global: mass rewrite to use modern exception syntax

Python 2.6 introduced the "except type as instance" syntax, replacing
the "except type, instance" syntax that came before. Python 3 dropped
support for the latter syntax. Since we no longer support Python 2.4 or
2.5, we have no need to continue supporting the "except type, instance".

This patch mass rewrites the exception syntax to be Python 2.6+ and
Python 3 compatible.

This patch was produced by running `2to3 -f except -w -n .`.

contrib/check-code.py

@@ -1,571 +1,571 b''
 #!/usr/bin/env python
 #
 # check-code - a style and portability checker for Mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """style and portability checker for Mercurial
 
 when a rule triggers wrong, do one of the following (prefer one from top):
  * do the work-around the rule suggests
  * doublecheck that it is a false match
  * improve the rule pattern
  * add an ignore pattern to the rule (3rd arg) which matches your good line
    (you can append a short comment and match this, like: #re-raises, # no-py24)
  * change the pattern to a warning and list the exception in test-check-code-hg
  * ONLY use no--check-code for skipping entire files from external sources
 """
 
 import re, glob, os, sys
 import keyword
 import optparse
 try:
     import re2
 except ImportError:
     re2 = None
 
 def compilere(pat, multiline=False):
     if multiline:
         pat = '(?m)' + pat
     if re2:
         try:
             return re2.compile(pat)
         except re2.error:
             pass
     return re.compile(pat)
 
 def repquote(m):
     fromc = '.:'
     tochr = 'pq'
     def encodechr(i):
         if i > 255:
             return 'u'
         c = chr(i)
         if c in ' \n':
             return c
         if c.isalpha():
             return 'x'
         if c.isdigit():
             return 'n'
         try:
             return tochr[fromc.find(c)]
         except (ValueError, IndexError):
             return 'o'
     t = m.group('text')
     tt = ''.join(encodechr(i) for i in xrange(256))
     t = t.translate(tt)
     return m.group('quote') + t + m.group('quote')
 
 def reppython(m):
     comment = m.group('comment')
     if comment:
         l = len(comment.rstrip())
         return "#" * l + comment[l:]
     return repquote(m)
 
 def repcomment(m):
     return m.group(1) + "#" * len(m.group(2))
 
 def repccomment(m):
     t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
     return m.group(1) + t + "*/"
 
 def repcallspaces(m):
     t = re.sub(r"\n\s+", "\n", m.group(2))
     return m.group(1) + t
 
 def repinclude(m):
     return m.group(1) + "<foo>"
 
 def rephere(m):
     t = re.sub(r"\S", "x", m.group(2))
     return m.group(1) + t
 
 
 testpats = [
   [
     (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"),
     (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"),
     (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
     (r'(?<!hg )grep.*-a', "don't use 'grep -a', use in-line python"),
     (r'sed.*-i', "don't use 'sed -i', use a temporary file"),
     (r'\becho\b.*\\n', "don't use 'echo \\n', use printf"),
     (r'echo -n', "don't use 'echo -n', use printf"),
     (r'(^|\|\s*)\bwc\b[^|]*$\n(?!.*\(re\))', "filter wc output"),
     (r'head -c', "don't use 'head -c', use 'dd'"),
     (r'tail -n', "don't use the '-n' option to tail, just use '-<num>'"),
     (r'sha1sum', "don't use sha1sum, use $TESTDIR/md5sum.py"),
     (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
     (r'printf.*[^\\]\\([1-9]|0\d)', "don't use 'printf \NNN', use Python"),
     (r'printf.*[^\\]\\x', "don't use printf \\x, use Python"),
     (r'\$\(.*\)', "don't use $(expr), use `expr`"),
     (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
     (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
      "use egrep for extended grep syntax"),
     (r'/bin/', "don't use explicit paths for tools"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'export.*=', "don't export and assign at once"),
     (r'^source\b', "don't use 'source', use '.'"),
     (r'touch -d', "don't use 'touch -d', use 'touch -t' instead"),
     (r'ls +[^|\n-]+ +-', "options to 'ls' must come before filenames"),
     (r'[^>\n]>\s*\$HGRCPATH', "don't overwrite $HGRCPATH, append to it"),
     (r'^stop\(\)', "don't use 'stop' as a shell function name"),
     (r'(\[|\btest\b).*-e ', "don't use 'test -e', use 'test -f'"),
     (r'\[\[\s+[^\]]*\]\]', "don't use '[[ ]]', use '[ ]'"),
     (r'^alias\b.*=', "don't use alias, use a function"),
     (r'if\s*!', "don't use '!' to negate exit status"),
     (r'/dev/u?random', "don't use entropy, use /dev/zero"),
     (r'do\s*true;\s*done', "don't use true as loop body, use sleep 0"),
     (r'^( *)\t', "don't use tabs to indent"),
     (r'sed (-e )?\'(\d+|/[^/]*/)i(?!\\\n)',
      "put a backslash-escaped newline after sed 'i' command"),
     (r'^diff *-\w*u.*$\n(^  \$ |^$)', "prefix diff -u with cmp"),
     (r'seq ', "don't use 'seq', use $TESTDIR/seq.py")
   ],
   # warnings
   [
     (r'^function', "don't use 'function', use old style"),
     (r'^diff.*-\w*N', "don't use 'diff -N'"),
     (r'\$PWD|\${PWD}', "don't use $PWD, use `pwd`"),
     (r'^([^"\'\n]|("[^"\n]*")|(\'[^\'\n]*\'))*\^', "^ must be quoted"),
     (r'kill (`|\$\()', "don't use kill, use killdaemons.py")
   ]
 ]
 
 testfilters = [
     (r"( *)(#([^\n]*\S)?)", repcomment),
     (r"<<(\S+)((.|\n)*?\n\1)", rephere),
 ]
 
 winglobmsg = "use (glob) to match Windows paths too"
 uprefix = r"^  \$ "
 utestpats = [
   [
     (r'^(\S.*||  [$>] .*)[ \t]\n', "trailing whitespace on non-output"),
     (uprefix + r'.*\|\s*sed[^|>\n]*\n',
      "use regex test output patterns instead of sed"),
     (uprefix + r'(true|exit 0)', "explicit zero exit unnecessary"),
     (uprefix + r'.*(?<!\[)\$\?', "explicit exit code checks unnecessary"),
     (uprefix + r'.*\|\| echo.*(fail|error)',
      "explicit exit code checks unnecessary"),
     (uprefix + r'set -e', "don't use set -e"),
     (uprefix + r'(\s|fi\b|done\b)', "use > for continued lines"),
     (uprefix + r'.*:\.\S*/', "x:.y in a path does not work on msys, rewrite "
      "as x://.y, or see `hg log -k msys` for alternatives", r'-\S+:\.|' #-Rxxx
      '# no-msys'), # in test-pull.t which is skipped on windows
     (r'^  saved backup bundle to \$TESTTMP.*\.hg$', winglobmsg),
     (r'^  changeset .* references (corrupted|missing) \$TESTTMP/.*[^)]$',
      winglobmsg),
     (r'^  pulling from \$TESTTMP/.*[^)]$', winglobmsg,
      '\$TESTTMP/unix-repo$'), # in test-issue1802.t which skipped on windows
     (r'^  reverting (?!subrepo ).*/.*[^)]$', winglobmsg),
     (r'^  cloning subrepo \S+/.*[^)]$', winglobmsg),
     (r'^  pushing to \$TESTTMP/.*[^)]$', winglobmsg),
     (r'^  pushing subrepo \S+/\S+ to.*[^)]$', winglobmsg),
     (r'^  moving \S+/.*[^)]$', winglobmsg),
     (r'^  no changes made to subrepo since.*/.*[^)]$', winglobmsg),
     (r'^  .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg),
     (r'^  .*file://\$TESTTMP',
      'write "file:/*/$TESTTMP" + (glob) to match on windows too'),
     (r'^  (cat|find): .*: No such file or directory',
      'use test -f to test for file existence'),
   ],
   # warnings
   [
     (r'^  [^*?/\n]* \(glob\)$',
      "glob match with no glob character (?*/)"),
   ]
 ]
 
 for i in [0, 1]:
     for tp in testpats[i]:
         p = tp[0]
         m = tp[1]
         if p.startswith(r'^'):
             p = r"^  [$>] (%s)" % p[1:]
         else:
             p = r"^  [$>] .*(%s)" % p
         utestpats[i].append((p, m) + tp[2:])
 
 utestfilters = [
     (r"<<(\S+)((.|\n)*?\n  > \1)", rephere),
     (r"( *)(#([^\n]*\S)?)", repcomment),
 ]
 
 pypats = [
   [
     (r'\([^)]*\*\w[^()]+\w+=', "can't pass varargs with keyword in Py2.5"),
     (r'^\s*def\s*\w+\s*\(.*,\s*\(',
      "tuple parameter unpacking not available in Python 3+"),
     (r'lambda\s*\(.*,.*\)',
      "tuple parameter unpacking not available in Python 3+"),
     (r'import (.+,[^.]+\.[^.]+|[^.]+\.[^.]+,)',
      '2to3 can\'t always rewrite "import qux, foo.bar", '
      'use "import foo.bar" on its own line instead.'),
     (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"),
     (r'\breduce\s*\(.*', "reduce is not available in Python 3+"),
     (r'dict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}',
      'dict-from-generator'),
     (r'\.has_key\b', "dict.has_key is not available in Python 3+"),
     (r'\s<>\s', '<> operator is not available in Python 3+, use !='),
     (r'^\s*\t', "don't use tabs"),
     (r'\S;\s*\n', "semicolon"),
     (r'[^_]_\([ \t\n]*(?:"[^"]+"[ \t\n+]*)+%', "don't use % inside _()"),
     (r"[^_]_\([ \t\n]*(?:'[^']+'[ \t\n+]*)+%", "don't use % inside _()"),
     (r'(\w|\)),\w', "missing whitespace after ,"),
     (r'(\w|\))[+/*\-<>]\w', "missing whitespace in expression"),
     (r'^\s+(\w|\.)+=\w[^,()\n]*$', "missing whitespace in assignment"),
     (r'.{81}', "line too long"),
     (r' x+[xo][\'"]\n\s+[\'"]x', 'string join across lines with no space'),
     (r'[^\n]\Z', "no trailing newline"),
     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
 #    (r'^\s+[^_ \n][^_. \n]+_[^_\n]+\s*=',
 #     "don't use underbars in identifiers"),
     (r'^\s+(self\.)?[A-za-z][a-z0-9]+[A-Z]\w* = ',
      "don't use camelcase in identifiers"),
     (r'^\s*(if|while|def|class|except|try)\s[^[\n]*:\s*[^\\n]#\s]+',
      "linebreak after :"),
     (r'class\s[^( \n]+:', "old-style class, use class foo(object)"),
     (r'class\s[^( \n]+\(\):',
      "class foo() creates old style object, use class foo(object)"),
     (r'\b(%s)\(' % '|'.join(k for k in keyword.kwlist
                             if k not in ('print', 'exec')),
      "Python keyword is not a function"),
     (r',]', "unneeded trailing ',' in list"),
 #    (r'class\s[A-Z][^\(]*\((?!Exception)',
 #     "don't capitalize non-exception classes"),
 #    (r'in range\(', "use xrange"),
 #    (r'^\s*print\s+', "avoid using print in core and extensions"),
     (r'[\x80-\xff]', "non-ASCII character literal"),
     (r'("\')\.format\(', "str.format() has no bytes counterpart, use %"),
     (r'^\s*(%s)\s\s' % '|'.join(keyword.kwlist),
      "gratuitous whitespace after Python keyword"),
     (r'([\(\[][ \t]\S)|(\S[ \t][\)\]])', "gratuitous whitespace in () or []"),
 #    (r'\s\s=', "gratuitous whitespace before ="),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
      "missing whitespace around operator"),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\s',
      "missing whitespace around operator"),
     (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=|%=)\S',
      "missing whitespace around operator"),
     (r'[^^+=*/!<>&| %-](\s=|=\s)[^= ]',
      "wrong whitespace around ="),
     (r'\([^()]*( =[^=]|[^<>!=]= )',
      "no whitespace around = for named parameters"),
     (r'raise Exception', "don't raise generic exceptions"),
     (r'raise [^,(]+, (\([^\)]+\)|[^,\(\)]+)$',
      "don't use old-style two-argument raise, use Exception(message)"),
     (r' is\s+(not\s+)?["\'0-9-]', "object comparison with literal"),
     (r' [=!]=\s+(True|False|None)',
      "comparison with singleton, use 'is' or 'is not' instead"),
     (r'^\s*(while|if) [01]:',
      "use True/False for constant Boolean expression"),
     (r'(?:(?<!def)\s+|\()hasattr',
      'hasattr(foo, bar) is broken, use util.safehasattr(foo, bar) instead'),
     (r'opener\([^)]*\).read\(',
      "use opener.read() instead"),
     (r'opener\([^)]*\).write\(',
      "use opener.write() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.read\(',
      "use util.readfile() instead"),
     (r'[\s\(](open|file)\([^)]*\)\.write\(',
      "use util.writefile() instead"),
     (r'^[\s\(]*(open(er)?|file)\([^)]*\)',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'[\s\(](open|file)\([^)]*\)\.',
      "always assign an opened file to a variable, and close it afterwards"),
     (r'(?i)descend[e]nt', "the proper spelling is descendAnt"),
     (r'\.debug\(\_', "don't mark debug messages for translation"),
     (r'\.strip\(\)\.split\(\)', "no need to strip before splitting"),
     (r'^\s*except\s*:', "naked except clause", r'#.*re-raises'),
     (r':\n(    )*( ){1,3}[^ ]', "must indent 4 spaces"),
     (r'ui\.(status|progress|write|note|warn)\([\'\"]x',
      "missing _() in ui message (use () to hide false-positives)"),
     (r'release\(.*wlock, .*lock\)', "wrong lock release order"),
     (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"),
     (r'os\.path\.join\(.*, *(""|\'\')\)',
      "use pathutil.normasprefix(path) instead of os.path.join(path, '')"),
     (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'),
   ],
   # warnings
   [
     (r'(^| )pp +xxxxqq[ \n][^\n]', "add two newlines after '.. note::'"),
   ]
 ]
 
 pyfilters = [
     (r"""(?msx)(?P<comment>\#.*?$)|
          ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
           (?P<text>(([^\\]|\\.)*?))
           (?P=quote))""", reppython),
 ]
 
 txtfilters = []
 
 txtpats = [
   [
     ('\s$', 'trailing whitespace'),
     ('.. note::[ \n][^\n]', 'add two newlines after note::')
   ],
   []
 ]
 
 cpats = [
   [
     (r'//', "don't use //-style comments"),
     (r'^  ', "don't use spaces to indent"),
     (r'\S\t', "don't use tabs except for indent"),
     (r'(\S[ \t]+|^[ \t]+)\n', "trailing whitespace"),
     (r'.{81}', "line too long"),
     (r'(while|if|do|for)\(', "use space after while/if/do/for"),
     (r'return\(', "return is not a function"),
     (r' ;', "no space before ;"),
     (r'[^;] \)', "no space before )"),
     (r'[)][{]', "space between ) and {"),
     (r'\w+\* \w+', "use int *foo, not int* foo"),
     (r'\W\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
     (r'\w+ (\+\+|--)', "use foo++, not foo ++"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'^[^#]\w[+/*]\w', "missing whitespace in expression"),
     (r'^#\s+\w', "use #foo, not # foo"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'^\s*#import\b', "use only #include in standard C code"),
   ],
   # warnings
   []
 ]
 
 cfilters = [
     (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
     (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
     (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
     (r'(\()([^)]+\))', repcallspaces),
 ]
 
 inutilpats = [
   [
     (r'\bui\.', "don't use ui in util"),
   ],
   # warnings
   []
 ]
 
 inrevlogpats = [
   [
     (r'\brepo\.', "don't use repo in revlog"),
   ],
   # warnings
   []
 ]
 
 webtemplatefilters = []
 
 webtemplatepats = [
   [],
   [
     (r'{desc(\|(?!websub|firstline)[^\|]*)+}',
      'follow desc keyword with either firstline or websub'),
   ]
 ]
 
 checks = [
     ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats),
     ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats),
     ('c', r'.*\.[ch]$', '', cfilters, cpats),
     ('unified test', r'.*\.t$', '', utestfilters, utestpats),
     ('layering violation repo in revlog', r'mercurial/revlog\.py', '',
      pyfilters, inrevlogpats),
     ('layering violation ui in util', r'mercurial/util\.py', '', pyfilters,
      inutilpats),
     ('txt', r'.*\.txt$', '', txtfilters, txtpats),
     ('web template', r'mercurial/templates/.*\.tmpl', '',
      webtemplatefilters, webtemplatepats),
 ]
 
 def _preparepats():
     for c in checks:
         failandwarn = c[-1]
         for pats in failandwarn:
             for i, pseq in enumerate(pats):
                 # fix-up regexes for multi-line searches
                 p = pseq[0]
                 # \s doesn't match \n
                 p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
                 # [^...] doesn't match newline
                 p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)
 
                 pats[i] = (re.compile(p, re.MULTILINE),) + pseq[1:]
         filters = c[3]
         for i, flt in enumerate(filters):
             filters[i] = re.compile(flt[0]), flt[1]
 _preparepats()
 
 class norepeatlogger(object):
     def __init__(self):
         self._lastseen = None
 
     def log(self, fname, lineno, line, msg, blame):
         """print error related a to given line of a given file.
 
         The faulty line will also be printed but only once in the case
         of multiple errors.
 
