # local unchanged - use remote
                     if n1 == n2: # optimization: keep local content
                         actions[f] = ('e', (fl2,), "update permissions")
                     else:
                         actions[f] = ('g', (fl2, False), "remote is newer")
                 elif nol and n2 == a: # remote only changed 'x'
                     actions[f] = ('e', (fl2,), "update permissions")
                 elif nol and n1 == a: # local only changed 'x'
                     actions[f] = ('g', (fl1, False), "remote is newer")
                 else: # both changed something
                     actions[f] = ('m', (f, f, f, False, pa.node()),
                                    "versions differ")
         elif n1: # file exists only on local side
             if f in copied:
                 pass # we'll deal with it on m2 side
             elif f in movewithdir: # directory rename, move local
                 f2 = movewithdir[f]
                 if f2 in m2:
                     actions[f2] = ('m', (f, f2, None, True, pa.node()),
                                    "remote directory rename, both created")
                 else:
                     actions[f2] = ('dm', (f, fl1),
                                    "remote directory rename - move from " + f)
             elif f in copy:
                 f2 = copy[f]
                 actions[f] = ('m', (f, f2, f2, False, pa.node()),
                               "local copied/moved from " + f2)
             elif f in ma: # clean, a different, no remote
                 if n1 != ma[f]:
                     if acceptremote:
                         actions[f] = ('r', None, "remote delete")
                     else:
                         actions[f] = ('cd', (f, None, f, False, pa.node()),
                                       "prompt changed/deleted")
                 elif n1[20:] == 'a':
                     # This extra 'a' is added by working copy manifest to mark
                     # the file as locally added. We should forget it instead of
                     # deleting it.
                     actions[f] = ('f', None, "remote deleted")
                 else:
                     actions[f] = ('r', None, "other deleted")
         elif n2: # file exists only on remote side
             if f in copied:
                 pass # we'll deal with it on m1 side
             elif f in movewithdir:
                 f2 = movewithdir[f]
                 if f2 in m1:
                     actions[f2] = ('m', (f2, f, None, False, pa.node()),
                                    "local directory rename, both created")
                 else:
                     actions[f2] = ('dg', (f, fl2),
                                    "local directory rename - get from " + f)
             elif f in copy:
                 f2 = copy[f]
                 if f2 in m2:
                     actions[f] = ('m', (f2, f, f2, False, pa.node()),
                                   "remote copied from " + f2)
                 else:
                     actions[f] = ('m', (f2, f, f2, True, pa.node()),
                                   "remote moved from " + f2)
             elif f not in ma:
                 # local unknown, remote created: the logic is described by the
                 # following table:
                 #
                 # force  branchmerge  different  |  action
                 #   n         *           *      |   create
                 #   y         n           *      |   create
                 #   y         y           n      |   create
                 #   y         y           y      |   merge
                 #
                 # Checking whether the files are different is expensive, so we
                 # don't do that when we can avoid it.
                 if not force:
                     actions[f] = ('c', (fl2,), "remote created")
                 elif not branchmerge:
                     actions[f] = ('c', (fl2,), "remote created")
                 else:
                     actions[f] = ('cm', (fl2, pa.node()),
                                   "remote created, get or merge")
             elif n2 != ma[f]:
                 if acceptremote:
                     actions[f] = ('c', (fl2,), "remote recreating")
                 else:
                     actions[f] = ('dc', (None, f, f, False, pa.node()),
                                   "prompt deleted/changed")
 
     return actions, diverge, renamedelete
 
 def _resolvetrivial(repo, wctx, mctx, ancestor, actions):
     """Resolves false conflicts where the nodeid changed but the content
        remained the same."""
 
     for f, (m, args, msg) in actions.items():
         if m == 'cd' and f in ancestor and not wctx[f].cmp(ancestor[f]):
             # local did change but ended up with same content
             actions[f] = 'r', None, "prompt same"
         elif m == 'dc' and f in ancestor and not mctx[f].cmp(ancestor[f]):
             # remote did change but ended up with same content
             del actions[f] # don't get = keep local deleted
 
 def calculateupdates(repo, wctx, mctx, ancestors, branchmerge, force,
                      acceptremote, followcopies, matcher=None,
                      mergeforce=False):
     "Calculate the actions needed to merge mctx into wctx using ancestors"
     if len(ancestors) == 1: # default
         actions, diverge, renamedelete = manifestmerge(
             repo, wctx, mctx, ancestors[0], branchmerge, force, matcher,
             acceptremote, followcopies)
         _checkunknownfiles(repo, wctx, mctx, force, actions, mergeforce)
 
     else: # only when merge.preferancestor=* - the default
         repo.ui.note(
             _("note: merging %s and %s using bids from ancestors %s\n") %
             (wctx, mctx, _(' and ').join(str(anc) for anc in ancestors)))
 
         # Call for bids
         fbids = {} # mapping filename to bids (action method to list af actions)
         diverge, renamedelete = None, None
         for ancestor in ancestors:
             repo.ui.note(_('\ncalculating bids for ancestor %s\n') % ancestor)
             actions, diverge1, renamedelete1 = manifestmerge(
                 repo, wctx, mctx, ancestor, branchmerge, force, matcher,
                 acceptremote, followcopies)
             _checkunknownfiles(repo, wctx, mctx, force, actions, mergeforce)
 
             # Track the shortest set of warning on the theory that bid
             # merge will correctly incorporate more information
             if diverge is None or len(diverge1) < len(diverge):
                 diverge = diverge1
             if renamedelete is None or len(renamedelete) < len(renamedelete1):
                 renamedelete = renamedelete1
 
             for f, a in sorted(actions.iteritems()):
                 m, args, msg = a
                 repo.ui.debug(' %s: %s -> %s\n' % (f, msg, m))
                 if f in fbids:
                     d = fbids[f]
                     if m in d:
                         d[m].append(a)
                     else:
                         d[m] = [a]
                 else:
                     fbids[f] = {m: [a]}
 
         # Pick the best bid for each file
         repo.ui.note(_('\nauction for merging merge bids\n'))
         actions = {}
         for f, bids in sorted(fbids.items()):
             # bids is a mapping from action method to list af actions
             # Consensus?
             if len(bids) == 1: # all bids are the same kind of method
                 m, l = bids.items()[0]
                 if all(a == l[0] for a in l[1:]): # len(bids) is > 1
                     repo.ui.note(" %s: consensus for %s\n" % (f, m))
                     actions[f] = l[0]
                     continue
             # If keep is an option, just do it.
             if 'k' in bids:
                 repo.ui.note(" %s: picking 'keep' action\n" % f)
                 actions[f] = bids['k'][0]
                 continue
             # If there are gets and they all agree [how could they not?], do it.
             if 'g' in bids:
                 ga0 = bids['g'][0]
                 if all(a == ga0 for a in bids['g'][1:]):
                     repo.ui.note(" %s: picking 'get' action\n" % f)
                     actions[f] = ga0
                     continue
             # TODO: Consider other simple actions such as mode changes
             # Handle inefficient democrazy.
             repo.ui.note(_(' %s: multiple bids for merge action:\n') % f)
             for m, l in sorted(bids.items()):
                 for _f, args, msg in l:
                     repo.ui.note('  %s -> %s\n' % (msg, m))
             # Pick random action. TODO: Instead, prompt user when resolving
             m, l = bids.items()[0]
             repo.ui.warn(_(' %s: ambiguous merge - picked %s action\n') %
                          (f, m))
             actions[f] = l[0]
             continue
         repo.ui.note(_('end of auction\n\n'))
 
     _resolvetrivial(repo, wctx, mctx, ancestors[0], actions)
 
     if wctx.rev() is None:
         fractions = _forgetremoved(wctx, mctx, branchmerge)
         actions.update(fractions)
 
     return actions, diverge, renamedelete
 
 def batchremove(repo, actions):
     """apply removes to the working directory
 
     yields tuples for progress updates
     """
     verbose = repo.ui.verbose
     unlink = util.unlinkpath
     wjoin = repo.wjoin
     audit = repo.wvfs.audit
     i = 0
     for f, args, msg in actions:
         repo.ui.debug(" %s: %s -> r\n" % (f, msg))
         if verbose:
             repo.ui.note(_("removing %s\n") % f)
         audit(f)
         try:
             unlink(wjoin(f), ignoremissing=True)
         except OSError as inst:
             repo.ui.warn(_("update failed to remove %s: %s!\n") %
                          (f, inst.strerror))
         if i == 100:
             yield i, f
             i = 0
         i += 1
     if i > 0:
         yield i, f
 
 def batchget(repo, mctx, actions):
     """apply gets to the working directory
 
     mctx is the context to get from
 
     yields tuples for progress updates
     """
     verbose = repo.ui.verbose
     fctx = mctx.filectx
     wwrite = repo.wwrite
     ui = repo.ui
     i = 0
     with repo.wvfs.backgroundclosing(ui, expectedcount=len(actions)):
         for f, (flags, backup), msg in actions:
             repo.ui.debug(" %s: %s -> g\n" % (f, msg))
             if verbose:
                 repo.ui.note(_("getting %s\n") % f)
 
             if backup:
                 absf = repo.wjoin(f)
                 orig = scmutil.origpath(ui, repo, absf)
                 try:
                     # TODO Mercurial has always aborted if an untracked
                     # directory is replaced by a tracked file, or generally
                     # with file/directory merges. This needs to be sorted out.
                     if repo.wvfs.isfileorlink(f):
                         util.rename(absf, orig)
                 except OSError as e:
                     if e.errno != errno.ENOENT:
                         raise
 
             wwrite(f, fctx(f).data(), flags, backgroundclose=True)
             if i == 100:
                 yield i, f
                 i = 0
             i += 1
     if i > 0:
         yield i, f
 
 def applyupdates(repo, actions, wctx, mctx, overwrite, labels=None):
     """apply the merge action list to the working directory
 
     wctx is the working copy context
     mctx is the context to be merged into the working copy
 
     Return a tuple of counts (updated, merged, removed, unresolved) that
     describes how many files were affected by the update.
     """
 
     updated, merged, removed = 0, 0, 0
     ms = mergestate.clean(repo, wctx.p1().node(), mctx.node(), labels)
     moves = []
     for m, l in actions.items():
         l.sort()
 
     # 'cd' and 'dc' actions are treated like other merge conflicts
     mergeactions = sorted(actions['cd'])
     mergeactions.extend(sorted(actions['dc']))
     mergeactions.extend(actions['m'])
     for f, args, msg in mergeactions:
         f1, f2, fa, move, anc = args
         if f == '.hgsubstate': # merged internally
             continue
         if f1 is None:
             fcl = filemerge.absentfilectx(wctx, fa)
         else:
             repo.ui.debug(" preserving %s for resolve of %s\n" % (f1, f))
             fcl = wctx[f1]
         if f2 is None:
             fco = filemerge.absentfilectx(mctx, fa)
         else:
             fco = mctx[f2]
         actx = repo[anc]
         if fa in actx:
             fca = actx[fa]
         else:
             # TODO: move to absentfilectx
             fca = repo.filectx(f1, fileid=nullrev)
         ms.add(fcl, fco, fca, f)
         if f1 != f and move:
             moves.append(f1)
 
     audit = repo.wvfs.audit
     _updating = _('updating')
     _files = _('files')
     progress = repo.ui.progress
 
     # remove renamed files after safely stored
     for f in moves:
         if os.path.lexists(repo.wjoin(f)):
             repo.ui.debug("removing %s\n" % f)
             audit(f)
             util.unlinkpath(repo.wjoin(f))
 
     numupdates = sum(len(l) for m, l in actions.items() if m != 'k')
 
     if [a for a in actions['r'] if a[0] == '.hgsubstate']:
         subrepo.submerge(repo, wctx, mctx, wctx, overwrite)
 
     # remove in parallel (must come first)
     z = 0
     prog = worker.worker(repo.ui, 0.001, batchremove, (repo,), actions['r'])
     for i, item in prog:
         z += i
         progress(_updating, z, item=item, total=numupdates, unit=_files)
     removed = len(actions['r'])
 
     # get in parallel
     prog = worker.worker(repo.ui, 0.001, batchget, (repo, mctx), actions['g'])
     for i, item in prog:
         z += i
         progress(_updating, z, item=item, total=numupdates, unit=_files)
     updated = len(actions['g'])
 
     if [a for a in actions['g'] if a[0] == '.hgsubstate']:
         subrepo.submerge(repo, wctx, mctx, wctx, overwrite)
 
     # forget (manifest only, just log it) (must come first)
     for f, args, msg in actions['f']:
         repo.ui.debug(" %s: %s -> f\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
 
     # re-add (manifest only, just log it)
     for f, args, msg in actions['a']:
         repo.ui.debug(" %s: %s -> a\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
 
     # re-add/mark as modified (manifest only, just log it)
     for f, args, msg in actions['am']:
         repo.ui.debug(" %s: %s -> am\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
 
     # keep (noop, just log it)
     for f, args, msg in actions['k']:
         repo.ui.debug(" %s: %s -> k\n" % (f, msg))
         # no progress
 
     # directory rename, move local
     for f, args, msg in actions['dm']:
         repo.ui.debug(" %s: %s -> dm\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         f0, flags = args
         repo.ui.note(_("moving %s to %s\n") % (f0, f))
         audit(f)
         repo.wwrite(f, wctx.filectx(f0).data(), flags)
         util.unlinkpath(repo.wjoin(f0))
         updated += 1
 
     # local directory rename, get
     for f, args, msg in actions['dg']:
         repo.ui.debug(" %s: %s -> dg\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         f0, flags = args
         repo.ui.note(_("getting %s to %s\n") % (f0, f))
         repo.wwrite(f, mctx.filectx(f0).data(), flags)
         updated += 1
 
     # exec
     for f, args, msg in actions['e']:
         repo.ui.debug(" %s: %s -> e\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         flags, = args
         audit(f)
         util.setflags(repo.wjoin(f), 'l' in flags, 'x' in flags)
         updated += 1
 
     # the ordering is important here -- ms.mergedriver will raise if the merge
     # driver has changed, and we want to be able to bypass it when overwrite is
     # True
     usemergedriver = not overwrite and mergeactions and ms.mergedriver
 
     if usemergedriver:
         ms.commit()
         proceed = driverpreprocess(repo, ms, wctx, labels=labels)
         # the driver might leave some files unresolved
         unresolvedf = set(ms.unresolved())
         if not proceed:
             # XXX setting unresolved to at least 1 is a hack to make sure we
             # error out
             return updated, merged, removed, max(len(unresolvedf), 1)
         newactions = []
         for f, args, msg in mergeactions:
             if f in unresolvedf:
                 newactions.append((f, args, msg))
         mergeactions = newactions
 
     # premerge
     tocomplete = []
     for f, args, msg in mergeactions:
         repo.ui.debug(" %s: %s -> m (premerge)\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         if f == '.hgsubstate': # subrepo states need updating
             subrepo.submerge(repo, wctx, mctx, wctx.ancestor(mctx),
                              overwrite)
             continue
         audit(f)
         complete, r = ms.preresolve(f, wctx)
         if not complete:
             numupdates += 1
             tocomplete.append((f, args, msg))
 
     # merge
     for f, args, msg in tocomplete:
         repo.ui.debug(" %s: %s -> m (merge)\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         ms.resolve(f, wctx)
 
     ms.commit()
 
     unresolved = ms.unresolvedcount()
 
     if usemergedriver and not unresolved and ms.mdstate() != 's':
         if not driverconclude(repo, ms, wctx, labels=labels):
             # XXX setting unresolved to at least 1 is a hack to make sure we
             # error out
             unresolved = max(unresolved, 1)
 
         ms.commit()
 
     msupdated, msmerged, msremoved = ms.counts()
     updated += msupdated
     merged += msmerged
     removed += msremoved
 
     extraactions = ms.actions()
     for k, acts in extraactions.iteritems():
         actions[k].extend(acts)
 
     progress(_updating, None, total=numupdates, unit=_files)
 
     return updated, merged, removed, unresolved
 
 def recordupdates(repo, actions, branchmerge):
     "record merge actions to the dirstate"
     # remove (must come first)
     for f, args, msg in actions.get('r', []):
         if branchmerge:
             repo.dirstate.remove(f)
         else:
             repo.dirstate.drop(f)
 
     # forget (must come first)
     for f, args, msg in actions.get('f', []):
         repo.dirstate.drop(f)
 
     # re-add
     for f, args, msg in actions.get('a', []):
         repo.dirstate.add(f)
 
     # re-add/mark as modified
     for f, args, msg in actions.get('am', []):
         if branchmerge:
             repo.dirstate.normallookup(f)
         else:
             repo.dirstate.add(f)
 
     # exec change
     for f, args, msg in actions.get('e', []):
         repo.dirstate.normallookup(f)
 
     # keep
     for f, args, msg in actions.get('k', []):
         pass
 
     # get
     for f, args, msg in actions.get('g', []):
         if branchmerge:
             repo.dirstate.otherparent(f)
         else:
             repo.dirstate.normal(f)
 
     # merge
     for f, args, msg in actions.get('m', []):
         f1, f2, fa, move, anc = args
         if branchmerge:
             # We've done a branch merge, mark this file as merged
             # so that we properly record the merger later
             repo.dirstate.merge(f)
             if f1 != f2: # copy/rename
                 if move:
                     repo.dirstate.remove(f1)
                 if f1 != f:
                     repo.dirstate.copy(f1, f)
                 else:
                     repo.dirstate.copy(f2, f)
         else:
             # We've update-merged a locally modified file, so
             # we set the dirstate to emulate a normal checkout
             # of that file some time in the past. Thus our
             # merge will appear as a normal local file
             # modification.
             if f2 == f: # file not locally copied/moved
                 repo.dirstate.normallookup(f)
             if move:
                 repo.dirstate.drop(f1)
 
     # directory rename, move local
     for f, args, msg in actions.get('dm', []):
         f0, flag = args
         if branchmerge:
             repo.dirstate.add(f)
             repo.dirstate.remove(f0)
             repo.dirstate.copy(f0, f)
         else:
             repo.dirstate.normal(f)
             repo.dirstate.drop(f0)
 
     # directory rename, get
     for f, args, msg in actions.get('dg', []):
         f0, flag = args
         if branchmerge:
             repo.dirstate.add(f)
             repo.dirstate.copy(f0, f)
         else:
             repo.dirstate.normal(f)
 
 def update(repo, node, branchmerge, force, ancestor=None,
            mergeancestor=False, labels=None, matcher=None, mergeforce=False):
     """
     Perform a merge between the working directory and the given node
 
     node = the node to update to, or None if unspecified
     branchmerge = whether to merge between branches
     force = whether to force branch merging or file overwriting
     matcher = a matcher to filter file lists (dirstate not updated)
     mergeancestor = whether it is merging with an ancestor. If true,
       we should accept the incoming changes for any prompts that occur.
       If false, merging with an ancestor (fast-forward) is only allowed
       between different named branches. This flag is used by rebase extension
       as a temporary fix and should be avoided in general.
     labels = labels to use for base, local and other
     mergeforce = whether the merge was run with 'merge --force' (deprecated): if
       this is True, then 'force' should be True as well.
 
