hgext: replace uses of hasattr with util.safehasattr

hgext/convert/cvsps.py

@@ -1,847 +1,848 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 version 2 or any later version.
 
 import os
 import re
 import cPickle as pickle
 from mercurial import util
 from mercurial.i18n import _
 from mercurial import hook
+from mercurial import util
 
 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
         .synthetic - is this a synthetic "file ... added on ..." revision?
         .mergepoint- the branch that has been merged from
                      (if present in rlog output)
         .branchpoints- the branches that start at the current entry
     '''
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         return "<%s at 0x%x: %s %s>" % (self.__class__.__name__,
                                         id(self),
                                         self.file,
                                         ".".join(map(str, self.revision)))
 
 class logerror(Exception):
     pass
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath('/foo/bar')
     '/foo/bar'
     >>> getrepopath('c:/foo/bar')
     'c:/foo/bar'
     >>> getrepopath(':pserver:10/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:10c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:c:/foo/bar')
     'c:/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:c:/foo/bar')
     'c:/foo/bar'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # Unfortunately, Windows absolute paths start with a drive letter
     # like 'c:' making it harder to parse. Here we assume that drive
     # letters are only one character long and any CVS component before
     # the repository path is at least 2 characters long, and use this
     # to disambiguate.
     parts = cvspath.split(':')
     if len(parts) == 1:
         return parts[0]
     # Here there is an ambiguous case if we have a port number
     # immediately followed by a Windows driver letter. We assume this
     # never happens and decide it must be CVS path component,
     # therefore ignoring it.
     if len(parts[-2]) > 1:
         return parts[-1].lstrip('0123456789')
     return parts[-2] + ':' + parts[-1]
 
 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+.+;)?$')
     re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
                        r'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
                        r'(.*mergepoint:\s+([^;]+);)?')
     re_70 = re.compile('branches: (.+);$')
 
     file_added_re = re.compile(r'file [^/]+ was (initially )?added on branch')
 
     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 = open(os.path.join('CVS','Repository')).read().strip()
             directory = prefix
             if prefix == ".":
                 prefix = ""
         except IOError:
             raise logerror(_('not a CVS sandbox'))
 
         if prefix and not prefix.endswith(os.sep):
             prefix += os.sep
 
         # Use the Root file in the sandbox, if it exists
         try:
             root = open(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(open(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 = util.normpath(getrepopath(root))
         if not p.endswith('/'):
             p += '/'
         if prefix:
             # looks like normpath replaces "" by "."
             prefix = p + util.normpath(prefix)
         else:
             prefix = p
     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
     branchmap = {} # mapping between branch names and revision numbers
     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))
 
     pfp = util.popen(' '.join(cmd))
     peek = pfp.readline()
     while True:
         line = peek
         if line == '':
             break
         peek = pfp.readline()
         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 = util.normpath(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 logerror(match.group(1))
             match = re_02.match(line)
             if match:
                 raise logerror(match.group(2))
             if re_03.match(line):
                 raise logerror(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 = util.normpath(match.group(1))
             state = 2
 
         elif state == 2:
             # expect 'symbolic names'
             if re_20.match(line):
                 branchmap = {}
                 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))
                 branchmap[match.group(1)] = match.group(2)
 
             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
 
             if match.group(7): # cvsnt mergepoint
                 myrev = match.group(8).split('.')
                 if len(myrev) == 2: # head
                     e.mergepoint = 'HEAD'
                 else:
                     myrev = '.'.join(myrev[:-2] + ['0', myrev[-2]])
                     branches = [b for b in branchmap if branchmap[b] == myrev]
                     assert len(branches) == 1, 'unknown branch: %s' % e.mergepoint
                     e.mergepoint = branches[0]
             else:
                 e.mergepoint = 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) and re_50.match(peek):
                 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)
 
         # When a file is added on a branch B1, CVS creates a synthetic
         # dead trunk revision 1.1 so that the branch has a root.
         # Likewise, if you merge such a file to a later branch B2 (one
         # that already existed when the file was added on B1), CVS
         # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
         # these revisions now, but mark them synthetic so
         # createchangeset() can take care of them.
         if (store and
               e.dead and
               e.revision[-1] == 1 and      # 1.1 or 1.1.x.1
               len(e.comment) == 1 and
               file_added_re.match(e.comment[0])):
             ui.debug('found synthetic revision in %s: %r\n'
                      % (e.rcs, e.comment[0]))
             e.synthetic = True
 
         if store:
             # clean up the results and save in the log.
             store = False
             e.tags = sorted([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
 
