Merge with stable

Simplify the copy search algorithm

contrib/dumprevlog

@@ -0,0 +1,25 b''
+#!/usr/bin/env python
+# Dump revlogs as raw data stream
+# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump
+
+import sys
+from mercurial import revlog, node, util
+
+for fp in (sys.stdin, sys.stdout, sys.stderr):
+    util.set_binary(fp)
+
+for f in sys.argv[1:]:
+    binopen = lambda fn: open(fn, 'rb')
+    r = revlog.revlog(binopen, f)
+    print "file:", f
+    for i in r:
+        n = r.node(i)
+        p = r.parents(n)
+        d = r.revision(n)
+        print "node:", node.hex(n)
+        print "linkrev:", r.linkrev(n)
+        print "parents:", node.hex(p[0]), node.hex(p[1])
+        print "length:", len(d)
+        print "-start-"
+        print d
+        print "-end-"

contrib/undumprevlog

@@ -0,0 +1,37 b''
+#!/usr/bin/env python
+# Undump a dump from dumprevlog
+# $ hg init
+# $ undumprevlog < repo.dump
+
+import sys
+from mercurial import revlog, node, util, transaction
+
+for fp in (sys.stdin, sys.stdout, sys.stderr):
+    util.set_binary(fp)
+
+opener = util.opener('.', False)
+tr = transaction.transaction(sys.stderr.write, opener, "undump.journal")
+while 1:
+    l = sys.stdin.readline()
+    if not l:
+        break
+    if l.startswith("file:"):
+        f = l[6:-1]
+        r = revlog.revlog(opener, f)
+        print f
+    elif l.startswith("node:"):
+        n = node.bin(l[6:-1])
+    elif l.startswith("linkrev:"):
+        lr = int(l[9:-1])
+    elif l.startswith("parents:"):
+        p = l[9:-1].split()
+        p1 = node.bin(p[0])
+        p2 = node.bin(p[1])
+    elif l.startswith("length:"):
+        length = int(l[8:-1])
+        sys.stdin.readline() # start marker
+        d = sys.stdin.read(length)
+        sys.stdin.readline() # end marker
+        r.addrevision(d, tr, lr, p1, p2)
+
+tr.close()

contrib/win32/hg.bat

@@ -0,0 +1,12 b''
+@echo off
+rem Windows Driver script for Mercurial
+
+setlocal
+set HG=%~f0
+
+rem Use a full path to Python (relative to this script) as the standard Python
+rem install does not put python.exe on the PATH...
+rem %~dp0 is the directory of this script
+
+%~dp0..\python "%~dp0hg" %*
+endlocal

hgext/convert/cvsps

@@ -0,0 +1,154 b''
+#!/usr/bin/env python
+#
+# Commandline front-end for cvsps.py
+#
+# Copyright 2008, Frank Kingswood <[e-mail]>
+#
+# This software may be used and distributed according to the terms
+# of the GNU General Public License, incorporated herein by reference.
+
+import sys
+from mercurial import util
+from mercurial.i18n import _
+from optparse import OptionParser, SUPPRESS_HELP
+from hgext.convert.cvsps import createlog, createchangeset, logerror
+
+def main():
+    '''Main program to mimic cvsps.'''
+
+    op = OptionParser(usage='%prog [-bpruvxz] path',
+                      description='Read CVS rlog for current directory or named '
+                                  'path in repository, and convert the log to changesets '
+                                  'based on matching commit log entries and dates.')
+
+    # Options that are ignored for compatibility with cvsps-2.1
+    op.add_option('-A', dest='Ignore', action='store_true', help=SUPPRESS_HELP)
+    op.add_option('--cvs-direct', dest='Ignore', action='store_true', help=SUPPRESS_HELP)
+    op.add_option('-q', dest='Ignore', action='store_true', help=SUPPRESS_HELP)
+
+    # Main options shared with cvsps-2.1
+    op.add_option('-b', dest='Branches', action='append', default=[],
+                  help='Only return changes on specified branches')
+    op.add_option('-p', dest='Prefix', action='store', default='',
+                  help='Prefix to remove from file names')
+    op.add_option('-r', dest='Revisions', action='append', default=[],
+                  help='Only return changes after or between specified tags')
+    op.add_option('-u', dest='Cache', action='store_const', const='update',
+                  help="Update cvs log cache")
+    op.add_option('-v', dest='Verbose', action='count', default=0,
+                  help='Be verbose')
+    op.add_option('-x', dest='Cache', action='store_const', const='write',
+                  help="Create new cvs log cache")
+    op.add_option('-z', dest='Fuzz', action='store', type='int', default=60,
+                  help='Set commit time fuzz', metavar='seconds')
+    op.add_option('--root', dest='Root', action='store', default='',
+                  help='Specify cvsroot', metavar='cvsroot')
+
+    # Options specific to this version
+    op.add_option('--parents', dest='Parents', action='store_true',
+                  help='Show parent changesets')
+    op.add_option('--ancestors', dest='Ancestors', action='store_true',
+                  help='Show current changeset in ancestor branches')
+
+    options, args = op.parse_args()
+
+    # Create a ui object for printing progress messages
+    class UI:
+        def __init__(self, verbose):
+            if verbose:
+                self.status = self.message
+            if verbose>1:
+                self.note = self.message
+            if verbose>2:
+                self.debug = self.message
+        def message(self, msg):
+            sys.stderr.write(msg)
+        def nomessage(self, msg):
+            pass
+        status = nomessage
+        note = nomessage
+        debug = nomessage
+    ui = UI(options.Verbose)
+
+    try:
+        if args:
+            log = []
+            for d in args:
+                log += createlog(ui, d, root=options.Root, cache=options.Cache)
+        else:
+            log = createlog(ui, root=options.Root, cache=options.Cache)
+    except logerror, e:
+        print e
+        return
+
+    changesets = createchangeset(ui, log, options.Fuzz)
+    del log
+
+    # Print changesets (optionally filtered)
+
+    off = len(options.Revisions)
+    branches = {}    # latest version number in each branch
+    ancestors = {}   # parent branch
+    for cs in changesets:
+
+        if options.Ancestors:
+            if cs.branch not in branches and cs.parents and cs.parents[0].id:
+                ancestors[cs.branch] = changesets[cs.parents[0].id-1].branch, cs.parents[0].id
+            branches[cs.branch] = cs.id
+
+        # limit by branches
+        if options.Branches and (cs.branch or 'HEAD') not in options.Branches:
+            continue
+
+        if not off:
+            # Note: trailing spaces on several lines here are needed to have
+            #       bug-for-bug compatibility with cvsps.
+            print '---------------------'
+            print 'PatchSet %d ' % cs.id
+            print 'Date: %s' % util.datestr(cs.date, '%Y/%m/%d %H:%M:%S %1%2')
+            print 'Author: %s' % cs.author
+            print 'Branch: %s' % (cs.branch or 'HEAD')
+            print 'Tag%s: %s ' % (['', 's'][len(cs.tags)>1],
+                                  ','.join(cs.tags) or '(none)')
+            if options.Parents and cs.parents:
+                if len(cs.parents)>1:
+                    print 'Parents: %s' % (','.join([str(p.id) for p in cs.parents]))
+                else:
+                    print 'Parent: %d' % cs.parents[0].id
+
+            if options.Ancestors:
+                b = cs.branch
+                r = []
+                while b:
+                    b, c = ancestors[b]
+                    r.append('%s:%d:%d' % (b or "HEAD", c, branches[b]))
+                if r:
+                    print 'Ancestors: %s' % (','.join(r))
+
+            print 'Log:'
+            print cs.comment
+            print
+            print 'Members: '
+            for f in cs.entries:
+                fn = f.file
+                if fn.startswith(options.Prefix):
+                    fn = fn[len(options.Prefix):]
+                print '\t%s:%s->%s%s ' % (fn, '.'.join([str(x) for x in f.parent]) or 'INITIAL',
+                                          '.'.join([str(x) for x in f.revision]), ['', '(DEAD)'][f.dead])
+            print
+
+        # have we seen the start tag?
+        if options.Revisions and off:
+            if options.Revisions[0] == str(cs.id) or \
+                options.Revisions[0] in cs.tags:
+                off = False
+
+        # see if we reached the end tag
+        if len(options.Revisions)>1 and not off:
+            if options.Revisions[1] == str(cs.id) or \
+                options.Revisions[1] in cs.tags:
+                break
+
+
+if __name__ == '__main__':
+    main()

hgext/convert/cvsps.py

@@ -0,0 +1,548 b''
+#
+# Mercurial built-in replacement for cvsps.
+#
+# Copyright 2008, Frank Kingswood <[e-mail]>
+#
+# This software may be used and distributed according to the terms
+# of the GNU General Public License, incorporated herein by reference.
+
+import os
+import re
+import sys
+import cPickle as pickle
+from mercurial import util
+from mercurial.i18n import _
+
+def listsort(list, key):
+    "helper to sort by key in Python 2.3"
+    try:
+        list.sort(key=key)
+    except TypeError:
+        list.sort(lambda l, r: cmp(key(l), key(r)))
+
+class logentry(object):
+    '''Class logentry has the following attributes:
+        .author    - author name as CVS knows it
+        .branch    - name of branch this revision is on
+        .branches  - revision tuple of branches starting at this revision
+        .comment   - commit message
+        .date      - the commit date as a (time, tz) tuple
+        .dead      - true if file revision is dead
+        .file      - Name of file
+        .lines     - a tuple (+lines, -lines) or None
+        .parent    - Previous revision of this entry
+        .rcs       - name of file as returned from CVS
+        .revision  - revision number as tuple
+        .tags      - list of tags on the file
+    '''
+    def __init__(self, **entries):
+        self.__dict__.update(entries)
+
+class logerror(Exception):
+    pass
+
+def createlog(ui, directory=None, root="", rlog=True, cache=None):
+    '''Collect the CVS rlog'''
+
+    # Because we store many duplicate commit log messages, reusing strings
+    # saves a lot of memory and pickle storage space.
+    _scache = {}
+    def scache(s):
+        "return a shared version of a string"
+        return _scache.setdefault(s, s)
+
+    ui.status(_('collecting CVS rlog\n'))
+
+    log = []      # list of logentry objects containing the CVS state
+
+    # patterns to match in CVS (r)log output, by state of use
+    re_00 = re.compile('RCS file: (.+)$')
+    re_01 = re.compile('cvs \\[r?log aborted\\]: (.+)$')
+    re_02 = re.compile('cvs (r?log|server): (.+)\n$')
+    re_03 = re.compile("(Cannot access.+CVSROOT)|(can't create temporary directory.+)$")
+    re_10 = re.compile('Working file: (.+)$')
+    re_20 = re.compile('symbolic names:')
+    re_30 = re.compile('\t(.+): ([\\d.]+)$')
+    re_31 = re.compile('----------------------------$')
+    re_32 = re.compile('=============================================================================$')
+    re_50 = re.compile('revision ([\\d.]+)(\s+locked by:\s+.+;)?$')
+    re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?')
+    re_70 = re.compile('branches: (.+);$')
+
+    prefix = ''   # leading path to strip of what we get from CVS
+
+    if directory is None:
+        # Current working directory
+
+        # Get the real directory in the repository
+        try:
+            prefix = file(os.path.join('CVS','Repository')).read().strip()
+            if prefix == ".":
+                prefix = ""
+            directory = prefix
+        except IOError:
+            raise logerror('Not a CVS sandbox')
+
+        if prefix and not prefix.endswith('/'):
+            prefix += '/'
+
+        # Use the Root file in the sandbox, if it exists
+        try:
+            root = file(os.path.join('CVS','Root')).read().strip()
+        except IOError:
+            pass
+
+    if not root:
+        root = os.environ.get('CVSROOT', '')
+
+    # read log cache if one exists
+    oldlog = []
+    date = None
+
+    if cache:
+        cachedir = os.path.expanduser('~/.hg.cvsps')
+        if not os.path.exists(cachedir):
+            os.mkdir(cachedir)
+
+        # The cvsps cache pickle needs a uniquified name, based on the
+        # repository location. The address may have all sort of nasties
+        # in it, slashes, colons and such. So here we take just the
+        # alphanumerics, concatenated in a way that does not mix up the
+        # various components, so that
+        #    :pserver:user@server:/path
+        # and
+        #    /pserver/user/server/path
+        # are mapped to different cache file names.
+        cachefile = root.split(":") + [directory, "cache"]
+        cachefile = ['-'.join(re.findall(r'\w+', s)) for s in cachefile if s]
+        cachefile = os.path.join(cachedir,
+                                 '.'.join([s for s in cachefile if s]))
+
+    if cache == 'update':
+        try:
+            ui.note(_('reading cvs log cache %s\n') % cachefile)
+            oldlog = pickle.load(file(cachefile))
+            ui.note(_('cache has %d log entries\n') % len(oldlog))
+        except Exception, e:
+            ui.note(_('error reading cache: %r\n') % e)
+
+        if oldlog:
+            date = oldlog[-1].date    # last commit date as a (time,tz) tuple
+            date = util.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')
+
+    # build the CVS commandline
+    cmd = ['cvs', '-q']
+    if root:
+        cmd.append('-d%s' % root)
+        p = root.split(':')[-1]
+        if not p.endswith('/'):
+            p += '/'
+        prefix = p + prefix
+    cmd.append(['log', 'rlog'][rlog])
+    if date:
+        # no space between option and date string
+        cmd.append('-d>%s' % date)
+    cmd.append(directory)
+
+    # state machine begins here
+    tags = {}     # dictionary of revisions on current file with their tags
+    state = 0
+    store = False # set when a new record can be appended
+
+    cmd = [util.shellquote(arg) for arg in cmd]
+    ui.note("running %s\n" % (' '.join(cmd)))
+    ui.debug("prefix=%r directory=%r root=%r\n" % (prefix, directory, root))
+
+    for line in util.popen(' '.join(cmd)):
+        if line.endswith('\n'):
+            line = line[:-1]
+        #ui.debug('state=%d line=%r\n' % (state, line))
+
+        if state == 0:
+            # initial state, consume input until we see 'RCS file'
+            match = re_00.match(line)
+            if match:
+                rcs = match.group(1)
+                tags = {}
+                if rlog:
+                    filename = rcs[:-2]
+                    if filename.startswith(prefix):
+                        filename = filename[len(prefix):]
+                    if filename.startswith('/'):
+                        filename = filename[1:]
+                    if filename.startswith('Attic/'):
+                        filename = filename[6:]
+                    else:
+                        filename = filename.replace('/Attic/', '/')
+                    state = 2
+                    continue
+                state = 1
+                continue
+            match = re_01.match(line)
+            if match:
+                raise Exception(match.group(1))
+            match = re_02.match(line)
+            if match:
+                raise Exception(match.group(2))
+            if re_03.match(line):
+                raise Exception(line)
+
+        elif state == 1:
+            # expect 'Working file' (only when using log instead of rlog)
+            match = re_10.match(line)
+            assert match, _('RCS file must be followed by working file')
+            filename = match.group(1)
+            state = 2
+
+        elif state == 2:
+            # expect 'symbolic names'
+            if re_20.match(line):
+                state = 3
+
+        elif state == 3:
+            # read the symbolic names and store as tags
+            match = re_30.match(line)
+            if match:
+                rev = [int(x) for x in match.group(2).split('.')]
+
+                # Convert magic branch number to an odd-numbered one
+                revn = len(rev)
+                if revn > 3 and (revn % 2) == 0 and rev[-2] == 0:
+                    rev = rev[:-2] + rev[-1:]
+                rev = tuple(rev)
+
+                if rev not in tags:
+                    tags[rev] = []
+                tags[rev].append(match.group(1))
+
+            elif re_31.match(line):
+                state = 5
+            elif re_32.match(line):
+                state = 0
+
+        elif state == 4:
+            # expecting '------' separator before first revision
+            if re_31.match(line):
+                state = 5
+            else:
+                assert not re_32.match(line), _('Must have at least some revisions')
+
+        elif state == 5:
+            # expecting revision number and possibly (ignored) lock indication
+            # we create the logentry here from values stored in states 0 to 4,
+            # as this state is re-entered for subsequent revisions of a file.
+            match = re_50.match(line)
+            assert match, _('expected revision number')
+            e = logentry(rcs=scache(rcs), file=scache(filename),
+                    revision=tuple([int(x) for x in match.group(1).split('.')]),
+                    branches=[], parent=None)
+            state = 6
+
+        elif state == 6:
+            # expecting date, author, state, lines changed
+            match = re_60.match(line)
+            assert match, _('revision must be followed by date line')
+            d = match.group(1)
+            if d[2] == '/':
+                # Y2K
+                d = '19' + d
+
+            if len(d.split()) != 3:
+                # cvs log dates always in GMT
+                d = d + ' UTC'
+            e.date = util.parsedate(d, ['%y/%m/%d %H:%M:%S', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S'])
+            e.author = scache(match.group(2))
+            e.dead = match.group(3).lower() == 'dead'
+
+            if match.group(5):
+                if match.group(6):
+                    e.lines = (int(match.group(5)), int(match.group(6)))
+                else:
+                    e.lines = (int(match.group(5)), 0)
+            elif match.group(6):
+                e.lines = (0, int(match.group(6)))
+            else:
+                e.lines = None
+            e.comment = []
+            state = 7
+
+        elif state == 7:
+            # read the revision numbers of branches that start at this revision
+            # or store the commit log message otherwise
+            m = re_70.match(line)
+            if m:
+                e.branches = [tuple([int(y) for y in x.strip().split('.')])
+                                for x in m.group(1).split(';')]
+                state = 8
+            elif re_31.match(line):
+                state = 5
+                store = True
+            elif re_32.match(line):
+                state = 0
+                store = True
+            else:
+                e.comment.append(line)
+
+        elif state == 8:
+            # store commit log message
+            if re_31.match(line):
+                state = 5
+                store = True
+            elif re_32.match(line):
+                state = 0
+                store = True
+            else:
+                e.comment.append(line)
+
+        if store:
+            # clean up the results and save in the log.
+            store = False
+            e.tags = util.sort([scache(x) for x in tags.get(e.revision, [])])
+            e.comment = scache('\n'.join(e.comment))
+
+            revn = len(e.revision)
+            if revn > 3 and (revn % 2) == 0:
+                e.branch = tags.get(e.revision[:-1], [None])[0]
+            else:
+                e.branch = None
+
+            log.append(e)
+
+            if len(log) % 100 == 0:
+                ui.status(util.ellipsis('%d %s' % (len(log), e.file), 80)+'\n')
+
+    listsort(log, key=lambda x:(x.rcs, x.revision))
+
+    # find parent revisions of individual files
+    versions = {}
+    for e in log:
+        branch = e.revision[:-1]
+        p = versions.get((e.rcs, branch), None)
+        if p is None:
+            p = e.revision[:-2]
+        e.parent = p
+        versions[(e.rcs, branch)] = e.revision
+
+    # update the log cache
+    if cache:
+        if log:
+            # join up the old and new logs
+            listsort(log, key=lambda x:x.date)
+
+            if oldlog and oldlog[-1].date >= log[0].date:
+                raise logerror('Log cache overlaps with new log entries,'
+                               ' re-run without cache.')
+
+            log = oldlog + log
+
+            # write the new cachefile
+            ui.note(_('writing cvs log cache %s\n') % cachefile)
+            pickle.dump(log, file(cachefile, 'w'))
+        else:
+            log = oldlog
+
+    ui.status(_('%d log entries\n') % len(log))
+
+    return log
+
+
+class changeset(object):
+    '''Class changeset has the following attributes:
+        .author    - author name as CVS knows it
+        .branch    - name of branch this changeset is on, or None
+        .comment   - commit message
+        .date      - the commit date as a (time,tz) tuple
+        .entries   - list of logentry objects in this changeset
+        .parents   - list of one or two parent changesets
+        .tags      - list of tags on this changeset
+    '''
+    def __init__(self, **entries):
+        self.__dict__.update(entries)
+
+def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
+    '''Convert log into changesets.'''
+
+    ui.status(_('creating changesets\n'))
+
+    # Merge changesets
+
+    listsort(log, key=lambda x:(x.comment, x.author, x.branch, x.date))
+
+    changesets = []
+    files = {}
+    c = None
+    for i, e in enumerate(log):
+
+        # Check if log entry belongs to the current changeset or not.
+        if not (c and
+                  e.comment == c.comment and
+                  e.author == c.author and
+                  e.branch == c.branch and
+                  ((c.date[0] + c.date[1]) <=
+                   (e.date[0] + e.date[1]) <=
+                   (c.date[0] + c.date[1]) + fuzz) and
+                  e.file not in files):
+            c = changeset(comment=e.comment, author=e.author,
+                          branch=e.branch, date=e.date, entries=[])
+            changesets.append(c)
+            files = {}
+            if len(changesets) % 100 == 0:
+                t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
+                ui.status(util.ellipsis(t, 80) + '\n')
+
+        c.entries.append(e)
+        files[e.file] = True
+        c.date = e.date       # changeset date is date of latest commit in it
+
+    # Sort files in each changeset
+
+    for c in changesets:
+        def pathcompare(l, r):
+            'Mimic cvsps sorting order'
+            l = l.split('/')
+            r = r.split('/')
+            nl = len(l)
+            nr = len(r)
+            n = min(nl, nr)
+            for i in range(n):
+                if i + 1 == nl and nl < nr:
+                    return -1
+                elif i + 1 == nr and nl > nr:
+                    return +1
+                elif l[i] < r[i]:
+                    return -1
+                elif l[i] > r[i]:
+                    return +1
+            return 0
+        def entitycompare(l, r):
+            return pathcompare(l.file, r.file)
+
+        c.entries.sort(entitycompare)
+
+    # Sort changesets by date
+
+    def cscmp(l, r):
+        d = sum(l.date) - sum(r.date)
+        if d:
+            return d
+
+        # detect vendor branches and initial commits on a branch
+        le = {}
+        for e in l.entries:
+            le[e.rcs] = e.revision
+        re = {}
+        for e in r.entries:
+            re[e.rcs] = e.revision
+
+        d = 0
+        for e in l.entries:
+            if re.get(e.rcs, None) == e.parent:
+                assert not d
+                d = 1
+                break
+
+        for e in r.entries:
+            if le.get(e.rcs, None) == e.parent:
+                assert not d
+                d = -1
+                break
+
+        return d
+
+    changesets.sort(cscmp)
+
+    # Collect tags
+
+    globaltags = {}
+    for c in changesets:
+        tags = {}
+        for e in c.entries:
+            for tag in e.tags:
+                # remember which is the latest changeset to have this tag
+                globaltags[tag] = c
+
+    for c in changesets:
+        tags = {}
+        for e in c.entries:
+            for tag in e.tags:
+                tags[tag] = True
+        # remember tags only if this is the latest changeset to have it
+        c.tags = util.sort([tag for tag in tags if globaltags[tag] is c])
+
+    # Find parent changesets, handle {{mergetobranch BRANCHNAME}}
+    # by inserting dummy changesets with two parents, and handle
+    # {{mergefrombranch BRANCHNAME}} by setting two parents.
+
+    if mergeto is None:
+        mergeto = r'{{mergetobranch ([-\w]+)}}'
+    if mergeto:
+        mergeto = re.compile(mergeto)
+
+    if mergefrom is None:
+        mergefrom = r'{{mergefrombranch ([-\w]+)}}'
+    if mergefrom:
+        mergefrom = re.compile(mergefrom)
+
+    versions = {}    # changeset index where we saw any particular file version
+    branches = {}    # changeset index where we saw a branch
+    n = len(changesets)
+    i = 0
+    while i<n:
+        c = changesets[i]
+
+        for f in c.entries:
+            versions[(f.rcs, f.revision)] = i
+
+        p = None
+        if c.branch in branches:
+            p = branches[c.branch]
+        else:
+            for f in c.entries:
+                p = max(p, versions.get((f.rcs, f.parent), None))
+
+        c.parents = []
+        if p is not None:
+            c.parents.append(changesets[p])
+
+        if mergefrom:
+            m = mergefrom.search(c.comment)
+            if m:
+                m = m.group(1)
+                if m == 'HEAD':
+                    m = None
+                if m in branches and c.branch != m:
+                    c.parents.append(changesets[branches[m]])
+
+        if mergeto:
+            m = mergeto.search(c.comment)
+            if m:
+                try:
+                    m = m.group(1)
+                    if m == 'HEAD':
+                        m = None
+                except:
+                    m = None   # if no group found then merge to HEAD
+                if m in branches and c.branch != m:
+                    # insert empty changeset for merge
+                    cc = changeset(author=c.author, branch=m, date=c.date,
+                            comment='convert-repo: CVS merge from branch %s' % c.branch,
+                            entries=[], tags=[], parents=[changesets[branches[m]], c])
+                    changesets.insert(i + 1, cc)
+                    branches[m] = i + 1
+
+                    # adjust our loop counters now we have inserted a new entry
+                    n += 1
+                    i += 2
+                    continue
+
+        branches[c.branch] = i
+        i += 1
+
+    # Number changesets
+
+    for i, c in enumerate(changesets):
+        c.id = i + 1
+
+    ui.status(_('%d changeset entries\n') % len(changesets))
+
+    return changesets

mercurial/graphmod.py

@@ -0,0 +1,74 b''
+# Revision graph generator for Mercurial
+#
+# Copyright 2008 Dirkjan Ochtman <[e-mail]>
+# Copyright 2007 Joel Rosdahl <[e-mail]>
+#
+# This software may be used and distributed according to the terms of
+# the GNU General Public License, incorporated herein by reference.
+
+from node import nullrev, short
+import ui, hg, util, templatefilters
+
+def graph(repo, start_rev, stop_rev):
+    """incremental revision grapher
+
+    This generator function walks through the revision history from
+    revision start_rev to revision stop_rev (which must be less than
+    or equal to start_rev) and for each revision emits tuples with the
+    following elements:
+
+      - Current node
+      - Column and color for the current node
+      - Edges; a list of (col, next_col, color) indicating the edges between
+        the current node and its parents.
+      - First line of the changeset description
+      - The changeset author
+      - The changeset date/time
+    """
+
+    assert start_rev >= stop_rev
+    curr_rev = start_rev
+    revs = []
+    cl = repo.changelog
+    colors = {}
+    new_color = 1
+
+    while curr_rev >= stop_rev:
+        node = cl.node(curr_rev)
+
+        # Compute revs and next_revs
+        if curr_rev not in revs:
+            revs.append(curr_rev) # new head
+            colors[curr_rev] = new_color
+            new_color += 1
+
+        idx = revs.index(curr_rev)
+        color = colors.pop(curr_rev)
+        next = revs[:]
+
+        # Add parents to next_revs
+        parents = [x for x in cl.parentrevs(curr_rev) if x != nullrev]
+        addparents = [p for p in parents if p not in next]
+        next[idx:idx + 1] = addparents
+
+        # Set colors for the parents
+        for i, p in enumerate(addparents):
+            if not i:
+                colors[p] = color
+            else:
+                colors[p] = new_color
+                new_color += 1
+
+        # Add edges to the graph
+        edges = []
+        for col, r in enumerate(revs):
+            if r in next:
+                edges.append((col, next.index(r), colors[r]))
+            elif r == curr_rev:
+                for p in parents:
+                    edges.append((col, next.index(p), colors[p]))
+
+        # Yield and move on
+        yield (repo[curr_rev], (idx, color), edges)
+        revs = next
+        curr_rev -= 1

mercurial/hgweb/webutil.py

@@ -0,0 +1,140 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, incorporated herein by reference.
+
+import os
+from mercurial.node import hex, nullid
+from mercurial.repo import RepoError
+from mercurial import 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 revnavgen(pos, pagelen, limit, nodefunc):
+    def seq(factor, limit=None):
+        if limit:
+            yield limit
+            if limit >= 20 and limit <= 40:
+                yield 50
+        else:
+            yield 1 * factor
+            yield 3 * factor
+        for f in seq(factor * 10):
+            yield f
+
+    def nav(**map):
+        l = []
+        last = 0
+        for f in seq(1, pagelen):
+            if f < pagelen or f <= last:
+                continue
+            if f > limit:
+                break
+            last = f
+            if pos + f < limit:
+                l.append(("+%d" % f, hex(nodefunc(pos + f).node())))
+            if pos - f >= 0:
+                l.insert(0, ("-%d" % f, hex(nodefunc(pos - f).node())))
+
+        try:
+            yield {"label": "(0)", "node": hex(nodefunc('0').node())}
+
+            for label, node in l:
+                yield {"label": label, "node": node}
+
+            yield {"label": "tip", "node": "tip"}
+        except RepoError:
+            pass
+
+    return nav
+
+def siblings(siblings=[], hiderev=None, **args):
+    siblings = [s for s in siblings if s.node() != nullid]
+    if len(siblings) == 1 and siblings[0].rev() == hiderev:
+        return
+    for s in siblings:
+        d = {'node': hex(s.node()), 'rev': s.rev()}
+        if hasattr(s, 'path'):
+            d['file'] = s.path()
+        d.update(args)
+        yield d
+
+def renamelink(fctx):
+    r = fctx.renamed()
+    if r:
+        return [dict(file=r[0], node=hex(r[1]))]
+    return []
+
+def nodetagsdict(repo, node):
+    return [{"name": i} for i in repo.nodetags(node)]
+
+def nodebranchdict(repo, ctx):
+    branches = []
+    branch = ctx.branch()
+    # If this is an empty repo, ctx.node() == nullid,
+    # ctx.branch() == 'default', but branchtags() is
+    # an empty dict. Using dict.get avoids a traceback.
+    if repo.branchtags().get(branch) == ctx.node():
+        branches.append({"name": branch})
+    return branches
+
+def nodeinbranch(repo, ctx):
+    branches = []
+    branch = ctx.branch()
+    if branch != 'default' and repo.branchtags().get(branch) != 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 cleanpath(repo, path):
+    path = path.lstrip('/')
+    return util.canonpath(repo.root, '', path)
+
+def changectx(repo, req):
+    changeid = "tip"
+    if 'node' in req.form:
+        changeid = req.form['node'][0]
+    elif 'manifest' in req.form:
+        changeid = req.form['manifest'][0]
+
+    try:
+        ctx = repo[changeid]
+    except RepoError:
+        man = repo.manifest
+        ctx = repo[man.linkrev(man.lookup(changeid))]
+
+    return ctx
+
+def filectx(repo, req):
+    path = cleanpath(repo, req.form['file'][0])
+    if 'node' in req.form:
+        changeid = req.form['node'][0]
+    else:
+        changeid = req.form['filenode'][0]
+    try:
+        fctx = repo[changeid][path]
+    except RepoError:
+        fctx = repo.filectx(path, fileid=changeid)
+
+    return fctx

mercurial/match.py

@@ -0,0 +1,47 b''
+import util
+
+class _match(object):
+    def __init__(self, root, cwd, files, mf, ap):
+        self._root = root
+        self._cwd = cwd
+        self._files = files
+        self._fmap = dict.fromkeys(files)
+        self.matchfn = mf
+        self._anypats = ap
+    def __call__(self, fn):
+        return self.matchfn(fn)
+    def __iter__(self):
+        for f in self._files:
+            yield f
+    def bad(self, f, msg):
+        return True
+    def dir(self, f):
+        pass
+    def missing(self, f):
+        pass
+    def exact(self, f):
+        return f in self._fmap
+    def rel(self, f):
+        return util.pathto(self._root, self._cwd, f)
+    def files(self):
+        return self._files
+    def anypats(self):
+        return self._anypats
+
+class always(_match):
+    def __init__(self, root, cwd):
+        _match.__init__(self, root, cwd, [], lambda f: True, False)
+
+class never(_match):
+    def __init__(self, root, cwd):
+        _match.__init__(self, root, cwd, [], lambda f: False, False)
+
+class exact(_match):
+    def __init__(self, root, cwd, files):
+        _match.__init__(self, root, cwd, files, lambda f: f in files, False)
+
+class match(_match):
+    def __init__(self, root, cwd, patterns, include, exclude, default):
+        f, mf, ap = util.matcher(root, cwd, patterns, include, exclude,
+                                 None, default)
+        _match.__init__(self, root, cwd, f, mf, ap)

mercurial/parsers.c

@@ -0,0 +1,169 b''
+/*
+ parsers.c - efficient content parsing
+
+ Copyright 2008 Matt Mackall <[e-mail]> and others
+
+ This software may be used and distributed according to the terms of
+ the GNU General Public License, incorporated herein by reference.
+*/
+
+#include <Python.h>
+#include <ctype.h>
+#include <string.h>
+
+static int hexdigit(char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+
+	if (c >= 'A' && c <= 'F')
+		return c - 'A' + 10;
+
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 10;
+	
+	return -1;
+}
+
+/*
+ * Turn a hex-encoded string into binary.
+ */
+static PyObject *unhexlify(const char *str, int len)
+{
+	PyObject *ret = NULL;
+	const char *c;
+	char *d;
+
+	if (len % 2) {
+		PyErr_SetString(PyExc_ValueError,
+				"input is not even in length");
+		goto bail;
+	}
+
+	ret = PyString_FromStringAndSize(NULL, len / 2);
+	if (!ret)
+		goto bail;
+
+	d = PyString_AsString(ret);
+	if (!d)
+		goto bail;
+
+	for (c = str; c < str + len;) {
+		int hi = hexdigit(*c++);
+		int lo = hexdigit(*c++);
+
+		if (hi == -1 || lo == -1) {
+			PyErr_SetString(PyExc_ValueError,
+					"input contains non-hex character");
+			goto bail;
+		}
+
+		*d++ = (hi << 4) | lo;
+	}
+	
+	goto done;
+	
+bail:
+	Py_XDECREF(ret);
+	ret = NULL;
+done:
+	return ret;
+}
+
+/*
+ * This code assumes that a manifest is stitched together with newline
+ * ('\n') characters.
+ */
+static PyObject *parse_manifest(PyObject *self, PyObject *args)
+{
+	PyObject *mfdict, *fdict;
+	char *str, *cur, *start, *zero;
+	int len;
+
+	if (!PyArg_ParseTuple(args, "O!O!s#:parse_manifest",
+			      &PyDict_Type, &mfdict,
+			      &PyDict_Type, &fdict,
+			      &str, &len))
+		goto quit;
+
+	for (start = cur = str, zero = NULL; cur < str + len; cur++) {
+		PyObject *file = NULL, *node = NULL;
+		PyObject *flags = NULL;
+		int nlen;
+
+		if (!*cur) {
+			zero = cur;
+			continue;
+		}
+		else if (*cur != '\n')
+			continue;
+
+		if (!zero) {
+			PyErr_SetString(PyExc_ValueError,
+					"manifest entry has no separator");
+			goto quit;
+		}
+
+		file = PyString_FromStringAndSize(start, zero - start);
+		if (!file)
+			goto bail;
+
+		nlen = cur - zero - 1;
+
+		node = unhexlify(zero + 1, nlen > 40 ? 40 : nlen);
+		if (!node)
+			goto bail;
+
+		if (nlen > 40) {
+			PyObject *flags;
+
+			flags = PyString_FromStringAndSize(zero + 41,
+							   nlen - 40);
+			if (!flags)
+				goto bail;
+
+			if (PyDict_SetItem(fdict, file, flags) == -1)
+				goto bail;
+		}
+
+		if (PyDict_SetItem(mfdict, file, node) == -1)
+			goto bail;
+
+		start = cur + 1;
+		zero = NULL;
+
+		Py_XDECREF(flags);
+		Py_XDECREF(node);
+		Py_XDECREF(file);
+		continue;
+	bail:
+		Py_XDECREF(flags);
+		Py_XDECREF(node);
+		Py_XDECREF(file);
+		goto quit;
+	}
+
+	if (len > 0 && *(cur - 1) != '\n') {
+		PyErr_SetString(PyExc_ValueError,
+				"manifest contains trailing garbage");
+		goto quit;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+
+quit:
+	return NULL;
+}
+
+static char parsers_doc[] = "Efficient content parsing.";
+
+static PyMethodDef methods[] = {
+	{"parse_manifest", parse_manifest, METH_VARARGS, "parse a manifest\n"},
+	{NULL, NULL}
+};
+
+PyMODINIT_FUNC initparsers(void)
+{
+	Py_InitModule3("parsers", methods, parsers_doc);
+}

mercurial/store.py

@@ -0,0 +1,125 b''
+# store.py - repository store handling 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, incorporated herein by reference.
+
+import os, stat, osutil, util
+
+def _buildencodefun():
+    e = '_'
+    win_reserved = [ord(x) for x in '\\:*?"<>|']
+    cmap = dict([ (chr(x), chr(x)) for x in xrange(127) ])
+    for x in (range(32) + range(126, 256) + win_reserved):
+        cmap[chr(x)] = "~%02x" % x
+    for x in range(ord("A"), ord("Z")+1) + [ord(e)]:
+        cmap[chr(x)] = e + chr(x).lower()
+    dmap = {}
+    for k, v in cmap.iteritems():
+        dmap[v] = k
+    def decode(s):
+        i = 0
+        while i < len(s):
+            for l in xrange(1, 4):
+                try:
+                    yield dmap[s[i:i+l]]
+                    i += l
+                    break
+                except KeyError:
+                    pass
+            else:
+                raise KeyError
+    return (lambda s: "".join([cmap[c] for c in s]),
+            lambda s: "".join(list(decode(s))))
+
+encodefilename, decodefilename = _buildencodefun()
+
+def _dirwalk(path, recurse):
+    '''yields (filename, size)'''
+    for e, kind, st in osutil.listdir(path, stat=True):
+        pe = os.path.join(path, e)
+        if kind == stat.S_IFDIR:
+            if recurse:
+                for x in _dirwalk(pe, True):
+                    yield x
+        elif kind == stat.S_IFREG:
+            yield pe, st.st_size
+
+class _store:
+    '''base class for local repository stores'''
+    def __init__(self, path):
+        self.path = path
+        try:
+            # files in .hg/ will be created using this mode
+            mode = os.stat(self.path).st_mode
+            # avoid some useless chmods
+            if (0777 & ~util._umask) == (0777 & mode):
+                mode = None
+        except OSError:
+            mode = None
+        self.createmode = mode
+
+    def join(self, f):
+        return os.path.join(self.path, f)
+
+    def _revlogfiles(self, relpath='', recurse=False):
+        '''yields (filename, size)'''
+        if relpath:
+            path = os.path.join(self.path, relpath)
+        else:
+            path = self.path
+        striplen = len(self.path) + len(os.sep)
+        filetypes = ('.d', '.i')
+        for f, size in _dirwalk(path, recurse):
+            if (len(f) > 2) and f[-2:] in filetypes:
+                yield util.pconvert(f[striplen:]), size
+
+    def _datafiles(self):
+        for x in self._revlogfiles('data', True):
+            yield x
+
+    def walk(self):
+        '''yields (direncoded filename, size)'''
+        # yield data files first
+        for x in self._datafiles():
+            yield x
+        # yield manifest before changelog
+        meta = util.sort(self._revlogfiles())
+        meta.reverse()
+        for x in meta:
+            yield x
+
+class directstore(_store):
+    def __init__(self, path):
+        _store.__init__(self, path)
+        self.encodefn = lambda x: x
+        self.opener = util.opener(self.path)
+        self.opener.createmode = self.createmode
+
+class encodedstore(_store):
+    def __init__(self, path):
+        _store.__init__(self, os.path.join(path, 'store'))
+        self.encodefn = encodefilename
+        op = util.opener(self.path)
+        op.createmode = self.createmode
+        self.opener = lambda f, *args, **kw: op(self.encodefn(f), *args, **kw)
+
+    def _datafiles(self):
+        for f, size in self._revlogfiles('data', True):
+            yield decodefilename(f), size
+
+    def join(self, f):
+        return os.path.join(self.path, self.encodefn(f))
+
+def encodefn(requirements):
+    if 'store' not in requirements:
+        return lambda x: x
+    else:
+        return encodefilename
+
+def store(requirements, path):
+    if 'store' not in requirements:
+        return directstore(path)
+    else:
+        return encodedstore(path)

templates/coal/changeset.tmpl

@@ -0,0 +1,72 b''
+{header}
+<title>{repo|escape}: {node|short}</title>
+</head>
+<body>
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+ <li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+ <li><a href="{url}graph/{node|short}{sessionvars%urlparameter}">graph</a></li>
+ <li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+<ul>
+ <li class="active">changeset</li>
+ <li><a href="{url}file/{node|short}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+<ul>
+ {archives%archiveentry}</ul>
+</ul>
+</div>
+
+<div class="main">
+
+<h2>{repo|escape}</h2>
+<h3>changeset {rev}:{node|short} {changesettag}</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="description">{desc|strip|escape|addbreaks}</div>
+
+<table id="changesetEntry">
+<tr>
+ <th class="author">author</th>
+ <td class="author">{author|obfuscate}</td>
+</tr>
+<tr>
+ <th class="date">date</th>
+ <td class="date">{date|date} ({date|age} ago)</td></tr>
+<tr>
+ <th class="author">parents</th>
+ <td class="author">{parent%changesetparent}</td>
+</tr>
+<tr>
+ <th class="author">children</th>
+ <td class="author">{child%changesetchild}</td>
+</tr>
+<tr>
+ <th class="files">files</th>
+ <td class="files">{files}</td></tr>
+</tr>
+</table>
+<tr>
+
+<div class="overflow">
+<table class="bigtable">
+<tr>
+ <th class="lineno">line</th>
+ <th class="source">diff</th>
+</tr>
+</table>
+{diff}
+</div>
+</div>
+{footer}
+
+

templates/coal/error.tmpl

@@ -0,0 +1,40 b''
+{header}
+<title>{repo|escape}: error</title>
+</head>
+<body>
+
+<div class="content">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}log{sessionvars%urlparameter}">log</a></li>
+<li><a href="{url}graph{sessionvars%urlparameter}">graph</a></li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+</div>
+
+<div class="main">
+
+<h2>{repo|escape}</h2>
+<h3>error</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="description">
+<p>
+An error occurred while processing your request:
+</p>
+<p>
+{error|escape}
+</p>
+</div>
+</div>
+</div>
+
+{footer}

templates/coal/fileannotate.tmpl

@@ -0,0 +1,77 b''
+{header}
+<title>{repo|escape}: {file|escape} annotate</title>
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+<li><a href="{url}graph/{node|short}{sessionvars%urlparameter}">graph</a></li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+
+<ul>
+<li><a href="{url}rev/{node|short}{sessionvars%urlparameter}">changeset</a></li>
+<li><a href="{url}file/{node|short}{path|urlescape}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+<ul>
+<li><a href="{url}file/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file</a></li>
+<li><a href="{url}diff/{node|short}/{file|urlescape}{sessionvars%urlparameter}">diff</a></li>
+<li class="active">annotate</li>
+<li><a href="{url}log/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file log</a></li>
+<li><a href="{url}raw-annotate/{node|short}/{file|urlescape}">raw</a></li>
+</ul>
+</div>
+
+<div class="main">
+<h2>{repo|escape}</h2>
+<h3>annotate {file|escape} @ {rev}:{node|short}</h2>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="description">{desc|strip|escape|addbreaks}</div>
+
+<table id="changesetEntry">
+<tr>
+ <th class="author">author</th>
+ <td class="author">{author|obfuscate}</td>
+</tr>
+<tr>
+ <th class="date">date</th>
+ <td class="date">{date|date} ({date|age} ago)</td>
+</tr>
+<tr>
+ <th class="author">parents</th>
+ <td class="author">{parent%filerevparent}</td>
+</tr>
+<tr>
+ <th class="author">children</th>
+ <td class="author">{child%filerevchild}</td>
+</tr>
+{changesettag}
+</table>
+
+<br/>
+
+<div class="overflow">
+<table class="bigtable">
+<tr>
+ <th class="annotate">rev</th>
+ <th class="lineno">line</th>
+ <th class="line">source</th>
+</tr>
+{annotate%annotateline}
+</table>
+</div>
+</div>
+</div>
+
+{footer}

templates/coal/filediff.tmpl

@@ -0,0 +1,75 b''
+{header}
+<title>{repo|escape}: {file|escape} diff</title>
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+<li><a href="{url}graph/{node|short}{sessionvars%urlparameter}">graph</a></li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+<ul>
+<li><a href="{url}rev/{node|short}{sessionvars%urlparameter}">changeset</a></li>
+<li><a href="{url}file/{node|short}{path|urlescape}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+<ul>
+<li><a href="{url}file/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file</a></li>
+<li class="active">diff</li>
+<li><a href="{url}annotate/{node|short}/{file|urlescape}{sessionvars%urlparameter}">annotate</a></li>
+<li><a href="{url}log/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file log</a></li>
+<li><a href="{url}raw-file/{node|short}/{file|urlescape}">raw</a></li>
+</ul>
+</div>
+
+<div class="main">
+<h2>{repo|escape}</h2>
+<h3>diff {file|escape} @ {rev}:{node|short}</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="description">{desc|strip|escape|addbreaks}</div>
+
+<table id="changesetEntry">
+<tr>
+ <th>author</th>
+ <td>{author|obfuscate}</td>
+</tr>
+<tr>
+ <th>date</th>
+ <td>{date|date} ({date|age} ago)</td>
+</tr>
+<tr>
+ <th>parents</th>
+ <td>{parent%filerevparent}</td>
+</tr>
+<tr>
+ <th>children</th>
+ <td>{child%filerevchild}</td>
+</tr>
+{changesettag}
+</table>
+
+<div class="overflow">
+<table class="bigtable">
+<tr>
+ <th class="lineno">line</th>
+ <th class="source">diff</th>
+</tr>
+<table>
+{diff}
+</div>
+</div>	
+</div>
+
+{footer}
+
+

templates/coal/filelog.tmpl

@@ -0,0 +1,59 b''
+{header}
+<title>{repo|escape}: {file|escape} history</title>
+<link rel="alternate" type="application/atom+xml"
+   href="{url}atom-log/tip/{file|urlescape}" title="Atom feed for {repo|escape}:{file}">
+<link rel="alternate" type="application/rss+xml"
+   href="{url}rss-log/tip/{file|urlescape}" title="RSS feed for {repo|escape}:{file}">
+</head>
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+<li><a href="{url}graph/{node|short}{sessionvars%urlparameter}">graph</a></li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+<ul>
+<li><a href="{url}rev/{node|short}{sessionvars%urlparameter}">changeset</a></li>
+<li><a href="{url}file/{node|short}{path|urlescape}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+<ul>
+<li><a href="{url}file/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file</a></li>
+<li><a href="{url}diff/{node|short}/{file|urlescape}{sessionvars%urlparameter}">diff</a></li>
+<li><a href="{url}annotate/{node|short}/{file|urlescape}{sessionvars%urlparameter}">annotate</a></li>
+<li class="active">file log</li>
+<li><a href="{url}raw-file/{node|short}/{file|urlescape}">raw</a></li>
+</ul>
+</div>
+
+<div class="main">
+
+<h2>{repo|escape}</h2>
+<h3>log {file|escape}</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="navigate">{nav%filenaventry}</div>
+
+<table class="bigtable">
+ <tr> 
+  <th class="age">age</td>
+  <th class="author">author</td>
+  <th class="description">description</td>
+ </tr>
+{entries%filelogentry}
+</table>
+
+</div>
+</div>
+
+{footer}

templates/coal/filelogentry.tmpl

@@ -0,0 +1,5 b''
+ <tr class="parity{parity}">
+  <td class="age">{date|age}</td>
+  <td class="author">{author|person}</td>
+  <td class="description"><a href="{url}rev/{node|short}{sessionvars%urlparameter}">{desc|strip|firstline|escape}</a></td>
+ </tr>

templates/coal/filerevision.tmpl

@@ -0,0 +1,74 b''
+{header}
+<title>{repo|escape}: {node|short} {file|escape}</title>
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+<li><a href="{url}graph/{node|short}{sessionvars%urlparameter}">graph</a></li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+<ul>
+<li><a href="{url}rev/{node|short}{sessionvars%urlparameter}">changeset</a></li>
+<li><a href="{url}file/{node|short}{path|urlescape}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+<ul>
+<li class="active">file</li>
+<li><a href="{url}diff/{node|short}/{file|urlescape}{sessionvars%urlparameter}">diff</a></li>
+<li><a href="{url}annotate/{node|short}/{file|urlescape}{sessionvars%urlparameter}">annotate</a></li>
+<li><a href="{url}log/{node|short}/{file|urlescape}{sessionvars%urlparameter}">file log</a></li>
+<li><a href="{url}raw-file/{node|short}/{file|urlescape}">raw</a></li>
+</ul>
+</div>
+
+<div class="main">
+
+<h2>{repo|escape}</h2>
+<h3>view {file|escape} @ {rev}:{node|short}</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="description">{desc|strip|escape|addbreaks}</div>
+
+<table id="changesetEntry">
+<tr>
+ <th class="author">author</th>
+ <td class="author">{author|obfuscate}</td>
+</tr>
+<tr>
+ <th class="date">date</th>
+ <td class="date">{date|date} ({date|age} ago)</td>
+</tr>
+<tr>
+ <th class="author">parents</th>
+ <td class="author">{parent%filerevparent}</td>
+</tr>
+<tr>
+ <th class="author">children</th>
+ <td class="author">{child%filerevchild}</td>
+</tr>
+{changesettag}
+</table>
+
+<div class="overflow">
+<table class="bigtable">
+<tr>
+ <th class="lineno">line</th>
+ <th class="source">source</th>
+</tr>
+{text%fileline}
+</table>
+</div>
+</div>
+</div>
+
+{footer}

templates/coal/footer.tmpl

@@ -0,0 +1,4 b''
+{motd}
+
+</body>
+</html>

templates/coal/graph.tmpl

@@ -0,0 +1,113 b''
+{header}
+<title>{repo|escape}: revision graph</title>
+<link rel="alternate" type="application/atom+xml"
+   href="{url}atom-log" title="Atom feed for {repo|escape}: log">
+<link rel="alternate" type="application/rss+xml"
+   href="{url}rss-log" title="RSS feed for {repo|escape}: log">
+<!--[if IE]><script type="text/javascript" src="{staticurl}excanvas.js"></script><![endif]-->
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<div class="logo">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<ul>
+<li><a href="{url}shortlog/{node|short}{sessionvars%urlparameter}">log</a></li>
+<li class="active">graph</li>
+<li><a href="{url}tags{sessionvars%urlparameter}">tags</a></li>
+</ul>
+<ul>
+<li><a href="{url}rev/{node|short}{sessionvars%urlparameter}">changeset</a></li>
+<li><a href="{url}file/{node|short}{path|urlescape}{sessionvars%urlparameter}">browse</a></li>
+</ul>
+</div>
+
+<div class="main">
+<h2>{repo|escape}</h2>
+<h3>graph</h3>
+
+<form class="search" action="{url}log">
+{sessionvars%hiddenformentry}
+<p><input name="rev" id="search1" type="text" size="30"></p>
+</form>
+
+<div class="navigate">
+<a href="{url}graph/{uprev}{sessionvars%urlparameter}?revcount={revcountless}">less</a>
+<a href="{url}graph/{uprev}{sessionvars%urlparameter}?revcount={revcountmore}">more</a>
+| {changenav%navgraphentry}
+</div>
+
+<div id="noscript">The revision graph only works with JavaScript-enabled browsers.</div>
+
+<div id="wrapper">
+<ul id="nodebgs"></ul>
+<canvas id="graph" width="224" height="{canvasheight}"></canvas>
+<ul id="graphnodes"></ul>
+</div>
+
+<script type="text/javascript" src="{staticurl}graph.js"></script>
+<script>
+<!-- hide script content
+
+document.getElementById('noscript').style.display = 'none';
+
+var data = {jsdata|json};
+var graph = new Graph();
+graph.scale({bg_height});
+
+graph.edge = function(x0, y0, x1, y1, color) {
+	
+	this.setColor(color, 0.0, 0.65);
+	this.ctx.beginPath();
+	this.ctx.moveTo(x0, y0);
+	this.ctx.lineTo(x1, y1);
+	this.ctx.stroke();
+	
+}
+
+var revlink = '<li style="_STYLE"><span class="desc">';
+revlink += '<a href="{url}rev/_NODEID{sessionvars%urlparameter}" title="_NODEID">_DESC</a>';
+revlink += '</span><span class="tag">_TAGS</span>';
+revlink += '<span class="info">_DATE ago, by _USER</span></li>';
+
+graph.vertex = function(x, y, color, parity, cur) {
+	
+	this.ctx.beginPath();
+	color = this.setColor(color, 0.25, 0.75);
+	this.ctx.arc(x, y, radius, 0, Math.PI * 2, true);
+	this.ctx.fill();
+	
+	var bg = '<li class="bg parity' + parity + '"></li>';
+	var left = (this.columns + 1) * this.bg_height;
+	var nstyle = 'padding-left: ' + left + 'px;';
+	var item = revlink.replace(/_STYLE/, nstyle);
+	item = item.replace(/_PARITY/, 'parity' + parity);
+	item = item.replace(/_NODEID/, cur[0]);
+	item = item.replace(/_NODEID/, cur[0]);
+	item = item.replace(/_DESC/, cur[3]);
+	item = item.replace(/_USER/, cur[4]);
+	item = item.replace(/_DATE/, cur[5]);
+	item = item.replace(/_TAGS/, cur[7].join('&nbsp; '));
+	
+	return [bg, item];
+	
+}
+
+graph.render(data);
+
+// stop hiding script -->
+</script>
+
+<div class="navigate">
+<a href="{url}graph/{uprev}{sessionvars%urlparameter}?revcount={revcountless}">less</a>
+<a href="{url}graph/{uprev}{sessionvars%urlparameter}?revcount={revcountmore}">more</a>
+| {changenav%navgraphentry}
+</div>
+
+</div>
+</div>
+
+{footer}

templates/coal/header.tmpl

@@ -0,0 +1,7 b''
+<!-- quirksmode -->
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html>
+<head>
+<link rel="icon" href="{staticurl}hgicon.png" type="image/png">
+<meta name="robots" content="index, nofollow" />
+<link rel="stylesheet" href="{staticurl}style-coal.css" type="text/css" />

templates/coal/index.tmpl

@@ -0,0 +1,26 b''
+{header}
+<title>Mercurial repositories index</title>
+</head>
+<body>
+
+<div class="container">
+<div class="menu">
+<a href="http://www.selenic.com/mercurial/">
+<img src="{staticurl}hglogo.png" width=75 height=90 border=0 alt="mercurial"></a>
+</div>
+<div class="main">
+<h2>Mercurial Repositories</h2>
+
+<table class="bigtable">
+    <tr>
+        <th><a href="?sort={sort_name}">Name</a></th>
+        <th><a href="?sort={sort_description}">Description</a></th>
+        <th><a href="?sort={sort_contact}">Contact</a></th>
+        <th><a href="?sort={sort_lastchange}">Last change</a></th>
+        <th>&nbsp;</th>
+    <tr>
+    {entries%indexentry}
+</table>
+</div>
+</div>
+{footer}

.hgignore

@@ -7,6 +7,7 b' syntax: glob'
 *.mergebackup
 *.o
 *.so
+*.pyd
 *.pyc
 *.swp
 *.prof

contrib/mercurial.el

@@ -35,8 +35,10 b''
 ;; This code has been developed under XEmacs 21.5, and may not work as
 ;; well under GNU Emacs (albeit tested under 21.4).  Patches to
 ;; enhance the portability of this code, fix bugs, and add features
-;; are most welcome.  You can clone a Mercurial repository for this
-;; package from http://www.serpentine.com/hg/hg-emacs
+;; are most welcome.
+
+;; As of version 22.3, GNU Emacs's VC mode has direct support for
+;; Mercurial, so this package may not prove as useful there.
 