     The table below shows all the behaviors of the update command
     given the -c and -C or no options, whether the working directory
     is dirty, whether a revision is specified, and the relationship of
     the parent rev to the target rev (linear, on the same named
     branch, or on another named branch).
 
     This logic is tested by test-update-branches.t.
 
     -c  -C  dirty  rev  |  linear      same    cross
      n   n    n     n   |    ok        (1)       x
      n   n    n     y   |    ok        ok       ok
      n   n    y     n   |   merge      (2)      (2)
      n   n    y     y   |   merge      (3)      (3)
      n   y    *     *   |   discard   discard   discard
      y   n    y     *   |    (4)       (4)      (4)
      y   n    n     *   |    ok        ok       ok
      y   y    *     *   |    (5)       (5)      (5)
 
     x = can't happen
     * = don't-care
     1 = abort: not a linear update (merge or update --check to force update)
     2 = abort: uncommitted changes (commit and merge, or update --clean to
                  discard changes)
     3 = abort: uncommitted changes (commit or update --clean to discard changes)
     4 = abort: uncommitted changes (checked in commands.py)
     5 = incompatible options (checked in commands.py)
 
     Return the same tuple as applyupdates().
     """
 
     onode = node
     # If we're doing a partial update, we need to skip updating
     # the dirstate, so make a note of any partial-ness to the
     # update here.
     if matcher is None or matcher.always():
         partial = False
     else:
         partial = True
     with repo.wlock():
         wc = repo[None]
         pl = wc.parents()
         p1 = pl[0]
         pas = [None]
         if ancestor is not None:
             pas = [repo[ancestor]]
 
         if node is None:
             repo.ui.deprecwarn('update with no target', '3.9')
             rev, _mark, _act = destutil.destupdate(repo)
             node = repo[rev].node()
 
         overwrite = force and not branchmerge
 
         p2 = repo[node]
         if pas[0] is None:
             if repo.ui.configlist('merge', 'preferancestor', ['*']) == ['*']:
                 cahs = repo.changelog.commonancestorsheads(p1.node(), p2.node())
                 pas = [repo[anc] for anc in (sorted(cahs) or [nullid])]
             else:
                 pas = [p1.ancestor(p2, warn=branchmerge)]
 
         fp1, fp2, xp1, xp2 = p1.node(), p2.node(), str(p1), str(p2)
 
         ### check phase
         if not overwrite:
             if len(pl) > 1:
                 raise error.Abort(_("outstanding uncommitted merge"))
             ms = mergestate.read(repo)
             if list(ms.unresolved()):
                 raise error.Abort(_("outstanding merge conflicts"))
         if branchmerge:
             if pas == [p2]:
                 raise error.Abort(_("merging with a working directory ancestor"
                                    " has no effect"))
             elif pas == [p1]:
                 if not mergeancestor and p1.branch() == p2.branch():
                     raise error.Abort(_("nothing to merge"),
                                      hint=_("use 'hg update' "
                                             "or check 'hg heads'"))
             if not force and (wc.files() or wc.deleted()):
                 raise error.Abort(_("uncommitted changes"),
                                  hint=_("use 'hg status' to list changes"))
             for s in sorted(wc.substate):
                 wc.sub(s).bailifchanged()
 
         elif not overwrite:
             if p1 == p2: # no-op update
                 # call the hooks and exit early
                 repo.hook('preupdate', throw=True, parent1=xp2, parent2='')
                 repo.hook('update', parent1=xp2, parent2='', error=0)
                 return 0, 0, 0, 0
 
             if pas not in ([p1], [p2]):  # nonlinear
                 dirty = wc.dirty(missing=True)
                 if dirty or onode is None:
                     # Branching is a bit strange to ensure we do the minimal
                     # amount of call to obsolete.background.
                     foreground = obsolete.foreground(repo, [p1.node()])
                     # note: the <node> variable contains a random identifier
                     if repo[node].node() in foreground:
                         pas = [p1]  # allow updating to successors
                     elif dirty:
                         msg = _("uncommitted changes")
                         if onode is None:
                             hint = _("commit and merge, or update --clean to"
                                      " discard changes")
                         else:
                             hint = _("commit or update --clean to discard"
                                      " changes")
                         raise error.Abort(msg, hint=hint)
                     else:  # node is none
                         msg = _("not a linear update")
                         hint = _("merge or update --check to force update")
                         raise error.Abort(msg, hint=hint)
                 else:
                     # Allow jumping branches if clean and specific rev given
                     pas = [p1]
 
         # deprecated config: merge.followcopies
         followcopies = False
         if overwrite:
             pas = [wc]
         elif pas == [p2]: # backwards
             pas = [wc.p1()]
         elif not branchmerge and not wc.dirty(missing=True):
             pass
         elif pas[0] and repo.ui.configbool('merge', 'followcopies', True):
             followcopies = True
 
         ### calculate phase
         actionbyfile, diverge, renamedelete = calculateupdates(
             repo, wc, p2, pas, branchmerge, force, mergeancestor,
             followcopies, matcher=matcher, mergeforce=mergeforce)
 
         # Prompt and create actions. Most of this is in the resolve phase
         # already, but we can't handle .hgsubstate in filemerge or
         # subrepo.submerge yet so we have to keep prompting for it.
         if '.hgsubstate' in actionbyfile:
             f = '.hgsubstate'
             m, args, msg = actionbyfile[f]
             if m == 'cd':
                 if repo.ui.promptchoice(
                     _("local changed %s which remote deleted\n"
                       "use (c)hanged version or (d)elete?"
                       "$$ &Changed $$ &Delete") % f, 0):
                     actionbyfile[f] = ('r', None, "prompt delete")
                 elif f in p1:
                     actionbyfile[f] = ('am', None, "prompt keep")
                 else:
                     actionbyfile[f] = ('a', None, "prompt keep")
             elif m == 'dc':
                 f1, f2, fa, move, anc = args
                 flags = p2[f2].flags()
                 if repo.ui.promptchoice(
                     _("remote changed %s which local deleted\n"
                       "use (c)hanged version or leave (d)eleted?"
                       "$$ &Changed $$ &Deleted") % f, 0) == 0:
                     actionbyfile[f] = ('g', (flags, False), "prompt recreating")
                 else:
                     del actionbyfile[f]
 
         # Convert to dictionary-of-lists format
         actions = dict((m, []) for m in 'a am f g cd dc r dm dg m e k'.split())
         for f, (m, args, msg) in actionbyfile.iteritems():
             if m not in actions:
                 actions[m] = []
             actions[m].append((f, args, msg))
 
         if not util.checkcase(repo.path):
             # check collision between files only in p2 for clean update
             if (not branchmerge and
                 (force or not wc.dirty(missing=True, branch=False))):
                 _checkcollision(repo, p2.manifest(), None)
             else:
                 _checkcollision(repo, wc.manifest(), actions)
 
         # divergent renames
         for f, fl in sorted(diverge.iteritems()):
             repo.ui.warn(_("note: possible conflict - %s was renamed "
                            "multiple times to:\n") % f)
             for nf in fl:
                 repo.ui.warn(" %s\n" % nf)
 
         # rename and delete
         for f, fl in sorted(renamedelete.iteritems()):
             repo.ui.warn(_("note: possible conflict - %s was deleted "
                            "and renamed to:\n") % f)
             for nf in fl:
                 repo.ui.warn(" %s\n" % nf)
 
         ### apply phase
         if not branchmerge: # just jump to the new rev
             fp1, fp2, xp1, xp2 = fp2, nullid, xp2, ''
         if not partial:
             repo.hook('preupdate', throw=True, parent1=xp1, parent2=xp2)
             # note that we're in the middle of an update
             repo.vfs.write('updatestate', p2.hex())
 
         stats = applyupdates(repo, actions, wc, p2, overwrite, labels=labels)
 
         if not partial:
             repo.dirstate.beginparentchange()
             repo.setparents(fp1, fp2)
             recordupdates(repo, actions, branchmerge)
             # update completed, clear state
             util.unlink(repo.join('updatestate'))
 
             if not branchmerge:
                 repo.dirstate.setbranch(p2.branch())
             repo.dirstate.endparentchange()
 
     if not partial:
         repo.hook('update', parent1=xp1, parent2=xp2, error=stats[3])
     return stats
 
 def graft(repo, ctx, pctx, labels, keepparent=False):
     """Do a graft-like merge.
 
     This is a merge where the merge ancestor is chosen such that one
     or more changesets are grafted onto the current changeset. In
     addition to the merge, this fixes up the dirstate to include only
     a single parent (if keepparent is False) and tries to duplicate any
     renames/copies appropriately.
 
     ctx - changeset to rebase
     pctx - merge base, usually ctx.p1()
     labels - merge labels eg ['local', 'graft']
     keepparent - keep second parent if any
 
     """
     # If we're grafting a descendant onto an ancestor, be sure to pass
     # mergeancestor=True to update. This does two things: 1) allows the merge if
     # the destination is the same as the parent of the ctx (so we can use graft
     # to copy commits), and 2) informs update that the incoming changes are
     # newer than the destination so it doesn't prompt about "remote changed foo
     # which local deleted".
     mergeancestor = repo.changelog.isancestor(repo['.'].node(), ctx.node())
 
     stats = update(repo, ctx.node(), True, True, pctx.node(),
                    mergeancestor=mergeancestor, labels=labels)
 
     pother = nullid
     parents = ctx.parents()
     if keepparent and len(parents) == 2 and pctx in parents:
         parents.remove(pctx)
         pother = parents[0].node()
 
     repo.dirstate.beginparentchange()
     repo.setparents(repo['.'].node(), pother)
     repo.dirstate.write(repo.currenttransaction())
     # fix up dirstate for copies and renames
     copies.duplicatecopies(repo, ctx.rev(), pctx.rev())
     repo.dirstate.endparentchange()
     return stats

mercurial/peer.py

@@ -1,155 +1,155 b''
 # peer.py - repository base classes for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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.
 
 from __future__ import absolute_import
 
 from .i18n import _
 from . import (
     error,
     util,
 )
 
 # abstract batching support
 
 class future(object):
     '''placeholder for a value to be set later'''
     def set(self, value):
         if util.safehasattr(self, 'value'):
             raise error.RepoError("future is already set")
         self.value = value
 
 class batcher(object):
     '''base class for batches of commands submittable in a single request
 
     All methods invoked on instances of this class are simply queued and
     return a a future for the result. Once you call submit(), all the queued
     calls are performed and the results set in their respective futures.
     '''
     def __init__(self):
         self.calls = []
     def __getattr__(self, name):
         def call(*args, **opts):
             resref = future()
             self.calls.append((name, args, opts, resref,))
             return resref
         return call
     def submit(self):
         raise NotImplementedError()
 
 class iterbatcher(batcher):
 
     def submit(self):
         raise NotImplementedError()
 
     def results(self):
         raise NotImplementedError()
 
 class localbatch(batcher):
     '''performs the queued calls directly'''
     def __init__(self, local):
         batcher.__init__(self)
         self.local = local
     def submit(self):
         for name, args, opts, resref in self.calls:
             resref.set(getattr(self.local, name)(*args, **opts))
 
 class localiterbatcher(iterbatcher):
     def __init__(self, local):
         super(iterbatcher, self).__init__()
         self.local = local
 
     def submit(self):
         # submit for a local iter batcher is a noop
         pass
 
     def results(self):
         for name, args, opts, resref in self.calls:
             yield getattr(self.local, name)(*args, **opts)
 
 def batchable(f):
     '''annotation for batchable methods
 
     Such methods must implement a coroutine as follows:
 
     @batchable
     def sample(self, one, two=None):
         # Handle locally computable results first:
         if not one:
             yield "a local result", None
         # Build list of encoded arguments suitable for your wire protocol:
         encargs = [('one', encode(one),), ('two', encode(two),)]
         # Create future for injection of encoded result:
         encresref = future()
         # Return encoded arguments and future:
         yield encargs, encresref
         # Assuming the future to be filled with the result from the batched
         # request now. Decode it:
         yield decode(encresref.value)
 
     The decorator returns a function which wraps this coroutine as a plain
     method, but adds the original method as an attribute called "batchable",
     which is used by remotebatch to split the call into separate encoding and
     decoding phases.
     '''
     def plain(*args, **opts):
         batchable = f(*args, **opts)
-        encargsorres, encresref = batchable.next()
+        encargsorres, encresref = next(batchable)
         if not encresref:
             return encargsorres # a local result in this case
         self = args[0]
         encresref.set(self._submitone(f.func_name, encargsorres))
-        return batchable.next()
+        return next(batchable)
     setattr(plain, 'batchable', f)
     return plain
 
 class peerrepository(object):
 
     def batch(self):
         return localbatch(self)
 
     def iterbatch(self):
         """Batch requests but allow iterating over the results.
 
         This is to allow interleaving responses with things like
         progress updates for clients.
         """
         return localiterbatcher(self)
 
     def capable(self, name):
         '''tell whether repo supports named capability.
         return False if not supported.
         if boolean capability, return True.
         if string capability, return string.'''
         caps = self._capabilities()
         if name in caps:
             return True
         name_eq = name + '='
         for cap in caps:
             if cap.startswith(name_eq):
                 return cap[len(name_eq):]
         return False
 
     def requirecap(self, name, purpose):
         '''raise an exception if the given capability is not present'''
         if not self.capable(name):
             raise error.CapabilityError(
                 _('cannot %s; remote repository does not '
                   'support the %r capability') % (purpose, name))
 
     def local(self):
         '''return peer as a localrepo, or None'''
         return None
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         pass

mercurial/revset.py

@@ -1,3396 +1,3396 b''
 # revset.py - revision set queries 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.
 
 from __future__ import absolute_import
 
 import heapq
 import re
 
 from .i18n import _
 from . import (
     destutil,
     encoding,
     error,
     hbisect,
     match as matchmod,
     node,
     obsolete as obsmod,
     parser,
     pathutil,
     phases,
     registrar,
     repoview,
     util,
 )
 
 def _revancestors(repo, revs, followfirst):
     """Like revlog.ancestors(), but supports followfirst."""
     if followfirst:
         cut = 1
     else:
         cut = None
     cl = repo.changelog
 
     def iterate():
         revs.sort(reverse=True)
         irevs = iter(revs)
         h = []
 
         inputrev = next(irevs, None)
         if inputrev is not None:
             heapq.heappush(h, -inputrev)
 
         seen = set()
         while h:
             current = -heapq.heappop(h)
             if current == inputrev:
                 inputrev = next(irevs, None)
                 if inputrev is not None:
                     heapq.heappush(h, -inputrev)
             if current not in seen:
                 seen.add(current)
                 yield current
                 for parent in cl.parentrevs(current)[:cut]:
                     if parent != node.nullrev:
                         heapq.heappush(h, -parent)
 
     return generatorset(iterate(), iterasc=False)
 
 def _revdescendants(repo, revs, followfirst):
     """Like revlog.descendants() but supports followfirst."""
     if followfirst:
         cut = 1
     else:
         cut = None
 
     def iterate():
         cl = repo.changelog
         # XXX this should be 'parentset.min()' assuming 'parentset' is a
         # smartset (and if it is not, it should.)
         first = min(revs)
         nullrev = node.nullrev
         if first == nullrev:
             # Are there nodes with a null first parent and a non-null
             # second one? Maybe. Do we care? Probably not.
             for i in cl:
                 yield i
         else:
             seen = set(revs)
             for i in cl.revs(first + 1):
                 for x in cl.parentrevs(i)[:cut]:
                     if x != nullrev and x in seen:
                         seen.add(i)
                         yield i
                         break
 
     return generatorset(iterate(), iterasc=True)
 
 def _reachablerootspure(repo, minroot, roots, heads, includepath):
     """return (heads(::<roots> and ::<heads>))
 
     If includepath is True, return (<roots>::<heads>)."""
     if not roots:
         return []
     parentrevs = repo.changelog.parentrevs
     roots = set(roots)
     visit = list(heads)
     reachable = set()
     seen = {}
     # prefetch all the things! (because python is slow)
     reached = reachable.add
     dovisit = visit.append
     nextvisit = visit.pop
     # open-code the post-order traversal due to the tiny size of
     # sys.getrecursionlimit()
     while visit:
         rev = nextvisit()
         if rev in roots:
             reached(rev)
             if not includepath:
                 continue
         parents = parentrevs(rev)
         seen[rev] = parents
         for parent in parents:
             if parent >= minroot and parent not in seen:
                 dovisit(parent)
     if not reachable:
         return baseset()
     if not includepath:
         return reachable
     for rev in sorted(seen):
         for parent in seen[rev]:
             if parent in reachable:
                 reached(rev)
     return reachable
 
 def reachableroots(repo, roots, heads, includepath=False):
     """return (heads(::<roots> and ::<heads>))
 
     If includepath is True, return (<roots>::<heads>)."""
     if not roots:
         return baseset()
     minroot = roots.min()
     roots = list(roots)
     heads = list(heads)
     try:
         revs = repo.changelog.reachableroots(minroot, heads, roots, includepath)
     except AttributeError:
         revs = _reachablerootspure(repo, minroot, roots, heads, includepath)
     revs = baseset(revs)
     revs.sort()
     return revs
 
 elements = {
     # token-type: binding-strength, primary, prefix, infix, suffix
     "(": (21, None, ("group", 1, ")"), ("func", 1, ")"), None),
     "##": (20, None, None, ("_concat", 20), None),
     "~": (18, None, None, ("ancestor", 18), None),
     "^": (18, None, None, ("parent", 18), ("parentpost", 18)),
     "-": (5, None, ("negate", 19), ("minus", 5), None),
     "::": (17, None, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     "..": (17, None, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     ":": (15, "rangeall", ("rangepre", 15), ("range", 15), ("rangepost", 15)),
     "not": (10, None, ("not", 10), None, None),
     "!": (10, None, ("not", 10), None, None),
     "and": (5, None, None, ("and", 5), None),
     "&": (5, None, None, ("and", 5), None),
     "%": (5, None, None, ("only", 5), ("onlypost", 5)),
     "or": (4, None, None, ("or", 4), None),
     "|": (4, None, None, ("or", 4), None),
     "+": (4, None, None, ("or", 4), None),
     "=": (3, None, None, ("keyvalue", 3), None),
     ",": (2, None, None, ("list", 2), None),
     ")": (0, None, None, None, None),
     "symbol": (0, "symbol", None, None, None),
     "string": (0, "string", None, None, None),
     "end": (0, None, None, None, None),
 }
 
 keywords = set(['and', 'or', 'not'])
 
 # default set of valid characters for the initial letter of symbols
 _syminitletters = set(c for c in [chr(i) for i in xrange(256)]
                       if c.isalnum() or c in '._@' or ord(c) > 127)
 
 # default set of valid characters for non-initial letters of symbols
 _symletters = set(c for c in  [chr(i) for i in xrange(256)]
                   if c.isalnum() or c in '-._/@' or ord(c) > 127)
 
 def tokenize(program, lookup=None, syminitletters=None, symletters=None):
     '''
     Parse a revset statement into a stream of tokens
 
     ``syminitletters`` is the set of valid characters for the initial
     letter of symbols.
 