         :fname: filename
         :lineno: line number
         :line: actual content of the line
         :msg: error message
         """
         msgid = fname, lineno, line
         if msgid != self._lastseen:
             if blame:
                 print "%s:%d (%s):" % (fname, lineno, blame)
             else:
                 print "%s:%d:" % (fname, lineno)
             print " > %s" % line
             self._lastseen = msgid
         print " " + msg
 
 _defaultlogger = norepeatlogger()
 
 def getblame(f):
     lines = []
     for l in os.popen('hg annotate -un %s' % f):
         start, line = l.split(':', 1)
         user, rev = start.split()
         lines.append((line[1:-1], user, rev))
     return lines
 
 def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False,
               blame=False, debug=False, lineno=True):
     """checks style and portability of a given file
 
     :f: filepath
     :logfunc: function used to report error
               logfunc(filename, linenumber, linecontent, errormessage)
     :maxerr: number of error to display before aborting.
              Set to false (default) to report all errors
 
     return True if no error is found, False otherwise.
     """
     blamecache = None
     result = True
 
     try:
         fp = open(f)
-    except IOError, e:
+    except IOError as e:
         print "Skipping %s, %s" % (f, str(e).split(':', 1)[0])
         return result
     pre = post = fp.read()
     fp.close()
 
     for name, match, magic, filters, pats in checks:
         if debug:
             print name, f
         fc = 0
         if not (re.match(match, f) or (magic and re.search(magic, f))):
             if debug:
                 print "Skipping %s for %s it doesn't match %s" % (
                        name, match, f)
             continue
         if "no-" "check-code" in pre:
             print "Skipping %s it has no-" "check-code" % f
             return "Skip" # skip checking this file
         for p, r in filters:
             post = re.sub(p, r, post)
         nerrs = len(pats[0]) # nerr elements are errors
         if warnings:
             pats = pats[0] + pats[1]
         else:
             pats = pats[0]
         # print post # uncomment to show filtered version
 
         if debug:
             print "Checking %s for %s" % (name, f)
 
         prelines = None
         errors = []
         for i, pat in enumerate(pats):
             if len(pat) == 3:
                 p, msg, ignore = pat
             else:
                 p, msg = pat
                 ignore = None
             if i >= nerrs:
                 msg = "warning: " + msg
 
             pos = 0
             n = 0
             for m in p.finditer(post):
                 if prelines is None:
                     prelines = pre.splitlines()
                     postlines = post.splitlines(True)
 
                 start = m.start()
                 while n < len(postlines):
                     step = len(postlines[n])
                     if pos + step > start:
                         break
                     pos += step
                     n += 1
                 l = prelines[n]
 
                 if ignore and re.search(ignore, l, re.MULTILINE):
                     if debug:
                         print "Skipping %s for %s:%s (ignore pattern)" % (
                             name, f, n)
                     continue
                 bd = ""
                 if blame:
                     bd = 'working directory'
                     if not blamecache:
                         blamecache = getblame(f)
                     if n < len(blamecache):
                         bl, bu, br = blamecache[n]
                         if bl == l:
                             bd = '%s@%s' % (bu, br)
 
                 errors.append((f, lineno and n + 1, l, msg, bd))
                 result = False
 
         errors.sort()
         for e in errors:
             logfunc(*e)
             fc += 1
             if maxerr and fc >= maxerr:
                 print " (too many errors, giving up)"
                 break
 
     return result
 
 if __name__ == "__main__":
     parser = optparse.OptionParser("%prog [options] [files]")
     parser.add_option("-w", "--warnings", action="store_true",
                       help="include warning-level checks")
     parser.add_option("-p", "--per-file", type="int",
                       help="max warnings per file")
     parser.add_option("-b", "--blame", action="store_true",
                       help="use annotate to generate blame info")
     parser.add_option("", "--debug", action="store_true",
                       help="show debug information")
     parser.add_option("", "--nolineno", action="store_false",
                       dest='lineno', help="don't show line numbers")
 
     parser.set_defaults(per_file=15, warnings=False, blame=False, debug=False,
                         lineno=True)
     (options, args) = parser.parse_args()
 
     if len(args) == 0:
         check = glob.glob("*")
     else:
         check = args
 
     ret = 0
     for f in check:
         if not checkfile(f, maxerr=options.per_file, warnings=options.warnings,
                          blame=options.blame, debug=options.debug,
                          lineno=options.lineno):
             ret = 1
     sys.exit(ret)

contrib/import-checker.py

@@ -1,377 +1,377 b''
 import ast
 import os
 import sys
 
 # Import a minimal set of stdlib modules needed for list_stdlib_modules()
 # to work when run from a virtualenv.  The modules were chosen empirically
 # so that the return value matches the return value without virtualenv.
 import BaseHTTPServer
 import zlib
 
 def dotted_name_of_path(path, trimpure=False):
     """Given a relative path to a source file, return its dotted module name.
 
     >>> dotted_name_of_path('mercurial/error.py')
     'mercurial.error'
     >>> dotted_name_of_path('mercurial/pure/parsers.py', trimpure=True)
     'mercurial.parsers'
     >>> dotted_name_of_path('zlibmodule.so')
     'zlib'
     """
     parts = path.split('/')
     parts[-1] = parts[-1].split('.', 1)[0] # remove .py and .so and .ARCH.so
     if parts[-1].endswith('module'):
         parts[-1] = parts[-1][:-6]
     if trimpure:
         return '.'.join(p for p in parts if p != 'pure')
     return '.'.join(parts)
 
 def fromlocalfunc(modulename, localmods):
     """Get a function to examine which locally defined module the
     target source imports via a specified name.
 
     `modulename` is an `dotted_name_of_path()`-ed source file path,
     which may have `.__init__` at the end of it, of the target source.
 
     `localmods` is a dict (or set), of which key is an absolute
     `dotted_name_of_path()`-ed source file path of locally defined (=
     Mercurial specific) modules.
 
     This function assumes that module names not existing in
     `localmods` are ones of Python standard libarary.
 
     This function returns the function, which takes `name` argument,
     and returns `(absname, dottedpath, hassubmod)` tuple if `name`
     matches against locally defined module. Otherwise, it returns
     False.
 
     It is assumed that `name` doesn't have `.__init__`.
 
     `absname` is an absolute module name of specified `name`
     (e.g. "hgext.convert"). This can be used to compose prefix for sub
     modules or so.
 
     `dottedpath` is a `dotted_name_of_path()`-ed source file path
     (e.g. "hgext.convert.__init__") of `name`. This is used to look
     module up in `localmods` again.
 
     `hassubmod` is whether it may have sub modules under it (for
     convenient, even though this is also equivalent to "absname !=
     dottednpath")
 
     >>> localmods = {'foo.__init__': True, 'foo.foo1': True,
     ...              'foo.bar.__init__': True, 'foo.bar.bar1': True,
     ...              'baz.__init__': True, 'baz.baz1': True }
     >>> fromlocal = fromlocalfunc('foo.xxx', localmods)
     >>> # relative
     >>> fromlocal('foo1')
     ('foo.foo1', 'foo.foo1', False)
     >>> fromlocal('bar')
     ('foo.bar', 'foo.bar.__init__', True)
     >>> fromlocal('bar.bar1')
     ('foo.bar.bar1', 'foo.bar.bar1', False)
     >>> # absolute
     >>> fromlocal('baz')
     ('baz', 'baz.__init__', True)
     >>> fromlocal('baz.baz1')
     ('baz.baz1', 'baz.baz1', False)
     >>> # unknown = maybe standard library
     >>> fromlocal('os')
     False
     """
     prefix = '.'.join(modulename.split('.')[:-1])
     if prefix:
         prefix += '.'
     def fromlocal(name):
         # check relative name at first
         for n in prefix + name, name:
             if n in localmods:
                 return (n, n, False)
             dottedpath = n + '.__init__'
             if dottedpath in localmods:
                 return (n, dottedpath, True)
         return False
     return fromlocal
 
 def list_stdlib_modules():
     """List the modules present in the stdlib.
 
     >>> mods = set(list_stdlib_modules())
     >>> 'BaseHTTPServer' in mods
     True
 
     os.path isn't really a module, so it's missing:
 
     >>> 'os.path' in mods
     False
 
     sys requires special treatment, because it's baked into the
     interpreter, but it should still appear:
 
     >>> 'sys' in mods
     True
 
     >>> 'collections' in mods
     True
 
     >>> 'cStringIO' in mods
     True
     """
     for m in sys.builtin_module_names:
         yield m
     # These modules only exist on windows, but we should always
     # consider them stdlib.
     for m in ['msvcrt', '_winreg']:
         yield m
     # These get missed too
     for m in 'ctypes', 'email':
         yield m
     yield 'builtins' # python3 only
     for m in 'fcntl', 'grp', 'pwd', 'termios':  # Unix only
         yield m
     stdlib_prefixes = set([sys.prefix, sys.exec_prefix])
     # We need to supplement the list of prefixes for the search to work
     # when run from within a virtualenv.
     for mod in (BaseHTTPServer, zlib):
         try:
             # Not all module objects have a __file__ attribute.
             filename = mod.__file__
         except AttributeError:
             continue
         dirname = os.path.dirname(filename)
         for prefix in stdlib_prefixes:
             if dirname.startswith(prefix):
                 # Then this directory is redundant.
                 break
         else:
             stdlib_prefixes.add(dirname)
     for libpath in sys.path:
         # We want to walk everything in sys.path that starts with
         # something in stdlib_prefixes. check-code suppressed because
         # the ast module used by this script implies the availability
         # of any().
         if not any(libpath.startswith(p) for p in stdlib_prefixes): # no-py24
             continue
         if 'site-packages' in libpath:
             continue
         for top, dirs, files in os.walk(libpath):
             for name in files:
                 if name == '__init__.py':
                     continue
                 if not (name.endswith('.py') or name.endswith('.so')
                         or name.endswith('.pyd')):
                     continue
                 full_path = os.path.join(top, name)
                 if 'site-packages' in full_path:
                     continue
                 rel_path = full_path[len(libpath) + 1:]
                 mod = dotted_name_of_path(rel_path)
                 yield mod
 
 stdlib_modules = set(list_stdlib_modules())
 
 def imported_modules(source, modulename, localmods, ignore_nested=False):
     """Given the source of a file as a string, yield the names
     imported by that file.
 
     Args:
       source: The python source to examine as a string.
       modulename: of specified python source (may have `__init__`)
       localmods: dict of locally defined module names (may have `__init__`)
       ignore_nested: If true, import statements that do not start in
                      column zero will be ignored.
 
     Returns:
       A list of absolute module names imported by the given source.
 
     >>> modulename = 'foo.xxx'
     >>> localmods = {'foo.__init__': True,
     ...              'foo.foo1': True, 'foo.foo2': True,
     ...              'foo.bar.__init__': True, 'foo.bar.bar1': True,
     ...              'baz.__init__': True, 'baz.baz1': True }
     >>> # standard library (= not locally defined ones)
     >>> sorted(imported_modules(
     ...        'from stdlib1 import foo, bar; import stdlib2',
     ...        modulename, localmods))
     []
     >>> # relative importing
     >>> sorted(imported_modules(
     ...        'import foo1; from bar import bar1',
     ...        modulename, localmods))
     ['foo.bar.__init__', 'foo.bar.bar1', 'foo.foo1']
     >>> sorted(imported_modules(
     ...        'from bar.bar1 import name1, name2, name3',
     ...        modulename, localmods))
     ['foo.bar.bar1']
     >>> # absolute importing
     >>> sorted(imported_modules(
     ...        'from baz import baz1, name1',
     ...        modulename, localmods))
     ['baz.__init__', 'baz.baz1']
     >>> # mixed importing, even though it shouldn't be recommended
     >>> sorted(imported_modules(
     ...        'import stdlib, foo1, baz',
     ...        modulename, localmods))
     ['baz.__init__', 'foo.foo1']
     >>> # ignore_nested
     >>> sorted(imported_modules(
     ... '''import foo
     ... def wat():
     ...     import bar
     ... ''', modulename, localmods))
     ['foo.__init__', 'foo.bar.__init__']
     >>> sorted(imported_modules(
     ... '''import foo
     ... def wat():
     ...     import bar
     ... ''', modulename, localmods, ignore_nested=True))
     ['foo.__init__']
     """
     fromlocal = fromlocalfunc(modulename, localmods)
     for node in ast.walk(ast.parse(source)):
         if ignore_nested and getattr(node, 'col_offset', 0) > 0:
             continue
         if isinstance(node, ast.Import):
             for n in node.names:
                 found = fromlocal(n.name)
                 if not found:
                     # this should import standard library
                     continue
                 yield found[1]
         elif isinstance(node, ast.ImportFrom):
             found = fromlocal(node.module)
             if not found:
                 # this should import standard library
                 continue
 
             absname, dottedpath, hassubmod = found
             yield dottedpath
             if not hassubmod:
                 # examination of "node.names" should be redundant
                 # e.g.: from mercurial.node import nullid, nullrev
                 continue
 
             prefix = absname + '.'
             for n in node.names:
                 found = fromlocal(prefix + n.name)
                 if not found:
                     # this should be a function or a property of "node.module"
                     continue
                 yield found[1]
 
 def verify_stdlib_on_own_line(source):
     """Given some python source, verify that stdlib imports are done
     in separate statements from relative local module imports.
 
     Observing this limitation is important as it works around an
     annoying lib2to3 bug in relative import rewrites:
     http://bugs.python.org/issue19510.
 
     >>> list(verify_stdlib_on_own_line('import sys, foo'))
     ['mixed imports\\n   stdlib:    sys\\n   relative:  foo']
     >>> list(verify_stdlib_on_own_line('import sys, os'))
     []
     >>> list(verify_stdlib_on_own_line('import foo, bar'))
     []
     """
     for node in ast.walk(ast.parse(source)):
         if isinstance(node, ast.Import):
             from_stdlib = {False: [], True: []}
             for n in node.names:
                 from_stdlib[n.name in stdlib_modules].append(n.name)
             if from_stdlib[True] and from_stdlib[False]:
                 yield ('mixed imports\n   stdlib:    %s\n   relative:  %s' %
                        (', '.join(sorted(from_stdlib[True])),
                         ', '.join(sorted(from_stdlib[False]))))
 
 class CircularImport(Exception):
     pass
 
 def checkmod(mod, imports):
     shortest = {}
     visit = [[mod]]
     while visit:
         path = visit.pop(0)
         for i in sorted(imports.get(path[-1], [])):
             if len(path) < shortest.get(i, 1000):
                 shortest[i] = len(path)
                 if i in path:
                     if i == path[0]:
                         raise CircularImport(path)
                     continue
                 visit.append(path + [i])
 
 def rotatecycle(cycle):
     """arrange a cycle so that the lexicographically first module listed first
 
     >>> rotatecycle(['foo', 'bar'])
     ['bar', 'foo', 'bar']
     """
     lowest = min(cycle)
     idx = cycle.index(lowest)
     return cycle[idx:] + cycle[:idx] + [lowest]
 
 def find_cycles(imports):
     """Find cycles in an already-loaded import graph.
 
     All module names recorded in `imports` should be absolute one.
 