             # find the branches starting from this revision
             branchpoints = set()
             for branch, revision in branchmap.iteritems():
                 revparts = tuple([int(i) for i in revision.split('.')])
                 if len(revparts) < 2: # bad tags
                     continue
                 if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                     # normal branch
                     if revparts[:-2] == e.revision:
                         branchpoints.add(branch)
                 elif revparts == (1, 1, 1): # vendor branch
                     if revparts in e.branches:
                         branchpoints.add(branch)
             e.branchpoints = branchpoints
 
             log.append(e)
 
             if len(log) % 100 == 0:
                 ui.status(util.ellipsis('%d %s' % (len(log), e.file), 80)+'\n')
 
     log.sort(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
             log.sort(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, open(cachefile, 'w'))
         else:
             log = oldlog
 
     ui.status(_('%d log entries\n') % len(log))
 
     hook.hook(ui, None, "cvslog", True, log=log)
 
     return log
 
 
 class changeset(object):
     '''Class changeset has the following attributes:
         .id        - integer identifying this changeset (list index)
         .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
         .synthetic - from synthetic revision "file ... added on branch ..."
         .mergepoint- the branch that has been merged from
                      (if present in rlog output)
         .branchpoints- the branches that start at the current entry
     '''
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         return "<%s at 0x%x: %s>" % (self.__class__.__name__,
                                      id(self),
                                      getattr(self, 'id', "(no id)"))
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_('creating changesets\n'))
 
     # Merge changesets
 
     log.sort(key=lambda x: (x.comment, x.author, x.branch, x.date))
 
     changesets = []
     files = set()
     c = None
     for i, e in enumerate(log):
 
         # Check if log entry belongs to the current changeset or not.
 
         # Since CVS is file centric, two different file revisions with
         # different branchpoints should be treated as belonging to two
         # different changesets (and the ordering is important and not
         # honoured by cvsps at this point).
         #
         # Consider the following case:
         # foo 1.1 branchpoints: [MYBRANCH]
         # bar 1.1 branchpoints: [MYBRANCH, MYBRANCH2]
         #
         # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
         # later version of foo may be in MYBRANCH2, so foo should be the
         # first changeset and bar the next and MYBRANCH and MYBRANCH2
         # should both start off of the bar changeset. No provisions are
         # made to ensure that this is, in fact, what happens.
         if not (c and
                   e.comment == c.comment and
                   e.author == c.author and
                   e.branch == c.branch and
-                  (not hasattr(e, 'branchpoints') or
-                    not hasattr (c, 'branchpoints') or
+                  (not util.safehasattr(e, 'branchpoints') or
+                    not util.safehasattr (c, 'branchpoints') or
                     e.branchpoints == c.branchpoints) 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=[],
                           mergepoint=getattr(e, 'mergepoint', None),
                           branchpoints=getattr(e, 'branchpoints', set()))
             changesets.append(c)
             files = set()
             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.add(e.file)
         c.date = e.date       # changeset date is date of latest commit in it
 
     # Mark synthetic changesets
 
     for c in changesets:
         # Synthetic revisions always get their own changeset, because
         # the log message includes the filename.  E.g. if you add file3
         # and file4 on a branch, you get four log entries and three
         # changesets:
         #   "File file3 was added on branch ..." (synthetic, 1 entry)
         #   "File file4 was added on branch ..." (synthetic, 1 entry)
         #   "Add file3 and file4 to fix ..."     (real, 2 entries)
         # Hence the check for 1 entry here.
         c.synthetic = len(c.entries) == 1 and c.entries[0].synthetic
 
     # 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:
         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 = set()
         for e in c.entries:
             tags.update(e.tags)
         # remember tags only if this is the latest changeset to have it
         c.tags = sorted(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:
             # first changeset on a new branch
             # the parent is a changeset with the branch in its
             # branchpoints such that it is the latest possible
             # commit without any intervening, unrelated commits.
 
             for candidate in xrange(i):
                 if c.branch not in changesets[candidate].branchpoints:
                     if p is not None:
                         break
                     continue
                 p = candidate
 
         c.parents = []
         if p is not None:
             p = changesets[p]
 