     By default, character ``c`` is recognized as valid for initial
     letter of symbols, if ``c.isalnum() or c in '._@' or ord(c) > 127``.
 
     ``symletters`` is the set of valid characters for non-initial
     letters of symbols.
 
     By default, character ``c`` is recognized as valid for non-initial
     letters of symbols, if ``c.isalnum() or c in '-._/@' or ord(c) > 127``.
 
     Check that @ is a valid unquoted token character (issue3686):
     >>> list(tokenize("@::"))
     [('symbol', '@', 0), ('::', None, 1), ('end', None, 3)]
 
     '''
     if syminitletters is None:
         syminitletters = _syminitletters
     if symletters is None:
         symletters = _symletters
 
     if program and lookup:
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         parts = program.split(':', 1)
         if all(lookup(sym) for sym in parts if sym):
             if parts[0]:
                 yield ('symbol', parts[0], 0)
             if len(parts) > 1:
                 s = len(parts[0])
                 yield (':', None, s)
                 if parts[1]:
                     yield ('symbol', parts[1], s + 1)
             yield ('end', None, len(program))
             return
 
     pos, l = 0, len(program)
     while pos < l:
         c = program[pos]
         if c.isspace(): # skip inter-token whitespace
             pass
         elif c == ':' and program[pos:pos + 2] == '::': # look ahead carefully
             yield ('::', None, pos)
             pos += 1 # skip ahead
         elif c == '.' and program[pos:pos + 2] == '..': # look ahead carefully
             yield ('..', None, pos)
             pos += 1 # skip ahead
         elif c == '#' and program[pos:pos + 2] == '##': # look ahead carefully
             yield ('##', None, pos)
             pos += 1 # skip ahead
         elif c in "():=,-|&+!~^%": # handle simple operators
             yield (c, None, pos)
         elif (c in '"\'' or c == 'r' and
               program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
             if c == 'r':
                 pos += 1
                 c = program[pos]
                 decode = lambda x: x
             else:
                 decode = parser.unescapestr
             pos += 1
             s = pos
             while pos < l: # find closing quote
                 d = program[pos]
                 if d == '\\': # skip over escaped characters
                     pos += 2
                     continue
                 if d == c:
                     yield ('string', decode(program[s:pos]), s)
                     break
                 pos += 1
             else:
                 raise error.ParseError(_("unterminated string"), s)
         # gather up a symbol/keyword
         elif c in syminitletters:
             s = pos
             pos += 1
             while pos < l: # find end of symbol
                 d = program[pos]
                 if d not in symletters:
                     break
                 if d == '.' and program[pos - 1] == '.': # special case for ..
                     pos -= 1
                     break
                 pos += 1
             sym = program[s:pos]
             if sym in keywords: # operator keywords
                 yield (sym, None, s)
             elif '-' in sym:
                 # some jerk gave us foo-bar-baz, try to check if it's a symbol
                 if lookup and lookup(sym):
                     # looks like a real symbol
                     yield ('symbol', sym, s)
                 else:
                     # looks like an expression
                     parts = sym.split('-')
                     for p in parts[:-1]:
                         if p: # possible consecutive -
                             yield ('symbol', p, s)
                         s += len(p)
                         yield ('-', None, pos)
                         s += 1
                     if parts[-1]: # possible trailing -
                         yield ('symbol', parts[-1], s)
             else:
                 yield ('symbol', sym, s)
             pos -= 1
         else:
             raise error.ParseError(_("syntax error in revset '%s'") %
                                    program, pos)
         pos += 1
     yield ('end', None, pos)
 
 # helpers
 
 def getstring(x, err):
     if x and (x[0] == 'string' or x[0] == 'symbol'):
         return x[1]
     raise error.ParseError(err)
 
 def getlist(x):
     if not x:
         return []
     if x[0] == 'list':
         return list(x[1:])
     return [x]
 
 def getargs(x, min, max, err):
     l = getlist(x)
     if len(l) < min or (max >= 0 and len(l) > max):
         raise error.ParseError(err)
     return l
 
 def getargsdict(x, funcname, keys):
     return parser.buildargsdict(getlist(x), funcname, keys.split(),
                                 keyvaluenode='keyvalue', keynode='symbol')
 
 def getset(repo, subset, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     s = methods[x[0]](repo, subset, *x[1:])
     if util.safehasattr(s, 'isascending'):
         return s
     # else case should not happen, because all non-func are internal,
     # ignoring for now.
     if x[0] == 'func' and x[1][0] == 'symbol' and x[1][1] in symbols:
         repo.ui.deprecwarn('revset "%s" uses list instead of smartset'
                            % x[1][1],
                            '3.9')
     return baseset(s)
 
 def _getrevsource(repo, r):
     extra = repo[r].extra()
     for label in ('source', 'transplant_source', 'rebase_source'):
         if label in extra:
             try:
                 return repo[extra[label]].rev()
             except error.RepoLookupError:
                 pass
     return None
 
 # operator methods
 
 def stringset(repo, subset, x):
     x = repo[x].rev()
     if (x in subset
         or x == node.nullrev and isinstance(subset, fullreposet)):
         return baseset([x])
     return baseset()
 
 def rangeset(repo, subset, x, y):
     m = getset(repo, fullreposet(repo), x)
     n = getset(repo, fullreposet(repo), y)
 
     if not m or not n:
         return baseset()
     m, n = m.first(), n.last()
 
     if m == n:
         r = baseset([m])
     elif n == node.wdirrev:
         r = spanset(repo, m, len(repo)) + baseset([n])
     elif m == node.wdirrev:
         r = baseset([m]) + spanset(repo, len(repo) - 1, n - 1)
     elif m < n:
         r = spanset(repo, m, n + 1)
     else:
         r = spanset(repo, m, n - 1)
     # XXX We should combine with subset first: 'subset & baseset(...)'. This is
     # necessary to ensure we preserve the order in subset.
     #
     # This has performance implication, carrying the sorting over when possible
     # would be more efficient.
     return r & subset
 
 def dagrange(repo, subset, x, y):
     r = fullreposet(repo)
     xs = reachableroots(repo, getset(repo, r, x), getset(repo, r, y),
                          includepath=True)
     return subset & xs
 
 def andset(repo, subset, x, y):
     return getset(repo, getset(repo, subset, x), y)
 
 def differenceset(repo, subset, x, y):
     return getset(repo, subset, x) - getset(repo, subset, y)
 
 def orset(repo, subset, *xs):
     assert xs
     if len(xs) == 1:
         return getset(repo, subset, xs[0])
     p = len(xs) // 2
     a = orset(repo, subset, *xs[:p])
     b = orset(repo, subset, *xs[p:])
     return a + b
 
 def notset(repo, subset, x):
     return subset - getset(repo, subset, x)
 
 def listset(repo, subset, *xs):
     raise error.ParseError(_("can't use a list in this context"),
                            hint=_('see hg help "revsets.x or y"'))
 
 def keyvaluepair(repo, subset, k, v):
     raise error.ParseError(_("can't use a key-value pair in this context"))
 
 def func(repo, subset, a, b):
     if a[0] == 'symbol' and a[1] in symbols:
         return symbols[a[1]](repo, subset, b)
 
     keep = lambda fn: getattr(fn, '__doc__', None) is not None
 
     syms = [s for (s, fn) in symbols.items() if keep(fn)]
     raise error.UnknownIdentifier(a[1], syms)
 
 # functions
 
 # symbols are callables like:
 #   fn(repo, subset, x)
 # with:
 #   repo - current repository instance
 #   subset - of revisions to be examined
 #   x - argument in tree form
 symbols = {}
 
 # symbols which can't be used for a DoS attack for any given input
 # (e.g. those which accept regexes as plain strings shouldn't be included)
 # functions that just return a lot of changesets (like all) don't count here
 safesymbols = set()
 
 predicate = registrar.revsetpredicate()
 
 @predicate('_destupdate')
 def _destupdate(repo, subset, x):
     # experimental revset for update destination
     args = getargsdict(x, 'limit', 'clean check')
     return subset & baseset([destutil.destupdate(repo, **args)[0]])
 
 @predicate('_destmerge')
 def _destmerge(repo, subset, x):
     # experimental revset for merge destination
     sourceset = None
     if x is not None:
         sourceset = getset(repo, fullreposet(repo), x)
     return subset & baseset([destutil.destmerge(repo, sourceset=sourceset)])
 
 @predicate('adds(pattern)', safe=True)
 def adds(repo, subset, x):
     """Changesets that add a file matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "adds" is a keyword
     pat = getstring(x, _("adds requires a pattern"))
     return checkstatus(repo, subset, pat, 1)
 
 @predicate('ancestor(*changeset)', safe=True)
 def ancestor(repo, subset, x):
     """A greatest common ancestor of the changesets.
 
     Accepts 0 or more changesets.
     Will return empty list when passed no args.
     Greatest common ancestor of a single changeset is that changeset.
     """
     # i18n: "ancestor" is a keyword
     l = getlist(x)
     rl = fullreposet(repo)
     anc = None
 
     # (getset(repo, rl, i) for i in l) generates a list of lists
     for revs in (getset(repo, rl, i) for i in l):
         for r in revs:
             if anc is None:
                 anc = repo[r]
             else:
                 anc = anc.ancestor(repo[r])
 
     if anc is not None and anc.rev() in subset:
         return baseset([anc.rev()])
     return baseset()
 
 def _ancestors(repo, subset, x, followfirst=False):
     heads = getset(repo, fullreposet(repo), x)
     if not heads:
         return baseset()
     s = _revancestors(repo, heads, followfirst)
     return subset & s
 
 @predicate('ancestors(set)', safe=True)
 def ancestors(repo, subset, x):
     """Changesets that are ancestors of a changeset in set.
     """
     return _ancestors(repo, subset, x)
 
 @predicate('_firstancestors', safe=True)
 def _firstancestors(repo, subset, x):
     # ``_firstancestors(set)``
     # Like ``ancestors(set)`` but follows only the first parents.
     return _ancestors(repo, subset, x, followfirst=True)
 
 def ancestorspec(repo, subset, x, n):
     """``set~n``
     Changesets that are the Nth ancestor (first parents only) of a changeset
     in set.
     """
     try:
         n = int(n[1])
     except (TypeError, ValueError):
         raise error.ParseError(_("~ expects a number"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         for i in range(n):
             r = cl.parentrevs(r)[0]
         ps.add(r)
     return subset & ps
 
 @predicate('author(string)', safe=True)
 def author(repo, subset, x):
     """Alias for ``user(string)``.
     """
     # i18n: "author" is a keyword
     n = encoding.lower(getstring(x, _("author requires a string")))
     kind, pattern, matcher = _substringmatcher(n)
     return subset.filter(lambda x: matcher(encoding.lower(repo[x].user())),
                          condrepr=('<user %r>', n))
 
 @predicate('bisect(string)', safe=True)
 def bisect(repo, subset, x):
     """Changesets marked in the specified bisect status:
 
     - ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
     - ``goods``, ``bads``      : csets topologically good/bad
     - ``range``              : csets taking part in the bisection
     - ``pruned``             : csets that are goods, bads or skipped
     - ``untested``           : csets whose fate is yet unknown
     - ``ignored``            : csets ignored due to DAG topology
     - ``current``            : the cset currently being bisected
     """
     # i18n: "bisect" is a keyword
     status = getstring(x, _("bisect requires a string")).lower()
     state = set(hbisect.get(repo, status))
     return subset & state
 
 # Backward-compatibility
 # - no help entry so that we do not advertise it any more
 @predicate('bisected', safe=True)
 def bisected(repo, subset, x):
     return bisect(repo, subset, x)
 
 @predicate('bookmark([name])', safe=True)
 def bookmark(repo, subset, x):
     """The named bookmark or all bookmarks.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a bookmark that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "bookmark" is a keyword
     args = getargs(x, 0, 1, _('bookmark takes one or no arguments'))
     if args:
         bm = getstring(args[0],
                        # i18n: "bookmark" is a keyword
                        _('the argument to bookmark must be a string'))
         kind, pattern, matcher = util.stringmatcher(bm)
         bms = set()
         if kind == 'literal':
             bmrev = repo._bookmarks.get(pattern, None)
             if not bmrev:
                 raise error.RepoLookupError(_("bookmark '%s' does not exist")
                                             % pattern)
             bms.add(repo[bmrev].rev())
         else:
             matchrevs = set()
             for name, bmrev in repo._bookmarks.iteritems():
                 if matcher(name):
                     matchrevs.add(bmrev)
             if not matchrevs:
                 raise error.RepoLookupError(_("no bookmarks exist"
                                               " that match '%s'") % pattern)
             for bmrev in matchrevs:
                 bms.add(repo[bmrev].rev())
     else:
         bms = set([repo[r].rev()
                    for r in repo._bookmarks.values()])
     bms -= set([node.nullrev])
     return subset & bms
 
 @predicate('branch(string or set)', safe=True)
 def branch(repo, subset, x):
     """
     All changesets belonging to the given branch or the branches of the given
     changesets.
 
     If `string` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a branch that actually starts with `re:`,
     use the prefix `literal:`.
     """
     getbi = repo.revbranchcache().branchinfo
 
     try:
         b = getstring(x, '')
     except error.ParseError:
         # not a string, but another revspec, e.g. tip()
         pass
     else:
         kind, pattern, matcher = util.stringmatcher(b)
         if kind == 'literal':
             # note: falls through to the revspec case if no branch with
             # this name exists and pattern kind is not specified explicitly
             if pattern in repo.branchmap():
                 return subset.filter(lambda r: matcher(getbi(r)[0]),
                                      condrepr=('<branch %r>', b))
             if b.startswith('literal:'):
                 raise error.RepoLookupError(_("branch '%s' does not exist")
                                             % pattern)
         else:
             return subset.filter(lambda r: matcher(getbi(r)[0]),
                                  condrepr=('<branch %r>', b))
 
     s = getset(repo, fullreposet(repo), x)
     b = set()
     for r in s:
         b.add(getbi(r)[0])
     c = s.__contains__
     return subset.filter(lambda r: c(r) or getbi(r)[0] in b,
                          condrepr=lambda: '<branch %r>' % sorted(b))
 
 @predicate('bumped()', safe=True)
 def bumped(repo, subset, x):
     """Mutable changesets marked as successors of public changesets.
 
     Only non-public and non-obsolete changesets can be `bumped`.
     """
     # i18n: "bumped" is a keyword
     getargs(x, 0, 0, _("bumped takes no arguments"))
     bumped = obsmod.getrevs(repo, 'bumped')
     return subset & bumped
 
 @predicate('bundle()', safe=True)
 def bundle(repo, subset, x):
     """Changesets in the bundle.
 
     Bundle must be specified by the -R option."""
 
     try:
         bundlerevs = repo.changelog.bundlerevs
     except AttributeError:
         raise error.Abort(_("no bundle provided - specify with -R"))
     return subset & bundlerevs
 
 def checkstatus(repo, subset, pat, field):
     hasset = matchmod.patkind(pat) == 'set'
 
     mcache = [None]
     def matches(x):
         c = repo[x]
         if not mcache[0] or hasset:
             mcache[0] = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
         m = mcache[0]
         fname = None
         if not m.anypats() and len(m.files()) == 1:
             fname = m.files()[0]
         if fname is not None:
             if fname not in c.files():
                 return False
         else:
             for f in c.files():
                 if m(f):
                     break
             else:
                 return False
         files = repo.status(c.p1().node(), c.node())[field]
         if fname is not None:
             if fname in files:
                 return True
         else:
             for f in files:
                 if m(f):
                     return True
 
     return subset.filter(matches, condrepr=('<status[%r] %r>', field, pat))
 
 def _children(repo, narrow, parentset):
     if not parentset:
         return baseset()
     cs = set()
     pr = repo.changelog.parentrevs
     minrev = parentset.min()
     for r in narrow:
         if r <= minrev:
             continue
         for p in pr(r):
             if p in parentset:
                 cs.add(r)
     # XXX using a set to feed the baseset is wrong. Sets are not ordered.
     # This does not break because of other fullreposet misbehavior.
     return baseset(cs)
 
 @predicate('children(set)', safe=True)
 def children(repo, subset, x):
     """Child changesets of changesets in set.
     """
     s = getset(repo, fullreposet(repo), x)
     cs = _children(repo, subset, s)
     return subset & cs
 
 @predicate('closed()', safe=True)
 def closed(repo, subset, x):
     """Changeset is closed.
     """
     # i18n: "closed" is a keyword
     getargs(x, 0, 0, _("closed takes no arguments"))
     return subset.filter(lambda r: repo[r].closesbranch(),
                          condrepr='<branch closed>')
 
 @predicate('contains(pattern)')
 def contains(repo, subset, x):
     """The revision's manifest contains a file matching pattern (but might not
     modify it). See :hg:`help patterns` for information about file patterns.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
     """
     # i18n: "contains" is a keyword
     pat = getstring(x, _("contains requires a pattern"))
 
     def matches(x):
         if not matchmod.patkind(pat):
             pats = pathutil.canonpath(repo.root, repo.getcwd(), pat)
             if pats in repo[x]:
                 return True
         else:
             c = repo[x]
             m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
             for f in c.manifest():
                 if m(f):
                     return True
         return False
 
     return subset.filter(matches, condrepr=('<contains %r>', pat))
 
 @predicate('converted([id])', safe=True)
 def converted(repo, subset, x):
     """Changesets converted from the given identifier in the old repository if
     present, or all converted changesets if no identifier is specified.
     """
 
     # There is exactly no chance of resolving the revision, so do a simple
     # string compare and hope for the best
 
     rev = None
     # i18n: "converted" is a keyword
     l = getargs(x, 0, 1, _('converted takes one or no arguments'))
     if l:
         # i18n: "converted" is a keyword
         rev = getstring(l[0], _('converted requires a revision'))
 
     def _matchvalue(r):
         source = repo[r].extra().get('convert_revision', None)
         return source is not None and (rev is None or source.startswith(rev))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<converted %r>', rev))
 