 ;; Please send problem reports and suggestions to [e-mail].
 

contrib/zsh_completion

@@ -205,8 +205,7 b' typeset -A _hg_cmd_globals'
 
 _hg_config() {
     typeset -a items
-    local line
-    items=(${${(%f)"$(_hg_cmd showconfig)"}%%\=*})
+    items=(${${(%f)"$(_call_program hg hg showconfig)"}%%\=*})
     (( $#items )) && _describe -t config 'config item' items
 }
 
@@ -291,10 +290,14 b' typeset -A _hg_cmd_globals'
     '--cwd[change working directory]:new working directory:_files -/'
     '(--noninteractive -y)'{-y,--noninteractive}'[do not prompt, assume yes for any required answers]'
     '(--verbose -v)'{-v,--verbose}'[enable additional output]'
+    '*--config[set/override config option]:defined config items:_hg_config'
     '(--quiet -q)'{-q,--quiet}'[suppress output]'
     '(--help -h)'{-h,--help}'[display help and exit]'
     '--debug[debug mode]'
     '--debugger[start debugger]'
+    '--encoding[set the charset encoding (default: UTF8)]'
+    '--encodingmode[set the charset encoding mode (default: strict)]'
+    '--lsprof[print improved command execution profile]'
     '--traceback[print traceback on exception]'
     '--time[time how long the command takes]'
     '--profile[profile]'

doc/gendoc.py

@@ -69,6 +69,7 b' def show_doc(ui):'
         if f.startswith("debug"): continue
         d = get_cmd(h[f])
         # synopsis
+        ui.write("[[%s]]\n" % d['cmd'])
         ui.write("%s::\n" % d['synopsis'].replace("hg ","", 1))
         # description
         ui.write("%s\n\n" % d['desc'][1])
@@ -91,11 +92,10 b' def show_doc(ui):'
             ui.write(_("    aliases: %s\n\n") % " ".join(d['aliases']))
 
     # print topics
-    for t in helptable:
+    for t, doc in helptable:
         l = t.split("|")
         section = l[-1]
         underlined(_(section).upper())
-        doc = helptable[t]
         if callable(doc):
             doc = doc()
         ui.write(_(doc))

doc/hg.1.txt

@@ -30,65 +30,13 b' revision::'
 
 repository path::
     either the pathname of a local repository or the URI of a remote
-    repository.  There are two available URI protocols, http:// which is
+    repository. There are two available URI protocols, http:// which is
     fast and the static-http:// protocol which is much slower but does not
     require a special server on the web host.
 
 
 include::hg.1.gendoc.txt[]
 
-SPECIFYING SINGLE REVISIONS
----------------------------
-
-    Mercurial accepts several notations for identifying individual
-    revisions.
-
-    A plain integer is treated as a revision number.  Negative
-    integers are treated as offsets from the tip, with -1 denoting the
-    tip.
-
-    A 40-digit hexadecimal string is treated as a unique revision
-    identifier.
-
-    A hexadecimal string less than 40 characters long is treated as a
-    unique revision identifier, and referred to as a short-form
-    identifier.  A short-form identifier is only valid if it is the
-    prefix of one full-length identifier.
-
-    Any other string is treated as a tag name, which is a symbolic
-    name associated with a revision identifier.  Tag names may not
-    contain the ":" character.
-
-    The reserved name "tip" is a special tag that always identifies
-    the most recent revision.
-
-    The reserved name "null" indicates the null revision. This is the
-    revision of an empty repository, and the parent of revision 0.
-
-    The reserved name "." indicates the working directory parent. If
-    no working directory is checked out, it is equivalent to null.
-    If an uncommitted merge is in progress, "." is the revision of
-    the first parent.
-
-SPECIFYING MULTIPLE REVISIONS
------------------------------
-
-    When Mercurial accepts more than one revision, they may be
-    specified individually, or provided as a continuous range,
-    separated by the ":" character.
-
-    The syntax of range notation is [BEGIN]:[END], where BEGIN and END
-    are revision identifiers.  Both BEGIN and END are optional.  If
-    BEGIN is not specified, it defaults to revision number 0.  If END
-    is not specified, it defaults to the tip.  The range ":" thus
-    means "all revisions".
-
-    If BEGIN is greater than END, revisions are treated in reverse
-    order.
-
-    A range acts as a closed interval.  This means that a range of 3:5
-    gives 3, 4 and 5.  Similarly, a range of 4:2 gives 4, 3, and 2.
-
 FILES
 -----
  .hgignore::
@@ -103,7 +51,7 b' FILES'
  /etc/mercurial/hgrc, $HOME/.hgrc, .hg/hgrc::
     This file contains defaults and configuration. Values in .hg/hgrc
     override those in $HOME/.hgrc, and these override settings made in the
-    global /etc/mercurial/hgrc configuration.  See hgrc(5) for details of
+    global /etc/mercurial/hgrc configuration. See hgrc(5) for details of
     the contents and format of these files.
 
 Some commands (e.g. revert) produce backup files ending in .orig, if

doc/hgignore.5.txt

@@ -17,25 +17,25 b' DESCRIPTION'
 -----------
 
 Mercurial ignores every unmanaged file that matches any pattern in an
-ignore file.  The patterns in an ignore file do not apply to files
-managed by Mercurial.  To control Mercurial's handling of files that
-it manages, see the hg(1) man page.  Look for the "-I" and "-X"
+ignore file. The patterns in an ignore file do not apply to files
+managed by Mercurial. To control Mercurial's handling of files that
+it manages, see the hg(1) man page. Look for the "-I" and "-X"
 options.
 
 In addition, a Mercurial configuration file can point to a set of
-per-user or global ignore files.  See the hgrc(5) man page for details
-of how to configure these files.  Look for the "ignore" entry in the
+per-user or global ignore files. See the hgrc(5) man page for details
+of how to configure these files. Look for the "ignore" entry in the
 "ui" section.
 
 SYNTAX
 ------
 
 An ignore file is a plain text file consisting of a list of patterns,
-with one pattern per line.  Empty lines are skipped.  The "#"
+with one pattern per line. Empty lines are skipped. The "#"
 character is treated as a comment character, and the "\" character is
 treated as an escape character.
 
-Mercurial supports several pattern syntaxes.  The default syntax used
+Mercurial supports several pattern syntaxes. The default syntax used
 is Python/Perl-style regular expressions.
 
 To change the syntax used, use a line of the following form:
@@ -52,9 +52,9 b' glob::'
 The chosen syntax stays in effect when parsing all patterns that
 follow, until another syntax is selected.
 
-Neither glob nor regexp patterns are rooted.  A glob-syntax pattern of
+Neither glob nor regexp patterns are rooted. A glob-syntax pattern of
 the form "*.c" will match a file ending in ".c" in any directory, and
-a regexp pattern of the form "\.c$" will do the same.  To root a
+a regexp pattern of the form "\.c$" will do the same. To root a
 regexp pattern, start it with "^".
 
 EXAMPLE

doc/hgrc.5.txt

@@ -17,26 +17,26 b' FILES'
 
 Mercurial reads configuration data from several files, if they exist.
 The names of these files depend on the system on which Mercurial is
-installed.  *.rc files from a single directory are read in
-alphabetical order, later ones overriding earlier ones.  Where
+installed. *.rc files from a single directory are read in
+alphabetical order, later ones overriding earlier ones. Where
 multiple paths are given below, settings from later paths override
 earlier ones.
 
 (Unix) <install-root>/etc/mercurial/hgrc.d/*.rc::
 (Unix) <install-root>/etc/mercurial/hgrc::
     Per-installation configuration files, searched for in the
-    directory where Mercurial is installed.  <install-root> is the
+    directory where Mercurial is installed. <install-root> is the
     parent directory of the hg executable (or symlink) being run.
     For example, if installed in /shared/tools/bin/hg, Mercurial will
-    look in /shared/tools/etc/mercurial/hgrc.  Options in these files
+    look in /shared/tools/etc/mercurial/hgrc. Options in these files
     apply to all Mercurial commands executed by any user in any
     directory.
 
 (Unix) /etc/mercurial/hgrc.d/*.rc::
 (Unix) /etc/mercurial/hgrc::
     Per-system configuration files, for the system on which Mercurial
-    is running.  Options in these files apply to all Mercurial
-    commands executed by any user in any directory.  Options in these
+    is running. Options in these files apply to all Mercurial
+    commands executed by any user in any directory. Options in these
     files override per-installation options.
 
 (Windows) <install-dir>\Mercurial.ini::
@@ -45,7 +45,7 b' earlier ones.'
   or else::
 (Windows) C:\Mercurial\Mercurial.ini::
     Per-installation/system configuration files, for the system on
-    which Mercurial is running.  Options in these files apply to all
+    which Mercurial is running. Options in these files apply to all
     Mercurial commands executed by any user in any directory.
     Registry keys contain PATH-like strings, every part of which must
     reference a Mercurial.ini file or be a directory where *.rc files
@@ -59,16 +59,16 b' earlier ones.'
     Per-user configuration file(s), for the user running Mercurial.
     On Windows 9x, %HOME% is replaced by %APPDATA%.
     Options in these files apply to all Mercurial commands executed
-    by this user in any directory.  Options in thes files override
+    by this user in any directory. Options in thes files override
     per-installation and per-system options.
 
 (Unix, Windows) <repo>/.hg/hgrc::
     Per-repository configuration options that only apply in a
-    particular repository.  This file is not version-controlled, and
-    will not get transferred during a "clone" operation.  Options in
+    particular repository. This file is not version-controlled, and
+    will not get transferred during a "clone" operation. Options in
     this file override options in all other configuration files.
     On Unix, most of this file will be ignored if it doesn't belong
-    to a trusted user or to a trusted group.  See the documentation
+    to a trusted user or to a trusted group. See the documentation
     for the trusted section below for more details.
 
 SYNTAX
@@ -82,10 +82,10 b' and followed by "name: value" entries; "'
     green=
        eggs
 
-Each line contains one entry.  If the lines that follow are indented,
+Each line contains one entry. If the lines that follow are indented,
 they are treated as continuations of that entry.
 
-Leading whitespace is removed from values.  Empty lines are skipped.
+Leading whitespace is removed from values. Empty lines are skipped.
 
 The optional values can contain format strings which refer to other
 values in the same section, or values in a special DEFAULT section.
@@ -100,6 +100,7 b' This section describes the different sec'
 Mercurial "hgrc" file, the purpose of each section, its possible
 keys, and their possible values.
 
+[[decode]]
 decode/encode::
   Filters for transforming files on checkout/checkin. This would
   typically be used for newline processing or other
@@ -107,12 +108,12 b' decode/encode::'
 
   Filters consist of a filter pattern followed by a filter command.
   Filter patterns are globs by default, rooted at the repository
-  root.  For example, to match any file ending in ".txt" in the root
-  directory only, use the pattern "*.txt".  To match any file ending
+  root. For example, to match any file ending in ".txt" in the root
+  directory only, use the pattern "*.txt". To match any file ending
   in ".c" anywhere in the repository, use the pattern "**.c".
 
   The filter command can start with a specifier, either "pipe:" or
-  "tempfile:".  If no specifier is given, "pipe:" is used by default.
+  "tempfile:". If no specifier is given, "pipe:" is used by default.
 
   A "pipe:" command must accept data on stdin and return the
   transformed data on stdout.
@@ -129,9 +130,9 b' decode/encode::'
     # can safely omit "pipe:", because it's the default)
     *.gz = gzip
 
-  A "tempfile:" command is a template.  The string INFILE is replaced
+  A "tempfile:" command is a template. The string INFILE is replaced
   with the name of a temporary file that contains the data to be
-  filtered by the command.  The string OUTFILE is replaced with the
+  filtered by the command. The string OUTFILE is replaced with the
   name of an empty temporary file, where the filtered data must be
   written by the command.
 
@@ -158,6 +159,7 b' decode/encode::'
     [decode]
     **.txt = dumbdecode:
 
+[[defaults]]
 defaults::
   Use the [defaults] section to define command defaults, i.e. the
   default options/arguments to pass to the specified commands.
@@ -173,6 +175,7 b' defaults::'
   defining command defaults. The command defaults will also be
   applied to the aliases of the commands defined.
 
+[[diff]]
 diff::
   Settings used when displaying diffs. They are all boolean and
   defaults to False.
@@ -189,25 +192,26 b' diff::'
   ignoreblanklines;;
     Ignore changes whose lines are all blank.
 
+[[email]]
 email::
   Settings for extensions that send email messages.
   from;;
-    Optional.  Email address to use in "From" header and SMTP envelope
+    Optional. Email address to use in "From" header and SMTP envelope
     of outgoing messages.
   to;;
-    Optional.  Comma-separated list of recipients' email addresses.
+    Optional. Comma-separated list of recipients' email addresses.
   cc;;
-    Optional.  Comma-separated list of carbon copy recipients'
+    Optional. Comma-separated list of carbon copy recipients'
     email addresses.
   bcc;;
-    Optional.  Comma-separated list of blind carbon copy
-    recipients' email addresses.  Cannot be set interactively.
+    Optional. Comma-separated list of blind carbon copy
+    recipients' email addresses. Cannot be set interactively.
   method;;
-    Optional.  Method to use to send email messages.  If value is
+    Optional. Method to use to send email messages. If value is
     "smtp" (default), use SMTP (see section "[smtp]" for
-    configuration).  Otherwise, use as name of program to run that
+    configuration). Otherwise, use as name of program to run that
     acts like sendmail (takes "-f" option for sender, list of
-    recipients on command line, message on stdin).  Normally, setting
+    recipients on command line, message on stdin). Normally, setting
     this to "sendmail" or "/usr/sbin/sendmail" is enough to use
     sendmail to send messages.
 
@@ -217,6 +221,7 b' email::'
     from = Joseph User <[e-mail]>
     method = /usr/sbin/sendmail
 
+[[extensions]]
 extensions::
   Mercurial has an extension mechanism for adding new features. To
   enable an extension, create an entry for it in this section.
@@ -241,6 +246,7 b' extensions::'
     # (this extension will get loaded from the file specified)
     myfeature = ~/.hgext/myfeature.py
 
+[[format]]
 format::
 
   usestore;;
@@ -250,6 +256,7 b' format::'
     you to store longer filenames in some situations at the expense of
     compatibility.
 
+[[merge-patterns]]
 merge-patterns::
   This section specifies merge tools to associate with particular file
   patterns. Tools matched here will take precedence over the default
@@ -261,6 +268,7 b' merge-patterns::'
     **.c = kdiff3
     **.jpg = myimgmerge
 
+[[merge-tools]]
 merge-tools::
   This section configures external merge tools to use for file-level
   merges.
@@ -281,6 +289,7 b' merge-tools::'
     myHtmlTool.priority = 1
 
   Supported arguments:
+
   priority;;
     The priority in which to evaluate this tool.
     Default: 0.
@@ -297,10 +306,10 b' merge-tools::'
     launching external tool.
     Default: True
   binary;;
-    This tool can merge binary files.  Defaults to False, unless tool
+    This tool can merge binary files. Defaults to False, unless tool
     was selected by file pattern match.
   symlink;;
-    This tool can merge symlinks.  Defaults to False, even if tool was
+    This tool can merge symlinks. Defaults to False, even if tool was
     selected by file pattern match.
   checkconflicts;;
     Check whether there are conflicts even though the tool reported
@@ -313,19 +322,20 b' merge-tools::'
   fixeol;;
     Attempt to fix up EOL changes caused by the merge tool.
     Default: False
-  gui:;
+  gui;;
     This tool requires a graphical interface to run. Default: False
   regkey;;
     Windows registry key which describes install location of this tool.
     Mercurial will search for this key first under HKEY_CURRENT_USER and
-    then under HKEY_LOCAL_MACHINE.  Default: None
+    then under HKEY_LOCAL_MACHINE. Default: None
   regname;;
-    Name of value to read from specified registry key.  Defaults to the
+    Name of value to read from specified registry key. Defaults to the
     unnamed (default) value.
   regappend;;
     String to append to the value read from the registry, typically the
-    executable name of the tool.  Default: None
+    executable name of the tool. Default: None
 
+[[hooks]]
 hooks::
   Commands or Python functions that get automatically executed by
   various actions such as starting or finishing a commit. Multiple
@@ -342,24 +352,24 b' hooks::'
     incoming.autobuild = /my/build/hook
 
   Most hooks are run with environment variables set that give added
-  useful information.  For each hook below, the environment variables
+  useful information. For each hook below, the environment variables
   it is passed are listed with names of the form "$HG_foo".
 
   changegroup;;
     Run after a changegroup has been added via push, pull or
-    unbundle. ID of the first new changeset is in $HG_NODE.  URL from
+    unbundle. ID of the first new changeset is in $HG_NODE. URL from
     which changes came is in $HG_URL.
   commit;;
     Run after a changeset has been created in the local repository.
-    ID of the newly created changeset is in $HG_NODE.  Parent
+    ID of the newly created changeset is in $HG_NODE. Parent
     changeset IDs are in $HG_PARENT1 and $HG_PARENT2.
   incoming;;
     Run after a changeset has been pulled, pushed, or unbundled into
-    the local repository.  The ID of the newly arrived changeset is in
-    $HG_NODE.  URL that was source of changes came is in $HG_URL.
+    the local repository. The ID of the newly arrived changeset is in
+    $HG_NODE. URL that was source of changes came is in $HG_URL.
   outgoing;;
-    Run after sending changes from local repository to another.  ID of
-    first changeset sent is in $HG_NODE.  Source of operation is in
+    Run after sending changes from local repository to another. ID of
+    first changeset sent is in $HG_NODE. Source of operation is in
     $HG_SOURCE; see "preoutgoing" hook for description.
   post-<command>;;
     Run after successful invocations of the associated command. The
@@ -371,56 +381,56 b' hooks::'
     the command doesn't execute and Mercurial returns the failure code.
   prechangegroup;;
     Run before a changegroup is added via push, pull or unbundle.
-    Exit status 0 allows the changegroup to proceed.  Non-zero status
-    will cause the push, pull or unbundle to fail.  URL from which
+    Exit status 0 allows the changegroup to proceed. Non-zero status
+    will cause the push, pull or unbundle to fail. URL from which
     changes will come is in $HG_URL.
   precommit;;
-    Run before starting a local commit.  Exit status 0 allows the
-    commit to proceed.  Non-zero status will cause the commit to fail.
+    Run before starting a local commit. Exit status 0 allows the
+    commit to proceed. Non-zero status will cause the commit to fail.
     Parent changeset IDs are in $HG_PARENT1 and $HG_PARENT2.
   preoutgoing;;
     Run before collecting changes to send from the local repository to
-    another.  Non-zero status will cause failure.  This lets you
-    prevent pull over http or ssh.  Also prevents against local pull,
+    another. Non-zero status will cause failure. This lets you
+    prevent pull over http or ssh. Also prevents against local pull,
     push (outbound) or bundle commands, but not effective, since you
-    can just copy files instead then.  Source of operation is in
-    $HG_SOURCE.  If "serve", operation is happening on behalf of
-    remote ssh or http repository.  If "push", "pull" or "bundle",
+    can just copy files instead then. Source of operation is in
+    $HG_SOURCE. If "serve", operation is happening on behalf of
+    remote ssh or http repository. If "push", "pull" or "bundle",
     operation is happening on behalf of repository on same system.
   pretag;;
-    Run before creating a tag.  Exit status 0 allows the tag to be
-    created.  Non-zero status will cause the tag to fail.  ID of
-    changeset to tag is in $HG_NODE.  Name of tag is in $HG_TAG.  Tag
+    Run before creating a tag. Exit status 0 allows the tag to be
+    created. Non-zero status will cause the tag to fail. ID of
+    changeset to tag is in $HG_NODE. Name of tag is in $HG_TAG. Tag
     is local if $HG_LOCAL=1, in repo if $HG_LOCAL=0.
   pretxnchangegroup;;
     Run after a changegroup has been added via push, pull or unbundle,
-    but before the transaction has been committed.  Changegroup is
-    visible to hook program.  This lets you validate incoming changes
-    before accepting them.  Passed the ID of the first new changeset
-    in $HG_NODE.  Exit status 0 allows the transaction to commit.
+    but before the transaction has been committed. Changegroup is
+    visible to hook program. This lets you validate incoming changes
+    before accepting them. Passed the ID of the first new changeset
+    in $HG_NODE. Exit status 0 allows the transaction to commit.
     Non-zero status will cause the transaction to be rolled back and
-    the push, pull or unbundle will fail.  URL that was source of
+    the push, pull or unbundle will fail. URL that was source of
     changes is in $HG_URL.
   pretxncommit;;
     Run after a changeset has been created but the transaction not yet
-    committed.  Changeset is visible to hook program.  This lets you
-    validate commit message and changes.  Exit status 0 allows the
-    commit to proceed.  Non-zero status will cause the transaction to
-    be rolled back.  ID of changeset is in $HG_NODE.  Parent changeset
+    committed. Changeset is visible to hook program. This lets you
+    validate commit message and changes. Exit status 0 allows the
+    commit to proceed. Non-zero status will cause the transaction to
+    be rolled back. ID of changeset is in $HG_NODE. Parent changeset
     IDs are in $HG_PARENT1 and $HG_PARENT2.
   preupdate;;
-    Run before updating the working directory.  Exit status 0 allows
-    the update to proceed.  Non-zero status will prevent the update.
-    Changeset ID of first new parent is in $HG_PARENT1.  If merge, ID
+    Run before updating the working directory. Exit status 0 allows
+    the update to proceed. Non-zero status will prevent the update.
+    Changeset ID of first new parent is in $HG_PARENT1. If merge, ID
     of second new parent is in $HG_PARENT2.
   tag;;
-    Run after a tag is created.  ID of tagged changeset is in
-    $HG_NODE.  Name of tag is in $HG_TAG.  Tag is local if
+    Run after a tag is created. ID of tagged changeset is in
+    $HG_NODE. Name of tag is in $HG_TAG. Tag is local if
     $HG_LOCAL=1, in repo if $HG_LOCAL=0.
   update;;
-    Run after updating the working directory.  Changeset ID of first
-    new parent is in $HG_PARENT1.  If merge, ID of second new parent
-    is in $HG_PARENT2.  If update succeeded, $HG_ERROR=0.  If update
+    Run after updating the working directory. Changeset ID of first
+    new parent is in $HG_PARENT1. If merge, ID of second new parent
+    is in $HG_PARENT2. If update succeeded, $HG_ERROR=0. If update
     failed (e.g. because conflicts not resolved), $HG_ERROR=1.
 
   Note: it is generally better to use standard hooks rather than the
@@ -438,16 +448,17 b' hooks::'
 
     hookname = python:modulename.submodule.callable
 
-  Python hooks are run within the Mercurial process.  Each hook is
+  Python hooks are run within the Mercurial process. Each hook is
   called with at least three keyword arguments: a ui object (keyword
   "ui"), a repository object (keyword "repo"), and a "hooktype"
-  keyword that tells what kind of hook is used.  Arguments listed as
+  keyword that tells what kind of hook is used. Arguments listed as
   environment variables above are passed as keyword arguments, with no
   "HG_" prefix, and names in lower case.
 
   If a Python hook returns a "true" value or raises an exception, this
   is treated as failure of the hook.
 
+[[http_proxy]]
 http_proxy::
   Used to access web-based Mercurial repositories through a HTTP
   proxy.
@@ -455,68 +466,72 b' http_proxy::'
     Host name and (optional) port of the proxy server, for example
     "myproxy:8000".
   no;;
-    Optional.  Comma-separated list of host names that should bypass
+    Optional. Comma-separated list of host names that should bypass
     the proxy.
   passwd;;
-    Optional.  Password to authenticate with at the proxy server.
+    Optional. Password to authenticate with at the proxy server.
   user;;
-    Optional.  User name to authenticate with at the proxy server.
+    Optional. User name to authenticate with at the proxy server.
 
+[[smtp]]
 smtp::
   Configuration for extensions that need to send email messages.
   host;;
     Host name of mail server, e.g. "mail.example.com".
   port;;
-    Optional.  Port to connect to on mail server.  Default: 25.
+    Optional. Port to connect to on mail server. Default: 25.
   tls;;
-    Optional.  Whether to connect to mail server using TLS.  True or
-    False.  Default: False.
+    Optional. Whether to connect to mail server using TLS. True or
+    False. Default: False.
   username;;
-    Optional.  User name to authenticate to SMTP server with.
+    Optional. User name to authenticate to SMTP server with.
     If username is specified, password must also be specified.
     Default: none.
   password;;
-    Optional.  Password to authenticate to SMTP server with.
+    Optional. Password to authenticate to SMTP server with.
     If username is specified, password must also be specified.
     Default: none.
   local_hostname;;
-    Optional.  It's the hostname that the sender can use to identify itself
+    Optional. It's the hostname that the sender can use to identify itself
     to the MTA.
 
+[[paths]]
 paths::
-  Assigns symbolic names to repositories.  The left side is the
+  Assigns symbolic names to repositories. The left side is the
   symbolic name, and the right gives the directory or URL that is the
-  location of the repository.  Default paths can be declared by
+  location of the repository. Default paths can be declared by
   setting the following entries.
   default;;
     Directory or URL to use when pulling if no source is specified.
     Default is set to repository from which the current repository
     was cloned.
   default-push;;
-    Optional.  Directory or URL to use when pushing if no destination
+    Optional. Directory or URL to use when pushing if no destination
     is specified.
 
+[[server]]
 server::
   Controls generic server settings.
   uncompressed;;
     Whether to allow clients to clone a repo using the uncompressed
-    streaming protocol.  This transfers about 40% more data than a
+    streaming protocol. This transfers about 40% more data than a
     regular clone, but uses less memory and CPU on both server and
-    client.  Over a LAN (100Mbps or better) or a very fast WAN, an
+    client. Over a LAN (100Mbps or better) or a very fast WAN, an
     uncompressed streaming clone is a lot faster (~10x) than a regular
-    clone.  Over most WAN connections (anything slower than about
+    clone. Over most WAN connections (anything slower than about
     6Mbps), uncompressed streaming is slower, because of the extra
-    data transfer overhead.  Default is False.
+    data transfer overhead. Default is False.
 
+[[trusted]]
 trusted::
   For security reasons, Mercurial will not use the settings in
   the .hg/hgrc file from a repository if it doesn't belong to a
-  trusted user or to a trusted group.  The main exception is the
+  trusted user or to a trusted group. The main exception is the
   web interface, which automatically uses some safe settings, since
   it's common to serve repositories from different users.
 
-  This section specifies what users and groups are trusted.  The
-  current user is always trusted.  To trust everybody, list a user
+  This section specifies what users and groups are trusted. The
+  current user is always trusted. To trust everybody, list a user
   or a group with name "*".
 
   users;;
@@ -524,6 +539,7 b' trusted::'
   groups;;
     Comma-separated list of trusted groups.
 
+[[ui]]
 ui::
   User interface controls.
   archivemeta;;
@@ -531,13 +547,19 b' ui::'
     (hashes for the repository base and for tip) in archives created by
     the hg archive command or downloaded via hgweb.
     Default is true.
+  askusername;;
+    Whether to prompt for a username when committing. If True, and
+    neither $HGUSER nor $EMAIL has been specified, then the user will
+    be prompted to enter a username.  If no username is entered, the
+    default USER@HOST is used instead.
+    Default is False.
   debug;;
-    Print debugging information.  True or False.  Default is False.
+    Print debugging information. True or False. Default is False.
   editor;;
-    The editor to use during a commit.  Default is $EDITOR or "vi".
+    The editor to use during a commit. Default is $EDITOR or "vi".
   fallbackencoding;;
     Encoding to try if it's not possible to decode the changelog using
-    UTF-8.  Default is ISO-8859-1.
+    UTF-8. Default is ISO-8859-1.
   ignore;;
     A file to read per-user ignore patterns from. This file should be in
     the same format as a repository-wide .hgignore file. This option
@@ -546,7 +568,7 b' ui::'
     "ignore.other = ~/.hgignore2". For details of the ignore file
     format, see the hgignore(5) man page.
   interactive;;
-    Allow to prompt the user.  True or False.  Default is True.
+    Allow to prompt the user. True or False. Default is True.
   logtemplate;;
     Template string for commands that print changesets.
   merge;;
@@ -563,18 +585,19 b' ui::'
         fail to merge
 
     See the merge-tools section for more information on configuring tools.
+
   patch;;
     command to use to apply patches. Look for 'gpatch' or 'patch' in PATH if
     unset.
   quiet;;
-    Reduce the amount of output printed.  True or False.  Default is False.
+    Reduce the amount of output printed. True or False. Default is False.
   remotecmd;;
     remote command to use for clone/push/pull operations. Default is 'hg'.
   report_untrusted;;
     Warn if a .hg/hgrc file is ignored due to not being owned by a
-    trusted user or group.  True or False.  Default is True.
+    trusted user or group. True or False. Default is True.
   slash;;
-    Display paths using a slash ("/") as the path separator.  This only
+    Display paths using a slash ("/") as the path separator. This only
     makes a difference on systems where the default path separator is not
     the slash character (e.g. Windows uses the backslash character ("\")).
     Default is False.
@@ -582,7 +605,7 b' ui::'
     command to use for SSH connections. Default is 'ssh'.
   strict;;
     Require exact command names, instead of allowing unambiguous
-    abbreviations.  True or False.  Default is False.
+    abbreviations. True or False. Default is False.
   style;;
     Name of style to use for command output.
   timeout;;
@@ -591,14 +614,15 b' ui::'
   username;;
     The committer of a changeset created when running "commit".
     Typically a person's name and email address, e.g. "Fred Widget
-    <[e-mail]>".  Default is $EMAIL or username@hostname.
+    <[e-mail]>". Default is $EMAIL or username@hostname.
     If the username in hgrc is empty, it has to be specified manually or
     in a different hgrc file (e.g. $HOME/.hgrc, if the admin set "username ="
     in the system hgrc).
   verbose;;
-    Increase the amount of output printed.  True or False.  Default is False.
+    Increase the amount of output printed. True or False. Default is False.
 
 
+[[web]]
 web::
   Web interface configuration.
   accesslog;;
@@ -617,9 +641,9 b' web::'
   allowpull;;
     Whether to allow pulling from the repository. Default is true.
   allow_push;;
-    Whether to allow pushing to the repository.  If empty or not set,
-    push is not allowed.  If the special value "*", any remote user
-    can push, including unauthenticated users.  Otherwise, the remote
+    Whether to allow pushing to the repository. If empty or not set,
+    push is not allowed. If the special value "*", any remote user
+    can push, including unauthenticated users. Otherwise, the remote
     user must have been authenticated, and the authenticated user name
     must be present in this list (separated by whitespace or ",").
     The contents of the allow_push list are examined after the
@@ -635,11 +659,11 b' web::'
     Name or email address of the person in charge of the repository.
     Defaults to ui.username or $EMAIL or "unknown" if unset or empty.
   deny_push;;
-    Whether to deny pushing to the repository.  If empty or not set,
-    push is not denied.  If the special value "*", all remote users
-    are denied push.  Otherwise, unauthenticated users are all denied,
+    Whether to deny pushing to the repository. If empty or not set,
+    push is not denied. If the special value "*", all remote users
+    are denied push. Otherwise, unauthenticated users are all denied,
     and any authenticated user name present in this list (separated by
-    whitespace or ",") is also denied.  The contents of the deny_push
+    whitespace or ",") is also denied. The contents of the deny_push
     list are examined before the allow_push list.
   description;;
     Textual description of the repository's purpose or contents.
@@ -666,7 +690,7 b' web::'
     Prefix path to serve from. Default is '' (server root).
   push_ssl;;
     Whether to require that inbound pushes be transported over SSL to
-    prevent password sniffing.  Default is true.
+    prevent password sniffing. Default is true.
   staticurl;;
     Base URL to use for static files. If unset, static files (e.g.
     the hgicon.png favicon) will be served by the CGI script itself.

hgext/acl.py

@@ -46,79 +46,45 b''
 #   ** = user6
 
 from mercurial.i18n import _
-from mercurial.node import bin, short
 from mercurial import util
 import getpass
 
-class checker(object):
-    '''acl checker.'''
-
-    def buildmatch(self, key):
-        '''return tuple of (match function, list enabled).'''
-        if not self.ui.has_section(key):
-            self.ui.debug(_('acl: %s not enabled\n') % key)
-            return None, False
-
-        thisuser = self.getuser()
-        pats = [pat for pat, users in self.ui.configitems(key)
-                if thisuser in users.replace(',', ' ').split()]
-        self.ui.debug(_('acl: %s enabled, %d entries for user %s\n') %
-                      (key, len(pats), thisuser))
-        if pats:
-            match = util.matcher(self.repo.root, names=pats)[1]
-        else:
-            match = util.never
-        return match, True
-
-    def getuser(self):
-        '''return name of authenticated user.'''
-        return self.user
+def buildmatch(ui, repo, user, key):
+    '''return tuple of (match function, list enabled).'''
+    if not ui.has_section(key):
+        ui.debug(_('acl: %s not enabled\n') % key)
+        return None
 
-    def __init__(self, ui, repo):
-        self.ui = ui
-        self.repo = repo
-        self.user = getpass.getuser()
-        cfg = self.ui.config('acl', 'config')
-        if cfg:
-            self.ui.readsections(cfg, 'acl.allow', 'acl.deny')
-        self.allow, self.allowable = self.buildmatch('acl.allow')
-        self.deny, self.deniable = self.buildmatch('acl.deny')
-
-    def skipsource(self, source):
-        '''true if incoming changes from this source should be skipped.'''
-        ok_sources = self.ui.config('acl', 'sources', 'serve').split()
-        return source not in ok_sources
-
-    def check(self, node):
-        '''return if access allowed, raise exception if not.'''
-        files = self.repo.changectx(node).files()
-        if self.deniable:
-            for f in files:
-                if self.deny(f):
-                    self.ui.debug(_('acl: user %s denied on %s\n') %
-                                  (self.getuser(), f))
-                    raise util.Abort(_('acl: access denied for changeset %s') %
-                                     short(node))
-        if self.allowable:
-            for f in files:
-                if not self.allow(f):
-                    self.ui.debug(_('acl: user %s not allowed on %s\n') %
-                                  (self.getuser(), f))
-                    raise util.Abort(_('acl: access denied for changeset %s') %
-                                     short(node))
-        self.ui.debug(_('acl: allowing changeset %s\n') % short(node))
+    pats = [pat for pat, users in ui.configitems(key)
+            if user in users.replace(',', ' ').split()]
+    ui.debug(_('acl: %s enabled, %d entries for user %s\n') %
+             (key, len(pats), user))
+    if pats:
+        return util.matcher(repo.root, names=pats)[1]
+    return util.never
 
 def hook(ui, repo, hooktype, node=None, source=None, **kwargs):
     if hooktype != 'pretxnchangegroup':
         raise util.Abort(_('config error - hook type "%s" cannot stop '
                            'incoming changesets') % hooktype)
-
-    c = checker(ui, repo)
-    if c.skipsource(source):
+    if source not in ui.config('acl', 'sources', 'serve').split():
         ui.debug(_('acl: changes have source "%s" - skipping\n') % source)
         return
 
-    start = repo.changelog.rev(bin(node))
-    end = repo.changelog.count()
-    for rev in xrange(start, end):
-        c.check(repo.changelog.node(rev))
+    user = getpass.getuser()
+    cfg = ui.config('acl', 'config')
+    if cfg:
+        ui.readsections(cfg, 'acl.allow', 'acl.deny')
+    allow = buildmatch(ui, repo, user, 'acl.allow')
+    deny = buildmatch(ui, repo, user, 'acl.deny')
+
+    for rev in xrange(repo[node], len(repo)):
+        ctx = repo[rev]
+        for f in ctx.files():
+            if deny and deny(f):
+                ui.debug(_('acl: user %s denied on %s\n') % (user, f))
+                raise util.Abort(_('acl: access denied for changeset %s') % ctx)
+            if allow and not allow(f):
+                ui.debug(_('acl: user %s not allowed on %s\n') % (user, f))
+                raise util.Abort(_('acl: access denied for changeset %s') % ctx)
+        ui.debug(_('acl: allowing changeset %s\n') % ctx)

hgext/bugzilla.py

@@ -55,7 +55,7 b''
 from mercurial.i18n import _
 from mercurial.node import short
 from mercurial import cmdutil, templater, util
-import os, re, time
+import re, time
 
 MySQLdb = None
 
@@ -99,9 +99,7 b' class bugzilla_2_16(object):'
     def filter_real_bug_ids(self, ids):
         '''filter not-existing bug ids from list.'''
         self.run('select bug_id from bugs where bug_id in %s' % buglist(ids))
-        ids = [c[0] for c in self.cursor.fetchall()]
-        ids.sort()
-        return ids
+        return util.sort([c[0] for c in self.cursor.fetchall()])
 
     def filter_unknown_bug_ids(self, node, ids):
         '''filter bug ids from list that already refer to this changeset.'''
@@ -114,9 +112,7 b' class bugzilla_2_16(object):'
             self.ui.status(_('bug %d already knows about changeset %s\n') %
                            (id, short(node)))
             unknown.pop(id, None)
-        ids = unknown.keys()
-        ids.sort()
-        return ids
+        return util.sort(unknown.keys())
 
     def notify(self, ids):
         '''tell bugzilla to send mail.'''
@@ -127,7 +123,7 b' class bugzilla_2_16(object):'
             cmd = self.ui.config('bugzilla', 'notify',
                                'cd /var/www/html/bugzilla && '
                                './processmail %s [e-mail]') % id
-            fp = os.popen('(%s) 2>&1' % cmd)
+            fp = util.popen('(%s) 2>&1' % cmd)
             out = fp.read()
             ret = fp.close()
             if ret:
@@ -300,7 +296,7 b' def hook(ui, repo, hooktype, node=None, '
                          hooktype)
     try:
         bz = bugzilla(ui, repo)
-        ctx = repo.changectx(node)
+        ctx = repo[node]
         ids = bz.find_bug_ids(ctx)
         if ids:
             for id in ids:

hgext/children.py

@@ -25,7 +25,7 b' def children(ui, repo, file_=None, **opt'
     if file_:
         ctx = repo.filectx(file_, changeid=rev)
     else:
-        ctx = repo.changectx(rev)
+        ctx = repo[rev]
 
     displayer = cmdutil.show_changeset(ui, repo, opts)
     for node in [cp.node() for cp in ctx.children()]:

hgext/churn.py

@@ -4,15 +4,10 b''
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
-#
-#
-# Aliases map file format is simple one alias per line in the following
-# format:
-#
-# <alias email> <actual email>
+'''allow graphing the number of lines changed per contributor'''
 
 from mercurial.i18n import gettext as _
-from mercurial import mdiff, cmdutil, util, node
+from mercurial import patch, cmdutil, util, node
 import os, sys
 
 def get_tty_width():
@@ -36,98 +31,41 b' def get_tty_width():'
         pass
     return 80
 
-def __gather(ui, repo, node1, node2):
-    def dirtywork(f, mmap1, mmap2):
-        lines = 0
-
-        to = mmap1 and repo.file(f).read(mmap1[f]) or None
-        tn = mmap2 and repo.file(f).read(mmap2[f]) or None
-
-        diff = mdiff.unidiff(to, "", tn, "", f, f).split("\n")
-
-        for line in diff:
-            if not line:
-                continue # skip EOF
-            if line.startswith(" "):
-                continue # context line
-            if line.startswith("--- ") or line.startswith("+++ "):
-                continue # begining of diff
-            if line.startswith("@@ "):
-                continue # info line
-
-            # changed lines
-            lines += 1
-
-        return lines
-
-    ##
-
-    lines = 0
-
-    changes = repo.status(node1, node2, None, util.always)[:5]
-
-    modified, added, removed, deleted, unknown = changes
-
-    who = repo.changelog.read(node2)[1]
-    who = util.email(who) # get the email of the person
-
-    mmap1 = repo.manifest.read(repo.changelog.read(node1)[0])
-    mmap2 = repo.manifest.read(repo.changelog.read(node2)[0])
-    for f in modified:
-        lines += dirtywork(f, mmap1, mmap2)
-
-    for f in added:
-        lines += dirtywork(f, None, mmap2)
-
-    for f in removed:
-        lines += dirtywork(f, mmap1, None)
-
-    for f in deleted:
-        lines += dirtywork(f, mmap1, mmap2)
-
-    for f in unknown:
-        lines += dirtywork(f, mmap1, mmap2)
-
-    return (who, lines)
-
-def gather_stats(ui, repo, amap, revs=None, progress=False):
+def countrevs(ui, repo, amap, revs, progress=False):
     stats = {}
-
-    cl    = repo.changelog
-
+    count = pct = 0
     if not revs:
-        revs = range(0, cl.count())
-
-    nr_revs = len(revs)
-    cur_rev = 0
+        revs = range(len(repo))
 
     for rev in revs:
-        cur_rev += 1 # next revision
-
-        node2    = cl.node(rev)
-        node1    = cl.parents(node2)[0]
-
-        if cl.parents(node2)[1] != node.nullid:
+        ctx2 = repo[rev]
+        parents = ctx2.parents()
+        if len(parents) > 1:
             ui.note(_('Revision %d is a merge, ignoring...\n') % (rev,))
             continue
 
-        who, lines = __gather(ui, repo, node1, node2)
+        ctx1 = parents[0]
+        lines = 0
+        ui.pushbuffer()
+        patch.diff(repo, ctx1.node(), ctx2.node())
+        diff = ui.popbuffer()
 
-        # remap the owner if possible
-        if who in amap:
-            ui.note("using '%s' alias for '%s'\n" % (amap[who], who))
-            who = amap[who]
+        for l in diff.split('\n'):
+            if (l.startswith("+") and not l.startswith("+++ ") or
+                l.startswith("-") and not l.startswith("--- ")):
+                lines += 1
 
-        if not who in stats:
-            stats[who] = 0
-        stats[who] += lines
-
-        ui.note("rev %d: %d lines by %s\n" % (rev, lines, who))
+        user = util.email(ctx2.user())
+        user = amap.get(user, user) # remap
+        stats[user] = stats.get(user, 0) + lines
+        ui.debug("rev %d: %d lines by %s\n" % (rev, lines, user))
 
         if progress:
-            nr_revs = max(nr_revs, 1)
-            if int(100.0*(cur_rev - 1)/nr_revs) < int(100.0*cur_rev/nr_revs):
-                ui.write("\rGenerating stats: %d%%" % (int(100.0*cur_rev/nr_revs),))
+            count += 1
+            newpct = int(100.0 * count / max(len(revs), 1))
+            if pct < newpct:
+                pct = newpct
+                ui.write("\rGenerating stats: %d%%" % pct)
                 sys.stdout.flush()
 
     if progress:
@@ -137,64 +75,39 b' def gather_stats(ui, repo, amap, revs=No'
     return stats
 
 def churn(ui, repo, **opts):
-    "Graphs the number of lines changed"
+    '''graphs the number of lines changed
+
+    The map file format used to specify aliases is fairly simple:
+
+    <alias email> <actual email>'''
 
     def pad(s, l):
-        if len(s) < l:
-            return s + " " * (l-len(s))
-        return s[0:l]
-
-    def graph(n, maximum, width, char):
-        maximum = max(1, maximum)
-        n = int(n * width / float(maximum))
-
-        return char * (n)
-
-    def get_aliases(f):
-        aliases = {}
-
-        for l in f.readlines():
-            l = l.strip()
-            alias, actual = l.split()
-            aliases[alias] = actual
-
-        return aliases
+        return (s + " " * l)[:l]
 
     amap = {}
     aliases = opts.get('aliases')
     if aliases:
-        try:
-            f = open(aliases,"r")
-        except OSError, e:
-            print "Error: " + e
-            return
+        for l in open(aliases, "r"):
+            l = l.strip()
+            alias, actual = l.split()
+            amap[alias] = actual
 
-        amap = get_aliases(f)
-        f.close()
-
-    revs = [int(r) for r in cmdutil.revrange(repo, opts['rev'])]
-    revs.sort()
-    stats = gather_stats(ui, repo, amap, revs, opts.get('progress'))
+    revs = util.sort([int(r) for r in cmdutil.revrange(repo, opts['rev'])])
+    stats = countrevs(ui, repo, amap, revs, opts.get('progress'))
+    if not stats:
+        return
 
-    # make a list of tuples (name, lines) and sort it in descending order
-    ordered = stats.items()
-    if not ordered:
-        return
-    ordered.sort(lambda x, y: cmp(y[1], x[1]))
-    max_churn = ordered[0][1]
+    stats = util.sort([(-l, u, l) for u,l in stats.items()])
+    maxchurn = float(max(1, stats[0][2]))
+    maxuser = max([len(u) for k, u, l in stats])
 
-    tty_width = get_tty_width()
-    ui.note(_("assuming %i character terminal\n") % tty_width)
-    tty_width -= 1
-
-    max_user_width = max([len(user) for user, churn in ordered])
+    ttywidth = get_tty_width()
+    ui.debug(_("assuming %i character terminal\n") % ttywidth)
+    width = ttywidth - maxuser - 2 - 6 - 2 - 2
 
-    graph_width = tty_width - max_user_width - 1 - 6 - 2 - 2
-
-    for user, churn in ordered:
-        print "%s %6d %s" % (pad(user, max_user_width),
-                             churn,
-                             graph(churn, max_churn, graph_width, '*'))
+    for k, user, churn in stats:
+        print "%s %6d %s" % (pad(user, maxuser), churn,
+                             "*" * int(churn * width / maxchurn))
 
 cmdtable = {
     "churn":

hgext/convert/__init__.py

@@ -4,6 +4,7 b''
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
+'''converting foreign VCS repositories to Mercurial'''
 
 import convcmd
 from mercurial import commands
@@ -85,6 +86,50 b' def convert(ui, src, dest=None, revmapfi'
     --config convert.hg.saverev=True          (boolean)
         allow target to preserve source revision ID
 
+    CVS Source
+    ----------
+
+    CVS source will use a sandbox (i.e. a checked-out copy) from CVS
+    to indicate the starting point of what will be converted. Direct
+    access to the repository files is not needed, unless of course
+    the repository is :local:. The conversion uses the top level
+    directory in the sandbox to find the CVS repository, and then uses
+    CVS rlog commands to find files to convert. This means that unless
+    a filemap is given, all files under the starting directory will be
+    converted, and that any directory reorganisation in the CVS
+    sandbox is ignored.
+
+    Because CVS does not have changesets, it is necessary to collect
+    individual commits to CVS and merge them into changesets. CVS source
+    can use the external 'cvsps' program (this is a legacy option and may
+    be removed in future) or use its internal changeset merging code.
+    External cvsps is default, and options may be passed to it by setting
+        --config convert.cvsps='cvsps -A -u --cvs-direct -q'
+    The options shown are the defaults.
+
+    Internal cvsps is selected by setting
+        --config convert.cvsps=builtin
+    and has a few more configurable options:
+        --config convert.cvsps.fuzz=60   (integer)
+            Specify the maximum time (in seconds) that is allowed between
+            commits with identical user and log message in a single
+            changeset. When very large files were checked in as part
+            of a changeset then the default may not be long enough.
+        --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
+            Specify a regular expression to which commit log messages are
+            matched. If a match occurs, then the conversion process will
+            insert a dummy revision merging the branch on which this log
+            message occurs to the branch indicated in the regex.
+        --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
+            Specify a regular expression to which commit log messages are
+            matched. If a match occurs, then the conversion process will
+            add the most recent revision on the branch indicated in the
+            regex as the second parent of the changeset.
+    
+    The hgext/convert/cvsps wrapper script allows the builtin changeset
+    merging code to be run without doing a conversion. Its parameters and
+    output are similar to that of cvsps 2.1.
+
     Subversion Source
     -----------------
 

hgext/convert/common.py

@@ -153,26 +153,18 b' class converter_sink(object):'
         mapping equivalent authors identifiers for each system."""
         return None
 
-    def putfile(self, f, e, data):
-        """Put file for next putcommit().
-        f: path to file
-        e: '', 'x', or 'l' (regular file, executable, or symlink)
-        data: file contents"""
-        raise NotImplementedError()
-
-    def delfile(self, f):
-        """Delete file for next putcommit().
-        f: path to file"""
-        raise NotImplementedError()
-
-    def putcommit(self, files, parents, commit):
+    def putcommit(self, files, copies, parents, commit, source):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object containing
         at a minimum the author, date, and message for this changeset.
-        Called after putfile() and delfile() calls. Note that the sink
-        repository is not told to update itself to a particular revision
-        (or even what that revision would be) before it receives the
-        file data."""
+        'files' is a list of (path, version) tuples, 'copies'is a dictionary
+        mapping destinations to sources, and 'source' is the source repository.
+        Only getfile() and getmode() should be called on 'source'.
+
+        Note that the sink repository is not told to update itself to
+        a particular revision (or even what that revision would be)
+        before it receives the file data.
+        """
         raise NotImplementedError()
 
     def puttags(self, tags):
@@ -181,7 +173,7 b' class converter_sink(object):'
         raise NotImplementedError()
 
     def setbranch(self, branch, pbranches):
-        """Set the current branch name. Called before the first putfile
+        """Set the current branch name. Called before the first putcommit
         on the branch.
         branch: branch name for subsequent commits
         pbranches: (converted parent revision, parent branch) tuples"""

hgext/convert/convcmd.py

@@ -221,8 +221,6 b' class converter(object):'
 
     def copy(self, rev):
         commit = self.commitcache[rev]
-        do_copies = hasattr(self.dest, 'copyfile')
-        filenames = []
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
@@ -241,21 +239,6 b' class converter(object):'
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
-        for f, v in files:
-            filenames.append(f)
-            try:
-                data = self.source.getfile(f, v)
-            except IOError, inst:
-                self.dest.delfile(f)
-            else:
-                e = self.source.getmode(f, v)
-                self.dest.putfile(f, e, data)
-                if do_copies:
-                    if f in copies:
-                        copyf = copies[f]
-                        # Merely marks that a copy happened.
-                        self.dest.copyfile(copyf, f)
-
         try:
             parents = self.splicemap[rev].replace(',', ' ').split()
             self.ui.status('spliced in %s as parents of %s\n' %
@@ -263,7 +246,7 b' class converter(object):'
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
-        newnode = self.dest.putcommit(filenames, parents, commit)
+        newnode = self.dest.putcommit(files, copies, parents, commit, self.source)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 

hgext/convert/cvs.py

@@ -3,8 +3,10 b''
 import os, locale, re, socket
 from cStringIO import StringIO
 from mercurial import util
+from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
+import cvsps
 
 class convert_cvs(converter_source):
     def __init__(self, ui, path, rev=None):
@@ -14,10 +16,13 b' class convert_cvs(converter_source):'
         if not os.path.exists(cvs):
             raise NoRepo("%s does not look like a CVS checkout" % path)
 
+        checktool('cvs')
         self.cmd = ui.config('convert', 'cvsps', 'cvsps -A -u --cvs-direct -q')
         cvspsexe = self.cmd.split(None, 1)[0]
-        for tool in (cvspsexe, 'cvs'):
-            checktool(tool)
+        self.builtin = cvspsexe == 'builtin'
+
+        if not self.builtin:
+            checktool(cvspsexe)
 
         self.changeset = {}
         self.files = {}
@@ -28,10 +33,11 b' class convert_cvs(converter_source):'
         self.cvsroot = file(os.path.join(cvs, "Root")).read()[:-1]
         self.cvsrepo = file(os.path.join(cvs, "Repository")).read()[:-1]
         self.encoding = locale.getpreferredencoding()
-        self._parse()
+
+        self._parse(ui)
         self._connect()
 
-    def _parse(self):
+    def _parse(self, ui):
         if self.changeset:
             return
 
@@ -56,80 +62,114 b' class convert_cvs(converter_source):'
             id = None
             state = 0
             filerevids = {}
-            for l in util.popen(cmd):
-                if state == 0: # header
-                    if l.startswith("PatchSet"):
-                        id = l[9:-2]
-                        if maxrev and int(id) > maxrev:
-                            # ignore everything
-                            state = 3
-                    elif l.startswith("Date"):
-                        date = util.parsedate(l[6:-1], ["%Y/%m/%d %H:%M:%S"])
-                        date = util.datestr(date)
-                    elif l.startswith("Branch"):
-                        branch = l[8:-1]
-                        self.parent[id] = self.lastbranch.get(branch, 'bad')
-                        self.lastbranch[branch] = id
-                    elif l.startswith("Ancestor branch"):
-                        ancestor = l[17:-1]
-                        # figure out the parent later
-                        self.parent[id] = self.lastbranch[ancestor]
-                    elif l.startswith("Author"):
-                        author = self.recode(l[8:-1])
-                    elif l.startswith("Tag:") or l.startswith("Tags:"):
-                        t = l[l.index(':')+1:]
-                        t = [ut.strip() for ut in t.split(',')]
-                        if (len(t) > 1) or (t[0] and (t[0] != "(none)")):
-                            self.tags.update(dict.fromkeys(t, id))
-                    elif l.startswith("Log:"):
-                        # switch to gathering log
-                        state = 1
-                        log = ""
-                elif state == 1: # log
-                    if l == "Members: \n":
-                        # switch to gathering members
-                        files = {}
-                        oldrevs = []
-                        log = self.recode(log[:-1])
-                        state = 2
-                    else:
-                        # gather log
-                        log += l
-                elif state == 2: # members
-                    if l == "\n": # start of next entry
-                        state = 0
-                        p = [self.parent[id]]
-                        if id == "1":
-                            p = []
-                        if branch == "HEAD":
-                            branch = ""
-                        if branch:
-                            latest = None
-                            # the last changeset that contains a base
-                            # file is our parent
-                            for r in oldrevs:
-                                latest = max(filerevids.get(r, None), latest)
-                            if latest:
-                                p = [latest]
+
+            if self.builtin:
+                # builtin cvsps code
+                ui.status(_('using builtin cvsps\n'))
+
+                db = cvsps.createlog(ui, cache='update')
+                db = cvsps.createchangeset(ui, db,
+                      fuzz=int(ui.config('convert', 'cvsps.fuzz', 60)),
+                      mergeto=ui.config('convert', 'cvsps.mergeto', None),
+                      mergefrom=ui.config('convert', 'cvsps.mergefrom', None))
+
+                for cs in db:
+                    if maxrev and cs.id>maxrev:
+                        break
+                    id = str(cs.id)
+                    cs.author = self.recode(cs.author)
+                    self.lastbranch[cs.branch] = id
+                    cs.comment = self.recode(cs.comment)
+                    date = util.datestr(cs.date)
+                    self.tags.update(dict.fromkeys(cs.tags, id))
+
+                    files = {}
+                    for f in cs.entries:
+                        files[f.file] = "%s%s" % ('.'.join([str(x) for x in f.revision]),
+                                                  ['', '(DEAD)'][f.dead])
 
-                        # add current commit to set
-                        c = commit(author=author, date=date, parents=p,
-                                   desc=log, branch=branch)
-                        self.changeset[id] = c
-                        self.files[id] = files
-                    else:
-                        colon = l.rfind(':')
-                        file = l[1:colon]
-                        rev = l[colon+1:-2]
-                        oldrev, rev = rev.split("->")
-                        files[file] = rev
+                    # add current commit to set
+                    c = commit(author=cs.author, date=date,
+                             parents=[str(p.id) for p in cs.parents],
+                             desc=cs.comment, branch=cs.branch or '')
+                    self.changeset[id] = c
+                    self.files[id] = files
+            else:
+                # external cvsps
+                for l in util.popen(cmd):
+                    if state == 0: # header
+                        if l.startswith("PatchSet"):
+                            id = l[9:-2]
+                            if maxrev and int(id) > maxrev:
+                                # ignore everything
+                                state = 3
+                        elif l.startswith("Date"):
+                            date = util.parsedate(l[6:-1], ["%Y/%m/%d %H:%M:%S"])
+                            date = util.datestr(date)
+                        elif l.startswith("Branch"):
+                            branch = l[8:-1]
+                            self.parent[id] = self.lastbranch.get(branch, 'bad')
+                            self.lastbranch[branch] = id
+                        elif l.startswith("Ancestor branch"):
+                            ancestor = l[17:-1]
+                            # figure out the parent later
+                            self.parent[id] = self.lastbranch[ancestor]
+                        elif l.startswith("Author"):
+                            author = self.recode(l[8:-1])
+                        elif l.startswith("Tag:") or l.startswith("Tags:"):
+                            t = l[l.index(':')+1:]
+                            t = [ut.strip() for ut in t.split(',')]
+                            if (len(t) > 1) or (t[0] and (t[0] != "(none)")):
+                                self.tags.update(dict.fromkeys(t, id))
+                        elif l.startswith("Log:"):
+                            # switch to gathering log
+                            state = 1
+                            log = ""
+                    elif state == 1: # log
+                        if l == "Members: \n":
+                            # switch to gathering members
+                            files = {}
+                            oldrevs = []
+                            log = self.recode(log[:-1])
+                            state = 2
+                        else:
+                            # gather log
+                            log += l
+                    elif state == 2: # members
+                        if l == "\n": # start of next entry
+                            state = 0
+                            p = [self.parent[id]]
+                            if id == "1":
+                                p = []
+                            if branch == "HEAD":
+                                branch = ""
+                            if branch:
+                                latest = None
+                                # the last changeset that contains a base
+                                # file is our parent
+                                for r in oldrevs:
+                                    latest = max(filerevids.get(r, None), latest)
+                                if latest:
+                                    p = [latest]
 
-                        # save some information for identifying branch points
-                        oldrevs.append("%s:%s" % (oldrev, file))
-                        filerevids["%s:%s" % (rev, file)] = id
-                elif state == 3:
-                    # swallow all input
-                    continue
+                            # add current commit to set
+                            c = commit(author=author, date=date, parents=p,
+                                       desc=log, branch=branch)
+                            self.changeset[id] = c
+                            self.files[id] = files
+                        else:
+                            colon = l.rfind(':')
+                            file = l[1:colon]
+                            rev = l[colon+1:-2]
+                            oldrev, rev = rev.split("->")
+                            files[file] = rev
+
+                            # save some information for identifying branch points
+                            oldrevs.append("%s:%s" % (oldrev, file))
+                            filerevids["%s:%s" % (rev, file)] = id
+                    elif state == 3:
+                        # swallow all input
+                        continue
 
             self.heads = self.lastbranch.values()
         finally:
@@ -297,10 +337,7 b' class convert_cvs(converter_source):'
 
     def getchanges(self, rev):
         self.modecache = {}
-        files = self.files[rev]
-        cl = files.items()
-        cl.sort()
-        return (cl, {})
+        return util.sort(self.files[rev].items()), {}
 
     def getcommit(self, rev):
         return self.changeset[rev]
@@ -309,7 +346,4 b' class convert_cvs(converter_source):'
         return self.tags
 
     def getchangedfiles(self, rev, i):
-        files = self.files[rev].keys()
-        files.sort()
-        return files
-
+        return util.sort(self.files[rev].keys())

hgext/convert/darcs.py

@@ -110,9 +110,8 b' class darcs_source(converter_source, com'
                 copies[elt.get('from')] = elt.get('to')
             else:
                 changes.append((elt.text.strip(), rev))
-        changes.sort()
         self.lastrev = rev
-        return changes, copies
+        return util.sort(changes), copies
 
     def getfile(self, name, rev):
         if rev != self.lastrev:

hgext/convert/gnuarch.py

@@ -130,10 +130,8 b' class gnuarch_source(converter_source, c'
             for c in cps:
                 copies[c] = cps[c]
 