             # Ensure no changeset has a synthetic changeset as a parent.
             while p.synthetic:
                 assert len(p.parents) <= 1, \
                        _('synthetic changeset cannot have multiple parents')
                 if p.parents:
                     p = p.parents[0]
                 else:
                     p = None
                     break
 
             if p is not None:
                 c.parents.append(p)
 
         if c.mergepoint:
             if c.mergepoint == 'HEAD':
                 c.mergepoint = None
             c.parents.append(changesets[branches[c.mergepoint]])
 
         if mergefrom:
             m = mergefrom.search(c.comment)
             if m:
                 m = m.group(1)
                 if m == 'HEAD':
                     m = None
                 try:
                     candidate = changesets[branches[m]]
                 except KeyError:
                     ui.warn(_("warning: CVS commit message references "
                               "non-existent branch %r:\n%s\n")
                             % (m, c.comment))
                 if m in branches and c.branch != m and not candidate.synthetic:
                     c.parents.append(candidate)
 
         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
 
     # Drop synthetic changesets (safe now that we have ensured no other
     # changesets can have them as parents).
     i = 0
     while i < len(changesets):
         if changesets[i].synthetic:
             del changesets[i]
         else:
             i += 1
 
     # Number changesets
 
     for i, c in enumerate(changesets):
         c.id = i + 1
 
     ui.status(_('%d changeset entries\n') % len(changesets))
 
     hook.hook(ui, None, "cvschangesets", True, changesets=changesets)
 
     return changesets
 
 
 def debugcvsps(ui, *args, **opts):
     '''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.
     '''
     if opts["new_cache"]:
         cache = "write"
     elif opts["update_cache"]:
         cache = "update"
     else:
         cache = None
 
     revisions = opts["revisions"]
 
     try:
         if args:
             log = []
             for d in args:
                 log += createlog(ui, d, root=opts["root"], cache=cache)
         else:
             log = createlog(ui, root=opts["root"], cache=cache)
     except logerror, e:
         ui.write("%r\n"%e)
         return
 
     changesets = createchangeset(ui, log, opts["fuzz"])
     del log
 
     # Print changesets (optionally filtered)
 
     off = len(revisions)
     branches = {}    # latest version number in each branch
     ancestors = {}   # parent branch
     for cs in changesets:
 
         if opts["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 opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]:
             continue
 
         if not off:
             # Note: trailing spaces on several lines here are needed to have
             #       bug-for-bug compatibility with cvsps.
             ui.write('---------------------\n')
             ui.write('PatchSet %d \n' % cs.id)
             ui.write('Date: %s\n' % util.datestr(cs.date,
                                                  '%Y/%m/%d %H:%M:%S %1%2'))
             ui.write('Author: %s\n' % cs.author)
             ui.write('Branch: %s\n' % (cs.branch or 'HEAD'))
             ui.write('Tag%s: %s \n' % (['', 's'][len(cs.tags) > 1],
                                   ','.join(cs.tags) or '(none)'))
             branchpoints = getattr(cs, 'branchpoints', None)
             if branchpoints:
                 ui.write('Branchpoints: %s \n' % ', '.join(branchpoints))
             if opts["parents"] and cs.parents:
                 if len(cs.parents) > 1:
                     ui.write('Parents: %s\n' %
                              (','.join([str(p.id) for p in cs.parents])))
                 else:
                     ui.write('Parent: %d\n' % cs.parents[0].id)
 
             if opts["ancestors"]:
                 b = cs.branch
                 r = []
                 while b:
                     b, c = ancestors[b]
                     r.append('%s:%d:%d' % (b or "HEAD", c, branches[b]))
                 if r:
                     ui.write('Ancestors: %s\n' % (','.join(r)))
 
             ui.write('Log:\n')
             ui.write('%s\n\n' % cs.comment)
             ui.write('Members: \n')
             for f in cs.entries:
                 fn = f.file
                 if fn.startswith(opts["prefix"]):
                     fn = fn[len(opts["prefix"]):]
                 ui.write('\t%s:%s->%s%s \n' % (
                         fn, '.'.join([str(x) for x in f.parent]) or 'INITIAL',
                         '.'.join([str(x) for x in f.revision]),
                         ['', '(DEAD)'][f.dead]))
             ui.write('\n')
 
         # have we seen the start tag?
         if revisions and off:
             if revisions[0] == str(cs.id) or \
                 revisions[0] in cs.tags:
                 off = False
 