 @predicate('date(interval)', safe=True)
 def date(repo, subset, x):
     """Changesets within the interval, see :hg:`help dates`.
     """
     # i18n: "date" is a keyword
     ds = getstring(x, _("date requires a string"))
     dm = util.matchdate(ds)
     return subset.filter(lambda x: dm(repo[x].date()[0]),
                          condrepr=('<date %r>', ds))
 
 @predicate('desc(string)', safe=True)
 def desc(repo, subset, x):
     """Search commit message for string. The match is case-insensitive.
     """
     # i18n: "desc" is a keyword
     ds = encoding.lower(getstring(x, _("desc requires a string")))
 
     def matches(x):
         c = repo[x]
         return ds in encoding.lower(c.description())
 
     return subset.filter(matches, condrepr=('<desc %r>', ds))
 
 def _descendants(repo, subset, x, followfirst=False):
     roots = getset(repo, fullreposet(repo), x)
     if not roots:
         return baseset()
     s = _revdescendants(repo, roots, followfirst)
 
     # Both sets need to be ascending in order to lazily return the union
     # in the correct order.
     base = subset & roots
     desc = subset & s
     result = base + desc
     if subset.isascending():
         result.sort()
     elif subset.isdescending():
         result.sort(reverse=True)
     else:
         result = subset & result
     return result
 
 @predicate('descendants(set)', safe=True)
 def descendants(repo, subset, x):
     """Changesets which are descendants of changesets in set.
     """
     return _descendants(repo, subset, x)
 
 @predicate('_firstdescendants', safe=True)
 def _firstdescendants(repo, subset, x):
     # ``_firstdescendants(set)``
     # Like ``descendants(set)`` but follows only the first parents.
     return _descendants(repo, subset, x, followfirst=True)
 
 @predicate('destination([set])', safe=True)
 def destination(repo, subset, x):
     """Changesets that were created by a graft, transplant or rebase operation,
     with the given revisions specified as the source.  Omitting the optional set
     is the same as passing all().
     """
     if x is not None:
         sources = getset(repo, fullreposet(repo), x)
     else:
         sources = fullreposet(repo)
 
     dests = set()
 
     # subset contains all of the possible destinations that can be returned, so
     # iterate over them and see if their source(s) were provided in the arg set.
     # Even if the immediate src of r is not in the arg set, src's source (or
     # further back) may be.  Scanning back further than the immediate src allows
     # transitive transplants and rebases to yield the same results as transitive
     # grafts.
     for r in subset:
         src = _getrevsource(repo, r)
         lineage = None
 
         while src is not None:
             if lineage is None:
                 lineage = list()
 
             lineage.append(r)
 
             # The visited lineage is a match if the current source is in the arg
             # set.  Since every candidate dest is visited by way of iterating
             # subset, any dests further back in the lineage will be tested by a
             # different iteration over subset.  Likewise, if the src was already
             # selected, the current lineage can be selected without going back
             # further.
             if src in sources or src in dests:
                 dests.update(lineage)
                 break
 
             r = src
             src = _getrevsource(repo, r)
 
     return subset.filter(dests.__contains__,
                          condrepr=lambda: '<destination %r>' % sorted(dests))
 
 @predicate('divergent()', safe=True)
 def divergent(repo, subset, x):
     """
     Final successors of changesets with an alternative set of final successors.
     """
     # i18n: "divergent" is a keyword
     getargs(x, 0, 0, _("divergent takes no arguments"))
     divergent = obsmod.getrevs(repo, 'divergent')
     return subset & divergent
 
 @predicate('extinct()', safe=True)
 def extinct(repo, subset, x):
     """Obsolete changesets with obsolete descendants only.
     """
     # i18n: "extinct" is a keyword
     getargs(x, 0, 0, _("extinct takes no arguments"))
     extincts = obsmod.getrevs(repo, 'extinct')
     return subset & extincts
 
 @predicate('extra(label, [value])', safe=True)
 def extra(repo, subset, x):
     """Changesets with the given label in the extra metadata, with the given
     optional value.
 
     If `value` starts with `re:`, the remainder of the value is treated as
     a regular expression. To match a value that actually starts with `re:`,
     use the prefix `literal:`.
     """
     args = getargsdict(x, 'extra', 'label value')
     if 'label' not in args:
         # i18n: "extra" is a keyword
         raise error.ParseError(_('extra takes at least 1 argument'))
     # i18n: "extra" is a keyword
     label = getstring(args['label'], _('first argument to extra must be '
                                        'a string'))
     value = None
 
     if 'value' in args:
         # i18n: "extra" is a keyword
         value = getstring(args['value'], _('second argument to extra must be '
                                            'a string'))
         kind, value, matcher = util.stringmatcher(value)
 
     def _matchvalue(r):
         extra = repo[r].extra()
         return label in extra and (value is None or matcher(extra[label]))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<extra[%r] %r>', label, value))
 
 @predicate('filelog(pattern)', safe=True)
 def filelog(repo, subset, x):
     """Changesets connected to the specified filelog.
 
     For performance reasons, visits only revisions mentioned in the file-level
     filelog, rather than filtering through all changesets (much faster, but
     doesn't include deletes or duplicate changes). For a slower, more accurate
     result, use ``file()``.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
 
     If some linkrev points to revisions filtered by the current repoview, we'll
     work around it to return a non-filtered value.
     """
 
     # i18n: "filelog" is a keyword
     pat = getstring(x, _("filelog requires a pattern"))
     s = set()
     cl = repo.changelog
 
     if not matchmod.patkind(pat):
         f = pathutil.canonpath(repo.root, repo.getcwd(), pat)
         files = [f]
     else:
         m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=repo[None])
         files = (f for f in repo[None] if m(f))
 
     for f in files:
         fl = repo.file(f)
         known = {}
         scanpos = 0
         for fr in list(fl):
             fn = fl.node(fr)
             if fn in known:
                 s.add(known[fn])
                 continue
 
             lr = fl.linkrev(fr)
             if lr in cl:
                 s.add(lr)
             elif scanpos is not None:
                 # lowest matching changeset is filtered, scan further
                 # ahead in changelog
                 start = max(lr, scanpos) + 1
                 scanpos = None
                 for r in cl.revs(start):
                     # minimize parsing of non-matching entries
                     if f in cl.revision(r) and f in cl.readfiles(r):
                         try:
                             # try to use manifest delta fastpath
                             n = repo[r].filenode(f)
                             if n not in known:
                                 if n == fn:
                                     s.add(r)
                                     scanpos = r
                                     break
                                 else:
                                     known[n] = r
                         except error.ManifestLookupError:
                             # deletion in changelog
                             continue
 
     return subset & s
 
 @predicate('first(set, [n])', safe=True)
 def first(repo, subset, x):
     """An alias for limit().
     """
     return limit(repo, subset, x)
 
 def _follow(repo, subset, x, name, followfirst=False):
     l = getargs(x, 0, 1, _("%s takes no arguments or a pattern") % name)
     c = repo['.']
     if l:
         x = getstring(l[0], _("%s expected a pattern") % name)
         matcher = matchmod.match(repo.root, repo.getcwd(), [x],
                                  ctx=repo[None], default='path')
 
         files = c.manifest().walk(matcher)
 
         s = set()
         for fname in files:
             fctx = c[fname]
             s = s.union(set(c.rev() for c in fctx.ancestors(followfirst)))
             # include the revision responsible for the most recent version
             s.add(fctx.introrev())
     else:
         s = _revancestors(repo, baseset([c.rev()]), followfirst)
 
     return subset & s
 
 @predicate('follow([pattern])', safe=True)
 def follow(repo, subset, x):
     """
     An alias for ``::.`` (ancestors of the working directory's first parent).
     If pattern is specified, the histories of files matching given
     pattern is followed, including copies.
     """
     return _follow(repo, subset, x, 'follow')
 
 @predicate('_followfirst', safe=True)
 def _followfirst(repo, subset, x):
     # ``followfirst([pattern])``
     # Like ``follow([pattern])`` but follows only the first parent of
     # every revisions or files revisions.
     return _follow(repo, subset, x, '_followfirst', followfirst=True)
 
 @predicate('all()', safe=True)
 def getall(repo, subset, x):
     """All changesets, the same as ``0:tip``.
     """
     # i18n: "all" is a keyword
     getargs(x, 0, 0, _("all takes no arguments"))
     return subset & spanset(repo)  # drop "null" if any
 
 @predicate('grep(regex)')
 def grep(repo, subset, x):
     """Like ``keyword(string)`` but accepts a regex. Use ``grep(r'...')``
     to ensure special escape characters are handled correctly. Unlike
     ``keyword(string)``, the match is case-sensitive.
     """
     try:
         # i18n: "grep" is a keyword
         gr = re.compile(getstring(x, _("grep requires a string")))
     except re.error as e:
         raise error.ParseError(_('invalid match pattern: %s') % e)
 
     def matches(x):
         c = repo[x]
         for e in c.files() + [c.user(), c.description()]:
             if gr.search(e):
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<grep %r>', gr.pattern))
 
 @predicate('_matchfiles', safe=True)
 def _matchfiles(repo, subset, x):
     # _matchfiles takes a revset list of prefixed arguments:
     #
     #   [p:foo, i:bar, x:baz]
     #
     # builds a match object from them and filters subset. Allowed
     # prefixes are 'p:' for regular patterns, 'i:' for include
     # patterns and 'x:' for exclude patterns. Use 'r:' prefix to pass
     # a revision identifier, or the empty string to reference the
     # working directory, from which the match object is
     # initialized. Use 'd:' to set the default matching mode, default
     # to 'glob'. At most one 'r:' and 'd:' argument can be passed.
 
     l = getargs(x, 1, -1, "_matchfiles requires at least one argument")
     pats, inc, exc = [], [], []
     rev, default = None, None
     for arg in l:
         s = getstring(arg, "_matchfiles requires string arguments")
         prefix, value = s[:2], s[2:]
         if prefix == 'p:':
             pats.append(value)
         elif prefix == 'i:':
             inc.append(value)
         elif prefix == 'x:':
             exc.append(value)
         elif prefix == 'r:':
             if rev is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'revision')
             if value != '': # empty means working directory; leave rev as None
                 rev = value
         elif prefix == 'd:':
             if default is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'default mode')
             default = value
         else:
             raise error.ParseError('invalid _matchfiles prefix: %s' % prefix)
     if not default:
         default = 'glob'
 
     m = matchmod.match(repo.root, repo.getcwd(), pats, include=inc,
                        exclude=exc, ctx=repo[rev], default=default)
 
     # This directly read the changelog data as creating changectx for all
     # revisions is quite expensive.
     getfiles = repo.changelog.readfiles
     wdirrev = node.wdirrev
     def matches(x):
         if x == wdirrev:
             files = repo[x].files()
         else:
             files = getfiles(x)
         for f in files:
             if m(f):
                 return True
         return False
 
     return subset.filter(matches,
                          condrepr=('<matchfiles patterns=%r, include=%r '
                                    'exclude=%r, default=%r, rev=%r>',
                                    pats, inc, exc, default, rev))
 
 @predicate('file(pattern)', safe=True)
 def hasfile(repo, subset, x):
     """Changesets affecting files matched by pattern.
 
     For a faster but less accurate result, consider using ``filelog()``
     instead.
 
     This predicate uses ``glob:`` as the default kind of pattern.
     """
     # i18n: "file" is a keyword
     pat = getstring(x, _("file requires a pattern"))
     return _matchfiles(repo, subset, ('string', 'p:' + pat))
 
 @predicate('head()', safe=True)
 def head(repo, subset, x):
     """Changeset is a named branch head.
     """
     # i18n: "head" is a keyword
     getargs(x, 0, 0, _("head takes no arguments"))
     hs = set()
     cl = repo.changelog
     for b, ls in repo.branchmap().iteritems():
         hs.update(cl.rev(h) for h in ls)
     # XXX using a set to feed the baseset is wrong. Sets are not ordered.
     # This does not break because of other fullreposet misbehavior.
     # XXX We should combine with subset first: 'subset & baseset(...)'. This is
     # necessary to ensure we preserve the order in subset.
     return baseset(hs) & subset
 
 @predicate('heads(set)', safe=True)
 def heads(repo, subset, x):
     """Members of set with no children in set.
     """
     s = getset(repo, subset, x)
     ps = parents(repo, subset, x)
     return s - ps
 
 @predicate('hidden()', safe=True)
 def hidden(repo, subset, x):
     """Hidden changesets.
     """
     # i18n: "hidden" is a keyword
     getargs(x, 0, 0, _("hidden takes no arguments"))
     hiddenrevs = repoview.filterrevs(repo, 'visible')
     return subset & hiddenrevs
 
 @predicate('keyword(string)', safe=True)
 def keyword(repo, subset, x):
     """Search commit message, user name, and names of changed files for
     string. The match is case-insensitive.
     """
     # i18n: "keyword" is a keyword
     kw = encoding.lower(getstring(x, _("keyword requires a string")))
 
     def matches(r):
         c = repo[r]
         return any(kw in encoding.lower(t)
                    for t in c.files() + [c.user(), c.description()])
 
     return subset.filter(matches, condrepr=('<keyword %r>', kw))
 
 @predicate('limit(set[, n[, offset]])', safe=True)
 def limit(repo, subset, x):
     """First n members of set, defaulting to 1, starting from offset.
     """
     args = getargsdict(x, 'limit', 'set n offset')
     if 'set' not in args:
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit requires one to three arguments"))
     try:
         lim, ofs = 1, 0
         if 'n' in args:
             # i18n: "limit" is a keyword
             lim = int(getstring(args['n'], _("limit requires a number")))
         if 'offset' in args:
             # i18n: "limit" is a keyword
             ofs = int(getstring(args['offset'], _("limit requires a number")))
         if ofs < 0:
             raise error.ParseError(_("negative offset"))
     except (TypeError, ValueError):
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit expects a number"))
     os = getset(repo, fullreposet(repo), args['set'])
     result = []
     it = iter(os)
     for x in xrange(ofs):
         y = next(it, None)
         if y is None:
             break
     for x in xrange(lim):
         y = next(it, None)
         if y is None:
             break
         elif y in subset:
             result.append(y)
     return baseset(result, datarepr=('<limit n=%d, offset=%d, %r, %r>',
                                      lim, ofs, subset, os))
 
 @predicate('last(set, [n])', safe=True)
 def last(repo, subset, x):
     """Last n members of set, defaulting to 1.
     """
     # i18n: "last" is a keyword
     l = getargs(x, 1, 2, _("last requires one or two arguments"))
     try:
         lim = 1
         if len(l) == 2:
             # i18n: "last" is a keyword
             lim = int(getstring(l[1], _("last requires a number")))
     except (TypeError, ValueError):
         # i18n: "last" is a keyword
         raise error.ParseError(_("last expects a number"))
     os = getset(repo, fullreposet(repo), l[0])
     os.reverse()
     result = []
     it = iter(os)
     for x in xrange(lim):
         y = next(it, None)
         if y is None:
             break
         elif y in subset:
             result.append(y)
     return baseset(result, datarepr=('<last n=%d, %r, %r>', lim, subset, os))
 
 @predicate('max(set)', safe=True)
 def maxrev(repo, subset, x):
     """Changeset with highest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.max()
         if m in subset:
             return baseset([m], datarepr=('<max %r, %r>', subset, os))
     except ValueError:
         # os.max() throws a ValueError when the collection is empty.
         # Same as python's max().
         pass
     return baseset(datarepr=('<max %r, %r>', subset, os))
 
 @predicate('merge()', safe=True)
 def merge(repo, subset, x):
     """Changeset is a merge changeset.
     """
     # i18n: "merge" is a keyword
     getargs(x, 0, 0, _("merge takes no arguments"))
     cl = repo.changelog
     return subset.filter(lambda r: cl.parentrevs(r)[1] != -1,
                          condrepr='<merge>')
 
 @predicate('branchpoint()', safe=True)
 def branchpoint(repo, subset, x):
     """Changesets with more than one child.
     """
     # i18n: "branchpoint" is a keyword
     getargs(x, 0, 0, _("branchpoint takes no arguments"))
     cl = repo.changelog
     if not subset:
         return baseset()
     # XXX this should be 'parentset.min()' assuming 'parentset' is a smartset
     # (and if it is not, it should.)
     baserev = min(subset)
     parentscount = [0]*(len(repo) - baserev)
     for r in cl.revs(start=baserev + 1):
         for p in cl.parentrevs(r):
             if p >= baserev:
                 parentscount[p - baserev] += 1
     return subset.filter(lambda r: parentscount[r - baserev] > 1,
                          condrepr='<branchpoint>')
 
 @predicate('min(set)', safe=True)
 def minrev(repo, subset, x):
     """Changeset with lowest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.min()
         if m in subset:
             return baseset([m], datarepr=('<min %r, %r>', subset, os))
     except ValueError:
         # os.min() throws a ValueError when the collection is empty.
         # Same as python's min().
         pass
     return baseset(datarepr=('<min %r, %r>', subset, os))
 
 @predicate('modifies(pattern)', safe=True)
 def modifies(repo, subset, x):
     """Changesets modifying files matched by pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "modifies" is a keyword
     pat = getstring(x, _("modifies requires a pattern"))
     return checkstatus(repo, subset, pat, 0)
 
 @predicate('named(namespace)')
 def named(repo, subset, x):
     """The changesets in a given namespace.
 