-        changes.sort()
         self.lastrev = rev
-
-        return changes, copies
+        return util.sort(changes), copies
 
     def getcommit(self, rev):
         changes = self.changes[rev]

hgext/convert/hg.py

@@ -17,7 +17,7 b' import os, time'
 from mercurial.i18n import _
 from mercurial.repo import RepoError
 from mercurial.node import bin, hex, nullid
-from mercurial import hg, revlog, util
+from mercurial import hg, revlog, util, context
 
 from common import NoRepo, commit, converter_source, converter_sink
 
@@ -54,11 +54,9 b' class mercurial_sink(converter_sink):'
         self.ui.debug(_('run hg sink pre-conversion action\n'))
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
-        self.repo.dirstate.clear()
 
     def after(self):
         self.ui.debug(_('run hg sink post-conversion action\n'))
-        self.repo.dirstate.invalidate()
         self.lock = None
         self.wlock = None
 
@@ -72,21 +70,6 b' class mercurial_sink(converter_sink):'
         h = self.repo.changelog.heads()
         return [ hex(x) for x in h ]
 
-    def putfile(self, f, e, data):
-        self.repo.wwrite(f, data, e)
-        if f not in self.repo.dirstate:
-            self.repo.dirstate.normallookup(f)
-
-    def copyfile(self, source, dest):
-        self.repo.copy(source, dest)
-
-    def delfile(self, f):
-        try:
-            util.unlink(self.repo.wjoin(f))
-            #self.repo.remove([f])
-        except OSError:
-            pass
-
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
@@ -125,13 +108,19 b' class mercurial_sink(converter_sink):'
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
-    def putcommit(self, files, parents, commit):
-        seen = {}
+    def putcommit(self, files, copies, parents, commit, source):
+
+        files = dict(files)
+        def getfilectx(repo, memctx, f):
+            v = files[f]
+            data = source.getfile(f, v)
+            e = source.getmode(f, v)
+            return context.memfilectx(f, data, 'l' in e, 'x' in e, copies.get(f))
+
         pl = []
         for p in parents:
-            if p not in seen:
+            if p not in pl:
                 pl.append(p)
-                seen[p] = 1
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
@@ -152,9 +141,9 b' class mercurial_sink(converter_sink):'
         while parents:
             p1 = p2
             p2 = parents.pop(0)
-            a = self.repo.rawcommit(files, text, commit.author, commit.date,
-                                    bin(p1), bin(p2), extra=extra)
-            self.repo.dirstate.clear()
+            ctx = context.memctx(self.repo, (p1, p2), text, files.keys(), getfilectx,
+                                 commit.author, commit.date, extra)
+            a = self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
@@ -163,43 +152,39 b' class mercurial_sink(converter_sink):'
             mnode = self.repo.changelog.read(bin(p2))[0]
             if not man.cmp(m1node, man.revision(mnode)):
                 self.repo.rollback()
-                self.repo.dirstate.clear()
                 return parent
         return p2
 
     def puttags(self, tags):
-        try:
-            old = self.repo.wfile(".hgtags").read()
-            oldlines = old.splitlines(1)
-            oldlines.sort()
-        except:
-            oldlines = []
+         try:
+             parentctx = self.repo[self.tagsbranch]
+             tagparent = parentctx.node()
+         except RepoError, inst:
+             parentctx = None
+             tagparent = nullid
 
-        k = tags.keys()
-        k.sort()
-        newlines = []
-        for tag in k:
-            newlines.append("%s %s\n" % (tags[tag], tag))
+         try:
+             oldlines = util.sort(parentctx['.hgtags'].data().splitlines(1))
+         except:
+             oldlines = []
 
-        newlines.sort()
+         newlines = util.sort([("%s %s\n" % (tags[tag], tag)) for tag in tags])
 
-        if newlines != oldlines:
-            self.ui.status("updating tags\n")
-            f = self.repo.wfile(".hgtags", "w")
-            f.write("".join(newlines))
-            f.close()
-            if not oldlines: self.repo.add([".hgtags"])
-            date = "%s 0" % int(time.mktime(time.gmtime()))
-            extra = {}
-            if self.tagsbranch != 'default':
-                extra['branch'] = self.tagsbranch
-            try:
-                tagparent = self.repo.changectx(self.tagsbranch).node()
-            except RepoError, inst:
-                tagparent = nullid
-            self.repo.rawcommit([".hgtags"], "update tags", "convert-repo",
-                                date, tagparent, nullid, extra=extra)
-            return hex(self.repo.changelog.tip())
+         if newlines == oldlines:
+             return None
+         data = "".join(newlines)
+
+         def getfilectx(repo, memctx, f):
+            return context.memfilectx(f, data, False, False, None)
+
+         self.ui.status("updating tags\n")
+         date = "%s 0" % int(time.mktime(time.gmtime()))
+         extra = {'branch': self.tagsbranch}
+         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
+                              [".hgtags"], getfilectx, "convert-repo", date,
+                              extra)
+         self.repo.commitctx(ctx)
+         return hex(self.repo.changelog.tip())
 
     def setfilemapmode(self, active):
         self.filemapmode = active
@@ -224,25 +209,24 b' class mercurial_source(converter_source)'
 
     def changectx(self, rev):
         if self.lastrev != rev:
-            self.lastctx = self.repo.changectx(rev)
+            self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def getheads(self):
         if self.rev:
-            return [hex(self.repo.changectx(self.rev).node())]
+            return [hex(self.repo[self.rev].node())]
         else:
             return [hex(node) for node in self.repo.heads()]
 
     def getfile(self, name, rev):
         try:
-            return self.changectx(rev).filectx(name).data()
+            return self.changectx(rev)[name].data()
         except revlog.LookupError, err:
             raise IOError(err)
 
     def getmode(self, name, rev):
-        m = self.changectx(rev).manifest()
-        return (m.execf(name) and 'x' or '') + (m.linkf(name) and 'l' or '')
+        return self.changectx(rev).manifest().flags(name)
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
@@ -251,8 +235,7 b' class mercurial_source(converter_source)'
         else:
             m, a, r = self.repo.status(ctx.parents()[0].node(), ctx.node())[:3]
         changes = [(name, rev) for name in m + a + r]
-        changes.sort()
-        return (changes, self.getcopies(ctx, m + a))
+        return util.sort(changes), self.getcopies(ctx, m + a)
 
     def getcopies(self, ctx, files):
         copies = {}

hgext/convert/subversion.py

@@ -655,8 +655,7 b' class svn_source(converter_source):'
                 # This will fail if a directory was copied
                 # from another branch and then some of its files
                 # were deleted in the same transaction.
-                children = self._find_children(path, revnum)
-                children.sort()
+                children = util.sort(self._find_children(path, revnum))
                 for child in children:
                     # Can we move a child directory and its
                     # parent in the same commit? (probably can). Could
@@ -729,8 +728,7 b' class svn_source(converter_source):'
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
-            orig_paths = orig_paths.items()
-            orig_paths.sort()
+            orig_paths = util.sort(orig_paths.items())
             root_paths = [(p,e) for p,e in orig_paths if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
@@ -1034,12 +1032,6 b' class svn_sink(converter_sink, commandli'
                 if 'x' in flags:
                     self.setexec.append(filename)
 
-    def delfile(self, name):
-        self.delete.append(name)
-
-    def copyfile(self, source, dest):
-        self.copies.append([source, dest])
-
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
@@ -1072,10 +1064,9 b' class svn_sink(converter_sink, commandli'
         return dirs
 
     def add_dirs(self, files):
-        add_dirs = [d for d in self.dirs_of(files)
+        add_dirs = [d for d in util.sort(self.dirs_of(files))
                     if not os.path.exists(self.wjoin(d, '.svn', 'entries'))]
         if add_dirs:
-            add_dirs.sort()
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
@@ -1085,8 +1076,7 b' class svn_sink(converter_sink, commandli'
         return files
 
     def tidy_dirs(self, names):
-        dirs = list(self.dirs_of(names))
-        dirs.sort()
+        dirs = util.sort(self.dirs_of(names))
         dirs.reverse()
         deleted = []
         for d in dirs:
@@ -1102,7 +1092,20 b' class svn_sink(converter_sink, commandli'
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
-    def putcommit(self, files, parents, commit):
+    def putcommit(self, files, copies, parents, commit, source):
+        # Apply changes to working copy
+        for f, v in files:
+            try:
+                data = source.getfile(f, v)
+            except IOError, inst:
+                self.delete.append(f)
+            else:
+                e = source.getmode(f, v)
+                self.putfile(f, e, data)
+                if f in copies:
+                    self.copies.append([copies[f], f])
+        files = [f[0] for f in files]
+
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])

hgext/extdiff.py

@@ -52,7 +52,6 b' import os, shlex, shutil, tempfile'
 
 def snapshot_node(ui, repo, files, node, tmproot):
     '''snapshot files as of some revision'''
-    mf = repo.changectx(node).manifest()
     dirname = os.path.basename(repo.root)
     if dirname == "":
         dirname = "root"
@@ -61,17 +60,18 b' def snapshot_node(ui, repo, files, node,'
     os.mkdir(base)
     ui.note(_('making snapshot of %d files from rev %s\n') %
             (len(files), short(node)))
+    ctx = repo[node]
     for fn in files:
-        if not fn in mf:
+        wfn = util.pconvert(fn)
+        if not wfn in ctx:
             # skipping new file after a merge ?
             continue
-        wfn = util.pconvert(fn)
         ui.note('  %s\n' % wfn)
         dest = os.path.join(base, wfn)
         destdir = os.path.dirname(dest)
         if not os.path.isdir(destdir):
             os.makedirs(destdir)
-        data = repo.wwritedata(wfn, repo.file(wfn).read(mf[wfn]))
+        data = repo.wwritedata(wfn, ctx[wfn].data())
         open(dest, 'wb').write(data)
     return dirname
 
@@ -121,9 +121,8 b' def dodiff(ui, repo, diffcmd, diffopts, '
     - just invoke the diff for a single file in the working dir
     '''
     node1, node2 = cmdutil.revpair(repo, opts['rev'])
-    files, matchfn, anypats = cmdutil.matchpats(repo, pats, opts)
-    modified, added, removed, deleted, unknown = repo.status(
-        node1, node2, files, match=matchfn)[:5]
+    matcher = cmdutil.match(repo, pats, opts)
+    modified, added, removed = repo.status(node1, node2, matcher)[:3]
     if not (modified or added or removed):
         return 0
 

hgext/fetch.py

@@ -4,6 +4,7 b''
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
+'''pulling, updating and merging in one command'''
 
 from mercurial.i18n import _
 from mercurial.node import nullid, short

hgext/gpg.py

@@ -239,7 +239,7 b' def sign(ui, repo, *revs, **opts):'
         repo.opener("localsigs", "ab").write(sigmessage)
         return
 
-    for x in repo.status()[:5]:
+    for x in repo.status(unknown=True)[:5]:
         if ".hgsigs" in x and not opts["force"]:
             raise util.Abort(_("working copy of .hgsigs is changed "
                                "(please commit .hgsigs manually "

hgext/graphlog.py

@@ -4,6 +4,7 b''
 #
 # This software may be used and distributed according to the terms of
 # the GNU General Public License, incorporated herein by reference.
+'''show revision graphs in terminal windows'''
 
 import os
 import sys
@@ -12,6 +13,7 b' from mercurial.commands import templateo'
 from mercurial.i18n import _
 from mercurial.node import nullrev
 from mercurial.util import Abort, canonpath
+from mercurial import util
 
 def revision_grapher(repo, start_rev, stop_rev):
     """incremental revision grapher
@@ -52,8 +54,7 b' def revision_grapher(repo, start_rev, st'
         for parent in parents:
             if parent not in next_revs:
                 parents_to_add.append(parent)
-        parents_to_add.sort()
-        next_revs[rev_index:rev_index + 1] = parents_to_add
+        next_revs[rev_index:rev_index + 1] = util.sort(parents_to_add)
 
         edges = []
         for parent in parents:
@@ -88,7 +89,7 b' def filelog_grapher(repo, path, start_re'
     assert start_rev >= stop_rev
     curr_rev = start_rev
     revs = []
-    filerev = repo.file(path).count() - 1
+    filerev = len(repo.file(path)) - 1
     while filerev >= 0:
         fctx = repo.filectx(path, fileid=filerev)
 
@@ -104,8 +105,7 b' def filelog_grapher(repo, path, start_re'
         for parent in parents:
             if parent not in next_revs:
                 parents_to_add.append(parent)
-        parents_to_add.sort()
-        next_revs[rev_index:rev_index + 1] = parents_to_add
+        next_revs[rev_index:rev_index + 1] = util.sort(parents_to_add)
 
         edges = []
         for parent in parents:
@@ -197,7 +197,7 b' def get_revs(repo, rev_opt):'
         revs = revrange(repo, rev_opt)
         return (max(revs), min(revs))
     else:
-        return (repo.changelog.count() - 1, 0)
+        return (len(repo) - 1, 0)
 
 def graphlog(ui, repo, path=None, **opts):
     """show revision history alongside an ASCII revision graph

hgext/hgk.py

@@ -4,60 +4,58 b''
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
-#
-# The hgk extension allows browsing the history of a repository in a
-# graphical way. It requires Tcl/Tk version 8.4 or later. (Tcl/Tk is
-# not distributed with Mercurial.)
-#
-# hgk consists of two parts: a Tcl script that does the displaying and
-# querying of information, and an extension to mercurial named hgk.py,
-# which provides hooks for hgk to get information. hgk can be found in
-# the contrib directory, and hgk.py can be found in the hgext
-# directory.
-#
-# To load the hgext.py extension, add it to your .hgrc file (you have
-# to use your global $HOME/.hgrc file, not one in a repository). You
-# can specify an absolute path:
-#
-#   [extensions]
-#   hgk=/usr/local/lib/hgk.py
-#
-# Mercurial can also scan the default python library path for a file
-# named 'hgk.py' if you set hgk empty:
-#
-#   [extensions]
-#   hgk=
-#
-# The hg view command will launch the hgk Tcl script. For this command
-# to work, hgk must be in your search path. Alternately, you can
-# specify the path to hgk in your .hgrc file:
-#
-#   [hgk]
-#   path=/location/of/hgk
-#
-# hgk can make use of the extdiff extension to visualize
-# revisions. Assuming you had already configured extdiff vdiff
-# command, just add:
-#
-#   [hgk]
-#   vdiff=vdiff
-#
-# Revisions context menu will now display additional entries to fire
-# vdiff on hovered and selected revisions.
+'''browsing the repository in a graphical way
+
+The hgk extension allows browsing the history of a repository in a
+graphical way. It requires Tcl/Tk version 8.4 or later. (Tcl/Tk is
+not distributed with Mercurial.)
+
+hgk consists of two parts: a Tcl script that does the displaying and
+querying of information, and an extension to mercurial named hgk.py,
+which provides hooks for hgk to get information. hgk can be found in
+the contrib directory, and hgk.py can be found in the hgext directory.
+
+To load the hgext.py extension, add it to your .hgrc file (you have
+to use your global $HOME/.hgrc file, not one in a repository). You
+can specify an absolute path:
+
+  [extensions]
+  hgk=/usr/local/lib/hgk.py
+
+Mercurial can also scan the default python library path for a file
+named 'hgk.py' if you set hgk empty:
+
+  [extensions]
+  hgk=
+
+The hg view command will launch the hgk Tcl script. For this command
+to work, hgk must be in your search path. Alternately, you can
+specify the path to hgk in your .hgrc file:
+
+  [hgk]
+  path=/location/of/hgk
+
+hgk can make use of the extdiff extension to visualize revisions.
+Assuming you had already configured extdiff vdiff command, just add:
+
+  [hgk]
+  vdiff=vdiff
+
+Revisions context menu will now display additional entries to fire
+vdiff on hovered and selected revisions.'''
 
 import os
-from mercurial import commands, util, patch, revlog
+from mercurial import commands, util, patch, revlog, cmdutil
 from mercurial.node import nullid, nullrev, short
 
 def difftree(ui, repo, node1=None, node2=None, *files, **opts):
     """diff trees from two commits"""
     def __difftree(repo, node1, node2, files=[]):
         assert node2 is not None
-        mmap = repo.changectx(node1).manifest()
-        mmap2 = repo.changectx(node2).manifest()
-        status = repo.status(node1, node2, files=files)[:5]
-        modified, added, removed, deleted, unknown = status
-
+        mmap = repo[node1].manifest()
+        mmap2 = repo[node2].manifest()
+        m = cmdutil.match(repo, files)
+        modified, added, removed  = repo.status(node1, node2, m)[:3]
         empty = short(nullid)
 
         for f in modified:
@@ -92,8 +90,8 b' def difftree(ui, repo, node1=None, node2'
         if opts['patch']:
             if opts['pretty']:
                 catcommit(ui, repo, node2, "")
-            patch.diff(repo, node1, node2,
-                       files=files,
+            m = cmdutil.match(repo, files)
+            patch.diff(repo, node1, node2, match=m,
                        opts=patch.diffopts(ui, {'git': True}))
         else:
             __difftree(repo, node1, node2, files=files)
@@ -103,11 +101,11 b' def difftree(ui, repo, node1=None, node2'
 def catcommit(ui, repo, n, prefix, ctx=None):
     nlprefix = '\n' + prefix;
     if ctx is None:
-        ctx = repo.changectx(n)
-    (p1, p2) = ctx.parents()
+        ctx = repo[n]
     ui.write("tree %s\n" % short(ctx.changeset()[0])) # use ctx.node() instead ??
-    if p1: ui.write("parent %s\n" % short(p1.node()))
-    if p2: ui.write("parent %s\n" % short(p2.node()))
+    for p in ctx.parents():
+        ui.write("parent %s\n" % p)
+
     date = ctx.date()
     description = ctx.description().replace("\0", "")
     lines = description.splitlines()
@@ -175,7 +173,7 b' def catfile(ui, repo, type=None, r=None,'
 # you can specify a commit to stop at by starting the sha1 with ^
 def revtree(ui, args, repo, full="tree", maxnr=0, parents=False):
     def chlogwalk():
-        count = repo.changelog.count()
+        count = len(repo)
         i = count
         l = [0] * 100
         chunk = 100
@@ -191,7 +189,7 b' def revtree(ui, args, repo, full="tree",'
                     l[chunk - x:] = [0] * (chunk - x)
                     break
                 if full != None:
-                    l[x] = repo.changectx(i + x)
+                    l[x] = repo[i + x]
                     l[x].changeset() # force reading
                 else:
                     l[x] = 1

hgext/highlight.py

@@ -1,6 +1,4 b''
-"""
-This is Mercurial extension for syntax highlighting in the file
-revision view of hgweb.
+"""a mercurial extension for syntax highlighting in hgweb
 
 It depends on the pygments syntax highlighting library:
 http://pygments.org/
@@ -15,23 +13,15 b' There is a single configuration option:'
 [web]
 pygments_style = <style>
 
-The default is 'colorful'.  If this is changed the corresponding CSS
-file should be re-generated by running
-
-# pygmentize -f html -S <newstyle>
-
+The default is 'colorful'.
 
 -- Adam Hupp <[e-mail]>
-
-
 """
 
 from mercurial import demandimport
-demandimport.ignore.extend(['pkgutil',
-                            'pkg_resources',
-                            '__main__',])
+demandimport.ignore.extend(['pkgutil', 'pkg_resources', '__main__',])
 
-from mercurial.hgweb.hgweb_mod import hgweb
+from mercurial.hgweb import webcommands, webutil, common
 from mercurial import util
 from mercurial.templatefilters import filters
 
@@ -40,10 +30,11 b' 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="#staticurl#highlight.css" '
+SYNTAX_CSS = ('\n<link rel="stylesheet" href="{url}highlightcss" '
               'type="text/css" />')
 
-def pygmentize(self, tmpl, fctx, field):
+def pygmentize(field, fctx, style, tmpl):
+
     # append a <link ...> to the syntax highlighting css
     old_header = ''.join(tmpl('header'))
     if SYNTAX_CSS not in old_header:
@@ -54,7 +45,6 b' def pygmentize(self, tmpl, fctx, field):'
     if util.binary(text):
         return
 
-    style = self.config("web", "pygments_style", "colorful")
     # To get multi-line strings right, we can't format line-by-line
     try:
         lexer = guess_lexer_for_filename(fctx.path(), text[:1024],
@@ -79,20 +69,30 b' def pygmentize(self, tmpl, fctx, field):'
     newl = oldl.replace('line|escape', 'line|colorize')
     tmpl.cache[field] = newl
 
-def filerevision_highlight(self, tmpl, fctx):
-    pygmentize(self, tmpl, fctx, 'fileline')
+web_filerevision = webcommands._filerevision
+web_annotate = webcommands.annotate
 
-    return realrevision(self, tmpl, fctx)
+def filerevision_highlight(web, tmpl, fctx):
+    style = web.config('web', 'pygments_style', 'colorful')
+    pygmentize('fileline', fctx, style, tmpl)
+    return web_filerevision(web, tmpl, fctx)
 
-def fileannotate_highlight(self, tmpl, fctx):
-    pygmentize(self, tmpl, fctx, 'annotateline')
+def annotate_highlight(web, req, tmpl):
+    fctx = webutil.filectx(web.repo, req)
+    style = web.config('web', 'pygments_style', 'colorful')
+    pygmentize('annotateline', fctx, style, tmpl)
+    return web_annotate(web, req, tmpl)
 
-    return realannotate(self, tmpl, fctx)
+def generate_css(web, req, tmpl):
+    pg_style = web.config('web', 'pygments_style', 'colorful')
+    fmter = HtmlFormatter(style = pg_style)
+    req.respond(common.HTTP_OK, 'text/css')
+    return ['/* pygments_style = %s */\n\n' % pg_style, fmter.get_style_defs('')]
+
 
 # monkeypatch in the new version
-# should be safer than overriding the method in a derived class
-# and then patching the class
-realrevision = hgweb.filerevision
-hgweb.filerevision = filerevision_highlight
-realannotate = hgweb.fileannotate
-hgweb.fileannotate = fileannotate_highlight
+
+webcommands._filerevision = filerevision_highlight
+webcommands.annotate = annotate_highlight
+webcommands.highlightcss = generate_css
+webcommands.__all__.append('highlightcss')

hgext/inotify/__init__.py

@@ -47,12 +47,12 b' def reposetup(ui, repo):'
         # to recurse.
         inotifyserver = False
 
-        def status(self, files, match, list_ignored, list_clean,
-                   list_unknown=True):
+        def status(self, match, ignored, clean, unknown=True):
+            files = match.files()
             try:
-                if not list_ignored and not self.inotifyserver:
+                if not ignored and not self.inotifyserver:
                     result = client.query(ui, repo, files, match, False,
-                                          list_clean, list_unknown)
+                                          clean, unknown)
                     if result is not None:
                         return result
             except socket.error, err:
@@ -81,15 +81,14 b' def reposetup(ui, repo):'
                     if query:
                         try:
                             return query(ui, repo, files or [], match,
-                                         list_ignored, list_clean, list_unknown)
+                                         ignored, clean, unknown)
                         except socket.error, err:
                             ui.warn(_('could not talk to new inotify '
                                            'server: %s\n') % err[1])
                             ui.print_exc()
 
             return super(inotifydirstate, self).status(
-                files, match or util.always, list_ignored, list_clean,
-                list_unknown)
+                match, ignored, clean, unknown)
 
     repo.dirstate.__class__ = inotifydirstate
 

hgext/inotify/client.py

@@ -11,7 +11,7 b' from mercurial import ui'
 import common
 import os, select, socket, stat, struct, sys
 
-def query(ui, repo, names, match, list_ignored, list_clean, list_unknown=True):
+def query(ui, repo, names, match, ignored, clean, unknown=True):
     sock = socket.socket(socket.AF_UNIX)
     sockpath = repo.join('inotify.sock')
     sock.connect(sockpath)
@@ -20,10 +20,10 b' def query(ui, repo, names, match, list_i'
         for n in names or []:
             yield n
         states = 'almrx!'
-        if list_ignored:
+        if ignored:
             raise ValueError('this is insanity')
-        if list_clean: states += 'n'
-        if list_unknown: states += '?'
+        if clean: states += 'n'
+        if unknown: states += '?'
         yield states
 
     req = '\0'.join(genquery())

hgext/inotify/server.py

@@ -534,9 +534,7 b' class Watcher(object):'
                 self.ui.note('%s processing %d deferred events as %d\n' %
                              (self.event_time(), self.deferred,
                               len(self.eventq)))
-            eventq = self.eventq.items()
-            eventq.sort()
-            for wpath, evts in eventq:
+            for wpath, evts in util.sort(self.eventq.items()):
                 for evt in evts:
                     self.deferred_event(wpath, evt)
             self.eventq.clear()

hgext/keyword.py

@@ -78,7 +78,7 b" like CVS' $Log$, are not supported. A ke"
 "Log = {desc}" expands to the first line of the changeset description.
 '''
 
-from mercurial import commands, cmdutil, context, dispatch, filelog, revlog
+from mercurial import commands, cmdutil, dispatch, filelog, revlog
 from mercurial import patch, localrepo, templater, templatefilters, util
 from mercurial.hgweb import webcommands
 from mercurial.node import nullid, hex
@@ -88,8 +88,8 b' import re, shutil, tempfile, time'
 commands.optionalrepo += ' kwdemo'
 
 # hg commands that do not act on keywords
-nokwcommands = ('add addremove bundle copy export grep incoming init'
-                ' log outgoing push rename rollback tip'
+nokwcommands = ('add addremove annotate bundle copy export grep incoming init'
+                ' log outgoing push rename rollback tip verify'
                 ' convert email glog')
 
 # hg commands that trigger expansion only when writing to working dir,
@@ -100,52 +100,8 b' def utcdate(date):'
     '''Returns hgdate in cvs-like UTC format.'''
     return time.strftime('%Y/%m/%d %H:%M:%S', time.gmtime(date[0]))
 
-
 # make keyword tools accessible
-kwtools = {'templater': None, 'hgcmd': None}
-
-# store originals of monkeypatches
-_patchfile_init = patch.patchfile.__init__
-_patch_diff = patch.diff
-_dispatch_parse = dispatch._parse
-
-def _kwpatchfile_init(self, ui, fname, missing=False):
-    '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
-    rejects or conflicts due to expanded keywords in working dir.'''
-    _patchfile_init(self, ui, fname, missing=missing)
-    # shrink keywords read from working dir
-    kwt = kwtools['templater']
-    self.lines = kwt.shrinklines(self.fname, self.lines)
-
-def _kw_diff(repo, node1=None, node2=None, files=None, match=util.always,
-             fp=None, changes=None, opts=None):
-    '''Monkeypatch patch.diff to avoid expansion except when
-    comparing against working dir.'''
-    if node2 is not None:
-        kwtools['templater'].matcher = util.never
-    elif node1 is not None and node1 != repo.changectx().node():
-        kwtools['templater'].restrict = True
-    _patch_diff(repo, node1=node1, node2=node2, files=files, match=match,
-                fp=fp, changes=changes, opts=opts)
-
-def _kwweb_changeset(web, req, tmpl):
-    '''Wraps webcommands.changeset turning off keyword expansion.'''
-    kwtools['templater'].matcher = util.never
-    return web.changeset(tmpl, web.changectx(req))
-
-def _kwweb_filediff(web, req, tmpl):
-    '''Wraps webcommands.filediff turning off keyword expansion.'''
-    kwtools['templater'].matcher = util.never
-    return web.filediff(tmpl, web.filectx(req))
-
-def _kwdispatch_parse(ui, args):
-    '''Monkeypatch dispatch._parse to obtain running hg command.'''
-    cmd, func, args, options, cmdoptions = _dispatch_parse(ui, args)
-    kwtools['hgcmd'] = cmd
-    return cmd, func, args, options, cmdoptions
-
-# dispatch._parse is run before reposetup, so wrap it here
-dispatch._parse = _kwdispatch_parse
+kwtools = {'templater': None, 'hgcmd': '', 'inc': [], 'exc': ['.hg*']}
 
 
 class kwtemplater(object):
@@ -163,15 +119,16 b' class kwtemplater(object):'
         'Header': '{root}/{file},v {node|short} {date|utcdate} {author|user}',
     }
 
-    def __init__(self, ui, repo, inc, exc):
+    def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
-        self.matcher = util.matcher(repo.root, inc=inc, exc=exc)[1]
+        self.matcher = util.matcher(repo.root,
+                                    inc=kwtools['inc'], exc=kwtools['exc'])[1]
         self.restrict = kwtools['hgcmd'] in restricted.split()
 
         kwmaps = self.ui.configitems('keywordmaps')
         if kwmaps: # override default templates
-            kwmaps = [(k, templater.parsestring(v, quoted=False))
+            kwmaps = [(k, templater.parsestring(v, False))
                       for (k, v) in kwmaps]
             self.templates = dict(kwmaps)
         escaped = map(re.escape, self.templates.keys())
@@ -185,7 +142,7 b' class kwtemplater(object):'
     def getnode(self, path, fnode):
         '''Derives changenode from file path and filenode.'''
         # used by kwfilelog.read and kwexpand
-        c = context.filectx(self.repo, path, fileid=fnode)
+        c = self.repo.filectx(path, fileid=fnode)
         return c.node()
 
     def substitute(self, data, path, node, subfunc):
@@ -206,25 +163,26 b' class kwtemplater(object):'
             return self.substitute(data, path, changenode, self.re_kw.sub)
         return data
 
-    def iskwfile(self, path, islink):
+    def iskwfile(self, path, flagfunc):
         '''Returns true if path matches [keyword] pattern
         and is not a symbolic link.
         Caveat: localrepository._link fails on Windows.'''
-        return self.matcher(path) and not islink(path)
+        return self.matcher(path) and not 'l' in flagfunc(path)
 
-    def overwrite(self, node=None, expand=True, files=None):
+    def overwrite(self, node, expand, files):
         '''Overwrites selected files expanding/shrinking keywords.'''
-        ctx = self.repo.changectx(node)
-        mf = ctx.manifest()
         if node is not None:     # commit
+            ctx = self.repo[node]
+            mf = ctx.manifest()
             files = [f for f in ctx.files() if f in mf]
             notify = self.ui.debug
         else:                    # kwexpand/kwshrink
+            ctx = self.repo['.']
+            mf = ctx.manifest()
             notify = self.ui.note
-        candidates = [f for f in files if self.iskwfile(f, mf.linkf)]
+        candidates = [f for f in files if self.iskwfile(f, ctx.flags)]
         if candidates:
             self.restrict = True # do not expand when reading
-            candidates.sort()
             action = expand and 'expanding' or 'shrinking'
             for f in candidates:
                 fp = self.repo.file(f)
@@ -271,9 +229,9 b' class kwfilelog(filelog.filelog):'
     Subclass of filelog to hook into its read, add, cmp methods.
     Keywords are "stored" unexpanded, and processed on reading.
     '''
-    def __init__(self, opener, path):
+    def __init__(self, opener, kwt, path):
         super(kwfilelog, self).__init__(opener, path)
-        self.kwt = kwtools['templater']
+        self.kwt = kwt
         self.path = path
 
     def read(self, node):
@@ -284,7 +242,7 b' class kwfilelog(filelog.filelog):'
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = self.kwt.shrink(self.path, text)
-        return super(kwfilelog, self).add(text, meta, tr, link, p1=p1, p2=p2)
+        return super(kwfilelog, self).add(text, meta, tr, link, p1, p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
@@ -294,28 +252,30 b' class kwfilelog(filelog.filelog):'
             return t2 != text
         return revlog.revlog.cmp(self, node, text)
 
-def _status(ui, repo, kwt, *pats, **opts):
+def _status(ui, repo, kwt, unknown, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if kwt:
-        files, match, anypats = cmdutil.matchpats(repo, pats, opts)
-        return repo.status(files=files, match=match, list_clean=True)
+        matcher = cmdutil.match(repo, pats, opts)
+        return repo.status(match=matcher, unknown=unknown, clean=True)
     if ui.configitems('keyword'):
         raise util.Abort(_('[keyword] patterns cannot match'))
     raise util.Abort(_('no [keyword] patterns configured'))
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to kwtemplater.overwrite.'''
+    if repo.dirstate.parents()[1] != nullid:
+        raise util.Abort(_('outstanding uncommitted merge'))
     kwt = kwtools['templater']
-    status = _status(ui, repo, kwt, *pats, **opts)
-    modified, added, removed, deleted, unknown, ignored, clean = status
+    status = _status(ui, repo, kwt, False, *pats, **opts)
+    modified, added, removed, deleted = status[:4]
     if modified or added or removed or deleted:
-        raise util.Abort(_('outstanding uncommitted changes in given files'))
+        raise util.Abort(_('outstanding uncommitted changes'))
     wlock = lock = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
-        kwt.overwrite(expand=expand, files=clean)
+        kwt.overwrite(None, expand, status[6])
     finally:
         del wlock, lock
 
@@ -345,7 +305,7 b' def demo(ui, repo, *args, **opts):'
     branchname = 'demobranch'
     tmpdir = tempfile.mkdtemp('', 'kwdemo.')
     ui.note(_('creating temporary repo at %s\n') % tmpdir)
-    repo = localrepo.localrepository(ui, path=tmpdir, create=True)
+    repo = localrepo.localrepository(ui, tmpdir, True)
     ui.setconfig('keyword', fn, '')
     if args or opts.get('rcfile'):
         kwstatus = 'custom'
@@ -367,6 +327,7 b' def demo(ui, repo, *args, **opts):'
         ui.readconfig(repo.join('hgrc'))
     if not opts.get('default'):
         kwmaps = dict(ui.configitems('keywordmaps')) or kwtemplater.templates
+    uisetup(ui)
     reposetup(ui, repo)
     for k, v in ui.configitems('extensions'):
         if k.endswith('keyword'):
@@ -418,15 +379,11 b' def files(ui, repo, *pats, **opts):'
     That is, files matched by [keyword] config patterns but not symlinks.
     '''
     kwt = kwtools['templater']
-    status = _status(ui, repo, kwt, *pats, **opts)
+    status = _status(ui, repo, kwt, opts.get('untracked'), *pats, **opts)
     modified, added, removed, deleted, unknown, ignored, clean = status
-    files = modified + added + clean
-    if opts.get('untracked'):
-        files += unknown
-    files.sort()
-    wctx = repo.workingctx()
-    islink = lambda p: 'l' in wctx.fileflags(p)
-    kwfiles = [f for f in files if kwt.iskwfile(f, islink)]
+    files = util.sort(modified + added + clean + unknown)
+    wctx = repo[None]
+    kwfiles = [f for f in files if kwt.iskwfile(f, wctx.flags)]
     cwd = pats and repo.getcwd() or ''
     kwfstats = not opts.get('ignore') and (('K', kwfiles),) or ()
     if opts.get('all') or opts.get('ignore'):
@@ -448,46 +405,57 b' def shrink(ui, repo, *pats, **opts):'
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 
+def uisetup(ui):
+    '''Collects [keyword] config in kwtools.
+    Monkeypatches dispatch._parse if needed.'''
+
+    for pat, opt in ui.configitems('keyword'):
+        if opt != 'ignore':
+            kwtools['inc'].append(pat)
+        else:
+            kwtools['exc'].append(pat)
+
+    if kwtools['inc']:
+        def kwdispatch_parse(ui, args):
+            '''Monkeypatch dispatch._parse to obtain running hg command.'''
+            cmd, func, args, options, cmdoptions = dispatch_parse(ui, args)
+            kwtools['hgcmd'] = cmd
+            return cmd, func, args, options, cmdoptions
+
+        dispatch_parse = dispatch._parse
+        dispatch._parse = kwdispatch_parse
+
 def reposetup(ui, repo):
     '''Sets up repo as kwrepo for keyword substitution.
     Overrides file method to return kwfilelog instead of filelog
     if file matches user configuration.
     Wraps commit to overwrite configured files with updated
     keyword substitutions.
-    This is done for local repos only, and only if there are
-    files configured at all for keyword substitution.'''
+    Monkeypatches patch and webcommands.'''
 
     try:
-        if (not repo.local() or kwtools['hgcmd'] in nokwcommands.split()
+        if (not repo.local() or not kwtools['inc']
+            or kwtools['hgcmd'] in nokwcommands.split()
             or '.hg' in util.splitpath(repo.root)
             or repo._url.startswith('bundle:')):
             return
     except AttributeError:
         pass
 
-    inc, exc = [], ['.hg*']
-    for pat, opt in ui.configitems('keyword'):
-        if opt != 'ignore':
-            inc.append(pat)
-        else:
-            exc.append(pat)
-    if not inc:
-        return
-
-    kwtools['templater'] = kwt = kwtemplater(ui, repo, inc, exc)
+    kwtools['templater'] = kwt = kwtemplater(ui, repo)
 
     class kwrepo(repo.__class__):
         def file(self, f):
             if f[0] == '/':
                 f = f[1:]
-            return kwfilelog(self.sopener, f)
+            return kwfilelog(self.sopener, kwt, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             return kwt.wread(filename, data)
 
         def commit(self, files=None, text='', user=None, date=None,
-                   match=util.always, force=False, force_editor=False,
+                   match=None, force=False, force_editor=False,
                    p1=None, p2=None, extra={}, empty_ok=False):
             wlock = lock = None
             _p1 = _p2 = None
@@ -512,28 +480,66 b' def reposetup(ui, repo):'
                     else:
                         _p2 = hex(_p2)
 
-                node = super(kwrepo,
-                             self).commit(files=files, text=text, user=user,
-                                          date=date, match=match, force=force,
-                                          force_editor=force_editor,
-                                          p1=p1, p2=p2, extra=extra,
-                                          empty_ok=empty_ok)
+                n = super(kwrepo, self).commit(files, text, user, date, match,
+                                               force, force_editor, p1, p2,
+                                               extra, empty_ok)
 
                 # restore commit hooks
                 for name, cmd in commithooks.iteritems():
                     ui.setconfig('hooks', name, cmd)
-                if node is not None:
-                    kwt.overwrite(node=node)
-                    repo.hook('commit', node=node, parent1=_p1, parent2=_p2)
-                return node
+                if n is not None:
+                    kwt.overwrite(n, True, None)
+                    repo.hook('commit', node=n, parent1=_p1, parent2=_p2)
+                return n
             finally:
                 del wlock, lock
 
+    # monkeypatches
+    def kwpatchfile_init(self, ui, fname, missing=False):
+        '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
+        rejects or conflicts due to expanded keywords in working dir.'''
+        patchfile_init(self, ui, fname, missing)
+        # shrink keywords read from working dir
+        self.lines = kwt.shrinklines(self.fname, self.lines)
+
+    def kw_diff(repo, node1=None, node2=None, match=None,
+                fp=None, changes=None, opts=None):
+        '''Monkeypatch patch.diff to avoid expansion except when
+        comparing against working dir.'''
+        if node2 is not None:
+            kwt.matcher = util.never
+        elif node1 is not None and node1 != repo['.'].node():
+            kwt.restrict = True
+        patch_diff(repo, node1, node2, match, fp, changes, opts)
+
+    def kwweb_annotate(web, req, tmpl):
+        '''Wraps webcommands.annotate turning off keyword expansion.'''
+        kwt.matcher = util.never
+        return webcommands_annotate(web, req, tmpl)
+
+    def kwweb_changeset(web, req, tmpl):
+        '''Wraps webcommands.changeset turning off keyword expansion.'''
+        kwt.matcher = util.never
+        return webcommands_changeset(web, req, tmpl)
+
+    def kwweb_filediff(web, req, tmpl):
+        '''Wraps webcommands.filediff turning off keyword expansion.'''
+        kwt.matcher = util.never
+        return webcommands_filediff(web, req, tmpl)
+
     repo.__class__ = kwrepo
-    patch.patchfile.__init__ = _kwpatchfile_init
-    patch.diff = _kw_diff
-    webcommands.changeset = webcommands.rev = _kwweb_changeset
-    webcommands.filediff = webcommands.diff = _kwweb_filediff
+
+    patchfile_init = patch.patchfile.__init__
+    patch_diff = patch.diff
+    webcommands_annotate = webcommands.annotate
+    webcommands_changeset = webcommands.changeset
+    webcommands_filediff = webcommands.filediff
+
+    patch.patchfile.__init__ = kwpatchfile_init
+    patch.diff = kw_diff
+    webcommands.annotate = kwweb_annotate
+    webcommands.changeset = webcommands.rev = kwweb_changeset
+    webcommands.filediff = webcommands.diff = kwweb_filediff
 
 
 cmdtable = {

hgext/mq.py

@@ -143,8 +143,7 b' class queue:'
             bad = self.check_guard(guard)
             if bad:
                 raise util.Abort(bad)
-        guards = dict.fromkeys(guards).keys()
-        guards.sort()
+        guards = util.sort(util.unique(guards))
         self.ui.debug('active guards: %s\n' % ' '.join(guards))
         self.active_guards = guards
         self.guards_dirty = True
@@ -322,10 +321,8 b' class queue:'
 
     def printdiff(self, repo, node1, node2=None, files=None,
                   fp=None, changes=None, opts={}):
-        fns, matchfn, anypats = cmdutil.matchpats(repo, files, opts)
-
-        patch.diff(repo, node1, node2, fns, match=matchfn,
-                   fp=fp, changes=changes, opts=self.diffopts())
+        m = cmdutil.match(repo, files, opts)
+        patch.diff(repo, node1, node2, m, fp, changes, self.diffopts())
 
     def mergeone(self, repo, mergeq, head, patch, rev):
         # first try just applying the patch
@@ -344,7 +341,7 b' class queue:'
         hg.clean(repo, head)
         self.strip(repo, n, update=False, backup='strip')
 
-        ctx = repo.changectx(rev)
+        ctx = repo[rev]
         ret = hg.merge(repo, rev)
         if ret:
             raise util.Abort(_("update returned %d") % ret)
@@ -510,8 +507,10 b' class queue:'
                     repo.dirstate.merge(f)
                 p1, p2 = repo.dirstate.parents()
                 repo.dirstate.setparents(p1, merge)
+
             files = patch.updatedir(self.ui, repo, files)
-            n = repo.commit(files, message, user, date, match=util.never,
+            match = cmdutil.matchfiles(repo, files or [])
+            n = repo.commit(files, message, user, date, match=match,
                             force=True)
 
             if n == None:
@@ -535,6 +534,40 b' class queue:'
                 break
         return (err, n)
 
+    def _clean_series(self, patches):
+        indices = util.sort([self.find_series(p) for p in patches])
+        for i in indices[-1::-1]:
+            del self.full_series[i]
+        self.parse_series()
+        self.series_dirty = 1
+
+    def finish(self, repo, revs):
+        revs.sort()
+        firstrev = repo[self.applied[0].rev].rev()
+        appliedbase = 0
+        patches = []
+        for rev in util.sort(revs):
+            if rev < firstrev:
+                raise util.Abort(_('revision %d is not managed') % rev)
+            base = revlog.bin(self.applied[appliedbase].rev)
+            node = repo.changelog.node(rev)
+            if node != base:
+                raise util.Abort(_('cannot delete revision %d above '
+                                   'applied patches') % rev)
+            patches.append(self.applied[appliedbase].name)
+            appliedbase += 1
+
+        r = self.qrepo()
+        if r:
+            r.remove(patches, True)
+        else:
+            for p in patches:
+                os.unlink(self.join(p))
+
+        del self.applied[:appliedbase]
+        self.applied_dirty = 1
+        self._clean_series(patches)
+
     def delete(self, repo, patches, opts):
         if not patches and not opts.get('rev'):
             raise util.Abort(_('qdelete requires at least one revision or '
@@ -580,12 +613,7 b' class queue:'
         if appliedbase:
             del self.applied[:appliedbase]
             self.applied_dirty = 1
-        indices = [self.find_series(p) for p in realpatches]
-        indices.sort()
-        for i in indices[-1::-1]:
-            del self.full_series[i]
-        self.parse_series()
-        self.series_dirty = 1
+        self._clean_series(realpatches)
 
     def check_toppatch(self, repo):
         if len(self.applied) > 0:
@@ -623,11 +651,11 b' class queue:'
         if os.path.exists(self.join(patch)):
             raise util.Abort(_('patch "%s" already exists') % patch)
         if opts.get('include') or opts.get('exclude') or pats:
-            fns, match, anypats = cmdutil.matchpats(repo, pats, opts)
-            m, a, r, d = repo.status(files=fns, match=match)[:4]
+            match = cmdutil.match(repo, pats, opts)
+            m, a, r, d = repo.status(match=match)[:4]
         else:
             m, a, r, d = self.check_localchanges(repo, force)
-            fns, match, anypats = cmdutil.matchpats(repo, m + a + r)
+            match = cmdutil.match(repo, m + a + r)
         commitfiles = m + a + r
         self.check_toppatch(repo)
         wlock = repo.wlock()
@@ -665,14 +693,14 b' class queue:'
         finally:
             del wlock
 
-    def strip(self, repo, rev, update=True, backup="all"):
+    def strip(self, repo, rev, update=True, backup="all", force=None):
         wlock = lock = None
         try:
             wlock = repo.wlock()
             lock = repo.lock()
 
             if update:
-                self.check_localchanges(repo, refresh=False)
+                self.check_localchanges(repo, force=force, refresh=False)
                 urev = self.qparents(repo, rev)
                 hg.clean(repo, urev)
                 repo.dirstate.write()
@@ -822,7 +850,7 b' class queue:'
                 self.ui.warn(_('cleaning up working directory...'))
                 node = repo.dirstate.parents()[0]
                 hg.revert(repo, node, None)
-                unknown = repo.status()[4]
+                unknown = repo.status(unknown=True)[4]
                 # only remove unknown files that we know we touched or
                 # created while patching
                 for f in unknown:
@@ -903,7 +931,7 b' class queue:'
                 qp = self.qparents(repo, rev)
                 changes = repo.changelog.read(qp)
                 mmap = repo.manifest.read(changes[0])
-                m, a, r, d, u = repo.status(qp, top)[:5]
+                m, a, r, d = repo.status(qp, top)[:4]
                 if d:
                     raise util.Abort("deletions found between repo revs")
                 for f in m:
@@ -937,10 +965,7 b' class queue:'
             self.ui.write("No patches applied\n")
             return
         qp = self.qparents(repo, top)
-        if opts.get('git'):
-            self.diffopts().git = True
-        if opts.get('unified') is not None:
-            self.diffopts().context = opts['unified']
+        self._diffopts = patch.diffopts(self.ui, opts)
         self.printdiff(repo, qp, files=pats, opts=opts)
 
     def refresh(self, repo, pats=None, **opts):
@@ -1026,7 +1051,7 b' class queue:'
 
             if opts.get('git'):
                 self.diffopts().git = True
-            fns, matchfn, anypats = cmdutil.matchpats(repo, pats, opts)
+            matchfn = cmdutil.match(repo, pats, opts)
             tip = repo.changelog.tip()
             if top == tip:
                 # if the top of our patch queue is also the tip, there is an
@@ -1039,21 +1064,19 b' class queue:'
                 # patch already
                 #
                 # this should really read:
-                #   mm, dd, aa, aa2, uu = repo.status(tip, patchparent)[:5]
+                #   mm, dd, aa, aa2 = repo.status(tip, patchparent)[:4]
                 # but we do it backwards to take advantage of manifest/chlog
                 # caching against the next repo.status call
                 #
-                mm, aa, dd, aa2, uu = repo.status(patchparent, tip)[:5]
+                mm, aa, dd, aa2 = repo.status(patchparent, tip)[:4]
                 changes = repo.changelog.read(tip)
                 man = repo.manifest.read(changes[0])
                 aaa = aa[:]
                 if opts.get('short'):
-                    filelist = mm + aa + dd
-                    match = dict.fromkeys(filelist).__contains__
+                    match = cmdutil.matchfiles(repo, mm + aa + dd)
                 else:
-                    filelist = None
-                    match = util.always
-                m, a, r, d, u = repo.status(files=filelist, match=match)[:5]
+                    match = cmdutil.matchall(repo)
+                m, a, r, d = repo.status(match=match)[:4]
 
                 # we might end up with files that were added between
                 # tip and the dirstate parent, but then changed in the
@@ -1086,9 +1109,9 b' class queue:'
                 m = util.unique(mm)
                 r = util.unique(dd)
                 a = util.unique(aa)
-                c = [filter(matchfn, l) for l in (m, a, r, [], u)]
-                filelist = util.unique(c[0] + c[1] + c[2])
-                patch.diff(repo, patchparent, files=filelist, match=matchfn,
+                c = [filter(matchfn, l) for l in (m, a, r)]
+                match = cmdutil.matchfiles(repo, util.unique(c[0] + c[1] + c[2]))
+                patch.diff(repo, patchparent, match=match,
                            fp=patchf, changes=c, opts=self.diffopts())
                 patchf.close()
 
@@ -1146,7 +1169,7 b' class queue:'
                 self.applied_dirty = 1
                 self.strip(repo, top, update=False,
                            backup='strip')
-                n = repo.commit(filelist, message, user, date, match=matchfn,
+                n = repo.commit(match.files(), message, user, date, match=match,
                                 force=1)
                 self.applied.append(statusentry(revlog.hex(n), patchfn))
                 self.removeundo(repo)
@@ -1236,8 +1259,7 b' class queue:'
                                    self.guards_path)
                         and not fl.startswith('.')):
                         msng_list.append(fl)
-            msng_list.sort()
-            for x in msng_list:
+            for x in util.sort(msng_list):
                 pfx = self.ui.verbose and ('D ') or ''
                 self.ui.write("%s%s\n" % (pfx, displayname(x)))
 
@@ -1499,9 +1521,8 b' def delete(ui, repo, *patches, **opts):'
     the --rev parameter. At least one patch or revision is required.
 
     With --rev, mq will stop managing the named revisions (converting
-    them to regular mercurial changesets). The patches must be applied
-    and at the base of the stack. This option is useful when the patches
-    have been applied upstream.
+    them to regular mercurial changesets). The qfinish command should be
+    used as an alternative for qdel -r, as the latter option is deprecated.
 
     With --keep, the patch files are preserved in the patch directory."""
     q = repo.mq
@@ -2086,7 +2107,7 b' def strip(ui, repo, rev, **opts):'
     elif rev not in (cl.ancestor(p[0], rev), cl.ancestor(p[1], rev)):
         update = False
 
-    repo.mq.strip(repo, rev, backup=backup, update=update)
+    repo.mq.strip(repo, rev, backup=backup, update=update, force=opts['force'])
     return 0
 
 def select(ui, repo, *args, **opts):
@@ -2191,6 +2212,34 b' def select(ui, repo, *args, **opts):'
         finally:
             q.save_dirty()
 
+def finish(ui, repo, *revrange, **opts):
+    """move applied patches into repository history
+
+    Finishes the specified revisions (corresponding to applied patches) by
+    moving them out of mq control into regular repository history.
+
+    Accepts a revision range or the --all option. If --all is specified, all
+    applied mq revisions are removed from mq control. Otherwise, the given
+    revisions must be at the base of the stack of applied patches.
+
+    This can be especially useful if your changes have been applied to an
+    upstream repository, or if you are about to push your changes to upstream.
+    """
+    if not opts['applied'] and not revrange:
+        raise util.Abort(_('no revisions specified'))
+    elif opts['applied']:
+        revrange = ('qbase:qtip',) + revrange
+
+    q = repo.mq
+    if not q.applied:
+        ui.status(_('no patches applied\n'))
+        return 0
+
+    revs = cmdutil.revrange(repo, revrange)
+    q.finish(repo, revs)
+    q.save_dirty()
+    return 0
+
 def reposetup(ui, repo):
     class mqrepo(repo.__class__):
         def abort_if_wdir_patched(self, errmsg, force=False):
@@ -2267,7 +2316,7 b' def reposetup(ui, repo):'
             # we might as well use it, but we won't save it.
 