         # see if we reached the end tag
         if len(revisions) > 1 and not off:
             if revisions[1] == str(cs.id) or \
                 revisions[1] in cs.tags:
                 break

hgext/convert/git.py

@@ -1,205 +1,205 b''
 # git.py - git support for the convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os
 from mercurial import util
 from mercurial.node import hex, nullid
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
 
 class convert_git(converter_source):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
-    if hasattr(os, 'unsetenv'):
+    if util.safehasattr(os, 'unsetenv'):
         def gitopen(self, s, noerr=False):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 if noerr:
                     (stdin, stdout, stderr) = util.popen3(s)
                     return stdout
                 else:
                     return util.popen(s, 'rb')
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
     else:
         def gitopen(self, s, noerr=False):
             if noerr:
                 (sin, so, se) = util.popen3('GIT_DIR=%s %s' % (self.path, s))
                 return so
             else:
                 return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')
 
     def gitread(self, s):
         fh = self.gitopen(s)
         data = fh.read()
         return data, fh.close()
 
     def __init__(self, ui, path, rev=None):
         super(convert_git, self).__init__(ui, path, rev=rev)
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
             raise NoRepo(_("%s does not look like a Git repository") % path)
 
         checktool('git', 'git')
 
         self.path = path
 
     def getheads(self):
         if not self.rev:
             heads, ret = self.gitread('git rev-parse --branches --remotes')
             heads = heads.splitlines()
         else:
             heads, ret = self.gitread("git rev-parse --verify %s" % self.rev)
             heads = [heads[:-1]]
         if ret:
             raise util.Abort(_('cannot retrieve git heads'))
         return heads
 
     def catfile(self, rev, type):
         if rev == hex(nullid):
             raise IOError()
         data, ret = self.gitread("git cat-file %s %s" % (type, rev))
         if ret:
             raise util.Abort(_('cannot read %r object at %s') % (type, rev))
         return data
 
     def getfile(self, name, rev):
         data = self.catfile(rev, "blob")
         mode = self.modecache[(name, rev)]
         return data, mode
 
     def getchanges(self, version):
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s" % version)
         changes = []
         seen = set()
         entry = None
         for l in fh.read().split('\x00'):
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l
                 continue
             f = l
             if f not in seen:
                 seen.add(f)
                 entry = entry.split()
                 h = entry[3]
                 p = (entry[1] == "100755")
                 s = (entry[1] == "120000")
                 self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                 changes.append((f, h))
             entry = None
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
         return (changes, {})
 
     def getcommit(self, version):
         c = self.catfile(version, "commit") # read the commit hash
         end = c.find("\n\n")
         message = c[end + 2:]
         message = self.recode(message)
         l = c[:end].splitlines()
         parents = []
         author = committer = None
         for e in l[1:]:
             n, v = e.split(" ", 1)
             if n == "author":
                 p = v.split()
                 tm, tz = p[-2:]
                 author = " ".join(p[:-2])
                 if author[0] == "<": author = author[1:-1]
                 author = self.recode(author)
             if n == "committer":
                 p = v.split()
                 tm, tz = p[-2:]
                 committer = " ".join(p[:-2])
                 if committer[0] == "<": committer = committer[1:-1]
                 committer = self.recode(committer)
             if n == "parent":
                 parents.append(v)
 
         if committer and committer != author:
             message += "\ncommitter: %s\n" % committer
         tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
         tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
         date = tm + " " + str(tz)
 
         c = commit(parents=parents, date=date, author=author, desc=message,
                    rev=version)
         return c
 
     def gettags(self):
         tags = {}
         fh = self.gitopen('git ls-remote --tags "%s"' % self.path)
         prefix = 'refs/tags/'
         for line in fh:
             line = line.strip()
             if not line.endswith("^{}"):
                 continue
             node, tag = line.split(None, 1)
             if not tag.startswith(prefix):
                 continue
             tag = tag[len(prefix):-3]
             tags[tag] = node
         if fh.close():
             raise util.Abort(_('cannot read tags from %s') % self.path)
 
         return tags
 
     def getchangedfiles(self, version, i):
         changes = []
         if i is None:
             fh = self.gitopen("git diff-tree --root -m -r %s" % version)
             for l in fh:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
         else:
             fh = self.gitopen('git diff-tree --name-only --root -r %s "%s^%s" --'
                              % (version, version, i + 1))
             changes = [f.rstrip('\n') for f in fh]
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         return changes
 
     def getbookmarks(self):
         bookmarks = {}
 
         # Interesting references in git are prefixed
         prefix = 'refs/heads/'
         prefixlen = len(prefix)
 
         # factor two commands
         gitcmd = { 'remote/': 'git ls-remote --heads origin',
                           '': 'git show-ref'}
 