     If `namespace` starts with `re:`, the remainder of the string is treated as
     a regular expression. To match a namespace that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "named" is a keyword
     args = getargs(x, 1, 1, _('named requires a namespace argument'))
 
     ns = getstring(args[0],
                    # i18n: "named" is a keyword
                    _('the argument to named must be a string'))
     kind, pattern, matcher = util.stringmatcher(ns)
     namespaces = set()
     if kind == 'literal':
         if pattern not in repo.names:
             raise error.RepoLookupError(_("namespace '%s' does not exist")
                                         % ns)
         namespaces.add(repo.names[pattern])
     else:
         for name, ns in repo.names.iteritems():
             if matcher(name):
                 namespaces.add(ns)
         if not namespaces:
             raise error.RepoLookupError(_("no namespace exists"
                                           " that match '%s'") % pattern)
 
     names = set()
     for ns in namespaces:
         for name in ns.listnames(repo):
             if name not in ns.deprecated:
                 names.update(repo[n].rev() for n in ns.nodes(repo, name))
 
     names -= set([node.nullrev])
     return subset & names
 
 @predicate('id(string)', safe=True)
 def node_(repo, subset, x):
     """Revision non-ambiguously specified by the given hex string prefix.
     """
     # i18n: "id" is a keyword
     l = getargs(x, 1, 1, _("id requires one argument"))
     # i18n: "id" is a keyword
     n = getstring(l[0], _("id requires a string"))
     if len(n) == 40:
         try:
             rn = repo.changelog.rev(node.bin(n))
         except (LookupError, TypeError):
             rn = None
     else:
         rn = None
         pm = repo.changelog._partialmatch(n)
         if pm is not None:
             rn = repo.changelog.rev(pm)
 
     if rn is None:
         return baseset()
     result = baseset([rn])
     return result & subset
 
 @predicate('obsolete()', safe=True)
 def obsolete(repo, subset, x):
     """Mutable changeset with a newer version."""
     # i18n: "obsolete" is a keyword
     getargs(x, 0, 0, _("obsolete takes no arguments"))
     obsoletes = obsmod.getrevs(repo, 'obsolete')
     return subset & obsoletes
 
 @predicate('only(set, [set])', safe=True)
 def only(repo, subset, x):
     """Changesets that are ancestors of the first set that are not ancestors
     of any other head in the repo. If a second set is specified, the result
     is ancestors of the first set that are not ancestors of the second set
     (i.e. ::<set1> - ::<set2>).
     """
     cl = repo.changelog
     # i18n: "only" is a keyword
     args = getargs(x, 1, 2, _('only takes one or two arguments'))
     include = getset(repo, fullreposet(repo), args[0])
     if len(args) == 1:
         if not include:
             return baseset()
 
         descendants = set(_revdescendants(repo, include, False))
         exclude = [rev for rev in cl.headrevs()
             if not rev in descendants and not rev in include]
     else:
         exclude = getset(repo, fullreposet(repo), args[1])
 
     results = set(cl.findmissingrevs(common=exclude, heads=include))
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & results
 
 @predicate('origin([set])', safe=True)
 def origin(repo, subset, x):
     """
     Changesets that were specified as a source for the grafts, transplants or
     rebases that created the given revisions.  Omitting the optional set is the
     same as passing all().  If a changeset created by these operations is itself
     specified as a source for one of these operations, only the source changeset
     for the first operation is selected.
     """
     if x is not None:
         dests = getset(repo, fullreposet(repo), x)
     else:
         dests = fullreposet(repo)
 
     def _firstsrc(rev):
         src = _getrevsource(repo, rev)
         if src is None:
             return None
 
         while True:
             prev = _getrevsource(repo, src)
 
             if prev is None:
                 return src
             src = prev
 
     o = set([_firstsrc(r) for r in dests])
     o -= set([None])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & o
 
 @predicate('outgoing([path])', safe=True)
 def outgoing(repo, subset, x):
     """Changesets not found in the specified destination repository, or the
     default push location.
     """
     # Avoid cycles.
     from . import (
         discovery,
         hg,
     )
     # i18n: "outgoing" is a keyword
     l = getargs(x, 0, 1, _("outgoing takes one or no arguments"))
     # i18n: "outgoing" is a keyword
     dest = l and getstring(l[0], _("outgoing requires a repository path")) or ''
     dest = repo.ui.expandpath(dest or 'default-push', dest or 'default')
     dest, branches = hg.parseurl(dest)
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     repo.ui.pushbuffer()
     outgoing = discovery.findcommonoutgoing(repo, other, onlyheads=revs)
     repo.ui.popbuffer()
     cl = repo.changelog
     o = set([cl.rev(r) for r in outgoing.missing])
     return subset & o
 
 @predicate('p1([set])', safe=True)
 def p1(repo, subset, x):
     """First parent of changesets in set, or the working directory.
     """
     if x is None:
         p = repo[x].p1().rev()
         if p >= 0:
             return subset & baseset([p])
         return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         ps.add(cl.parentrevs(r)[0])
     ps -= set([node.nullrev])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & ps
 
 @predicate('p2([set])', safe=True)
 def p2(repo, subset, x):
     """Second parent of changesets in set, or the working directory.
     """
     if x is None:
         ps = repo[x].parents()
         try:
             p = ps[1].rev()
             if p >= 0:
                 return subset & baseset([p])
             return baseset()
         except IndexError:
             return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         ps.add(cl.parentrevs(r)[1])
     ps -= set([node.nullrev])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & ps
 
 @predicate('parents([set])', safe=True)
 def parents(repo, subset, x):
     """
     The set of all parents for all changesets in set, or the working directory.
     """
     if x is None:
         ps = set(p.rev() for p in repo[x].parents())
     else:
         ps = set()
         cl = repo.changelog
         up = ps.update
         parentrevs = cl.parentrevs
         for r in getset(repo, fullreposet(repo), x):
             if r == node.wdirrev:
                 up(p.rev() for p in repo[r].parents())
             else:
                 up(parentrevs(r))
     ps -= set([node.nullrev])
     return subset & ps
 
 def _phase(repo, subset, target):
     """helper to select all rev in phase <target>"""
     repo._phasecache.loadphaserevs(repo) # ensure phase's sets are loaded
     if repo._phasecache._phasesets:
         s = repo._phasecache._phasesets[target] - repo.changelog.filteredrevs
         s = baseset(s)
         s.sort() # set are non ordered, so we enforce ascending
         return subset & s
     else:
         phase = repo._phasecache.phase
         condition = lambda r: phase(repo, r) == target
         return subset.filter(condition, condrepr=('<phase %r>', target),
                              cache=False)
 
 @predicate('draft()', safe=True)
 def draft(repo, subset, x):
     """Changeset in draft phase."""
     # i18n: "draft" is a keyword
     getargs(x, 0, 0, _("draft takes no arguments"))
     target = phases.draft
     return _phase(repo, subset, target)
 
 @predicate('secret()', safe=True)
 def secret(repo, subset, x):
     """Changeset in secret phase."""
     # i18n: "secret" is a keyword
     getargs(x, 0, 0, _("secret takes no arguments"))
     target = phases.secret
     return _phase(repo, subset, target)
 
 def parentspec(repo, subset, x, n):
     """``set^0``
     The set.
     ``set^1`` (or ``set^``), ``set^2``
     First or second parent, respectively, of all changesets in set.
     """
     try:
         n = int(n[1])
         if n not in (0, 1, 2):
             raise ValueError
     except (TypeError, ValueError):
         raise error.ParseError(_("^ expects a number 0, 1, or 2"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         if n == 0:
             ps.add(r)
         elif n == 1:
             ps.add(cl.parentrevs(r)[0])
         elif n == 2:
             parents = cl.parentrevs(r)
             if len(parents) > 1:
                 ps.add(parents[1])
     return subset & ps
 
 @predicate('present(set)', safe=True)
 def present(repo, subset, x):
     """An empty set, if any revision in set isn't found; otherwise,
     all revisions in set.
 
     If any of specified revisions is not present in the local repository,
     the query is normally aborted. But this predicate allows the query
     to continue even in such cases.
     """
     try:
         return getset(repo, subset, x)
     except error.RepoLookupError:
         return baseset()
 
 # for internal use
 @predicate('_notpublic', safe=True)
 def _notpublic(repo, subset, x):
     getargs(x, 0, 0, "_notpublic takes no arguments")
     repo._phasecache.loadphaserevs(repo) # ensure phase's sets are loaded
     if repo._phasecache._phasesets:
         s = set()
         for u in repo._phasecache._phasesets[1:]:
             s.update(u)
         s = baseset(s - repo.changelog.filteredrevs)
         s.sort()
         return subset & s
     else:
         phase = repo._phasecache.phase
         target = phases.public
         condition = lambda r: phase(repo, r) != target
         return subset.filter(condition, condrepr=('<phase %r>', target),
                              cache=False)
 
 @predicate('public()', safe=True)
 def public(repo, subset, x):
     """Changeset in public phase."""
     # i18n: "public" is a keyword
     getargs(x, 0, 0, _("public takes no arguments"))
     phase = repo._phasecache.phase
     target = phases.public
     condition = lambda r: phase(repo, r) == target
     return subset.filter(condition, condrepr=('<phase %r>', target),
                          cache=False)
 
 @predicate('remote([id [,path]])', safe=True)
 def remote(repo, subset, x):
     """Local revision that corresponds to the given identifier in a
     remote repository, if present. Here, the '.' identifier is a
     synonym for the current local branch.
     """
 
     from . import hg # avoid start-up nasties
     # i18n: "remote" is a keyword
     l = getargs(x, 0, 2, _("remote takes zero, one, or two arguments"))
 
     q = '.'
     if len(l) > 0:
     # i18n: "remote" is a keyword
         q = getstring(l[0], _("remote requires a string id"))
     if q == '.':
         q = repo['.'].branch()
 
     dest = ''
     if len(l) > 1:
         # i18n: "remote" is a keyword
         dest = getstring(l[1], _("remote requires a repository path"))
     dest = repo.ui.expandpath(dest or 'default')
     dest, branches = hg.parseurl(dest)
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     n = other.lookup(q)
     if n in repo:
         r = repo[n].rev()
         if r in subset:
             return baseset([r])
     return baseset()
 
 @predicate('removes(pattern)', safe=True)
 def removes(repo, subset, x):
     """Changesets which remove files matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "removes" is a keyword
     pat = getstring(x, _("removes requires a pattern"))
     return checkstatus(repo, subset, pat, 2)
 
 @predicate('rev(number)', safe=True)
 def rev(repo, subset, x):
     """Revision with the given numeric identifier.
     """
     # i18n: "rev" is a keyword
     l = getargs(x, 1, 1, _("rev requires one argument"))
     try:
         # i18n: "rev" is a keyword
         l = int(getstring(l[0], _("rev requires a number")))
     except (TypeError, ValueError):
         # i18n: "rev" is a keyword
         raise error.ParseError(_("rev expects a number"))
     if l not in repo.changelog and l != node.nullrev:
         return baseset()
     return subset & baseset([l])
 
 @predicate('matching(revision [, field])', safe=True)
 def matching(repo, subset, x):
     """Changesets in which a given set of fields match the set of fields in the
     selected revision or set.
 
     To match more than one field pass the list of fields to match separated
     by spaces (e.g. ``author description``).
 
     Valid fields are most regular revision fields and some special fields.
 
     Regular revision fields are ``description``, ``author``, ``branch``,
     ``date``, ``files``, ``phase``, ``parents``, ``substate``, ``user``
     and ``diff``.
     Note that ``author`` and ``user`` are synonyms. ``diff`` refers to the
     contents of the revision. Two revisions matching their ``diff`` will
     also match their ``files``.
 
     Special fields are ``summary`` and ``metadata``:
     ``summary`` matches the first line of the description.
     ``metadata`` is equivalent to matching ``description user date``
     (i.e. it matches the main metadata fields).
 
     ``metadata`` is the default field which is used when no fields are
     specified. You can match more than one field at a time.
     """
     # i18n: "matching" is a keyword
     l = getargs(x, 1, 2, _("matching takes 1 or 2 arguments"))
 
     revs = getset(repo, fullreposet(repo), l[0])
 
     fieldlist = ['metadata']
     if len(l) > 1:
             fieldlist = getstring(l[1],
                 # i18n: "matching" is a keyword
                 _("matching requires a string "
                 "as its second argument")).split()
 
     # Make sure that there are no repeated fields,
     # expand the 'special' 'metadata' field type
     # and check the 'files' whenever we check the 'diff'
     fields = []
     for field in fieldlist:
         if field == 'metadata':
             fields += ['user', 'description', 'date']
         elif field == 'diff':
             # a revision matching the diff must also match the files
             # since matching the diff is very costly, make sure to
             # also match the files first
             fields += ['files', 'diff']
         else:
             if field == 'author':
                 field = 'user'
             fields.append(field)
     fields = set(fields)
     if 'summary' in fields and 'description' in fields:
         # If a revision matches its description it also matches its summary
         fields.discard('summary')
 
     # We may want to match more than one field
     # Not all fields take the same amount of time to be matched
     # Sort the selected fields in order of increasing matching cost
     fieldorder = ['phase', 'parents', 'user', 'date', 'branch', 'summary',
         'files', 'description', 'substate', 'diff']
     def fieldkeyfunc(f):
         try:
             return fieldorder.index(f)
         except ValueError:
             # assume an unknown field is very costly
             return len(fieldorder)
     fields = list(fields)
     fields.sort(key=fieldkeyfunc)
 
     # Each field will be matched with its own "getfield" function
     # which will be added to the getfieldfuncs array of functions
     getfieldfuncs = []
     _funcs = {
         'user': lambda r: repo[r].user(),
         'branch': lambda r: repo[r].branch(),
         'date': lambda r: repo[r].date(),
         'description': lambda r: repo[r].description(),
         'files': lambda r: repo[r].files(),
         'parents': lambda r: repo[r].parents(),
         'phase': lambda r: repo[r].phase(),
         'substate': lambda r: repo[r].substate,
         'summary': lambda r: repo[r].description().splitlines()[0],
         'diff': lambda r: list(repo[r].diff(git=True),)
     }
     for info in fields:
         getfield = _funcs.get(info, None)
         if getfield is None:
             raise error.ParseError(
                 # i18n: "matching" is a keyword
                 _("unexpected field name passed to matching: %s") % info)
         getfieldfuncs.append(getfield)
     # convert the getfield array of functions into a "getinfo" function
     # which returns an array of field values (or a single value if there
     # is only one field to match)
     getinfo = lambda r: [f(r) for f in getfieldfuncs]
 
     def matches(x):
         for rev in revs:
             target = getinfo(rev)
             match = True
             for n, f in enumerate(getfieldfuncs):
                 if target[n] != f(x):
                     match = False
             if match:
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<matching%r %r>', fields, revs))
 
 @predicate('reverse(set)', safe=True)
 def reverse(repo, subset, x):
     """Reverse order of set.
     """
     l = getset(repo, subset, x)
     l.reverse()
     return l
 
 @predicate('roots(set)', safe=True)
 def roots(repo, subset, x):
     """Changesets in set with no parent changeset in set.
     """
     s = getset(repo, fullreposet(repo), x)
     parents = repo.changelog.parentrevs
     def filter(r):
         for p in parents(r):
             if 0 <= p and p in s:
                 return False
         return True
     return subset & s.filter(filter, condrepr='<roots>')
 
 @predicate('sort(set[, [-]key...])', safe=True)
 def sort(repo, subset, x):
     """Sort set by keys. The default sort order is ascending, specify a key
     as ``-key`` to sort in descending order.
 
     The keys can be:
 
     - ``rev`` for the revision number,
     - ``branch`` for the branch name,
     - ``desc`` for the commit message (description),
     - ``user`` for user name (``author`` can be used as an alias),
     - ``date`` for the commit date
     """
     # i18n: "sort" is a keyword
     l = getargs(x, 1, 2, _("sort requires one or two arguments"))
     keys = "rev"
     if len(l) == 2:
         # i18n: "sort" is a keyword
         keys = getstring(l[1], _("sort spec must be a string"))
 
     s = l[0]
     keys = keys.split()
     revs = getset(repo, subset, s)
     if keys == ["rev"]:
         revs.sort()
         return revs
     elif keys == ["-rev"]:
         revs.sort(reverse=True)
         return revs
     # sort() is guaranteed to be stable
     ctxs = [repo[r] for r in revs]
     for k in reversed(keys):
         if k == 'rev':
             ctxs.sort(key=lambda c: c.rev())
         elif k == '-rev':
             ctxs.sort(key=lambda c: c.rev(), reverse=True)
         elif k == 'branch':
             ctxs.sort(key=lambda c: c.branch())
         elif k == '-branch':
             ctxs.sort(key=lambda c: c.branch(), reverse=True)
         elif k == 'desc':
             ctxs.sort(key=lambda c: c.description())
         elif k == '-desc':
             ctxs.sort(key=lambda c: c.description(), reverse=True)
         elif k in 'user author':
             ctxs.sort(key=lambda c: c.user())
         elif k in '-user -author':
             ctxs.sort(key=lambda c: c.user(), reverse=True)
         elif k == 'date':
             ctxs.sort(key=lambda c: c.date()[0])
         elif k == '-date':
             ctxs.sort(key=lambda c: c.date()[0], reverse=True)
         else:
             raise error.ParseError(_("unknown sort key %r") % k)
     return baseset([c.rev() for c in ctxs])
 
 @predicate('subrepo([pattern])')
 def subrepo(repo, subset, x):
     """Changesets that add, modify or remove the given subrepo.  If no subrepo
     pattern is named, any subrepo changes are returned.
     """
     # i18n: "subrepo" is a keyword
     args = getargs(x, 0, 1, _('subrepo takes at most one argument'))
     pat = None
     if len(args) != 0:
         pat = getstring(args[0], _("subrepo requires a pattern"))
 
     m = matchmod.exact(repo.root, repo.root, ['.hgsubstate'])
 
     def submatches(names):
         k, p, m = util.stringmatcher(pat)
         for name in names:
             if m(name):
                 yield name
 
     def matches(x):
         c = repo[x]
         s = repo.status(c.p1().node(), c.node(), match=m)
 
         if pat is None:
             return s.added or s.modified or s.removed
 
         if s.added:
             return any(submatches(c.substate.keys()))
 
         if s.modified:
             subs = set(c.p1().substate.keys())
             subs.update(c.substate.keys())
 
             for path in submatches(subs):
                 if c.p1().substate.get(path) != c.substate.get(path):
                     return True
 
         if s.removed:
             return any(submatches(c.p1().substate.keys()))
 
         return False
 
     return subset.filter(matches, condrepr=('<subrepo %r>', pat))
 
 def _substringmatcher(pattern):
     kind, pattern, matcher = util.stringmatcher(pattern)
     if kind == 'literal':
         matcher = lambda s: pattern in s
     return kind, pattern, matcher
 
 @predicate('tag([name])', safe=True)
 def tag(repo, subset, x):
     """The specified tag by name, or all tagged revisions if no name is given.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a tag that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "tag" is a keyword
     args = getargs(x, 0, 1, _("tag takes one or no arguments"))
     cl = repo.changelog
     if args:
         pattern = getstring(args[0],
                             # i18n: "tag" is a keyword
                             _('the argument to tag must be a string'))
         kind, pattern, matcher = util.stringmatcher(pattern)
         if kind == 'literal':
             # avoid resolving all tags
             tn = repo._tagscache.tags.get(pattern, None)
             if tn is None:
                 raise error.RepoLookupError(_("tag '%s' does not exist")
                                             % pattern)
             s = set([repo[tn].rev()])
         else:
             s = set([cl.rev(n) for t, n in repo.tagslist() if matcher(t)])
     else:
         s = set([cl.rev(n) for t, n in repo.tagslist() if t != 'tip'])
     return subset & s
 
 @predicate('tagged', safe=True)
 def tagged(repo, subset, x):
     return tag(repo, subset, x)
 
 @predicate('unstable()', safe=True)
 def unstable(repo, subset, x):
     """Non-obsolete changesets with obsolete ancestors.
     """
     # i18n: "unstable" is a keyword
     getargs(x, 0, 0, _("unstable takes no arguments"))
     unstables = obsmod.getrevs(repo, 'unstable')
     return subset & unstables
 
 
 @predicate('user(string)', safe=True)
 def user(repo, subset, x):
     """User name contains string. The match is case-insensitive.
 