             # update the cache up to the tip
-            self._updatebranchcache(partial, start, cl.count())
+            self._updatebranchcache(partial, start, len(cl))
 
             return partial
 
@@ -2300,10 +2349,8 b' cmdtable = {'
          _('hg qcommit [OPTION]... [FILE]...')),
     "^qdiff":
         (diff,
-         [('g', 'git', None, _('use git extended diff format')),
-          ('U', 'unified', 3, _('number of lines of context to show')),
-         ] + commands.walkopts,
-         _('hg qdiff [-I] [-X] [-U NUM] [-g] [FILE]...')),
+         commands.diffopts + commands.diffopts2 + commands.walkopts,
+         _('hg qdiff [OPTION]... [FILE]...')),
     "qdelete|qremove|qrm":
         (delete,
          [('k', 'keep', None, _('keep patch file')),
@@ -2395,9 +2442,14 b' cmdtable = {'
          _('hg qseries [-ms]')),
     "^strip":
         (strip,
-         [('b', 'backup', None, _('bundle unrelated changesets')),
+         [('f', 'force', None, _('force removal with local changes')),
+          ('b', 'backup', None, _('bundle unrelated changesets')),
           ('n', 'nobackup', None, _('no backups'))],
          _('hg strip [-f] [-b] [-n] REV')),
     "qtop": (top, [] + seriesopts, _('hg qtop [-s]')),
     "qunapplied": (unapplied, [] + seriesopts, _('hg qunapplied [-s] [PATCH]')),
+    "qfinish":
+        (finish,
+         [('a', 'applied', None, _('finish all applied changesets'))],
+         _('hg qfinish [-a] [REV...]')),
 }

hgext/notify.py

@@ -156,9 +156,7 b' class notifier(object):'
             if fnmatch.fnmatch(self.repo.root, pat):
                 for user in users.split(','):
                     subs[self.fixmail(user)] = 1
-        subs = subs.keys()
-        subs.sort()
-        return subs
+        return util.sort(subs)
 
     def url(self, path=None):
         return self.ui.config('web', 'baseurl') + (path or self.root)
@@ -269,11 +267,11 b' def hook(ui, repo, hooktype, node=None, '
     node = bin(node)
     ui.pushbuffer()
     if hooktype == 'changegroup':
-        start = repo.changelog.rev(node)
-        end = repo.changelog.count()
+        start = repo[node].rev()
+        end = len(repo)
         count = end - start
         for rev in xrange(start, end):
-            n.node(repo.changelog.node(rev))
+            n.node(repo[node].rev())
         n.diff(node, repo.changelog.tip())
     else:
         count = 1

hgext/pager.py

@@ -10,26 +10,56 b''
 #   [extension]
 #   hgext.pager =
 #
-# To set the pager that should be used, set the application variable:
-#
-#   [pager]
-#   pager = LESS='FSRX' less
-#
-# If no pager is set, the pager extensions uses the environment
-# variable $PAGER. If neither pager.pager, nor $PAGER is set, no pager
-# is used.
-#
-# If you notice "BROKEN PIPE" error messages, you can disable them
-# by setting:
-#
-#   [pager]
-#   quiet = True
+# Run "hg help pager" to get info on configuration.
+
+'''browse command output with external pager
+
+To set the pager that should be used, set the application variable:
+
+  [pager]
+  pager = LESS='FSRX' less
+
+If no pager is set, the pager extensions uses the environment
+variable $PAGER. If neither pager.pager, nor $PAGER is set, no pager
+is used.
+
+If you notice "BROKEN PIPE" error messages, you can disable them
+by setting:
+
+  [pager]
+  quiet = True
+
+You can disable the pager for certain commands by adding them to the
+pager.ignore list:
+
+  [pager]
+  ignore = version, help, update
+
+You can also enable the pager only for certain commands using pager.attend:
+
+  [pager]
+  attend = log
+
+If pager.attend is present, pager.ignore will be ignored.
+
+To ignore global commands like "hg version" or "hg help", you have to specify
+them in the global .hgrc
+'''
 
 import sys, os, signal
+from mercurial import dispatch, util
 
 def uisetup(ui):
-    p = ui.config("pager", "pager", os.environ.get("PAGER"))
-    if p and sys.stdout.isatty() and '--debugger' not in sys.argv:
-        if ui.configbool('pager', 'quiet'):
-            signal.signal(signal.SIGPIPE, signal.SIG_DFL)
-        sys.stderr = sys.stdout = os.popen(p, "wb")
+    def pagecmd(ui, options, cmd, cmdfunc):
+        p = ui.config("pager", "pager", os.environ.get("PAGER"))
+        if p and sys.stdout.isatty() and '--debugger' not in sys.argv:
+            attend = ui.configlist('pager', 'attend')
+            if (cmd in attend or
+                (cmd not in ui.configlist('pager', 'ignore') and not attend)):
+                sys.stderr = sys.stdout = util.popen(p, "wb")
+                if ui.configbool('pager', 'quiet'):
+                    signal.signal(signal.SIGPIPE, signal.SIG_DFL)
+        return oldrun(ui, options, cmd, cmdfunc)
+
+    oldrun = dispatch._runcommand
+    dispatch._runcommand = pagecmd

hgext/patchbomb.py

@@ -1,72 +1,69 b''
-# Command for sending a collection of Mercurial changesets as a series
-# of patch emails.
-#
-# The series is started off with a "[PATCH 0 of N]" introduction,
-# which describes the series as a whole.
-#
-# Each patch email has a Subject line of "[PATCH M of N] ...", using
-# the first line of the changeset description as the subject text.
-# The message contains two or three body parts:
-#
-#   The remainder of the changeset description.
-#
-#   [Optional] If the diffstat program is installed, the result of
-#   running diffstat on the patch.
-#
-#   The patch itself, as generated by "hg export".
-#
-# Each message refers to all of its predecessors using the In-Reply-To
-# and References headers, so they will show up as a sequence in
-# threaded mail and news readers, and in mail archives.
-#
-# For each changeset, you will be prompted with a diffstat summary and
-# the changeset summary, so you can be sure you are sending the right
-# changes.
-#
-# To enable this extension:
-#
-#   [extensions]
-#   hgext.patchbomb =
-#
-# To configure other defaults, add a section like this to your hgrc
-# file:
-#
-#   [email]
-#   from = My Name <my@email>
-#   to = recipient1, recipient2, ...
-#   cc = cc1, cc2, ...
-#   bcc = bcc1, bcc2, ...
-#
-# Then you can use the "hg email" command to mail a series of changesets
-# as a patchbomb.
-#
-# To avoid sending patches prematurely, it is a good idea to first run
-# the "email" command with the "-n" option (test only).  You will be
-# prompted for an email recipient address, a subject an an introductory
-# message describing the patches of your patchbomb.  Then when all is
-# done, patchbomb messages are displayed. If PAGER environment variable
-# is set, your pager will be fired up once for each patchbomb message, so
-# you can verify everything is alright.
-#
-# The "-m" (mbox) option is also very useful.  Instead of previewing
-# each patchbomb message in a pager or sending the messages directly,
-# it will create a UNIX mailbox file with the patch emails.  This
-# mailbox file can be previewed with any mail user agent which supports
-# UNIX mbox files, i.e. with mutt:
-#
-#   % mutt -R -f mbox
-#
-# When you are previewing the patchbomb messages, you can use `formail'
-# (a utility that is commonly installed as part of the procmail package),
-# to send each message out:
-#
-#  % formail -s sendmail -bm -t < mbox
-#
-# That should be all.  Now your patchbomb is on its way out.
+'''sending Mercurial changesets as a series of patch emails
+
+The series is started off with a "[PATCH 0 of N]" introduction,
+which describes the series as a whole.
+
+Each patch email has a Subject line of "[PATCH M of N] ...", using
+the first line of the changeset description as the subject text.
+The message contains two or three body parts:
+
+  The remainder of the changeset description.
+
+  [Optional] If the diffstat program is installed, the result of
+  running diffstat on the patch.
+
+  The patch itself, as generated by "hg export".
+
+Each message refers to all of its predecessors using the In-Reply-To
+and References headers, so they will show up as a sequence in
+threaded mail and news readers, and in mail archives.
+
+For each changeset, you will be prompted with a diffstat summary and
+the changeset summary, so you can be sure you are sending the right changes.
+
+To enable this extension:
+
+  [extensions]
+  hgext.patchbomb =
+
+To configure other defaults, add a section like this to your hgrc file:
 
-import os, errno, socket, tempfile
+  [email]
+  from = My Name <my@email>
+  to = recipient1, recipient2, ...
+  cc = cc1, cc2, ...
+  bcc = bcc1, bcc2, ...
+
+Then you can use the "hg email" command to mail a series of changesets
+as a patchbomb.
+
+To avoid sending patches prematurely, it is a good idea to first run
+the "email" command with the "-n" option (test only).  You will be
+prompted for an email recipient address, a subject an an introductory
+message describing the patches of your patchbomb.  Then when all is
+done, patchbomb messages are displayed. If PAGER environment variable
+is set, your pager will be fired up once for each patchbomb message, so
+you can verify everything is alright.
+
+The "-m" (mbox) option is also very useful.  Instead of previewing
+each patchbomb message in a pager or sending the messages directly,
+it will create a UNIX mailbox file with the patch emails.  This
+mailbox file can be previewed with any mail user agent which supports
+UNIX mbox files, i.e. with mutt:
+
+  % mutt -R -f mbox
+
+When you are previewing the patchbomb messages, you can use `formail'
+(a utility that is commonly installed as part of the procmail package),
+to send each message out:
+
+  % formail -s sendmail -bm -t < mbox
+
+That should be all. Now your patchbomb is on its way out.'''
+
+import os, errno, socket, tempfile, cStringIO
 import email.MIMEMultipart, email.MIMEText, email.MIMEBase
-import email.Utils, email.Encoders
+import email.Utils, email.Encoders, email.Generator
 from mercurial import cmdutil, commands, hg, mail, patch, util
 from mercurial.i18n import _
 from mercurial.node import bin
@@ -404,11 +401,12 b' def patchbomb(ui, repo, *revs, **opts):'
             ui.status('Displaying ', m['Subject'], ' ...\n')
             ui.flush()
             if 'PAGER' in os.environ:
-                fp = os.popen(os.environ['PAGER'], 'w')
+                fp = util.popen(os.environ['PAGER'], 'w')
             else:
                 fp = ui
+            generator = email.Generator.Generator(fp, mangle_from_=False)
             try:
-                fp.write(m.as_string(0))
+                generator.flatten(m, 0)
                 fp.write('\n')
             except IOError, inst:
                 if inst.errno != errno.EPIPE:
@@ -418,9 +416,10 b' def patchbomb(ui, repo, *revs, **opts):'
         elif opts.get('mbox'):
             ui.status('Writing ', m['Subject'], ' ...\n')
             fp = open(opts.get('mbox'), 'In-Reply-To' in m and 'ab+' or 'wb+')
+            generator = email.Generator.Generator(fp, mangle_from_=True)
             date = util.datestr(start_time, '%a %b %d %H:%M:%S %Y')
             fp.write('From %s %s\n' % (sender_addr, date))
-            fp.write(m.as_string(0))
+            generator.flatten(m, 0)
             fp.write('\n\n')
             fp.close()
         else:
@@ -429,7 +428,10 b' def patchbomb(ui, repo, *revs, **opts):'
             ui.status('Sending ', m['Subject'], ' ...\n')
             # Exim does not remove the Bcc field
             del m['Bcc']
-            sendmail(sender, to + bcc + cc, m.as_string(0))
+            fp = cStringIO.StringIO()
+            generator = email.Generator.Generator(fp, mangle_from_=False)
+            generator.flatten(m, 0)
+            sendmail(sender, to + bcc + cc, fp.getvalue())
 
 cmdtable = {
     "email":

hgext/purge.py

@@ -27,79 +27,10 b''
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 
-from mercurial import util, commands
+from mercurial import util, commands, cmdutil
 from mercurial.i18n import _
 import os
 
-def dopurge(ui, repo, dirs=None, act=True, ignored=False,
-            abort_on_err=False, eol='\n',
-            force=False, include=None, exclude=None):
-    def error(msg):
-        if abort_on_err:
-            raise util.Abort(msg)
-        else:
-            ui.warn(_('warning: %s\n') % msg)
-
-    def remove(remove_func, name):
-        if act:
-            try:
-                remove_func(os.path.join(repo.root, name))
-            except OSError, e:
-                error(_('%s cannot be removed') % name)
-        else:
-            ui.write('%s%s' % (name, eol))
-
-    if not force:
-        _check_fs(ui, repo)
-
-    directories = []
-    files = []
-    missing = []
-    roots, match, anypats = util.cmdmatcher(repo.root, repo.getcwd(), dirs,
-                                            include, exclude)
-    for src, f, st in repo.dirstate.statwalk(files=roots, match=match,
-                                             ignored=ignored, directories=True):
-        if src == 'd':
-            directories.append(f)
-        elif src == 'm':
-            missing.append(f)
-        elif src == 'f' and f not in repo.dirstate:
-            files.append(f)
-
-    directories.sort()
-
-    for f in files:
-        if f not in repo.dirstate:
-            ui.note(_('Removing file %s\n') % f)
-            remove(os.remove, f)
-
-    for f in directories[::-1]:
-        if match(f) and not os.listdir(repo.wjoin(f)):
-            ui.note(_('Removing directory %s\n') % f)
-            remove(os.rmdir, f)
-
-def _check_fs(ui, repo):
-    """Abort if there is the chance of having problems with name-mangling fs
-
-    In a name mangling filesystem (e.g. a case insensitive one)
-    dirstate.walk() can yield filenames different from the ones
-    stored in the dirstate. This already confuses the status and
-    add commands, but with purge this may cause data loss.
-
-    To prevent this, this function will abort if there are uncommitted
-    changes.
-    """
-
-    # We can't use (files, match) to do a partial walk here - we wouldn't
-    # notice a modified README file if the user ran "hg purge readme"
-    modified, added, removed, deleted = repo.status()[:4]
-    if modified or added or removed or deleted:
-        if not util.checkfolding(repo.path) and not ui.quiet:
-            ui.warn(_("Purging on name mangling filesystems is not "
-                      "fully supported.\n"))
-        raise util.Abort(_("outstanding uncommitted changes"))
-
-
 def purge(ui, repo, *dirs, **opts):
     '''removes files not tracked by mercurial
 
@@ -125,25 +56,42 b' def purge(ui, repo, *dirs, **opts):'
     files that this program would delete use the --print option.
     '''
     act = not opts['print']
-    ignored = bool(opts['all'])
-    abort_on_err = bool(opts['abort_on_err'])
-    eol = opts['print0'] and '\0' or '\n'
-    if eol == '\0':
-        # --print0 implies --print
-        act = False
-    force = bool(opts['force'])
-    include = opts['include']
-    exclude = opts['exclude']
-    dopurge(ui, repo, dirs, act, ignored, abort_on_err,
-            eol, force, include, exclude)
+    eol = '\n'
+    if opts['print0']:
+        eol = '\0'
+        act = False # --print0 implies --print
 
+    def remove(remove_func, name):
+        if act:
+            try:
+                remove_func(os.path.join(repo.root, name))
+            except OSError, e:
+                m = _('%s cannot be removed') % name
+                if opts['abort_on_err']:
+                    raise util.Abort(m)
+                ui.warn(_('warning: %s\n') % m)
+        else:
+            ui.write('%s%s' % (name, eol))
+
+    directories = []
+    match = cmdutil.match(repo, dirs, opts)
+    match.dir = directories.append
+    status = repo.status(match=match, ignored=opts['all'], unknown=True)
+
+    for f in util.sort(status[4] + status[5]):
+        ui.note(_('Removing file %s\n') % f)
+        remove(os.remove, f)
+
+    for f in util.sort(directories)[::-1]:
+        if match(f) and not os.listdir(repo.wjoin(f)):
+            ui.note(_('Removing directory %s\n') % f)
+            remove(os.rmdir, f)
 
 cmdtable = {
     'purge|clean':
         (purge,
          [('a', 'abort-on-err', None, _('abort if an error occurs')),
           ('',  'all', None, _('purge ignored files too')),
-          ('f', 'force', None, _('purge even when there are uncommitted changes')),
           ('p', 'print', None, _('print the file names instead of deleting them')),
           ('0', 'print0', None, _('end filenames with NUL, for use with xargs'
                                   ' (implies -p)')),

hgext/record.py

@@ -389,7 +389,7 b' def dorecord(ui, repo, committer, *pats,'
     if not ui.interactive:
         raise util.Abort(_('running non-interactively, use commit instead'))
 
-    def recordfunc(ui, repo, files, message, match, opts):
+    def recordfunc(ui, repo, message, match, opts):
         """This is generic record driver.
 
         It's job is to interactively filter local changes, and accordingly
@@ -402,16 +402,16 b' def dorecord(ui, repo, committer, *pats,'
         In the end we'll record intresting changes, and everything else will be
         left in place, so the user can continue his work.
         """
-        if files:
+        if match.files():
             changes = None
         else:
-            changes = repo.status(files=files, match=match)[:5]
-            modified, added, removed = changes[:3]
-            files = modified + added + removed
+            changes = repo.status(match=match)[:3]
+            modified, added, removed = changes
+            match = cmdutil.matchfiles(repo, modified + added + removed)
         diffopts = mdiff.diffopts(git=True, nodates=True)
         fp = cStringIO.StringIO()
-        patch.diff(repo, repo.dirstate.parents()[0], files=files,
-                   match=match, changes=changes, opts=diffopts, fp=fp)
+        patch.diff(repo, repo.dirstate.parents()[0], match=match,
+                   changes=changes, opts=diffopts, fp=fp)
         fp.seek(0)
 
         # 1. filter patch, so we have intending-to apply subset of it
@@ -423,14 +423,15 b' def dorecord(ui, repo, committer, *pats,'
             try: contenders.update(dict.fromkeys(h.files()))
             except AttributeError: pass
 
-        newfiles = [f for f in files if f in contenders]
+        newfiles = [f for f in match.files() if f in contenders]
 
         if not newfiles:
             ui.status(_('no changes to record\n'))
             return 0
 
         if changes is None:
-            changes = repo.status(files=newfiles, match=match)[:5]
+            match = cmdutil.matchfiles(repo, newfiles)
+            changes = repo.status(match=match)
         modified = dict.fromkeys(changes[0])
 
         # 2. backup changed files, so we can restore them in the end

hgext/transplant.py

@@ -88,9 +88,7 b' class transplanter:'
 
     def apply(self, repo, source, revmap, merges, opts={}):
         '''apply the revisions in revmap one by one in revision order'''
-        revs = revmap.keys()
-        revs.sort()
-
+        revs = util.sort(revmap)
         p1, p2 = repo.dirstate.parents()
         pulls = []
         diffopts = patch.diffopts(self.ui, opts)
@@ -310,9 +308,7 b' class transplanter:'
         if not os.path.isdir(self.path):
             os.mkdir(self.path)
         series = self.opener('series', 'w')
-        revs = revmap.keys()
-        revs.sort()
-        for rev in revs:
+        for rev in util.sort(revmap):
             series.write(revlog.hex(revmap[rev]) + '\n')
         if merges:
             series.write('# Merges\n')
@@ -572,10 +568,6 b' def transplant(ui, repo, *revs, **opts):'
         for r in merges:
             revmap[source.changelog.rev(r)] = r
 
-        revs = revmap.keys()
-        revs.sort()
-        pulls = []
-
         tp.apply(repo, source, revmap, merges, opts)
     finally:
         if bundle:

hgext/win32text.py

@@ -1,4 +1,4 b''
-# win32text.py - LF <-> CRLF translation utilities for Windows users
+# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
@@ -9,95 +9,133 b''
 # hgext.win32text =
 # [encode]
 # ** = cleverencode:
+# # or ** = macencode:
 # [decode]
 # ** = cleverdecode:
+# # or ** = macdecode:
 #
-# If not doing conversion, to make sure you do not commit CRLF by accident:
+# If not doing conversion, to make sure you do not commit CRLF/CR by accident:
 #
 # [hooks]
 # pretxncommit.crlf = python:hgext.win32text.forbidcrlf
+# # or pretxncommit.cr = python:hgext.win32text.forbidcr
 #
-# To do the same check on a server to prevent CRLF from being pushed or pulled:
+# To do the same check on a server to prevent CRLF/CR from being pushed or
+# pulled:
 #
 # [hooks]
 # pretxnchangegroup.crlf = python:hgext.win32text.forbidcrlf
+# # or pretxnchangegroup.cr = python:hgext.win32text.forbidcr
 
 from mercurial.i18n import gettext as _
 from mercurial.node import bin, short
+from mercurial import util
 import re
 
 # regexp for single LF without CR preceding.
 re_single_lf = re.compile('(^|[^\r])\n', re.MULTILINE)
 
-def dumbdecode(s, cmd, ui=None, repo=None, filename=None, **kwargs):
-    # warn if already has CRLF in repository.
+newlinestr = {'\r\n': 'CRLF', '\r': 'CR'}
+filterstr = {'\r\n': 'clever', '\r': 'mac'}
+
+def checknewline(s, newline, ui=None, repo=None, filename=None):
+    # warn if already has 'newline' in repository.
     # it might cause unexpected eol conversion.
     # see issue 302:
     #   http://www.selenic.com/mercurial/bts/issue302
-    if '\r\n' in s and ui and filename and repo:
-        ui.warn(_('WARNING: %s already has CRLF line endings\n'
+    if newline in s and ui and filename and repo:
+        ui.warn(_('WARNING: %s already has %s line endings\n'
                   'and does not need EOL conversion by the win32text plugin.\n'
                   'Before your next commit, please reconsider your '
                   'encode/decode settings in \nMercurial.ini or %s.\n') %
-                (filename, repo.join('hgrc')))
+                (filename, newlinestr[newline], repo.join('hgrc')))
+
+def dumbdecode(s, cmd, **kwargs):
+    checknewline(s, '\r\n', **kwargs)
     # replace single LF to CRLF
     return re_single_lf.sub('\\1\r\n', s)
 
 def dumbencode(s, cmd):
     return s.replace('\r\n', '\n')
 
-def clevertest(s, cmd):
-    if '\0' in s: return False
-    return True
+def macdumbdecode(s, cmd, **kwargs):
+    checknewline(s, '\r', **kwargs)
+    return s.replace('\n', '\r')
+
+def macdumbencode(s, cmd):
+    return s.replace('\r', '\n')
 
 def cleverdecode(s, cmd, **kwargs):
-    if clevertest(s, cmd):
+    if not util.binary(s):
         return dumbdecode(s, cmd, **kwargs)
     return s
 
 def cleverencode(s, cmd):
-    if clevertest(s, cmd):
+    if not util.binary(s):
         return dumbencode(s, cmd)
     return s
 
+def macdecode(s, cmd, **kwargs):
+    if not util.binary(s):
+        return macdumbdecode(s, cmd, **kwargs)
+    return s
+
+def macencode(s, cmd):
+    if not util.binary(s):
+        return macdumbencode(s, cmd)
+    return s
+
 _filters = {
     'dumbdecode:': dumbdecode,
     'dumbencode:': dumbencode,
     'cleverdecode:': cleverdecode,
     'cleverencode:': cleverencode,
+    'macdumbdecode:': macdumbdecode,
+    'macdumbencode:': macdumbencode,
+    'macdecode:': macdecode,
+    'macencode:': macencode,
     }
 
-def forbidcrlf(ui, repo, hooktype, node, **kwargs):
+def forbidnewline(ui, repo, hooktype, node, newline, **kwargs):
     halt = False
-    for rev in xrange(repo.changelog.rev(bin(node)), repo.changelog.count()):
-        c = repo.changectx(rev)
+    for rev in xrange(repo[node].rev(), len(repo)):
+        c = repo[rev]
         for f in c.files():
             if f not in c:
                 continue
             data = c[f].data()
-            if '\0' not in data and '\r\n' in data:
+            if not util.binary(data) and newline in data:
                 if not halt:
                     ui.warn(_('Attempt to commit or push text file(s) '
-                              'using CRLF line endings\n'))
+                              'using %s line endings\n') %
+                              newlinestr[newline])
                 ui.warn(_('in %s: %s\n') % (short(c.node()), f))
                 halt = True
     if halt and hooktype == 'pretxnchangegroup':
+        crlf = newlinestr[newline].lower()
+        filter = filterstr[newline]
         ui.warn(_('\nTo prevent this mistake in your local repository,\n'
                   'add to Mercurial.ini or .hg/hgrc:\n'
                   '\n'
                   '[hooks]\n'
-                  'pretxncommit.crlf = python:hgext.win32text.forbidcrlf\n'
+                  'pretxncommit.%s = python:hgext.win32text.forbid%s\n'
                   '\n'
                   'and also consider adding:\n'
                   '\n'
                   '[extensions]\n'
                   'hgext.win32text =\n'
                   '[encode]\n'
-                  '** = cleverencode:\n'
+                  '** = %sencode:\n'
                   '[decode]\n'
-                  '** = cleverdecode:\n'))
+                  '** = %sdecode:\n') % (crlf, crlf, filter, filter))
     return halt
 
+def forbidcrlf(ui, repo, hooktype, node, **kwargs):
+    return forbidnewline(ui, repo, hooktype, node, '\r\n', **kwargs)
+
+def forbidcr(ui, repo, hooktype, node, **kwargs):
+    return forbidnewline(ui, repo, hooktype, node, '\r', **kwargs)
+
 def reposetup(ui, repo):
     if not repo.local():
         return

mercurial/archival.py

@@ -52,7 +52,8 b' class tarit:'
         def _write_gzip_header(self):
             self.fileobj.write('\037\213')             # magic header
             self.fileobj.write('\010')                 # compression method
-            fname = self.filename[:-3]
+            # Python 2.6 deprecates self.filename
+            fname = getattr(self, 'name', None) or self.filename
             flags = 0
             if fname:
                 flags = gzip.FNAME
@@ -207,18 +208,17 b' def archive(repo, dest, node, kind, deco'
             data = repo.wwritedata(name, data)
         archiver.addfile(name, mode, islink, data)
 
-    ctx = repo.changectx(node)
     if kind not in archivers:
         raise util.Abort(_("unknown archive type '%s'" % kind))
+
+    ctx = repo[node]
     archiver = archivers[kind](dest, prefix, mtime or ctx.date()[0])
-    m = ctx.manifest()
-    items = m.items()
-    items.sort()
+
     if repo.ui.configbool("ui", "archivemeta", True):
         write('.hg_archival.txt', 0644, False,
               lambda: 'repo: %s\nnode: %s\n' % (
                   hex(repo.changelog.node(0)), hex(node)))
-    for filename, filenode in items:
-        write(filename, m.execf(filename) and 0755 or 0644, m.linkf(filename),
-              lambda: repo.file(filename).read(filenode))
+    for f in ctx:
+        ff = ctx.flags(f)
+        write(f, 'x' in ff and 0755 or 0644, 'l' in ff, ctx[f].data)
     archiver.done()

mercurial/bundlerepo.py

@@ -12,7 +12,7 b' of the GNU General Public License, incor'
 
 from node import hex, nullid, short
 from i18n import _
-import changegroup, util, os, struct, bz2, tempfile, shutil, mdiff
+import changegroup, util, os, struct, bz2, zlib, tempfile, shutil, mdiff
 import repo, localrepo, changelog, manifest, filelog, revlog
 
 class bundlerevlog(revlog.revlog):
@@ -34,7 +34,7 b' class bundlerevlog(revlog.revlog):'
             for chunk in changegroup.chunkiter(bundlefile):
                 pos = bundlefile.tell()
                 yield chunk, pos - len(chunk)
-        n = self.count()
+        n = len(self)
         prev = None
         for chunk, start in chunkpositer():
             size = len(chunk)
@@ -127,7 +127,7 b' class bundlerevlog(revlog.revlog):'
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
-    def addgroup(self, revs, linkmapper, transaction, unique=0):
+    def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
@@ -173,14 +173,17 b' class bundlerepository(localrepo.localre'
             raise util.Abort(_("%s: not a Mercurial bundle file") % bundlename)
         elif not header.startswith("HG10"):
             raise util.Abort(_("%s: unknown bundle version") % bundlename)
-        elif header == "HG10BZ":
+        elif (header == "HG10BZ") or (header == "HG10GZ"):
             fdtemp, temp = tempfile.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un", dir=self.path)
             self.tempfile = temp
             fptemp = os.fdopen(fdtemp, 'wb')
             def generator(f):
-                zd = bz2.BZ2Decompressor()
-                zd.decompress("BZ")
+                if header == "HG10BZ":
+                    zd = bz2.BZ2Decompressor()
+                    zd.decompress("BZ")
+                elif header == "HG10GZ":
+                    zd = zlib.decompressobj()
                 for chunk in f:
                     yield zd.decompress(chunk)
             gen = generator(util.filechunkiter(self.bundlefile, 4096))

mercurial/changelog.py

@@ -82,7 +82,7 b' class changelog(revlog):'
         "delay visibility of index updates to other readers"
         self._realopener = self.opener
         self.opener = self._delayopener
-        self._delaycount = self.count()
+        self._delaycount = len(self)
         self._delaybuf = []
         self._delayname = None
 
@@ -108,7 +108,7 b' class changelog(revlog):'
         # if we're doing an initial clone, divert to another file
         if self._delaycount == 0:
             self._delayname = fp.name
-            if not self.count():
+            if not len(self):
                 # make sure to truncate the file
                 mode = mode.replace('a', 'w')
             return self._realopener(name + ".a", mode)
@@ -130,9 +130,7 b' class changelog(revlog):'
 
     def encode_extra(self, d):
         # keys must be sorted to produce a deterministic changelog entry
-        keys = d.keys()
-        keys.sort()
-        items = [_string_escape('%s:%s' % (k, d[k])) for k in keys]
+        items = [_string_escape('%s:%s' % (k, d[k])) for k in util.sort(d)]
         return "\0".join(items)
 
     def read(self, node):
@@ -175,7 +173,7 b' class changelog(revlog):'
         files = l[3:]
         return (manifest, user, (time, timezone), files, desc, extra)
 
-    def add(self, manifest, list, desc, transaction, p1=None, p2=None,
+    def add(self, manifest, files, desc, transaction, p1=None, p2=None,
                   user=None, date=None, extra={}):
 
         user, desc = util.fromlocal(user), util.fromlocal(desc)
@@ -189,7 +187,6 b' class changelog(revlog):'
         if extra:
             extra = self.encode_extra(extra)
             parseddate = "%s %s" % (parseddate, extra)
-        list.sort()
-        l = [hex(manifest), user, parseddate] + list + ["", desc]
+        l = [hex(manifest), user, parseddate] + util.sort(files) + ["", desc]
         text = "\n".join(l)
-        return self.addrevision(text, transaction, self.count(), p1, p2)
+        return self.addrevision(text, transaction, len(self), p1, p2)

mercurial/cmdutil.py

@@ -9,6 +9,7 b' from node import hex, nullid, nullrev, s'
 from i18n import _
 import os, sys, bisect, stat
 import mdiff, bdiff, util, templater, templatefilters, patch, errno
+import match as _match
 
 revrangesep = ':'
 
@@ -125,7 +126,7 b' def revpair(repo, revs):'
         if revrangesep in revs[0]:
             start, end = revs[0].split(revrangesep, 1)
             start = revfix(repo, start, 0)
-            end = revfix(repo, end, repo.changelog.count() - 1)
+            end = revfix(repo, end, len(repo) - 1)
         else:
             start = revfix(repo, revs[0], None)
     elif len(revs) == 2:
@@ -150,7 +151,7 b' def revrange(repo, revs):'
         if revrangesep in spec:
             start, end = spec.split(revrangesep, 1)
             start = revfix(repo, start, 0)
-            end = revfix(repo, end, repo.changelog.count() - 1)
+            end = revfix(repo, end, len(repo) - 1)
             step = start > end and -1 or 1
             for rev in xrange(start, end+step, step):
                 if rev in seen:
@@ -223,27 +224,28 b' def make_file(repo, pat, node=None,'
                               pathname),
                 mode)
 
-def matchpats(repo, pats=[], opts={}, globbed=False, default=None):
-    cwd = repo.getcwd()
-    return util.cmdmatcher(repo.root, cwd, pats or [], opts.get('include'),
-                           opts.get('exclude'), globbed=globbed,
-                           default=default)
+def match(repo, pats=[], opts={}, globbed=False, default='relpath'):
+    if not globbed and default == 'relpath':
+        pats = util.expand_glob(pats or [])
+    m = _match.match(repo.root, repo.getcwd(), pats,
+                    opts.get('include'), opts.get('exclude'), default)
+    def badfn(f, msg):
+        repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
+        return False
+    m.bad = badfn
+    return m
 
-def walk(repo, pats=[], opts={}, node=None, badmatch=None, globbed=False,
-         default=None):
-    files, matchfn, anypats = matchpats(repo, pats, opts, globbed=globbed,
-                                        default=default)
-    exact = dict.fromkeys(files)
-    cwd = repo.getcwd()
-    for src, fn in repo.walk(node=node, files=files, match=matchfn,
-                             badmatch=badmatch):
-        yield src, fn, repo.pathto(fn, cwd), fn in exact
+def matchall(repo):
+    return _match.always(repo.root, repo.getcwd())
+
+def matchfiles(repo, files):
+    return _match.exact(repo.root, repo.getcwd(), files)
 
 def findrenames(repo, added=None, removed=None, threshold=0.5):
     '''find renamed files -- yields (before, after, score) tuples'''
     if added is None or removed is None:
         added, removed = repo.status()[1:3]
-    ctx = repo.changectx()
+    ctx = repo['.']
     for a in added:
         aa = repo.wread(a)
         bestname, bestscore = None, threshold
@@ -275,16 +277,19 b' def addremove(repo, pats=[], opts={}, dr'
     add, remove = [], []
     mapping = {}
     audit_path = util.path_auditor(repo.root)
-    for src, abs, rel, exact in walk(repo, pats, opts):
+    m = match(repo, pats, opts)
+    for abs in repo.walk(m):
         target = repo.wjoin(abs)
         good = True
         try:
             audit_path(abs)
         except:
             good = False
-        if src == 'f' and good and abs not in repo.dirstate:
+        rel = m.rel(abs)
+        exact = m.exact(abs)
+        if good and abs not in repo.dirstate:
             add.append(abs)
-            mapping[abs] = rel, exact
+            mapping[abs] = rel, m.exact(abs)
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('adding %s\n') % ((pats and rel) or abs))
         if repo.dirstate[abs] != 'r' and (not good or not util.lexists(target)
@@ -319,8 +324,11 b' def copy(ui, repo, pats, opts, rename=Fa'
 
     def walkpat(pat):
         srcs = []
-        for tag, abs, rel, exact in walk(repo, [pat], opts, globbed=True):
+        m = match(repo, [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 '?r':
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
@@ -645,9 +653,7 b' class changeset_printer(object):'
             self.ui.write(_("copies:      %s\n") % ' '.join(copies))
 
         if extra and self.ui.debugflag:
-            extraitems = extra.items()
-            extraitems.sort()
-            for key, value in extraitems:
+            for key, value in util.sort(extra.items()):
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')))
 
@@ -791,9 +797,7 b' class changeset_templater(changeset_prin'
             return showlist('tag', self.repo.nodetags(changenode), **args)
 
         def showextras(**args):
-            extras = changes[5].items()
-            extras.sort()
-            for key, value in extras:
+            for key, value in util.sort(changes[5].items()):
                 args = args.copy()
                 args.update(dict(key=key, value=value))
                 yield self.t('extra', **args)
@@ -889,7 +893,7 b' def show_changeset(ui, repo, opts, buffe'
     # options
     patch = False
     if opts.get('patch'):
-        patch = matchfn or util.always
+        patch = matchfn or matchall(repo)
 
     tmpl = opts.get('template')
     mapfile = None
@@ -922,7 +926,7 b' def show_changeset(ui, repo, opts, buffe'
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
     df = util.matchdate(date)
-    get = util.cachefunc(lambda r: repo.changectx(r).changeset())
+    get = util.cachefunc(lambda r: repo[r].changeset())
     changeiter, matchfn = walkchangerevs(ui, repo, [], get, {'rev':None})
     results = {}
     for st, rev, fns in changeiter:
@@ -977,31 +981,31 b' def walkchangerevs(ui, repo, pats, chang'
                 if windowsize < sizelimit:
                     windowsize *= 2
 
-    files, matchfn, anypats = matchpats(repo, pats, opts)
+    m = match(repo, pats, opts)
     follow = opts.get('follow') or opts.get('follow_first')
 
-    if repo.changelog.count() == 0:
-        return [], matchfn
+    if not len(repo):
+        return [], m
 
     if follow:
-        defrange = '%s:0' % repo.changectx().rev()
+        defrange = '%s:0' % repo['.'].rev()
     else:
         defrange = '-1:0'
     revs = revrange(repo, opts['rev'] or [defrange])
     wanted = {}
-    slowpath = anypats or opts.get('removed')
+    slowpath = m.anypats() or opts.get('removed')
     fncache = {}
 
-    if not slowpath and not files:
+    if not slowpath and not m.files():
         # No files, no patterns.  Display all revs.
         wanted = dict.fromkeys(revs)
     copies = []
     if not slowpath:
         # Only files, no patterns.  Check the history of each file.
         def filerevgen(filelog, node):
-            cl_count = repo.changelog.count()
+            cl_count = len(repo)
             if node is None:
-                last = filelog.count() - 1
+                last = len(filelog) - 1
             else:
                 last = filelog.rev(node)
             for i, window in increasing_windows(last, nullrev):
@@ -1017,14 +1021,14 b' def walkchangerevs(ui, repo, pats, chang'
                     if rev[0] < cl_count:
                         yield rev
         def iterfiles():
-            for filename in files:
+            for filename in m.files():
                 yield filename, None
             for filename_node in copies:
                 yield filename_node
         minrev, maxrev = min(revs), max(revs)
         for file_, node in iterfiles():
             filelog = repo.file(file_)
-            if filelog.count() == 0:
+            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.
@@ -1050,13 +1054,12 b' def walkchangerevs(ui, repo, pats, chang'
 
         # The slow path checks files modified in every changeset.
         def changerevgen():
-            for i, window in increasing_windows(repo.changelog.count()-1,
-                                                nullrev):
+            for i, window in increasing_windows(len(repo) - 1, nullrev):
                 for j in xrange(i - window, i + 1):
                     yield j, change(j)[3]
 
         for rev, changefiles in changerevgen():
-            matches = filter(matchfn, changefiles)
+            matches = filter(m, changefiles)
             if matches:
                 fncache[rev] = matches
                 wanted[rev] = 1
@@ -1109,7 +1112,7 b' def walkchangerevs(ui, repo, pats, chang'
                 del wanted[x]
 
     def iterate():
-        if follow and not files:
+        if follow and not m.files():
             ff = followfilter(onlyfirst=opts.get('follow_first'))
             def want(rev):
                 if ff.match(rev) and rev in wanted:
@@ -1122,20 +1125,18 b' def walkchangerevs(ui, repo, pats, chang'
         for i, window in increasing_windows(0, len(revs)):
             yield 'window', revs[0] < revs[-1], revs[-1]
             nrevs = [rev for rev in revs[i:i+window] if want(rev)]
-            srevs = list(nrevs)
-            srevs.sort()
-            for rev in srevs:
+            for rev in util.sort(list(nrevs)):
                 fns = fncache.get(rev)
                 if not fns:
                     def fns_generator():
                         for f in change(rev)[3]:
-                            if matchfn(f):
+                            if m(f):
                                 yield f
                     fns = fns_generator()
                 yield 'add', rev, fns
             for rev in nrevs:
                 yield 'iter', rev, None
-    return iterate(), matchfn
+    return iterate(), m
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
@@ -1149,13 +1150,12 b' def commit(ui, repo, commitfunc, pats, o'
     if opts.get('addremove'):
         addremove(repo, pats, opts)
 
-    fns, match, anypats = matchpats(repo, pats, opts)
+    m = match(repo, pats, opts)
     if pats:
-        status = repo.status(files=fns, match=match)
-        modified, added, removed, deleted, unknown = status[:5]
-        files = modified + added + removed
+        modified, added, removed = repo.status(match=m)[:3]
+        files = util.sort(modified + added + removed)
         slist = None
-        for f in fns:
+        for f in m.files():
             if f == '.':
                 continue
             if f not in files:
@@ -1167,11 +1167,8 b' def commit(ui, repo, commitfunc, pats, o'
                     raise util.Abort(_("file %s not found!") % rel)
                 if stat.S_ISDIR(mode):
                     name = f + '/'
-                    if slist is None:
-                        slist = list(files)
-                        slist.sort()
-                    i = bisect.bisect(slist, name)
-                    if i >= len(slist) or not slist[i].startswith(name):
+                    i = bisect.bisect(files, name)
+                    if i >= len(files) or not files[i].startswith(name):
                         raise util.Abort(_("no match under directory %s!")
                                          % rel)
                 elif not (stat.S_ISREG(mode) or stat.S_ISLNK(mode)):
@@ -1179,9 +1176,8 b' def commit(ui, repo, commitfunc, pats, o'
                                        "unsupported file type!") % rel)
                 elif f not in repo.dirstate:
                     raise util.Abort(_("file %s not tracked!") % rel)
-    else:
-        files = []
+        m = matchfiles(repo, files)
     try:
-        return commitfunc(ui, repo, files, message, match, opts)
+        return commitfunc(ui, repo, message, m, opts)
     except ValueError, inst:
         raise util.Abort(str(inst))

mercurial/commands.py

@@ -13,6 +13,7 b' import hg, util, revlog, bundlerepo, ext'
 import difflib, patch, time, help, mdiff, tempfile
 import version, socket
 import archival, changegroup, cmdutil, hgweb.server, sshserver, hbisect
+import merge as merge_
 
 # Commands start here, listed alphabetically
 
@@ -30,15 +31,16 b' def add(ui, repo, *pats, **opts):'
     rejected = None
     exacts = {}
     names = []
-    for src, abs, rel, exact in cmdutil.walk(repo, pats, opts,
-                                             badmatch=util.always):
-        if exact:
+    m = cmdutil.match(repo, pats, opts)
+    m.bad = lambda x,y: True
+    for abs in repo.walk(m):
+        if m.exact(abs):
             if ui.verbose:
-                ui.status(_('adding %s\n') % rel)
+                ui.status(_('adding %s\n') % m.rel(abs))
             names.append(abs)
             exacts[abs] = 1
         elif abs not in repo.dirstate:
-            ui.status(_('adding %s\n') % rel)
+            ui.status(_('adding %s\n') % m.rel(abs))
             names.append(abs)
     if not opts.get('dry_run'):
         rejected = repo.add(names)
@@ -53,11 +55,11 b' def addremove(ui, repo, *pats, **opts):'
     New files are ignored if they match any of the patterns in .hgignore. As
     with add, these changes take effect at the next commit.
 
-    Use the -s option to detect renamed files.  With a parameter > 0,
+    Use the -s option to detect renamed files. With a parameter > 0,
     this compares every removed file with every added file and records
-    those similar enough as renames.  This option takes a percentage
+    those similar enough as renames. This option takes a percentage
     between 0 (disabled) and 100 (files must be identical) as its
-    parameter.  Detecting renamed files this way can be expensive.
+    parameter. Detecting renamed files this way can be expensive.
     """
     try:
         sim = float(opts.get('similarity') or 0)
@@ -105,13 +107,13 b' def annotate(ui, repo, *pats, **opts):'
         lastfunc = funcmap[-1]
         funcmap[-1] = lambda x: "%s:%s" % (lastfunc(x), x[1])
 
-    ctx = repo.changectx(opts['rev'])
-
-    for src, abs, rel, exact in cmdutil.walk(repo, pats, opts,
-                                             node=ctx.node()):
-        fctx = ctx.filectx(abs)
+    ctx = repo[opts['rev']]
+
+    m = cmdutil.match(repo, pats, opts)
+    for abs in ctx.walk(m):
+        fctx = ctx[abs]
         if not opts['text'] and util.binary(fctx.data()):
-            ui.write(_("%s: binary file\n") % ((pats and rel) or abs))
+            ui.write(_("%s: binary file\n") % ((pats and m.rel(abs)) or abs))
             continue
 
         lines = fctx.annotate(follow=opts.get('follow'),
@@ -134,7 +136,7 b' def archive(ui, repo, dest, **opts):'
     By default, the revision used is the parent of the working
     directory; use "-r" to specify a different revision.
 
-    To specify the type of archive to create, use "-t".  Valid
+    To specify the type of archive to create, use "-t". Valid
     types are:
 
     "files" (default): a directory full of files
@@ -148,18 +150,18 b' def archive(ui, repo, dest, **opts):'
     using a format string; see "hg help export" for details.
 
     Each member added to an archive file has a directory prefix
-    prepended.  Use "-p" to specify a format string for the prefix.
+    prepended. Use "-p" to specify a format string for the prefix.
     The default is the basename of the archive, with suffixes removed.
     '''
 
-    ctx = repo.changectx(opts['rev'])
+    ctx = repo[opts['rev']]
     if not ctx:
         raise util.Abort(_('repository has no revisions'))
     node = ctx.node()
     dest = cmdutil.make_filename(repo, dest, node)
     if os.path.realpath(dest) == repo.root:
         raise util.Abort(_('repository root cannot be destination'))
-    dummy, matchfn, dummy = cmdutil.matchpats(repo, [], opts)
+    matchfn = cmdutil.match(repo, [], opts)
     kind = opts.get('type') or 'files'
     prefix = opts['prefix']
     if dest == '-':
@@ -174,20 +176,20 b' def archive(ui, repo, dest, **opts):'
 def backout(ui, repo, node=None, rev=None, **opts):
     '''reverse effect of earlier changeset
 
-    Commit the backed out changes as a new changeset.  The new
+    Commit the backed out changes as a new changeset. The new
     changeset is a child of the backed out changeset.
 
     If you back out a changeset other than the tip, a new head is
-    created.  This head will be the new tip and you should merge this
+    created. This head will be the new tip and you should merge this
     backout changeset with another head (current one by default).
 
     The --merge option remembers the parent of the working directory
     before starting the backout, then merges the new head with that
-    changeset afterwards.  This saves you from doing the merge by
-    hand.  The result of this merge is not committed, as for a normal
+    changeset afterwards. This saves you from doing the merge by
+    hand. The result of this merge is not committed, as for a normal
     merge.
 
-    See 'hg help dates' for a list of formats valid for -d/--date.
+    See \'hg help dates\' for a list of formats valid for -d/--date.
     '''
     if rev and node:
         raise util.Abort(_("please specify just one revision"))
@@ -368,7 +370,7 b' def branch(ui, repo, label=None, **opts)'
 
     if label:
         if not opts.get('force') and label in repo.branchtags():
-            if label not in [p.branch() for p in repo.workingctx().parents()]:
+            if label not in [p.branch() for p in repo.parents()]:
                 raise util.Abort(_('a branch of the same name already exists'
                                    ' (use --force to override)'))
         repo.dirstate.setbranch(util.fromlocal(label))
@@ -380,18 +382,17 b' def branches(ui, repo, active=False):'
     """list repository named branches
 
     List the repository's named branches, indicating which ones are
-    inactive.  If active is specified, only show active branches.
+    inactive. If active is specified, only show active branches.
 
     A branch is considered active if it contains repository heads.
 
     Use the command 'hg update' to switch to an existing branch.
     """
     hexfunc = ui.debugflag and hex or short
-    activebranches = [util.tolocal(repo.changectx(n).branch())
+    activebranches = [util.tolocal(repo[n].branch())
                             for n in repo.heads()]
-    branches = [(tag in activebranches, repo.changelog.rev(node), tag)
-                            for tag, node in repo.branchtags().items()]
-    branches.sort()
+    branches = util.sort([(tag in activebranches, repo.changelog.rev(node), tag)
+                          for tag, node in repo.branchtags().items()])
     branches.reverse()
 
     for isactive, node, tag in branches:
@@ -412,8 +413,9 b' def bundle(ui, repo, fname, dest=None, *'
 
     If no destination repository is specified the destination is
     assumed to have all the nodes specified by one or more --base
-    parameters.  To create a bundle containing all changesets, use
-    --all (or --base null).
+    parameters. To create a bundle containing all changesets, use
+    --all (or --base null). To change the compression method applied,
+    use the -t option (by default, bundles are compressed using bz2).
 
     The bundle file can then be transferred using conventional means and
     applied to another repository with the unbundle or pull command.
@@ -467,7 +469,14 b' def bundle(ui, repo, fname, dest=None, *'
         cg = repo.changegroupsubset(o, revs, 'bundle')
     else:
         cg = repo.changegroup(o, 'bundle')
-    changegroup.writebundle(cg, fname, "HG10BZ")
+
+    bundletype = opts.get('type', 'bzip2').lower()
+    btypes = {'none': 'HG10UN', 'bzip2': 'HG10BZ', 'gzip': 'HG10GZ'}
+    bundletype = btypes.get(bundletype)
+    if bundletype not in changegroup.bundletypes:
+        raise util.Abort(_('unknown bundle type specified with --type'))
+
+    changegroup.writebundle(cg, fname, bundletype)
 
 def cat(ui, repo, file1, *pats, **opts):
     """output the current or given revision of files
@@ -477,19 +486,19 b' def cat(ui, repo, file1, *pats, **opts):'
     or tip if no revision is checked out.
 
     Output may be to a file, in which case the name of the file is
-    given using a format string.  The formatting rules are the same as
+    given using a format string. The formatting rules are the same as
     for the export command, with the following additions:
 
     %s   basename of file being printed
     %d   dirname of file being printed, or '.' if in repo root
     %p   root-relative path name of file being printed
     """
-    ctx = repo.changectx(opts['rev'])
+    ctx = repo[opts['rev']]
     err = 1
-    for src, abs, rel, exact in cmdutil.walk(repo, (file1,) + pats, opts,
-                                             ctx.node()):
+    m = cmdutil.match(repo, (file1,) + pats, opts)
+    for abs in ctx.walk(m):
         fp = cmdutil.make_file(repo, opts['output'], ctx.node(), pathname=abs)
-        data = ctx.filectx(abs).data()
+        data = ctx[abs].data()
         if opts.get('decode'):
             data = repo.wwritedata(abs, data)
         fp.write(data)
@@ -509,20 +518,22 b' def clone(ui, source, dest=None, **opts)'
 
     For efficiency, hardlinks are used for cloning whenever the source
     and destination are on the same filesystem (note this applies only
-    to the repository data, not to the checked out files).  Some
+    to the repository data, not to the checked out files). Some
     filesystems, such as AFS, implement hardlinking incorrectly, but
-    do not report errors.  In these cases, use the --pull option to
+    do not report errors. In these cases, use the --pull option to
     avoid hardlinking.
 
-    You can safely clone repositories and checked out files using full
-    hardlinks with
+    In some cases, you can clone repositories and checked out files
+    using full hardlinks with
 
       $ cp -al REPO REPOCLONE
 
-    which is the fastest way to clone. However, the operation is not
-    atomic (making sure REPO is not modified during the operation is
-    up to you) and you have to make sure your editor breaks hardlinks
-    (Emacs and most Linux Kernel tools do so).
+    This is the fastest way to clone, but it is not always safe.  The
+    operation is not atomic (making sure REPO is not modified during
+    the operation is up to you) and you have to make sure your editor
+    breaks hardlinks (Emacs and most Linux Kernel tools do so).  Also,
+    this is not compatible with certain extensions that place their
+    metadata under the .hg directory, such as mq.
 
     If you use the -r option to clone up to a specific revision, no
     subsequent revisions will be present in the cloned repository.
@@ -561,9 +572,9 b' def commit(ui, repo, *pats, **opts):'
 
     See 'hg help dates' for a list of formats valid for -d/--date.
     """
-    def commitfunc(ui, repo, files, message, match, opts):
-        return repo.commit(files, message, opts['user'], opts['date'], match,
-                           force_editor=opts.get('force_editor'))
+    def commitfunc(ui, repo, message, match, opts):
+        return repo.commit(match.files(), message, opts['user'], opts['date'],
+                           match, force_editor=opts.get('force_editor'))
 
     node = cmdutil.commit(ui, repo, commitfunc, pats, opts)
     if not node:
@@ -582,12 +593,12 b' def commit(ui, repo, *pats, **opts):'
 def copy(ui, repo, *pats, **opts):
     """mark files as copied for the next commit
 
-    Mark dest as having copies of source files.  If dest is a
-    directory, copies are put in that directory.  If dest is a file,
+    Mark dest as having copies of source files. If dest is a
+    directory, copies are put in that directory. If dest is a file,
     there can only be one source.
 
     By default, this command copies the contents of files as they
-    stand in the working directory.  If invoked with --after, the
+    stand in the working directory. If invoked with --after, the
     operation is recorded, but no copying is performed.
 
     This command takes effect in the next commit. To undo a copy
@@ -634,35 +645,30 b" def debugcomplete(ui, cmd='', **opts):"
         ui.write("%s\n" % "\n".join(options))
         return
 
-    clist = cmdutil.findpossible(ui, cmd, table).keys()
-    clist.sort()
-    ui.write("%s\n" % "\n".join(clist))
+    ui.write("%s\n" % "\n".join(util.sort(cmdutil.findpossible(ui, cmd, table))))
 
 def debugfsinfo(ui, path = "."):
     file('.debugfsinfo', 'w').write('')
     ui.write('exec: %s\n' % (util.checkexec(path) and 'yes' or 'no'))
     ui.write('symlink: %s\n' % (util.checklink(path) and 'yes' or 'no'))
-    ui.write('case-sensitive: %s\n' % (util.checkfolding('.debugfsinfo')
+    ui.write('case-sensitive: %s\n' % (util.checkcase('.debugfsinfo')
                                 and 'yes' or 'no'))
     os.unlink('.debugfsinfo')
 
-def debugrebuildstate(ui, repo, rev=""):
+def debugrebuildstate(ui, repo, rev="tip"):
     """rebuild the dirstate as it would look like for the given revision"""
-    if rev == "":
-        rev = repo.changelog.tip()
-    ctx = repo.changectx(rev)
-    files = ctx.manifest()
+    ctx = repo[rev]
     wlock = repo.wlock()
     try:
-        repo.dirstate.rebuild(rev, files)
+        repo.dirstate.rebuild(ctx.node(), ctx.manifest())
     finally:
         del wlock
 
 def debugcheckstate(ui, repo):
     """validate the correctness of the current dirstate"""
     parent1, parent2 = repo.dirstate.parents()
-    m1 = repo.changectx(parent1).manifest()
-    m2 = repo.changectx(parent2).manifest()
+    m1 = repo[parent1].manifest()
+    m2 = repo[parent2].manifest()
     errors = 0
     for f in repo.dirstate:
         state = repo.dirstate[f]
@@ -729,11 +735,9 b' def debugsetparents(ui, repo, rev1, rev2'
 
 def debugstate(ui, repo, nodates=None):
     """show the contents of the current dirstate"""
-    k = repo.dirstate._map.items()
-    k.sort()
     timestr = ""
     showdate = not nodates
-    for file_, ent in k:
+    for file_, ent in util.sort(repo.dirstate._map.items()):
         if showdate:
             if ent[3] == -1:
                 # Pad or slice to locale representation
@@ -775,7 +779,7 b' def debugindex(ui, file_):'
     r = revlog.revlog(util.opener(os.getcwd(), audit=False), file_)
     ui.write("   rev    offset  length   base linkrev" +
              " nodeid       p1           p2\n")
-    for i in xrange(r.count()):
+    for i in r:
         node = r.node(i)
         try:
             pp = r.parents(node)
@@ -789,7 +793,7 b' def debugindexdot(ui, file_):'
     """dump an index DAG as a .dot file"""
     r = revlog.revlog(util.opener(os.getcwd(), audit=False), file_)
     ui.write("digraph G {\n")
-    for i in xrange(r.count()):
+    for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write("\t%d -> %d\n" % (r.rev(pp[0]), i))
@@ -912,26 +916,28 b' def debuginstall(ui):'
 def debugrename(ui, repo, file1, *pats, **opts):
     """dump rename information"""
 
-    ctx = repo.changectx(opts.get('rev', 'tip'))
-    for src, abs, rel, exact in cmdutil.walk(repo, (file1,) + pats, opts,
-                                             ctx.node()):
-        fctx = ctx.filectx(abs)
-        m = fctx.filelog().renamed(fctx.filenode())
-        if m:
-            ui.write(_("%s renamed from %s:%s\n") % (rel, m[0], hex(m[1])))
+    ctx = repo[opts.get('rev')]
+    m = cmdutil.match(repo, (file1,) + pats, opts)
+    for abs in ctx.walk(m):
+        fctx = ctx[abs]
+        o = fctx.filelog().renamed(fctx.filenode())
+        rel = m.rel(abs)
+        if o:
+            ui.write(_("%s renamed from %s:%s\n") % (rel, o[0], hex(o[1])))
         else:
             ui.write(_("%s not renamed\n") % rel)
 
 def debugwalk(ui, repo, *pats, **opts):
     """show how files match on given patterns"""
-    items = list(cmdutil.walk(repo, pats, opts))
+    m = cmdutil.match(repo, pats, opts)
+    items = list(repo.walk(m))
     if not items:
         return
-    fmt = '%%s  %%-%ds  %%-%ds  %%s' % (
-        max([len(abs) for (src, abs, rel, exact) in items]),
-        max([len(rel) for (src, abs, rel, exact) in items]))
-    for src, abs, rel, exact in items:
-        line = fmt % (src, abs, rel, exact and 'exact' or '')
+    fmt = 'f  %%-%ds  %%-%ds  %%s' % (
+        max([len(abs) for abs in items]),
+        max([len(m.rel(abs)) for abs in items]))
+    for abs in items:
+        line = fmt % (abs, m.rel(abs), m.exact(abs) and 'exact' or '')
         ui.write("%s\n" % line.rstrip())
 
 def diff(ui, repo, *pats, **opts):
@@ -957,10 +963,8 b' def diff(ui, repo, *pats, **opts):'
     """
     node1, node2 = cmdutil.revpair(repo, opts['rev'])
 
-    fns, matchfn, anypats = cmdutil.matchpats(repo, pats, opts)
-
-    patch.diff(repo, node1, node2, fns, match=matchfn,
-               opts=patch.diffopts(ui, opts))
+    m = cmdutil.match(repo, pats, opts)
+    patch.diff(repo, node1, node2, match=m, opts=patch.diffopts(ui, opts))
 
 def export(ui, repo, *changesets, **opts):
     """dump the header and diffs for one or more changesets
@@ -974,7 +978,7 b' def export(ui, repo, *changesets, **opts'
     as it will compare the merge changeset against its first parent only.
 
     Output may be to a file, in which case the name of the file is
-    given using a format string.  The formatting rules are as follows:
+    given using a format string. The formatting rules are as follows:
 
     %%   literal "%" character
     %H   changeset hash (40 bytes of hexadecimal)
@@ -1008,13 +1012,13 b' def grep(ui, repo, pattern, *pats, **opt'
 
     Search revisions of files for a regular expression.
 
-    This command behaves differently than Unix grep.  It only accepts
-    Python/Perl regexps.  It searches repository history, not the
-    working directory.  It always prints the revision number in which
+    This command behaves differently than Unix grep. It only accepts
+    Python/Perl regexps. It searches repository history, not the
+    working directory. It always prints the revision number in which
     a match appears.
 
     By default, grep only prints output for the first revision of a
-    file in which it finds a match.  To get it to print every revision
+    file in which it finds a match. To get it to print every revision
     that contains a change in match status ("-" for a match that
     becomes a non-match, or "+" for a non-match that becomes a match),
     use the --all flag.
@@ -1058,6 +1062,9 b' def grep(ui, repo, pattern, *pats, **opt'
             self.colstart = colstart
             self.colend = colend
 
+        def __hash__(self):
+            return hash((self.linenum, self.line))
+
         def __eq__(self, other):
             return self.line == other.line
 
@@ -1118,7 +1125,7 b' def grep(ui, repo, pattern, *pats, **opt'
 
     fstate = {}
     skip = {}
-    get = util.cachefunc(lambda r: repo.changectx(r).changeset())
+    get = util.cachefunc(lambda r: repo[r].changeset())
     changeiter, matchfn = cmdutil.walkchangerevs(ui, repo, pats, get, opts)
     found = False
     follow = opts.get('follow')
@@ -1126,7 +1133,7 b' def grep(ui, repo, pattern, *pats, **opt'
         if st == 'window':
             matches.clear()
         elif st == 'add':
-            ctx = repo.changectx(rev)
+            ctx = repo[rev]
             matches[rev] = {}
             for fn in fns:
                 if fn in skip:
@@ -1141,9 +1148,7 b' def grep(ui, repo, pattern, *pats, **opt'
                 except revlog.LookupError:
                     pass
         elif st == 'iter':
-            states = matches[rev].items()
-            states.sort()
-            for fn, m in states:
+            for fn, m in util.sort(matches[rev].items()):
                 copy = copies.get(rev, {}).get(fn)
                 if fn in skip:
                     if copy:
@@ -1161,9 +1166,7 b' def grep(ui, repo, pattern, *pats, **opt'
                     fstate[copy] = m
                 prev[fn] = rev
 
-    fstate = fstate.items()
-    fstate.sort()
-    for fn, state in fstate:
+    for fn, state in util.sort(fstate.items()):
         if fn in skip:
             continue
         if fn not in copies.get(prev[fn], {}):
@@ -1184,7 +1187,7 b' def heads(ui, repo, *branchrevs, **opts)'
     are the usual targets for update and merge operations.
 