         # Origin heads
         for reftype in gitcmd:
             try:
                 fh = self.gitopen(gitcmd[reftype], noerr=True)
                 for line in fh:
                     line = line.strip()
                     rev, name = line.split(None, 1)
                     if not name.startswith(prefix):
                         continue
                     name = '%s%s' % (reftype, name[prefixlen:])
                     bookmarks[name] = rev
             except:
                 pass
 
         return bookmarks

hgext/convert/transport.py

@@ -1,128 +1,128 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2007 Daniel Holth <[e-mail]>
 # This is a stripped-down version of the original bzr-svn transport.py,
 # Copyright (C) 2006 Jelmer Vernooij <[e-mail]>
 
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation; either version 2 of the License, or
 # (at your option) any later version.
 
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 
 # You should have received a copy of the GNU General Public License
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 from svn.core import SubversionException, Pool
 import svn.ra
 import svn.client
 import svn.core
 
 # Some older versions of the Python bindings need to be
 # explicitly initialized. But what we want to do probably
 # won't work worth a darn against those libraries anyway!
 svn.ra.initialize()
 
 svn_config = svn.core.svn_config_get_config(None)
 
 
 def _create_auth_baton(pool):
     """Create a Subversion authentication baton. """
     import svn.client
     # Give the client context baton a suite of authentication
     # providers.h
     providers = [
         svn.client.get_simple_provider(pool),
         svn.client.get_username_provider(pool),
         svn.client.get_ssl_client_cert_file_provider(pool),
         svn.client.get_ssl_client_cert_pw_file_provider(pool),
         svn.client.get_ssl_server_trust_file_provider(pool),
         ]
     # Platform-dependant authentication methods
     getprovider = getattr(svn.core, 'svn_auth_get_platform_specific_provider',
                           None)
     if getprovider:
         # Available in svn >= 1.6
         for name in ('gnome_keyring', 'keychain', 'kwallet', 'windows'):
             for type in ('simple', 'ssl_client_cert_pw', 'ssl_server_trust'):
                 p = getprovider(name, type, pool)
                 if p:
                     providers.append(p)
     else:
-        if hasattr(svn.client, 'get_windows_simple_provider'):
+        if util.safehasattr(svn.client, 'get_windows_simple_provider'):
             providers.append(svn.client.get_windows_simple_provider(pool))
 
     return svn.core.svn_auth_open(providers, pool)
 
 class NotBranchError(SubversionException):
     pass
 
 class SvnRaTransport(object):
     """
     Open an ra connection to a Subversion repository.
     """
     def __init__(self, url="", ra=None):
         self.pool = Pool()
         self.svn_url = url
         self.username = ''
         self.password = ''
 
         # Only Subversion 1.4 has reparent()
-        if ra is None or not hasattr(svn.ra, 'reparent'):
+        if ra is None or not util.safehasattr(svn.ra, 'reparent'):
             self.client = svn.client.create_context(self.pool)
             ab = _create_auth_baton(self.pool)
             if False:
                 svn.core.svn_auth_set_parameter(
                     ab, svn.core.SVN_AUTH_PARAM_DEFAULT_USERNAME, self.username)
                 svn.core.svn_auth_set_parameter(
                     ab, svn.core.SVN_AUTH_PARAM_DEFAULT_PASSWORD, self.password)
             self.client.auth_baton = ab
             self.client.config = svn_config
             try:
                 self.ra = svn.client.open_ra_session(
                     self.svn_url.encode('utf8'),
                     self.client, self.pool)
             except SubversionException, (inst, num):
                 if num in (svn.core.SVN_ERR_RA_ILLEGAL_URL,
                            svn.core.SVN_ERR_RA_LOCAL_REPOS_OPEN_FAILED,
                            svn.core.SVN_ERR_BAD_URL):
                     raise NotBranchError(url)
                 raise
         else:
             self.ra = ra
             svn.ra.reparent(self.ra, self.svn_url.encode('utf8'))
 
     class Reporter(object):
         def __init__(self, reporter_data):
             self._reporter, self._baton = reporter_data
 