     If `string` starts with `re:`, the remainder of the string is treated as
     a regular expression. To match a user that actually contains `re:`, use
     the prefix `literal:`.
     """
     return author(repo, subset, x)
 
 # experimental
 @predicate('wdir', safe=True)
 def wdir(repo, subset, x):
     # i18n: "wdir" is a keyword
     getargs(x, 0, 0, _("wdir takes no arguments"))
     if node.wdirrev in subset or isinstance(subset, fullreposet):
         return baseset([node.wdirrev])
     return baseset()
 
 # for internal use
 @predicate('_list', safe=True)
 def _list(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     # remove duplicates here. it's difficult for caller to deduplicate sets
     # because different symbols can point to the same rev.
     cl = repo.changelog
     ls = []
     seen = set()
     for t in s.split('\0'):
         try:
             # fast path for integer revision
             r = int(t)
             if str(r) != t or r not in cl:
                 raise ValueError
             revs = [r]
         except ValueError:
             revs = stringset(repo, subset, t)
 
         for r in revs:
             if r in seen:
                 continue
             if (r in subset
                 or r == node.nullrev and isinstance(subset, fullreposet)):
                 ls.append(r)
             seen.add(r)
     return baseset(ls)
 
 # for internal use
 @predicate('_intlist', safe=True)
 def _intlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     ls = [int(r) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 # for internal use
 @predicate('_hexlist', safe=True)
 def _hexlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     cl = repo.changelog
     ls = [cl.rev(node.bin(r)) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 methods = {
     "range": rangeset,
     "dagrange": dagrange,
     "string": stringset,
     "symbol": stringset,
     "and": andset,
     "or": orset,
     "not": notset,
     "difference": differenceset,
     "list": listset,
     "keyvalue": keyvaluepair,
     "func": func,
     "ancestor": ancestorspec,
     "parent": parentspec,
     "parentpost": p1,
 }
 
 def _matchonly(revs, bases):
     """
     >>> f = lambda *args: _matchonly(*map(parse, args))
     >>> f('ancestors(A)', 'not ancestors(B)')
     ('list', ('symbol', 'A'), ('symbol', 'B'))
     """
     if (revs is not None
         and revs[0] == 'func'
         and getstring(revs[1], _('not a symbol')) == 'ancestors'
         and bases is not None
         and bases[0] == 'not'
         and bases[1][0] == 'func'
         and getstring(bases[1][1], _('not a symbol')) == 'ancestors'):
         return ('list', revs[2], bases[1][2])
 
 def _optimize(x, small):
     if x is None:
         return 0, x
 
     smallbonus = 1
     if small:
         smallbonus = .5
 
     op = x[0]
     if op == 'minus':
         return _optimize(('and', x[1], ('not', x[2])), small)
     elif op == 'only':
         t = ('func', ('symbol', 'only'), ('list', x[1], x[2]))
         return _optimize(t, small)
     elif op == 'onlypost':
         return _optimize(('func', ('symbol', 'only'), x[1]), small)
     elif op == 'dagrangepre':
         return _optimize(('func', ('symbol', 'ancestors'), x[1]), small)
     elif op == 'dagrangepost':
         return _optimize(('func', ('symbol', 'descendants'), x[1]), small)
     elif op == 'rangeall':
         return _optimize(('range', ('string', '0'), ('string', 'tip')), small)
     elif op == 'rangepre':
         return _optimize(('range', ('string', '0'), x[1]), small)
     elif op == 'rangepost':
         return _optimize(('range', x[1], ('string', 'tip')), small)
     elif op == 'negate':
         s = getstring(x[1], _("can't negate that"))
         return _optimize(('string', '-' + s), small)
     elif op in 'string symbol negate':
         return smallbonus, x # single revisions are small
     elif op == 'and':
         wa, ta = _optimize(x[1], True)
         wb, tb = _optimize(x[2], True)
         w = min(wa, wb)
 
         # (::x and not ::y)/(not ::y and ::x) have a fast path
         tm = _matchonly(ta, tb) or _matchonly(tb, ta)
         if tm:
             return w, ('func', ('symbol', 'only'), tm)
 
         if tb is not None and tb[0] == 'not':
             return wa, ('difference', ta, tb[1])
 
         if wa > wb:
             return w, (op, tb, ta)
         return w, (op, ta, tb)
     elif op == 'or':
         # fast path for machine-generated expression, that is likely to have
         # lots of trivial revisions: 'a + b + c()' to '_list(a b) + c()'
         ws, ts, ss = [], [], []
         def flushss():
             if not ss:
                 return
             if len(ss) == 1:
                 w, t = ss[0]
             else:
                 s = '\0'.join(t[1] for w, t in ss)
                 y = ('func', ('symbol', '_list'), ('string', s))
                 w, t = _optimize(y, False)
             ws.append(w)
             ts.append(t)
             del ss[:]
         for y in x[1:]:
             w, t = _optimize(y, False)
             if t is not None and (t[0] == 'string' or t[0] == 'symbol'):
                 ss.append((w, t))
                 continue
             flushss()
             ws.append(w)
             ts.append(t)
         flushss()
         if len(ts) == 1:
             return ws[0], ts[0] # 'or' operation is fully optimized out
         # we can't reorder trees by weight because it would change the order.
         # ("sort(a + b)" == "sort(b + a)", but "a + b" != "b + a")
         #   ts = tuple(t for w, t in sorted(zip(ws, ts), key=lambda wt: wt[0]))
         return max(ws), (op,) + tuple(ts)
     elif op == 'not':
         # Optimize not public() to _notpublic() because we have a fast version
         if x[1] == ('func', ('symbol', 'public'), None):
             newsym = ('func', ('symbol', '_notpublic'), None)
             o = _optimize(newsym, not small)
             return o[0], o[1]
         else:
             o = _optimize(x[1], not small)
             return o[0], (op, o[1])
     elif op == 'parentpost':
         o = _optimize(x[1], small)
         return o[0], (op, o[1])
     elif op == 'group':
         return _optimize(x[1], small)
     elif op in 'dagrange range parent ancestorspec':
         if op == 'parent':
             # x^:y means (x^) : y, not x ^ (:y)
             post = ('parentpost', x[1])
             if x[2][0] == 'dagrangepre':
                 return _optimize(('dagrange', post, x[2][1]), small)
             elif x[2][0] == 'rangepre':
                 return _optimize(('range', post, x[2][1]), small)
 
         wa, ta = _optimize(x[1], small)
         wb, tb = _optimize(x[2], small)
         return wa + wb, (op, ta, tb)
     elif op == 'list':
         ws, ts = zip(*(_optimize(y, small) for y in x[1:]))
         return sum(ws), (op,) + ts
     elif op == 'func':
         f = getstring(x[1], _("not a symbol"))
         wa, ta = _optimize(x[2], small)
         if f in ("author branch closed date desc file grep keyword "
                  "outgoing user"):
             w = 10 # slow
         elif f in "modifies adds removes":
             w = 30 # slower
         elif f == "contains":
             w = 100 # very slow
         elif f == "ancestor":
             w = 1 * smallbonus
         elif f in "reverse limit first _intlist":
             w = 0
         elif f in "sort":
             w = 10 # assume most sorts look at changelog
         else:
             w = 1
         return w + wa, (op, x[1], ta)
     return 1, x
 
 def optimize(tree):
     _weight, newtree = _optimize(tree, small=True)
     return newtree
 
 # the set of valid characters for the initial letter of symbols in
 # alias declarations and definitions
 _aliassyminitletters = set(c for c in [chr(i) for i in xrange(256)]
                            if c.isalnum() or c in '._@$' or ord(c) > 127)
 
 def _parsewith(spec, lookup=None, syminitletters=None):
     """Generate a parse tree of given spec with given tokenizing options
 
     >>> _parsewith('foo($1)', syminitletters=_aliassyminitletters)
     ('func', ('symbol', 'foo'), ('symbol', '$1'))
     >>> _parsewith('$1')
     Traceback (most recent call last):
       ...
     ParseError: ("syntax error in revset '$1'", 0)
     >>> _parsewith('foo bar')
     Traceback (most recent call last):
       ...
     ParseError: ('invalid token', 4)
     """
     p = parser.parser(elements)
     tree, pos = p.parse(tokenize(spec, lookup=lookup,
                                  syminitletters=syminitletters))
     if pos != len(spec):
         raise error.ParseError(_('invalid token'), pos)
     return parser.simplifyinfixops(tree, ('list', 'or'))
 
 class _aliasrules(parser.basealiasrules):
     """Parsing and expansion rule set of revset aliases"""
     _section = _('revset alias')
 
     @staticmethod
     def _parse(spec):
         """Parse alias declaration/definition ``spec``
 
         This allows symbol names to use also ``$`` as an initial letter
         (for backward compatibility), and callers of this function should
         examine whether ``$`` is used also for unexpected symbols or not.
         """
         return _parsewith(spec, syminitletters=_aliassyminitletters)
 
     @staticmethod
     def _trygetfunc(tree):
         if tree[0] == 'func' and tree[1][0] == 'symbol':
             return tree[1][1], getlist(tree[2])
 
 def expandaliases(ui, tree, showwarning=None):
     aliases = _aliasrules.buildmap(ui.configitems('revsetalias'))
     tree = _aliasrules.expand(aliases, tree)
     if showwarning:
         # warn about problematic (but not referred) aliases
         for name, alias in sorted(aliases.iteritems()):
             if alias.error and not alias.warned:
                 showwarning(_('warning: %s\n') % (alias.error))
                 alias.warned = True
     return tree
 
 def foldconcat(tree):
     """Fold elements to be concatenated by `##`
     """
     if not isinstance(tree, tuple) or tree[0] in ('string', 'symbol'):
         return tree
     if tree[0] == '_concat':
         pending = [tree]
         l = []
         while pending:
             e = pending.pop()
             if e[0] == '_concat':
                 pending.extend(reversed(e[1:]))
             elif e[0] in ('string', 'symbol'):
                 l.append(e[1])
             else:
                 msg = _("\"##\" can't concatenate \"%s\" element") % (e[0])
                 raise error.ParseError(msg)
         return ('string', ''.join(l))
     else:
         return tuple(foldconcat(t) for t in tree)
 
 def parse(spec, lookup=None):
     return _parsewith(spec, lookup=lookup)
 
 def posttreebuilthook(tree, repo):
     # hook for extensions to execute code on the optimized tree
     pass
 
 def match(ui, spec, repo=None):
     if not spec:
         raise error.ParseError(_("empty query"))
     lookup = None
     if repo:
         lookup = repo.__contains__
     tree = parse(spec, lookup)
     return _makematcher(ui, tree, repo)
 
 def matchany(ui, specs, repo=None):
     """Create a matcher that will include any revisions matching one of the
     given specs"""
     if not specs:
         def mfunc(repo, subset=None):
             return baseset()
         return mfunc
     if not all(specs):
         raise error.ParseError(_("empty query"))
     lookup = None
     if repo:
         lookup = repo.__contains__
     if len(specs) == 1:
         tree = parse(specs[0], lookup)
     else:
         tree = ('or',) + tuple(parse(s, lookup) for s in specs)
     return _makematcher(ui, tree, repo)
 
 def _makematcher(ui, tree, repo):
     if ui:
         tree = expandaliases(ui, tree, showwarning=ui.warn)
     tree = foldconcat(tree)
     tree = optimize(tree)
     posttreebuilthook(tree, repo)
     def mfunc(repo, subset=None):
         if subset is None:
             subset = fullreposet(repo)
         if util.safehasattr(subset, 'isascending'):
             result = getset(repo, subset, tree)
         else:
             result = getset(repo, baseset(subset), tree)
         return result
     return mfunc
 
 def formatspec(expr, *args):
     '''
     This is a convenience function for using revsets internally, and
     escapes arguments appropriately. Aliases are intentionally ignored
     so that intended expression behavior isn't accidentally subverted.
 
     Supported arguments:
 
     %r = revset expression, parenthesized
     %d = int(arg), no quoting
     %s = string(arg), escaped and single-quoted
     %b = arg.branch(), escaped and single-quoted
     %n = hex(arg), single-quoted
     %% = a literal '%'
 
     Prefixing the type with 'l' specifies a parenthesized list of that type.
 
     >>> formatspec('%r:: and %lr', '10 or 11', ("this()", "that()"))
     '(10 or 11):: and ((this()) or (that()))'
     >>> formatspec('%d:: and not %d::', 10, 20)
     '10:: and not 20::'
     >>> formatspec('%ld or %ld', [], [1])
     "_list('') or 1"
     >>> formatspec('keyword(%s)', 'foo\\xe9')
     "keyword('foo\\\\xe9')"
     >>> b = lambda: 'default'
     >>> b.branch = b
     >>> formatspec('branch(%b)', b)
     "branch('default')"
     >>> formatspec('root(%ls)', ['a', 'b', 'c', 'd'])
     "root(_list('a\\x00b\\x00c\\x00d'))"
     '''
 
     def quote(s):
         return repr(str(s))
 
     def argtype(c, arg):
         if c == 'd':
             return str(int(arg))
         elif c == 's':
             return quote(arg)
         elif c == 'r':
             parse(arg) # make sure syntax errors are confined
             return '(%s)' % arg
         elif c == 'n':
             return quote(node.hex(arg))
         elif c == 'b':
             return quote(arg.branch())
 
     def listexp(s, t):
         l = len(s)
         if l == 0:
             return "_list('')"
         elif l == 1:
             return argtype(t, s[0])
         elif t == 'd':
             return "_intlist('%s')" % "\0".join(str(int(a)) for a in s)
         elif t == 's':
             return "_list('%s')" % "\0".join(s)
         elif t == 'n':
             return "_hexlist('%s')" % "\0".join(node.hex(a) for a in s)
         elif t == 'b':
             return "_list('%s')" % "\0".join(a.branch() for a in s)
 
         m = l // 2
         return '(%s or %s)' % (listexp(s[:m], t), listexp(s[m:], t))
 
     ret = ''
     pos = 0
     arg = 0
     while pos < len(expr):
         c = expr[pos]
         if c == '%':
             pos += 1
             d = expr[pos]
             if d == '%':
                 ret += d
             elif d in 'dsnbr':
                 ret += argtype(d, args[arg])
                 arg += 1
             elif d == 'l':
                 # a list of some type
                 pos += 1
                 d = expr[pos]
                 ret += listexp(list(args[arg]), d)
                 arg += 1
             else:
                 raise error.Abort('unexpected revspec format character %s' % d)
         else:
             ret += c
         pos += 1
 
     return ret
 
 def prettyformat(tree):
     return parser.prettyformat(tree, ('string', 'symbol'))
 
 def depth(tree):
     if isinstance(tree, tuple):
         return max(map(depth, tree)) + 1
     else:
         return 0
 
 def funcsused(tree):
     if not isinstance(tree, tuple) or tree[0] in ('string', 'symbol'):
         return set()
     else:
         funcs = set()
         for s in tree[1:]:
             funcs |= funcsused(s)
         if tree[0] == 'func':
             funcs.add(tree[1][1])
         return funcs
 
 def _formatsetrepr(r):
     """Format an optional printable representation of a set
 
     ========  =================================
     type(r)   example
     ========  =================================
     tuple     ('<not %r>', other)
     str       '<branch closed>'
     callable  lambda: '<branch %r>' % sorted(b)
     object    other
     ========  =================================
     """
     if r is None:
         return ''
     elif isinstance(r, tuple):
         return r[0] % r[1:]
     elif isinstance(r, str):
         return r
     elif callable(r):
         return r()
     else:
         return repr(r)
 
 class abstractsmartset(object):
 
     def __nonzero__(self):
         """True if the smartset is not empty"""
         raise NotImplementedError()
 
     def __contains__(self, rev):
         """provide fast membership testing"""
         raise NotImplementedError()
 
     def __iter__(self):
         """iterate the set in the order it is supposed to be iterated"""
         raise NotImplementedError()
 
     # Attributes containing a function to perform a fast iteration in a given
     # direction. A smartset can have none, one, or both defined.
     #
     # Default value is None instead of a function returning None to avoid
     # initializing an iterator just for testing if a fast method exists.
     fastasc = None
     fastdesc = None
 
     def isascending(self):
         """True if the set will iterate in ascending order"""
         raise NotImplementedError()
 
     def isdescending(self):
         """True if the set will iterate in descending order"""
         raise NotImplementedError()
 
     @util.cachefunc
     def min(self):
         """return the minimum element in the set"""
         if self.fastasc is not None:
             for r in self.fastasc():
                 return r
             raise ValueError('arg is an empty sequence')
         return min(self)
 
     @util.cachefunc
     def max(self):
         """return the maximum element in the set"""
         if self.fastdesc is not None:
             for r in self.fastdesc():
                 return r
             raise ValueError('arg is an empty sequence')
         return max(self)
 
     def first(self):
         """return the first element in the set (user iteration perspective)
 
         Return None if the set is empty"""
         raise NotImplementedError()
 
     def last(self):
         """return the last element in the set (user iteration perspective)
 
         Return None if the set is empty"""
         raise NotImplementedError()
 
     def __len__(self):
         """return the length of the smartsets
 
         This can be expensive on smartset that could be lazy otherwise."""
         raise NotImplementedError()
 
     def reverse(self):
         """reverse the expected iteration order"""
         raise NotImplementedError()
 
     def sort(self, reverse=True):
         """get the set to iterate in an ascending or descending order"""
         raise NotImplementedError()
 
     def __and__(self, other):
         """Returns a new object with the intersection of the two collections.
 
         This is part of the mandatory API for smartset."""
         if isinstance(other, fullreposet):
             return self
         return self.filter(other.__contains__, condrepr=other, cache=False)
 
     def __add__(self, other):
         """Returns a new object with the union of the two collections.
 
         This is part of the mandatory API for smartset."""
         return addset(self, other)
 
     def __sub__(self, other):
         """Returns a new object with the substraction of the two collections.
 
         This is part of the mandatory API for smartset."""
         c = other.__contains__
         return self.filter(lambda r: not c(r), condrepr=('<not %r>', other),
                            cache=False)
 
     def filter(self, condition, condrepr=None, cache=True):
         """Returns this smartset filtered by condition as a new smartset.
 
         `condition` is a callable which takes a revision number and returns a
         boolean. Optional `condrepr` provides a printable representation of
         the given `condition`.
 
         This is part of the mandatory API for smartset."""
         # builtin cannot be cached. but do not needs to
         if cache and util.safehasattr(condition, 'func_code'):
             condition = util.cachefunc(condition)
         return filteredset(self, condition, condrepr)
 
 class baseset(abstractsmartset):
     """Basic data structure that represents a revset and contains the basic
     operation that it should be able to perform.
 