     >>> imports = {'top.foo': ['top.bar', 'os.path', 'top.qux'],
     ...            'top.bar': ['top.baz', 'sys'],
     ...            'top.baz': ['top.foo'],
     ...            'top.qux': ['top.foo']}
     >>> print '\\n'.join(sorted(find_cycles(imports)))
     top.bar -> top.baz -> top.foo -> top.bar
     top.foo -> top.qux -> top.foo
     """
     cycles = set()
     for mod in sorted(imports.iterkeys()):
         try:
             checkmod(mod, imports)
-        except CircularImport, e:
+        except CircularImport as e:
             cycle = e.args[0]
             cycles.add(" -> ".join(rotatecycle(cycle)))
     return cycles
 
 def _cycle_sortkey(c):
     return len(c), c
 
 def main(argv):
     if len(argv) < 2 or (argv[1] == '-' and len(argv) > 2):
         print 'Usage: %s {-|file [file] [file] ...}'
         return 1
     if argv[1] == '-':
         argv = argv[:1]
         argv.extend(l.rstrip() for l in sys.stdin.readlines())
     localmods = {}
     used_imports = {}
     any_errors = False
     for source_path in argv[1:]:
         modname = dotted_name_of_path(source_path, trimpure=True)
         localmods[modname] = source_path
     for modname, source_path in sorted(localmods.iteritems()):
         f = open(source_path)
         src = f.read()
         used_imports[modname] = sorted(
             imported_modules(src, modname, localmods, ignore_nested=True))
         for error in verify_stdlib_on_own_line(src):
             any_errors = True
             print source_path, error
         f.close()
     cycles = find_cycles(used_imports)
     if cycles:
         firstmods = set()
         for c in sorted(cycles, key=_cycle_sortkey):
             first = c.split()[0]
             # As a rough cut, ignore any cycle that starts with the
             # same module as some other cycle. Otherwise we see lots
             # of cycles that are effectively duplicates.
             if first in firstmods:
                 continue
             print 'Import cycle:', c
             firstmods.add(first)
         any_errors = True
     return not any_errors
 
 if __name__ == '__main__':
     sys.exit(int(main(sys.argv)))

contrib/revsetbenchmarks.py

@@ -1,317 +1,317 b''
 #!/usr/bin/env python
 
 # Measure the performance of a list of revsets against multiple revisions
 # defined by parameter. Checkout one by one and run perfrevset with every
 # revset in the list to benchmark its performance.
 #
 # You should run this from the root of your mercurial repository.
 #
 # call with --help for details
 
 import sys
 import os
 import re
 import math
 from subprocess import check_call, Popen, CalledProcessError, STDOUT, PIPE
 # cannot use argparse, python 2.7 only
 from optparse import OptionParser
 
 DEFAULTVARIANTS = ['plain', 'min', 'max', 'first', 'last',
                    'reverse', 'reverse+first', 'reverse+last',
                    'sort', 'sort+first', 'sort+last']
 
 def check_output(*args, **kwargs):
     kwargs.setdefault('stderr', PIPE)
     kwargs.setdefault('stdout', PIPE)
     proc = Popen(*args, **kwargs)
     output, error = proc.communicate()
     if proc.returncode != 0:
         raise CalledProcessError(proc.returncode, ' '.join(args[0]))
     return output
 
 def update(rev):
     """update the repo to a revision"""
     try:
         check_call(['hg', 'update', '--quiet', '--check', str(rev)])
-    except CalledProcessError, exc:
+    except CalledProcessError as exc:
         print >> sys.stderr, 'update to revision %s failed, aborting' % rev
         sys.exit(exc.returncode)
 
 
 def hg(cmd, repo=None):
     """run a mercurial command
 
     <cmd> is the list of command + argument,
     <repo> is an optional repository path to run this command in."""
     fullcmd = ['./hg']
     if repo is not None:
         fullcmd += ['-R', repo]
     fullcmd += ['--config',
                 'extensions.perf=' + os.path.join(contribdir, 'perf.py')]
     fullcmd += cmd
     return check_output(fullcmd, stderr=STDOUT)
 
 def perf(revset, target=None):
     """run benchmark for this very revset"""
     try:
         output = hg(['perfrevset', revset], repo=target)
         return parseoutput(output)
-    except CalledProcessError, exc:
+    except CalledProcessError as exc:
         print >> sys.stderr, 'abort: cannot run revset benchmark: %s' % exc.cmd
         if exc.output is None:
             print >> sys.stderr, '(no ouput)'
         else:
             print >> sys.stderr, exc.output
         return None
 
 outputre = re.compile(r'! wall (\d+.\d+) comb (\d+.\d+) user (\d+.\d+) '
                       'sys (\d+.\d+) \(best of (\d+)\)')
 
 def parseoutput(output):
     """parse a textual output into a dict
 
     We cannot just use json because we want to compare with old
     versions of Mercurial that may not support json output.
     """
     match = outputre.search(output)
     if not match:
         print >> sys.stderr, 'abort: invalid output:'
         print >> sys.stderr, output
         sys.exit(1)
     return {'comb': float(match.group(2)),
             'count': int(match.group(5)),
             'sys': float(match.group(3)),
             'user': float(match.group(4)),
             'wall': float(match.group(1)),
             }
 
 def printrevision(rev):
     """print data about a revision"""
     sys.stdout.write("Revision ")
     sys.stdout.flush()
     check_call(['hg', 'log', '--rev', str(rev), '--template',
                 '{if(tags, " ({tags})")} '
                 '{rev}:{node|short}: {desc|firstline}\n'])
 
 def idxwidth(nbidx):
     """return the max width of number used for index
 
     This is similar to log10(nbidx), but we use custom code here
     because we start with zero and we'd rather not deal with all the
     extra rounding business that log10 would imply.
     """
     nbidx -= 1 # starts at 0
     idxwidth = 0
     while nbidx:
         idxwidth += 1
         nbidx //= 10
     if not idxwidth:
         idxwidth = 1
     return idxwidth
 
 def getfactor(main, other, field, sensitivity=0.05):
     """return the relative factor between values for 'field' in main and other
 
     Return None if the factor is insignicant (less than <sensitivity>
     variation)."""
     factor = 1
     if main is not None:
         factor = other[field] / main[field]
     low, high = 1 - sensitivity, 1 + sensitivity
     if (low < factor < high):
         return None
     return factor
 
 def formatfactor(factor):
     """format a factor into a 4 char string
 
      22%
     156%
     x2.4
      x23
     x789
     x1e4
     x5x7
 
     """
     if factor is None:
         return '    '
     elif factor < 2:
         return '%3i%%' % (factor * 100)
     elif factor < 10:
         return 'x%3.1f' % factor
     elif factor < 1000:
         return '%4s' % ('x%i' % factor)
     else:
         order = int(math.log(factor)) + 1
         while 1 < math.log(factor):
             factor //= 0
         return 'x%ix%i' % (factor, order)
 
 def formattiming(value):
     """format a value to strictly 8 char, dropping some precision if needed"""
     if value < 10**7:
         return ('%.6f' % value)[:8]
     else:
         # value is HUGE very unlikely to happen (4+ month run)
         return '%i' % value
 
 _marker = object()
 def printresult(variants, idx, data, maxidx, verbose=False, reference=_marker):
     """print a line of result to stdout"""
     mask = '%%0%ii) %%s' % idxwidth(maxidx)
 
     out = []
     for var in variants:
         if data[var] is None:
             out.append('error   ')
             out.append(' ' * 4)
             continue
         out.append(formattiming(data[var]['wall']))
         if reference is not _marker:
             factor = None
             if reference is not None:
                 factor = getfactor(reference[var], data[var], 'wall')
             out.append(formatfactor(factor))
         if verbose:
             out.append(formattiming(data[var]['comb']))
             out.append(formattiming(data[var]['user']))
             out.append(formattiming(data[var]['sys']))
             out.append('%6d'    % data[var]['count'])
     print mask % (idx, ' '.join(out))
 
 def printheader(variants, maxidx, verbose=False, relative=False):
     header = [' ' * (idxwidth(maxidx) + 1)]
     for var in variants:
         if not var:
             var = 'iter'
         if 8 < len(var):
             var = var[:3] + '..' + var[-3:]
         header.append('%-8s' % var)
         if relative:
             header.append('    ')
         if verbose:
             header.append('%-8s' % 'comb')
             header.append('%-8s' % 'user')
             header.append('%-8s' % 'sys')
             header.append('%6s' % 'count')
     print ' '.join(header)
 
 def getrevs(spec):
     """get the list of rev matched by a revset"""
     try:
         out = check_output(['hg', 'log', '--template={rev}\n', '--rev', spec])
-    except CalledProcessError, exc:
+    except CalledProcessError as exc:
         print >> sys.stderr, "abort, can't get revision from %s" % spec
         sys.exit(exc.returncode)
     return [r for r in out.split() if r]
 
 
 def applyvariants(revset, variant):
     if variant == 'plain':
         return revset
     for var in variant.split('+'):
         revset = '%s(%s)' % (var, revset)
     return revset
 
 helptext="""This script will run multiple variants of provided revsets using
 different revisions in your mercurial repository. After the benchmark are run
 summary output is provided. Use itto demonstrate speed improvements or pin
 point regressions. Revsets to run are specified in a file (or from stdin), one
 revsets per line. Line starting with '#' will be ignored, allowing insertion of
 comments."""
 parser = OptionParser(usage="usage: %prog [options] <revs>",
                       description=helptext)
 parser.add_option("-f", "--file",
                   help="read revset from FILE (stdin if omitted)",
                   metavar="FILE")
 parser.add_option("-R", "--repo",
                   help="run benchmark on REPO", metavar="REPO")
 
 parser.add_option("-v", "--verbose",
                   action='store_true',
                   help="display all timing data (not just best total time)")
 
 parser.add_option("", "--variants",
                   default=','.join(DEFAULTVARIANTS),
                   help="comma separated list of variant to test "
                        "(eg: plain,min,sorted) (plain = no modification)")
 
 (options, args) = parser.parse_args()
 
 if not args:
     parser.print_help()
     sys.exit(255)
 
 # the directory where both this script and the perf.py extension live.
 contribdir = os.path.dirname(__file__)
 
 revsetsfile = sys.stdin
 if options.file:
     revsetsfile = open(options.file)
 
 revsets = [l.strip() for l in revsetsfile if not l.startswith('#')]
 revsets = [l for l in revsets if l]
 
 print "Revsets to benchmark"
 print "----------------------------"
 
 for idx, rset in enumerate(revsets):
     print "%i) %s" % (idx, rset)
 
 print "----------------------------"
 print
 
 revs = []
 for a in args:
     revs.extend(getrevs(a))
 
 variants = options.variants.split(',')
 
 results = []
 for r in revs:
     print "----------------------------"
     printrevision(r)
     print "----------------------------"
     update(r)
     res = []
     results.append(res)
     printheader(variants, len(revsets), verbose=options.verbose)
     for idx, rset in enumerate(revsets):
         varres = {}
         for var in variants:
             varrset = applyvariants(rset, var)
             data = perf(varrset, target=options.repo)
             varres[var] = data
         res.append(varres)
         printresult(variants, idx, varres, len(revsets),
                     verbose=options.verbose)
         sys.stdout.flush()
     print "----------------------------"
 
 
 print """
 
 Result by revset
 ================
 """
 
 print 'Revision:'
 for idx, rev in enumerate(revs):
     sys.stdout.write('%i) ' % idx)
     sys.stdout.flush()
     printrevision(rev)
 
 print
 print
 
 for ridx, rset in enumerate(revsets):
 
     print "revset #%i: %s" % (ridx, rset)
     printheader(variants, len(results), verbose=options.verbose, relative=True)
     ref = None
     for idx, data in enumerate(results):
         printresult(variants, idx, data[ridx], len(results),
                     verbose=options.verbose, reference=ref)
         ref = data[ridx]
     print

contrib/synthrepo.py

@@ -1,495 +1,495 b''
 # synthrepo.py - repo synthesis
 #
 # Copyright 2012 Facebook
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''synthesize structurally interesting change history
 
 This extension is useful for creating a repository with properties
 that are statistically similar to an existing repository. During
 analysis, a simple probability table is constructed from the history
 of an existing repository.  During synthesis, these properties are
 reconstructed.
 
 Properties that are analyzed and synthesized include the following:
 
 - Lines added or removed when an existing file is modified
 - Number and sizes of files added
 - Number of files removed
 - Line lengths
 - Topological distance to parent changeset(s)
 - Probability of a commit being a merge
 - Probability of a newly added file being added to a new directory
 - Interarrival time, and time zone, of commits
 - Number of files in each directory
 
 A few obvious properties that are not currently handled realistically:
 
 - Merges are treated as regular commits with two parents, which is not
   realistic
 - Modifications are not treated as operations on hunks of lines, but
   as insertions and deletions of randomly chosen single lines
 - Committer ID (always random)
 - Executability of files
 - Symlinks and binary files are ignored
 '''
 
 import bisect, collections, itertools, json, os, random, time, sys
 from mercurial import cmdutil, context, patch, scmutil, util, hg
 from mercurial.i18n import _
 from mercurial.node import nullrev, nullid, short
 
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 newfile = set(('new fi', 'rename', 'copy f', 'copy t'))
 
 def zerodict():
     return collections.defaultdict(lambda: 0)
 
 def roundto(x, k):
     if x > k * 2:
         return int(round(x / float(k)) * k)
     return int(round(x))
 
 def parsegitdiff(lines):
     filename, mar, lineadd, lineremove = None, None, zerodict(), 0
     binary = False
     for line in lines:
         start = line[:6]
         if start == 'diff -':
             if filename:
                 yield filename, mar, lineadd, lineremove, binary
             mar, lineadd, lineremove, binary = 'm', zerodict(), 0, False
             filename = patch.gitre.match(line).group(1)
         elif start in newfile:
             mar = 'a'
         elif start == 'GIT bi':
             binary = True
         elif start == 'delete':
             mar = 'r'
         elif start:
             s = start[0]
             if s == '-' and not line.startswith('--- '):
                 lineremove += 1
             elif s == '+' and not line.startswith('+++ '):
                 lineadd[roundto(len(line) - 1, 5)] += 1
     if filename:
         yield filename, mar, lineadd, lineremove, binary
 
 @command('analyze',
          [('o', 'output', '', _('write output to given file'), _('FILE')),
           ('r', 'rev', [], _('analyze specified revisions'), _('REV'))],
          _('hg analyze'), optionalrepo=True)
 def analyze(ui, repo, *revs, **opts):
     '''create a simple model of a repository to use for later synthesis
 
     This command examines every changeset in the given range (or all
     of history if none are specified) and creates a simple statistical
     model of the history of the repository. It also measures the directory
     structure of the repository as checked out.
 
     The model is written out to a JSON file, and can be used by
     :hg:`synthesize` to create or augment a repository with synthetic
     commits that have a structure that is statistically similar to the
     analyzed repository.
     '''
     root = repo.root
     if not root.endswith(os.path.sep):
         root += os.path.sep
 
     revs = list(revs)
     revs.extend(opts['rev'])
     if not revs:
         revs = [':']
 
     output = opts['output']
     if not output:
         output = os.path.basename(root) + '.json'
 
     if output == '-':
         fp = sys.stdout
     else:
         fp = open(output, 'w')
 
     # Always obtain file counts of each directory in the given root directory.
     def onerror(e):
         ui.warn(_('error walking directory structure: %s\n') % e)
 
     dirs = {}
     rootprefixlen = len(root)
     for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):
         dirpathfromroot = dirpath[rootprefixlen:]
         dirs[dirpathfromroot] = len(filenames)
         if '.hg' in dirnames:
             dirnames.remove('.hg')
 
     lineschanged = zerodict()
     children = zerodict()
     p1distance = zerodict()
     p2distance = zerodict()
     linesinfilesadded = zerodict()
     fileschanged = zerodict()
     filesadded = zerodict()
     filesremoved = zerodict()
     linelengths = zerodict()
     interarrival = zerodict()
     parents = zerodict()
     dirsadded = zerodict()
     tzoffset = zerodict()
 
     # If a mercurial repo is available, also model the commit history.
     if repo:
         revs = scmutil.revrange(repo, revs)
         revs.sort()
 
         progress = ui.progress
         _analyzing = _('analyzing')
         _changesets = _('changesets')
         _total = len(revs)
 
         for i, rev in enumerate(revs):
             progress(_analyzing, i, unit=_changesets, total=_total)
             ctx = repo[rev]
             pl = ctx.parents()
             pctx = pl[0]
             prev = pctx.rev()
             children[prev] += 1
             p1distance[rev - prev] += 1
             parents[len(pl)] += 1
             tzoffset[ctx.date()[1]] += 1
             if len(pl) > 1:
                 p2distance[rev - pl[1].rev()] += 1
             if prev == rev - 1:
                 lastctx = pctx
             else:
                 lastctx = repo[rev - 1]
             if lastctx.rev() != nullrev:
                 timedelta = ctx.date()[0] - lastctx.date()[0]
                 interarrival[roundto(timedelta, 300)] += 1
             diff = sum((d.splitlines() for d in ctx.diff(pctx, git=True)), [])
             fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0
             for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):
                 if isbin:
                     continue
                 added = sum(lineadd.itervalues(), 0)
                 if mar == 'm':
                     if added and lineremove:
                         lineschanged[roundto(added, 5),
                                      roundto(lineremove, 5)] += 1
                         filechanges += 1
                 elif mar == 'a':
                     fileadds += 1
                     if '/' in filename:
                         filedir = filename.rsplit('/', 1)[0]
                         if filedir not in pctx.dirs():
                             diradds += 1
                     linesinfilesadded[roundto(added, 5)] += 1
                 elif mar == 'r':
                     fileremoves += 1
                 for length, count in lineadd.iteritems():
                     linelengths[length] += count
             fileschanged[filechanges] += 1
             filesadded[fileadds] += 1
             dirsadded[diradds] += 1
             filesremoved[fileremoves] += 1
 
     invchildren = zerodict()
 
     for rev, count in children.iteritems():
         invchildren[count] += 1
 
     if output != '-':
         ui.status(_('writing output to %s\n') % output)
 
     def pronk(d):
         return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)
 
     json.dump({'revs': len(revs),
                'initdirs': pronk(dirs),
                'lineschanged': pronk(lineschanged),
                'children': pronk(invchildren),
                'fileschanged': pronk(fileschanged),
                'filesadded': pronk(filesadded),
                'linesinfilesadded': pronk(linesinfilesadded),
                'dirsadded': pronk(dirsadded),
                'filesremoved': pronk(filesremoved),
                'linelengths': pronk(linelengths),
                'parents': pronk(parents),
                'p1distance': pronk(p1distance),
                'p2distance': pronk(p2distance),
                'interarrival': pronk(interarrival),
                'tzoffset': pronk(tzoffset),
                },
               fp)
     fp.close()
 
 @command('synthesize',
          [('c', 'count', 0, _('create given number of commits'), _('COUNT')),
           ('', 'dict', '', _('path to a dictionary of words'), _('FILE')),
           ('', 'initfiles', 0, _('initial file count to create'), _('COUNT'))],
          _('hg synthesize [OPTION].. DESCFILE'))
 def synthesize(ui, repo, descpath, **opts):
     '''synthesize commits based on a model of an existing repository
 
     The model must have been generated by :hg:`analyze`. Commits will
     be generated randomly according to the probabilities described in
     the model. If --initfiles is set, the repository will be seeded with
     the given number files following the modeled repository's directory
     structure.
 