         def set_path(self, path, revnum, start_empty, lock_token, pool=None):
             svn.ra.reporter2_invoke_set_path(self._reporter, self._baton,
                         path, revnum, start_empty, lock_token, pool)
 
         def delete_path(self, path, pool=None):
             svn.ra.reporter2_invoke_delete_path(self._reporter, self._baton,
                     path, pool)
 
         def link_path(self, path, url, revision, start_empty, lock_token,
                       pool=None):
             svn.ra.reporter2_invoke_link_path(self._reporter, self._baton,
                     path, url, revision, start_empty, lock_token,
                     pool)
 
         def finish_report(self, pool=None):
             svn.ra.reporter2_invoke_finish_report(self._reporter,
                     self._baton, pool)
 
         def abort_report(self, pool=None):
             svn.ra.reporter2_invoke_abort_report(self._reporter,
                     self._baton, pool)
 
     def do_update(self, revnum, path, *args, **kwargs):
         return self.Reporter(svn.ra.do_update(self.ra, revnum, path,
                                               *args, **kwargs))

hgext/inotify/__init__.py

@@ -1,89 +1,90 b''
 # __init__.py - inotify-based status acceleration for Linux
 #
 # Copyright 2006, 2007, 2008 Bryan O'Sullivan <[e-mail]>
 # Copyright 2007, 2008 Brendan Cully <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''accelerate status report using Linux's inotify service'''
 
 # todo: socket permissions
 
 from mercurial.i18n import _
+from mercurial import util
 import server
 from client import client, QueryFailed
 
 def serve(ui, repo, **opts):
     '''start an inotify server for this repository'''
     server.start(ui, repo.dirstate, repo.root, opts)
 
 def debuginotify(ui, repo, **opts):
     '''debugging information for inotify extension
 
     Prints the list of directories being watched by the inotify server.
     '''
     cli = client(ui, repo)
     response = cli.debugquery()
 
     ui.write(_('directories being watched:\n'))
     for path in response:
         ui.write(('  %s/\n') % path)
 
 def reposetup(ui, repo):
-    if not hasattr(repo, 'dirstate'):
+    if not util.safehasattr(repo, 'dirstate'):
         return
 
     class inotifydirstate(repo.dirstate.__class__):
 
         # We'll set this to false after an unsuccessful attempt so that
         # next calls of status() within the same instance don't try again
         # to start an inotify server if it won't start.
         _inotifyon = True
 
         def status(self, match, subrepos, ignored, clean, unknown):
             files = match.files()
             if '.' in files:
                 files = []
             if self._inotifyon and not ignored and not subrepos and not self._dirty:
                 cli = client(ui, repo)
                 try:
                     result = cli.statusquery(files, match, False,
                                             clean, unknown)
                 except QueryFailed, instr:
                     ui.debug(str(instr))
                     # don't retry within the same hg instance
                     inotifydirstate._inotifyon = False
                     pass
                 else:
                     if ui.config('inotify', 'debug'):
                         r2 = super(inotifydirstate, self).status(
                             match, [], False, clean, unknown)
                         for c, a, b in zip('LMARDUIC', result, r2):
                             for f in a:
                                 if f not in b:
                                     ui.warn('*** inotify: %s +%s\n' % (c, f))
                             for f in b:
                                 if f not in a:
                                     ui.warn('*** inotify: %s -%s\n' % (c, f))
                         result = r2
                     return result
             return super(inotifydirstate, self).status(
                 match, subrepos, ignored, clean, unknown)
 
     repo.dirstate.__class__ = inotifydirstate
 
 cmdtable = {
     'debuginotify':
         (debuginotify, [], ('hg debuginotify')),
     '^inserve':
         (serve,
          [('d', 'daemon', None, _('run server in background')),
           ('', 'daemon-pipefds', '',
            _('used internally by daemon mode'), _('NUM')),
           ('t', 'idle-timeout', '',
            _('minutes to sit idle before exiting'), _('NUM')),
           ('', 'pid-file', '',
            _('name of file to write process ID to'), _('FILE'))],
          _('hg inserve [OPTION]...')),
     }

hgext/pager.py

@@ -1,117 +1,117 b''
 # pager.py - display output using a pager
 #
 # Copyright 2008 David Soria Parra <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 #
 # To load the extension, add it to your configuration file:
 #
 #   [extension]
 #   pager =
 #
 # Run "hg help pager" to get info on configuration.
 