     Every method in this class should be implemented by any smartset class.
     """
     def __init__(self, data=(), datarepr=None):
         """
         datarepr: a tuple of (format, obj, ...), a function or an object that
                   provides a printable representation of the given data.
         """
         self._ascending = None
         if not isinstance(data, list):
             if isinstance(data, set):
                 self._set = data
                 # set has no order we pick one for stability purpose
                 self._ascending = True
             data = list(data)
         self._list = data
         self._datarepr = datarepr
 
     @util.propertycache
     def _set(self):
         return set(self._list)
 
     @util.propertycache
     def _asclist(self):
         asclist = self._list[:]
         asclist.sort()
         return asclist
 
     def __iter__(self):
         if self._ascending is None:
             return iter(self._list)
         elif self._ascending:
             return iter(self._asclist)
         else:
             return reversed(self._asclist)
 
     def fastasc(self):
         return iter(self._asclist)
 
     def fastdesc(self):
         return reversed(self._asclist)
 
     @util.propertycache
     def __contains__(self):
         return self._set.__contains__
 
     def __nonzero__(self):
         return bool(self._list)
 
     def sort(self, reverse=False):
         self._ascending = not bool(reverse)
 
     def reverse(self):
         if self._ascending is None:
             self._list.reverse()
         else:
             self._ascending = not self._ascending
 
     def __len__(self):
         return len(self._list)
 
     def isascending(self):
         """Returns True if the collection is ascending order, False if not.
 
         This is part of the mandatory API for smartset."""
         if len(self) <= 1:
             return True
         return self._ascending is not None and self._ascending
 
     def isdescending(self):
         """Returns True if the collection is descending order, False if not.
 
         This is part of the mandatory API for smartset."""
         if len(self) <= 1:
             return True
         return self._ascending is not None and not self._ascending
 
     def first(self):
         if self:
             if self._ascending is None:
                 return self._list[0]
             elif self._ascending:
                 return self._asclist[0]
             else:
                 return self._asclist[-1]
         return None
 
     def last(self):
         if self:
             if self._ascending is None:
                 return self._list[-1]
             elif self._ascending:
                 return self._asclist[-1]
             else:
                 return self._asclist[0]
         return None
 
     def __repr__(self):
         d = {None: '', False: '-', True: '+'}[self._ascending]
         s = _formatsetrepr(self._datarepr)
         if not s:
             l = self._list
             # if _list has been built from a set, it might have a different
             # order from one python implementation to another.
             # We fallback to the sorted version for a stable output.
             if self._ascending is not None:
                 l = self._asclist
             s = repr(l)
         return '<%s%s %s>' % (type(self).__name__, d, s)
 
 class filteredset(abstractsmartset):
     """Duck type for baseset class which iterates lazily over the revisions in
     the subset and contains a function which tests for membership in the
     revset
     """
     def __init__(self, subset, condition=lambda x: True, condrepr=None):
         """
         condition: a function that decide whether a revision in the subset
                    belongs to the revset or not.
         condrepr: a tuple of (format, obj, ...), a function or an object that
                   provides a printable representation of the given condition.
         """
         self._subset = subset
         self._condition = condition
         self._condrepr = condrepr
 
     def __contains__(self, x):
         return x in self._subset and self._condition(x)
 
     def __iter__(self):
         return self._iterfilter(self._subset)
 
     def _iterfilter(self, it):
         cond = self._condition
         for x in it:
             if cond(x):
                 yield x
 
     @property
     def fastasc(self):
         it = self._subset.fastasc
         if it is None:
             return None
         return lambda: self._iterfilter(it())
 
     @property
     def fastdesc(self):
         it = self._subset.fastdesc
         if it is None:
             return None
         return lambda: self._iterfilter(it())
 
     def __nonzero__(self):
         fast = self.fastasc
         if fast is None:
             fast = self.fastdesc
         if fast is not None:
             it = fast()
         else:
             it = self
 
         for r in it:
             return True
         return False
 
     def __len__(self):
         # Basic implementation to be changed in future patches.
         # until this gets improved, we use generator expression
         # here, since list compr is free to call __len__ again
         # causing infinite recursion
         l = baseset(r for r in self)
         return len(l)
 
     def sort(self, reverse=False):
         self._subset.sort(reverse=reverse)
 
     def reverse(self):
         self._subset.reverse()
 
     def isascending(self):
         return self._subset.isascending()
 
     def isdescending(self):
         return self._subset.isdescending()
 
     def first(self):
         for x in self:
             return x
         return None
 
     def last(self):
         it = None
         if self.isascending():
             it = self.fastdesc
         elif self.isdescending():
             it = self.fastasc
         if it is not None:
             for x in it():
                 return x
             return None #empty case
         else:
             x = None
             for x in self:
                 pass
             return x
 
     def __repr__(self):
         xs = [repr(self._subset)]
         s = _formatsetrepr(self._condrepr)
         if s:
             xs.append(s)
         return '<%s %s>' % (type(self).__name__, ', '.join(xs))
 
 def _iterordered(ascending, iter1, iter2):
     """produce an ordered iteration from two iterators with the same order
 
     The ascending is used to indicated the iteration direction.
     """
     choice = max
     if ascending:
         choice = min
 
     val1 = None
     val2 = None
     try:
         # Consume both iterators in an ordered way until one is empty
         while True:
             if val1 is None:
-                val1 = iter1.next()
+                val1 = next(iter1)
             if val2 is None:
-                val2 = iter2.next()
+                val2 = next(iter2)
             n = choice(val1, val2)
             yield n
             if val1 == n:
                 val1 = None
             if val2 == n:
                 val2 = None
     except StopIteration:
         # Flush any remaining values and consume the other one
         it = iter2
         if val1 is not None:
             yield val1
             it = iter1
         elif val2 is not None:
             # might have been equality and both are empty
             yield val2
         for val in it:
             yield val
 
 class addset(abstractsmartset):
     """Represent the addition of two sets
 
     Wrapper structure for lazily adding two structures without losing much
     performance on the __contains__ method
 
     If the ascending attribute is set, that means the two structures are
     ordered in either an ascending or descending way. Therefore, we can add
     them maintaining the order by iterating over both at the same time
 
     >>> xs = baseset([0, 3, 2])
     >>> ys = baseset([5, 2, 4])
 
     >>> rs = addset(xs, ys)
     >>> bool(rs), 0 in rs, 1 in rs, 5 in rs, rs.first(), rs.last()
     (True, True, False, True, 0, 4)
     >>> rs = addset(xs, baseset([]))
     >>> bool(rs), 0 in rs, 1 in rs, rs.first(), rs.last()
     (True, True, False, 0, 2)
     >>> rs = addset(baseset([]), baseset([]))
     >>> bool(rs), 0 in rs, rs.first(), rs.last()
     (False, False, None, None)
 
     iterate unsorted:
     >>> rs = addset(xs, ys)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs)  # without _genlist
     [0, 3, 2, 5, 4]
     >>> assert not rs._genlist
     >>> len(rs)
     5
     >>> [x for x in rs]  # with _genlist
     [0, 3, 2, 5, 4]
     >>> assert rs._genlist
 
     iterate ascending:
     >>> rs = addset(xs, ys, ascending=True)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs), list(x for x in rs.fastasc())  # without _asclist
     ([0, 2, 3, 4, 5], [0, 2, 3, 4, 5])
     >>> assert not rs._asclist
     >>> len(rs)
     5
     >>> [x for x in rs], [x for x in rs.fastasc()]
     ([0, 2, 3, 4, 5], [0, 2, 3, 4, 5])
     >>> assert rs._asclist
 
     iterate descending:
     >>> rs = addset(xs, ys, ascending=False)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs), list(x for x in rs.fastdesc())  # without _asclist
     ([5, 4, 3, 2, 0], [5, 4, 3, 2, 0])
     >>> assert not rs._asclist
     >>> len(rs)
     5
     >>> [x for x in rs], [x for x in rs.fastdesc()]
     ([5, 4, 3, 2, 0], [5, 4, 3, 2, 0])
     >>> assert rs._asclist
 
     iterate ascending without fastasc:
     >>> rs = addset(xs, generatorset(ys), ascending=True)
     >>> assert rs.fastasc is None
     >>> [x for x in rs]
     [0, 2, 3, 4, 5]
 
     iterate descending without fastdesc:
     >>> rs = addset(generatorset(xs), ys, ascending=False)
     >>> assert rs.fastdesc is None
     >>> [x for x in rs]
     [5, 4, 3, 2, 0]
     """
     def __init__(self, revs1, revs2, ascending=None):
         self._r1 = revs1
         self._r2 = revs2
         self._iter = None
         self._ascending = ascending
         self._genlist = None
         self._asclist = None
 
     def __len__(self):
         return len(self._list)
 
     def __nonzero__(self):
         return bool(self._r1) or bool(self._r2)
 
     @util.propertycache
     def _list(self):
         if not self._genlist:
             self._genlist = baseset(iter(self))
         return self._genlist
 
     def __iter__(self):
         """Iterate over both collections without repeating elements
 
         If the ascending attribute is not set, iterate over the first one and
         then over the second one checking for membership on the first one so we
         dont yield any duplicates.
 
         If the ascending attribute is set, iterate over both collections at the
         same time, yielding only one value at a time in the given order.
         """
         if self._ascending is None:
             if self._genlist:
                 return iter(self._genlist)
             def arbitraryordergen():
                 for r in self._r1:
                     yield r
                 inr1 = self._r1.__contains__
                 for r in self._r2:
                     if not inr1(r):
                         yield r
             return arbitraryordergen()
         # try to use our own fast iterator if it exists
         self._trysetasclist()
         if self._ascending:
             attr = 'fastasc'
         else:
             attr = 'fastdesc'
         it = getattr(self, attr)
         if it is not None:
             return it()
         # maybe half of the component supports fast
         # get iterator for _r1
         iter1 = getattr(self._r1, attr)
         if iter1 is None:
             # let's avoid side effect (not sure it matters)
             iter1 = iter(sorted(self._r1, reverse=not self._ascending))
         else:
             iter1 = iter1()
         # get iterator for _r2
         iter2 = getattr(self._r2, attr)
         if iter2 is None:
             # let's avoid side effect (not sure it matters)
             iter2 = iter(sorted(self._r2, reverse=not self._ascending))
         else:
             iter2 = iter2()
         return _iterordered(self._ascending, iter1, iter2)
 
     def _trysetasclist(self):
         """populate the _asclist attribute if possible and necessary"""
         if self._genlist is not None and self._asclist is None:
             self._asclist = sorted(self._genlist)
 
     @property
     def fastasc(self):
         self._trysetasclist()
         if self._asclist is not None:
             return self._asclist.__iter__
         iter1 = self._r1.fastasc
         iter2 = self._r2.fastasc
         if None in (iter1, iter2):
             return None
         return lambda: _iterordered(True, iter1(), iter2())
 
     @property
     def fastdesc(self):
         self._trysetasclist()
         if self._asclist is not None:
             return self._asclist.__reversed__
         iter1 = self._r1.fastdesc
         iter2 = self._r2.fastdesc
         if None in (iter1, iter2):
             return None
         return lambda: _iterordered(False, iter1(), iter2())
 
     def __contains__(self, x):
         return x in self._r1 or x in self._r2
 
     def sort(self, reverse=False):
         """Sort the added set
 
         For this we use the cached list with all the generated values and if we
         know they are ascending or descending we can sort them in a smart way.
         """
         self._ascending = not reverse
 
     def isascending(self):
         return self._ascending is not None and self._ascending
 
     def isdescending(self):
         return self._ascending is not None and not self._ascending
 
     def reverse(self):
         if self._ascending is None:
             self._list.reverse()
         else:
             self._ascending = not self._ascending
 
     def first(self):
         for x in self:
             return x
         return None
 
     def last(self):
         self.reverse()
         val = self.first()
         self.reverse()
         return val
 
     def __repr__(self):
         d = {None: '', False: '-', True: '+'}[self._ascending]
         return '<%s%s %r, %r>' % (type(self).__name__, d, self._r1, self._r2)
 
 class generatorset(abstractsmartset):
     """Wrap a generator for lazy iteration
 
     Wrapper structure for generators that provides lazy membership and can
     be iterated more than once.
     When asked for membership it generates values until either it finds the
     requested one or has gone through all the elements in the generator
     """
     def __init__(self, gen, iterasc=None):
         """
         gen: a generator producing the values for the generatorset.
         """
         self._gen = gen
         self._asclist = None
         self._cache = {}
         self._genlist = []
         self._finished = False
         self._ascending = True
         if iterasc is not None:
             if iterasc:
                 self.fastasc = self._iterator
                 self.__contains__ = self._asccontains
             else:
                 self.fastdesc = self._iterator
                 self.__contains__ = self._desccontains
 
     def __nonzero__(self):
         # Do not use 'for r in self' because it will enforce the iteration
         # order (default ascending), possibly unrolling a whole descending
         # iterator.
         if self._genlist:
             return True
         for r in self._consumegen():
             return True
         return False
 
     def __contains__(self, x):
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
 
         self._cache[x] = False
         return False
 
     def _asccontains(self, x):
         """version of contains optimised for ascending generator"""
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
             if l > x:
                 break
 
         self._cache[x] = False
         return False
 
     def _desccontains(self, x):
         """version of contains optimised for descending generator"""
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
             if l < x:
                 break
 
         self._cache[x] = False
         return False
 
     def __iter__(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         if it is not None:
             return it()
         # we need to consume the iterator
         for x in self._consumegen():
             pass
         # recall the same code
         return iter(self)
 
     def _iterator(self):
         if self._finished:
             return iter(self._genlist)
 
         # We have to use this complex iteration strategy to allow multiple
         # iterations at the same time. We need to be able to catch revision
         # removed from _consumegen and added to genlist in another instance.
         #
         # Getting rid of it would provide an about 15% speed up on this
         # iteration.
         genlist = self._genlist
         nextrev = self._consumegen().next
         _len = len # cache global lookup
         def gen():
             i = 0
             while True:
                 if i < _len(genlist):
                     yield genlist[i]
                 else:
                     yield nextrev()
                 i += 1
         return gen()
 
     def _consumegen(self):
         cache = self._cache
         genlist = self._genlist.append
         for item in self._gen:
             cache[item] = True
             genlist(item)
             yield item
         if not self._finished:
             self._finished = True
             asc = self._genlist[:]
             asc.sort()
             self._asclist = asc
             self.fastasc = asc.__iter__
             self.fastdesc = asc.__reversed__
 
     def __len__(self):
         for x in self._consumegen():
             pass
         return len(self._genlist)
 
     def sort(self, reverse=False):
         self._ascending = not reverse
 
     def reverse(self):
         self._ascending = not self._ascending
 
     def isascending(self):
         return self._ascending
 
     def isdescending(self):
         return not self._ascending
 
     def first(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         if it is None:
             # we need to consume all and try again
             for x in self._consumegen():
                 pass
             return self.first()
         return next(it(), None)
 
     def last(self):
         if self._ascending:
             it = self.fastdesc
         else:
             it = self.fastasc
         if it is None:
             # we need to consume all and try again
             for x in self._consumegen():
                 pass
             return self.first()
         return next(it(), None)
 
     def __repr__(self):
         d = {False: '-', True: '+'}[self._ascending]
         return '<%s%s>' % (type(self).__name__, d)
 
 class spanset(abstractsmartset):
     """Duck type for baseset class which represents a range of revisions and
     can work lazily and without having all the range in memory
 
     Note that spanset(x, y) behave almost like xrange(x, y) except for two
     notable points:
     - when x < y it will be automatically descending,
     - revision filtered with this repoview will be skipped.
 
     """
     def __init__(self, repo, start=0, end=None):
         """
         start: first revision included the set
                (default to 0)
         end:   first revision excluded (last+1)
                (default to len(repo)
 
         Spanset will be descending if `end` < `start`.
         """
         if end is None:
             end = len(repo)
         self._ascending = start <= end
         if not self._ascending:
             start, end = end + 1, start +1
         self._start = start
         self._end = end
         self._hiddenrevs = repo.changelog.filteredrevs
 
     def sort(self, reverse=False):
         self._ascending = not reverse
 
     def reverse(self):
         self._ascending = not self._ascending
 
     def _iterfilter(self, iterrange):
         s = self._hiddenrevs
         for r in iterrange:
             if r not in s:
                 yield r
 
     def __iter__(self):
         if self._ascending:
             return self.fastasc()
         else:
             return self.fastdesc()
 
     def fastasc(self):
         iterrange = xrange(self._start, self._end)
         if self._hiddenrevs:
             return self._iterfilter(iterrange)
         return iter(iterrange)
 
     def fastdesc(self):
         iterrange = xrange(self._end - 1, self._start - 1, -1)
         if self._hiddenrevs:
             return self._iterfilter(iterrange)
         return iter(iterrange)
 
     def __contains__(self, rev):
         hidden = self._hiddenrevs
         return ((self._start <= rev < self._end)
                 and not (hidden and rev in hidden))
 
     def __nonzero__(self):
         for r in self:
             return True
         return False
 
     def __len__(self):
         if not self._hiddenrevs:
             return abs(self._end - self._start)
         else:
             count = 0
             start = self._start
             end = self._end
             for rev in self._hiddenrevs:
                 if (end < rev <= start) or (start <= rev < end):
                     count += 1
             return abs(self._end - self._start) - count
 
     def isascending(self):
         return self._ascending
 
     def isdescending(self):
         return not self._ascending
 
     def first(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         for x in it():
             return x
         return None
 
     def last(self):
         if self._ascending:
             it = self.fastdesc
         else:
             it = self.fastasc
         for x in it():
             return x
         return None
 
     def __repr__(self):
         d = {False: '-', True: '+'}[self._ascending]
         return '<%s%s %d:%d>' % (type(self).__name__, d,
                                  self._start, self._end - 1)
 
 class fullreposet(spanset):
     """a set containing all revisions in the repo
 
     This class exists to host special optimization and magic to handle virtual
     revisions such as "null".
     """
 
     def __init__(self, repo):
         super(fullreposet, self).__init__(repo)
 
     def __and__(self, other):
         """As self contains the whole repo, all of the other set should also be
         in self. Therefore `self & other = other`.
 