     Branch heads are changesets that have a given branch tag, but have
-    no child changesets with that tag.  They are usually where
+    no child changesets with that tag. They are usually where
     development on the given branch takes place.
     """
     if opts['rev']:
@@ -1198,7 +1201,7 b' def heads(ui, repo, *branchrevs, **opts)'
         heads = []
         visitedset = util.set()
         for branchrev in branchrevs:
-            branch = repo.changectx(branchrev).branch()
+            branch = repo[branchrev].branch()
             if branch in visitedset:
                 continue
             visitedset.add(branch)
@@ -1250,7 +1253,14 b' def help_(ui, name=None, with_version=Fa'
         if with_version:
             version_(ui)
             ui.write('\n')
-        aliases, i = cmdutil.findcmd(ui, name, table)
+
+        try:
+            aliases, i = cmdutil.findcmd(ui, name, table)
+        except cmdutil.AmbiguousCommand, inst:
+            select = lambda c: c.lstrip('^').startswith(inst.args[0])
+            helplist(_('list of commands:\n\n'), select)
+            return
+
         # synopsis
         ui.write("%s\n" % i[2])
 
@@ -1296,8 +1306,7 b' def help_(ui, name=None, with_version=Fa'
             return
 
         ui.status(header)
-        fns = h.keys()
-        fns.sort()
+        fns = util.sort(h)
         m = max(map(len, fns))
         for f in fns:
             if ui.verbose:
@@ -1311,16 +1320,16 b' def help_(ui, name=None, with_version=Fa'
 
     def helptopic(name):
         v = None
-        for i in help.helptable:
+        for i, d in help.helptable:
             l = i.split('|')
             if name in l:
                 v = i
                 header = l[-1]
+                doc = d
         if not v:
             raise cmdutil.UnknownCommand(name)
 
         # description
-        doc = help.helptable[v]
         if not doc:
             doc = _("(No help text available)")
         if callable(doc):
@@ -1391,6 +1400,16 b' def help_(ui, name=None, with_version=Fa'
                                          and _(" (default: %s)") % default
                                          or "")))
 
+    if ui.verbose:
+        ui.write(_("\nspecial help topics:\n"))
+        topics = []
+        for i, d in help.helptable:
+            l = i.split('|')
+            topics.append((", ".join(l[:-1]), l[-1]))
+        topics_len = max([len(s[0]) for s in topics])
+        for t, desc in topics:
+            ui.write(" %-*s  %s\n" % (topics_len, t, desc))
+
     if opt_output:
         opts_len = max([len(line[0]) for line in opt_output if line[1]] or [0])
         for first, second in opt_output:
@@ -1433,7 +1452,7 b' def identify(ui, repo, source=None,'
                 "can't query remote revision number, branch, or tags")
         output = [hexfunc(srepo.lookup(rev))]
     elif not rev:
-        ctx = repo.workingctx()
+        ctx = repo[None]
         parents = ctx.parents()
         changed = False
         if default or id or num:
@@ -1445,7 +1464,7 b' def identify(ui, repo, source=None,'
             output.append("%s%s" % ('+'.join([str(p.rev()) for p in parents]),
                                     (changed) and "+" or ""))
     else:
-        ctx = repo.changectx(rev)
+        ctx = repo[rev]
         if default or id:
             output = [hexfunc(ctx.node())]
         if num:
@@ -1477,15 +1496,15 b' def import_(ui, repo, patch1, *patches, '
     If there are outstanding changes in the working directory, import
     will abort unless given the -f flag.
 
-    You can import a patch straight from a mail message.  Even patches
+    You can import a patch straight from a mail message. Even patches
     as attachments work (body part must be type text/plain or
-    text/x-patch to be used).  From and Subject headers of email
-    message are used as default committer and commit message.  All
+    text/x-patch to be used). From and Subject headers of email
+    message are used as default committer and commit message. All
     text/plain body parts before first diff are added to commit
     message.
 
     If the imported patch was generated by hg export, user and description
-    from patch override values from message headers and body.  Values
+    from patch override values from message headers and body. Values
     given on command line with -m and -u override these.
 
     If --exact is specified, import will set the working directory
@@ -1542,7 +1561,7 b' def import_(ui, repo, patch1, *patches, '
                     message = None
                 ui.debug(_('message:\n%s\n') % message)
 
-                wp = repo.workingctx().parents()
+                wp = repo.parents()
                 if opts.get('exact'):
                     if not nodeid or not p1:
                         raise util.Abort(_('not a mercurial patch'))
@@ -1654,7 +1673,7 b' def incoming(ui, repo, source="default",'
 def init(ui, dest=".", **opts):
     """create a new repository in the given directory
 
-    Initialize a new repository in the given directory.  If the given
+    Initialize a new repository in the given directory. If the given
     directory does not exist, it is created.
 
     If no directory is given, the current directory is used.
@@ -1672,7 +1691,7 b' def locate(ui, repo, *pats, **opts):'
     Print all files under Mercurial control whose names match the
     given patterns.
 
-    This command searches the entire repository by default.  To search
+    This command searches the entire repository by default. To search
     just the current directory and its subdirectories, use
     "--include .".
 
@@ -1685,24 +1704,18 b' def locate(ui, repo, *pats, **opts):'
     that contain white space as multiple filenames.
     """
     end = opts['print0'] and '\0' or '\n'
-    rev = opts['rev']
-    if rev:
-        node = repo.lookup(rev)
-    else:
-        node = None
+    rev = opts.get('rev') or None
 
     ret = 1
-    for src, abs, rel, exact in cmdutil.walk(repo, pats, opts, node=node,
-                                             badmatch=util.always,
-                                             default='relglob'):
-        if src == 'b':
-            continue
-        if not node and abs not in repo.dirstate:
+    m = cmdutil.match(repo, pats, opts, default='relglob')
+    m.bad = lambda x,y: False
+    for abs in repo[rev].walk(m):
+        if not rev and abs not in repo.dirstate:
             continue
         if opts['fullpath']:
             ui.write(os.path.join(repo.root, abs), end)
         else:
-            ui.write(((pats and rel) or abs), end)
+            ui.write(((pats and m.rel(abs)) or abs), end)
         ret = 0
 
     return ret
@@ -1714,7 +1727,7 b' def log(ui, repo, *pats, **opts):'
     project.
 
     File history is shown without following rename or copy history of
-    files.  Use -f/--follow with a file name to follow history across
+    files. Use -f/--follow with a file name to follow history across
     renames and copies. --follow without a file name will only show
     ancestors or descendants of the starting revision. --follow-first
     only follows the first parent of merge revisions.
@@ -1737,7 +1750,7 b' def log(ui, repo, *pats, **opts):'
 
     """
 
-    get = util.cachefunc(lambda r: repo.changectx(r).changeset())
+    get = util.cachefunc(lambda r: repo[r].changeset())
     changeiter, matchfn = cmdutil.walkchangerevs(ui, repo, pats, get, opts)
 
     limit = cmdutil.loglimit(opts)
@@ -1746,7 +1759,7 b' def log(ui, repo, *pats, **opts):'
     if opts['copies'] and opts['rev']:
         endrev = max(cmdutil.revrange(repo, opts['rev'])) + 1
     else:
-        endrev = repo.changelog.count()
+        endrev = len(repo)
     rcache = {}
     ncache = {}
     def getrenamed(fn, rev):
@@ -1758,7 +1771,7 b' def log(ui, repo, *pats, **opts):'
             rcache[fn] = {}
             ncache[fn] = {}
             fl = repo.file(fn)
-            for i in xrange(fl.count()):
+            for i in fl:
                 node = fl.node(i)
                 lr = fl.linkrev(node)
                 renamed = fl.renamed(node)
@@ -1774,7 +1787,7 b' def log(ui, repo, *pats, **opts):'
         # filectx logic.
 
         try:
-            return repo.changectx(rev).filectx(fn).renamed()
+            return repo[rev][fn].renamed()
         except revlog.LookupError:
             pass
         return None
@@ -1850,17 +1863,13 b' def manifest(ui, repo, node=None, rev=No'
     if not node:
         node = rev
 
-    m = repo.changectx(node).manifest()
-    files = m.keys()
-    files.sort()
-
-    for f in files:
+    decor = {'l':'644 @ ', 'x':'755 * ', '':'644   '}
+    ctx = repo[node]
+    for f in ctx:
         if ui.debugflag:
-            ui.write("%40s " % hex(m[f]))
+            ui.write("%40s " % hex(ctx.manifest()[f]))
         if ui.verbose:
-            type = m.execf(f) and "*" or m.linkf(f) and "@" or " "
-            perm = m.execf(f) and "755" or "644"
-            ui.write("%3s %1s " % (perm, type))
+            ui.write(decor[ctx.flags(f)])
         ui.write("%s\n" % f)
 
 def merge(ui, repo, node=None, force=None, rev=None):
@@ -1872,8 +1881,8 b' def merge(ui, repo, node=None, force=Non'
     performed before any further updates are allowed.
 
     If no revision is specified, the working directory's parent is a
-    head revision, and the repository contains exactly one other head,
-    the other head is merged with by default.  Otherwise, an explicit
+    head revision, and the current branch contains exactly one other head,
+    the other head is merged with by default. Otherwise, an explicit
     revision to merge with must be provided.
     """
 
@@ -1883,22 +1892,28 b' def merge(ui, repo, node=None, force=Non'
         node = rev
 
     if not node:
-        heads = repo.heads()
-        if len(heads) > 2:
-            raise util.Abort(_('repo has %d heads - '
-                               'please merge with an explicit rev') %
-                             len(heads))
+        branch = repo.changectx(None).branch()
+        bheads = repo.branchheads(branch)
+        if len(bheads) > 2:
+            raise util.Abort(_("branch '%s' has %d heads - "
+                               "please merge with an explicit rev") %
+                             (branch, len(bheads)))
+
         parent = repo.dirstate.parents()[0]
-        if len(heads) == 1:
+        if len(bheads) == 1:
+            if len(repo.heads()) > 1:
+                raise util.Abort(_("branch '%s' has one head - "
+                                   "please merge with an explicit rev") %
+                                 branch)
             msg = _('there is nothing to merge')
-            if parent != repo.lookup(repo.workingctx().branch()):
+            if parent != repo.lookup(repo[None].branch()):
                 msg = _('%s - use "hg update" instead') % msg
             raise util.Abort(msg)
 
-        if parent not in heads:
+        if parent not in bheads:
             raise util.Abort(_('working dir not at a head rev - '
                                'use "hg update" or merge with an explicit rev'))
-        node = parent == heads[0] and heads[-1] or heads[0]
+        node = parent == bheads[0] and bheads[-1] or bheads[0]
     return hg.merge(repo, node, force=force)
 
 def outgoing(ui, repo, dest=None, **opts):
@@ -1948,15 +1963,15 b' def parents(ui, repo, file_=None, **opts'
     """
     rev = opts.get('rev')
     if rev:
-        ctx = repo.changectx(rev)
+        ctx = repo[rev]
     else:
-        ctx = repo.workingctx()
+        ctx = repo[None]
 
     if file_:
-        files, match, anypats = cmdutil.matchpats(repo, (file_,), opts)
-        if anypats or len(files) != 1:
+        m = cmdutil.match(repo, (file_,), opts)
+        if m.anypats() or len(m.files()) != 1:
             raise util.Abort(_('can only specify an explicit file name'))
-        file_ = files[0]
+        file_ = m.files()[0]
         filenodes = []
         for cp in ctx.parents():
             if not cp:
@@ -1984,7 +1999,7 b' def paths(ui, repo, search=None):'
     definition of available names.
 
     Path names are defined in the [paths] section of /etc/mercurial/hgrc
-    and $HOME/.hgrc.  If run inside a repository, .hg/hgrc is used, too.
+    and $HOME/.hgrc. If run inside a repository, .hg/hgrc is used, too.
     """
     if search:
         for name, path in ui.configitems("paths"):
@@ -2022,9 +2037,9 b' def pull(ui, repo, source="default", **o'
     Valid URLs are of the form:
 
       local/filesystem/path (or file://local/filesystem/path)
-      http://[user@]host[:port]/[path]
-      https://[user@]host[:port]/[path]
-      ssh://[user@]host[:port]/[path]
+      http://[user[:pass]@]host[:port]/[path]
+      https://[user[:pass]@]host[:port]/[path]
+      ssh://[user[:pass]@]host[:port]/[path]
       static-http://host[:port]/[path]
 
     Paths in the local filesystem can either point to Mercurial
@@ -2084,9 +2099,9 b' def push(ui, repo, dest=None, **opts):'
     Valid URLs are of the form:
 
       local/filesystem/path (or file://local/filesystem/path)
-      ssh://[user@]host[:port]/[path]
-      http://[user@]host[:port]/[path]
-      https://[user@]host[:port]/[path]
+      ssh://[user[:pass]@]host[:port]/[path]
+      http://[user[:pass]@]host[:port]/[path]
+      https://[user[:pass]@]host[:port]/[path]
 
     An optional identifier after # indicates a particular branch, tag,
     or changeset to push. If -r is used, the named changeset and all its
@@ -2126,7 +2141,7 b' def rawcommit(ui, repo, *pats, **opts):'
 
     message = cmdutil.logmessage(opts)
 
-    files, match, anypats = cmdutil.matchpats(repo, pats, opts)
+    files = cmdutil.match(repo, pats, opts).files()
     if opts['files']:
         files += open(opts['files']).read().splitlines()
 
@@ -2178,47 +2193,28 b' def remove(ui, repo, *pats, **opts):'
     if not pats and not after:
         raise util.Abort(_('no files specified'))
 
-    files, matchfn, anypats = cmdutil.matchpats(repo, pats, opts)
-    mardu = map(dict.fromkeys, repo.status(files=files, match=matchfn))[:5]
-    modified, added, removed, deleted, unknown = mardu
-
-    remove, forget = [], []
-    for src, abs, rel, exact in cmdutil.walk(repo, pats, opts):
-
-        reason = None
-        if abs in removed or abs in unknown:
-            continue
-
-        # last column
-        elif abs in deleted:
-            remove.append(abs)
-
-        # rest of the third row
-        elif after and not force:
-            reason = _('still exists (use -f to force removal)')
-
-        # rest of the first column
-        elif abs in added:
-            if not force:
-                reason = _('has been marked for add (use -f to force removal)')
-            else:
-                forget.append(abs)
-
-        # rest of the third column
-        elif abs in modified:
-            if not force:
-                reason = _('is modified (use -f to force removal)')
-            else:
-                remove.append(abs)
-
-        # rest of the second column
-        elif not reason:
-            remove.append(abs)
-
-        if reason:
-            ui.warn(_('not removing %s: file %s\n') % (rel, reason))
-        elif ui.verbose or not exact:
-            ui.status(_('removing %s\n') % rel)
+    m = cmdutil.match(repo, pats, opts)
+    s = repo.status(match=m, clean=True)
+    modified, added, deleted, clean = s[0], s[1], s[3], s[6]
+
+    def warn(files, reason):
+        for f in files:
+            ui.warn(_('not removing %s: file %s (use -f to force removal)\n')
+                    % (m.rel(f), reason))
+
+    if force:
+        remove, forget = modified + deleted + clean, added
+    elif after:
+        remove, forget = deleted, []
+        warn(modified + added + clean, _('still exists'))
+    else:
+        remove, forget = deleted + clean, []
+        warn(modified, _('is modified'))
+        warn(added, _('has been marked for add'))
+
+    for f in util.sort(remove + forget):
+        if ui.verbose or not m.exact(f):
+            ui.status(_('removing %s\n') % m.rel(f))
 
     repo.forget(forget)
     repo.remove(remove, unlink=not after)
@@ -2226,12 +2222,12 b' def remove(ui, repo, *pats, **opts):'
 def rename(ui, repo, *pats, **opts):
     """rename files; equivalent of copy + remove
 
-    Mark dest as copies of sources; mark sources for deletion.  If
-    dest is a directory, copies are put in that directory.  If dest is
+    Mark dest as copies of sources; mark sources for deletion. If
+    dest is a directory, copies are put in that directory. If dest is
     a file, there can only be one source.
 
     By default, this command copies the contents of files as they
-    stand in the working directory.  If invoked with --after, the
+    stand in the working directory. If invoked with --after, the
     operation is recorded, but no copying is performed.
 
     This command takes effect in the next commit. To undo a rename
@@ -2243,6 +2239,39 b' def rename(ui, repo, *pats, **opts):'
     finally:
         del wlock
 
+def resolve(ui, repo, *pats, **opts):
+    """resolve file merges from a branch merge or update
+
+    This command will attempt to resolve unresolved merges from the
+    last update or merge command. This will use the local file
+    revision preserved at the last update or merge to cleanly retry
+    the file merge attempt. With no file or options specified, this
+    command will attempt to resolve all unresolved files.
+
+    The codes used to show the status of files are:
+    U = unresolved
+    R = resolved
+    """
+
+    if len([x for x in opts if opts[x]]) > 1:
+        raise util.Abort(_("too many options specified"))
+
+    ms = merge_.mergestate(repo)
+    m = cmdutil.match(repo, pats, opts)
+
+    for f in ms:
+        if m(f):
+            if opts.get("list"):
+                ui.write("%s %s\n" % (ms[f].upper(), f))
+            elif opts.get("mark"):
+                ms.mark(f, "r")
+            elif opts.get("unmark"):
+                ms.mark(f, "u")
+            else:
+                wctx = repo[None]
+                mctx = wctx.parents()[-1]
+                ms.resolve(f, wctx, mctx)
+
 def revert(ui, repo, *pats, **opts):
     """restore individual files or dirs to an earlier state
 
@@ -2261,13 +2290,13 b' def revert(ui, repo, *pats, **opts):'
     back" some or all of an earlier change.
     See 'hg help dates' for a list of formats valid for -d/--date.
 
-    Revert modifies the working directory.  It does not commit any
-    changes, or change the parent of the working directory.  If you
+    Revert modifies the working directory. It does not commit any
+    changes, or change the parent of the working directory. If you
     revert to a revision other than the parent of the working
     directory, the reverted files will thus appear modified
     afterwards.
 
-    If a file has been deleted, it is restored.  If the executable
+    If a file has been deleted, it is restored. If the executable
     mode of a file was changed, it is reset.
 
     If names are given, all files matching the names are reverted.
@@ -2290,7 +2319,7 b' def revert(ui, repo, *pats, **opts):'
     if not opts['rev'] and p2 != nullid:
         raise util.Abort(_('uncommitted merge - please provide a '
                            'specific revision'))
-    ctx = repo.changectx(opts['rev'])
+    ctx = repo[opts['rev']]
     node = ctx.node()
     mf = ctx.manifest()
     if node == parent:
@@ -2308,30 +2337,32 b' def revert(ui, repo, *pats, **opts):'
     try:
         # walk dirstate.
         files = []
-        for src, abs, rel, exact in cmdutil.walk(repo, pats, opts,
-                                                 badmatch=mf.has_key):
-            names[abs] = (rel, exact)
-            if src != 'b':
-                files.append(abs)
+
+        m = cmdutil.match(repo, pats, opts)
+        m.bad = lambda x,y: False
+        for abs in repo.walk(m):
+            names[abs] = m.rel(abs), m.exact(abs)
 
         # walk target manifest.
 
-        def badmatch(path):
+        def badfn(path, msg):
             if path in names:
-                return True
+                return False
             path_ = path + '/'
             for f in names:
                 if f.startswith(path_):
-                    return True
+                    return False
+            repo.ui.warn("%s: %s\n" % (m.rel(path), msg))
             return False
 
-        for src, abs, rel, exact in cmdutil.walk(repo, pats, opts, node=node,
-                                                 badmatch=badmatch):
-            if abs in names or src == 'b':
-                continue
-            names[abs] = (rel, exact)
-
-        changes = repo.status(files=files, match=names.has_key)[:4]
+        m = cmdutil.match(repo, pats, opts)
+        m.bad = badfn
+        for abs in repo[node].walk(m):
+            if abs not in names:
+                names[abs] = m.rel(abs), m.exact(abs)
+
+        m = cmdutil.matchfiles(repo, names)
+        changes = repo.status(match=m)[:4]
         modified, added, removed, deleted = map(dict.fromkeys, changes)
 
         # if f is a rename, also revert the source
@@ -2365,10 +2396,7 b' def revert(ui, repo, *pats, **opts):'
             (deleted, revert, remove, False, False),
             )
 
-        entries = names.items()
-        entries.sort()
-
-        for abs, (rel, exact) in entries:
+        for abs, (rel, exact) in util.sort(names.items()):
             mfentry = mf.get(abs)
             target = repo.wjoin(abs)
             def handle(xlist, dobackup):
@@ -2406,7 +2434,7 b' def revert(ui, repo, *pats, **opts):'
                 if pmf is None:
                     # only need parent manifest in this unlikely case,
                     # so do not read by default
-                    pmf = repo.changectx(parent).manifest()
+                    pmf = repo[parent].manifest()
                 if abs in pmf:
                     if mfentry:
                         # if version of file is same in parent and target
@@ -2420,7 +2448,7 b' def revert(ui, repo, *pats, **opts):'
         if not opts.get('dry_run'):
             def checkout(f):
                 fc = ctx[f]
-                repo.wwrite(f, fc.data(), fc.fileflags())
+                repo.wwrite(f, fc.data(), fc.flags())
 
             audit_path = util.path_auditor(repo.root)
             for f in remove[0]:
@@ -2503,7 +2531,7 b' def serve(ui, repo, **opts):'
     Start a local HTTP repository browser and pull server.
 
     By default, the server logs accesses to stdout and errors to
-    stderr.  Use the "-A" and "-E" options to log to files.
+    stderr. Use the "-A" and "-E" options to log to files.
     """
 
     if opts["stdio"]:
@@ -2542,8 +2570,17 b' def serve(ui, repo, **opts):'
             if port == ':80':
                 port = ''
 
-            ui.status(_('listening at http://%s%s/%s (%s:%d)\n') %
-                      (self.httpd.fqaddr, port, prefix, self.httpd.addr, self.httpd.port))
+            bindaddr = self.httpd.addr
+            if bindaddr == '0.0.0.0':
+                bindaddr = '*'
+            elif ':' in bindaddr: # IPv6
+                bindaddr = '[%s]' % bindaddr
+
+            fqaddr = self.httpd.fqaddr
+            if ':' in fqaddr:
+                fqaddr = '[%s]' % fqaddr
+            ui.status(_('listening at http://%s%s/%s (bound to %s:%d)\n') %
+                      (fqaddr, port, prefix, bindaddr, self.httpd.port))
 
         def run(self):
             self.httpd.serve_forever()
@@ -2555,10 +2592,10 b' def serve(ui, repo, **opts):'
 def status(ui, repo, *pats, **opts):
     """show changed files in the working directory
 
-    Show status of files in the repository.  If names are given, only
-    files that match are shown.  Files that are clean or ignored or
+    Show status of files in the repository. If names are given, only
+    files that match are shown. Files that are clean or ignored or
     source of a copy/move operation, are not listed unless -c (clean),
-    -i (ignored), -C (copies) or -A is given.  Unless options described
+    -i (ignored), -C (copies) or -A is given. Unless options described
     with "show only ..." are given, the options -mardu are used.
 
     Option -q/--quiet hides untracked (unknown and ignored) files
@@ -2583,65 +2620,45 b' def status(ui, repo, *pats, **opts):'
       = the previous added file was copied from here
     """
 
-    all = opts['all']
     node1, node2 = cmdutil.revpair(repo, opts.get('rev'))
-
-    files, matchfn, anypats = cmdutil.matchpats(repo, pats, opts)
     cwd = (pats and repo.getcwd()) or ''
-    modified, added, removed, deleted, unknown, ignored, clean = [
-        n for n in repo.status(node1=node1, node2=node2, files=files,
-                               match=matchfn,
-                               list_ignored=opts['ignored']
-                                            or all and not ui.quiet,
-                               list_clean=opts['clean'] or all,
-                               list_unknown=opts['unknown']
-                                            or not (ui.quiet or
-                                                    opts['modified'] or
-                                                    opts['added'] or
-                                                    opts['removed'] or
-                                                    opts['deleted'] or
-                                                    opts['ignored']))]
-
-    changetypes = (('modified', 'M', modified),
-                   ('added', 'A', added),
-                   ('removed', 'R', removed),
-                   ('deleted', '!', deleted),
-                   ('unknown', '?', unknown),
-                   ('ignored', 'I', ignored))
-
-    explicit_changetypes = changetypes + (('clean', 'C', clean),)
-
+    end = opts['print0'] and '\0' or '\n'
     copy = {}
-    showcopy = {}
-    if ((all or opts.get('copies')) and not opts.get('no_status')):
-        if opts.get('rev') == []:
-            # fast path, more correct with merge parents
-            showcopy = copy = repo.dirstate.copies().copy()
-        else:
-            ctxn = repo.changectx(nullid)
-            ctx1 = repo.changectx(node1)
-            ctx2 = repo.changectx(node2)
-            if node2 is None:
-                ctx2 = repo.workingctx()
-            copy, diverge = copies.copies(repo, ctx1, ctx2, ctxn)
-            for k, v in copy.items():
+    states = 'modified added removed deleted unknown ignored clean'.split()
+    show = [k for k in states if opts[k]]
+    if opts['all']:
+        show += ui.quiet and (states[:4] + ['clean']) or states
+    if not show:
+        show = ui.quiet and states[:4] or states[:5]
+
+    stat = repo.status(node1, node2, cmdutil.match(repo, pats, opts),
+                       'ignored' in show, 'clean' in show, 'unknown' in show)
+    changestates = zip(states, 'MAR!?IC', stat)
+
+    if (opts['all'] or opts['copies']) and not opts['no_status']:
+        ctxn = repo[nullid]
+        ctx1 = repo[node1]
+        ctx2 = repo[node2]
+        added = stat[1]
+        if node2 is None:
+            added = stat[0] + stat[1] # merged?
+
+        for k, v in copies.copies(repo, ctx1, ctx2, ctxn)[0].items():
+            if k in added:
+                copy[k] = v
+            elif v in added:
                 copy[v] = k
 
-    end = opts['print0'] and '\0' or '\n'
-
-    for opt, char, changes in ([ct for ct in explicit_changetypes
-                                if all or opts[ct[0]]]
-                               or changetypes):
-
-        if opts['no_status']:
-            format = "%%s%s" % end
-        else:
+    for state, char, files in changestates:
+        if state in show:
             format = "%s %%s%s" % (char, end)
-
-        for f in changes:
-            ui.write(format % repo.pathto(f, cwd))
-            if f in copy and (f in added or f in showcopy):
-                ui.write('  %s%s' % (repo.pathto(copy[f], cwd), end))
+            if opts['no_status']:
+                format = "%%s%s" % end
+
+            for f in files:
+                ui.write(format % repo.pathto(f, cwd))
+                if f in copy:
+                    ui.write('  %s%s' % (repo.pathto(copy[f], cwd), end))
 
 def tag(ui, repo, name1, *names, **opts):
     """add one or more tags for the current or given revision
@@ -2658,13 +2675,13 b' def tag(ui, repo, name1, *names, **opts)'
     To facilitate version control, distribution, and merging of tags,
     they are stored as a file named ".hgtags" which is managed
     similarly to other project files and can be hand-edited if
-    necessary.  The file '.hg/localtags' is used for local tags (not
+    necessary. The file '.hg/localtags' is used for local tags (not
     shared among repositories).
 
     See 'hg help dates' for a list of formats valid for -d/--date.
     """
 
-    rev_ = None
+    rev_ = "."
     names = (name1,) + names
     if len(names) != len(dict.fromkeys(names)):
         raise util.Abort(_('tag names must be unique'))
@@ -2695,7 +2712,7 b' def tag(ui, repo, name1, *names, **opts)'
     if not rev_ and repo.dirstate.parents()[1] != nullid:
         raise util.Abort(_('uncommitted merge - please provide a '
                            'specific revision'))
-    r = repo.changectx(rev_).node()
+    r = repo[rev_].node()
 
     if not message:
         message = (_('Added tag %s for changeset %s') %
@@ -2752,7 +2769,7 b' def tip(ui, repo, **opts):'
     that repository becomes the current tip. The "tip" tag is special
     and cannot be renamed or assigned to a different changeset.
     """
-    cmdutil.show_changeset(ui, repo, opts).show(nullrev+repo.changelog.count())
+    cmdutil.show_changeset(ui, repo, opts).show(len(repo) - 1)
 
 def unbundle(ui, repo, fname1, *fnames, **opts):
     """apply one or more changegroup files
@@ -2780,8 +2797,8 b' def unbundle(ui, repo, fname1, *fnames, '
 def update(ui, repo, node=None, rev=None, clean=False, date=None):
     """update working directory
 
-    Update the working directory to the specified revision, or the
-    tip of the current branch if none is specified.
+    Update the repository's working directory to the specified revision,
+    or the tip of the current branch if none is specified.
 
     If the requested revision is a descendant of the working
     directory, any outstanding changes in the working directory will
@@ -2892,6 +2909,23 b' logopts = ['
     ('M', 'no-merges', None, _('do not show merges')),
 ] + templateopts
 
+diffopts = [
+    ('a', 'text', None, _('treat all files as text')),
+    ('g', 'git', None, _('use git extended diff format')),
+    ('', 'nodates', None, _("don't include dates in diff headers"))
+]
+
+diffopts2 = [
+    ('p', 'show-function', None, _('show which function each change is in')),
+    ('w', 'ignore-all-space', None,
+     _('ignore white space when comparing lines')),
+    ('b', 'ignore-space-change', None,
+     _('ignore changes in the amount of white space')),
+    ('B', 'ignore-blank-lines', None,
+     _('ignore changes whose lines are all blank')),
+    ('U', 'unified', '', _('number of lines of context to show'))
+]
+
 table = {
     "^add": (add, walkopts + dryrunopts, _('hg add [OPTION]... [FILE]...')),
     "addremove":
@@ -2955,8 +2989,8 b' table = {'
            _('a changeset up to which you would like to bundle')),
           ('', 'base', [],
            _('a base changeset to specify instead of a destination')),
-          ('a', 'all', None,
-           _('bundle all changesets in the repository')),
+          ('a', 'all', None, _('bundle all changesets in the repository')),
+          ('t', 'type', 'bzip2', _('bundle compression type to use')),
          ] + remoteopts,
          _('hg bundle [-f] [-a] [-r REV]... [--base REV]... FILE [DEST]')),
     "cat":
@@ -3031,29 +3065,14 b' table = {'
     "debugwalk": (debugwalk, walkopts, _('hg debugwalk [OPTION]... [FILE]...')),
     "^diff":
         (diff,
-         [('r', 'rev', [], _('revision')),
-          ('a', 'text', None, _('treat all files as text')),
-          ('p', 'show-function', None,
-           _('show which function each change is in')),
-          ('g', 'git', None, _('use git extended diff format')),
-          ('', 'nodates', None, _("don't include dates in diff headers")),
-          ('w', 'ignore-all-space', None,
-           _('ignore white space when comparing lines')),
-          ('b', 'ignore-space-change', None,
-           _('ignore changes in the amount of white space')),
-          ('B', 'ignore-blank-lines', None,
-           _('ignore changes whose lines are all blank')),
-          ('U', 'unified', '',
-           _('number of lines of context to show'))
-         ] + walkopts,
+         [('r', 'rev', [], _('revision'))
+         ] + diffopts + diffopts2 + walkopts,
          _('hg diff [OPTION]... [-r REV1 [-r REV2]] [FILE]...')),
     "^export":
         (export,
          [('o', 'output', '', _('print output to file with formatted name')),
-          ('a', 'text', None, _('treat all files as text')),
-          ('g', 'git', None, _('use git extended diff format')),
-          ('', 'nodates', None, _("don't include dates in diff headers")),
-          ('', 'switch-parent', None, _('diff against the second parent'))],
+          ('', 'switch-parent', None, _('diff against the second parent'))
+          ] + diffopts,
          _('hg export [OPTION]... [-o OUTFILESPEC] REV...')),
     "grep":
         (grep,
@@ -3197,6 +3216,12 b' table = {'
            _('forcibly copy over an existing managed file')),
          ] + walkopts + dryrunopts,
          _('hg rename [OPTION]... SOURCE... DEST')),
+    "resolve":
+        (resolve,
+         [('l', 'list', None, _('list state of files needing merge')),
+          ('m', 'mark', None, _('mark files as resolved')),
+          ('u', 'unmark', None, _('unmark files as resolved'))],
+          ('hg resolve [OPTION] [FILES...]')),
     "revert":
         (revert,
          [('a', 'all', None, _('revert all changes when no arguments given')),
@@ -3271,7 +3296,7 b' table = {'
          _('hg unbundle [-u] FILE...')),
     "^update|up|checkout|co":
         (update,
-         [('C', 'clean', None, _('overwrite locally modified files')),
+         [('C', 'clean', None, _('overwrite locally modified files (no backup)')),
           ('d', 'date', '', _('tipmost revision matching date')),
           ('r', 'rev', '', _('revision'))],
          _('hg update [-C] [-d DATE] [[-r] REV]')),

mercurial/context.py

@@ -5,35 +5,36 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-from node import nullid, nullrev, short
+from node import nullid, nullrev, short, hex
 from i18n import _
 import ancestor, bdiff, revlog, util, os, errno
 
 class changectx(object):
     """A changecontext object makes access to data related to a particular
     changeset convenient."""
-    def __init__(self, repo, changeid=None):
+    def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
+        if changeid == '':
+            changeid = '.'
         self._repo = repo
-
-        if not changeid and changeid != 0:
-            p1, p2 = self._repo.dirstate.parents()
-            self._rev = self._repo.changelog.rev(p1)
-            if self._rev == -1:
-                changeid = 'tip'
-            else:
-                self._node = p1
-                return
-
         self._node = self._repo.lookup(changeid)
         self._rev = self._repo.changelog.rev(self._node)
 
     def __str__(self):
         return short(self.node())
 
+    def __int__(self):
+        return self.rev()
+
     def __repr__(self):
         return "<changectx %s>" % str(self)
 
+    def __hash__(self):
+        try:
+            return hash(self._rev)
+        except AttributeError:
+            return id(self)
+
     def __eq__(self, other):
         try:
             return self._rev == other._rev
@@ -57,6 +58,12 b' class changectx(object):'
             md = self._repo.manifest.readdelta(self._changeset[0])
             self._manifestdelta = md
             return self._manifestdelta
+        elif name == '_parents':
+            p = self._repo.changelog.parents(self._node)
+            if p[1] == nullid:
+                p = p[:-1]
+            self._parents = [changectx(self._repo, x) for x in p]
+            return self._parents
         else:
             raise AttributeError, name
 
@@ -67,9 +74,7 b' class changectx(object):'
         return self.filectx(key)
 
     def __iter__(self):
-        a = self._manifest.keys()
-        a.sort()
-        for f in a:
+        for f in util.sort(self._manifest):
             yield f
 
     def changeset(self): return self._changeset
@@ -77,6 +82,7 b' class changectx(object):'
 
     def rev(self): return self._rev
     def node(self): return self._node
+    def hex(self): return hex(self._node)
     def user(self): return self._changeset[1]
     def date(self): return self._changeset[2]
     def files(self): return self._changeset[3]
@@ -87,14 +93,21 b' class changectx(object):'
 
     def parents(self):
         """return contexts for each parent changeset"""
-        p = self._repo.changelog.parents(self._node)
-        return [changectx(self._repo, x) for x in p]
+        return self._parents
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
+    def ancestors(self):
+        for a in self._repo.changelog.ancestors(self._rev):
+            yield changectx(self._repo, a)
+
+    def descendants(self):
+        for d in self._repo.changelog.descendants(self._rev):
+            yield changectx(self._repo, d)
+
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
@@ -115,7 +128,7 b' class changectx(object):'
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
-    def fileflags(self, path):
+    def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except revlog.LookupError:
@@ -128,15 +141,6 b' class changectx(object):'
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
-    def filectxs(self):
-        """generate a file context for each file in this changeset's
-           manifest"""
-        mf = self.manifest()
-        m = mf.keys()
-        m.sort()
-        for f in m:
-            yield self.filectx(f, fileid=mf[f])
-
     def ancestor(self, c2):
         """
         return the ancestor context of self and c2
@@ -144,6 +148,23 b' class changectx(object):'
         n = self._repo.changelog.ancestor(self._node, c2._node)
         return changectx(self._repo, n)
 
+    def walk(self, match):
+        fdict = dict.fromkeys(match.files())
+        # for dirstate.walk, files=['.'] means "walk the whole tree".
+        # follow that here, too
+        fdict.pop('.', None)
+        for fn in self:
+            for ffn in fdict:
+                # match if the file is the exact name or a directory
+                if ffn == fn or fn.startswith("%s/" % ffn):
+                    del fdict[ffn]
+                    break
+            if match(fn):
+                yield fn
+        for fn in util.sort(fdict):
+            if match.bad(fn, 'No such file in rev ' + str(self)) and match(fn):
+                yield fn
+
 class filectx(object):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
@@ -210,6 +231,12 b' class filectx(object):'
     def __repr__(self):
         return "<filectx %s>" % str(self)
 
+    def __hash__(self):
+        try:
+            return hash((self._path, self._fileid))
+        except AttributeError:
+            return id(self)
+
     def __eq__(self, other):
         try:
             return (self._path == other._path
@@ -228,9 +255,7 b' class filectx(object):'
 
     def filerev(self): return self._filerev
     def filenode(self): return self._filenode
-    def fileflags(self): return self._changectx.fileflags(self._path)
-    def isexec(self): return 'x' in self.fileflags()
-    def islink(self): return 'l' in self.fileflags()
+    def flags(self): return self._changectx.flags(self._path)
     def filelog(self): return self._filelog
 
     def rev(self):
@@ -376,12 +401,11 b' class filectx(object):'
         # sort by revision (per file) which is a topological order
         visit = []
         for f in files:
-            fn = [(n.rev(), n) for n in needed.keys() if n._path == f]
+            fn = [(n.rev(), n) for n in needed if n._path == f]
             visit.extend(fn)
-        visit.sort()
+
         hist = {}
-
-        for r, f in visit:
+        for r, f in util.sort(visit):
             curr = decorate(f.data(), f)
             for p in parents(f):
                 if p != nullid:
@@ -432,11 +456,41 b' class filectx(object):'
 
 class workingctx(changectx):
     """A workingctx object makes access to data related to
-    the current working directory convenient."""
-    def __init__(self, repo):
+    the current working directory convenient.
+    parents - a pair of parent nodeids, or None to use the dirstate.
+    date - any valid date string or (unixtime, offset), or None.
+    user - username string, or None.
+    extra - a dictionary of extra values, or None.
+    changes - a list of file lists as returned by localrepo.status()
+               or None to use the repository status.
+    """
+    def __init__(self, repo, parents=None, text="", user=None, date=None,
+                 extra=None, changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
+        self._text = text
+        if date:
+            self._date = util.parsedate(date)
+        if user:
+            self._user = user
+        if parents:
+            self._parents = [changectx(self._repo, p) for p in parents]
+        if changes:
+            self._status = list(changes)
+
+        self._extra = {}
+        if extra:
+            self._extra = extra.copy()
+        if 'branch' not in self._extra:
+            branch = self._repo.dirstate.branch()
+            try:
+                branch = branch.decode('UTF-8').encode('UTF-8')
+            except UnicodeDecodeError:
+                raise util.Abort(_('branch name not in UTF-8!'))
+            self._extra['branch'] = branch
+        if self._extra['branch'] == '':
+            self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
@@ -444,16 +498,28 b' class workingctx(changectx):'
     def __nonzero__(self):
         return True
 
+    def __contains__(self, key):
+        return self._dirstate[key] not in "?r"
+
     def __getattr__(self, name):
-        if name == '_parents':
-            self._parents = self._repo.parents()
-            return self._parents
         if name == '_status':
-            self._status = self._repo.status()
+            self._status = self._repo.status(unknown=True)
             return self._status
+        elif name == '_user':
+            self._user = self._repo.ui.username()
+            return self._user
+        elif name == '_date':
+            self._date = util.makedate()
+            return self._date
         if name == '_manifest':
             self._buildmanifest()
             return self._manifest
+        elif name == '_parents':
+            p = self._repo.dirstate.parents()
+            if p[1] == nullid:
+                p = p[:-1]
+            self._parents = [changectx(self._repo, x) for x in p]
+            return self._parents
         else:
             raise AttributeError, name
 
@@ -462,16 +528,14 b' class workingctx(changectx):'
 
         man = self._parents[0].manifest().copy()
         copied = self._repo.dirstate.copies()
-        is_exec = util.execfunc(self._repo.root,
-                                lambda p: man.execf(copied.get(p,p)))
-        is_link = util.linkfunc(self._repo.root,
-                                lambda p: man.linkf(copied.get(p,p)))
+        cf = lambda x: man.flags(copied.get(x, x))
+        ff = self._repo.dirstate.flagfunc(cf)
         modified, added, removed, deleted, unknown = self._status[:5]
         for i, l in (("a", added), ("m", modified), ("u", unknown)):
             for f in l:
                 man[f] = man.get(copied.get(f, f), nullid) + i
                 try:
-                    man.set(f, is_exec(f), is_link(f))
+                    man.set(f, ff(f))
                 except OSError:
                     pass
 
@@ -483,13 +547,11 b' class workingctx(changectx):'
 
     def manifest(self): return self._manifest
 
-    def user(self): return self._repo.ui.username()
-    def date(self): return util.makedate()
-    def description(self): return ""
+    def user(self): return self._user or self._repo.ui.username()
+    def date(self): return self._date
+    def description(self): return self._text
     def files(self):
-        f = self.modified() + self.added() + self.removed()
-        f.sort()
-        return f
+        return util.sort(self._status[0] + self._status[1] + self._status[2])
 
     def modified(self): return self._status[0]
     def added(self): return self._status[1]
@@ -497,21 +559,18 b' class workingctx(changectx):'
     def deleted(self): return self._status[3]
     def unknown(self): return self._status[4]
     def clean(self): return self._status[5]
-    def branch(self): return self._repo.dirstate.branch()
+    def branch(self): return self._extra['branch']
+    def extra(self): return self._extra
 
     def tags(self):
         t = []
         [t.extend(p.tags()) for p in self.parents()]
         return t
 
-    def parents(self):
-        """return contexts for each parent changeset"""
-        return self._parents
-
     def children(self):
         return []
 
-    def fileflags(self, path):
+    def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
@@ -521,12 +580,9 b' class workingctx(changectx):'
         pnode = self._parents[0].changeset()[0]
         orig = self._repo.dirstate.copies().get(path, path)
         node, flag = self._repo.manifest.find(pnode, orig)
-        is_link = util.linkfunc(self._repo.root,
-                                lambda p: flag and 'l' in flag)
-        is_exec = util.execfunc(self._repo.root,
-                                lambda p: flag and 'x' in flag)
         try:
-            return (is_link(path) and 'l' or '') + (is_exec(path) and 'x' or '')
+            ff = self._repo.dirstate.flagfunc(lambda x: flag or '')
+            return ff(path)
         except OSError:
             pass
 
@@ -543,6 +599,9 b' class workingctx(changectx):'
         """return the ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
+    def walk(self, match):
+        return util.sort(self._repo.dirstate.walk(match, True, False).keys())
+
 class workingfilectx(filectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
@@ -625,3 +684,92 b' class workingfilectx(filectx):'
             return (t, tz)
 
     def cmp(self, text): return self._repo.wread(self._path) == text
+
+class memctx(object):
+    """A memctx is a subset of changectx supposed to be built on memory
+    and passed to commit functions.
+
+    NOTE: this interface and the related memfilectx are experimental and
+    may change without notice.
+
+    parents - a pair of parent nodeids.
+    filectxfn - a callable taking (repo, memctx, path) arguments and
+    returning a memctx object.
+    date - any valid date string or (unixtime, offset), or None.
+    user - username string, or None.
+    extra - a dictionary of extra values, or None.
+    """
+    def __init__(self, repo, parents, text, files, filectxfn, user=None,
+                 date=None, extra=None):
+        self._repo = repo
+        self._rev = None
+        self._node = None
+        self._text = text
+        self._date = date and util.parsedate(date) or util.makedate()
+        self._user = user
+        parents = [(p or nullid) for p in parents]
+        p1, p2 = parents
+        self._parents = [changectx(self._repo, p) for p in (p1, p2)]
+        files = util.sort(list(files))
+        self._status = [files, [], [], [], []]
+        self._filectxfn = filectxfn
+
+        self._extra = extra and extra.copy() or {}
+        if 'branch' not in self._extra:
+            self._extra['branch'] = 'default'
+        elif self._extra.get('branch') == '':
+            self._extra['branch'] = 'default'
+
+    def __str__(self):
+        return str(self._parents[0]) + "+"
+
+    def __int__(self):
+        return self._rev
+
+    def __nonzero__(self):
+        return True
+
+    def user(self): return self._user or self._repo.ui.username()
+    def date(self): return self._date
+    def description(self): return self._text
+    def files(self): return self.modified()
+    def modified(self): return self._status[0]
+    def added(self): return self._status[1]
+    def removed(self): return self._status[2]
+    def deleted(self): return self._status[3]
+    def unknown(self): return self._status[4]
+    def clean(self): return self._status[5]
+    def branch(self): return self._extra['branch']
+    def extra(self): return self._extra
+    def flags(self, f): return self[f].flags()
+
+    def parents(self):
+        """return contexts for each parent changeset"""
+        return self._parents
+
+    def filectx(self, path, filelog=None):
+        """get a file context from the working directory"""
+        return self._filectxfn(self._repo, self, path)
+
+class memfilectx(object):
+    """A memfilectx is a subset of filectx supposed to be built by client
+    code and passed to commit functions.
+    """
+    def __init__(self, path, data, islink, isexec, copied):
+        """copied is the source file path, or None."""
+        self._path = path
+        self._data = data
+        self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
+        self._copied = None
+        if copied:
+            self._copied = (copied, nullid)
+
+    def __nonzero__(self): return True
+    def __str__(self): return "%s@%s" % (self.path(), self._changectx)
+    def path(self): return self._path
+    def data(self): return self._data
+    def flags(self): return self._flags
+    def isexec(self): return 'x' in self._flags
+    def islink(self): return 'l' in self._flags
+    def renamed(self): return self._copied
+

mercurial/copies.py

@@ -11,9 +11,7 b' import util, heapq'
 
 def _nonoverlap(d1, d2, d3):
     "Return list of elements in d1 not in d2 or d3"
-    l = [d for d in d1 if d not in d3 and d not in d2]
-    l.sort()
-    return l
+    return util.sort([d for d in d1 if d not in d3 and d not in d2])
 
 def _dirname(f):
     s = f.rfind("/")
@@ -49,9 +47,7 b' def _findoldnames(fctx, limit):'
         visit += [(p, depth - 1) for p in fc.parents()]
 
     # return old names sorted by depth
-    old = old.values()
-    old.sort()
-    return [o[1] for o in old]
+    return [o[1] for o in util.sort(old.values())]
 
 def _findlimit(repo, a, b):
     "find the earliest revision that's an ancestor of a or b but not both"
@@ -67,7 +63,7 b' def _findlimit(repo, a, b):'
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
-    working = cl.count() # pseudo rev for the working directory
+    working = len(cl) # pseudo rev for the working directory
     if a is None:
         a = working
     if b is None:
@@ -109,6 +105,10 b' def copies(repo, c1, c2, ca, checkdirs=F'
     if not c1 or not c2 or c1 == c2:
         return {}, {}
 
+    # avoid silly behavior for parent -> working dir
+    if c2.node() == None and c1.node() == repo.dirstate.parents()[0]:
+        return repo.dirstate.copies(), {}
+
     limit = _findlimit(repo, c1.rev(), c2.rev())
     m1 = c1.manifest()
     m2 = c2.manifest()

mercurial/dirstate.py

@@ -9,12 +9,20 b' of the GNU General Public License, incor'
 
 from node import nullid
 from i18n import _
-import struct, os, bisect, stat, strutil, util, errno, ignore
+import struct, os, bisect, stat, util, errno, ignore
 import cStringIO, osutil, sys
 
 _unknown = ('?', 0, 0, 0)
 _format = ">cllll"
 
+def _finddirs(path):
+    pos = len(path)
+    while 1:
+        pos = path.rfind('/', 0, pos)
+        if pos == -1:
+            break
+        yield path[:pos]
+
 class dirstate(object):
 
     def __init__(self, opener, ui, root):
@@ -31,6 +39,13 b' class dirstate(object):'
         elif name == '_copymap':
             self._read()
             return self._copymap
+        elif name == '_foldmap':
+            _foldmap = {}
+            for name in self._map:
+                norm = os.path.normcase(os.path.normpath(name))
+                _foldmap[norm] = name
+            self._foldmap = _foldmap
+            return self._foldmap
         elif name == '_branch':
             try:
                 self._branch = (self._opener("branch").read().strip()
@@ -48,10 +63,12 b' class dirstate(object):'
                 if err.errno != errno.ENOENT: raise
             return self._pl
         elif name == '_dirs':
-            self._dirs = {}
-            for f in self._map:
-                if self[f] != 'r':
-                    self._incpath(f)
+            dirs = {}
+            for f,s in self._map.items():
+                if s[0] != 'r':
+                    for base in _finddirs(f):
+                        dirs[base] = dirs.get(base, 0) + 1
+            self._dirs = dirs
             return self._dirs
         elif name == '_ignore':
             files = [self._join('.hgignore')]
@@ -63,15 +80,55 b' class dirstate(object):'
         elif name == '_slash':
             self._slash = self._ui.configbool('ui', 'slash') and os.sep != '/'
             return self._slash
+        elif name == '_checklink':
+            self._checklink = util.checklink(self._root)
+            return self._checklink
         elif name == '_checkexec':
             self._checkexec = util.checkexec(self._root)
             return self._checkexec
+        elif name == '_checkcase':
+            self._checkcase = not util.checkcase(self._join('.hg'))
+            return self._checkcase
+        elif name == 'normalize':
+            if self._checkcase:
+                self.normalize = self._normalize
+            else:
+                self.normalize = lambda x: x
+            return self.normalize
         else:
             raise AttributeError, name
 
     def _join(self, f):
         return os.path.join(self._root, f)
 
+    def flagfunc(self, fallback):
+        if self._checklink:
+            if self._checkexec:
+                def f(x):
+                    p = os.path.join(self._root, x)
+                    if os.path.islink(p):
+                        return 'l'
+                    if util.is_exec(p):
+                        return 'x'
+                    return ''
+                return f
+            def f(x):
+                if os.path.islink(os.path.join(self._root, x)):
+                    return 'l'
+                if 'x' in fallback(x):
+                    return 'x'
+                return ''
+            return f
+        if self._checkexec:
+            def f(x):
+                if 'l' in fallback(x):
+                    return 'l'
+                if util.is_exec(os.path.join(self._root, x)):
+                    return 'x'
+                return ''
+            return f
+        return fallback
+
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root: return ''
@@ -106,9 +163,7 b' class dirstate(object):'
         return key in self._map
 
     def __iter__(self):
-        a = self._map.keys()
-        a.sort()
-        for x in a:
+        for x in util.sort(self._map):
             yield x
 
     def parents(self):
@@ -161,7 +216,7 b' class dirstate(object):'
             dmap[f] = e # we hold onto e[4] because making a subtuple is slow
 
     def invalidate(self):
-        for a in "_map _copymap _branch _pl _dirs _ignore".split():
+        for a in "_map _copymap _foldmap _branch _pl _dirs _ignore".split():
             if a in self.__dict__:
                 delattr(self, a)
         self._dirty = False
@@ -178,67 +233,39 b' class dirstate(object):'
     def copies(self):
         return self._copymap
 
-    def _incpath(self, path):
-        c = path.rfind('/')
-        if c >= 0:
+    def _droppath(self, f):
+        if self[f] not in "?r" and "_dirs" in self.__dict__:
             dirs = self._dirs
-            base = path[:c]
-            if base not in dirs:
-                self._incpath(base)
-                dirs[base] = 1
-            else:
-                dirs[base] += 1
-
-    def _decpath(self, path):
-        c = path.rfind('/')
-        if c >= 0:
-            base = path[:c]
-            dirs = self._dirs
-            if dirs[base] == 1:
-                del dirs[base]
-                self._decpath(base)
-            else:
-                dirs[base] -= 1
+            for base in _finddirs(f):
+                if dirs[base] == 1:
+                    del dirs[base]
+                else:
+                    dirs[base] -= 1
 
-    def _incpathcheck(self, f):
-        if '\r' in f or '\n' in f:
-            raise util.Abort(_("'\\n' and '\\r' disallowed in filenames: %r")
-                             % f)
-        # shadows
-        if f in self._dirs:
-            raise util.Abort(_('directory %r already in dirstate') % f)
-        for c in strutil.rfindall(f, '/'):
-            d = f[:c]
-            if d in self._dirs:
-                break
-            if d in self._map and self[d] != 'r':
-                raise util.Abort(_('file %r in dirstate clashes with %r') %
-                                 (d, f))
-        self._incpath(f)
-
-    def _changepath(self, f, newstate, relaxed=False):
-        # handle upcoming path changes
+    def _addpath(self, f, check=False):
         oldstate = self[f]
-        if oldstate not in "?r" and newstate in "?r":
-            if "_dirs" in self.__dict__:
-                self._decpath(f)
-            return
-        if oldstate in "?r" and newstate not in "?r":
-            if relaxed and oldstate == '?':
-                # XXX
-                # in relaxed mode we assume the caller knows
-                # what it is doing, workaround for updating
-                # dir-to-file revisions
-                if "_dirs" in self.__dict__:
-                    self._incpath(f)
-                return
-            self._incpathcheck(f)
-            return
+        if check or oldstate == "r":
+            if '\r' in f or '\n' in f:
+                raise util.Abort(
+                    _("'\\n' and '\\r' disallowed in filenames: %r") % f)
+            if f in self._dirs:
+                raise util.Abort(_('directory %r already in dirstate') % f)
+            # shadows
+            for d in _finddirs(f):
+                if d in self._dirs:
+                    break
+                if d in self._map and self[d] != 'r':
+                    raise util.Abort(
+                        _('file %r in dirstate clashes with %r') % (d, f))
+        if oldstate in "?r" and "_dirs" in self.__dict__:
+            dirs = self._dirs
+            for base in _finddirs(f):
+                dirs[base] = dirs.get(base, 0) + 1
 
     def normal(self, f):
         'mark a file normal and clean'
         self._dirty = True
-        self._changepath(f, 'n', True)
+        self._addpath(f)
         s = os.lstat(self._join(f))
         self._map[f] = ('n', s.st_mode, s.st_size, s.st_mtime, 0)
         if f in self._copymap:
@@ -262,7 +289,7 b' class dirstate(object):'
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._dirty = True
-        self._changepath(f, 'n', True)
+        self._addpath(f)
         self._map[f] = ('n', 0, -1, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
@@ -270,7 +297,7 b' class dirstate(object):'
     def normaldirty(self, f):
         'mark a file normal, but dirty'
         self._dirty = True
-        self._changepath(f, 'n', True)
+        self._addpath(f)
         self._map[f] = ('n', 0, -2, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
@@ -278,7 +305,7 b' class dirstate(object):'
     def add(self, f):
         'mark a file added'
         self._dirty = True
-        self._changepath(f, 'a')
+        self._addpath(f, True)
         self._map[f] = ('a', 0, -1, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
@@ -286,7 +313,7 b' class dirstate(object):'
     def remove(self, f):
         'mark a file removed'
         self._dirty = True
-        self._changepath(f, 'r')
+        self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             entry = self._map[f]
@@ -302,7 +329,7 b' class dirstate(object):'
         'mark a file merged'
         self._dirty = True
         s = os.lstat(self._join(f))
-        self._changepath(f, 'm', True)
+        self._addpath(f)
         self._map[f] = ('m', s.st_mode, s.st_size, s.st_mtime, 0)
         if f in self._copymap:
             del self._copymap[f]
@@ -311,11 +338,18 b' class dirstate(object):'
         'forget a file'
         self._dirty = True
         try:
-            self._changepath(f, '?')
+            self._droppath(f)
             del self._map[f]
         except KeyError:
             self._ui.warn(_("not in dirstate: %s\n") % f)
 
+    def _normalize(self, path):
+        if path not in self._foldmap:
+            if not os.path.exists(path):
+                return path
+            self._foldmap[path] = util.fspath(path, self._root)
+        return self._foldmap[path]
+
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
@@ -327,7 +361,7 b' class dirstate(object):'
     def rebuild(self, parent, files):
         self.clear()
         for f in files:
-            if files.execf(f):
+            if 'x' in files.flags(f):
                 self._map[f] = ('n', 0777, -1, 0, 0)
             else:
                 self._map[f] = ('n', 0666, -1, 0, 0)
@@ -364,40 +398,33 b' class dirstate(object):'
         st.rename()
         self._dirty = self._dirtypl = False
 
-    def _filter(self, files):
-        ret = {}
-        unknown = []
-
-        for x in files:
-            if x == '.':
-                return self._map.copy()
-            if x not in self._map:
-                unknown.append(x)
-            else:
-                ret[x] = self._map[x]
-
-        if not unknown:
-            return ret
+    def _dirignore(self, f):
+        if f == '.':
+            return False
+        if self._ignore(f):
+            return True
+        for p in _finddirs(f):
+            if self._ignore(p):
+                return True
+        return False
 
-        b = self._map.keys()
-        b.sort()
-        blen = len(b)
+    def walk(self, match, unknown, ignored):
+        '''
+        walk recursively through the directory tree, finding all files
+        matched by the match function
+
+        results are yielded in a tuple (filename, stat), where stat
+        and st is the stat result if the file was found in the directory.
+        '''
 
-        for x in unknown:
-            bs = bisect.bisect(b, "%s%s" % (x, '/'))
-            while bs < blen:
-                s = b[bs]
-                if len(s) > len(x) and s.startswith(x):
-                    ret[s] = self._map[s]
-                else:
-                    break
-                bs += 1
-        return ret
+        def fwarn(f, msg):
+            self._ui.warn('%s: %s\n' % (self.pathto(ff), msg))
+            return False
+        badfn = fwarn
+        if hasattr(match, 'bad'):
+            badfn = match.bad
 