     When synthesizing new content, commit descriptions, and user
     names, words will be chosen randomly from a dictionary that is
     presumed to contain one word per line. Use --dict to specify the
     path to an alternate dictionary to use.
     '''
     try:
         fp = hg.openpath(ui, descpath)
-    except Exception, err:
+    except Exception as err:
         raise util.Abort('%s: %s' % (descpath, err[0].strerror))
     desc = json.load(fp)
     fp.close()
 
     def cdf(l):
         if not l:
             return [], []
         vals, probs = zip(*sorted(l, key=lambda x: x[1], reverse=True))
         t = float(sum(probs, 0))
         s, cdfs = 0, []
         for v in probs:
             s += v
             cdfs.append(s / t)
         return vals, cdfs
 
     lineschanged = cdf(desc['lineschanged'])
     fileschanged = cdf(desc['fileschanged'])
     filesadded = cdf(desc['filesadded'])
     dirsadded = cdf(desc['dirsadded'])
     filesremoved = cdf(desc['filesremoved'])
     linelengths = cdf(desc['linelengths'])
     parents = cdf(desc['parents'])
     p1distance = cdf(desc['p1distance'])
     p2distance = cdf(desc['p2distance'])
     interarrival = cdf(desc['interarrival'])
     linesinfilesadded = cdf(desc['linesinfilesadded'])
     tzoffset = cdf(desc['tzoffset'])
 
     dictfile = opts.get('dict') or '/usr/share/dict/words'
     try:
         fp = open(dictfile, 'rU')
-    except IOError, err:
+    except IOError as err:
         raise util.Abort('%s: %s' % (dictfile, err.strerror))
     words = fp.read().splitlines()
     fp.close()
 
     initdirs = {}
     if desc['initdirs']:
         for k, v in desc['initdirs']:
             initdirs[k.encode('utf-8').replace('.hg', '_hg')] = v
         initdirs = renamedirs(initdirs, words)
     initdirscdf = cdf(initdirs)
 
     def pick(cdf):
         return cdf[0][bisect.bisect_left(cdf[1], random.random())]
 
     def pickpath():
         return os.path.join(pick(initdirscdf), random.choice(words))
 
     def makeline(minimum=0):
         total = max(minimum, pick(linelengths))
         c, l = 0, []
         while c < total:
             w = random.choice(words)
             c += len(w) + 1
             l.append(w)
         return ' '.join(l)
 
     wlock = repo.wlock()
     lock = repo.lock()
 
     nevertouch = set(('.hgsub', '.hgignore', '.hgtags'))
 
     progress = ui.progress
     _synthesizing = _('synthesizing')
     _files = _('initial files')
     _changesets = _('changesets')
 
     # Synthesize a single initial revision adding files to the repo according
     # to the modeled directory structure.
     initcount = int(opts['initfiles'])
     if initcount and initdirs:
         pctx = repo[None].parents()[0]
         dirs = set(pctx.dirs())
         files = {}
 
         def validpath(path):
             # Don't pick filenames which are already directory names.
             if path in dirs:
                 return False
             # Don't pick directories which were used as file names.
             while path:
                 if path in files:
                     return False
                 path = os.path.dirname(path)
             return True
 
         for i in xrange(0, initcount):
             ui.progress(_synthesizing, i, unit=_files, total=initcount)
 
             path = pickpath()
             while not validpath(path):
                 path = pickpath()
             data = '%s contents\n' % path
             files[path] = context.memfilectx(repo, path, data)
             dir = os.path.dirname(path)
             while dir and dir not in dirs:
                 dirs.add(dir)
                 dir = os.path.dirname(dir)
 
         def filectxfn(repo, memctx, path):
             return files[path]
 
         ui.progress(_synthesizing, None)
         message = 'synthesized wide repo with %d files' % (len(files),)
         mc = context.memctx(repo, [pctx.node(), nullid], message,
                             files.iterkeys(), filectxfn, ui.username(),
                             '%d %d' % util.makedate())
         initnode = mc.commit()
         if ui.debugflag:
             hexfn = hex
         else:
             hexfn = short
         ui.status(_('added commit %s with %d files\n')
                   % (hexfn(initnode), len(files)))
 
     # Synthesize incremental revisions to the repository, adding repo depth.
     count = int(opts['count'])
     heads = set(map(repo.changelog.rev, repo.heads()))
     for i in xrange(count):
         progress(_synthesizing, i, unit=_changesets, total=count)
 
         node = repo.changelog.node
         revs = len(repo)
 
         def pickhead(heads, distance):
             if heads:
                 lheads = sorted(heads)
                 rev = revs - min(pick(distance), revs)
                 if rev < lheads[-1]:
                     rev = lheads[bisect.bisect_left(lheads, rev)]
                 else:
                     rev = lheads[-1]
                 return rev, node(rev)
             return nullrev, nullid
 
         r1 = revs - min(pick(p1distance), revs)
         p1 = node(r1)
 
         # the number of heads will grow without bound if we use a pure
         # model, so artificially constrain their proliferation
         toomanyheads = len(heads) > random.randint(1, 20)
         if p2distance[0] and (pick(parents) == 2 or toomanyheads):
             r2, p2 = pickhead(heads.difference([r1]), p2distance)
         else:
             r2, p2 = nullrev, nullid
 
         pl = [p1, p2]
         pctx = repo[r1]
         mf = pctx.manifest()
         mfk = mf.keys()
         changes = {}
         if mfk:
             for __ in xrange(pick(fileschanged)):
                 for __ in xrange(10):
                     fctx = pctx.filectx(random.choice(mfk))
                     path = fctx.path()
                     if not (path in nevertouch or fctx.isbinary() or
                             'l' in fctx.flags()):
                         break
                 lines = fctx.data().splitlines()
                 add, remove = pick(lineschanged)
                 for __ in xrange(remove):
                     if not lines:
                         break
                     del lines[random.randrange(0, len(lines))]
                 for __ in xrange(add):
                     lines.insert(random.randint(0, len(lines)), makeline())
                 path = fctx.path()
                 changes[path] = context.memfilectx(repo, path,
                                                    '\n'.join(lines) + '\n')
             for __ in xrange(pick(filesremoved)):
                 path = random.choice(mfk)
                 for __ in xrange(10):
                     path = random.choice(mfk)
                     if path not in changes:
                         changes[path] = None
                         break
         if filesadded:
             dirs = list(pctx.dirs())
             dirs.insert(0, '')
         for __ in xrange(pick(filesadded)):
             pathstr = ''
             while pathstr in dirs:
                 path = [random.choice(dirs)]
                 if pick(dirsadded):
                     path.append(random.choice(words))
                 path.append(random.choice(words))
                 pathstr = '/'.join(filter(None, path))
             data = '\n'.join(makeline()
                              for __ in xrange(pick(linesinfilesadded))) + '\n'
             changes[pathstr] = context.memfilectx(repo, pathstr, data)
         def filectxfn(repo, memctx, path):
             return changes[path]
         if not changes:
             continue
         if revs:
             date = repo['tip'].date()[0] + pick(interarrival)
         else:
             date = time.time() - (86400 * count)
         # dates in mercurial must be positive, fit in 32-bit signed integers.
         date = min(0x7fffffff, max(0, date))
         user = random.choice(words) + '@' + random.choice(words)
         mc = context.memctx(repo, pl, makeline(minimum=2),
                             sorted(changes.iterkeys()),
                             filectxfn, user, '%d %d' % (date, pick(tzoffset)))
         newnode = mc.commit()
         heads.add(repo.changelog.rev(newnode))
         heads.discard(r1)
         heads.discard(r2)
 
     lock.release()
     wlock.release()
 
 def renamedirs(dirs, words):
     '''Randomly rename the directory names in the per-dir file count dict.'''
     wordgen = itertools.cycle(words)
     replacements = {'': ''}
     def rename(dirpath):
         '''Recursively rename the directory and all path prefixes.
 
         The mapping from path to renamed path is stored for all path prefixes
         as in dynamic programming, ensuring linear runtime and consistent
         renaming regardless of iteration order through the model.
         '''
         if dirpath in replacements:
             return replacements[dirpath]
         head, _ = os.path.split(dirpath)
         if head:
             head = rename(head)
         else:
             head = ''
         renamed = os.path.join(head, wordgen.next())
         replacements[dirpath] = renamed
         return renamed
     result = []
     for dirpath, count in dirs.iteritems():
         result.append([rename(dirpath.lstrip(os.sep)), count])
     return result

hgext/blackbox.py

@@ -1,162 +1,162 b''
 # blackbox.py - log repository events to a file for post-mortem debugging
 #
 # Copyright 2010 Nicolas Dumazet
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """log repository events to a blackbox for debugging
 
 Logs event information to .hg/blackbox.log to help debug and diagnose problems.
 The events that get logged can be configured via the blackbox.track config key.
 Examples::
 
   [blackbox]
   track = *
 
   [blackbox]
   track = command, commandfinish, commandexception, exthook, pythonhook
 
   [blackbox]
   track = incoming
 
   [blackbox]
   # limit the size of a log file
   maxsize = 1.5 MB
   # rotate up to N log files when the current one gets too big
   maxfiles = 3
 
 """
 
 from mercurial import util, cmdutil
 from mercurial.i18n import _
 import errno, os, re
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 lastblackbox = None
 
 def wrapui(ui):
     class blackboxui(ui.__class__):
         @util.propertycache
         def track(self):
             return self.configlist('blackbox', 'track', ['*'])
 
         def _openlogfile(self):
             def rotate(oldpath, newpath):
                 try:
                     os.unlink(newpath)
-                except OSError, err:
+                except OSError as err:
                     if err.errno != errno.ENOENT:
                         self.debug("warning: cannot remove '%s': %s\n" %
                                    (newpath, err.strerror))
                 try:
                     if newpath:
                         os.rename(oldpath, newpath)
-                except OSError, err:
+                except OSError as err:
                     if err.errno != errno.ENOENT:
                         self.debug("warning: cannot rename '%s' to '%s': %s\n" %
                                    (newpath, oldpath, err.strerror))
 
             fp = self._bbopener('blackbox.log', 'a')
             maxsize = self.configbytes('blackbox', 'maxsize', 1048576)
             if maxsize > 0:
                 st = os.fstat(fp.fileno())
                 if st.st_size >= maxsize:
                     path = fp.name
                     fp.close()
                     maxfiles = self.configint('blackbox', 'maxfiles', 7)
                     for i in xrange(maxfiles - 1, 1, -1):
                         rotate(oldpath='%s.%d' % (path, i - 1),
                                newpath='%s.%d' % (path, i))
                     rotate(oldpath=path,
                            newpath=maxfiles > 0 and path + '.1')
                     fp = self._bbopener('blackbox.log', 'a')
             return fp
 
         def log(self, event, *msg, **opts):
             global lastblackbox
             super(blackboxui, self).log(event, *msg, **opts)
 
             if not '*' in self.track and not event in self.track:
                 return
 
             if util.safehasattr(self, '_blackbox'):
                 blackbox = self._blackbox
             elif util.safehasattr(self, '_bbopener'):
                 try:
                     self._blackbox = self._openlogfile()
-                except (IOError, OSError), err:
+                except (IOError, OSError) as err:
                     self.debug('warning: cannot write to blackbox.log: %s\n' %
                                err.strerror)
                     del self._bbopener
                     self._blackbox = None
                 blackbox = self._blackbox
             else:
                 # certain ui instances exist outside the context of
                 # a repo, so just default to the last blackbox that
                 # was seen.
                 blackbox = lastblackbox
 
             if blackbox:
                 date = util.datestr(None, '%Y/%m/%d %H:%M:%S')
                 user = util.getuser()
                 formattedmsg = msg[0] % msg[1:]
                 try:
                     blackbox.write('%s %s> %s' % (date, user, formattedmsg))
-                except IOError, err:
+                except IOError as err:
                     self.debug('warning: cannot write to blackbox.log: %s\n' %
                                err.strerror)
                 lastblackbox = blackbox
 
         def setrepo(self, repo):
             self._bbopener = repo.vfs
 
     ui.__class__ = blackboxui
 
 def uisetup(ui):
     wrapui(ui)
 
 def reposetup(ui, repo):
     # During 'hg pull' a httppeer repo is created to represent the remote repo.
     # It doesn't have a .hg directory to put a blackbox in, so we don't do
     # the blackbox setup for it.
     if not repo.local():
         return
 
     if util.safehasattr(ui, 'setrepo'):
         ui.setrepo(repo)
 
 @command('^blackbox',
     [('l', 'limit', 10, _('the number of events to show')),
     ],
     _('hg blackbox [OPTION]...'))
 def blackbox(ui, repo, *revs, **opts):
     '''view the recent repository events
     '''
 
     if not os.path.exists(repo.join('blackbox.log')):
         return
 
     limit = opts.get('limit')
     blackbox = repo.vfs('blackbox.log', 'r')
     lines = blackbox.read().split('\n')
 
     count = 0
     output = []
     for line in reversed(lines):
         if count >= limit:
             break
 
         # count the commands by matching lines like: 2013/01/23 19:13:36 root>
         if re.match('^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
             count += 1
         output.append(line)
 
     ui.status('\n'.join(reversed(output)))

hgext/bugzilla.py

@@ -1,914 +1,914 b''
 # bugzilla.py - bugzilla integration for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 # Copyright 2011-4 Jim Hague <[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.
 
 '''hooks for integrating with the Bugzilla bug tracker
 
 This hook extension adds comments on bugs in Bugzilla when changesets
 that refer to bugs by Bugzilla ID are seen. The comment is formatted using
 the Mercurial template mechanism.
 
 The bug references can optionally include an update for Bugzilla of the
 hours spent working on the bug. Bugs can also be marked fixed.
 
 Three basic modes of access to Bugzilla are provided:
 
 1. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later.
 
 2. Check data via the Bugzilla XMLRPC interface and submit bug change
    via email to Bugzilla email interface. Requires Bugzilla 3.4 or later.
 
 3. Writing directly to the Bugzilla database. Only Bugzilla installations
    using MySQL are supported. Requires Python MySQLdb.
 
 Writing directly to the database is susceptible to schema changes, and
 relies on a Bugzilla contrib script to send out bug change
 notification emails. This script runs as the user running Mercurial,
 must be run on the host with the Bugzilla install, and requires
 permission to read Bugzilla configuration details and the necessary
 MySQL user and password to have full access rights to the Bugzilla
 database. For these reasons this access mode is now considered
 deprecated, and will not be updated for new Bugzilla versions going
 forward. Only adding comments is supported in this access mode.
 
 Access via XMLRPC needs a Bugzilla username and password to be specified
 in the configuration. Comments are added under that username. Since the
 configuration must be readable by all Mercurial users, it is recommended
 that the rights of that user are restricted in Bugzilla to the minimum
 necessary to add comments. Marking bugs fixed requires Bugzilla 4.0 and later.
 
 Access via XMLRPC/email uses XMLRPC to query Bugzilla, but sends
 email to the Bugzilla email interface to submit comments to bugs.
 The From: address in the email is set to the email address of the Mercurial
 user, so the comment appears to come from the Mercurial user. In the event
 that the Mercurial user email is not recognized by Bugzilla as a Bugzilla
 user, the email associated with the Bugzilla username used to log into
 Bugzilla is used instead as the source of the comment. Marking bugs fixed
 works on all supported Bugzilla versions.
 
 Configuration items common to all access modes:
 
 bugzilla.version
   The access type to use. Values recognized are:
 
   :``xmlrpc``:       Bugzilla XMLRPC interface.
   :``xmlrpc+email``: Bugzilla XMLRPC and email interfaces.
   :``3.0``:          MySQL access, Bugzilla 3.0 and later.
   :``2.18``:         MySQL access, Bugzilla 2.18 and up to but not
                      including 3.0.
   :``2.16``:         MySQL access, Bugzilla 2.16 and up to but not
                      including 2.18.
 
 bugzilla.regexp
   Regular expression to match bug IDs for update in changeset commit message.
   It must contain one "()" named group ``<ids>`` containing the bug
   IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Bug 1234``, ``Bug no. 1234``,
   ``Bug number 1234``, ``Bugs 1234,5678``, ``Bug 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixregexp
   Regular expression to match bug IDs for marking fixed in changeset
   commit message. This must contain a "()" named group ``<ids>` containing
   the bug IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Fixes 1234``, ``Fixes bug 1234``,
   ``Fixes bugs 1234,5678``, ``Fixes 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixstatus
   The status to set a bug to when marking fixed. Default ``RESOLVED``.
 
 bugzilla.fixresolution
   The resolution to set a bug to when marking fixed. Default ``FIXED``.
 
 bugzilla.style
   The style file to use when formatting comments.
 
 bugzilla.template
   Template to use when formatting comments. Overrides style if
   specified. In addition to the usual Mercurial keywords, the
   extension specifies:
 
   :``{bug}``:     The Bugzilla bug ID.
   :``{root}``:    The full pathname of the Mercurial repository.
   :``{webroot}``: Stripped pathname of the Mercurial repository.
   :``{hgweb}``:   Base URL for browsing Mercurial repositories.
 
   Default ``changeset {node|short} in repo {root} refers to bug
   {bug}.\\ndetails:\\n\\t{desc|tabindent}``
 
 bugzilla.strip
   The number of path separator characters to strip from the front of
   the Mercurial repository path (``{root}`` in templates) to produce
   ``{webroot}``. For example, a repository with ``{root}``
   ``/var/local/my-project`` with a strip of 2 gives a value for
   ``{webroot}`` of ``my-project``. Default 0.
 
 web.baseurl
   Base URL for browsing Mercurial repositories. Referenced from
   templates as ``{hgweb}``.
 
 Configuration items common to XMLRPC+email and MySQL access modes:
 
 bugzilla.usermap
   Path of file containing Mercurial committer email to Bugzilla user email
   mappings. If specified, the file should contain one mapping per
   line::
 
     committer = Bugzilla user
 
   See also the ``[usermap]`` section.
 
 The ``[usermap]`` section is used to specify mappings of Mercurial
 committer email to Bugzilla user email. See also ``bugzilla.usermap``.
 Contains entries of the form ``committer = Bugzilla user``.
 