 '''browse command output with an external pager
 
 To set the pager that should be used, set the application variable::
 
   [pager]
   pager = less -FRSX
 
 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. Below is the default list of commands to be paged::
 
   [pager]
   attend = annotate, cat, diff, export, glog, log, qdiff
 
 Setting pager.attend to an empty value will cause all commands to be
 paged.
 
 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 your user configuration file.
 
 The --pager=... option can also be used to control when the pager is
 used. Use a boolean value like yes, no, on, off, or use auto for
 normal behavior.
 '''
 
 import sys, os, signal, shlex, errno
 from mercurial import commands, dispatch, util, extensions
 from mercurial.i18n import _
 
 def _runpager(p):
-    if not hasattr(os, 'fork'):
+    if not util.safehasattr(os, 'fork'):
         sys.stdout = util.popen(p, 'wb')
         if util.isatty(sys.stderr):
             sys.stderr = sys.stdout
         return
     fdin, fdout = os.pipe()
     pid = os.fork()
     if pid == 0:
         os.close(fdin)
         os.dup2(fdout, sys.stdout.fileno())
         if util.isatty(sys.stderr):
             os.dup2(fdout, sys.stderr.fileno())
         os.close(fdout)
         return
     os.dup2(fdin, sys.stdin.fileno())
     os.close(fdin)
     os.close(fdout)
     try:
         os.execvp('/bin/sh', ['/bin/sh', '-c', p])
     except OSError, e:
         if e.errno == errno.ENOENT:
             # no /bin/sh, try executing the pager directly
             args = shlex.split(p)
             os.execvp(args[0], args)
         else:
             raise
 
 def uisetup(ui):
     if ui.plain() or '--debugger' in sys.argv or not util.isatty(sys.stdout):
         return
 
     def pagecmd(orig, ui, options, cmd, cmdfunc):
         p = ui.config("pager", "pager", os.environ.get("PAGER"))
 
         if p:
             attend = ui.configlist('pager', 'attend', attended)
             auto = options['pager'] == 'auto'
             always = util.parsebool(options['pager'])
             if (always or auto and
                 (cmd in attend or
                  (cmd not in ui.configlist('pager', 'ignore') and not attend))):
                 ui.setconfig('ui', 'formatted', ui.formatted())
                 ui.setconfig('ui', 'interactive', False)
                 _runpager(p)
                 if ui.configbool('pager', 'quiet'):
                     signal.signal(signal.SIGPIPE, signal.SIG_DFL)
         return orig(ui, options, cmd, cmdfunc)
 
     extensions.wrapfunction(dispatch, '_runcommand', pagecmd)
 
 def extsetup(ui):
     commands.globalopts.append(
         ('', 'pager', 'auto',
          _("when to paginate (boolean, always, auto, or never)"),
          _('TYPE')))
 
 attended = ['annotate', 'cat', 'diff', 'export', 'glog', 'log', 'qdiff']

hgext/relink.py

@@ -1,183 +1,184 b''
 # Mercurial extension to provide 'hg relink' command
 #
 # Copyright (C) 2007 Brendan Cully <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """recreates hardlinks between repository clones"""
 
 from mercurial import hg, util
 from mercurial.i18n import _
 import os, stat
 
 def relink(ui, repo, origin=None, **opts):
     """recreate hardlinks between two repositories
 
     When repositories are cloned locally, their data files will be
     hardlinked so that they only use the space of a single repository.
 
     Unfortunately, subsequent pulls into either repository will break
     hardlinks for any files touched by the new changesets, even if
     both repositories end up pulling the same changes.
 
     Similarly, passing --rev to "hg clone" will fail to use any
     hardlinks, falling back to a complete copy of the source
     repository.
 
     This command lets you recreate those hardlinks and reclaim that
     wasted space.
 
     This repository will be relinked to share space with ORIGIN, which
     must be on the same local disk. If ORIGIN is omitted, looks for
     "default-relink", then "default", in [paths].
 