-    def _supported(self, f, mode, verbose=False):
-        if stat.S_ISREG(mode) or stat.S_ISLNK(mode):
-            return True
-        if verbose:
+        def badtype(f, mode):
             kind = 'unknown'
             if stat.S_ISCHR(mode): kind = _('character device')
             elif stat.S_ISBLK(mode): kind = _('block device')
@@ -406,173 +433,121 b' class dirstate(object):'
             elif stat.S_ISDIR(mode): kind = _('directory')
             self._ui.warn(_('%s: unsupported file type (type is %s)\n')
                           % (self.pathto(f), kind))
-        return False
-
-    def _dirignore(self, f):
-        if f == '.':
-            return False
-        if self._ignore(f):
-            return True
-        for c in strutil.findall(f, '/'):
-            if self._ignore(f[:c]):
-                return True
-        return False
-
-    def walk(self, files=None, match=util.always, badmatch=None):
-        # filter out the stat
-        for src, f, st in self.statwalk(files, match, badmatch=badmatch):
-            yield src, f
-
-    def statwalk(self, files=None, match=util.always, unknown=True,
-                 ignored=False, badmatch=None, directories=False):
-        '''
-        walk recursively through the directory tree, finding all files
-        matched by the match function
-
-        results are yielded in a tuple (src, filename, st), where src
-        is one of:
-        'f' the file was found in the directory tree
-        'd' the file is a directory of the tree
-        'm' the file was only in the dirstate and not in the tree
-        'b' file was not found and matched badmatch
-
-        and st is the stat result if the file was found in the directory.
-        '''
-
-        # walk all files by default
-        if not files:
-            files = ['.']
-            dc = self._map.copy()
-        else:
-            files = util.unique(files)
-            dc = self._filter(files)
-
-        def imatch(file_):
-            if file_ not in dc and self._ignore(file_):
-                return False
-            return match(file_)
 
         # TODO: don't walk unknown directories if unknown and ignored are False
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
-            imatch = match
             ignore = util.never
             dirignore = util.never
 
-        # self._root may end with a path separator when self._root == '/'
-        common_prefix_len = len(self._root)
-        if not util.endswithsep(self._root):
-            common_prefix_len += 1
-
+        matchfn = match.matchfn
+        dmap = self._map
         normpath = util.normpath
+        normalize = self.normalize
         listdir = osutil.listdir
         lstat = os.lstat
         bisect_left = bisect.bisect_left
-        isdir = os.path.isdir
         pconvert = util.pconvert
-        join = os.path.join
-        s_isdir = stat.S_ISDIR
-        supported = self._supported
-        _join = self._join
-        known = {'.hg': 1}
+        getkind = stat.S_IFMT
+        dirkind = stat.S_IFDIR
+        regkind = stat.S_IFREG
+        lnkkind = stat.S_IFLNK
+        join = self._join
+        work = []
+        wadd = work.append
+
+        files = util.unique(match.files())
+        if not files or '.' in files:
+            files = ['']
+        results = {'.hg': None}
+
+        # step 1: find all explicit files
+        for ff in util.sort(files):
+            nf = normalize(normpath(ff))
+            if nf in results:
+                continue
 
-        # recursion free walker, faster than os.walk.
-        def findfiles(s):
-            work = [s]
-            wadd = work.append
-            found = []
-            add = found.append
-            if directories:
-                add((normpath(s[common_prefix_len:]), 'd', lstat(s)))
-            while work:
-                top = work.pop()
-                entries = listdir(top, stat=True)
-                # nd is the top of the repository dir tree
-                nd = normpath(top[common_prefix_len:])
-                if nd == '.':
-                    nd = ''
+            try:
+                st = lstat(join(nf))
+                kind = getkind(st.st_mode)
+                if kind == dirkind:
+                    if not dirignore(nf):
+                        wadd(nf)
+                elif kind == regkind or kind == lnkkind:
+                    results[nf] = st
                 else:
-                    # do not recurse into a repo contained in this
-                    # one. use bisect to find .hg directory so speed
-                    # is good on big directory.
-                    names = [e[0] for e in entries]
-                    hg = bisect_left(names, '.hg')
-                    if hg < len(names) and names[hg] == '.hg':
-                        if isdir(join(top, '.hg')):
-                            continue
-                for f, kind, st in entries:
-                    np = pconvert(join(nd, f))
-                    if np in known:
+                    badtype(ff, kind)
+                    if nf in dmap:
+                        results[nf] = None
+            except OSError, inst:
+                keep = False
+                prefix = nf + "/"
+                for fn in dmap:
+                    if nf == fn or fn.startswith(prefix):
+                        keep = True
+                        break
+                if not keep:
+                    if inst.errno != errno.ENOENT:
+                        fwarn(ff, inst.strerror)
+                    elif badfn(ff, inst.strerror):
+                        if (nf in dmap or not ignore(nf)) and matchfn(nf):
+                            results[nf] = None
+
+        # step 2: visit subdirectories
+        while work:
+            nd = work.pop()
+            if hasattr(match, 'dir'):
+                match.dir(nd)
+            entries = listdir(join(nd), stat=True)
+            if nd == '.':
+                nd = ''
+            else:
+                # do not recurse into a repo contained in this
+                # one. use bisect to find .hg directory so speed
+                # is good on big directory.
+                hg = bisect_left(entries, ('.hg'))
+                if hg < len(entries) and entries[hg][0] == '.hg' \
+                        and entries[hg][1] == dirkind:
                         continue
-                    known[np] = 1
-                    p = join(top, f)
-                    # don't trip over symlinks
-                    if kind == stat.S_IFDIR:
-                        if not ignore(np):
-                            wadd(p)
-                            if directories:
-                                add((np, 'd', st))
-                        if np in dc and match(np):
-                            add((np, 'm', st))
-                    elif imatch(np):
-                        if supported(np, st.st_mode):
-                            add((np, 'f', st))
-                        elif np in dc:
-                            add((np, 'm', st))
-            found.sort()
-            return found
+            for f, kind, st in entries:
+                nf = normalize(nd and (nd + "/" + f) or f)
+                if nf not in results:
+                    if kind == dirkind:
+                        if not ignore(nf):
+                            wadd(nf)
+                        if nf in dmap and matchfn(nf):
+                            results[nf] = None
+                    elif kind == regkind or kind == lnkkind:
+                        if nf in dmap:
+                            if matchfn(nf):
+                                results[nf] = st
+                        elif matchfn(nf) and not ignore(nf):
+                            results[nf] = st
+                    elif nf in dmap and matchfn(nf):
+                        results[nf] = None
 
-        # step one, find all files that match our criteria
-        files.sort()
-        for ff in files:
-            nf = normpath(ff)
-            f = _join(ff)
+        # step 3: report unseen items in the dmap hash
+        visit = [f for f in dmap if f not in results and match(f)]
+        for nf in util.sort(visit):
+            results[nf] = None
             try:
-                st = lstat(f)
+                st = lstat(join(nf))
+                kind = getkind(st.st_mode)
+                if kind == regkind or kind == lnkkind:
+                    results[nf] = st
             except OSError, inst:
-                found = False
-                for fn in dc:
-                    if nf == fn or (fn.startswith(nf) and fn[len(nf)] == '/'):
-                        found = True
-                        break
-                if not found:
-                    if inst.errno != errno.ENOENT or not badmatch:
-                        self._ui.warn('%s: %s\n' %
-                                      (self.pathto(ff), inst.strerror))
-                    elif badmatch and badmatch(ff) and imatch(nf):
-                        yield 'b', ff, None
-                continue
-            if s_isdir(st.st_mode):
-                if not dirignore(nf):
-                    for f, src, st in findfiles(f):
-                        yield src, f, st
-            else:
-                if nf in known:
-                    continue
-                known[nf] = 1
-                if match(nf):
-                    if supported(ff, st.st_mode, verbose=True):
-                        yield 'f', nf, st
-                    elif ff in dc:
-                        yield 'm', nf, st
+                if inst.errno not in (errno.ENOENT, errno.ENOTDIR):
+                    raise
 
-        # step two run through anything left in the dc hash and yield
-        # if we haven't already seen it
-        ks = dc.keys()
-        ks.sort()
-        for k in ks:
-            if k in known:
-                continue
-            known[k] = 1
-            if imatch(k):
-                yield 'm', k, None
+        del results['.hg']
+        return results
 
-    def status(self, files, match, list_ignored, list_clean, list_unknown=True):
+    def status(self, match, ignored, clean, unknown):
+        listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
-        files = files or []
         _join = self._join
         lstat = os.lstat
         cmap = self._copymap
@@ -586,38 +561,20 b' class dirstate(object):'
         dadd = deleted.append
         cadd = clean.append
 
-        for src, fn, st in self.statwalk(files, match, unknown=list_unknown,
-                                         ignored=list_ignored):
-            if fn in dmap:
-                type_, mode, size, time, foo = dmap[fn]
-            else:
-                if (list_ignored or fn in files) and self._dirignore(fn):
-                    if list_ignored:
+        for fn, st in self.walk(match, listunknown, listignored).iteritems():
+            if fn not in dmap:
+                if (listignored or match.exact(fn)) and self._dirignore(fn):
+                    if listignored:
                         iadd(fn)
-                elif list_unknown:
+                elif listunknown:
                     uadd(fn)
                 continue
-            if src == 'm':
-                nonexistent = True
-                if not st:
-                    try:
-                        st = lstat(_join(fn))
-                    except OSError, inst:
-                        if inst.errno not in (errno.ENOENT, errno.ENOTDIR):
-                            raise
-                        st = None
-                    # We need to re-check that it is a valid file
-                    if st and self._supported(fn, st.st_mode):
-                        nonexistent = False
-                # XXX: what to do with file no longer present in the fs
-                # who are not removed in the dirstate ?
-                if nonexistent and type_ in "nma":
-                    dadd(fn)
-                    continue
-            # check the common case first
-            if type_ == 'n':
-                if not st:
-                    st = lstat(_join(fn))
+
+            state, mode, size, time, foo = dmap[fn]
+
+            if not st and state in "nma":
+                dadd(fn)
+            elif state == 'n':
                 if (size >= 0 and
                     (size != st.st_size
                      or ((mode ^ st.st_mode) & 0100 and self._checkexec))
@@ -626,13 +583,13 b' class dirstate(object):'
                     madd(fn)
                 elif time != int(st.st_mtime):
                     ladd(fn)
-                elif list_clean:
+                elif listclean:
                     cadd(fn)
-            elif type_ == 'm':
+            elif state == 'm':
                 madd(fn)
-            elif type_ == 'a':
+            elif state == 'a':
                 aadd(fn)
-            elif type_ == 'r':
+            elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,

mercurial/filemerge.py

@@ -5,7 +5,7 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-from node import nullrev
+from node import nullrev, short
 from i18n import _
 import util, os, tempfile, simplemerge, re, filecmp
 
@@ -63,8 +63,7 b' def _picktool(repo, ui, path, binary, sy'
         if t not in tools:
             tools[t] = int(_toolstr(ui, t, "priority", "0"))
     names = tools.keys()
-    tools = [(-p,t) for t,p in tools.items()]
-    tools.sort()
+    tools = util.sort([(-p,t) for t,p in tools.items()])
     uimerge = ui.config("ui", "merge")
     if uimerge:
         if uimerge not in names:
@@ -101,13 +100,14 b' def _matcheol(file, origfile):'
             if newdata != data:
                 open(file, "wb").write(newdata)
 
-def filemerge(repo, fw, fd, fo, wctx, mctx):
+def filemerge(repo, mynode, orig, fcd, fco, fca):
     """perform a 3-way merge in the working directory
 
-    fw = original filename in the working directory
-    fd = destination filename in the working directory
-    fo = filename in other parent
-    wctx, mctx = working and merge changecontexts
+    mynode = parent node before merge
+    orig = original local filename before merge
+    fco = other file context
+    fca = ancestor file context
+    fcd = local file context for current/destination file
     """
 
     def temp(prefix, ctx):
@@ -125,29 +125,27 b' def filemerge(repo, fw, fd, fo, wctx, mc'
         except IOError:
             return False
 
-    fco = mctx.filectx(fo)
-    if not fco.cmp(wctx.filectx(fd).data()): # files identical?
+    if not fco.cmp(fcd.data()): # files identical?
         return None
 
     ui = repo.ui
-    fcm = wctx.filectx(fw)
-    fca = fcm.ancestor(fco) or repo.filectx(fw, fileid=nullrev)
-    binary = isbin(fcm) or isbin(fco) or isbin(fca)
-    symlink = fcm.islink() or fco.islink()
-    tool, toolpath = _picktool(repo, ui, fw, binary, symlink)
+    fd = fcd.path()
+    binary = isbin(fcd) or isbin(fco) or isbin(fca)
+    symlink = 'l' in fcd.flags() + fco.flags()
+    tool, toolpath = _picktool(repo, ui, fd, binary, symlink)
     ui.debug(_("picked tool '%s' for %s (binary %s symlink %s)\n") %
-               (tool, fw, binary, symlink))
+               (tool, fd, binary, symlink))
 
     if not tool:
         tool = "internal:local"
         if ui.prompt(_(" no tool found to merge %s\n"
-                       "keep (l)ocal or take (o)ther?") % fw,
+                       "keep (l)ocal or take (o)ther?") % fd,
                      _("[lo]"), _("l")) != _("l"):
             tool = "internal:other"
     if tool == "internal:local":
         return 0
     if tool == "internal:other":
-        repo.wwrite(fd, fco.data(), fco.fileflags())
+        repo.wwrite(fd, fco.data(), fco.flags())
         return 0
     if tool == "internal:fail":
         return 1
@@ -160,11 +158,12 b' def filemerge(repo, fw, fd, fo, wctx, mc'
     back = a + ".orig"
     util.copyfile(a, back)
 
-    if fw != fo:
-        repo.ui.status(_("merging %s and %s\n") % (fw, fo))
+    if orig != fco.path():
+        repo.ui.status(_("merging %s and %s to %s\n") % (orig, fco.path(), fd))
     else:
-        repo.ui.status(_("merging %s\n") % fw)
-    repo.ui.debug(_("my %s other %s ancestor %s\n") % (fcm, fco, fca))
+        repo.ui.status(_("merging %s\n") % fd)
+
+    repo.ui.debug(_("my %s other %s ancestor %s\n") % (fcd, fco, fca))
 
     # do we attempt to simplemerge first?
     if _toolbool(ui, tool, "premerge", not (binary or symlink)):
@@ -178,11 +177,11 b' def filemerge(repo, fw, fd, fo, wctx, mc'
         util.copyfile(back, a) # restore from backup and try again
 
     env = dict(HG_FILE=fd,
-               HG_MY_NODE=str(wctx.parents()[0]),
-               HG_OTHER_NODE=str(mctx),
-               HG_MY_ISLINK=fcm.islink(),
-               HG_OTHER_ISLINK=fco.islink(),
-               HG_BASE_ISLINK=fca.islink())
+               HG_MY_NODE=short(mynode),
+               HG_OTHER_NODE=str(fco.changectx()),
+               HG_MY_ISLINK='l' in fcd.flags(),
+               HG_OTHER_ISLINK='l' in fco.flags(),
+               HG_BASE_ISLINK='l' in fca.flags())
 
     if tool == "internal:merge":
         r = simplemerge.simplemerge(a, b, c, label=['local', 'other'])
@@ -196,7 +195,7 b' def filemerge(repo, fw, fd, fo, wctx, mc'
         r = util.system(toolpath + ' ' + args, cwd=repo.root, environ=env)
 
     if not r and _toolbool(ui, tool, "checkconflicts"):
-        if re.match("^(<<<<<<< .*|=======|>>>>>>> .*)$", fcm.data()):
+        if re.match("^(<<<<<<< .*|=======|>>>>>>> .*)$", fcd.data()):
             r = 1
 
     if not r and _toolbool(ui, tool, "checkchanged"):

mercurial/hbisect.py

@@ -30,12 +30,12 b' def bisect(changelog, state):'
         badrev = min([changelog.rev(n) for n in bad])
         goodrevs = [changelog.rev(n) for n in good]
         # build ancestors array
-        ancestors = [[]] * (changelog.count() + 1) # an extra for [-1]
+        ancestors = [[]] * (len(changelog) + 1) # an extra for [-1]
 
         # clear good revs from array
         for node in goodrevs:
             ancestors[node] = None
-        for rev in xrange(changelog.count(), -1, -1):
+        for rev in xrange(len(changelog), -1, -1):
             if ancestors[rev] is None:
                 for prev in clparents(rev):
                     ancestors[prev] = None

mercurial/help.py

@@ -5,8 +5,8 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-helptable = {
-    "dates|Date Formats":
+helptable = (
+    ("dates|Date Formats",
     r'''
     Some commands allow the user to specify a date:
     backout, commit, import, tag: Specify the commit date.
@@ -21,7 +21,7 b' helptable = {'
     "13:18" (today assumed)
     "3:39" (3:39AM assumed)
     "3:39pm" (15:39)
-    "2006-12-6 13:18:29" (ISO 8601 format)
+    "2006-12-06 13:18:29" (ISO 8601 format)
     "2006-12-6 13:18"
     "2006-12-6"
     "12-6"
@@ -43,9 +43,55 b' helptable = {'
     ">{date}" - on or after a given date
     "{date} to {date}" - a date range, inclusive
     "-{days}" - within a given number of days of today
-    ''',
+    '''),
+
+    ("patterns|File Name Patterns",
+    r'''
+    Mercurial accepts several notations for identifying one or more
+    files at a time.
+
+    By default, Mercurial treats filenames as shell-style extended
+    glob patterns.
+
+    Alternate pattern notations must be specified explicitly.
+
+    To use a plain path name without any pattern matching, start a
+    name with "path:".  These path names must match completely, from
+    the root of the current repository.
+
+    To use an extended glob, start a name with "glob:".  Globs are
+    rooted at the current directory; a glob such as "*.c" will match
+    files ending in ".c" in the current directory only.
+
+    The supported glob syntax extensions are "**" to match any string
+    across path separators, and "{a,b}" to mean "a or b".
 
-    'environment|env|Environment Variables':
+    To use a Perl/Python regular expression, start a name with "re:".
+    Regexp pattern matching is anchored at the root of the repository.
+
+    Plain examples:
+
+    path:foo/bar   a name bar in a directory named foo in the root of
+                   the repository
+    path:path:name a file or directory named "path:name"
+
+    Glob examples:
+
+    glob:*.c       any name ending in ".c" in the current directory
+    *.c            any name ending in ".c" in the current directory
+    **.c           any name ending in ".c" in the current directory, or
+                   any subdirectory
+    foo/*.c        any name ending in ".c" in the directory foo
+    foo/**.c       any name ending in ".c" in the directory foo, or any
+                   subdirectory
+
+    Regexp examples:
+
+    re:.*\.c$      any name ending in ".c", anywhere in the repository
+
+    '''),
+
+    ('environment|env|Environment Variables',
     r'''
 HG::
     Path to the 'hg' executable, automatically passed when running hooks,
@@ -114,51 +160,57 b' EDITOR::'
 PYTHONPATH::
     This is used by Python to find imported modules and may need to be set
     appropriately if Mercurial is not installed system-wide.
-    ''',
+    '''),
 
-    "patterns|File Name Patterns": r'''
-    Mercurial accepts several notations for identifying one or more
-    files at a time.
+    ('revs|revisions|Specifying Single Revisions',
+    r'''
+    Mercurial accepts several notations for identifying individual
+    revisions.
 
-    By default, Mercurial treats filenames as shell-style extended
-    glob patterns.
-
-    Alternate pattern notations must be specified explicitly.
+    A plain integer is treated as a revision number. Negative
+    integers are treated as offsets from the tip, with -1 denoting the
+    tip.
 
-    To use a plain path name without any pattern matching, start a
-    name with "path:".  These path names must match completely, from
-    the root of the current repository.
+    A 40-digit hexadecimal string is treated as a unique revision
+    identifier.
 
-    To use an extended glob, start a name with "glob:".  Globs are
-    rooted at the current directory; a glob such as "*.c" will match
-    files ending in ".c" in the current directory only.
+    A hexadecimal string less than 40 characters long is treated as a
+    unique revision identifier, and referred to as a short-form
+    identifier. A short-form identifier is only valid if it is the
+    prefix of one full-length identifier.
 
-    The supported glob syntax extensions are "**" to match any string
-    across path separators, and "{a,b}" to mean "a or b".
+    Any other string is treated as a tag name, which is a symbolic
+    name associated with a revision identifier. Tag names may not
+    contain the ":" character.
+
+    The reserved name "tip" is a special tag that always identifies
+    the most recent revision.
 
-    To use a Perl/Python regular expression, start a name with "re:".
-    Regexp pattern matching is anchored at the root of the repository.
-
-    Plain examples:
+    The reserved name "null" indicates the null revision. This is the
+    revision of an empty repository, and the parent of revision 0.
 
-    path:foo/bar   a name bar in a directory named foo in the root of
-                   the repository
-    path:path:name a file or directory named "path:name"
-
-    Glob examples:
+    The reserved name "." indicates the working directory parent. If
+    no working directory is checked out, it is equivalent to null.
+    If an uncommitted merge is in progress, "." is the revision of
+    the first parent.
+    '''),
 
-    glob:*.c       any name ending in ".c" in the current directory
-    *.c            any name ending in ".c" in the current directory
-    **.c           any name ending in ".c" in the current directory, or
-                   any subdirectory
-    foo/*.c        any name ending in ".c" in the directory foo
-    foo/**.c       any name ending in ".c" in the directory foo, or any
-                   subdirectory
+    ('mrevs|multirevs|Specifying Multiple Revisions',
+    r'''
+    When Mercurial accepts more than one revision, they may be
+    specified individually, or provided as a continuous range,
+    separated by the ":" character.
 
-    Regexp examples:
-
-    re:.*\.c$      any name ending in ".c", anywhere in the repository
+    The syntax of range notation is [BEGIN]:[END], where BEGIN and END
+    are revision identifiers. Both BEGIN and END are optional. If
+    BEGIN is not specified, it defaults to revision number 0. If END
+    is not specified, it defaults to the tip. The range ":" thus
+    means "all revisions".
 
-''',
-}
+    If BEGIN is greater than END, revisions are treated in reverse
+    order.
 
+    A range acts as a closed interval. This means that a range of 3:5
+    gives 3, 4 and 5. Similarly, a range of 4:2 gives 4, 3, and 2.
+    '''),
+)

mercurial/hg.py

@@ -16,7 +16,7 b' def _local(path):'
     return (os.path.isfile(util.drop_scheme('file', path)) and
             bundlerepo or localrepo)
 
-def parseurl(url, revs):
+def parseurl(url, revs=[]):
     '''parse url#branch, returning url, branch + revs'''
 
     if '#' not in url:
@@ -69,6 +69,15 b' def defaultdest(source):'
     '''return default destination of clone if none is given'''
     return os.path.basename(os.path.normpath(source))
 
+def localpath(path):
+    if path.startswith('file://localhost/'):
+        return path[16:]
+    if path.startswith('file://'):
+        return path[7:]
+    if path.startswith('file:'):
+        return path[5:]
+    return path
+
 def clone(ui, source, dest=None, pull=False, rev=None, update=True,
           stream=False):
     """Make a copy of an existing repository.
@@ -100,7 +109,8 b' def clone(ui, source, dest=None, pull=Fa'
     rev: revision to clone up to (implies pull=True)
 
     update: update working directory after clone completes, if
-    destination is local repository
+    destination is local repository (True means update to default rev,
+    anything else is treated as a revision)
     """
 
     if isinstance(source, str):
@@ -116,15 +126,6 b' def clone(ui, source, dest=None, pull=Fa'
         dest = defaultdest(source)
         ui.status(_("destination directory: %s\n") % dest)
 
-    def localpath(path):
-        if path.startswith('file://localhost/'):
-            return path[16:]
-        if path.startswith('file://'):
-            return path[7:]
-        if path.startswith('file:'):
-            return path[5:]
-        return path
-
     dest = localpath(dest)
     source = localpath(source)
 
@@ -244,7 +245,9 b' def clone(ui, source, dest=None, pull=Fa'
 
             if update:
                 dest_repo.ui.status(_("updating working directory\n"))
-                if not checkout:
+                if update is not True:
+                    checkout = update
+                elif not checkout:
                     try:
                         checkout = dest_repo.lookup("default")
                     except:
@@ -271,15 +274,7 b' def update(repo, node):'
     stats = _merge.update(repo, node, False, False, None)
     _showstats(repo, stats)
     if stats[3]:
-        repo.ui.status(_("There are unresolved merges with"
-                         " locally modified files.\n"))
-        if stats[1]:
-            repo.ui.status(_("You can finish the partial merge using:\n"))
-        else:
-            repo.ui.status(_("You can redo the full merge using:\n"))
-        # len(pl)==1, otherwise _merge.update() would have raised util.Abort:
-        repo.ui.status(_("  hg update %s\n  hg update %s\n")
-                       % (pl[0].rev(), repo.changectx(node).rev()))
+        repo.ui.status(_("use 'hg resolve' to retry unresolved file merges\n"))
     return stats[3] > 0
 
 def clean(repo, node, show_stats=True):
@@ -294,11 +289,7 b' def merge(repo, node, force=None, remind'
     _showstats(repo, stats)
     if stats[3]:
         pl = repo.parents()
-        repo.ui.status(_("There are unresolved merges,"
-                         " you can redo the full merge using:\n"
-                         "  hg update -C %s\n"
-                         "  hg merge %s\n")
-                       % (pl[0].rev(), pl[1].rev()))
+        repo.ui.status(_("use 'hg resolve' to retry unresolved file merges\n"))
     elif remind:
         repo.ui.status(_("(branch merge, don't forget to commit)\n"))
     return stats[3] > 0

mercurial/hgweb/hgweb_mod.py

@@ -6,79 +6,22 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-import os, mimetypes, re, mimetools, cStringIO
-from mercurial.node import hex, nullid, short
+import os, mimetypes
+from mercurial.node import hex, nullid
 from mercurial.repo import RepoError
-from mercurial import mdiff, ui, hg, util, archival, patch, hook
-from mercurial import revlog, templater, templatefilters, changegroup
-from common import get_mtime, style_map, paritygen, countgen, get_contact
-from common import ErrorResponse
+from mercurial import mdiff, ui, hg, util, patch, hook
+from mercurial import revlog, templater, templatefilters
+from common import get_mtime, style_map, paritygen, countgen, ErrorResponse
 from common import HTTP_OK, HTTP_BAD_REQUEST, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from request import wsgirequest
-import webcommands, protocol
-
-shortcuts = {
-    'cl': [('cmd', ['changelog']), ('rev', None)],
-    'sl': [('cmd', ['shortlog']), ('rev', None)],
-    'cs': [('cmd', ['changeset']), ('node', None)],
-    'f': [('cmd', ['file']), ('filenode', None)],
-    'fl': [('cmd', ['filelog']), ('filenode', None)],
-    'fd': [('cmd', ['filediff']), ('node', None)],
-    'fa': [('cmd', ['annotate']), ('filenode', None)],
-    'mf': [('cmd', ['manifest']), ('manifest', None)],
-    'ca': [('cmd', ['archive']), ('node', None)],
-    'tags': [('cmd', ['tags'])],
-    'tip': [('cmd', ['changeset']), ('node', ['tip'])],
-    'static': [('cmd', ['static']), ('file', None)]
-}
-
-def _up(p):
-    if p[0] != "/":
-        p = "/" + p
-    if p[-1] == "/":
-        p = p[:-1]
-    up = os.path.dirname(p)
-    if up == "/":
-        return "/"
-    return up + "/"
+import webcommands, protocol, webutil
 
-def revnavgen(pos, pagelen, limit, nodefunc):
-    def seq(factor, limit=None):
-        if limit:
-            yield limit
-            if limit >= 20 and limit <= 40:
-                yield 50
-        else:
-            yield 1 * factor
-            yield 3 * factor
-        for f in seq(factor * 10):
-            yield f
-
-    def nav(**map):
-        l = []
-        last = 0
-        for f in seq(1, pagelen):
-            if f < pagelen or f <= last:
-                continue
-            if f > limit:
-                break
-            last = f
-            if pos + f < limit:
-                l.append(("+%d" % f, hex(nodefunc(pos + f).node())))
-            if pos - f >= 0:
-                l.insert(0, ("-%d" % f, hex(nodefunc(pos - f).node())))
-
-        try:
-            yield {"label": "(0)", "node": hex(nodefunc('0').node())}
-
-            for label, node in l:
-                yield {"label": label, "node": node}
-
-            yield {"label": "tip", "node": "tip"}
-        except RepoError:
-            pass
-
-    return nav
+perms = {
+    'changegroup': 'pull',
+    'changegroupsubset': 'pull',
+    'unbundle': 'push',
+    'stream_out': 'pull',
+}
 
 class hgweb(object):
     def __init__(self, repo, name=None):
@@ -93,7 +36,6 b' class hgweb(object):'
         self.reponame = name
         self.archives = 'zip', 'gz', 'bz2'
         self.stripecount = 1
-        self._capabilities = None
         # a repo owner may set web.templates in .hg/hgrc to get any file
         # readable by the user running the CGI script
         self.templatepath = self.config("web", "templates",
@@ -125,18 +67,6 b' class hgweb(object):'
             self.maxfiles = int(self.config("web", "maxfiles", 10))
             self.allowpull = self.configbool("web", "allowpull", True)
             self.encoding = self.config("web", "encoding", util._encoding)
-            self._capabilities = None
-
-    def capabilities(self):
-        if self._capabilities is not None:
-            return self._capabilities
-        caps = ['lookup', 'changegroupsubset']
-        if self.configbool('server', 'uncompressed'):
-            caps.append('stream=%d' % self.repo.changelog.version)
-        if changegroup.bundlepriority:
-            caps.append('unbundle=%s' % ','.join(changegroup.bundlepriority))
-        self._capabilities = caps
-        return caps
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
@@ -146,22 +76,22 b' class hgweb(object):'
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
-        self.run_wsgi(req)
-        return req
+        return self.run_wsgi(req)
 
     def run_wsgi(self, req):
 
         self.refresh()
 
-        # expand form shortcuts
+        # process this if it's a protocol request
+        # protocol bits don't need to create any URLs
+        # and the clients always use the old URL structure
 
-        for k in shortcuts.iterkeys():
-            if k in req.form:
-                for name, value in shortcuts[k]:
-                    if value is None:
-                        value = req.form[k]
-                    req.form[name] = value
-                del req.form[k]
+        cmd = req.form.get('cmd', [''])[0]
+        if cmd and cmd in protocol.__all__:
+            if cmd in perms and not self.check_perm(req, perms[cmd]):
+                return []
+            method = getattr(protocol, cmd)
+            return method(self.repo, req)
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
@@ -194,8 +124,10 b' class hgweb(object):'
                 cmd = cmd[style+1:]
 
             # avoid accepting e.g. style parameter as command
-            if hasattr(webcommands, cmd) or hasattr(protocol, cmd):
+            if hasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
+            else:
+                cmd = ''
 
             if args and args[0]:
                 node = args.pop(0)
@@ -213,30 +145,13 b' class hgweb(object):'
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
-        # process this if it's a protocol request
-
-        cmd = req.form.get('cmd', [''])[0]
-        if cmd in protocol.__all__:
-            method = getattr(protocol, cmd)
-            method(self, req)
-            return
-
         # process the web interface request
 
         try:
 
             tmpl = self.templater(req)
-            try:
-                ctype = tmpl('mimetype', encoding=self.encoding)
-                ctype = templater.stringify(ctype)
-            except KeyError:
-                # old templates with inline HTTP headers?
-                if 'mimetype' in tmpl:
-                    raise
-                header = tmpl('header', encoding=self.encoding)
-                header_file = cStringIO.StringIO(templater.stringify(header))
-                msg = mimetools.Message(header_file, 0)
-                ctype = msg['content-type']
+            ctype = tmpl('mimetype', encoding=self.encoding)
+            ctype = templater.stringify(ctype)
 
             if cmd == '':
                 req.form['cmd'] = [tmpl.cache['default']]
@@ -254,6 +169,7 b' class hgweb(object):'
 
             req.write(content)
             del tmpl
+            return []
 
         except revlog.LookupError, err:
             req.respond(HTTP_NOT_FOUND, ctype)
@@ -261,12 +177,15 b' class hgweb(object):'
             if 'manifest' not in msg:
                 msg = 'revision not found: %s' % err.name
             req.write(tmpl('error', error=msg))
+            return []
         except (RepoError, revlog.RevlogError), inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             req.write(tmpl('error', error=str(inst)))
+            return []
         except ErrorResponse, inst:
             req.respond(inst.code, ctype)
             req.write(tmpl('error', error=inst.message))
+            return []
 
     def templater(self, req):
 
@@ -291,13 +210,7 b' class hgweb(object):'
         # some functions for the templater
 
         def header(**map):
-            header = tmpl('header', encoding=self.encoding, **map)
-            if 'mimetype' not in tmpl:
-                # old template with inline HTTP headers
-                header_file = cStringIO.StringIO(templater.stringify(header))
-                msg = mimetools.Message(header_file, 0)
-                header = header_file.read()
-            yield header
+            yield tmpl('header', encoding=self.encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)
@@ -355,54 +268,6 b' class hgweb(object):'
         if len(files) > self.maxfiles:
             yield tmpl("fileellipses")
 
-    def siblings(self, siblings=[], hiderev=None, **args):
-        siblings = [s for s in siblings if s.node() != nullid]
-        if len(siblings) == 1 and siblings[0].rev() == hiderev:
-            return
-        for s in siblings:
-            d = {'node': hex(s.node()), 'rev': s.rev()}
-            if hasattr(s, 'path'):
-                d['file'] = s.path()
-            d.update(args)
-            yield d
-
-    def renamelink(self, fl, node):
-        r = fl.renamed(node)
-        if r:
-            return [dict(file=r[0], node=hex(r[1]))]
-        return []
-
-    def nodetagsdict(self, node):
-        return [{"name": i} for i in self.repo.nodetags(node)]
-
-    def nodebranchdict(self, ctx):
-        branches = []
-        branch = ctx.branch()
-        # If this is an empty repo, ctx.node() == nullid,
-        # ctx.branch() == 'default', but branchtags() is
-        # an empty dict. Using dict.get avoids a traceback.
-        if self.repo.branchtags().get(branch) == ctx.node():
-            branches.append({"name": branch})
-        return branches
-
-    def nodeinbranch(self, ctx):
-        branches = []
-        branch = ctx.branch()
-        if branch != 'default' and self.repo.branchtags().get(branch) != ctx.node():
-            branches.append({"name": branch})
-        return branches
-
-    def nodebranchnodefault(self, ctx):
-        branches = []
-        branch = ctx.branch()
-        if branch != 'default':
-            branches.append({"name": branch})
-        return branches
-
-    def showtag(self, tmpl, t1, node=nullid, **args):
-        for t in self.repo.nodetags(node):
-            yield tmpl(t1, tag=t, **args)
-
     def diff(self, tmpl, node1, node2, files):
         def filterfiles(filters, files):
             l = [x for x in files if x in filters]
@@ -443,8 +308,8 b' class hgweb(object):'
                            linenumber="% 8s" % lineno)
 
         r = self.repo
-        c1 = r.changectx(node1)
-        c2 = r.changectx(node2)
+        c1 = r[node1]
+        c2 = r[node2]
         date1 = util.datestr(c1.date())
         date2 = util.datestr(c2.date())
 
@@ -470,524 +335,45 b' class hgweb(object):'
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
 
-    def changelog(self, tmpl, ctx, shortlog=False):
-        def changelist(limit=0,**map):
-            cl = self.repo.changelog
-            l = [] # build a list in forward order for efficiency
-            for i in xrange(start, end):
-                ctx = self.repo.changectx(i)
-                n = ctx.node()
-                showtags = self.showtag(tmpl, 'changelogtag', n)
-
-                l.insert(0, {"parity": parity.next(),
-                             "author": ctx.user(),
-                             "parent": self.siblings(ctx.parents(), i - 1),
-                             "child": self.siblings(ctx.children(), i + 1),
-                             "changelogtag": showtags,
-                             "desc": ctx.description(),
-                             "date": ctx.date(),
-                             "files": self.listfilediffs(tmpl, ctx.files(), n),
-                             "rev": i,
-                             "node": hex(n),
-                             "tags": self.nodetagsdict(n),
-                             "inbranch": self.nodeinbranch(ctx),
-                             "branches": self.nodebranchdict(ctx)})
-
-            if limit > 0:
-                l = l[:limit]
-
-            for e in l:
-                yield e
-
-        maxchanges = shortlog and self.maxshortchanges or self.maxchanges
-        cl = self.repo.changelog
-        count = cl.count()
-        pos = ctx.rev()
-        start = max(0, pos - maxchanges + 1)
-        end = min(count, start + maxchanges)
-        pos = end - 1
-        parity = paritygen(self.stripecount, offset=start-end)
-
-        changenav = revnavgen(pos, maxchanges, count, self.repo.changectx)
-
-        return tmpl(shortlog and 'shortlog' or 'changelog',
-                    changenav=changenav,
-                    node=hex(cl.tip()),
-                    rev=pos, changesets=count,
-                    entries=lambda **x: changelist(limit=0,**x),
-                    latestentry=lambda **x: changelist(limit=1,**x),
-                    archives=self.archivelist("tip"))
-
-    def search(self, tmpl, query):
-
-        def changelist(**map):
-            cl = self.repo.changelog
-            count = 0
-            qw = query.lower().split()
-
-            def revgen():
-                for i in xrange(cl.count() - 1, 0, -100):
-                    l = []
-                    for j in xrange(max(0, i - 100), i + 1):
-                        ctx = self.repo.changectx(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 ctx.user().lower() or
-                            q in ctx.description().lower() or
-                            q in " ".join(ctx.files()).lower()):
-                        miss = 1
-                        break
-                if miss:
-                    continue
-
-                count += 1
-                n = ctx.node()
-                showtags = self.showtag(tmpl, 'changelogtag', n)
-
-                yield tmpl('searchentry',
-                           parity=parity.next(),
-                           author=ctx.user(),
-                           parent=self.siblings(ctx.parents()),
-                           child=self.siblings(ctx.children()),
-                           changelogtag=showtags,
-                           desc=ctx.description(),
-                           date=ctx.date(),
-                           files=self.listfilediffs(tmpl, ctx.files(), n),
-                           rev=ctx.rev(),
-                           node=hex(n),
-                           tags=self.nodetagsdict(n),
-                           inbranch=self.nodeinbranch(ctx),
-                           branches=self.nodebranchdict(ctx))
-
-                if count >= self.maxchanges:
-                    break
-
-        cl = self.repo.changelog
-        parity = paritygen(self.stripecount)
-
-        return tmpl('search',
-                    query=query,
-                    node=hex(cl.tip()),
-                    entries=changelist,
-                    archives=self.archivelist("tip"))
-
-    def changeset(self, tmpl, ctx):
-        n = ctx.node()
-        showtags = self.showtag(tmpl, 'changesettag', n)
-        parents = ctx.parents()
-        p1 = parents[0].node()
-
-        files = []
-        parity = paritygen(self.stripecount)
-        for f in ctx.files():
-            files.append(tmpl("filenodelink",
-                              node=hex(n), file=f,
-                              parity=parity.next()))
-
-        def diff(**map):
-            yield self.diff(tmpl, p1, n, None)
-
-        return tmpl('changeset',
-                    diff=diff,
-                    rev=ctx.rev(),
-                    node=hex(n),
-                    parent=self.siblings(parents),
-                    child=self.siblings(ctx.children()),
-                    changesettag=showtags,
-                    author=ctx.user(),
-                    desc=ctx.description(),
-                    date=ctx.date(),
-                    files=files,
-                    archives=self.archivelist(hex(n)),
-                    tags=self.nodetagsdict(n),
-                    branch=self.nodebranchnodefault(ctx),
-                    inbranch=self.nodeinbranch(ctx),
-                    branches=self.nodebranchdict(ctx))
-
-    def filelog(self, tmpl, fctx):
-        f = fctx.path()
-        fl = fctx.filelog()
-        count = fl.count()
-        pagelen = self.maxshortchanges
-        pos = fctx.filerev()
-        start = max(0, pos - pagelen + 1)
-        end = min(count, start + pagelen)
-        pos = end - 1
-        parity = paritygen(self.stripecount, offset=start-end)
-
-        def entries(limit=0, **map):
-            l = []
-
-            for i in xrange(start, end):
-                ctx = fctx.filectx(i)
-                n = fl.node(i)
-
-                l.insert(0, {"parity": parity.next(),
-                             "filerev": i,
-                             "file": f,
-                             "node": hex(ctx.node()),
-                             "author": ctx.user(),
-                             "date": ctx.date(),
-                             "rename": self.renamelink(fl, n),
-                             "parent": self.siblings(fctx.parents()),
-                             "child": self.siblings(fctx.children()),
-                             "desc": ctx.description()})
-
-            if limit > 0:
-                l = l[:limit]
-
-            for e in l:
-                yield e
-
-        nodefunc = lambda x: fctx.filectx(fileid=x)
-        nav = revnavgen(pos, pagelen, count, nodefunc)
-        return tmpl("filelog", file=f, node=hex(fctx.node()), nav=nav,
-                    entries=lambda **x: entries(limit=0, **x),
-                    latestentry=lambda **x: entries(limit=1, **x))
-
-    def filerevision(self, tmpl, fctx):
-        f = fctx.path()
-        text = fctx.data()
-        fl = fctx.filelog()
-        n = fctx.filenode()
-        parity = paritygen(self.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(1)):
-                yield {"line": t,
-                       "lineid": "l%d" % (lineno + 1),
-                       "linenumber": "% 6d" % (lineno + 1),
-                       "parity": parity.next()}
-
-        return tmpl("filerevision",
-                    file=f,
-                    path=_up(f),
-                    text=lines(),
-                    rev=fctx.rev(),
-                    node=hex(fctx.node()),
-                    author=fctx.user(),
-                    date=fctx.date(),
-                    desc=fctx.description(),
-                    branch=self.nodebranchnodefault(fctx),
-                    parent=self.siblings(fctx.parents()),
-                    child=self.siblings(fctx.children()),
-                    rename=self.renamelink(fl, n),
-                    permissions=fctx.manifest().flags(f))
-
-    def fileannotate(self, tmpl, fctx):
-        f = fctx.path()
-        n = fctx.filenode()
-        fl = fctx.filelog()
-        parity = paritygen(self.stripecount)
-
-        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))
-            for lineno, ((f, targetline), l) in lines:
-                fnode = f.filenode()
-                name = self.repo.ui.shortuser(f.user())
-
-                if last != fnode:
-                    last = fnode
-
-                yield {"parity": parity.next(),
-                       "node": hex(f.node()),
-                       "rev": f.rev(),
-                       "author": name,
-                       "file": f.path(),
-                       "targetline": targetline,
-                       "line": l,
-                       "lineid": "l%d" % (lineno + 1),
-                       "linenumber": "% 6d" % (lineno + 1)}
-
-        return tmpl("fileannotate",
-                    file=f,
-                    annotate=annotate,
-                    path=_up(f),
-                    rev=fctx.rev(),
-                    node=hex(fctx.node()),
-                    author=fctx.user(),
-                    date=fctx.date(),
-                    desc=fctx.description(),
-                    rename=self.renamelink(fl, n),
-                    branch=self.nodebranchnodefault(fctx),
-                    parent=self.siblings(fctx.parents()),
-                    child=self.siblings(fctx.children()),
-                    permissions=fctx.manifest().flags(f))
-
-    def manifest(self, tmpl, ctx, path):
-        mf = ctx.manifest()
-        node = ctx.node()
-
-        files = {}
-        parity = paritygen(self.stripecount)
-
-        if path and path[-1] != "/":
-            path += "/"
-        l = len(path)
-        abspath = "/" + path
-
-        for f, n in mf.items():
-            if f[:l] != path:
-                continue
-            remain = f[l:]
-            if "/" in remain:
-                short = remain[:remain.index("/") + 1] # bleah
-                files[short] = (f, None)
-            else:
-                short = os.path.basename(remain)
-                files[short] = (f, n)
-
-        if not files:
-            raise ErrorResponse(HTTP_NOT_FOUND, 'path not found: ' + path)
-
-        def filelist(**map):
-            fl = files.keys()
-            fl.sort()
-            for f in fl:
-                full, fnode = files[f]
-                if not fnode:
-                    continue
-
-                fctx = ctx.filectx(full)
-                yield {"file": full,
-                       "parity": parity.next(),
-                       "basename": f,
-                       "date": fctx.changectx().date(),
-                       "size": fctx.size(),
-                       "permissions": mf.flags(full)}
-
-        def dirlist(**map):
-            fl = files.keys()
-            fl.sort()
-            for f in fl:
-                full, fnode = files[f]
-                if fnode:
-                    continue
-
-                yield {"parity": parity.next(),
-                       "path": "%s%s" % (abspath, f),
-                       "basename": f[:-1]}
-
-        return tmpl("manifest",
-                    rev=ctx.rev(),
-                    node=hex(node),
-                    path=abspath,
-                    up=_up(abspath),
-                    upparity=parity.next(),
-                    fentries=filelist,
-                    dentries=dirlist,
-                    archives=self.archivelist(hex(node)),
-                    tags=self.nodetagsdict(node),
-                    inbranch=self.nodeinbranch(ctx),
-                    branches=self.nodebranchdict(ctx))
-
-    def tags(self, tmpl):
-        i = self.repo.tagslist()
-        i.reverse()
-        parity = paritygen(self.stripecount)
-
-        def entries(notip=False,limit=0, **map):
-            count = 0
-            for k, n in i:
-                if notip and k == "tip":
-                    continue
-                if limit > 0 and count >= limit:
-                    continue
-                count = count + 1
-                yield {"parity": parity.next(),
-                       "tag": k,
-                       "date": self.repo.changectx(n).date(),
-                       "node": hex(n)}
-
-        return tmpl("tags",
-                    node=hex(self.repo.changelog.tip()),
-                    entries=lambda **x: entries(False,0, **x),
-                    entriesnotip=lambda **x: entries(True,0, **x),
-                    latestentry=lambda **x: entries(True,1, **x))
-
-    def summary(self, tmpl):
-        i = self.repo.tagslist()
-        i.reverse()
-
-        def tagentries(**map):
-            parity = paritygen(self.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(),
-                           tag=k,
-                           node=hex(n),
-                           date=self.repo.changectx(n).date())
-
-
-        def branches(**map):
-            parity = paritygen(self.stripecount)
-
-            b = self.repo.branchtags()
-            l = [(-self.repo.changelog.rev(n), n, t) for t, n in b.items()]
-            l.sort()
-
-            for r,n,t in l:
-                ctx = self.repo.changectx(n)
-
-                yield {'parity': parity.next(),
-                       'branch': t,
-                       'node': hex(n),
-                       'date': ctx.date()}
-
-        def changelist(**map):
-            parity = paritygen(self.stripecount, offset=start-end)
-            l = [] # build a list in forward order for efficiency
-            for i in xrange(start, end):
-                ctx = self.repo.changectx(i)
-                n = ctx.node()
-                hn = hex(n)
-
-                l.insert(0, tmpl(
-                   'shortlogentry',
-                    parity=parity.next(),
-                    author=ctx.user(),
-                    desc=ctx.description(),
-                    date=ctx.date(),
-                    rev=i,
-                    node=hn,
-                    tags=self.nodetagsdict(n),
-                    inbranch=self.nodeinbranch(ctx),
-                    branches=self.nodebranchdict(ctx)))
-
-            yield l
-
-        cl = self.repo.changelog
-        count = cl.count()
-        start = max(0, count - self.maxchanges)
-        end = min(count, start + self.maxchanges)
-
-        return tmpl("summary",
-                    desc=self.config("web", "description", "unknown"),
-                    owner=get_contact(self.config) or "unknown",
-                    lastchange=cl.read(cl.tip())[2],
-                    tags=tagentries,
-                    branches=branches,
-                    shortlog=changelist,
-                    node=hex(cl.tip()),
-                    archives=self.archivelist("tip"))
-
-    def filediff(self, tmpl, fctx):
-        n = fctx.node()
-        path = fctx.path()
-        parents = fctx.parents()
-        p1 = parents and parents[0].node() or nullid
-
-        def diff(**map):
-            yield self.diff(tmpl, p1, n, [path])
-
-        return tmpl("filediff",
-                    file=path,
-                    node=hex(n),
-                    rev=fctx.rev(),
-                    branch=self.nodebranchnodefault(fctx),
-                    parent=self.siblings(parents),
-                    child=self.siblings(fctx.children()),
-                    diff=diff)
-
     archive_specs = {
         'bz2': ('application/x-tar', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-tar', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
-    def archive(self, tmpl, req, key, type_):
-        reponame = re.sub(r"\W+", "-", os.path.basename(self.reponame))
-        cnode = self.repo.lookup(key)
-        arch_version = key
-        if cnode == key or key == 'tip':
-            arch_version = short(cnode)
-        name = "%s-%s" % (reponame, arch_version)
-        mimetype, artype, extension, encoding = self.archive_specs[type_]
-        headers = [
-            ('Content-Type', mimetype),
-            ('Content-Disposition', 'attachment; filename=%s%s' %
-                (name, extension))
-        ]
-        if encoding:
-            headers.append(('Content-Encoding', encoding))
-        req.header(headers)
-        req.respond(HTTP_OK)
-        archival.archive(self.repo, req, cnode, artype, prefix=name)
+    def check_perm(self, req, op):
+        '''Check permission for operation based on request data (including
+        authentication info. Return true if op allowed, else false.'''
 