 XMLRPC access mode configuration:
 
 bugzilla.bzurl
   The base URL for the Bugzilla installation.
   Default ``http://localhost/bugzilla``.
 
 bugzilla.user
   The username to use to log into Bugzilla via XMLRPC. Default
   ``bugs``.
 
 bugzilla.password
   The password for Bugzilla login.
 
 XMLRPC+email access mode uses the XMLRPC access mode configuration items,
 and also:
 
 bugzilla.bzemail
   The Bugzilla email address.
 
 In addition, the Mercurial email settings must be configured. See the
 documentation in hgrc(5), sections ``[email]`` and ``[smtp]``.
 
 MySQL access mode configuration:
 
 bugzilla.host
   Hostname of the MySQL server holding the Bugzilla database.
   Default ``localhost``.
 
 bugzilla.db
   Name of the Bugzilla database in MySQL. Default ``bugs``.
 
 bugzilla.user
   Username to use to access MySQL server. Default ``bugs``.
 
 bugzilla.password
   Password to use to access MySQL server.
 
 bugzilla.timeout
   Database connection timeout (seconds). Default 5.
 
 bugzilla.bzuser
   Fallback Bugzilla user name to record comments with, if changeset
   committer cannot be found as a Bugzilla user.
 
 bugzilla.bzdir
    Bugzilla install directory. Used by default notify. Default
    ``/var/www/html/bugzilla``.
 
 bugzilla.notify
   The command to run to get Bugzilla to send bug change notification
   emails. Substitutes from a map with 3 keys, ``bzdir``, ``id`` (bug
   id) and ``user`` (committer bugzilla email). Default depends on
   version; from 2.18 it is "cd %(bzdir)s && perl -T
   contrib/sendbugmail.pl %(id)s %(user)s".
 
 Activating the extension::
 
     [extensions]
     bugzilla =
 
     [hooks]
     # run bugzilla hook on every change pulled or pushed in here
     incoming.bugzilla = python:hgext.bugzilla.hook
 
 Example configurations:
 
 XMLRPC example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
 XMLRPC+email example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. Bug comments
 are sent to the Bugzilla email address
 ``[e-mail]``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc+email
     bzemail=[e-mail]
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 MySQL example configuration. This has a local Bugzilla 3.2 installation
 in ``/opt/bugzilla-3.2``. The MySQL database is on ``localhost``,
 the Bugzilla database name is ``bugs`` and MySQL is
 accessed with MySQL username ``bugs`` password ``XYZZY``. It is used
 with a collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     host=localhost
     password=XYZZY
     version=3.0
     bzuser=[e-mail]
     bzdir=/opt/bugzilla-3.2
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 All the above add a comment to the Bugzilla bug record of the form::
 
     Changeset 3b16791d6642 in repository-name.
     http://my-project.org/hg/repository-name/rev/3b16791d6642
 
     Changeset commit comment. Bug 1234.
 '''
 
 from mercurial.i18n import _
 from mercurial.node import short
 from mercurial import cmdutil, mail, util
 import re, time, urlparse, xmlrpclib
 
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 class bzaccess(object):
     '''Base class for access to Bugzilla.'''
 
     def __init__(self, ui):
         self.ui = ui
         usermap = self.ui.config('bugzilla', 'usermap')
         if usermap:
             self.ui.readconfig(usermap, sections=['usermap'])
 
     def map_committer(self, user):
         '''map name of committer to Bugzilla user name.'''
         for committer, bzuser in self.ui.configitems('usermap'):
             if committer.lower() == user.lower():
                 return bzuser
         return user
 
     # Methods to be implemented by access classes.
     #
     # 'bugs' is a dict keyed on bug id, where values are a dict holding
     # updates to bug state. Recognized dict keys are:
     #
     # 'hours': Value, float containing work hours to be updated.
     # 'fix':   If key present, bug is to be marked fixed. Value ignored.
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
         pass
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
         pass
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
         pass
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
         pass
 
 # Bugzilla via direct access to MySQL database.
 class bzmysql(bzaccess):
     '''Support for direct MySQL access to Bugzilla.
 
     The earliest Bugzilla version this is tested with is version 2.16.
 
     If your Bugzilla is version 3.4 or above, you are strongly
     recommended to use the XMLRPC access method instead.
     '''
 
     @staticmethod
     def sql_buglist(ids):
         '''return SQL-friendly list of bug ids'''
         return '(' + ','.join(map(str, ids)) + ')'
 
     _MySQLdb = None
 
     def __init__(self, ui):
         try:
             import MySQLdb as mysql
             bzmysql._MySQLdb = mysql
-        except ImportError, err:
+        except ImportError as err:
             raise util.Abort(_('python mysql support not available: %s') % err)
 
         bzaccess.__init__(self, ui)
 
         host = self.ui.config('bugzilla', 'host', 'localhost')
         user = self.ui.config('bugzilla', 'user', 'bugs')
         passwd = self.ui.config('bugzilla', 'password')
         db = self.ui.config('bugzilla', 'db', 'bugs')
         timeout = int(self.ui.config('bugzilla', 'timeout', 5))
         self.ui.note(_('connecting to %s:%s as %s, password %s\n') %
                      (host, db, user, '*' * len(passwd)))
         self.conn = bzmysql._MySQLdb.connect(host=host,
                                                    user=user, passwd=passwd,
                                                    db=db,
                                                    connect_timeout=timeout)
         self.cursor = self.conn.cursor()
         self.longdesc_id = self.get_longdesc_id()
         self.user_ids = {}
         self.default_notify = "cd %(bzdir)s && ./processmail %(id)s %(user)s"
 
     def run(self, *args, **kwargs):
         '''run a query.'''
         self.ui.note(_('query: %s %s\n') % (args, kwargs))
         try:
             self.cursor.execute(*args, **kwargs)
         except bzmysql._MySQLdb.MySQLError:
             self.ui.note(_('failed query: %s %s\n') % (args, kwargs))
             raise
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select fieldid from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise util.Abort(_('unknown database schema'))
         return ids[0][0]
 
     def filter_real_bug_ids(self, bugs):
         '''filter not-existing bugs from set.'''
         self.run('select bug_id from bugs where bug_id in %s' %
                  bzmysql.sql_buglist(bugs.keys()))
         existing = [id for (id,) in self.cursor.fetchall()]
         for id in bugs.keys():
             if id not in existing:
                 self.ui.status(_('bug %d does not exist\n') % id)
                 del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''filter bug ids that already refer to this changeset from set.'''
         self.run('''select bug_id from longdescs where
                     bug_id in %s and thetext like "%%%s%%"''' %
                  (bzmysql.sql_buglist(bugs.keys()), short(node)))
         for (id,) in self.cursor.fetchall():
             self.ui.status(_('bug %d already knows about changeset %s\n') %
                            (id, short(node)))
             del bugs[id]
 
     def notify(self, bugs, committer):
         '''tell bugzilla to send mail.'''
         self.ui.status(_('telling bugzilla to send mail:\n'))
         (user, userid) = self.get_bugzilla_user(committer)
         for id in bugs.keys():
             self.ui.status(_('  bug %s\n') % id)
             cmdfmt = self.ui.config('bugzilla', 'notify', self.default_notify)
             bzdir = self.ui.config('bugzilla', 'bzdir',
                                    '/var/www/html/bugzilla')
             try:
                 # Backwards-compatible with old notify string, which
                 # took one string. This will throw with a new format
                 # string.
                 cmd = cmdfmt % id
             except TypeError:
                 cmd = cmdfmt % {'bzdir': bzdir, 'id': id, 'user': user}
             self.ui.note(_('running notify command %s\n') % cmd)
             fp = util.popen('(%s) 2>&1' % cmd)
             out = fp.read()
             ret = fp.close()
             if ret:
                 self.ui.warn(out)
                 raise util.Abort(_('bugzilla notify command %s') %
                                  util.explainexit(ret)[0])
         self.ui.status(_('done\n'))
 
     def get_user_id(self, user):
         '''look up numeric bugzilla user id.'''
         try:
             return self.user_ids[user]
         except KeyError:
             try:
                 userid = int(user)
             except ValueError:
                 self.ui.note(_('looking up user %s\n') % user)
                 self.run('''select userid from profiles
                             where login_name like %s''', user)
                 all = self.cursor.fetchall()
                 if len(all) != 1:
                     raise KeyError(user)
                 userid = int(all[0][0])
             self.user_ids[user] = userid
             return userid
 
     def get_bugzilla_user(self, committer):
         '''See if committer is a registered bugzilla user. Return
         bugzilla username and userid if so. If not, return default
         bugzilla username and userid.'''
         user = self.map_committer(committer)
         try:
             userid = self.get_user_id(user)
         except KeyError:
             try:
                 defaultuser = self.ui.config('bugzilla', 'bzuser')
                 if not defaultuser:
                     raise util.Abort(_('cannot find bugzilla user id for %s') %
                                      user)
                 userid = self.get_user_id(defaultuser)
                 user = defaultuser
             except KeyError:
                 raise util.Abort(_('cannot find bugzilla user id for %s or %s')
                                  % (user, defaultuser))
         return (user, userid)
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update bug state with comment text.
 
         Try adding comment as committer of changeset, otherwise as
         default bugzilla user.'''
         if len(newstate) > 0:
             self.ui.warn(_("Bugzilla/MySQL cannot update bug state\n"))
 
         (user, userid) = self.get_bugzilla_user(committer)
         now = time.strftime('%Y-%m-%d %H:%M:%S')
         self.run('''insert into longdescs
                     (bug_id, who, bug_when, thetext)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, text))
         self.run('''insert into bugs_activity (bug_id, who, bug_when, fieldid)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, self.longdesc_id))
         self.conn.commit()
 
 class bzmysql_2_18(bzmysql):
     '''support for bugzilla 2.18 series.'''
 
     def __init__(self, ui):
         bzmysql.__init__(self, ui)
         self.default_notify = \
             "cd %(bzdir)s && perl -T contrib/sendbugmail.pl %(id)s %(user)s"
 
 class bzmysql_3_0(bzmysql_2_18):
     '''support for bugzilla 3.0 series.'''
 
     def __init__(self, ui):
         bzmysql_2_18.__init__(self, ui)
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select id from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise util.Abort(_('unknown database schema'))
         return ids[0][0]
 
 # Bugzilla via XMLRPC interface.
 
 class cookietransportrequest(object):
     """A Transport request method that retains cookies over its lifetime.
 
     The regular xmlrpclib transports ignore cookies. Which causes
     a bit of a problem when you need a cookie-based login, as with
     the Bugzilla XMLRPC interface prior to 4.4.3.
 
     So this is a helper for defining a Transport which looks for
     cookies being set in responses and saves them to add to all future
     requests.
     """
 
     # Inspiration drawn from
     # http://blog.godson.in/2010/09/how-to-make-python-xmlrpclib-client.html
     # http://www.itkovian.net/base/transport-class-for-pythons-xml-rpc-lib/
 
     cookies = []
     def send_cookies(self, connection):
         if self.cookies:
             for cookie in self.cookies:
                 connection.putheader("Cookie", cookie)
 
     def request(self, host, handler, request_body, verbose=0):
         self.verbose = verbose
         self.accept_gzip_encoding = False
 
         # issue XML-RPC request
         h = self.make_connection(host)
         if verbose:
             h.set_debuglevel(1)
 
         self.send_request(h, handler, request_body)
         self.send_host(h, host)
         self.send_cookies(h)
         self.send_user_agent(h)
         self.send_content(h, request_body)
 
         # Deal with differences between Python 2.4-2.6 and 2.7.
         # In the former h is a HTTP(S). In the latter it's a
         # HTTP(S)Connection. Luckily, the 2.4-2.6 implementation of
         # HTTP(S) has an underlying HTTP(S)Connection, so extract
         # that and use it.
         try:
             response = h.getresponse()
         except AttributeError:
             response = h._conn.getresponse()
 
         # Add any cookie definitions to our list.
         for header in response.msg.getallmatchingheaders("Set-Cookie"):
             val = header.split(": ", 1)[1]
             cookie = val.split(";", 1)[0]
             self.cookies.append(cookie)
 
         if response.status != 200:
             raise xmlrpclib.ProtocolError(host + handler, response.status,
                                           response.reason, response.msg.headers)
 
         payload = response.read()
         parser, unmarshaller = self.getparser()
         parser.feed(payload)
         parser.close()
 
         return unmarshaller.close()
 
 # The explicit calls to the underlying xmlrpclib __init__() methods are
 # necessary. The xmlrpclib.Transport classes are old-style classes, and
 # it turns out their __init__() doesn't get called when doing multiple
 # inheritance with a new-style class.
 class cookietransport(cookietransportrequest, xmlrpclib.Transport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.Transport.__init__(self, use_datetime)
 
 class cookiesafetransport(cookietransportrequest, xmlrpclib.SafeTransport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.SafeTransport.__init__(self, use_datetime)
 
 class bzxmlrpc(bzaccess):
     """Support for access to Bugzilla via the Bugzilla XMLRPC API.
 
     Requires a minimum Bugzilla version 3.4.
     """
 
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
 
         bzweb = self.ui.config('bugzilla', 'bzurl',
                                'http://localhost/bugzilla/')
         bzweb = bzweb.rstrip("/") + "/xmlrpc.cgi"
 
         user = self.ui.config('bugzilla', 'user', 'bugs')
         passwd = self.ui.config('bugzilla', 'password')
 
         self.fixstatus = self.ui.config('bugzilla', 'fixstatus', 'RESOLVED')
         self.fixresolution = self.ui.config('bugzilla', 'fixresolution',
                                             'FIXED')
 
         self.bzproxy = xmlrpclib.ServerProxy(bzweb, self.transport(bzweb))
         ver = self.bzproxy.Bugzilla.version()['version'].split('.')
         self.bzvermajor = int(ver[0])
         self.bzverminor = int(ver[1])
         login = self.bzproxy.User.login({'login': user, 'password': passwd,
                                          'restrict_login': True})
         self.bztoken = login.get('token', '')
 
     def transport(self, uri):
         if urlparse.urlparse(uri, "http")[0] == "https":
             return cookiesafetransport()
         else:
             return cookietransport()
 
     def get_bug_comments(self, id):
         """Return a string with all comment text for a bug."""
         c = self.bzproxy.Bug.comments({'ids': [id],
                                        'include_fields': ['text'],
                                        'token': self.bztoken})
         return ''.join([t['text'] for t in c['bugs'][str(id)]['comments']])
 
     def filter_real_bug_ids(self, bugs):
         probe = self.bzproxy.Bug.get({'ids': sorted(bugs.keys()),
                                       'include_fields': [],
                                       'permissive': True,
                                       'token': self.bztoken,
                                       })
         for badbug in probe['faults']:
             id = badbug['id']
             self.ui.status(_('bug %d does not exist\n') % id)
             del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         for id in sorted(bugs.keys()):
             if self.get_bug_comments(id).find(short(node)) != -1:
                 self.ui.status(_('bug %d already knows about changeset %s\n') %
                                (id, short(node)))
                 del bugs[id]
 
     def updatebug(self, bugid, newstate, text, committer):
         args = {}
         if 'hours' in newstate:
             args['work_time'] = newstate['hours']
 
         if self.bzvermajor >= 4:
             args['ids'] = [bugid]
             args['comment'] = {'body' : text}
             if 'fix' in newstate:
                 args['status'] = self.fixstatus
                 args['resolution'] = self.fixresolution
             args['token'] = self.bztoken
             self.bzproxy.Bug.update(args)
         else:
             if 'fix' in newstate:
                 self.ui.warn(_("Bugzilla/XMLRPC needs Bugzilla 4.0 or later "
                                "to mark bugs fixed\n"))
             args['id'] = bugid
             args['comment'] = text
             self.bzproxy.Bug.add_comment(args)
 
 class bzxmlrpcemail(bzxmlrpc):
     """Read data from Bugzilla via XMLRPC, send updates via email.
 
     Advantages of sending updates via email:
       1. Comments can be added as any user, not just logged in user.
       2. Bug statuses or other fields not accessible via XMLRPC can
          potentially be updated.
 
     There is no XMLRPC function to change bug status before Bugzilla
     4.0, so bugs cannot be marked fixed via XMLRPC before Bugzilla 4.0.
     But bugs can be marked fixed via email from 3.4 onwards.
     """
 
     # The email interface changes subtly between 3.4 and 3.6. In 3.4,
     # in-email fields are specified as '@<fieldname> = <value>'. In
     # 3.6 this becomes '@<fieldname> <value>'. And fieldname @bug_id
     # in 3.4 becomes @id in 3.6. 3.6 and 4.0 both maintain backwards
     # compatibility, but rather than rely on this use the new format for
     # 4.0 onwards.
 
     def __init__(self, ui):
         bzxmlrpc.__init__(self, ui)
 
         self.bzemail = self.ui.config('bugzilla', 'bzemail')
         if not self.bzemail:
             raise util.Abort(_("configuration 'bzemail' missing"))
         mail.validateconfig(self.ui)
 
     def makecommandline(self, fieldname, value):
         if self.bzvermajor >= 4:
             return "@%s %s" % (fieldname, str(value))
         else:
             if fieldname == "id":
                 fieldname = "bug_id"
             return "@%s = %s" % (fieldname, str(value))
 
     def send_bug_modify_email(self, bugid, commands, comment, committer):
         '''send modification message to Bugzilla bug via email.
 
         The message format is documented in the Bugzilla email_in.pl
         specification. commands is a list of command lines, comment is the
         comment text.
 