     Do not attempt any read operations on this repository while the
     command is running. (Both repositories will be locked against
     writes.)
     """
-    if not hasattr(util, 'samefile') or not hasattr(util, 'samedevice'):
+    if (not util.safehasattr(util, 'samefile') or
+        not util.safehasattr(util, 'samedevice')):
         raise util.Abort(_('hardlinks are not supported on this system'))
     src = hg.repository(ui, ui.expandpath(origin or 'default-relink',
                                           origin or 'default'))
     if not src.local():
         raise util.Abort(_('must specify local origin repository'))
     ui.status(_('relinking %s to %s\n') % (src.store.path, repo.store.path))
     if repo.root == src.root:
         ui.status(_('there is nothing to relink\n'))
         return
 
     locallock = repo.lock()
     try:
         remotelock = src.lock()
         try:
             candidates = sorted(collect(src, ui))
             targets = prune(candidates, src.store.path, repo.store.path, ui)
             do_relink(src.store.path, repo.store.path, targets, ui)
         finally:
             remotelock.release()
     finally:
         locallock.release()
 
 def collect(src, ui):
     seplen = len(os.path.sep)
     candidates = []
     live = len(src['tip'].manifest())
     # Your average repository has some files which were deleted before
     # the tip revision. We account for that by assuming that there are
     # 3 tracked files for every 2 live files as of the tip version of
     # the repository.
     #
     # mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
     total = live * 3 // 2
     src = src.store.path
     pos = 0
     ui.status(_("tip has %d files, estimated total number of files: %s\n")
               % (live, total))
     for dirpath, dirnames, filenames in os.walk(src):
         dirnames.sort()
         relpath = dirpath[len(src) + seplen:]
         for filename in sorted(filenames):
             if not filename[-2:] in ('.d', '.i'):
                 continue
             st = os.stat(os.path.join(dirpath, filename))
             if not stat.S_ISREG(st.st_mode):
                 continue
             pos += 1
             candidates.append((os.path.join(relpath, filename), st))
             ui.progress(_('collecting'), pos, filename, _('files'), total)
 
     ui.progress(_('collecting'), None)
     ui.status(_('collected %d candidate storage files\n') % len(candidates))
     return candidates
 
 def prune(candidates, src, dst, ui):
     def linkfilter(src, dst, st):
         try:
             ts = os.stat(dst)
         except OSError:
             # Destination doesn't have this file?
             return False
         if util.samefile(src, dst):
             return False
         if not util.samedevice(src, dst):
             # No point in continuing
             raise util.Abort(
                 _('source and destination are on different devices'))
         if st.st_size != ts.st_size:
             return False
         return st
 
     targets = []
     total = len(candidates)
     pos = 0
     for fn, st in candidates:
         pos += 1
         srcpath = os.path.join(src, fn)
         tgt = os.path.join(dst, fn)
         ts = linkfilter(srcpath, tgt, st)
         if not ts:
             ui.debug('not linkable: %s\n' % fn)
             continue
         targets.append((fn, ts.st_size))
         ui.progress(_('pruning'), pos, fn, _('files'), total)
 
     ui.progress(_('pruning'), None)
     ui.status(_('pruned down to %d probably relinkable files\n') % len(targets))
     return targets
 
 def do_relink(src, dst, files, ui):
     def relinkfile(src, dst):
         bak = dst + '.bak'
         os.rename(dst, bak)
         try:
             util.oslink(src, dst)
         except OSError:
             os.rename(bak, dst)
             raise
         os.remove(bak)
 
     CHUNKLEN = 65536
     relinked = 0
     savedbytes = 0
 
     pos = 0
     total = len(files)
     for f, sz in files:
         pos += 1
         source = os.path.join(src, f)
         tgt = os.path.join(dst, f)
         # Binary mode, so that read() works correctly, especially on Windows
         sfp = file(source, 'rb')
         dfp = file(tgt, 'rb')
         sin = sfp.read(CHUNKLEN)
         while sin:
             din = dfp.read(CHUNKLEN)
             if sin != din:
                 break
             sin = sfp.read(CHUNKLEN)
         sfp.close()
         dfp.close()
         if sin:
             ui.debug('not linkable: %s\n' % f)
             continue
         try:
             relinkfile(source, tgt)
             ui.progress(_('relinking'), pos, f, _('files'), total)
             relinked += 1
             savedbytes += sz
         except OSError, inst:
             ui.warn('%s: %s\n' % (tgt, str(inst)))
 
     ui.progress(_('relinking'), None)
 
     ui.status(_('relinked %d files (%s reclaimed)\n') %
               (relinked, util.bytecount(savedbytes)))
 
 cmdtable = {
     'relink': (
         relink,
         [],
         _('[ORIGIN]')
     )
 }