         This boldly assumes the other contains valid revs only.
         """
         # other not a smartset, make is so
         if not util.safehasattr(other, 'isascending'):
             # filter out hidden revision
             # (this boldly assumes all smartset are pure)
             #
             # `other` was used with "&", let's assume this is a set like
             # object.
             other = baseset(other - self._hiddenrevs)
 
         # XXX As fullreposet is also used as bootstrap, this is wrong.
         #
         # With a giveme312() revset returning [3,1,2], this makes
         #   'hg log -r "giveme312()"' -> 1, 2, 3 (wrong)
         # We cannot just drop it because other usage still need to sort it:
         #   'hg log -r "all() and giveme312()"' -> 1, 2, 3 (right)
         #
         # There is also some faulty revset implementations that rely on it
         # (eg: children as of its state in e8075329c5fb)
         #
         # When we fix the two points above we can move this into the if clause
         other.sort(reverse=self.isdescending())
         return other
 
 def prettyformatset(revs):
     lines = []
     rs = repr(revs)
     p = 0
     while p < len(rs):
         q = rs.find('<', p + 1)
         if q < 0:
             q = len(rs)
         l = rs.count('<', 0, p) - rs.count('>', 0, p)
         assert l >= 0
         lines.append((l, rs[p:q].rstrip()))
         p = q
     return '\n'.join('  ' * l + s for l, s in lines)
 
 def loadpredicate(ui, extname, registrarobj):
     """Load revset predicates from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         symbols[name] = func
         if func._safe:
             safesymbols.add(name)
 
 # load built-in predicates explicitly to setup safesymbols
 loadpredicate(None, None, predicate)
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

mercurial/tags.py

@@ -1,571 +1,571 b''
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Matt Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[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.
 
 # Currently this module only deals with reading and caching tags.
 # Eventually, it could take care of updating (adding/removing/moving)
 # tags too.
 
 from __future__ import absolute_import
 
 import array
 import errno
 import time
 
 from .node import (
     bin,
     hex,
     nullid,
     short,
 )
 from . import (
     encoding,
     error,
     util,
 )
 
 array = array.array
 
 # Tags computation can be expensive and caches exist to make it fast in
 # the common case.
 #
 # The "hgtagsfnodes1" cache file caches the .hgtags filenode values for
 # each revision in the repository. The file is effectively an array of
 # fixed length records. Read the docs for "hgtagsfnodescache" for technical
 # details.
 #
 # The .hgtags filenode cache grows in proportion to the length of the
 # changelog. The file is truncated when the # changelog is stripped.
 #
 # The purpose of the filenode cache is to avoid the most expensive part
 # of finding global tags, which is looking up the .hgtags filenode in the
 # manifest for each head. This can take dozens or over 100ms for
 # repositories with very large manifests. Multiplied by dozens or even
 # hundreds of heads and there is a significant performance concern.
 #
 # There also exist a separate cache file for each repository filter.
 # These "tags-*" files store information about the history of tags.
 #
 # The tags cache files consists of a cache validation line followed by
 # a history of tags.
 #
 # The cache validation line has the format:
 #
 #   <tiprev> <tipnode> [<filteredhash>]
 #
 # <tiprev> is an integer revision and <tipnode> is a 40 character hex
 # node for that changeset. These redundantly identify the repository
 # tip from the time the cache was written. In addition, <filteredhash>,
 # if present, is a 40 character hex hash of the contents of the filtered
 # revisions for this filter. If the set of filtered revs changes, the
 # hash will change and invalidate the cache.
 #
 # The history part of the tags cache consists of lines of the form:
 #
 #   <node> <tag>
 #
 # (This format is identical to that of .hgtags files.)
 #
 # <tag> is the tag name and <node> is the 40 character hex changeset
 # the tag is associated with.
 #
 # Tags are written sorted by tag name.
 #
 # Tags associated with multiple changesets have an entry for each changeset.
 # The most recent changeset (in terms of revlog ordering for the head
 # setting it) for each tag is last.
 
 def findglobaltags(ui, repo, alltags, tagtypes):
     '''Find global tags in a repo.
 
     "alltags" maps tag name to (node, hist) 2-tuples.
 
     "tagtypes" maps tag name to tag type. Global tags always have the
     "global" tag type.
 
     The "alltags" and "tagtypes" dicts are updated in place. Empty dicts
     should be passed in.
 
     The tags cache is read and updated as a side-effect of calling.
     '''
     # This is so we can be lazy and assume alltags contains only global
     # tags when we pass it to _writetagcache().
     assert len(alltags) == len(tagtypes) == 0, \
            "findglobaltags() should be called first"
 
     (heads, tagfnode, valid, cachetags, shouldwrite) = _readtagcache(ui, repo)
     if cachetags is not None:
         assert not shouldwrite
         # XXX is this really 100% correct?  are there oddball special
         # cases where a global tag should outrank a local tag but won't,
         # because cachetags does not contain rank info?
         _updatetags(cachetags, 'global', alltags, tagtypes)
         return
 
     seen = set()  # set of fnode
     fctx = None
     for head in reversed(heads):  # oldest to newest
         assert head in repo.changelog.nodemap, \
                "tag cache returned bogus head %s" % short(head)
 
         fnode = tagfnode.get(head)
         if fnode and fnode not in seen:
             seen.add(fnode)
             if not fctx:
                 fctx = repo.filectx('.hgtags', fileid=fnode)
             else:
                 fctx = fctx.filectx(fnode)
 
             filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
             _updatetags(filetags, 'global', alltags, tagtypes)
 
     # and update the cache (if necessary)
     if shouldwrite:
         _writetagcache(ui, repo, valid, alltags)
 
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo. Update alltags and tagtypes.'''
     try:
         data = repo.vfs.read("localtags")
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return
 
     # localtags is in the local encoding; re-encode to UTF-8 on
     # input for consistency with the rest of this module.
     filetags = _readtags(
         ui, repo, data.splitlines(), "localtags",
         recode=encoding.fromlocal)
 
     # remove tags pointing to invalid nodes
     cl = repo.changelog
     for t in filetags.keys():
         try:
             cl.rev(filetags[t][0])
         except (LookupError, ValueError):
             del filetags[t]
 
     _updatetags(filetags, "local", alltags, tagtypes)
 
 def _readtaghist(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     This function returns two sortdicts with similar information:
 
     - the first dict, bintaghist, contains the tag information as expected by
       the _readtags function, i.e. a mapping from tag name to (node, hist):
         - node is the node id from the last line read for that name,
         - hist is the list of node ids previously associated with it (in file
           order). All node ids are binary, not hex.
 
     - the second dict, hextaglines, is a mapping from tag name to a list of
       [hexnode, line number] pairs, ordered from the oldest to the newest node.
 
     When calcnodelines is False the hextaglines dict is not calculated (an
     empty dict is returned). This is done to improve this function's
     performance in cases where the line numbers are not needed.
     '''
 
     bintaghist = util.sortdict()
     hextaglines = util.sortdict()
     count = 0
 
     def dbg(msg):
         ui.debug("%s, line %s: %s\n" % (fn, count, msg))
 
     for nline, line in enumerate(lines):
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(" ", 1)
         except ValueError:
             dbg("cannot parse entry")
             continue
         name = name.strip()
         if recode:
             name = recode(name)
         try:
             nodebin = bin(nodehex)
         except TypeError:
             dbg("node '%s' is not well formed" % nodehex)
             continue
 
         # update filetags
         if calcnodelines:
             # map tag name to a list of line numbers
             if name not in hextaglines:
                 hextaglines[name] = []
             hextaglines[name].append([nodehex, nline])
             continue
         # map tag name to (node, hist)
         if name not in bintaghist:
             bintaghist[name] = []
         bintaghist[name].append(nodebin)
     return bintaghist, hextaglines
 
 def _readtags(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     Returns a mapping from tag name to (node, hist).
 
     "node" is the node id from the last line read for that name. "hist"
     is the list of node ids previously associated with it (in file order).
     All node ids are binary, not hex.
     '''
     filetags, nodelines = _readtaghist(ui, repo, lines, fn, recode=recode,
                                        calcnodelines=calcnodelines)
     # util.sortdict().__setitem__ is much slower at replacing then inserting
     # new entries. The difference can matter if there are thousands of tags.
     # Create a new sortdict to avoid the performance penalty.
     newtags = util.sortdict()
     for tag, taghist in filetags.items():
         newtags[tag] = (taghist[-1], taghist[:-1])
     return newtags
 
 def _updatetags(filetags, tagtype, alltags, tagtypes):
     '''Incorporate the tag info read from one file into the two
     dictionaries, alltags and tagtypes, that contain all tag
     info (global across all heads plus local).'''
 
     for name, nodehist in filetags.iteritems():
         if name not in alltags:
             alltags[name] = nodehist
             tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supersedes us OR
         #  mutual supersedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (bnode != anode and anode in bhist and
             (bnode not in ahist or len(bhist) > len(ahist))):
             anode = bnode
         else:
             tagtypes[name] = tagtype
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
 
 def _filename(repo):
     """name of a tagcache file for a given repo or repoview"""
     filename = 'cache/tags2'
     if repo.filtername:
         filename = '%s-%s' % (filename, repo.filtername)
     return filename
 
 def _readtagcache(ui, repo):
     '''Read the tag cache.
 
     Returns a tuple (heads, fnodes, validinfo, cachetags, shouldwrite).
 
     If the cache is completely up-to-date, "cachetags" is a dict of the
     form returned by _readtags() and "heads", "fnodes", and "validinfo" are
     None and "shouldwrite" is False.
 
     If the cache is not up to date, "cachetags" is None. "heads" is a list
     of all heads currently in the repository, ordered from tip to oldest.
     "validinfo" is a tuple describing cache validation info. This is used
     when writing the tags cache. "fnodes" is a mapping from head to .hgtags
     filenode. "shouldwrite" is True.
 
     If the cache is not up to date, the caller is responsible for reading tag
     info from each returned head. (See findglobaltags().)
     '''
     from . import scmutil  # avoid cycle
 
     try:
         cachefile = repo.vfs(_filename(repo), 'r')
         # force reading the file for static-http
         cachelines = iter(cachefile)
     except IOError:
         cachefile = None
 
     cacherev = None
     cachenode = None
     cachehash = None
     if cachefile:
         try:
-            validline = cachelines.next()
+            validline = next(cachelines)
             validline = validline.split()
             cacherev = int(validline[0])
             cachenode = bin(validline[1])
             if len(validline) > 2:
                 cachehash = bin(validline[2])
         except Exception:
             # corruption of the cache, just recompute it.
             pass
 
     tipnode = repo.changelog.tip()
     tiprev = len(repo.changelog) - 1
 
     # Case 1 (common): tip is the same, so nothing has changed.
     # (Unchanged tip trivially means no changesets have been added.
     # But, thanks to localrepository.destroyed(), it also means none
     # have been destroyed by strip or rollback.)
     if (cacherev == tiprev
             and cachenode == tipnode
             and cachehash == scmutil.filteredhash(repo, tiprev)):
         tags = _readtags(ui, repo, cachelines, cachefile.name)
         cachefile.close()
         return (None, None, None, tags, False)
     if cachefile:
         cachefile.close()               # ignore rest of file
 
     valid = (tiprev, tipnode, scmutil.filteredhash(repo, tiprev))
 
     repoheads = repo.heads()
     # Case 2 (uncommon): empty repo; get out quickly and don't bother
     # writing an empty cache.
     if repoheads == [nullid]:
         return ([], {}, valid, {}, False)
 
     # Case 3 (uncommon): cache file missing or empty.
 
     # Case 4 (uncommon): tip rev decreased.  This should only happen
     # when we're called from localrepository.destroyed().  Refresh the
     # cache so future invocations will not see disappeared heads in the
     # cache.
 
     # Case 5 (common): tip has changed, so we've added/replaced heads.
 
     # As it happens, the code to handle cases 3, 4, 5 is the same.
 
     # N.B. in case 4 (nodes destroyed), "new head" really means "newly
     # exposed".
     if not len(repo.file('.hgtags')):
         # No tags have ever been committed, so we can avoid a
         # potentially expensive search.
         return ([], {}, valid, None, True)
 
     starttime = time.time()
 
     # Now we have to lookup the .hgtags filenode for every new head.
     # This is the most expensive part of finding tags, so performance
     # depends primarily on the size of newheads.  Worst case: no cache
     # file, so newheads == repoheads.
     fnodescache = hgtagsfnodescache(repo.unfiltered())
     cachefnode = {}
     for head in reversed(repoheads):
         fnode = fnodescache.getfnode(head)
         if fnode != nullid:
             cachefnode[head] = fnode
 
     fnodescache.write()
 
     duration = time.time() - starttime
     ui.log('tagscache',
            '%d/%d cache hits/lookups in %0.4f '
            'seconds\n',
            fnodescache.hitcount, fnodescache.lookupcount, duration)
 
     # Caller has to iterate over all heads, but can use the filenodes in
     # cachefnode to get to each .hgtags revision quickly.
     return (repoheads, cachefnode, valid, None, True)
 
 def _writetagcache(ui, repo, valid, cachetags):
     filename = _filename(repo)
     try:
         cachefile = repo.vfs(filename, 'w', atomictemp=True)
     except (OSError, IOError):
         return
 
     ui.log('tagscache', 'writing .hg/%s with %d tags\n',
            filename, len(cachetags))
 
     if valid[2]:
         cachefile.write('%d %s %s\n' % (valid[0], hex(valid[1]), hex(valid[2])))
     else:
         cachefile.write('%d %s\n' % (valid[0], hex(valid[1])))
 
     # Tag names in the cache are in UTF-8 -- which is the whole reason
     # we keep them in UTF-8 throughout this module.  If we converted
     # them local encoding on input, we would lose info writing them to
     # the cache.
     for (name, (node, hist)) in sorted(cachetags.iteritems()):
         for n in hist:
             cachefile.write("%s %s\n" % (hex(n), name))
         cachefile.write("%s %s\n" % (hex(node), name))
 
     try:
         cachefile.close()
     except (OSError, IOError):
         pass
 
 _fnodescachefile = 'cache/hgtagsfnodes1'
 _fnodesrecsize = 4 + 20 # changeset fragment + filenode
 _fnodesmissingrec = '\xff' * 24
 
 class hgtagsfnodescache(object):
     """Persistent cache mapping revisions to .hgtags filenodes.
 
     The cache is an array of records. Each item in the array corresponds to
     a changelog revision. Values in the array contain the first 4 bytes of
     the node hash and the 20 bytes .hgtags filenode for that revision.
 
     The first 4 bytes are present as a form of verification. Repository
     stripping and rewriting may change the node at a numeric revision in the
     changelog. The changeset fragment serves as a verifier to detect
     rewriting. This logic is shared with the rev branch cache (see
     branchmap.py).
 
     The instance holds in memory the full cache content but entries are
     only parsed on read.
 
     Instances behave like lists. ``c[i]`` works where i is a rev or
     changeset node. Missing indexes are populated automatically on access.
     """
     def __init__(self, repo):
         assert repo.filtername is None
 
         self._repo = repo
 
         # Only for reporting purposes.
         self.lookupcount = 0
         self.hitcount = 0
 
         self._raw = array('c')
 
         try:
             data = repo.vfs.read(_fnodescachefile)
         except (OSError, IOError):
             data = ""
         self._raw.fromstring(data)
 
         # The end state of self._raw is an array that is of the exact length
         # required to hold a record for every revision in the repository.
         # We truncate or extend the array as necessary. self._dirtyoffset is
         # defined to be the start offset at which we need to write the output
         # file. This offset is also adjusted when new entries are calculated
         # for array members.
         cllen = len(repo.changelog)
         wantedlen = cllen * _fnodesrecsize
         rawlen = len(self._raw)
 
         self._dirtyoffset = None
 
         if rawlen < wantedlen:
             self._dirtyoffset = rawlen
             self._raw.extend('\xff' * (wantedlen - rawlen))
         elif rawlen > wantedlen:
             # There's no easy way to truncate array instances. This seems
             # slightly less evil than copying a potentially large array slice.
             for i in range(rawlen - wantedlen):
                 self._raw.pop()
             self._dirtyoffset = len(self._raw)
 
     def getfnode(self, node, computemissing=True):
         """Obtain the filenode of the .hgtags file at a specified revision.
 
         If the value is in the cache, the entry will be validated and returned.
         Otherwise, the filenode will be computed and returned unless
         "computemissing" is False, in which case None will be returned without
         any potentially expensive computation being performed.
 
         If an .hgtags does not exist at the specified revision, nullid is
         returned.
         """
         ctx = self._repo[node]
         rev = ctx.rev()
 
         self.lookupcount += 1
 
         offset = rev * _fnodesrecsize
         record = self._raw[offset:offset + _fnodesrecsize].tostring()
         properprefix = node[0:4]
 
         # Validate and return existing entry.
         if record != _fnodesmissingrec:
             fileprefix = record[0:4]
 
             if fileprefix == properprefix:
                 self.hitcount += 1
                 return record[4:]
 
             # Fall through.
 
         # If we get here, the entry is either missing or invalid.
 
         if not computemissing:
             return None
 
         # Populate missing entry.
         try:
             fnode = ctx.filenode('.hgtags')
         except error.LookupError:
             # No .hgtags file on this revision.
             fnode = nullid
 
         self._writeentry(offset, properprefix, fnode)
         return fnode
 
     def setfnode(self, node, fnode):
         """Set the .hgtags filenode for a given changeset."""
         assert len(fnode) == 20
         ctx = self._repo[node]
 
         # Do a lookup first to avoid writing if nothing has changed.
         if self.getfnode(ctx.node(), computemissing=False) == fnode:
             return
 
         self._writeentry(ctx.rev() * _fnodesrecsize, node[0:4], fnode)
 
     def _writeentry(self, offset, prefix, fnode):
         # Slices on array instances only accept other array.
         entry = array('c', prefix + fnode)
         self._raw[offset:offset + _fnodesrecsize] = entry
         # self._dirtyoffset could be None.
         self._dirtyoffset = min(self._dirtyoffset, offset) or 0
 
     def write(self):
         """Perform all necessary writes to cache file.
 
         This may no-op if no writes are needed or if a write lock could
         not be obtained.
         """
         if self._dirtyoffset is None:
             return
 
         data = self._raw[self._dirtyoffset:]
         if not data:
             return
 
         repo = self._repo
 
         try:
             lock = repo.wlock(wait=False)
         except error.LockError:
             repo.ui.log('tagscache',
                         'not writing .hg/%s because lock cannot be acquired\n' %
                         (_fnodescachefile))
             return
 
         try:
             f = repo.vfs.open(_fnodescachefile, 'ab')
             try:
                 # if the file has been truncated
                 actualoffset = f.tell()
                 if actualoffset < self._dirtyoffset:
                     self._dirtyoffset = actualoffset
                     data = self._raw[self._dirtyoffset:]
                 f.seek(self._dirtyoffset)
                 f.truncate()
                 repo.ui.log('tagscache',
                             'writing %d bytes to %s\n' % (
                             len(data), _fnodescachefile))
                 f.write(data)
                 self._dirtyoffset = None
             finally:
                 f.close()
         except (IOError, OSError) as inst:
             repo.ui.log('tagscache',
                         "couldn't write %s: %s\n" % (
                         _fnodescachefile, inst))
         finally:
             lock.release()