         To stop users from crafting commit comments with
         Bugzilla commands, specify the bug ID via the message body, rather
         than the subject line, and leave a blank line after it.
         '''
         user = self.map_committer(committer)
         matches = self.bzproxy.User.get({'match': [user],
                                          'token': self.bztoken})
         if not matches['users']:
             user = self.ui.config('bugzilla', 'user', 'bugs')
             matches = self.bzproxy.User.get({'match': [user],
                                              'token': self.bztoken})
             if not matches['users']:
                 raise util.Abort(_("default bugzilla user %s email not found") %
                                  user)
         user = matches['users'][0]['email']
         commands.append(self.makecommandline("id", bugid))
 
         text = "\n".join(commands) + "\n\n" + comment
 
         _charsets = mail._charsets(self.ui)
         user = mail.addressencode(self.ui, user, _charsets)
         bzemail = mail.addressencode(self.ui, self.bzemail, _charsets)
         msg = mail.mimeencode(self.ui, text, _charsets)
         msg['From'] = user
         msg['To'] = bzemail
         msg['Subject'] = mail.headencode(self.ui, "Bug modification", _charsets)
         sendmail = mail.connect(self.ui)
         sendmail(user, bzemail, msg.as_string())
 
     def updatebug(self, bugid, newstate, text, committer):
         cmds = []
         if 'hours' in newstate:
             cmds.append(self.makecommandline("work_time", newstate['hours']))
         if 'fix' in newstate:
             cmds.append(self.makecommandline("bug_status", self.fixstatus))
             cmds.append(self.makecommandline("resolution", self.fixresolution))
         self.send_bug_modify_email(bugid, cmds, text, committer)
 
 class bugzilla(object):
     # supported versions of bugzilla. different versions have
     # different schemas.
     _versions = {
         '2.16': bzmysql,
         '2.18': bzmysql_2_18,
         '3.0':  bzmysql_3_0,
         'xmlrpc': bzxmlrpc,
         'xmlrpc+email': bzxmlrpcemail
         }
 
     _default_bug_re = (r'bugs?\s*,?\s*(?:#|nos?\.?|num(?:ber)?s?)?\s*'
                        r'(?P<ids>(?:\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
                        r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 
     _default_fix_re = (r'fix(?:es)?\s*(?:bugs?\s*)?,?\s*'
                        r'(?:nos?\.?|num(?:ber)?s?)?\s*'
                        r'(?P<ids>(?:#?\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
                        r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
 
         bzversion = self.ui.config('bugzilla', 'version')
         try:
             bzclass = bugzilla._versions[bzversion]
         except KeyError:
             raise util.Abort(_('bugzilla version %s not supported') %
                              bzversion)
         self.bzdriver = bzclass(self.ui)
 
         self.bug_re = re.compile(
             self.ui.config('bugzilla', 'regexp',
                            bugzilla._default_bug_re), re.IGNORECASE)
         self.fix_re = re.compile(
             self.ui.config('bugzilla', 'fixregexp',
                            bugzilla._default_fix_re), re.IGNORECASE)
         self.split_re = re.compile(r'\D+')
 
     def find_bugs(self, ctx):
         '''return bugs dictionary created from commit comment.
 
         Extract bug info from changeset comments. Filter out any that are
         not known to Bugzilla, and any that already have a reference to
         the given changeset in their comments.
         '''
         start = 0
         hours = 0.0
         bugs = {}
         bugmatch = self.bug_re.search(ctx.description(), start)
         fixmatch = self.fix_re.search(ctx.description(), start)
         while True:
             bugattribs = {}
             if not bugmatch and not fixmatch:
                 break
             if not bugmatch:
                 m = fixmatch
             elif not fixmatch:
                 m = bugmatch
             else:
                 if bugmatch.start() < fixmatch.start():
                     m = bugmatch
                 else:
                     m = fixmatch
             start = m.end()
             if m is bugmatch:
                 bugmatch = self.bug_re.search(ctx.description(), start)
                 if 'fix' in bugattribs:
                     del bugattribs['fix']
             else:
                 fixmatch = self.fix_re.search(ctx.description(), start)
                 bugattribs['fix'] = None
 
             try:
                 ids = m.group('ids')
             except IndexError:
                 ids = m.group(1)
             try:
                 hours = float(m.group('hours'))
                 bugattribs['hours'] = hours
             except IndexError:
                 pass
             except TypeError:
                 pass
             except ValueError:
                 self.ui.status(_("%s: invalid hours\n") % m.group('hours'))
 
             for id in self.split_re.split(ids):
                 if not id:
                     continue
                 bugs[int(id)] = bugattribs
         if bugs:
             self.bzdriver.filter_real_bug_ids(bugs)
         if bugs:
             self.bzdriver.filter_cset_known_bug_ids(ctx.node(), bugs)
         return bugs
 
     def update(self, bugid, newstate, ctx):
         '''update bugzilla bug with reference to changeset.'''
 
         def webroot(root):
             '''strip leading prefix of repo root and turn into
             url-safe path.'''
             count = int(self.ui.config('bugzilla', 'strip', 0))
             root = util.pconvert(root)
             while count > 0:
                 c = root.find('/')
                 if c == -1:
                     break
                 root = root[c + 1:]
                 count -= 1
             return root
 
         mapfile = self.ui.config('bugzilla', 'style')
         tmpl = self.ui.config('bugzilla', 'template')
         if not mapfile and not tmpl:
             tmpl = _('changeset {node|short} in repo {root} refers '
                      'to bug {bug}.\ndetails:\n\t{desc|tabindent}')
         t = cmdutil.changeset_templater(self.ui, self.repo,
                                         False, None, tmpl, mapfile, False)
         self.ui.pushbuffer()
         t.show(ctx, changes=ctx.changeset(),
                bug=str(bugid),
                hgweb=self.ui.config('web', 'baseurl'),
                root=self.repo.root,
                webroot=webroot(self.repo.root))
         data = self.ui.popbuffer()
         self.bzdriver.updatebug(bugid, newstate, data, util.email(ctx.user()))
 
     def notify(self, bugs, committer):
         '''ensure Bugzilla users are notified of bug change.'''
         self.bzdriver.notify(bugs, committer)
 
 def hook(ui, repo, hooktype, node=None, **kwargs):
     '''add comment to bugzilla for each changeset that refers to a
     bugzilla bug id. only add a comment once per bug, so same change
     seen multiple times does not fill bug with duplicate data.'''
     if node is None:
         raise util.Abort(_('hook type %s does not pass a changeset id') %
                          hooktype)
     try:
         bz = bugzilla(ui, repo)
         ctx = repo[node]
         bugs = bz.find_bugs(ctx)
         if bugs:
             for bug in bugs:
                 bz.update(bug, bugs[bug], ctx)
             bz.notify(bugs, util.email(ctx.user()))
-    except Exception, e:
+    except Exception as e:
         raise util.Abort(_('Bugzilla error: %s') % e)

hgext/censor.py

@@ -1,165 +1,165 b''
 # Copyright (C) 2015 - Mike Edgar <[e-mail]>
 #
 # This extension enables removal of file content at a given revision,
 # rewriting the data/metadata of successive revisions to preserve revision log
 # integrity.
 
 """erase file content at a given revision
 
 The censor command instructs Mercurial to erase all content of a file at a given
 revision *without updating the changeset hash.* This allows existing history to
 remain valid while preventing future clones/pulls from receiving the erased
 data.
 
 Typical uses for censor are due to security or legal requirements, including::
 
  * Passwords, private keys, crytographic material
  * Licensed data/code/libraries for which the license has expired
  * Personally Identifiable Information or other private data
 
 Censored nodes can interrupt mercurial's typical operation whenever the excised
 data needs to be materialized. Some commands, like ``hg cat``/``hg revert``,
 simply fail when asked to produce censored data. Others, like ``hg verify`` and
 ``hg update``, must be capable of tolerating censored data to continue to
 function in a meaningful way. Such commands only tolerate censored file
 revisions if they are allowed by the "censor.policy=ignore" config option.
 """
 
 from mercurial.node import short
 from mercurial import cmdutil, error, filelog, revlog, scmutil, util
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 @command('censor',
     [('r', 'rev', '', _('censor file from specified revision'), _('REV')),
      ('t', 'tombstone', '', _('replacement tombstone data'), _('TEXT'))],
     _('-r REV [-t TEXT] [FILE]'))
 def censor(ui, repo, path, rev='', tombstone='', **opts):
     if not path:
         raise util.Abort(_('must specify file path to censor'))
     if not rev:
         raise util.Abort(_('must specify revision to censor'))
 
     flog = repo.file(path)
     if not len(flog):
         raise util.Abort(_('cannot censor file with no history'))
 
     rev = scmutil.revsingle(repo, rev, rev).rev()
     try:
         ctx = repo[rev]
     except KeyError:
         raise util.Abort(_('invalid revision identifier %s') % rev)
 
     try:
         fctx = ctx.filectx(path)
     except error.LookupError:
         raise util.Abort(_('file does not exist at revision %s') % rev)
 
     fnode = fctx.filenode()
     headctxs = [repo[c] for c in repo.heads()]
     heads = [c for c in headctxs if path in c and c.filenode(path) == fnode]
     if heads:
         headlist = ', '.join([short(c.node()) for c in heads])
         raise util.Abort(_('cannot censor file in heads (%s)') % headlist,
             hint=_('clean/delete and commit first'))
 
     wctx = repo[None]
     wp = wctx.parents()
     if ctx.node() in [p.node() for p in wp]:
         raise util.Abort(_('cannot censor working directory'),
             hint=_('clean/delete/update first'))
 
     flogv = flog.version & 0xFFFF
     if flogv != revlog.REVLOGNG:
         raise util.Abort(
             _('censor does not support revlog version %d') % (flogv,))
 
     tombstone = filelog.packmeta({"censored": tombstone}, "")
 
     crev = fctx.filerev()
 
     if len(tombstone) > flog.rawsize(crev):
         raise util.Abort(_(
             'censor tombstone must be no longer than censored data'))
 
     # Using two files instead of one makes it easy to rewrite entry-by-entry
     idxread = repo.svfs(flog.indexfile, 'r')
     idxwrite = repo.svfs(flog.indexfile, 'wb', atomictemp=True)
     if flog.version & revlog.REVLOGNGINLINEDATA:
         dataread, datawrite = idxread, idxwrite
     else:
         dataread = repo.svfs(flog.datafile, 'r')
         datawrite = repo.svfs(flog.datafile, 'wb', atomictemp=True)
 
     # Copy all revlog data up to the entry to be censored.
     rio = revlog.revlogio()
     offset = flog.start(crev)
 
     for chunk in util.filechunkiter(idxread, limit=crev * rio.size):
         idxwrite.write(chunk)
     for chunk in util.filechunkiter(dataread, limit=offset):
         datawrite.write(chunk)
 
     def rewriteindex(r, newoffs, newdata=None):
         """Rewrite the index entry with a new data offset and optional new data.
 
         The newdata argument, if given, is a tuple of three positive integers:
         (new compressed, new uncompressed, added flag bits).
         """
         offlags, comp, uncomp, base, link, p1, p2, nodeid = flog.index[r]
         flags = revlog.gettype(offlags)
         if newdata:
             comp, uncomp, nflags = newdata
             flags |= nflags
         offlags = revlog.offset_type(newoffs, flags)
         e = (offlags, comp, uncomp, r, link, p1, p2, nodeid)
         idxwrite.write(rio.packentry(e, None, flog.version, r))
         idxread.seek(rio.size, 1)
 
     def rewrite(r, offs, data, nflags=revlog.REVIDX_DEFAULT_FLAGS):
         """Write the given full text to the filelog with the given data offset.
 
         Returns:
             The integer number of data bytes written, for tracking data offsets.
         """
         flag, compdata = flog.compress(data)
         newcomp = len(flag) + len(compdata)
         rewriteindex(r, offs, (newcomp, len(data), nflags))
         datawrite.write(flag)
         datawrite.write(compdata)
         dataread.seek(flog.length(r), 1)
         return newcomp
 
     # Rewrite censored revlog entry with (padded) tombstone data.
     pad = ' ' * (flog.rawsize(crev) - len(tombstone))
     offset += rewrite(crev, offset, tombstone + pad, revlog.REVIDX_ISCENSORED)
 
     # Rewrite all following filelog revisions fixing up offsets and deltas.
     for srev in xrange(crev + 1, len(flog)):
         if crev in flog.parentrevs(srev):
             # Immediate children of censored node must be re-added as fulltext.
             try:
                 revdata = flog.revision(srev)
-            except error.CensoredNodeError, e:
+            except error.CensoredNodeError as e:
                 revdata = e.tombstone
             dlen = rewrite(srev, offset, revdata)
         else:
             # Copy any other revision data verbatim after fixing up the offset.
             rewriteindex(srev, offset)
             dlen = flog.length(srev)
             for chunk in util.filechunkiter(dataread, limit=dlen):
                 datawrite.write(chunk)
         offset += dlen
 
     idxread.close()
     idxwrite.close()
     if dataread is not idxread:
         dataread.close()
         datawrite.close()

hgext/churn.py

@@ -1,205 +1,205 b''
 # churn.py - create a graph of revisions count grouped by template
 #
 # Copyright 2006 Josef "Jeff" Sipek <[e-mail]>
 # Copyright 2008 Alexander Solovyov <[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.
 
 '''command to display statistics about repository history'''
 
 from mercurial.i18n import _
 from mercurial import patch, cmdutil, scmutil, util, commands
 from mercurial import encoding
 import os
 import time, datetime
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 def maketemplater(ui, repo, tmpl):
     try:
         t = cmdutil.changeset_templater(ui, repo, False, None, tmpl,
                                         None, False)
-    except SyntaxError, inst:
+    except SyntaxError as inst:
         raise util.Abort(inst.args[0])
     return t
 
 def changedlines(ui, repo, ctx1, ctx2, fns):
     added, removed = 0, 0
     fmatch = scmutil.matchfiles(repo, fns)
     diff = ''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
     for l in diff.split('\n'):
         if l.startswith("+") and not l.startswith("+++ "):
             added += 1
         elif l.startswith("-") and not l.startswith("--- "):
             removed += 1
     return (added, removed)
 
 def countrate(ui, repo, amap, *pats, **opts):
     """Calculate stats"""
     if opts.get('dateformat'):
         def getkey(ctx):
             t, tz = ctx.date()
             date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
             return date.strftime(opts['dateformat'])
     else:
         tmpl = opts.get('oldtemplate') or opts.get('template')
         tmpl = maketemplater(ui, repo, tmpl)
         def getkey(ctx):
             ui.pushbuffer()
             tmpl.show(ctx)
             return ui.popbuffer()
 
     state = {'count': 0}
     rate = {}
     df = False
     if opts.get('date'):
         df = util.matchdate(opts['date'])
 
     m = scmutil.match(repo[None], pats, opts)
     def prep(ctx, fns):
         rev = ctx.rev()
         if df and not df(ctx.date()[0]): # doesn't match date format
             return
 
         key = getkey(ctx).strip()
         key = amap.get(key, key) # alias remap
         if opts.get('changesets'):
             rate[key] = (rate.get(key, (0,))[0] + 1, 0)
         else:
             parents = ctx.parents()
             if len(parents) > 1:
                 ui.note(_('revision %d is a merge, ignoring...\n') % (rev,))
                 return
 
             ctx1 = parents[0]
             lines = changedlines(ui, repo, ctx1, ctx, fns)
             rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
 
         state['count'] += 1
         ui.progress(_('analyzing'), state['count'], total=len(repo))
 
     for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
         continue
 
     ui.progress(_('analyzing'), None)
 
     return rate
 
 
 @command('churn',
     [('r', 'rev', [],
      _('count rate for the specified revision or revset'), _('REV')),
     ('d', 'date', '',
      _('count rate for revisions matching date spec'), _('DATE')),
     ('t', 'oldtemplate', '',
      _('template to group changesets (DEPRECATED)'), _('TEMPLATE')),
     ('T', 'template', '{author|email}',
      _('template to group changesets'), _('TEMPLATE')),
     ('f', 'dateformat', '',
      _('strftime-compatible format for grouping by date'), _('FORMAT')),
     ('c', 'changesets', False, _('count rate by number of changesets')),
     ('s', 'sort', False, _('sort by key (default: sort by count)')),
     ('', 'diffstat', False, _('display added/removed lines separately')),
     ('', 'aliases', '', _('file with email aliases'), _('FILE')),
     ] + commands.walkopts,
     _("hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
     inferrepo=True)
 def churn(ui, repo, *pats, **opts):
     '''histogram of changes to the repository
 
     This command will display a histogram representing the number
     of changed lines or revisions, grouped according to the given
     template. The default template will group changes by author.
     The --dateformat option may be used to group the results by
     date instead.
 
     Statistics are based on the number of changed lines, or
     alternatively the number of matching revisions if the
     --changesets option is specified.
 