-    # add tags to things
-    # tags -> list of changesets corresponding to tags
-    # find tag, changeset, file
+        def error(status, message):
+            req.respond(status, protocol.HGTYPE)
+            req.write('0\n%s\n' % message)
 
-    def cleanpath(self, path):
-        path = path.lstrip('/')
-        return util.canonpath(self.repo.root, '', path)
+        if op == 'pull':
+            return self.allowpull
 
-    def changectx(self, req):
-        if 'node' in req.form:
-            changeid = req.form['node'][0]
-        elif 'manifest' in req.form:
-            changeid = req.form['manifest'][0]
-        else:
-            changeid = self.repo.changelog.count() - 1
-
-        try:
-            ctx = self.repo.changectx(changeid)
-        except RepoError:
-            man = self.repo.manifest
-            mn = man.lookup(changeid)
-            ctx = self.repo.changectx(man.linkrev(mn))
-
-        return ctx
+        # enforce that you can only push using POST requests
+        if req.env['REQUEST_METHOD'] != 'POST':
+            error('405 Method Not Allowed', 'push requires POST request')
+            return False
 
-    def filectx(self, req):
-        path = self.cleanpath(req.form['file'][0])
-        if 'node' in req.form:
-            changeid = req.form['node'][0]
-        else:
-            changeid = req.form['filenode'][0]
-        try:
-            ctx = self.repo.changectx(changeid)
-            fctx = ctx.filectx(path)
-        except RepoError:
-            fctx = self.repo.filectx(path, fileid=changeid)
-
-        return fctx
-
-    def check_perm(self, req, op, default):
-        '''check permission for operation based on user auth.
-        return true if op allowed, else false.
-        default is policy to use if no config given.'''
+        # require ssl by default for pushing, auth info cannot be sniffed
+        # and replayed
+        scheme = req.env.get('wsgi.url_scheme')
+        if self.configbool('web', 'push_ssl', True) and scheme != 'https':
+            error(HTTP_OK, 'ssl required')
+            return False
 
         user = req.env.get('REMOTE_USER')
 
-        deny = self.configlist('web', 'deny_' + op)
+        deny = self.configlist('web', 'deny_push')
         if deny and (not user or deny == ['*'] or user in deny):
+            error('401 Unauthorized', 'push not authorized')
             return False
 
-        allow = self.configlist('web', 'allow_' + op)
-        return (allow and (allow == ['*'] or user in allow)) or default
+        allow = self.configlist('web', 'allow_push')
+        result = allow and (allow == ['*'] or user in allow)
+        if not result:
+            error('401 Unauthorized', 'push not authorized')
+
+        return result

mercurial/hgweb/hgwebdir_mod.py

@@ -6,7 +6,7 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-import os, mimetools, cStringIO
+import os
 from mercurial.i18n import gettext as _
 from mercurial.repo import RepoError
 from mercurial import ui, hg, util, templater, templatefilters
@@ -19,8 +19,8 b' from request import wsgirequest'
 class hgwebdir(object):
     def __init__(self, config, parentui=None):
         def cleannames(items):
-            return [(util.pconvert(name).strip('/'), path)
-                    for name, path in items]
+            return util.sort([(util.pconvert(name).strip('/'), path)
+                              for name, path in items])
 
         self.parentui = parentui or ui.ui(report_untrusted=False,
                                           interactive = False)
@@ -34,7 +34,6 b' class hgwebdir(object):'
             self.repos_sorted = ('', False)
         elif isinstance(config, dict):
             self.repos = cleannames(config.items())
-            self.repos.sort()
         else:
             if isinstance(config, util.configparser):
                 cp = config
@@ -71,8 +70,7 b' class hgwebdir(object):'
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
-        self.run_wsgi(req)
-        return req
+        return self.run_wsgi(req)
 
     def run_wsgi(self, req):
 
@@ -81,17 +79,8 b' class hgwebdir(object):'
 
                 virtual = req.env.get("PATH_INFO", "").strip('/')
                 tmpl = self.templater(req)
-                try:
-                    ctype = tmpl('mimetype', encoding=util._encoding)
-                    ctype = templater.stringify(ctype)
-                except KeyError:
-                    # old templates with inline HTTP headers?
-                    if 'mimetype' in tmpl:
-                        raise
-                    header = tmpl('header', encoding=util._encoding)
-                    header_file = cStringIO.StringIO(templater.stringify(header))
-                    msg = mimetools.Message(header_file, 0)
-                    ctype = msg['content-type']
+                ctype = tmpl('mimetype', encoding=util._encoding)
+                ctype = templater.stringify(ctype)
 
                 # a static file
                 if virtual.startswith('static/') or 'static' in req.form:
@@ -101,13 +90,13 b' class hgwebdir(object):'
                     else:
                         fname = req.form['static'][0]
                     req.write(staticfile(static, fname, req))
-                    return
+                    return []
 
                 # top-level index
                 elif not virtual:
                     req.respond(HTTP_OK, ctype)
                     req.write(self.makeindex(req, tmpl))
-                    return
+                    return []
 
                 # nested indexes and hgwebs
 
@@ -118,8 +107,7 b' class hgwebdir(object):'
                         req.env['REPO_NAME'] = virtual
                         try:
                             repo = hg.repository(self.parentui, real)
-                            hgweb(repo).run_wsgi(req)
-                            return
+                            return hgweb(repo).run_wsgi(req)
                         except IOError, inst:
                             msg = inst.strerror
                             raise ErrorResponse(HTTP_SERVER_ERROR, msg)
@@ -131,7 +119,7 b' class hgwebdir(object):'
                     if [r for r in repos if r.startswith(subdir)]:
                         req.respond(HTTP_OK, ctype)
                         req.write(self.makeindex(req, tmpl, subdir))
-                        return
+                        return []
 
                     up = virtual.rfind('/')
                     if up < 0:
@@ -141,10 +129,12 b' class hgwebdir(object):'
                 # prefixes not found
                 req.respond(HTTP_NOT_FOUND, ctype)
                 req.write(tmpl("notfound", repo=virtual))
+                return []
 
             except ErrorResponse, err:
                 req.respond(err.code, ctype)
                 req.write(tmpl('error', error=err.message or ''))
+                return []
         finally:
             tmpl = None
 
@@ -257,13 +247,7 b' class hgwebdir(object):'
     def templater(self, req):
 
         def header(**map):
-            header = tmpl('header', encoding=util._encoding, **map)
-            if 'mimetype' not in tmpl:
-                # old template with inline HTTP headers
-                header_file = cStringIO.StringIO(templater.stringify(header))
-                msg = mimetools.Message(header_file, 0)
-                header = header_file.read()
-            yield header
+            yield tmpl('header', encoding=util._encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)

mercurial/hgweb/protocol.py

@@ -21,69 +21,65 b' from common import HTTP_OK, HTTP_NOT_FOU'
 
 HGTYPE = 'application/mercurial-0.1'
 
-def lookup(web, req):
+def lookup(repo, req):
     try:
-        r = hex(web.repo.lookup(req.form['key'][0]))
+        r = hex(repo.lookup(req.form['key'][0]))
         success = 1
     except Exception,inst:
         r = str(inst)
         success = 0
     resp = "%s %s\n" % (success, r)
     req.respond(HTTP_OK, HGTYPE, length=len(resp))
-    req.write(resp)
+    yield resp
 
-def heads(web, req):
-    resp = " ".join(map(hex, web.repo.heads())) + "\n"
+def heads(repo, req):
+    resp = " ".join(map(hex, repo.heads())) + "\n"
     req.respond(HTTP_OK, HGTYPE, length=len(resp))
-    req.write(resp)
+    yield resp
 
-def branches(web, req):
+def branches(repo, req):
     nodes = []
     if 'nodes' in req.form:
         nodes = map(bin, req.form['nodes'][0].split(" "))
     resp = cStringIO.StringIO()
-    for b in web.repo.branches(nodes):
+    for b in repo.branches(nodes):
         resp.write(" ".join(map(hex, b)) + "\n")
     resp = resp.getvalue()
     req.respond(HTTP_OK, HGTYPE, length=len(resp))
-    req.write(resp)
+    yield resp
 
-def between(web, req):
+def between(repo, req):
     if 'pairs' in req.form:
         pairs = [map(bin, p.split("-"))
                  for p in req.form['pairs'][0].split(" ")]
     resp = cStringIO.StringIO()
-    for b in web.repo.between(pairs):
+    for b in repo.between(pairs):
         resp.write(" ".join(map(hex, b)) + "\n")
     resp = resp.getvalue()
     req.respond(HTTP_OK, HGTYPE, length=len(resp))
-    req.write(resp)
+    yield resp
 
-def changegroup(web, req):
+def changegroup(repo, req):
     req.respond(HTTP_OK, HGTYPE)
     nodes = []
-    if not web.allowpull:
-        return
 
     if 'roots' in req.form:
         nodes = map(bin, req.form['roots'][0].split(" "))
 
     z = zlib.compressobj()
-    f = web.repo.changegroup(nodes, 'serve')
+    f = repo.changegroup(nodes, 'serve')
     while 1:
         chunk = f.read(4096)
         if not chunk:
             break
-        req.write(z.compress(chunk))
+        yield z.compress(chunk)
 
-    req.write(z.flush())
+    yield z.flush()
 
-def changegroupsubset(web, req):
+def changegroupsubset(repo, req):
     req.respond(HTTP_OK, HGTYPE)
     bases = []
     heads = []
-    if not web.allowpull:
-        return
 
     if 'bases' in req.form:
         bases = [bin(x) for x in req.form['bases'][0].split(' ')]
@@ -91,67 +87,44 b' def changegroupsubset(web, req):'
         heads = [bin(x) for x in req.form['heads'][0].split(' ')]
 
     z = zlib.compressobj()
-    f = web.repo.changegroupsubset(bases, heads, 'serve')
+    f = repo.changegroupsubset(bases, heads, 'serve')
     while 1:
         chunk = f.read(4096)
         if not chunk:
             break
-        req.write(z.compress(chunk))
+        yield z.compress(chunk)
 
-    req.write(z.flush())
+    yield z.flush()
 
-def capabilities(web, req):
-    resp = ' '.join(web.capabilities())
-    req.respond(HTTP_OK, HGTYPE, length=len(resp))
-    req.write(resp)
+def capabilities(repo, req):
+    caps = ['lookup', 'changegroupsubset']
+    if repo.ui.configbool('server', 'uncompressed', untrusted=True):
+        caps.append('stream=%d' % repo.changelog.version)
+    if changegroupmod.bundlepriority:
+        caps.append('unbundle=%s' % ','.join(changegroupmod.bundlepriority))
+    rsp = ' '.join(caps)
+    req.respond(HTTP_OK, HGTYPE, length=len(rsp))
+    yield rsp
 
-def unbundle(web, req):
+def unbundle(repo, req):
+
+    errorfmt = '0\n%s\n'
+    proto = req.env.get('wsgi.url_scheme') or 'http'
+    their_heads = req.form['heads'][0].split(' ')
 
-    def bail(response, headers={}):
+    def check_heads():
+        heads = map(hex, repo.heads())
+        return their_heads == [hex('force')] or their_heads == heads
+
+    # fail early if possible
+    if not check_heads():
         length = int(req.env.get('CONTENT_LENGTH', 0))
         for s in util.filechunkiter(req, limit=length):
             # drain incoming bundle, else client will not see
             # response when run outside cgi script
             pass
-
-        status = headers.pop('status', HTTP_OK)
-        req.header(headers.items())
-        req.respond(status, HGTYPE)
-        req.write('0\n')
-        req.write(response)
-
-    # enforce that you can only unbundle with POST requests
-    if req.env['REQUEST_METHOD'] != 'POST':
-        headers = {'status': '405 Method Not Allowed'}
-        bail('unbundle requires POST request\n', headers)
-        return
-
-    # require ssl by default, auth info cannot be sniffed and
-    # replayed
-    ssl_req = web.configbool('web', 'push_ssl', True)
-    if ssl_req:
-        if req.env.get('wsgi.url_scheme') != 'https':
-            bail('ssl required\n')
-            return
-        proto = 'https'
-    else:
-        proto = 'http'
-
-    # do not allow push unless explicitly allowed
-    if not web.check_perm(req, 'push', False):
-        bail('push not authorized\n', headers={'status': '401 Unauthorized'})
-        return
-
-    their_heads = req.form['heads'][0].split(' ')
-
-    def check_heads():
-        heads = map(hex, web.repo.heads())
-        return their_heads == [hex('force')] or their_heads == heads
-
-    # fail early if possible
-    if not check_heads():
-        bail('unsynced changes\n')
-        return
+        req.respond(HTTP_OK, HGTYPE)
+        return errorfmt % 'unsynced changes',
 
     req.respond(HTTP_OK, HGTYPE)
 
@@ -166,12 +139,10 b' def unbundle(web, req):'
             fp.write(s)
 
         try:
-            lock = web.repo.lock()
+            lock = repo.lock()
             try:
                 if not check_heads():
-                    req.write('0\n')
-                    req.write('unsynced changes\n')
-                    return
+                    return errorfmt % 'unsynced changes',
 
                 fp.seek(0)
                 header = fp.read(6)
@@ -190,26 +161,23 b' def unbundle(web, req):'
                     url = 'remote:%s:%s' % (proto,
                                             req.env.get('REMOTE_HOST', ''))
                     try:
-                        ret = web.repo.addchangegroup(gen, 'serve', url)
+                        ret = repo.addchangegroup(gen, 'serve', url)
                     except util.Abort, inst:
                         sys.stdout.write("abort: %s\n" % inst)
                         ret = 0
                 finally:
                     val = sys.stdout.getvalue()
                     sys.stdout, sys.stderr = oldio
-                req.write('%d\n' % ret)
-                req.write(val)
+                return '%d\n%s' % (ret, val),
             finally:
                 del lock
         except ValueError, inst:
-            req.write('0\n')
-            req.write(str(inst) + '\n')
+            return errorfmt % inst,
         except (OSError, IOError), inst:
-            req.write('0\n')
             filename = getattr(inst, 'filename', '')
             # Don't send our filesystem layout to the client
-            if filename.startswith(web.repo.root):
-                filename = filename[len(web.repo.root)+1:]
+            if filename.startswith(repo.root):
+                filename = filename[len(repo.root)+1:]
             else:
                 filename = ''
             error = getattr(inst, 'strerror', 'Unknown error')
@@ -218,13 +186,12 b' def unbundle(web, req):'
             else:
                 code = HTTP_SERVER_ERROR
             req.respond(code)
-            req.write('%s: %s\n' % (error, filename))
+            return '0\n%s: %s\n' % (error, filename),
     finally:
         fp.close()
         os.unlink(tempname)
 
-def stream_out(web, req):
-    if not web.allowpull:
-        return
+def stream_out(repo, req):
     req.respond(HTTP_OK, HGTYPE)
-    streamclone.stream_out(web.repo, req, untrusted=True)
+    streamclone.stream_out(repo, req, untrusted=True)
+    return []

mercurial/hgweb/request.py

@@ -9,6 +9,31 b''
 import socket, cgi, errno
 from common import ErrorResponse, statusmessage
 
+shortcuts = {
+    'cl': [('cmd', ['changelog']), ('rev', None)],
+    'sl': [('cmd', ['shortlog']), ('rev', None)],
+    'cs': [('cmd', ['changeset']), ('node', None)],
+    'f': [('cmd', ['file']), ('filenode', None)],
+    'fl': [('cmd', ['filelog']), ('filenode', None)],
+    'fd': [('cmd', ['filediff']), ('node', None)],
+    'fa': [('cmd', ['annotate']), ('filenode', None)],
+    'mf': [('cmd', ['manifest']), ('manifest', None)],
+    'ca': [('cmd', ['archive']), ('node', None)],
+    'tags': [('cmd', ['tags'])],
+    'tip': [('cmd', ['changeset']), ('node', ['tip'])],
+    'static': [('cmd', ['static']), ('file', None)]
+}
+
+def expand(form):
+    for k in shortcuts.iterkeys():
+        if k in form:
+            for name, value in shortcuts[k]:
+                if value is None:
+                    value = form[k]
+                form[name] = value
+            del form[k]
+    return form
+
 class wsgirequest(object):
     def __init__(self, wsgienv, start_response):
         version = wsgienv['wsgi.version']
@@ -21,7 +46,7 b' class wsgirequest(object):'
         self.multiprocess = wsgienv['wsgi.multiprocess']
         self.run_once = wsgienv['wsgi.run_once']
         self.env = wsgienv
-        self.form = cgi.parse(self.inp, self.env, keep_blank_values=1)
+        self.form = expand(cgi.parse(self.inp, self.env, keep_blank_values=1))
         self._start_response = start_response
         self.server_write = None
         self.headers = []

mercurial/hgweb/server.py

@@ -122,7 +122,8 b' class _hgwebhandler(object, BaseHTTPServ'
         self.saved_headers = []
         self.sent_headers = False
         self.length = None
-        self.server.application(env, self._start_response)
+        for chunk in self.server.application(env, self._start_response):
+            self._write(chunk)
 
     def send_headers(self):
         if not self.saved_status:
@@ -268,12 +269,7 b' def create_server(ui, repo):'
 
             self.addr, self.port = self.socket.getsockname()[0:2]
             self.prefix = prefix
-
             self.fqaddr = socket.getfqdn(address)
-            try:
-                socket.getaddrbyhost(self.fqaddr)
-            except:
-                fqaddr = address
 
     class IPv6HTTPServer(MercurialHTTPServer):
         address_family = getattr(socket, 'AF_INET6', None)

mercurial/hgweb/webcommands.py

@@ -5,10 +5,15 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-import os, mimetypes
-from mercurial import revlog, util
+import os, mimetypes, re, cgi
+import webutil
+from mercurial import revlog, archival, templatefilters
+from mercurial.node import short, hex, nullid
+from mercurial.util import binary, datestr
 from mercurial.repo import RepoError
-from common import staticfile, ErrorResponse, HTTP_OK, HTTP_NOT_FOUND
+from common import paritygen, staticfile, get_contact, ErrorResponse
+from common import HTTP_OK, HTTP_NOT_FOUND
+from mercurial import graphmod, util
 
 # __all__ is populated with the allowed commands. Be sure to add to it if
 # you're adding a new command, or the new command won't work.
@@ -16,7 +21,7 b' from common import staticfile, ErrorResp'
 __all__ = [
    'log', 'rawfile', 'file', 'changelog', 'shortlog', 'changeset', 'rev',
    'manifest', 'tags', 'summary', 'filediff', 'diff', 'annotate', 'filelog',
-   'archive', 'static',
+   'archive', 'static', 'graph',
 ]
 
 def log(web, req, tmpl):
@@ -26,17 +31,17 b' def log(web, req, tmpl):'
         return changelog(web, req, tmpl)
 
 def rawfile(web, req, tmpl):
-    path = web.cleanpath(req.form.get('file', [''])[0])
+    path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
-        content = web.manifest(tmpl, web.changectx(req), path)
+        content = manifest(web, req, tmpl)
         req.respond(HTTP_OK, web.ctype)
         return content
 
     try:
-        fctx = web.filectx(req)
+        fctx = webutil.filectx(web.repo, req)
     except revlog.LookupError, inst:
         try:
-            content = web.manifest(tmpl, web.changectx(req), path)
+            content = manifest(web, req, tmpl)
             req.respond(HTTP_OK, web.ctype)
             return content
         except ErrorResponse:
@@ -45,76 +50,514 b' def rawfile(web, req, tmpl):'
     path = fctx.path()
     text = fctx.data()
     mt = mimetypes.guess_type(path)[0]
-    if mt is None or util.binary(text):
+    if mt is None or binary(text):
         mt = mt or 'application/octet-stream'
 
     req.respond(HTTP_OK, mt, path, len(text))
     return [text]
 
+def _filerevision(web, tmpl, fctx):
+    f = fctx.path()
+    text = fctx.data()
+    fl = fctx.filelog()
+    n = fctx.filenode()
+    parity = paritygen(web.stripecount)
+
+    if 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(1)):
+            yield {"line": t,
+                   "lineid": "l%d" % (lineno + 1),
+                   "linenumber": "% 6d" % (lineno + 1),
+                   "parity": parity.next()}
+
+    return tmpl("filerevision",
+                file=f,
+                path=webutil.up(f),
+                text=lines(),
+                rev=fctx.rev(),
+                node=hex(fctx.node()),
+                author=fctx.user(),
+                date=fctx.date(),
+                desc=fctx.description(),
+                branch=webutil.nodebranchnodefault(fctx),
+                parent=webutil.siblings(fctx.parents()),
+                child=webutil.siblings(fctx.children()),
+                rename=webutil.renamelink(fctx),
+                permissions=fctx.manifest().flags(f))
+
 def file(web, req, tmpl):
-    path = web.cleanpath(req.form.get('file', [''])[0])
+    path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
-        return web.manifest(tmpl, web.changectx(req), path)
+        return manifest(web, req, tmpl)
     try:
-        return web.filerevision(tmpl, web.filectx(req))
+        return _filerevision(web, tmpl, webutil.filectx(web.repo, req))
     except revlog.LookupError, inst:
         try:
-            return web.manifest(tmpl, web.changectx(req), path)
+            return manifest(web, req, tmpl)
         except ErrorResponse:
             raise inst
 
+def _search(web, tmpl, query):
+
+    def changelist(**map):
+        cl = web.repo.changelog
+        count = 0
+        qw = query.lower().split()
+
+        def revgen():
+            for i in xrange(len(cl) - 1, 0, -100):
+                l = []
+                for j in xrange(max(0, i - 100), i + 1):
+                    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 ctx.user().lower() or
+                        q in ctx.description().lower() or
+                        q in " ".join(ctx.files()).lower()):
+                    miss = 1
+                    break
+            if miss:
+                continue
+
+            count += 1
+            n = ctx.node()
+            showtags = webutil.showtag(web.repo, tmpl, 'changelogtag', n)
+
+            yield tmpl('searchentry',
+                       parity=parity.next(),
+                       author=ctx.user(),
+                       parent=webutil.siblings(ctx.parents()),
+                       child=webutil.siblings(ctx.children()),
+                       changelogtag=showtags,
+                       desc=ctx.description(),
+                       date=ctx.date(),
+                       files=web.listfilediffs(tmpl, ctx.files(), n),
+                       rev=ctx.rev(),
+                       node=hex(n),
+                       tags=webutil.nodetagsdict(web.repo, n),
+                       inbranch=webutil.nodeinbranch(web.repo, ctx),
+                       branches=webutil.nodebranchdict(web.repo, ctx))
+
+            if count >= web.maxchanges:
+                break
+
+    cl = web.repo.changelog
+    parity = paritygen(web.stripecount)
+
+    return tmpl('search',
+                query=query,
+                node=hex(cl.tip()),
+                entries=changelist,
+                archives=web.archivelist("tip"))
+
 def changelog(web, req, tmpl, shortlog = False):
     if 'node' in req.form:
-        ctx = web.changectx(req)
+        ctx = webutil.changectx(web.repo, req)
     else:
         if 'rev' in req.form:
             hi = req.form['rev'][0]
         else:
-            hi = web.repo.changelog.count() - 1
+            hi = len(web.repo) - 1
         try:
-            ctx = web.repo.changectx(hi)
+            ctx = web.repo[hi]
         except RepoError:
-            return web.search(tmpl, hi) # XXX redirect to 404 page?
+            return _search(web, tmpl, hi) # XXX redirect to 404 page?
+
+    def changelist(limit=0, **map):
+        cl = web.repo.changelog
+        l = [] # build a list in forward order for efficiency
+        for i in xrange(start, end):
+            ctx = web.repo[i]
+            n = ctx.node()
+            showtags = webutil.showtag(web.repo, tmpl, 'changelogtag', n)
+
+            l.insert(0, {"parity": parity.next(),
+                         "author": ctx.user(),
+                         "parent": webutil.siblings(ctx.parents(), i - 1),
+                         "child": webutil.siblings(ctx.children(), i + 1),
+                         "changelogtag": showtags,
+                         "desc": ctx.description(),
+                         "date": ctx.date(),
+                         "files": web.listfilediffs(tmpl, ctx.files(), n),
+                         "rev": i,
+                         "node": hex(n),
+                         "tags": webutil.nodetagsdict(web.repo, n),
+                         "inbranch": webutil.nodeinbranch(web.repo, ctx),
+                         "branches": webutil.nodebranchdict(web.repo, ctx)
+                        })
 
-    return web.changelog(tmpl, ctx, shortlog = shortlog)
+        if limit > 0:
+            l = l[:limit]
+
+        for e in l:
+            yield e
+
+    maxchanges = shortlog and web.maxshortchanges or web.maxchanges
+    cl = web.repo.changelog
+    count = len(cl)
+    pos = ctx.rev()
+    start = max(0, pos - maxchanges + 1)
+    end = min(count, start + maxchanges)
+    pos = end - 1
+    parity = paritygen(web.stripecount, offset=start-end)
+
+    changenav = webutil.revnavgen(pos, maxchanges, count, web.repo.changectx)
+
+    return tmpl(shortlog and 'shortlog' or 'changelog',
+                changenav=changenav,
+                node=hex(ctx.node()),
+                rev=pos, changesets=count,
+                entries=lambda **x: changelist(limit=0,**x),
+                latestentry=lambda **x: changelist(limit=1,**x),
+                archives=web.archivelist("tip"))
 
 def shortlog(web, req, tmpl):
     return changelog(web, req, tmpl, shortlog = True)
 
 def changeset(web, req, tmpl):
-    return web.changeset(tmpl, web.changectx(req))
+    ctx = webutil.changectx(web.repo, req)
+    n = ctx.node()
+    showtags = webutil.showtag(web.repo, tmpl, 'changesettag', n)
+    parents = ctx.parents()
+    p1 = parents[0].node()
+
+    files = []
+    parity = paritygen(web.stripecount)
+    for f in ctx.files():
+        files.append(tmpl("filenodelink",
+                          node=hex(n), file=f,
+                          parity=parity.next()))
+
+    diffs = web.diff(tmpl, p1, n, None)
+    return tmpl('changeset',
+                diff=diffs,
+                rev=ctx.rev(),
+                node=hex(n),
+                parent=webutil.siblings(parents),
+                child=webutil.siblings(ctx.children()),
+                changesettag=showtags,
+                author=ctx.user(),
+                desc=ctx.description(),
+                date=ctx.date(),
+                files=files,
+                archives=web.archivelist(hex(n)),
+                tags=webutil.nodetagsdict(web.repo, n),
+                branch=webutil.nodebranchnodefault(ctx),
+                inbranch=webutil.nodeinbranch(web.repo, ctx),
+                branches=webutil.nodebranchdict(web.repo, ctx))
 
 rev = changeset
 
 def manifest(web, req, tmpl):
-    return web.manifest(tmpl, web.changectx(req),
-                        web.cleanpath(req.form['path'][0]))
+    ctx = webutil.changectx(web.repo, req)
+    path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
+    mf = ctx.manifest()
+    node = ctx.node()
+
+    files = {}
+    parity = paritygen(web.stripecount)
+
+    if path and path[-1] != "/":
+        path += "/"
+    l = len(path)
+    abspath = "/" + path
+
+    for f, n in mf.items():
+        if f[:l] != path:
+            continue
+        remain = f[l:]
+        if "/" in remain:
+            short = remain[:remain.index("/") + 1] # bleah
+            files[short] = (f, None)
+        else:
+            short = os.path.basename(remain)
+            files[short] = (f, n)
+
+    if not files:
+        raise ErrorResponse(HTTP_NOT_FOUND, 'path not found: ' + path)
+
+    def filelist(**map):
+        for f in util.sort(files):
+            full, fnode = files[f]
+            if not fnode:
+                continue
+
+            fctx = ctx.filectx(full)
+            yield {"file": full,
+                   "parity": parity.next(),
+                   "basename": f,
+                   "date": fctx.date(),
+                   "size": fctx.size(),
+                   "permissions": mf.flags(full)}
+
+    def dirlist(**map):
+        for f in util.sort(files):
+            full, fnode = files[f]
+            if fnode:
+                continue
+
+            yield {"parity": parity.next(),
+                   "path": "%s%s" % (abspath, f),
+                   "basename": f[:-1]}
+
+    return tmpl("manifest",
+                rev=ctx.rev(),
+                node=hex(node),
+                path=abspath,
+                up=webutil.up(abspath),
+                upparity=parity.next(),
+                fentries=filelist,
+                dentries=dirlist,
+                archives=web.archivelist(hex(node)),
+                tags=webutil.nodetagsdict(web.repo, node),
+                inbranch=webutil.nodeinbranch(web.repo, ctx),
+                branches=webutil.nodebranchdict(web.repo, ctx))
 
 def tags(web, req, tmpl):
-    return web.tags(tmpl)
+    i = web.repo.tagslist()
+    i.reverse()
+    parity = paritygen(web.stripecount)
+
+    def entries(notip=False,limit=0, **map):
+        count = 0
+        for k, n in i:
+            if notip and k == "tip":
+                continue
+            if limit > 0 and count >= limit:
+                continue
+            count = count + 1
+            yield {"parity": parity.next(),
+                   "tag": k,
+                   "date": web.repo[n].date(),
+                   "node": hex(n)}
+
+    return tmpl("tags",
+                node=hex(web.repo.changelog.tip()),
+                entries=lambda **x: entries(False,0, **x),
+                entriesnotip=lambda **x: entries(True,0, **x),
+                latestentry=lambda **x: entries(True,1, **x))
 
 def summary(web, req, tmpl):
-    return web.summary(tmpl)
+    i = web.repo.tagslist()
+    i.reverse()
+
+    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(),
+                       tag=k,
+                       node=hex(n),
+                       date=web.repo[n].date())
+
+    def branches(**map):
+        parity = paritygen(web.stripecount)
+
+        b = web.repo.branchtags()
+        l = [(-web.repo.changelog.rev(n), n, t) for t, n in b.items()]
+        for r,n,t in util.sort(l):
+            yield {'parity': parity.next(),
+                   'branch': t,
+                   'node': hex(n),
+                   'date': web.repo[n].date()}
+
+    def changelist(**map):
+        parity = paritygen(web.stripecount, offset=start-end)
+        l = [] # build a list in forward order for efficiency
+        for i in xrange(start, end):
+            ctx = web.repo[i]
+            n = ctx.node()
+            hn = hex(n)
+
+            l.insert(0, tmpl(
+               'shortlogentry',
+                parity=parity.next(),
+                author=ctx.user(),
+                desc=ctx.description(),
+                date=ctx.date(),
+                rev=i,
+                node=hn,
+                tags=webutil.nodetagsdict(web.repo, n),
+                inbranch=webutil.nodeinbranch(web.repo, ctx),
+                branches=webutil.nodebranchdict(web.repo, ctx)))
+
+        yield l
+
+    cl = web.repo.changelog
+    count = len(cl)
+    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=cl.read(cl.tip())[2],
+                tags=tagentries,
+                branches=branches,
+                shortlog=changelist,
+                node=hex(cl.tip()),
+                archives=web.archivelist("tip"))
 
 def filediff(web, req, tmpl):
-    return web.filediff(tmpl, web.filectx(req))
+    fctx = webutil.filectx(web.repo, req)
+    n = fctx.node()
+    path = fctx.path()
+    parents = fctx.parents()
+    p1 = parents and parents[0].node() or nullid
+
+    diffs = web.diff(tmpl, p1, n, [path])
+    return tmpl("filediff",
+                file=path,
+                node=hex(n),
+                rev=fctx.rev(),
+                date=fctx.date(),
+                desc=fctx.description(),
+                author=fctx.user(),
+                rename=webutil.renamelink(fctx),
+                branch=webutil.nodebranchnodefault(fctx),
+                parent=webutil.siblings(parents),
+                child=webutil.siblings(fctx.children()),
+                diff=diffs)
 
 diff = filediff
 
 def annotate(web, req, tmpl):
-    return web.fileannotate(tmpl, web.filectx(req))
+    fctx = webutil.filectx(web.repo, req)
+    f = fctx.path()
+    n = fctx.filenode()
+    fl = fctx.filelog()
+    parity = paritygen(web.stripecount)
+
+    def annotate(**map):
+        last = None
+        if 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))
+        for lineno, ((f, targetline), l) in lines:
+            fnode = f.filenode()
+
+            if last != fnode:
+                last = fnode
+
+            yield {"parity": parity.next(),
+                   "node": hex(f.node()),
+                   "rev": f.rev(),
+                   "author": f.user(),
+                   "desc": f.description(),
+                   "file": f.path(),
+                   "targetline": targetline,
+                   "line": l,
+                   "lineid": "l%d" % (lineno + 1),
+                   "linenumber": "% 6d" % (lineno + 1)}
+
+    return tmpl("fileannotate",
+                file=f,
+                annotate=annotate,
+                path=webutil.up(f),
+                rev=fctx.rev(),
+                node=hex(fctx.node()),
+                author=fctx.user(),
+                date=fctx.date(),
+                desc=fctx.description(),
+                rename=webutil.renamelink(fctx),
+                branch=webutil.nodebranchnodefault(fctx),
+                parent=webutil.siblings(fctx.parents()),
+                child=webutil.siblings(fctx.children()),
+                permissions=fctx.manifest().flags(f))
 
 def filelog(web, req, tmpl):
-    return web.filelog(tmpl, web.filectx(req))
+    fctx = webutil.filectx(web.repo, req)
+    f = fctx.path()
+    fl = fctx.filelog()
+    count = len(fl)
+    pagelen = web.maxshortchanges
+    pos = fctx.filerev()
+    start = max(0, pos - pagelen + 1)
+    end = min(count, start + pagelen)
+    pos = end - 1
+    parity = paritygen(web.stripecount, offset=start-end)
+
+    def entries(limit=0, **map):
+        l = []
+
+        for i in xrange(start, end):
+            ctx = fctx.filectx(i)
+            n = fl.node(i)
+
+            l.insert(0, {"parity": parity.next(),
+                         "filerev": i,
+                         "file": f,
+                         "node": hex(ctx.node()),
+                         "author": ctx.user(),
+                         "date": ctx.date(),
+                         "rename": webutil.renamelink(fctx),
+                         "parent": webutil.siblings(fctx.parents()),
+                         "child": webutil.siblings(fctx.children()),
+                         "desc": ctx.description()})
+
+        if limit > 0:
+            l = l[:limit]
+
+        for e in l:
+            yield e
+
+    nodefunc = lambda x: fctx.filectx(fileid=x)
+    nav = webutil.revnavgen(pos, pagelen, count, nodefunc)
+    return tmpl("filelog", file=f, node=hex(fctx.node()), nav=nav,
+                entries=lambda **x: entries(limit=0, **x),
+                latestentry=lambda **x: entries(limit=1, **x))
+
 
 def archive(web, req, tmpl):
     type_ = req.form.get('type', [None])[0]
     allowed = web.configlist("web", "allow_archive")
-    if (type_ in web.archives and (type_ in allowed or
+    key = req.form['node'][0]
+
+    if not (type_ in web.archives and (type_ in allowed or
         web.configbool("web", "allow" + type_, False))):
-        web.archive(tmpl, req, req.form['node'][0], type_)
-        return []
-    raise ErrorResponse(HTTP_NOT_FOUND, 'unsupported archive type: %s' % type_)
+        msg = 'Unsupported archive type: %s' % type_
+        raise ErrorResponse(HTTP_NOT_FOUND, 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)
+    mimetype, artype, extension, encoding = web.archive_specs[type_]
+    headers = [
+        ('Content-Type', mimetype),
+        ('Content-Disposition', 'attachment; filename=%s%s' % (name, extension))
+    ]
+    if encoding:
+        headers.append(('Content-Encoding', encoding))
+    req.header(headers)
+    req.respond(HTTP_OK)
+    archival.archive(web.repo, req, cnode, artype, prefix=name)
+    return []
+
 
 def static(web, req, tmpl):
     fname = req.form['file'][0]
@@ -124,3 +567,39 b' def static(web, req, tmpl):'
                         os.path.join(web.templatepath, "static"),
                         untrusted=False)
     return [staticfile(static, fname, req)]
+
+def graph(web, req, tmpl):
+    rev = webutil.changectx(web.repo, req).rev()
+    bg_height = 39
+
+    max_rev = len(web.repo) - 1
+    revcount = min(max_rev, int(req.form.get('revcount', [25])[0]))
+    revnode = web.repo.changelog.node(rev)
+    revnode_hex = hex(revnode)
+    uprev = min(max_rev, rev + revcount)
+    downrev = max(0, rev - revcount)
+    lessrev = max(0, rev - revcount / 2)
+
+    maxchanges = web.maxshortchanges or web.maxchanges
+    count = len(web.repo)
+    changenav = webutil.revnavgen(rev, maxchanges, count, web.repo.changectx)
+
+    tree = list(graphmod.graph(web.repo, rev, rev - revcount))
+    canvasheight = (len(tree) + 1) * bg_height - 27;
+
+    data = []
+    for i, (ctx, vtx, edges) in enumerate(tree):
+        node = short(ctx.node())
+        age = templatefilters.age(ctx.date())
+        desc = templatefilters.firstline(ctx.description())
+        desc = cgi.escape(desc)
+        user = cgi.escape(templatefilters.person(ctx.user()))
+        branch = ctx.branch()
+        branch = branch, web.repo.branchtags().get(branch) == ctx.node()
+        data.append((node, vtx, edges, desc, user, age, branch, ctx.tags()))
+
+    return tmpl('graph', rev=rev, revcount=revcount, uprev=uprev,
+                lessrev=lessrev, revcountmore=revcount and 2 * revcount or 1,
+                revcountless=revcount / 2, downrev=downrev,
+                canvasheight=canvasheight, bg_height=bg_height,
+                jsdata=data, node=revnode_hex, changenav=changenav)

mercurial/hook.py

@@ -96,10 +96,9 b' def hook(ui, repo, name, throw=False, **'
         oldstdout = os.dup(sys.__stdout__.fileno())
         os.dup2(sys.__stderr__.fileno(), sys.__stdout__.fileno())
 
-    hooks = [(hname, cmd) for hname, cmd in ui.configitems("hooks")
-             if hname.split(".", 1)[0] == name and cmd]
-    hooks.sort()
-    for hname, cmd in hooks:
+    for hname, cmd in util.sort(ui.configitems('hooks')):
+        if hname.split('.')[0] != name or not cmd:
+            continue
         if callable(cmd):
             r = _pythonhook(ui, repo, name, hname, cmd, args, throw) or r
         elif cmd.startswith('python:'):

mercurial/httprepo.py

@@ -268,6 +268,7 b' class httprepository(repo.repository):'
 
         # 1.0 here is the _protocol_ version
         opener.addheaders = [('User-agent', 'mercurial/proto-1.0')]
+        opener.addheaders.append(('Accept', 'application/mercurial-0.1'))
         urllib2.install_opener(opener)
 
     def url(self):

mercurial/keepalive.py

@@ -19,6 +19,8 b''
 
 # Modified by Benoit Boissinot:
 #  - fix for digest auth (inspired from urllib2.py @ Python v2.4)
+# Modified by Dirkjan Ochtman:
+#  - import md5 function from a local util module
 
 """An HTTP handler for urllib2 that supports HTTP 1.1 and keepalive.
 
@@ -450,7 +452,7 b' def error_handler(url):'
     keepalive_handler.close_all()
 
 def continuity(url):
-    import md5
+    from util import md5
     format = '%25s: %s'
 
     # first fetch the file with the normal http handler

mercurial/localrepo.py

@@ -9,8 +9,9 b' from node import bin, hex, nullid, nullr'
 from i18n import _
 import repo, changegroup
 import changelog, dirstate, filelog, manifest, context, weakref
-import lock, transaction, stat, errno, ui
+import lock, transaction, stat, errno, ui, store
 import os, revlog, time, util, extensions, hook, inspect
+import match as match_
 
 class localrepository(repo.repository):
     capabilities = util.set(('lookup', 'changegroupsubset'))
@@ -59,30 +60,13 b' class localrepository(repo.repository):'
             if r not in self.supported:
                 raise repo.RepoError(_("requirement '%s' not supported") % r)
 
-        # setup store
-        if "store" in requirements:
-            self.encodefn = util.encodefilename
-            self.decodefn = util.decodefilename
-            self.spath = os.path.join(self.path, "store")
-        else:
-            self.encodefn = lambda x: x
-            self.decodefn = lambda x: x
-            self.spath = self.path
+        self.store = store.store(requirements, self.path)
 
-        try:
-            # files in .hg/ will be created using this mode
-            mode = os.stat(self.spath).st_mode
-            # avoid some useless chmods
-            if (0777 & ~util._umask) == (0777 & mode):
-                mode = None
-        except OSError:
-            mode = None
-
-        self._createmode = mode
-        self.opener.createmode = mode
-        sopener = util.opener(self.spath)
-        sopener.createmode = mode
-        self.sopener = util.encodedopener(sopener, self.encodefn)
+        self.spath = self.store.path
+        self.sopener = self.store.opener
+        self.sjoin = self.store.join
+        self._createmode = self.store.createmode
+        self.opener.createmode = self.store.createmode
 
         self.ui = ui.ui(parentui=parentui)
         try:
@@ -116,6 +100,21 b' class localrepository(repo.repository):'
         else:
             raise AttributeError, name
 
+    def __getitem__(self, changeid):
+        if changeid == None:
+            return context.workingctx(self)
+        return context.changectx(self, changeid)
+
+    def __nonzero__(self):
+        return True
+
+    def __len__(self):
+        return len(self.changelog)
+
+    def __iter__(self):
+        for i in xrange(len(self)):
+            yield i
+
     def url(self):
         return 'file:' + self.root
 
@@ -146,7 +145,11 b' class localrepository(repo.repository):'
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
-                fp.write('%s %s\n' % (hex(node), munge and munge(name) or name))
+                m = munge and munge(name) or name
+                if self._tagstypecache and name in self._tagstypecache:
+                    old = self.tagscache.get(name, nullid)
+                    fp.write('%s %s\n' % (hex(old), m))
+                fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
@@ -302,9 +305,8 b' class localrepository(repo.repository):'
             n = nh[0]
             if n != nullid:
                 self.tagscache[k] = n
-                self._tagstypecache[k] = tagtypes[k]
+            self._tagstypecache[k] = tagtypes[k]
         self.tagscache['tip'] = self.changelog.tip()
-
         return self.tagscache
 
     def tagtype(self, tagname):
@@ -326,7 +328,7 b' class localrepository(repo.repository):'
         last = {}
         ret = []
         for node in heads:
-            c = self.changectx(node)
+            c = self[node]
             rev = c.rev()
             try:
                 fnode = c.filenode('.hgtags')
@@ -347,8 +349,7 b' class localrepository(repo.repository):'
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
-        l.sort()
-        return [(t, n) for r, t, n in l]
+        return [(t, n) for r, t, n in util.sort(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
@@ -359,7 +360,7 b' class localrepository(repo.repository):'
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
-        tiprev = self.changelog.count() - 1
+        tiprev = len(self) - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
@@ -404,8 +405,7 b' class localrepository(repo.repository):'
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
-            if not (lrev < self.changelog.count() and
-                    self.changelog.node(lrev) == last): # sanity check
+            if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
@@ -432,18 +432,13 b' class localrepository(repo.repository):'
 
     def _updatebranchcache(self, partial, start, end):
         for r in xrange(start, end):
-            c = self.changectx(r)
+            c = self[r]
             b = c.branch()
             partial[b] = c.node()
 
     def lookup(self, key):
         if key == '.':
-            key, second = self.dirstate.parents()
-            if key == nullid:
-                raise repo.RepoError(_("no revision checked out"))
-            if second != nullid:
-                self.ui.warn(_("warning: working directory has two parents, "
-                               "tag '.' uses the first\n"))
+            return self.dirstate.parents()[0]
         elif key == 'null':
             return nullid
         n = self.changelog._match(key)
@@ -469,36 +464,23 b' class localrepository(repo.repository):'
     def join(self, f):
         return os.path.join(self.path, f)
 
-    def sjoin(self, f):
-        f = self.encodefn(f)
-        return os.path.join(self.spath, f)
-
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
+    def rjoin(self, f):
+        return os.path.join(self.root, util.pconvert(f))
+
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
-    def changectx(self, changeid=None):
-        return context.changectx(self, changeid)
-
-    def workingctx(self):
-        return context.workingctx(self)
+    def changectx(self, changeid):
+        return self[changeid]
 
     def parents(self, changeid=None):
-        '''
-        get list of changectxs for parents of changeid or working directory
-        '''
-        if changeid is None:
-            pl = self.dirstate.parents()
-        else:
-            n = self.changelog.lookup(changeid)
-            pl = self.changelog.parents(n)
-        if pl[1] == nullid:
-            return [self.changectx(pl[0])]
-        return [self.changectx(pl[0]), self.changectx(pl[1])]
+        '''get list of changectxs for parents of changeid'''
+        return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
@@ -676,19 +658,20 b' class localrepository(repo.repository):'
         self._wlockref = weakref.ref(l)
         return l
 
-    def filecommit(self, fn, manifest1, manifest2, linkrev, tr, changelist):
+    def filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
-        t = self.wread(fn)
+        fn = fctx.path()
+        t = fctx.data()
         fl = self.file(fn)
         fp1 = manifest1.get(fn, nullid)
         fp2 = manifest2.get(fn, nullid)
 
         meta = {}
-        cf = self.dirstate.copied(fn)
-        if cf and cf != fn:
+        cp = fctx.renamed()
+        if cp and cp[0] != fn:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
@@ -708,6 +691,7 b' class localrepository(repo.repository):'
             #    \- 2 --- 4        as the merge base
             #
 
+            cf = cp[0]
             cr = manifest1.get(cf)
             nfp = fp2
 
@@ -721,19 +705,10 b' class localrepository(repo.repository):'
             if not cr:
                 self.ui.debug(_(" %s: searching for copy revision for %s\n") %
                               (fn, cf))
-                p1 = self.dirstate.parents()[0]
-                rev = self.changelog.rev(p1)
-                seen = {-1:None}
-                visit = [rev]
-                while visit:
-                    for p in self.changelog.parentrevs(visit.pop(0)):
-                        if p not in seen:
-                            seen[p] = True
-                            visit.append(p)
-                            ctx = self.changectx(p)
-                            if cf in ctx:
-                                cr = ctx[cf].filenode()
-                                break
+		for a in self['.'].ancestors():
+                    if cf in a:
+                        cr = a[cf].filenode()
+                        break
 
             self.ui.debug(_(" %s: copy %s:%s\n") % (fn, cf, hex(cr)))
             meta["copy"] = cf
@@ -761,66 +736,80 b' class localrepository(repo.repository):'
                            p1=p1, p2=p2, extra=extra, empty_ok=True)
 
     def commit(self, files=None, text="", user=None, date=None,
-               match=util.always, force=False, force_editor=False,
+               match=None, force=False, force_editor=False,
                p1=None, p2=None, extra={}, empty_ok=False):
-        wlock = lock = tr = None
-        valid = 0 # don't save the dirstate if this isn't set
+        wlock = lock = None
         if files:
             files = util.unique(files)
         try:
             wlock = self.wlock()
             lock = self.lock()
-            commit = []
-            remove = []
-            changed = []
             use_dirstate = (p1 is None) # not rawcommit
-            extra = extra.copy()
-
-            if use_dirstate:
-                if files:
-                    for f in files:
-                        s = self.dirstate[f]
-                        if s in 'nma':
-                            commit.append(f)
-                        elif s == 'r':
-                            remove.append(f)
-                        else:
-                            self.ui.warn(_("%s not tracked!\n") % f)
-                else:
-                    changes = self.status(match=match)[:5]
-                    modified, added, removed, deleted, unknown = changes
-                    commit = modified + added
-                    remove = removed
-            else:
-                commit = files
 
             if use_dirstate:
                 p1, p2 = self.dirstate.parents()
                 update_dirstate = True
 
                 if (not force and p2 != nullid and
-                    (files or match != util.always)):
+                    (match and (match.files() or match.anypats()))):
                     raise util.Abort(_('cannot partially commit a merge '
                                        '(do not specify files or patterns)'))
+
+                if files:
+                    modified, removed = [], []
+                    for f in files:
+                        s = self.dirstate[f]
+                        if s in 'nma':
+                            modified.append(f)
+                        elif s == 'r':
+                            removed.append(f)
+                        else:
+                            self.ui.warn(_("%s not tracked!\n") % f)
+                    changes = [modified, [], removed, [], []]
+                else:
+                    changes = self.status(match=match)
             else:
                 p1, p2 = p1, p2 or nullid
                 update_dirstate = (self.dirstate.parents()[0] == p1)
+                changes = [files, [], [], [], []]
 
+            wctx = context.workingctx(self, (p1, p2), text, user, date,
+                                      extra, changes)
+            return self._commitctx(wctx, force, force_editor, empty_ok,
+                                   use_dirstate, update_dirstate)
+        finally:
+            del lock, wlock
+
+    def commitctx(self, ctx):
+        wlock = lock = None
+        try:
+            wlock = self.wlock()
+            lock = self.lock()
+            return self._commitctx(ctx, force=True, force_editor=False,
+                                   empty_ok=True, use_dirstate=False,
+                                   update_dirstate=False)
+        finally:
+            del lock, wlock
+
+    def _commitctx(self, wctx, force=False, force_editor=False, empty_ok=False,
+                  use_dirstate=True, update_dirstate=True):
+        tr = None
+        valid = 0 # don't save the dirstate if this isn't set
+        try:
+            commit = util.sort(wctx.modified() + wctx.added())
+            remove = wctx.removed()
+            extra = wctx.extra().copy()
+            branchname = extra['branch']
+            user = wctx.user()
+            text = wctx.description()
+
+            p1, p2 = [p.node() for p in wctx.parents()]
             c1 = self.changelog.read(p1)
             c2 = self.changelog.read(p2)
             m1 = self.manifest.read(c1[0]).copy()
             m2 = self.manifest.read(c2[0])
 
             if use_dirstate:
-                branchname = self.workingctx().branch()
-                try:
-                    branchname = branchname.decode('UTF-8').encode('UTF-8')
-                except UnicodeDecodeError:
-                    raise util.Abort(_('branch name not in UTF-8!'))
-            else:
-                branchname = ""
-
-            if use_dirstate:
                 oldname = c1[5].get("branch") # stored in UTF-8
                 if (not commit and not remove and not force and p2 == nullid
                     and branchname == oldname):
@@ -838,26 +827,22 b' class localrepository(repo.repository):'
 
             # check in files
             new = {}
-            linkrev = self.changelog.count()
-            commit.sort()
-            is_exec = util.execfunc(self.root, m1.execf)
-            is_link = util.linkfunc(self.root, m1.linkf)
+            changed = []
+            linkrev = len(self)
             for f in commit:
                 self.ui.note(f + "\n")
                 try:
-                    new[f] = self.filecommit(f, m1, m2, linkrev, trp, changed)
-                    new_exec = is_exec(f)
-                    new_link = is_link(f)
+                    fctx = wctx.filectx(f)
+                    newflags = fctx.flags()
+                    new[f] = self.filecommit(fctx, m1, m2, linkrev, trp, changed)
                     if ((not changed or changed[-1] != f) and
                         m2.get(f) != new[f]):
                         # mention the file in the changelog if some
                         # flag changed, even if there was no content
                         # change.
-                        old_exec = m1.execf(f)
-                        old_link = m1.linkf(f)
-                        if old_exec != new_exec or old_link != new_link:
+                        if m1.flags(f) != newflags:
                             changed.append(f)
-                    m1.set(f, new_exec, new_link)
+                    m1.set(f, newflags)
                     if use_dirstate:
                         self.dirstate.normal(f)
 
@@ -870,10 +855,9 b' class localrepository(repo.repository):'
 
             # update manifest
             m1.update(new)
-            remove.sort()
             removed = []
 
-            for f in remove:
+            for f in util.sort(remove):
                 if f in m1:
                     del m1[f]
                     removed.append(f)
@@ -883,10 +867,6 b' class localrepository(repo.repository):'
                                    (new, removed))
 
             # add changeset
-            new = new.keys()
-            new.sort()
-
-            user = user or self.ui.username()
             if (not empty_ok and not text) or force_editor:
                 edittext = []
                 if text:
@@ -911,9 +891,6 b' class localrepository(repo.repository):'
                 text = self.ui.edit("\n".join(edittext), user)
                 os.chdir(olddir)
 
-            if branchname:
-                extra["branch"] = branchname
-
             lines = [line.rstrip() for line in text.rstrip().splitlines()]
             while lines and not lines[0]:
                 del lines[0]
@@ -922,7 +899,7 b' class localrepository(repo.repository):'
             text = '\n'.join(lines)
 
             n = self.changelog.add(mn, changed + removed, text, trp, p1, p2,
-                                   user, date, extra)
+                                   user, wctx.date(), extra)
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             tr.close()
@@ -942,169 +919,103 b' class localrepository(repo.repository):'
         finally:
             if not valid: # don't save our updated dirstate
                 self.dirstate.invalidate()
-            del tr, lock, wlock
+            del tr
 
-    def walk(self, node=None, files=[], match=util.always, badmatch=None):
+    def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
-
-        results are yielded in a tuple (src, filename), where src
-        is one of:
-        'f' the file was found in the directory tree
-        'm' the file was only in the dirstate and not in the tree
-        'b' file was not found and matched badmatch
         '''
+        return self[node].walk(match)
 
-        if node:
-            fdict = dict.fromkeys(files)
-            # for dirstate.walk, files=['.'] means "walk the whole tree".
-            # follow that here, too
-            fdict.pop('.', None)
-            mdict = self.manifest.read(self.changelog.read(node)[0])
-            mfiles = mdict.keys()
-            mfiles.sort()
-            for fn in mfiles:
-                for ffn in fdict:
-                    # match if the file is the exact name or a directory
-                    if ffn == fn or fn.startswith("%s/" % ffn):
-                        del fdict[ffn]
-                        break
-                if match(fn):
-                    yield 'm', fn
-            ffiles = fdict.keys()
-            ffiles.sort()
-            for fn in ffiles:
-                if badmatch and badmatch(fn):
-                    if match(fn):
-                        yield 'b', fn
-                else:
-                    self.ui.warn(_('%s: No such file in rev %s\n')
-                                 % (self.pathto(fn), short(node)))
-        else:
-            for src, fn in self.dirstate.walk(files, match, badmatch=badmatch):
-                yield src, fn
-
-    def status(self, node1=None, node2=None, files=[], match=util.always,
-               list_ignored=False, list_clean=False, list_unknown=True):
+    def status(self, node1='.', node2=None, match=None,
+               ignored=False, clean=False, unknown=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
-        def fcmp(fn, getnode):
-            t1 = self.wread(fn)
-            return self.file(fn).cmp(getnode(fn), t1)
-
-        def mfmatches(node):
-            change = self.changelog.read(node)
-            mf = self.manifest.read(change[0]).copy()
+        def mfmatches(ctx):
+            mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
-        modified, added, removed, deleted, unknown = [], [], [], [], []
-        ignored, clean = [], []
-
-        compareworking = False
-        if not node1 or (not node2 and node1 == self.dirstate.parents()[0]):
-            compareworking = True
+        ctx1 = self[node1]
+        ctx2 = self[node2]
+        working = ctx2 == self[None]
+        parentworking = working and ctx1 == self['.']
+        match = match or match_.always(self.root, self.getcwd())
+        listignored, listclean, listunknown = ignored, clean, unknown
 
-        if not compareworking:
-            # read the manifest from node1 before the manifest from node2,
-            # so that we'll hit the manifest cache if we're going through
-            # all the revisions in parent->child order.
-            mf1 = mfmatches(node1)
-
-        # are we comparing the working directory?
-        if not node2:
-            (lookup, modified, added, removed, deleted, unknown,
-             ignored, clean) = self.dirstate.status(files, match,
-                                                    list_ignored, list_clean,
-                                                    list_unknown)
+        if working: # we need to scan the working dir
+            s = self.dirstate.status(match, listignored, listclean, listunknown)
+            cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
-            # are we comparing working dir against its parent?
-            if compareworking:
-                if lookup:
-                    fixup = []
-                    # do a full compare of any files that might have changed
-                    ctx = self.changectx()
-                    mexec = lambda f: 'x' in ctx.fileflags(f)
-                    mlink = lambda f: 'l' in ctx.fileflags(f)
-                    is_exec = util.execfunc(self.root, mexec)
-                    is_link = util.linkfunc(self.root, mlink)
-                    def flags(f):
-                        return is_link(f) and 'l' or is_exec(f) and 'x' or ''
-                    for f in lookup:
-                        if (f not in ctx or flags(f) != ctx.fileflags(f)
-                            or ctx[f].cmp(self.wread(f))):
-                            modified.append(f)
-                        else:
-                            fixup.append(f)
-                            if list_clean:
-                                clean.append(f)
+            # check for any possibly clean files
+            if parentworking and cmp:
+                fixup = []
+                # do a full compare of any files that might have changed
+                for f in cmp:
+                    if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
+                        or ctx1[f].cmp(ctx2[f].data())):
+                        modified.append(f)
+                    else:
+                        fixup.append(f)
+
+                if listclean:
+                    clean += fixup
 
-                    # update dirstate for files that are actually clean
-                    if fixup:
-                        wlock = None
+                # update dirstate for files that are actually clean
+                if fixup:
+                    wlock = None
+                    try:
                         try:
-                            try:
-                                wlock = self.wlock(False)
-                            except lock.LockException:
-                                pass
-                            if wlock:
-                                for f in fixup:
-                                    self.dirstate.normal(f)
-                        finally:
-                            del wlock
-            else:
+                            wlock = self.wlock(False)
+                            for f in fixup:
+                                self.dirstate.normal(f)
+                        except lock.LockException:
+                            pass
+                    finally:
+                        del wlock
+
+        if not parentworking:
+            mf1 = mfmatches(ctx1)
+            if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
-                # XXX: create it in dirstate.py ?
-                mf2 = mfmatches(self.dirstate.parents()[0])
-                is_exec = util.execfunc(self.root, mf2.execf)
-                is_link = util.linkfunc(self.root, mf2.linkf)
-                for f in lookup + modified + added:
-                    mf2[f] = ""
-                    mf2.set(f, is_exec(f), is_link(f))
+                mf2 = mfmatches(self['.'])
+                for f in cmp + modified + added:
+                    mf2[f] = None
+                    mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
+            else:
+                # we are comparing two revisions
+                deleted, unknown, ignored = [], [], []
+                mf2 = mfmatches(ctx2)
 
-        else:
-            # we are comparing two revisions
-            mf2 = mfmatches(node2)
-
-        if not compareworking:
-            # flush lists from dirstate before comparing manifests
             modified, added, clean = [], [], []
-
-            # make sure to sort the files so we talk to the disk in a
-            # reasonable order
-            mf2keys = mf2.keys()
-            mf2keys.sort()
-            getnode = lambda fn: mf1.get(fn, nullid)
-            for fn in mf2keys:
+            for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
-                         (mf2[fn] != "" or fcmp(fn, getnode)))):
+                         (mf2[fn] or ctx1[fn].cmp(ctx2[fn].data())))):
                         modified.append(fn)
-                    elif list_clean:
+                    elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
-
             removed = mf1.keys()
 
-        # sort and return results:
-        for l in modified, added, removed, deleted, unknown, ignored, clean:
-            l.sort()
-        return (modified, added, removed, deleted, unknown, ignored, clean)
+        r = modified, added, removed, deleted, unknown, ignored, clean
+        [l.sort() for l in r]
+        return r
 
     def add(self, list):
         wlock = self.wlock()
@@ -1209,10 +1120,11 b' class localrepository(repo.repository):'
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
-        heads.sort()
-        return [n for (r, n) in heads]
+        return [n for (r, n) in util.sort(heads)]
 
-    def branchheads(self, branch, start=None):
+    def branchheads(self, branch=None, start=None):
+        if branch is None:
+            branch = self[None].branch()
         branches = self.branchtags()
         if branch not in branches:
             return []
@@ -1250,7 +1162,7 b' class localrepository(repo.repository):'
             if rev in ancestors:
                 ancestors.update(self.changelog.parentrevs(rev))
                 ancestors.remove(rev)
-            elif self.changectx(rev).branch() == branch:
+            elif self[rev].branch() == branch:
                 heads.append(rev)
                 ancestors.update(self.changelog.parentrevs(rev))
         heads = [self.changelog.node(rev) for rev in heads]
@@ -1665,7 +1577,7 b' class localrepository(repo.repository):'
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
-        junk = mnfst.index[mnfst.count() - 1] # Get around a bug in lazyindex
+        junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
@@ -1860,12 +1772,10 b' class localrepository(repo.repository):'
                     add_extra_nodes(fname,
                                     msng_filenode_set.setdefault(fname, {}))
                     changedfiles[fname] = 1
-            changedfiles = changedfiles.keys()
-            changedfiles.sort()
             # Go through all our files in order sorted by name.
-            for fname in changedfiles:
+            for fname in util.sort(changedfiles):
                 filerevlog = self.file(fname)
-                if filerevlog.count() == 0:
+                if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
@@ -1916,10 +1826,10 b' class localrepository(repo.repository):'
         def identity(x):
             return x
 
-        def gennodelst(revlog):
-            for r in xrange(0, revlog.count()):
-                n = revlog.node(r)
-                if revlog.linkrev(n) in revset:
+        def gennodelst(log):
+            for r in log:
+                n = log.node(r)
+                if log.linkrev(n) in revset:
                     yield n
 
         def changed_file_collector(changedfileset):
@@ -1941,17 +1851,15 b' class localrepository(repo.repository):'
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
-            changedfiles = changedfiles.keys()
-            changedfiles.sort()
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
-            for fname in changedfiles:
+            for fname in util.sort(changedfiles):
                 filerevlog = self.file(fname)
-                if filerevlog.count() == 0:
+                if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
@@ -1980,7 +1888,7 b' class localrepository(repo.repository):'
         """
         def csmap(x):
             self.ui.debug(_("add changeset %s\n") % short(x))
-            return cl.count()
+            return len(cl)
 
         def revmap(x):
             return cl.rev(x)
@@ -2003,11 +1911,11 b' class localrepository(repo.repository):'
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
-            cor = cl.count() - 1
+            cor = len(cl) - 1
             chunkiter = changegroup.chunkiter(source)
-            if cl.addgroup(chunkiter, csmap, trp, 1) is None and not emptyok:
+            if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
-            cnr = cl.count() - 1
+            cnr = len(cl) - 1
             changesets = cnr - cor
 
             # pull off the manifest group
@@ -2027,11 +1935,11 b' class localrepository(repo.repository):'
                     break
                 self.ui.debug(_("adding %s revisions\n") % f)
                 fl = self.file(f)
-                o = fl.count()
+                o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
-                revisions += fl.count() - o
+                revisions += len(fl) - o
                 files += 1
 
             # make changelog see real files again
@@ -2139,6 +2047,25 b' class localrepository(repo.repository):'
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
+    def storefiles(self):
+        '''get all *.i and *.d files in the store
+
+        Returns (list of (filename, size), total_bytes)'''
+
+        lock = None
+        try:
+            self.ui.debug('scanning\n')
+            entries = []
+            total_bytes = 0
+            # get consistent snapshot of repo, lock during scan
+            lock = self.lock()
+            for name, size in self.store.walk():
+                entries.append((name, size))
+                total_bytes += size
+            return entries, total_bytes
+        finally:
+            del lock
+
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]

mercurial/mail.py

@@ -6,7 +6,8 b''
 # of the GNU General Public License, incorporated herein by reference.
 
 from i18n import _
-import os, smtplib, util, socket
+import os, smtplib, socket
+import util
 
 def _smtp(ui):
     '''build an smtp connection and return a function to send mail'''
@@ -53,7 +54,7 b' def _sendmail(ui, sender, recipients, ms'
     cmdline = '%s -f %s %s' % (program, util.email(sender),
                                ' '.join(map(util.email, recipients)))
     ui.note(_('sending mail: %s\n') % cmdline)
-    fp = os.popen(cmdline, 'w')
+    fp = util.popen(cmdline, 'w')
     fp.write(msg)
     ret = fp.close()
     if ret:

mercurial/manifest.py

@@ -8,7 +8,7 b''
 from node import bin, hex, nullid
 from revlog import revlog, RevlogError
 from i18n import _
-import array, struct, mdiff
+import array, struct, mdiff, parsers, util
 
 class manifestdict(dict):
     def __init__(self, mapping=None, flags=None):
@@ -18,16 +18,8 b' class manifestdict(dict):'
         self._flags = flags
     def flags(self, f):
         return self._flags.get(f, "")
-    def execf(self, f):
-        "test for executable in manifest flags"
-        return "x" in self.flags(f)
-    def linkf(self, f):
-        "test for symlink in manifest flags"
-        return "l" in self.flags(f)
-    def set(self, f, execf=False, linkf=False):
-        if linkf: self._flags[f] = "l"
-        elif execf: self._flags[f] = "x"
-        else: self._flags[f] = ""
+    def set(self, f, flags):
+        self._flags[f] = flags
     def copy(self):
         return manifestdict(dict.copy(self), dict.copy(self._flags))
 
@@ -39,14 +31,7 b' class manifest(revlog):'
 
     def parse(self, lines):
         mfdict = manifestdict()
-        fdict = mfdict._flags
-        for l in lines.splitlines():
-            f, n = l.split('\0')
-            if len(n) > 40:
-                fdict[f] = n[40:]
-                mfdict[f] = bin(n[:40])
-            else:
-                mfdict[f] = bin(n)
+        parsers.parse_manifest(mfdict, mfdict._flags, lines)
         return mfdict
 
     def readdelta(self, node):
@@ -134,18 +119,16 b' class manifest(revlog):'
             return "".join([struct.pack(">lll", d[0], d[1], len(d[2])) + d[2]
                             for d in x ])
 