     Examples::
 
       # display count of changed lines for every committer
       hg churn -t "{author|email}"
 
       # display daily activity graph
       hg churn -f "%H" -s -c
 
       # display activity of developers by month
       hg churn -f "%Y-%m" -s -c
 
       # display count of lines changed in every year
       hg churn -f "%Y" -s
 
     It is possible to map alternate email addresses to a main address
     by providing a file using the following format::
 
       <alias email> = <actual email>
 
     Such a file may be specified with the --aliases option, otherwise
     a .hgchurn file will be looked for in the working directory root.
     Aliases will be split from the rightmost "=".
     '''
     def pad(s, l):
         return s + " " * (l - encoding.colwidth(s))
 
     amap = {}
     aliases = opts.get('aliases')
     if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
         aliases = repo.wjoin('.hgchurn')
     if aliases:
         for l in open(aliases, "r"):
             try:
                 alias, actual = l.rsplit('=' in l and '=' or None, 1)
                 amap[alias.strip()] = actual.strip()
             except ValueError:
                 l = l.strip()
                 if l:
                     ui.warn(_("skipping malformed alias: %s\n") % l)
                 continue
 
     rate = countrate(ui, repo, amap, *pats, **opts).items()
     if not rate:
         return
 
     if opts.get('sort'):
         rate.sort()
     else:
         rate.sort(key=lambda x: (-sum(x[1]), x))
 
     # Be careful not to have a zero maxcount (issue833)
     maxcount = float(max(sum(v) for k, v in rate)) or 1.0
     maxname = max(len(k) for k, v in rate)
 
     ttywidth = ui.termwidth()
     ui.debug("assuming %i character terminal\n" % ttywidth)
     width = ttywidth - maxname - 2 - 2 - 2
 
     if opts.get('diffstat'):
         width -= 15
         def format(name, diffstat):
             added, removed = diffstat
             return "%s %15s %s%s\n" % (pad(name, maxname),
                                        '+%d/-%d' % (added, removed),
                                        ui.label('+' * charnum(added),
                                                 'diffstat.inserted'),
                                        ui.label('-' * charnum(removed),
                                                 'diffstat.deleted'))
     else:
         width -= 6
         def format(name, count):
             return "%s %6d %s\n" % (pad(name, maxname), sum(count),
                                     '*' * charnum(sum(count)))
 
     def charnum(count):
         return int(round(count * width / maxcount))
 
     for name, count in rate:
         ui.write(format(name, count))

hgext/color.py

@@ -1,688 +1,688 b''
 # color.py color output for Mercurial commands
 #
 # Copyright (C) 2007 Kevin Christen <[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.
 
 '''colorize output from some commands
 
 The color extension colorizes output from several Mercurial commands.
 For example, the diff command shows additions in green and deletions
 in red, while the status command shows modified files in magenta. Many
 other commands have analogous colors. It is possible to customize
 these colors.
 
 Effects
 -------
 
 Other effects in addition to color, like bold and underlined text, are
 also available. By default, the terminfo database is used to find the
 terminal codes used to change color and effect.  If terminfo is not
 available, then effects are rendered with the ECMA-48 SGR control
 function (aka ANSI escape codes).
 
 The available effects in terminfo mode are 'blink', 'bold', 'dim',
 'inverse', 'invisible', 'italic', 'standout', and 'underline'; in
 ECMA-48 mode, the options are 'bold', 'inverse', 'italic', and
 'underline'.  How each is rendered depends on the terminal emulator.
 Some may not be available for a given terminal type, and will be
 silently ignored.
 
 Labels
 ------
 
 Text receives color effects depending on the labels that it has. Many
 default Mercurial commands emit labelled text. You can also define
 your own labels in templates using the label function, see :hg:`help
 templates`. A single portion of text may have more than one label. In
 that case, effects given to the last label will override any other
 effects. This includes the special "none" effect, which nullifies
 other effects.
 
 Labels are normally invisible. In order to see these labels and their
 position in the text, use the global --color=debug option. The same
 anchor text may be associated to multiple labels, e.g.
 
   [log.changeset changeset.secret|changeset:   22611:6f0a53c8f587]
 
 The following are the default effects for some default labels. Default
 effects may be overridden from your configuration file::
 
   [color]
   status.modified = blue bold underline red_background
   status.added = green bold
   status.removed = red bold blue_background
   status.deleted = cyan bold underline
   status.unknown = magenta bold underline
   status.ignored = black bold
 
   # 'none' turns off all effects
   status.clean = none
   status.copied = none
 
   qseries.applied = blue bold underline
   qseries.unapplied = black bold
   qseries.missing = red bold
 
   diff.diffline = bold
   diff.extended = cyan bold
   diff.file_a = red bold
   diff.file_b = green bold
   diff.hunk = magenta
   diff.deleted = red
   diff.inserted = green
   diff.changed = white
   diff.tab =
   diff.trailingwhitespace = bold red_background
 
   # Blank so it inherits the style of the surrounding label
   changeset.public =
   changeset.draft =
   changeset.secret =
 
   resolve.unresolved = red bold
   resolve.resolved = green bold
 
   bookmarks.active = green
 
   branches.active = none
   branches.closed = black bold
   branches.current = green
   branches.inactive = none
 
   tags.normal = green
   tags.local = black bold
 
   rebase.rebased = blue
   rebase.remaining = red bold
 
   shelve.age = cyan
   shelve.newest = green bold
   shelve.name = blue bold
 
   histedit.remaining = red bold
 
 Custom colors
 -------------
 
 Because there are only eight standard colors, this module allows you
 to define color names for other color slots which might be available
 for your terminal type, assuming terminfo mode.  For instance::
 
   color.brightblue = 12
   color.pink = 207
   color.orange = 202
 
 to set 'brightblue' to color slot 12 (useful for 16 color terminals
 that have brighter colors defined in the upper eight) and, 'pink' and
 'orange' to colors in 256-color xterm's default color cube.  These
 defined colors may then be used as any of the pre-defined eight,
 including appending '_background' to set the background to that color.
 
 Modes
 -----
 
 By default, the color extension will use ANSI mode (or win32 mode on
 Windows) if it detects a terminal. To override auto mode (to enable
 terminfo mode, for example), set the following configuration option::
 
   [color]
   mode = terminfo
 
 Any value other than 'ansi', 'win32', 'terminfo', or 'auto' will
 disable color.
 
 Note that on some systems, terminfo mode may cause problems when using
 color with the pager extension and less -R. less with the -R option
 will only display ECMA-48 color codes, and terminfo mode may sometimes
 emit codes that less doesn't understand. You can work around this by
 either using ansi mode (or auto mode), or by using less -r (which will
 pass through all terminal control codes, not just color control
 codes).
 
 On some systems (such as MSYS in Windows), the terminal may support
 a different color mode than the pager (activated via the "pager"
 extension). It is possible to define separate modes depending on whether
 the pager is active::
 
   [color]
   mode = auto
   pagermode = ansi
 
 If ``pagermode`` is not defined, the ``mode`` will be used.
 '''
 
 import os
 
 from mercurial import cmdutil, commands, dispatch, extensions, subrepo, util
 from mercurial import ui as uimod
 from mercurial import templater, error
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 # start and stop parameters for effects
 _effects = {'none': 0, 'black': 30, 'red': 31, 'green': 32, 'yellow': 33,
             'blue': 34, 'magenta': 35, 'cyan': 36, 'white': 37, 'bold': 1,
             'italic': 3, 'underline': 4, 'inverse': 7, 'dim': 2,
             'black_background': 40, 'red_background': 41,
             'green_background': 42, 'yellow_background': 43,
             'blue_background': 44, 'purple_background': 45,
             'cyan_background': 46, 'white_background': 47}
 
 def _terminfosetup(ui, mode):
     '''Initialize terminfo data and the terminal if we're in terminfo mode.'''
 
     global _terminfo_params
     # If we failed to load curses, we go ahead and return.
     if not _terminfo_params:
         return
     # Otherwise, see what the config file says.
     if mode not in ('auto', 'terminfo'):
         return
 
     _terminfo_params.update((key[6:], (False, int(val)))
         for key, val in ui.configitems('color')
         if key.startswith('color.'))
 
     try:
         curses.setupterm()
-    except curses.error, e:
+    except curses.error as e:
         _terminfo_params = {}
         return
 
     for key, (b, e) in _terminfo_params.items():
         if not b:
             continue
         if not curses.tigetstr(e):
             # Most terminals don't support dim, invis, etc, so don't be
             # noisy and use ui.debug().
             ui.debug("no terminfo entry for %s\n" % e)
             del _terminfo_params[key]
     if not curses.tigetstr('setaf') or not curses.tigetstr('setab'):
         # Only warn about missing terminfo entries if we explicitly asked for
         # terminfo mode.
         if mode == "terminfo":
             ui.warn(_("no terminfo entry for setab/setaf: reverting to "
               "ECMA-48 color\n"))
         _terminfo_params = {}
 
 def _modesetup(ui, coloropt):
     global _terminfo_params
 
     if coloropt == 'debug':
         return 'debug'
 
     auto = (coloropt == 'auto')
     always = not auto and util.parsebool(coloropt)
     if not always and not auto:
         return None
 
     formatted = always or (os.environ.get('TERM') != 'dumb' and ui.formatted())
 
     mode = ui.config('color', 'mode', 'auto')
 
     # If pager is active, color.pagermode overrides color.mode.
     if getattr(ui, 'pageractive', False):
         mode = ui.config('color', 'pagermode', mode)
 
     realmode = mode
     if mode == 'auto':
         if os.name == 'nt':
             term = os.environ.get('TERM')
             # TERM won't be defined in a vanilla cmd.exe environment.
 
             # UNIX-like environments on Windows such as Cygwin and MSYS will
             # set TERM. They appear to make a best effort attempt at setting it
             # to something appropriate. However, not all environments with TERM
             # defined support ANSI. Since "ansi" could result in terminal
             # gibberish, we error on the side of selecting "win32". However, if
             # w32effects is not defined, we almost certainly don't support
             # "win32", so don't even try.
             if (term and 'xterm' in term) or not w32effects:
                 realmode = 'ansi'
             else:
                 realmode = 'win32'
         else:
             realmode = 'ansi'
 
     def modewarn():
         # only warn if color.mode was explicitly set and we're in
         # an interactive terminal
         if mode == realmode and ui.interactive():
             ui.warn(_('warning: failed to set color mode to %s\n') % mode)
 
     if realmode == 'win32':
         _terminfo_params = {}
         if not w32effects:
             modewarn()
             return None
         _effects.update(w32effects)
     elif realmode == 'ansi':
         _terminfo_params = {}
     elif realmode == 'terminfo':
         _terminfosetup(ui, mode)
         if not _terminfo_params:
             ## FIXME Shouldn't we return None in this case too?
             modewarn()
             realmode = 'ansi'
     else:
         return None
 
     if always or (auto and formatted):
         return realmode
     return None
 
 try:
     import curses
     # Mapping from effect name to terminfo attribute name or color number.
     # This will also force-load the curses module.
     _terminfo_params = {'none': (True, 'sgr0'),
                         'standout': (True, 'smso'),
                         'underline': (True, 'smul'),
                         'reverse': (True, 'rev'),
                         'inverse': (True, 'rev'),
                         'blink': (True, 'blink'),
                         'dim': (True, 'dim'),
                         'bold': (True, 'bold'),
                         'invisible': (True, 'invis'),
                         'italic': (True, 'sitm'),
                         'black': (False, curses.COLOR_BLACK),
                         'red': (False, curses.COLOR_RED),
                         'green': (False, curses.COLOR_GREEN),
                         'yellow': (False, curses.COLOR_YELLOW),
                         'blue': (False, curses.COLOR_BLUE),
                         'magenta': (False, curses.COLOR_MAGENTA),
                         'cyan': (False, curses.COLOR_CYAN),
                         'white': (False, curses.COLOR_WHITE)}
 except ImportError:
     _terminfo_params = {}
 
 _styles = {'grep.match': 'red bold',
            'grep.linenumber': 'green',
            'grep.rev': 'green',
            'grep.change': 'green',
            'grep.sep': 'cyan',
            'grep.filename': 'magenta',
            'grep.user': 'magenta',
            'grep.date': 'magenta',
            'bookmarks.active': 'green',
            'branches.active': 'none',
            'branches.closed': 'black bold',
            'branches.current': 'green',
            'branches.inactive': 'none',
            'diff.changed': 'white',
            'diff.deleted': 'red',
            'diff.diffline': 'bold',
            'diff.extended': 'cyan bold',
            'diff.file_a': 'red bold',
            'diff.file_b': 'green bold',
            'diff.hunk': 'magenta',
            'diff.inserted': 'green',
            'diff.tab': '',
            'diff.trailingwhitespace': 'bold red_background',
            'changeset.public' : '',
            'changeset.draft' : '',
            'changeset.secret' : '',
            'diffstat.deleted': 'red',
            'diffstat.inserted': 'green',
            'histedit.remaining': 'red bold',
            'ui.prompt': 'yellow',
            'log.changeset': 'yellow',
            'patchbomb.finalsummary': '',
            'patchbomb.from': 'magenta',
            'patchbomb.to': 'cyan',
            'patchbomb.subject': 'green',
            'patchbomb.diffstats': '',
            'rebase.rebased': 'blue',
            'rebase.remaining': 'red bold',
            'resolve.resolved': 'green bold',
            'resolve.unresolved': 'red bold',
            'shelve.age': 'cyan',
            'shelve.newest': 'green bold',
            'shelve.name': 'blue bold',
            'status.added': 'green bold',
            'status.clean': 'none',
            'status.copied': 'none',
            'status.deleted': 'cyan bold underline',
            'status.ignored': 'black bold',
            'status.modified': 'blue bold',
            'status.removed': 'red bold',
            'status.unknown': 'magenta bold underline',
            'tags.normal': 'green',
            'tags.local': 'black bold'}
 
 
 def _effect_str(effect):
     '''Helper function for render_effects().'''
 
     bg = False
     if effect.endswith('_background'):
         bg = True
         effect = effect[:-11]
     attr, val = _terminfo_params[effect]
     if attr:
         return curses.tigetstr(val)
     elif bg:
         return curses.tparm(curses.tigetstr('setab'), val)
     else:
         return curses.tparm(curses.tigetstr('setaf'), val)
 
 def render_effects(text, effects):
     'Wrap text in commands to turn on each effect.'
     if not text:
         return text
     if not _terminfo_params:
         start = [str(_effects[e]) for e in ['none'] + effects.split()]
         start = '\033[' + ';'.join(start) + 'm'
         stop = '\033[' + str(_effects['none']) + 'm'
     else:
         start = ''.join(_effect_str(effect)
                         for effect in ['none'] + effects.split())
         stop = _effect_str('none')
     return ''.join([start, text, stop])
 
 def extstyles():
     for name, ext in extensions.extensions():
         _styles.update(getattr(ext, 'colortable', {}))
 
 def valideffect(effect):
     'Determine if the effect is valid or not.'
     good = False
     if not _terminfo_params and effect in _effects:
         good = True
     elif effect in _terminfo_params or effect[:-11] in _terminfo_params:
         good = True
     return good
 
 def configstyles(ui):
     for status, cfgeffects in ui.configitems('color'):
         if '.' not in status or status.startswith('color.'):
             continue
         cfgeffects = ui.configlist('color', status)
         if cfgeffects:
             good = []
             for e in cfgeffects:
                 if valideffect(e):
                     good.append(e)
                 else:
                     ui.warn(_("ignoring unknown color/effect %r "
                               "(configured in color.%s)\n")
                             % (e, status))
             _styles[status] = ' '.join(good)
 
 class colorui(uimod.ui):
     def popbuffer(self, labeled=False):
         if self._colormode is None:
             return super(colorui, self).popbuffer(labeled)
 
         self._bufferstates.pop()
         if labeled:
             return ''.join(self.label(a, label) for a, label
                            in self._buffers.pop())
         return ''.join(a for a, label in self._buffers.pop())
 
     _colormode = 'ansi'
     def write(self, *args, **opts):
         if self._colormode is None:
             return super(colorui, self).write(*args, **opts)
 
         label = opts.get('label', '')
         if self._buffers:
             self._buffers[-1].extend([(str(a), label) for a in args])
         elif self._colormode == 'win32':
             for a in args:
                 win32print(a, super(colorui, self).write, **opts)
         else:
             return super(colorui, self).write(
                 *[self.label(str(a), label) for a in args], **opts)
 
     def write_err(self, *args, **opts):
         if self._colormode is None:
             return super(colorui, self).write_err(*args, **opts)
 
         label = opts.get('label', '')
         if self._bufferstates and self._bufferstates[-1][0]:
             return self.write(*args, **opts)
         if self._colormode == 'win32':
             for a in args:
                 win32print(a, super(colorui, self).write_err, **opts)
         else:
             return super(colorui, self).write_err(
                 *[self.label(str(a), label) for a in args], **opts)
 
     def showlabel(self, msg, label):
         if label and msg:
             if msg[-1] == '\n':
                 return "[%s|%s]\n" % (label, msg[:-1])
             else:
                 return "[%s|%s]" % (label, msg)
         else:
             return msg
 
     def label(self, msg, label):
         if self._colormode is None:
             return super(colorui, self).label(msg, label)
 
         if self._colormode == 'debug':
             return self.showlabel(msg, label)
 
         effects = []
         for l in label.split():
             s = _styles.get(l, '')
             if s:
                 effects.append(s)
             elif valideffect(l):
                 effects.append(l)
         effects = ' '.join(effects)
         if effects:
             return '\n'.join([render_effects(s, effects)
                               for s in msg.split('\n')])
         return msg
 
 def templatelabel(context, mapping, args):
     if len(args) != 2:
         # i18n: "label" is a keyword
         raise error.ParseError(_("label expects two arguments"))
 
     # add known effects to the mapping so symbols like 'red', 'bold',
     # etc. don't need to be quoted
     mapping.update(dict([(k, k) for k in _effects]))
 
     thing = args[1][0](context, mapping, args[1][1])
 