-        def checkforbidden(f):
-            if '\n' in f or '\r' in f:
-                raise RevlogError(_("'\\n' and '\\r' disallowed in filenames"))
+        def checkforbidden(l):
+            for f in l:
+                if '\n' in f or '\r' in f:
+                    raise RevlogError(_("'\\n' and '\\r' disallowed in filenames"))
 
         # if we're using the listcache, make sure it is valid and
         # parented by the same node we're diffing against
         if not (changed and self.listcache and p1 and self.mapcache[0] == p1):
-            files = map.keys()
-            files.sort()
-
-            for f in files:
-                checkforbidden(f)
+            files = util.sort(map)
+            checkforbidden(files)
 
             # if this is changed to support newlines in filenames,
             # be sure to check the templates/ dir again (especially *-raw.tmpl)
@@ -156,8 +139,7 b' class manifest(revlog):'
         else:
             addlist = self.listcache
 
-            for f in changed[0]:
-                checkforbidden(f)
+            checkforbidden(changed[0])
             # combine the changed lists into one list for sorting
             work = [[x, 0] for x in changed[0]]
             work[len(work):] = [[x, 1] for x in changed[1]]

mercurial/mdiff.py

@@ -6,7 +6,7 b''
 # of the GNU General Public License, incorporated herein by reference.
 
 from i18n import _
-import bdiff, mpatch, re, struct, util, md5
+import bdiff, mpatch, re, struct, util
 
 def splitnewlines(text):
     '''like str.splitlines, but only split on newlines.'''
@@ -78,10 +78,7 b' def unidiff(a, ad, b, bd, fn1, fn2, r=No'
     epoch = util.datestr((0, 0))
 
     if not opts.text and (util.binary(a) or util.binary(b)):
-        def h(v):
-            # md5 is used instead of sha1 because md5 is supposedly faster
-            return md5.new(v).digest()
-        if a and b and len(a) == len(b) and h(a) == h(b):
+        if a and b and len(a) == len(b) and a == b:
             return ""
         l = ['Binary file %s has changed\n' % fn1]
     elif not a:

mercurial/merge.py

@@ -5,9 +5,70 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-from node import nullid, nullrev
+from node import nullid, nullrev, hex, bin
 from i18n import _
-import errno, util, os, filemerge, copies
+import errno, util, os, filemerge, copies, shutil
+
+class mergestate(object):
+    '''track 3-way merge state of individual files'''
+    def __init__(self, repo):
+        self._repo = repo
+        self._read()
+    def reset(self, node):
+        self._state = {}
+        self._local = node
+        shutil.rmtree(self._repo.join("merge"), True)
+    def _read(self):
+        self._state = {}
+        try:
+            localnode = None
+            f = self._repo.opener("merge/state")
+            for i, l in enumerate(f):
+                if i == 0:
+                    localnode = l[:-1]
+                else:
+                    bits = l[:-1].split("\0")
+                    self._state[bits[0]] = bits[1:]
+            self._local = bin(localnode)
+        except IOError, err:
+            if err.errno != errno.ENOENT:
+                raise
+    def _write(self):
+        f = self._repo.opener("merge/state", "w")
+        f.write(hex(self._local) + "\n")
+        for d, v in self._state.items():
+            f.write("\0".join([d] + v) + "\n")
+    def add(self, fcl, fco, fca, fd, flags):
+        hash = util.sha1(fcl.path()).hexdigest()
+        self._repo.opener("merge/" + hash, "w").write(fcl.data())
+        self._state[fd] = ['u', hash, fcl.path(), fca.path(),
+                           hex(fca.filenode()), fco.path(), flags]
+        self._write()
+    def __contains__(self, dfile):
+        return dfile in self._state
+    def __getitem__(self, dfile):
+        return self._state[dfile][0]
+    def __iter__(self):
+        l = self._state.keys()
+        l.sort()
+        for f in l:
+            yield f
+    def mark(self, dfile, state):
+        self._state[dfile][0] = state
+        self._write()
+    def resolve(self, dfile, wctx, octx):
+        if self[dfile] == 'r':
+            return 0
+        state, hash, lfile, afile, anode, ofile, flags = self._state[dfile]
+        f = self._repo.opener("merge/" + hash)
+        self._repo.wwrite(dfile, f.read(), flags)
+        fcd = wctx[dfile]
+        fco = octx[ofile]
+        fca = self._repo.filectx(afile, fileid=anode)
+        r = filemerge.filemerge(self._repo, self._local, lfile, fcd, fco, fca)
+        if not r:
+            self.mark(dfile, 'r')
+        return r
 
 def _checkunknown(wctx, mctx):
     "check for collisions between unknown files and files in mctx"
@@ -197,19 +258,44 b' def manifestmerge(repo, p1, p2, pa, over'
 
     return action
 
+def actioncmp(a1, a2):
+    m1 = a1[1]
+    m2 = a2[1]
+    if m1 == m2:
+        return cmp(a1, a2)
+    if m1 == 'r':
+        return -1
+    if m2 == 'r':
+        return 1
+    return cmp(a1, a2)
+
 def applyupdates(repo, action, wctx, mctx):
     "apply the merge action list to the working directory"
 
     updated, merged, removed, unresolved = 0, 0, 0, 0
-    action.sort()
-    # prescan for copy/renames
+    ms = mergestate(repo)
+    ms.reset(wctx.parents()[0].node())
+    moves = []
+    action.sort(actioncmp)
+
+    # prescan for merges
     for a in action:
         f, m = a[:2]
         if m == 'm': # merge
             f2, fd, flags, move = a[2:]
-            if f != fd:
-                repo.ui.debug(_("copying %s to %s\n") % (f, fd))
-                repo.wwrite(fd, repo.wread(f), flags)
+            repo.ui.debug(_("preserving %s for resolve of %s\n") % (f, fd))
+            fcl = wctx[f]
+            fco = mctx[f2]
+            fca = fcl.ancestor(fco) or repo.filectx(f, fileid=nullrev)
+            ms.add(fcl, fco, fca, fd, flags)
+            if f != fd and move:
+                moves.append(f)
+
+    # remove renamed files after safely stored
+    for f in moves:
+        if util.lexists(repo.wjoin(f)):
+            repo.ui.debug(_("removing %s\n") % f)
+            os.unlink(repo.wjoin(f))
 
     audit_path = util.path_auditor(repo.root)
 
@@ -229,7 +315,7 b' def applyupdates(repo, action, wctx, mct'
             removed += 1
         elif m == "m": # merge
             f2, fd, flags, move = a[2:]
-            r = filemerge.filemerge(repo, f, fd, f2, wctx, mctx)
+            r = ms.resolve(fd, wctx, mctx)
             if r > 0:
                 unresolved += 1
             else:
@@ -237,10 +323,6 b' def applyupdates(repo, action, wctx, mct'
                     updated += 1
                 else:
                     merged += 1
-            util.set_flags(repo.wjoin(fd), flags)
-            if f != fd and move and util.lexists(repo.wjoin(f)):
-                repo.ui.debug(_("removing %s\n") % f)
-                os.unlink(repo.wjoin(f))
         elif m == "g": # get
             flags = a[2]
             repo.ui.note(_("getting %s\n") % f)
@@ -337,7 +419,7 b' def update(repo, node, branchmerge, forc'
 
     wlock = repo.wlock()
     try:
-        wc = repo.workingctx()
+        wc = repo[None]
         if node is None:
             # tip of current branch
             try:
@@ -349,7 +431,7 b' def update(repo, node, branchmerge, forc'
                     raise util.Abort(_("branch %s not found") % wc.branch())
         overwrite = force and not branchmerge
         pl = wc.parents()
-        p1, p2 = pl[0], repo.changectx(node)
+        p1, p2 = pl[0], repo[node]
         pa = p1.ancestor(p2)
         fp1, fp2, xp1, xp2 = p1.node(), p2.node(), str(p1), str(p2)
         fastforward = False
@@ -388,7 +470,7 b' def update(repo, node, branchmerge, forc'
         action = []
         if not force:
             _checkunknown(wc, p2)
-        if not util.checkfolding(repo.path):
+        if not util.checkcase(repo.path):
             _checkcollision(p2)
         action += _forgetremoved(wc, p2, branchmerge)
         action += manifestmerge(repo, wc, p2, pa, overwrite, partial)

mercurial/patch.py

@@ -8,8 +8,8 b''
 
 from i18n import _
 from node import hex, nullid, short
-import base85, cmdutil, mdiff, util, context, revlog, diffhelpers, copies
-import cStringIO, email.Parser, os, popen2, re, sha, errno
+import base85, cmdutil, mdiff, util, revlog, diffhelpers, copies
+import cStringIO, email.Parser, os, popen2, re, errno
 import sys, tempfile, zlib
 
 class PatchError(Exception):
@@ -1094,8 +1094,7 b' def updatedir(ui, repo, patches):'
         repo.copy(src, dst)
     removes = removes.keys()
     if removes:
-        removes.sort()
-        repo.remove(removes, True)
+        repo.remove(util.sort(removes), True)
     for f in patches:
         ctype, gp = patches[f]
         if gp and gp.mode:
@@ -1113,9 +1112,7 b' def updatedir(ui, repo, patches):'
     cmdutil.addremove(repo, cfiles)
     files = patches.keys()
     files.extend([r for r in removes if r not in files])
-    files.sort()
-
-    return files
+    return util.sort(files)
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
@@ -1123,7 +1120,7 b' def b85diff(to, tn):'
         if not text:
             return '0' * 40
         l = len(text)
-        s = sha.new('blob %d\0' % l)
+        s = util.sha1('blob %d\0' % l)
         s.update(text)
         return s.hexdigest()
 
@@ -1155,7 +1152,7 b' def b85diff(to, tn):'
     ret.append('\n')
     return ''.join(ret)
 
-def diff(repo, node1=None, node2=None, files=None, match=util.always,
+def diff(repo, node1=None, node2=None, match=None,
          fp=None, changes=None, opts=None):
     '''print diff of changes to files between two nodes, or node and
     working directory.
@@ -1163,6 +1160,9 b' def diff(repo, node1=None, node2=None, f'
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.'''
 
+    if not match:
+        match = cmdutil.matchall(repo)
+
     if opts is None:
         opts = mdiff.defaultopts
     if fp is None:
@@ -1171,12 +1171,6 b' def diff(repo, node1=None, node2=None, f'
     if not node1:
         node1 = repo.dirstate.parents()[0]
 
-    ccache = {}
-    def getctx(r):
-        if r not in ccache:
-            ccache[r] = context.changectx(repo, r)
-        return ccache[r]
-
     flcache = {}
     def getfilectx(f, ctx):
         flctx = ctx.filectx(f, filelog=flcache.get(f))
@@ -1186,30 +1180,19 b' def diff(repo, node1=None, node2=None, f'
 
     # reading the data for node1 early allows it to play nicely
     # with repo.status and the revlog cache.
-    ctx1 = context.changectx(repo, node1)
+    ctx1 = repo[node1]
     # force manifest reading
     man1 = ctx1.manifest()
     date1 = util.datestr(ctx1.date())
 
     if not changes:
-        changes = repo.status(node1, node2, files, match=match)[:5]
-    modified, added, removed, deleted, unknown = changes
+        changes = repo.status(node1, node2, match=match)
+    modified, added, removed = changes[:3]
 
     if not modified and not added and not removed:
         return
 
-    if node2:
-        ctx2 = context.changectx(repo, node2)
-        execf2 = ctx2.manifest().execf
-        linkf2 = ctx2.manifest().linkf
-    else:
-        ctx2 = context.workingctx(repo)
-        execf2 = util.execfunc(repo.root, None)
-        linkf2 = util.linkfunc(repo.root, None)
-        if execf2 is None:
-            mc = ctx2.parents()[0].manifest().copy()
-            execf2 = mc.execf
-            linkf2 = mc.linkf
+    ctx2 = repo[node2]
 
     if repo.ui.quiet:
         r = None
@@ -1218,15 +1201,14 b' def diff(repo, node1=None, node2=None, f'
         r = [hexfunc(node) for node in [node1, node2] if node]
 
     if opts.git:
-        copy, diverge = copies.copies(repo, ctx1, ctx2, repo.changectx(nullid))
+        copy, diverge = copies.copies(repo, ctx1, ctx2, repo[nullid])
         for k, v in copy.items():
             copy[v] = k
 
-    all = modified + added + removed
-    all.sort()
     gone = {}
+    gitmode = {'l': '120000', 'x': '100755', '': '100644'}
 
-    for f in all:
+    for f in util.sort(modified + added + removed):
         to = None
         tn = None
         dodiff = True
@@ -1237,18 +1219,16 b' def diff(repo, node1=None, node2=None, f'
             tn = getfilectx(f, ctx2).data()
         a, b = f, f
         if opts.git:
-            def gitmode(x, l):
-                return l and '120000' or (x and '100755' or '100644')
             def addmodehdr(header, omode, nmode):
                 if omode != nmode:
                     header.append('old mode %s\n' % omode)
                     header.append('new mode %s\n' % nmode)
 
             if f in added:
-                mode = gitmode(execf2(f), linkf2(f))
+                mode = gitmode[ctx2.flags(f)]
                 if f in copy:
                     a = copy[f]
-                    omode = gitmode(man1.execf(a), man1.linkf(a))
+                    omode = gitmode[man1.flags(a)]
                     addmodehdr(header, omode, mode)
                     if a in removed and a not in gone:
                         op = 'rename'
@@ -1267,11 +1247,11 b' def diff(repo, node1=None, node2=None, f'
                 if f in copy and copy[f] in added and copy[copy[f]] == f:
                     dodiff = False
                 else:
-                    mode = gitmode(man1.execf(f), man1.linkf(f))
-                    header.append('deleted file mode %s\n' % mode)
+                    header.append('deleted file mode %s\n' %
+                                  gitmode[man1.flags(f)])
             else:
-                omode = gitmode(man1.execf(f), man1.linkf(f))
-                nmode = gitmode(execf2(f), linkf2(f))
+                omode = gitmode[man1.flags(f)]
+                nmode = gitmode[ctx2.flags(f)]
                 addmodehdr(header, omode, nmode)
                 if util.binary(to) or util.binary(tn):
                     dodiff = 'binary'
@@ -1297,7 +1277,7 b" def export(repo, revs, template='hg-%h.p"
     revwidth = max([len(str(rev)) for rev in revs])
 
     def single(rev, seqno, fp):
-        ctx = repo.changectx(rev)
+        ctx = repo[rev]
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()

mercurial/repair.py

@@ -23,8 +23,8 b' def _collectfiles(repo, striprev):'
     """find out the filelogs affected by the strip"""
     files = {}
 
-    for x in xrange(striprev, repo.changelog.count()):
-        for name in repo.changectx(x).files():
+    for x in xrange(striprev, len(repo)):
+        for name in repo[x].files():
             if name in files:
                 continue
             files[name] = 1
@@ -37,7 +37,7 b' def _collectextranodes(repo, files, link'
     """return the nodes that have to be saved before the strip"""
     def collectone(revlog):
         extra = []
-        startrev = count = revlog.count()
+        startrev = count = len(revlog)
         # find the truncation point of the revlog
         for i in xrange(0, count):
             node = revlog.node(i)
@@ -72,7 +72,6 b' def _collectextranodes(repo, files, link'
 def strip(ui, repo, node, backup="all"):
     cl = repo.changelog
     # TODO delete the undo files, and handle undo of merge sets
-    pp = cl.parents(node)
     striprev = cl.rev(node)
 
     # Some revisions with rev > striprev may not be descendants of striprev.
@@ -85,7 +84,7 b' def strip(ui, repo, node, backup="all"):'
     tostrip = {striprev: 1}
     saveheads = {}
     savebases = []
-    for r in xrange(striprev + 1, cl.count()):
+    for r in xrange(striprev + 1, len(cl)):
         parents = cl.parentrevs(r)
         if parents[0] in tostrip or parents[1] in tostrip:
             # r is a descendant of striprev

mercurial/repo.py

@@ -40,3 +40,9 b' class repository(object):'
 
     def cancopy(self):
         return self.local()
+
+    def rjoin(self, path):
+        url = self.url()
+        if url.endswith('/'):
+            return url + path
+        return url + '/' + path

mercurial/revlog.py

@@ -13,13 +13,13 b' of the GNU General Public License, incor'
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import changegroup, errno, ancestor, mdiff
-import sha, struct, util, zlib
+import struct, util, zlib
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
-_sha = sha.new
+_sha = util.sha1
 
 # revlog flags
 REVLOGV0 = 0
@@ -32,13 +32,16 b' REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_'
 class RevlogError(Exception):
     pass
 
-class LookupError(RevlogError):
+class LookupError(RevlogError, KeyError):
     def __init__(self, name, index, message):
         self.name = name
         if isinstance(name, str) and len(name) == 20:
             name = short(name)
         RevlogError.__init__(self, _('%s@%s: %s') % (index, name, message))
 
+    def __str__(self):
+        return RevlogError.__str__(self)
+
 def getoffset(q):
     return int(q >> 16)
 
@@ -512,9 +515,11 b' class revlog(object):'
 
     def tip(self):
         return self.node(len(self.index) - 2)
-    def count(self):
+    def __len__(self):
         return len(self.index) - 1
-
+    def __iter__(self):
+        for i in xrange(len(self)):
+            yield i
     def rev(self, node):
         try:
             return self.nodemap[node]
@@ -591,6 +596,27 b' class revlog(object):'
                     visit.append(p)
         return reachable
 
+    def ancestors(self, *revs):
+        'Generate the ancestors of revs using a breadth-first visit'
+        visit = list(revs)
+        seen = util.set([nullrev])
+        while visit:
+            for parent in self.parentrevs(visit.pop(0)):
+                if parent not in seen:
+                    visit.append(parent)
+                    seen.add(parent)
+                    yield parent
+
+    def descendants(self, *revs):
+        'Generate the descendants of revs in topological order'
+        seen = util.set(revs)
+        for i in xrange(min(revs) + 1, len(self)):
+            for x in self.parentrevs(i):
+                if x != nullrev and x in seen:
+                    seen.add(i)
+                    yield i
+                    break
+
     def nodesbetween(self, roots=None, heads=None):
         """Return a tuple containing three elements. Elements 1 and 2 contain
         a final list bases and heads after all the unreachable ones have been
@@ -617,12 +643,11 b' class revlog(object):'
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
-            return ([self.node(r) for r in xrange(0, self.count())],
-                    [nullid], list(self.heads()))
+            return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
-            highestrev = self.count() - 1
+            highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
@@ -751,15 +776,15 b' class revlog(object):'
         as if they had no children
         """
         if start is None and stop is None:
-            count = self.count()
+            count = len(self)
             if not count:
                 return [nullid]
             ishead = [1] * (count + 1)
             index = self.index
-            for r in xrange(count):
+            for r in self:
                 e = index[r]
                 ishead[e[5]] = ishead[e[6]] = 0
-            return [self.node(r) for r in xrange(count) if ishead[r]]
+            return [self.node(r) for r in self if ishead[r]]
 
         if start is None:
             start = nullid
@@ -771,7 +796,7 b' class revlog(object):'
         heads = {startrev: 1}
 
         parentrevs = self.parentrevs
-        for r in xrange(startrev + 1, self.count()):
+        for r in xrange(startrev + 1, len(self)):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
@@ -786,7 +811,7 b' class revlog(object):'
         """find the children of a given node"""
         c = []
         p = self.rev(node)
-        for r in range(p + 1, self.count()):
+        for r in range(p + 1, len(self)):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
@@ -815,8 +840,8 b' class revlog(object):'
             if str(rev) != id:
                 raise ValueError
             if rev < 0:
-                rev = self.count() + rev
-            if rev < 0 or rev >= self.count():
+                rev = len(self) + rev
+            if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
@@ -979,7 +1004,7 b' class revlog(object):'
         df = self.opener(self.datafile, 'w')
         try:
             calc = self._io.size
-            for r in xrange(self.count()):
+            for r in self:
                 start = self.start(r) + (r + 1) * calc
                 length = self.length(r)
                 fp.seek(start)
@@ -992,7 +1017,7 b' class revlog(object):'
         fp = self.opener(self.indexfile, 'w', atomictemp=True)
         self.version &= ~(REVLOGNGINLINEDATA)
         self._inline = False
-        for i in xrange(self.count()):
+        for i in self:
             e = self._io.packentry(self.index[i], self.node, self.version, i)
             fp.write(e)
 
@@ -1028,7 +1053,7 b' class revlog(object):'
         if node in self.nodemap:
             return node
 
-        curr = self.count()
+        curr = len(self)
         prev = curr - 1
         base = self.base(prev)
         offset = self.end(prev)
@@ -1133,7 +1158,7 b' class revlog(object):'
 
         yield changegroup.closechunk()
 
-    def addgroup(self, revs, linkmapper, transaction, unique=0):
+    def addgroup(self, revs, linkmapper, transaction):
         """
         add a delta group
 
@@ -1143,7 +1168,7 b' class revlog(object):'
         """
 
         #track the base of the current delta log
-        r = self.count()
+        r = len(self)
         t = r - 1
         node = None
 
@@ -1170,8 +1195,6 b' class revlog(object):'
                 link = linkmapper(cs)
                 if node in self.nodemap:
                     # this can happen if two branches make the same change
-                    # if unique:
-                    #    raise RevlogError(_("already have %s") % hex(node[:4]))
                     chain = node
                     continue
                 delta = buffer(chunk, 80)
@@ -1264,13 +1287,13 b' class revlog(object):'
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll readd them after this truncation.
         """
-        if self.count() == 0:
+        if len(self) == 0:
             return
 
         if isinstance(self.index, lazyindex):
             self._loadindexmap()
 
-        for rev in xrange(0, self.count()):
+        for rev in self:
             if self.index[rev][4] >= minlink:
                 break
         else:
@@ -1291,15 +1314,15 b' class revlog(object):'
         # then reset internal state in memory to forget those revisions
         self._cache = None
         self._chunkcache = None
-        for x in xrange(rev, self.count()):
+        for x in xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
 
     def checksize(self):
         expected = 0
-        if self.count():
-            expected = max(0, self.end(self.count() - 1))
+        if len(self):
+            expected = max(0, self.end(len(self) - 1))
 
         try:
             f = self.opener(self.datafile)
@@ -1320,10 +1343,10 b' class revlog(object):'
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
-                for r in xrange(self.count()):
+                for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
-                di = actual - self.count() * s - databytes
+                di = actual - len(self) * s - databytes
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise

mercurial/statichttprepo.py

@@ -9,7 +9,7 b''
 
 from i18n import _
 import changelog, httprangereader
-import repo, localrepo, manifest, util
+import repo, localrepo, manifest, util, store
 import urllib, urllib2, errno
 
 class rangereader(httprangereader.httprangereader):
@@ -55,14 +55,13 b' class statichttprepository(localrepo.loc'
 
         # setup store
         if "store" in requirements:
-            self.encodefn = util.encodefilename
-            self.decodefn = util.decodefilename
             self.spath = self.path + "/store"
         else:
-            self.encodefn = lambda x: x
-            self.decodefn = lambda x: x
             self.spath = self.path
-        self.sopener = util.encodedopener(opener(self.spath), self.encodefn)
+        self.encodefn = store.encodefn(requirements)
+        so = opener(self.spath)
+        self.sopener = lambda path, *args, **kw: so(
+            self.encodefn(path), *args, **kw)
 
         self.manifest = manifest.manifest(self.sopener)
         self.changelog = changelog.changelog(self.sopener)

mercurial/streamclone.py

@@ -5,41 +5,12 b''
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-import os, osutil, stat, util, lock
+import util, lock
 
 # if server supports streaming clone, it advertises "stream"
 # capability with value that is version+flags of repo it is serving.
 # client only streams if it can read that repo format.
 
-def walkrepo(root):
-    '''iterate over metadata files in repository.
-    walk in natural (sorted) order.
-    yields 2-tuples: name of .d or .i file, size of file.'''
-
-    strip_count = len(root) + len(os.sep)
-    def walk(path, recurse):
-        for e, kind, st in osutil.listdir(path, stat=True):
-            pe = os.path.join(path, e)
-            if kind == stat.S_IFDIR:
-                if recurse:
-                    for x in walk(pe, True):
-                        yield x
-            else:
-                if kind != stat.S_IFREG or len(e) < 2:
-                    continue
-                sfx = e[-2:]
-                if sfx in ('.d', '.i'):
-                    yield pe[strip_count:], st.st_size
-    # write file data first
-    for x in walk(os.path.join(root, 'data'), True):
-        yield x
-    # write manifest before changelog
-    meta = list(walk(root, False))
-    meta.sort()
-    meta.reverse()
-    for x in meta:
-        yield x
-
 # stream file format is simple.
 #
 # server writes out line that says how many files, how many total
@@ -60,28 +31,14 b' def stream_out(repo, fileobj, untrusted='
         fileobj.write('1\n')
         return
 
-    # get consistent snapshot of repo. lock during scan so lock not
-    # needed while we stream, and commits can happen.
-    repolock = None
     try:
-        try:
-            repolock = repo.lock()
-        except (lock.LockHeld, lock.LockUnavailable), inst:
-            repo.ui.warn('locking the repository failed: %s\n' % (inst,))
-            fileobj.write('2\n')
-            return
+        entries, total_bytes = repo.storefiles()
+    except (lock.LockHeld, lock.LockUnavailable), inst:
+        repo.ui.warn('locking the repository failed: %s\n' % (inst,))
+        fileobj.write('2\n')
+        return
 
-        fileobj.write('0\n')
-        repo.ui.debug('scanning\n')
-        entries = []
-        total_bytes = 0
-        for name, size in walkrepo(repo.spath):
-            name = repo.decodefn(util.pconvert(name))
-            entries.append((name, size))
-            total_bytes += size
-    finally:
-        del repolock
-
+    fileobj.write('0\n')
     repo.ui.debug('%d files, %d bytes to transfer\n' %
                   (len(entries), total_bytes))
     fileobj.write('%d %d\n' % (len(entries), total_bytes))

mercurial/templatefilters.py

@@ -122,6 +122,36 b' def xmlescape(text):'
             .replace("'", ''')) # ' invalid in HTML
     return re.sub('[\x00-\x08\x0B\x0C\x0E-\x1F]', ' ', text)
 
+_escapes = [
+    ('\\', '\\\\'), ('"', '\\"'), ('\t', '\\t'), ('\n', '\\n'),
+    ('\r', '\\r'), ('\f', '\\f'), ('\b', '\\b'),
+]
+
+def json(obj):
+    if obj is None or obj is False or obj is True:
+        return {None: 'null', False: 'false', True: 'true'}[obj]
+    elif isinstance(obj, int) or isinstance(obj, float):
+        return str(obj)
+    elif isinstance(obj, str):
+        for k, v in _escapes:
+            obj = obj.replace(k, v)
+        return '"%s"' % obj
+    elif isinstance(obj, unicode):
+        return json(obj.encode('utf-8'))
+    elif hasattr(obj, 'keys'):
+        out = []
+        for k, v in obj.iteritems():
+            s = '%s: %s' % (json(k), json(v))
+            out.append(s)
+        return '{' + ', '.join(out) + '}'
+    elif hasattr(obj, '__iter__'):
+        out = []
+        for i in obj:
+            out.append(json(i))
+        return '[' + ', '.join(out) + ']'
+    else:
+        raise TypeError('cannot encode type %s' % obj.__class__.__name__)
+
 filters = {
     "addbreaks": nl2br,
     "basename": os.path.basename,
@@ -150,5 +180,5 b' filters = {'
     "user": lambda x: util.shortuser(x),
     "stringescape": lambda x: x.encode('string_escape'),
     "xmlescape": xmlescape,
-    }
-
+    "json": json,
+}

mercurial/templater.py

@@ -81,18 +81,18 b' class templater(object):'
     def __contains__(self, key):
         return key in self.cache or key in self.map
 
-    def __call__(self, t, **map):
-        '''perform expansion.
-        t is name of map element to expand.
-        map is added elements to use during expansion.'''
+    def _template(self, t):
+        '''Get the template for the given template name. Use a local cache.'''
         if not t in self.cache:
             try:
                 self.cache[t] = file(self.map[t]).read()
             except IOError, inst:
                 raise IOError(inst.args[0], _('template file %s: %s') %
                               (self.map[t], inst.args[1]))
-        tmpl = self.cache[t]
+        return self.cache[t]
 
+    def _process(self, tmpl, map):
+        '''Render a template. Returns a generator.'''
         while tmpl:
             m = self.template_re.search(tmpl)
             if not m:
@@ -114,18 +114,39 b' class templater(object):'
                 v = v(**map)
             if format:
                 if not hasattr(v, '__iter__'):
-                    raise SyntaxError(_("Error expanding '%s%s'")
+                    raise SyntaxError(_("Error expanding '%s%%%s'")
                                       % (key, format))
                 lm = map.copy()
                 for i in v:
                     lm.update(i)
-                    yield self(format, **lm)
+                    t = self._template(format)
+                    yield self._process(t, lm)
             else:
                 if fl:
                     for f in fl.split("|")[1:]:
                         v = self.filters[f](v)
                 yield v
 
+    def __call__(self, t, **map):
+        '''Perform expansion. t is name of map element to expand. map contains
+        added elements for use during expansion. Is a generator.'''
+        tmpl = self._template(t)
+        iters = [self._process(tmpl, map)]
+        while iters:
+            try:
+                item = iters[0].next()
+            except StopIteration:
+                iters.pop(0)
+                continue
+            if isinstance(item, str):
+                yield item
+            elif item is None:
+                yield ''
+            elif hasattr(item, '__iter__'):
+                iters.insert(0, iter(item))
+            else:
+                yield str(item)
+
 def templatepath(name=None):
     '''return location of template file or directory (if no name).
     returns None if not found.'''

mercurial/transaction.py

@@ -96,9 +96,13 b' def rollback(opener, file):'
     files = {}
     for l in open(file).readlines():
         f, o = l.split('\0')
-        files[f] = o
+        files[f] = int(o)
     for f in files:
         o = files[f]
-        opener(f, "a").truncate(int(o))
+        if o:
+            opener(f, "a").truncate(int(o))
+        else:
+            fn = opener(f).name
+            os.unlink(fn)
     os.unlink(file)
 

mercurial/ui.py

@@ -312,15 +312,11 b' class ui(object):'
         items = self._configitems(section, untrusted=untrusted, abort=True)
         if self.debugflag and not untrusted and self.ucdata:
             uitems = self._configitems(section, untrusted=True, abort=False)
-            keys = uitems.keys()
-            keys.sort()
-            for k in keys:
+            for k in util.sort(uitems):
                 if uitems[k] != items.get(k):
                     self.warn(_("Ignoring untrusted configuration option "
                                 "%s.%s = %s\n") % (section, k, uitems[k]))
-        x = items.items()
-        x.sort()
-        return x
+        return util.sort(items.items())
 
     def walkconfig(self, untrusted=False):
         cdata = self._get_cdata(untrusted)
@@ -335,14 +331,16 b' class ui(object):'
 
         Searched in this order: $HGUSER, [ui] section of hgrcs, $EMAIL
         and stop searching if one of these is set.
-        If not found, use ($LOGNAME or $USER or $LNAME or
-        $USERNAME) +"@full.hostname".
+        If not found and ui.askusername is True, ask the user, else use
+        ($LOGNAME or $USER or $LNAME or $USERNAME) + "@full.hostname".
         """
         user = os.environ.get("HGUSER")
         if user is None:
             user = self.config("ui", "username")
         if user is None:
             user = os.environ.get("EMAIL")
+        if user is None and self.configbool("ui", "askusername"):
+            user = self.prompt(_("Enter a commit username:"), default=None)
         if user is None:
             try:
                 user = '%s@%s' % (util.getuser(), socket.getfqdn())

mercurial/util.py

@@ -15,7 +15,9 b' platform-specific details from the core.'
 from i18n import _
 import cStringIO, errno, getpass, re, shutil, sys, tempfile
 import os, stat, threading, time, calendar, ConfigParser, locale, glob, osutil
-import urlparse
+import imp, urlparse
+
+# Python compatibility
 
 try:
     set = set
@@ -23,6 +25,30 b' try:'
 except NameError:
     from sets import Set as set, ImmutableSet as frozenset
 
+_md5 = None
+def md5(s):
+    global _md5
+    if _md5 is None:
+        try:
+            import hashlib
+            _md5 = hashlib.md5
+        except ImportError:
+            import md5
+            _md5 = md5.md5
+    return _md5(s)
+
+_sha1 = None
+def sha1(s):
+    global _sha1
+    if _sha1 is None:
+        try:
+            import hashlib
+            _sha1 = hashlib.sha1
+        except ImportError:
+            import sha
+            _sha1 = sha.sha
+    return _sha1(s)
+
 try:
     _encoding = os.environ.get("HGENCODING")
     if sys.platform == 'darwin' and not _encoding:
@@ -217,8 +243,8 b' def filter(s, cmd):'
     return pipefilter(s, cmd)
 
 def binary(s):
-    """return true if a string is binary data using diff's heuristic"""
-    if s and '\0' in s[:4096]:
+    """return true if a string is binary data"""
+    if s and '\0' in s:
         return True
     return False
 
@@ -226,6 +252,12 b' def unique(g):'
     """return the uniq elements of iterable g"""
     return dict.fromkeys(g).keys()
 
+def sort(l):
+    if not isinstance(l, list):
+        l = list(l)
+    l.sort()
+    return l
+
 class Abort(Exception):
     """Raised if a command needs to print an error and exit."""
 
@@ -251,12 +283,12 b' def expand_glob(pats):'
         ret.append(p)
     return ret
 
-def patkind(name, dflt_pat='glob'):
+def patkind(name, default):
     """Split a string into an optional pattern kind prefix and the
     actual pattern."""
     for prefix in 're', 'glob', 'path', 'relglob', 'relpath', 'relre':
         if name.startswith(prefix + ':'): return name.split(':', 1)
-    return dflt_pat, name
+    return default, name
 
 def globre(pat, head='^', tail='$'):
     "convert a glob pattern into a regexp"
@@ -386,17 +418,7 b' def canonpath(root, cwd, myname):'
 
         raise Abort('%s not under root' % myname)
 
-def matcher(canonroot, cwd='', names=[], inc=[], exc=[], src=None):
-    return _matcher(canonroot, cwd, names, inc, exc, 'glob', src)
-
-def cmdmatcher(canonroot, cwd='', names=[], inc=[], exc=[], src=None,
-               globbed=False, default=None):
-    default = default or 'relpath'
-    if default == 'relpath' and not globbed:
-        names = expand_glob(names)
-    return _matcher(canonroot, cwd, names, inc, exc, default, src)
-
-def _matcher(canonroot, cwd, names, inc, exc, dflt_pat, src):
+def matcher(canonroot, cwd='', names=[], inc=[], exc=[], src=None, dflt_pat='glob'):
     """build a function to match a set of file patterns
 
     arguments:
@@ -537,13 +559,29 b' def _matcher(canonroot, cwd, names, inc,'
 
 _hgexecutable = None
 
+def main_is_frozen():
+    """return True if we are a frozen executable.
+
+    The code supports py2exe (most common, Windows only) and tools/freeze
+    (portable, not much used).
+    """
+    return (hasattr(sys, "frozen") or # new py2exe
+            hasattr(sys, "importers") or # old py2exe
+            imp.is_frozen("__main__")) # tools/freeze
+
 def hgexecutable():
     """return location of the 'hg' executable.
 
     Defaults to $HG or 'hg' in the search path.
     """
     if _hgexecutable is None:
-        set_hgexecutable(os.environ.get('HG') or find_exe('hg', 'hg'))
+        hg = os.environ.get('HG')
+        if hg:
+            set_hgexecutable(hg)
+        elif main_is_frozen():
+            set_hgexecutable(sys.executable)
+        else:
+            set_hgexecutable(find_exe('hg', 'hg'))
     return _hgexecutable
 
 def set_hgexecutable(path):
@@ -807,7 +845,7 b' def groupname(gid=None):'
 
 # File system features
 
-def checkfolding(path):
+def checkcase(path):
     """
     Check whether the given path is on a case-sensitive filesystem
 
@@ -827,6 +865,53 b' def checkfolding(path):'
     except:
         return True
 
+_fspathcache = {}
+def fspath(name, root):
+    '''Get name in the case stored in the filesystem
+
+    The name is either relative to root, or it is an absolute path starting
+    with root. Note that this function is unnecessary, and should not be
+    called, for case-sensitive filesystems (simply because it's expensive).
+    '''
+    # If name is absolute, make it relative
+    if name.lower().startswith(root.lower()):
+        l = len(root)
+        if name[l] == os.sep or name[l] == os.altsep:
+            l = l + 1
+        name = name[l:]
+
+    if not os.path.exists(os.path.join(root, name)):
+        return None
+
+    seps = os.sep
+    if os.altsep:
+        seps = seps + os.altsep
+    # Protect backslashes. This gets silly very quickly.
+    seps.replace('\\','\\\\')
+    pattern = re.compile(r'([^%s]+)|([%s]+)' % (seps, seps))
+    dir = os.path.normcase(os.path.normpath(root))
+    result = []
+    for part, sep in pattern.findall(name):
+        if sep:
+            result.append(sep)
+            continue
+
+        if dir not in _fspathcache:
+            _fspathcache[dir] = os.listdir(dir)
+        contents = _fspathcache[dir]
+
+        lpart = part.lower()
+        for n in contents:
+            if n.lower() == lpart:
+                result.append(n)
+                break
+        else:
+            # Cannot happen, as the file exists!
+            result.append(part)
+        dir = os.path.join(dir, lpart)
+
+    return ''.join(result)
+
 def checkexec(path):
     """
     Check whether the given path is on a filesystem with UNIX-like exec flags
@@ -854,12 +939,6 b' def checkexec(path):'
         return False
     return not (new_file_has_exec or exec_flags_cannot_flip)
 
-def execfunc(path, fallback):
-    '''return an is_exec() function with default to fallback'''
-    if checkexec(path):
-        return lambda x: is_exec(os.path.join(path, x))
-    return fallback
-
 def checklink(path):
     """check whether the given path is on a symlink-capable filesystem"""
     # mktemp is not racy because symlink creation will fail if the
@@ -872,12 +951,6 b' def checklink(path):'
     except (OSError, AttributeError):
         return False
 
-def linkfunc(path, fallback):
-    '''return an is_link() function with default to fallback'''
-    if checklink(path):
-        return lambda x: os.path.islink(os.path.join(path, x))
-    return fallback
-
 _umask = os.umask(0)
 os.umask(_umask)
 
@@ -1044,12 +1117,12 b" if os.name == 'nt':"
         # through the current COMSPEC. cmd.exe suppress enclosing quotes.
         return '"' + cmd + '"'
 
-    def popen(command):
+    def popen(command, mode='r'):
         # Work around "popen spawned process may not write to stdout
         # under windows"
         # http://bugs.python.org/issue1366
         command += " 2> %s" % nulldev
-        return os.popen(quotecommand(command))
+        return os.popen(quotecommand(command), mode)
 
     def explain_exit(code):
         return _("exited with status %d") % code, code
@@ -1210,8 +1283,8 b' else:'
     def quotecommand(cmd):
         return cmd
 
-    def popen(command):
-        return os.popen(command)
+    def popen(command, mode='r'):
+        return os.popen(command, mode)
 
     def testpid(pid):
         '''return False if pid dead, True if running or not sure'''
@@ -1272,39 +1345,6 b' def find_exe(name, default=None):'
         return name
     return find_in_path(name, os.environ.get('PATH', ''), default=default)
 
-def _buildencodefun():
-    e = '_'
-    win_reserved = [ord(x) for x in '\\:*?"<>|']
-    cmap = dict([ (chr(x), chr(x)) for x in xrange(127) ])
-    for x in (range(32) + range(126, 256) + win_reserved):
-        cmap[chr(x)] = "~%02x" % x
-    for x in range(ord("A"), ord("Z")+1) + [ord(e)]:
-        cmap[chr(x)] = e + chr(x).lower()
-    dmap = {}
-    for k, v in cmap.iteritems():
-        dmap[v] = k
-    def decode(s):
-        i = 0
-        while i < len(s):
-            for l in xrange(1, 4):
-                try:
-                    yield dmap[s[i:i+l]]
-                    i += l
-                    break
-                except KeyError:
-                    pass
-            else:
-                raise KeyError
-    return (lambda s: "".join([cmap[c] for c in s]),
-            lambda s: "".join(list(decode(s))))
-
-encodefilename, decodefilename = _buildencodefun()
-
-def encodedopener(openerfn, fn):
-    def o(path, *args, **kw):
-        return openerfn(fn(path), *args, **kw)
-    return o
-
 def mktempcopy(name, emptyok=False, createmode=None):
     """Create a temporary file with the same contents from name
 

mercurial/verify.py

@@ -7,7 +7,7 b''
 
 from node import nullid, short
 from i18n import _
-import revlog
+import revlog, util
 
 def verify(repo):
     lock = repo.lock()
@@ -17,265 +17,201 b' def verify(repo):'
         del lock
 
 def _verify(repo):
+    mflinkrevs = {}
     filelinkrevs = {}
     filenodes = {}
-    changesets = revisions = files = 0
-    firstbad = [None]
+    revisions = 0
+    badrevs = {}
     errors = [0]
     warnings = [0]
-    neededmanifests = {}
+    ui = repo.ui
+    cl = repo.changelog
+    mf = repo.manifest
 
     def err(linkrev, msg, filename=None):
         if linkrev != None:
-            if firstbad[0] != None:
-                firstbad[0] = min(firstbad[0], linkrev)
-            else:
-                firstbad[0] = linkrev
+            badrevs[linkrev] = True
         else:
-            linkrev = "?"
+            linkrev = '?'
         msg = "%s: %s" % (linkrev, msg)
         if filename:
             msg = "%s@%s" % (filename, msg)
-        repo.ui.warn(" " + msg + "\n")
+        ui.warn(" " + msg + "\n")
         errors[0] += 1
 
+    def exc(linkrev, msg, inst, filename=None):
+        if isinstance(inst, KeyboardInterrupt):
+            ui.warn(_("interrupted"))
+            raise
+        err(linkrev, "%s: %s" % (msg, inst), filename)
+
     def warn(msg):
-        repo.ui.warn(msg + "\n")
+        ui.warn(msg + "\n")
         warnings[0] += 1
 
-    def checksize(obj, name):
+    def checklog(obj, name):
+        if not len(obj) and (havecl or havemf):
+            err(0, _("empty or missing %s") % name)
+            return
+
         d = obj.checksize()
         if d[0]:
             err(None, _("data length off by %d bytes") % d[0], name)
         if d[1]:
             err(None, _("index contains %d extra bytes") % d[1], name)
 
-    def checkversion(obj, name):
         if obj.version != revlog.REVLOGV0:
             if not revlogv1:
                 warn(_("warning: `%s' uses revlog format 1") % name)
         elif revlogv1:
             warn(_("warning: `%s' uses revlog format 0") % name)
 
-    revlogv1 = repo.changelog.version != revlog.REVLOGV0
-    if repo.ui.verbose or not revlogv1:
-        repo.ui.status(_("repository uses revlog format %d\n") %
+    def checkentry(obj, i, node, seen, linkrevs, f):
+        lr = obj.linkrev(node)
+        if lr < 0 or (havecl and lr not in linkrevs):
+            t = "unexpected"
+            if lr < 0 or lr >= len(cl):
+                t = "nonexistent"
+            err(None, _("rev %d point to %s changeset %d") % (i, t, lr), f)
+            if linkrevs:
+                warn(_(" (expected %s)") % " ".join(map(str,linkrevs)))
+            lr = None # can't be trusted
+
+        try:
+            p1, p2 = obj.parents(node)
+            if p1 not in seen and p1 != nullid:
+                err(lr, _("unknown parent 1 %s of %s") %
+                    (short(p1), short(n)), f)
+            if p2 not in seen and p2 != nullid:
+                err(lr, _("unknown parent 2 %s of %s") %
+                    (short(p2), short(p1)), f)
+        except Exception, inst:
+            exc(lr, _("checking parents of %s") % short(node), inst, f)
+
+        if node in seen:
+            err(lr, _("duplicate revision %d (%d)") % (i, seen[n]), f)
+        seen[n] = i
+        return lr
+
+    revlogv1 = cl.version != revlog.REVLOGV0
+    if ui.verbose or not revlogv1:
+        ui.status(_("repository uses revlog format %d\n") %
                        (revlogv1 and 1 or 0))
 
-    havecl = havemf = 1
-    seen = {}
-    repo.ui.status(_("checking changesets\n"))
-    if repo.changelog.count() == 0 and repo.manifest.count() > 1:
-        havecl = 0
-        err(0, _("empty or missing 00changelog.i"))
-    else:
-        checksize(repo.changelog, "changelog")
-
-    for i in xrange(repo.changelog.count()):
-        changesets += 1
-        n = repo.changelog.node(i)
-        l = repo.changelog.linkrev(n)
-        if l != i:
-            err(i, _("incorrect link (%d) for changeset") %(l))
-        if n in seen:
-            err(i, _("duplicates changeset at revision %d") % seen[n])
-        seen[n] = i
-
-        for p in repo.changelog.parents(n):
-            if p not in repo.changelog.nodemap:
-                err(i, _("changeset has unknown parent %s") % short(p))
-        try:
-            changes = repo.changelog.read(n)
-        except KeyboardInterrupt:
-            repo.ui.warn(_("interrupted"))
-            raise
-        except Exception, inst:
-            err(i, _("unpacking changeset: %s") % inst)
-            continue
+    havecl = len(cl) > 0
+    havemf = len(mf) > 0
 
-        if changes[0] not in neededmanifests:
-            neededmanifests[changes[0]] = i
-
-        for f in changes[3]:
-            filelinkrevs.setdefault(f, []).append(i)
-
+    ui.status(_("checking changesets\n"))
     seen = {}
-    repo.ui.status(_("checking manifests\n"))
-    if repo.changelog.count() > 0 and repo.manifest.count() == 0:
-        havemf = 0
-        err(0, _("empty or missing 00manifest.i"))
-    else:
-        checkversion(repo.manifest, "manifest")
-        checksize(repo.manifest, "manifest")
-
-    for i in xrange(repo.manifest.count()):
-        n = repo.manifest.node(i)
-        l = repo.manifest.linkrev(n)
-
-        if l < 0 or (havecl and l >= repo.changelog.count()):
-            err(None, _("bad link (%d) at manifest revision %d") % (l, i))
-
-        if n in neededmanifests:
-            del neededmanifests[n]
-
-        if n in seen:
-            err(l, _("duplicates manifest from %d") % seen[n])
-
-        seen[n] = l
-
-        for p in repo.manifest.parents(n):
-            if p not in repo.manifest.nodemap:
-                err(l, _("manifest has unknown parent %s") % short(p))
+    checklog(cl, "changelog")
+    for i in repo:
+        n = cl.node(i)
+        checkentry(cl, i, n, seen, [i], "changelog")
 
         try:
-            for f, fn in repo.manifest.readdelta(n).iteritems():
-                fns = filenodes.setdefault(f, {})
-                if fn not in fns:
-                    fns[fn] = n
-        except KeyboardInterrupt:
-            repo.ui.warn(_("interrupted"))
-            raise
+            changes = cl.read(n)
+            mflinkrevs.setdefault(changes[0], []).append(i)
+            for f in changes[3]:
+                filelinkrevs.setdefault(f, []).append(i)
         except Exception, inst:
-            err(l, _("reading manifest delta: %s") % inst)
-            continue
-
-    repo.ui.status(_("crosschecking files in changesets and manifests\n"))
+            exc(i, _("unpacking changeset %s") % short(n), inst)
 
-    if havemf > 0:
-        nm = [(c, m) for m, c in neededmanifests.items()]
-        nm.sort()
-        for c, m in nm:
-            err(c, _("changeset refers to unknown manifest %s") % short(m))
-        del neededmanifests, nm
+    ui.status(_("checking manifests\n"))
+    seen = {}
+    checklog(mf, "manifest")
+    for i in mf:
+        n = mf.node(i)
+        lr = checkentry(mf, i, n, seen, mflinkrevs.get(n, []), "manifest")
+        if n in mflinkrevs:
+            del mflinkrevs[n]
 
-    if havecl:
-        fl = filenodes.keys()
-        fl.sort()
-        for f in fl:
-            if f not in filelinkrevs:
-                lrs = [repo.manifest.linkrev(n) for n in filenodes[f]]
-                lrs.sort()
-                err(lrs[0], _("in manifest but not in changeset"), f)
-        del fl
+        try:
+            for f, fn in mf.readdelta(n).iteritems():
+                if not f:
+                    err(lr, _("file without name in manifest"))
+                elif f != "/dev/null":
+                    fns = filenodes.setdefault(f, {})
+                    if fn not in fns:
+                        fns[fn] = n
+        except Exception, inst:
+            exc(lr, _("reading manifest delta %s") % short(n), inst)
+
+    ui.status(_("crosschecking files in changesets and manifests\n"))
 
     if havemf:
-        fl = filelinkrevs.keys()
-        fl.sort()
-        for f in fl:
+        for c, m in util.sort([(c, m) for m in mflinkrevs for c in mflinkrevs[m]]):
+            err(c, _("changeset refers to unknown manifest %s") % short(m))
+        del mflinkrevs
+
+        for f in util.sort(filelinkrevs):
             if f not in filenodes:
                 lr = filelinkrevs[f][0]
                 err(lr, _("in changeset but not in manifest"), f)
-        del fl
 
-    repo.ui.status(_("checking files\n"))
-    ff = dict.fromkeys(filenodes.keys() + filelinkrevs.keys()).keys()
-    ff.sort()
-    for f in ff:
-        if f == "/dev/null":
-            continue
-        files += 1
-        if not f:
-            lr = filelinkrevs[f][0]
-            err(lr, _("file without name in manifest"))
-            continue
+    if havecl:
+        for f in util.sort(filenodes):
+            if f not in filelinkrevs:
+                try:
+                    lr = min([repo.file(f).linkrev(n) for n in filenodes[f]])
+                except:
+                    lr = None
+                err(lr, _("in manifest but not in changeset"), f)
+
+    ui.status(_("checking files\n"))
+    files = util.sort(util.unique(filenodes.keys() + filelinkrevs.keys()))
+    for f in files:
         fl = repo.file(f)
-        checkversion(fl, f)
-        checksize(fl, f)
-
-        if fl.count() == 0:
-            err(filelinkrevs[f][0], _("empty or missing revlog"), f)
-            continue
-
+        checklog(fl, f)
         seen = {}
-        nodes = {nullid: 1}
-        for i in xrange(fl.count()):
+        for i in fl:
             revisions += 1
             n = fl.node(i)
-            flr = fl.linkrev(n)
-
-            if flr < 0 or (havecl and flr not in filelinkrevs.get(f, [])):
-                if flr < 0 or flr >= repo.changelog.count():
-                    err(None, _("rev %d point to nonexistent changeset %d")
-                        % (i, flr), f)
-                else:
-                    err(None, _("rev %d points to unexpected changeset %d")
-                        % (i, flr), f)
-                if f in filelinkrevs:
-                    warn(_(" (expected %s)") % filelinkrevs[f][0])
-                flr = None # can't be trusted
-            else:
-                if havecl:
-                    filelinkrevs[f].remove(flr)
-
-            if n in seen:
-                err(flr, _("duplicate revision %d") % i, f)
+            lr = checkentry(fl, i, n, seen, filelinkrevs.get(f, []), f)
             if f in filenodes:
                 if havemf and n not in filenodes[f]:
-                    err(flr, _("%s not in manifests") % (short(n)), f)
+                    err(lr, _("%s not in manifests") % (short(n)), f)
                 else:
                     del filenodes[f][n]
 
             # verify contents
             try:
                 t = fl.read(n)
-            except KeyboardInterrupt:
-                repo.ui.warn(_("interrupted"))
-                raise
+                rp = fl.renamed(n)
+                if len(t) != fl.size(i):
+                    if not fl._readmeta(n): # ancient copy?
+                        err(lr, _("unpacked size is %s, %s expected") %
+                            (len(t), fl.size(i)), f)
             except Exception, inst:
-                err(flr, _("unpacking %s: %s") % (short(n), inst), f)
-
-            # verify parents
-            try:
-                (p1, p2) = fl.parents(n)
-                if p1 not in nodes:
-                    err(flr, _("unknown parent 1 %s of %s") %
-                        (short(p1), short(n)), f)
-                if p2 not in nodes:
-                    err(flr, _("unknown parent 2 %s of %s") %
-                            (short(p2), short(p1)), f)
-            except KeyboardInterrupt:
-                repo.ui.warn(_("interrupted"))
-                raise
-            except Exception, inst:
-                err(flr, _("checking parents of %s: %s") % (short(n), inst), f)
-            nodes[n] = 1
+                exc(lr, _("unpacking %s") % short(n), inst, f)
 
             # check renames
             try:
-                rp = fl.renamed(n)
                 if rp:
                     fl2 = repo.file(rp[0])
-                    if fl2.count() == 0:
-                        err(flr, _("empty or missing copy source revlog %s:%s")
+                    if not len(fl2):
+                        err(lr, _("empty or missing copy source revlog %s:%s")
                             % (rp[0], short(rp[1])), f)
                     elif rp[1] == nullid:
-                        err(flr, _("copy source revision is nullid %s:%s")
+                        err(lr, _("copy source revision is nullid %s:%s")
                             % (rp[0], short(rp[1])), f)
                     else:
                         rev = fl2.rev(rp[1])
-            except KeyboardInterrupt:
-                repo.ui.warn(_("interrupted"))
-                raise
             except Exception, inst:
-                err(flr, _("checking rename of %s: %s") %
-                    (short(n), inst), f)
+                exc(lr, _("checking rename of %s") % short(n), inst, f)
 
         # cross-check
         if f in filenodes:
-            fns = [(repo.manifest.linkrev(filenodes[f][n]), n)
-                   for n in filenodes[f]]
-            fns.sort()
-            for lr, node in fns:
+            fns = [(mf.linkrev(l), n) for n,l in filenodes[f].items()]
+            for lr, node in util.sort(fns):
                 err(lr, _("%s in manifests not found") % short(node), f)
 
-    repo.ui.status(_("%d files, %d changesets, %d total revisions\n") %
-                   (files, changesets, revisions))
-
+    ui.status(_("%d files, %d changesets, %d total revisions\n") %
+                   (len(files), len(cl), revisions))
     if warnings[0]:
-        repo.ui.warn(_("%d warnings encountered!\n") % warnings[0])
+        ui.warn(_("%d warnings encountered!\n") % warnings[0])
     if errors[0]:
-        repo.ui.warn(_("%d integrity errors encountered!\n") % errors[0])
-        if firstbad[0]:
-            repo.ui.warn(_("(first damaged changeset appears to be %d)\n")
-                         % firstbad[0])
+        ui.warn(_("%d integrity errors encountered!\n") % errors[0])
+        if badrevs:
+            ui.warn(_("(first damaged changeset appears to be %d)\n")
+                    % min(badrevs))
         return 1

setup.py

@@ -19,6 +19,9 b' from distutils.ccompiler import new_comp'
 import mercurial.version
 
 extra = {}
+scripts = ['hg']
+if os.name == 'nt':
+    scripts.append('contrib/win32/hg.bat')
 
 # simplified version of distutils.ccompiler.CCompiler.has_function
 # that actually removes its temporary files.
@@ -88,10 +91,11 b' mercurial.version.remember_version(versi'
 cmdclass = {'install_data': install_package_data}
 
 ext_modules=[
-    Extension('mercurial.mpatch', ['mercurial/mpatch.c']),
+    Extension('mercurial.base85', ['mercurial/base85.c']),
     Extension('mercurial.bdiff', ['mercurial/bdiff.c']),
-    Extension('mercurial.base85', ['mercurial/base85.c']),
-    Extension('mercurial.diffhelpers', ['mercurial/diffhelpers.c'])
+    Extension('mercurial.diffhelpers', ['mercurial/diffhelpers.c']),
+    Extension('mercurial.mpatch', ['mercurial/mpatch.c']),
+    Extension('mercurial.parsers', ['mercurial/parsers.c']),
     ]
 
 packages = ['mercurial', 'mercurial.hgweb', 'hgext', 'hgext.convert']
@@ -118,7 +122,7 b" setup(name='mercurial',"
       url='http://selenic.com/mercurial',
       description='Scalable distributed SCM',
       license='GNU GPL',
-      scripts=['hg'],
+      scripts=scripts,
       packages=packages,
       ext_modules=ext_modules,
       data_files=[(os.path.join('mercurial', root),

templates/changelog.tmpl

@@ -9,6 +9,7 b''
 
 <div class="buttons">
 <a href="#url#shortlog/#rev#{sessionvars%urlparameter}">shortlog</a>
+<a href="#url#graph{sessionvars%urlparameter}">graph</a>
 <a href="#url#tags{sessionvars%urlparameter}">tags</a>
 <a href="#url#file/#node|short#{sessionvars%urlparameter}">files</a>
 #archives%archiveentry#

templates/changeset.tmpl

@@ -6,6 +6,7 b''
 <div class="buttons">
 <a href="#url#log/#rev#{sessionvars%urlparameter}">changelog</a>
 <a href="#url#shortlog/#rev#{sessionvars%urlparameter}">shortlog</a>
+<a href="#url#graph{sessionvars%urlparameter}">graph</a>
 <a href="#url#tags{sessionvars%urlparameter}">tags</a>
 <a href="#url#file/#node|short#{sessionvars%urlparameter}">files</a>
 <a href="#url#raw-rev/#node|short#">raw</a>