     # apparently, repo could be a string that is the favicon?
     repo = mapping.get('repo', '')
     if isinstance(repo, str):
         return thing
 
     label = args[0][0](context, mapping, args[0][1])
 
     thing = templater.stringify(thing)
     label = templater.stringify(label)
 
     return repo.ui.label(thing, label)
 
 def uisetup(ui):
     if ui.plain():
         return
     if not isinstance(ui, colorui):
         colorui.__bases__ = (ui.__class__,)
         ui.__class__ = colorui
     def colorcmd(orig, ui_, opts, cmd, cmdfunc):
         mode = _modesetup(ui_, opts['color'])
         colorui._colormode = mode
         if mode and mode != 'debug':
             extstyles()
             configstyles(ui_)
         return orig(ui_, opts, cmd, cmdfunc)
     def colorgit(orig, gitsub, commands, env=None, stream=False, cwd=None):
         if gitsub.ui._colormode and len(commands) and commands[0] == "diff":
                 # insert the argument in the front,
                 # the end of git diff arguments is used for paths
                 commands.insert(1, '--color')
         return orig(gitsub, commands, env, stream, cwd)
     extensions.wrapfunction(dispatch, '_runcommand', colorcmd)
     extensions.wrapfunction(subrepo.gitsubrepo, '_gitnodir', colorgit)
     templatelabel.__doc__ = templater.funcs['label'].__doc__
     templater.funcs['label'] = templatelabel
 
 def extsetup(ui):
     commands.globalopts.append(
         ('', 'color', 'auto',
          # i18n: 'always', 'auto', 'never', and 'debug' are keywords
          # and should not be translated
          _("when to colorize (boolean, always, auto, never, or debug)"),
          _('TYPE')))
 
 @command('debugcolor', [], 'hg debugcolor')
 def debugcolor(ui, repo, **opts):
     global _styles
     _styles = {}
     for effect in _effects.keys():
         _styles[effect] = effect
     ui.write(('color mode: %s\n') % ui._colormode)
     ui.write(_('available colors:\n'))
     for label, colors in _styles.items():
         ui.write(('%s\n') % colors, label=label)
 
 if os.name != 'nt':
     w32effects = None
 else:
     import re, ctypes
 
     _kernel32 = ctypes.windll.kernel32
 
     _WORD = ctypes.c_ushort
 
     _INVALID_HANDLE_VALUE = -1
 
     class _COORD(ctypes.Structure):
         _fields_ = [('X', ctypes.c_short),
                     ('Y', ctypes.c_short)]
 
     class _SMALL_RECT(ctypes.Structure):
         _fields_ = [('Left', ctypes.c_short),
                     ('Top', ctypes.c_short),
                     ('Right', ctypes.c_short),
                     ('Bottom', ctypes.c_short)]
 
     class _CONSOLE_SCREEN_BUFFER_INFO(ctypes.Structure):
         _fields_ = [('dwSize', _COORD),
                     ('dwCursorPosition', _COORD),
                     ('wAttributes', _WORD),
                     ('srWindow', _SMALL_RECT),
                     ('dwMaximumWindowSize', _COORD)]
 
     _STD_OUTPUT_HANDLE = 0xfffffff5L # (DWORD)-11
     _STD_ERROR_HANDLE = 0xfffffff4L  # (DWORD)-12
 
     _FOREGROUND_BLUE = 0x0001
     _FOREGROUND_GREEN = 0x0002
     _FOREGROUND_RED = 0x0004
     _FOREGROUND_INTENSITY = 0x0008
 
     _BACKGROUND_BLUE = 0x0010
     _BACKGROUND_GREEN = 0x0020
     _BACKGROUND_RED = 0x0040
     _BACKGROUND_INTENSITY = 0x0080
 
     _COMMON_LVB_REVERSE_VIDEO = 0x4000
     _COMMON_LVB_UNDERSCORE = 0x8000
 
     # http://msdn.microsoft.com/en-us/library/ms682088%28VS.85%29.aspx
     w32effects = {
         'none': -1,
         'black': 0,
         'red': _FOREGROUND_RED,
         'green': _FOREGROUND_GREEN,
         'yellow': _FOREGROUND_RED | _FOREGROUND_GREEN,
         'blue': _FOREGROUND_BLUE,
         'magenta': _FOREGROUND_BLUE | _FOREGROUND_RED,
         'cyan': _FOREGROUND_BLUE | _FOREGROUND_GREEN,
         'white': _FOREGROUND_RED | _FOREGROUND_GREEN | _FOREGROUND_BLUE,
         'bold': _FOREGROUND_INTENSITY,
         'black_background': 0x100,                  # unused value > 0x0f
         'red_background': _BACKGROUND_RED,
         'green_background': _BACKGROUND_GREEN,
         'yellow_background': _BACKGROUND_RED | _BACKGROUND_GREEN,
         'blue_background': _BACKGROUND_BLUE,
         'purple_background': _BACKGROUND_BLUE | _BACKGROUND_RED,
         'cyan_background': _BACKGROUND_BLUE | _BACKGROUND_GREEN,
         'white_background': (_BACKGROUND_RED | _BACKGROUND_GREEN |
                              _BACKGROUND_BLUE),
         'bold_background': _BACKGROUND_INTENSITY,
         'underline': _COMMON_LVB_UNDERSCORE,  # double-byte charsets only
         'inverse': _COMMON_LVB_REVERSE_VIDEO, # double-byte charsets only
     }
 
     passthrough = set([_FOREGROUND_INTENSITY,
                        _BACKGROUND_INTENSITY,
                        _COMMON_LVB_UNDERSCORE,
                        _COMMON_LVB_REVERSE_VIDEO])
 
     stdout = _kernel32.GetStdHandle(
                   _STD_OUTPUT_HANDLE)  # don't close the handle returned
     if stdout is None or stdout == _INVALID_HANDLE_VALUE:
         w32effects = None
     else:
         csbi = _CONSOLE_SCREEN_BUFFER_INFO()
         if not _kernel32.GetConsoleScreenBufferInfo(
                     stdout, ctypes.byref(csbi)):
             # stdout may not support GetConsoleScreenBufferInfo()
             # when called from subprocess or redirected
             w32effects = None
         else:
             origattr = csbi.wAttributes
             ansire = re.compile('\033\[([^m]*)m([^\033]*)(.*)',
                                 re.MULTILINE | re.DOTALL)
 
     def win32print(text, orig, **opts):
         label = opts.get('label', '')
         attr = origattr
 
         def mapcolor(val, attr):
             if val == -1:
                 return origattr
             elif val in passthrough:
                 return attr | val
             elif val > 0x0f:
                 return (val & 0x70) | (attr & 0x8f)
             else:
                 return (val & 0x07) | (attr & 0xf8)
 
         # determine console attributes based on labels
         for l in label.split():
             style = _styles.get(l, '')
             for effect in style.split():
                 try:
                     attr = mapcolor(w32effects[effect], attr)
                 except KeyError:
                     # w32effects could not have certain attributes so we skip
                     # them if not found
                     pass
         # hack to ensure regexp finds data
         if not text.startswith('\033['):
             text = '\033[m' + text
 
         # Look for ANSI-like codes embedded in text
         m = re.match(ansire, text)
 
         try:
             while m:
                 for sattr in m.group(1).split(';'):
                     if sattr:
                         attr = mapcolor(int(sattr), attr)
                 _kernel32.SetConsoleTextAttribute(stdout, attr)
                 orig(m.group(2), **opts)
                 m = re.match(ansire, m.group(3))
         finally:
             # Explicitly reset original attributes
             _kernel32.SetConsoleTextAttribute(stdout, origattr)

hgext/convert/common.py

@@ -1,471 +1,471 b''
 # common.py - common code 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 base64, errno, subprocess, os, datetime, re
 import cPickle as pickle
 from mercurial import phases, util
 from mercurial.i18n import _
 
 propertycache = util.propertycache
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64.encodestring(s)
         lines = [l.splitlines()[0] for l in lines]
         return ''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 def decodeargs(s):
     s = base64.decodestring(s)
     return pickle.loads(s)
 
 class MissingTool(Exception):
     pass
 
 def checktool(exe, name=None, abort=True):
     name = name or exe
     if not util.findexe(exe):
         if abort:
             exc = util.Abort
         else:
             exc = MissingTool
         raise exc(_('cannot find required "%s" tool') % name)
 
 class NoRepo(Exception):
     pass
 
 SKIPREV = 'SKIP'
 
 class commit(object):
     def __init__(self, author, date, desc, parents, branch=None, rev=None,
                  extra={}, sortkey=None, saverev=True, phase=phases.draft):
         self.author = author or 'unknown'
         self.date = date or '0 0'
         self.desc = desc
         self.parents = parents
         self.branch = branch
         self.rev = rev
         self.extra = extra
         self.sortkey = sortkey
         self.saverev = saverev
         self.phase = phase
 
 class converter_source(object):
     """Conversion source interface"""
 
     def __init__(self, ui, path=None, rev=None):
         """Initialize conversion source (or raise NoRepo("message")
         exception if path is not a valid repository)"""
         self.ui = ui
         self.path = path
         self.rev = rev
 
         self.encoding = 'utf-8'
 
     def checkhexformat(self, revstr, mapname='splicemap'):
         """ fails if revstr is not a 40 byte hex. mercurial and git both uses
             such format for their revision numbering
         """
         if not re.match(r'[0-9a-fA-F]{40,40}$', revstr):
             raise util.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def setrevmap(self, revmap):
         """set the map of already-converted revisions"""
         pass
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError
 
     def getfile(self, name, rev):
         """Return a pair (data, mode) where data is the file content
         as a string and mode one of '', 'x' or 'l'. rev is the
         identifier returned by a previous call to getchanges().
         Data is None if file is missing/deleted in rev.
         """
         raise NotImplementedError
 
     def getchanges(self, version, full):
         """Returns a tuple of (files, copies, cleanp2).
 
         files is a sorted list of (filename, id) tuples for all files
         changed between version and its first parent returned by
         getcommit(). If full, all files in that revision is returned.
         id is the source revision id of the file.
 
         copies is a dictionary of dest: source
 
         cleanp2 is the set of files filenames that are clean against p2.
         (Files that are clean against p1 are already not in files (unless
         full). This makes it possible to handle p2 clean files similarly.)
         """
         raise NotImplementedError
 
     def getcommit(self, version):
         """Return the commit object for version"""
         raise NotImplementedError
 
     def numcommits(self):
         """Return the number of commits in this source.
 
         If unknown, return None.
         """
         return None
 
     def gettags(self):
         """Return the tags as a dictionary of name: revision
 
         Tag names must be UTF-8 strings.
         """
         raise NotImplementedError
 
     def recode(self, s, encoding=None):
         if not encoding:
             encoding = self.encoding or 'utf-8'
 
         if isinstance(s, unicode):
             return s.encode("utf-8")
         try:
             return s.decode(encoding).encode("utf-8")
         except UnicodeError:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except UnicodeError:
                 return s.decode(encoding, "replace").encode("utf-8")
 
     def getchangedfiles(self, rev, i):
         """Return the files changed by rev compared to parent[i].
 
         i is an index selecting one of the parents of rev.  The return
         value should be the list of files that are different in rev and
         this parent.
 
         If rev has no parents, i is None.
 
         This function is only needed to support --filemap
         """
         raise NotImplementedError
 
     def converted(self, rev, sinkrev):
         '''Notify the source that a revision has been converted.'''
         pass
 
     def hasnativeorder(self):
         """Return true if this source has a meaningful, native revision
         order. For instance, Mercurial revisions are store sequentially
         while there is no such global ordering with Darcs.
         """
         return False
 
     def hasnativeclose(self):
         """Return true if this source has ability to close branch.
         """
         return False
 
     def lookuprev(self, rev):
         """If rev is a meaningful revision reference in source, return
         the referenced identifier in the same format used by getcommit().
         return None otherwise.
         """
         return None
 
     def getbookmarks(self):
         """Return the bookmarks as a dictionary of name: revision
 
         Bookmark names are to be UTF-8 strings.
         """
         return {}
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """revstr is a string that describes a revision in the given
            source control system.  Return true if revstr has correct
            format.
         """
         return True
 
 class converter_sink(object):
     """Conversion sink (target) interface"""
 
     def __init__(self, ui, path):
         """Initialize conversion sink (or raise NoRepo("message")
         exception if path is not a valid repository)
 
         created is a list of paths to remove if a fatal error occurs
         later"""
         self.ui = ui
         self.path = path
         self.created = []
 
     def revmapfile(self):
         """Path to a file that will contain lines
         source_rev_id sink_rev_id
         mapping equivalent revision identifiers for each system."""
         raise NotImplementedError
 
     def authorfile(self):
         """Path to a file that will contain lines
         srcauthor=dstauthor
         mapping equivalent authors identifiers for each system."""
         return None
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         """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.  'files' is a list of (path, version) tuples,
         'copies' is a dictionary mapping destinations to sources,
         'source' is the source repository, and 'revmap' is a mapfile
         of source revisions to converted revisions. Only getfile() and
         lookuprev() should be called on 'source'. 'full' means that 'files'
         is complete and all other files should be removed.
         'cleanp2' is a set of the filenames that are unchanged from p2
         (only in the common merge case where there two parents).
 
         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):
         """Put tags into sink.
 
         tags: {tagname: sink_rev_id, ...} where tagname is an UTF-8 string.
         Return a pair (tag_revision, tag_parent_revision), or (None, None)
         if nothing was changed.
         """
         raise NotImplementedError
 
     def setbranch(self, branch, pbranches):
         """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"""
         pass
 
     def setfilemapmode(self, active):
         """Tell the destination that we're using a filemap
 
         Some converter_sources (svn in particular) can claim that a file
         was changed in a revision, even if there was no change.  This method
         tells the destination that we're using a filemap and that it should
         filter empty revisions.
         """
         pass
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def putbookmarks(self, bookmarks):
         """Put bookmarks into sink.
 
         bookmarks: {bookmarkname: sink_rev_id, ...}
         where bookmarkname is an UTF-8 string.
         """
         pass
 
     def hascommitfrommap(self, rev):
         """Return False if a rev mentioned in a filemap is known to not be
         present."""
         raise NotImplementedError
 
     def hascommitforsplicemap(self, rev):
         """This method is for the special needs for splicemap handling and not
         for general use. Returns True if the sink contains rev, aborts on some
         special cases."""
         raise NotImplementedError
 
 class commandline(object):
     def __init__(self, ui, command):
         self.ui = ui
         self.command = command
 
     def prerun(self):
         pass
 
     def postrun(self):
         pass
 
     def _cmdline(self, cmd, *args, **kwargs):
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.iteritems():
             if len(k) == 1:
                 cmdline.append('-' + k)
             else:
                 cmdline.append('--' + k.replace('_', '-'))
             try:
                 if len(k) == 1:
                     cmdline.append('' + v)
                 else:
                     cmdline[-1] += '=' + v
             except TypeError:
                 pass
         cmdline = [util.shellquote(arg) for arg in cmdline]
         if not self.ui.debugflag:
             cmdline += ['2>', os.devnull]
         cmdline = ' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         def popen(cmdline):
             p = subprocess.Popen(cmdline, shell=True, bufsize=-1,
                     close_fds=util.closefds,
                     stdout=subprocess.PIPE)
             return p
         return self._dorun(popen, cmd, *args, **kwargs)
 
     def _run2(self, cmd, *args, **kwargs):
         return self._dorun(util.popen2, cmd, *args, **kwargs)
 
     def _dorun(self, openfunc, cmd,  *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug('running: %s\n' % (cmdline,))
         self.prerun()
         try:
             return openfunc(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.communicate()[0]
         self.ui.debug(output)
         return output, p.returncode
 
     def runlines(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.stdout.readlines()
         p.wait()
         self.ui.debug(''.join(output))
         return output, p.returncode
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = util.explainexit(status)[0]
             raise util.Abort('%s %s' % (self.command, msg))
 
     def run0(self, cmd, *args, **kwargs):
         output, status = self.run(cmd, *args, **kwargs)
         self.checkexit(status, output)
         return output
 
     def runlines0(self, cmd, *args, **kwargs):
         output, status = self.runlines(cmd, *args, **kwargs)
         self.checkexit(status, ''.join(output))
         return output
 
     @propertycache
     def argmax(self):
         # POSIX requires at least 4096 bytes for ARG_MAX
         argmax = 4096
         try:
             argmax = os.sysconf("SC_ARG_MAX")
         except (AttributeError, ValueError):
             pass
 
         # Windows shells impose their own limits on command line length,
         # down to 2047 bytes for cmd.exe under Windows NT/2k and 2500 bytes
         # for older 4nt.exe. See http://support.microsoft.com/kb/830473 for
         # details about cmd.exe limitations.
 
         # Since ARG_MAX is for command line _and_ environment, lower our limit
         # (and make happy Windows shells while doing this).
         return argmax // 2 - 1
 
     def _limit_arglist(self, arglist, cmd, *args, **kwargs):
         cmdlen = len(self._cmdline(cmd, *args, **kwargs))
         limit = self.argmax - cmdlen
         bytes = 0
         fl = []
         for fn in arglist:
             b = len(fn) + 3
             if bytes + b < limit or len(fl) == 0:
                 fl.append(fn)
                 bytes += b
             else:
                 yield fl
                 fl = [fn]
                 bytes = b
         if fl:
             yield fl
 
     def xargs(self, arglist, cmd, *args, **kwargs):
         for l in self._limit_arglist(arglist, cmd, *args, **kwargs):
             self.run0(cmd, *(list(args) + l), **kwargs)
 
 class mapfile(dict):
     def __init__(self, ui, path):
         super(mapfile, self).__init__()
         self.ui = ui
         self.path = path
         self.fp = None
         self.order = []
         self._read()
 
     def _read(self):
         if not self.path:
             return
         try:
             fp = open(self.path, 'r')
-        except IOError, err:
+        except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for i, line in enumerate(fp):
             line = line.splitlines()[0].rstrip()
             if not line:
                 # Ignore blank lines
                 continue
             try:
                 key, value = line.rsplit(' ', 1)
             except ValueError:
                 raise util.Abort(
                     _('syntax error in %s(%d): key/value pair expected')
                     % (self.path, i + 1))
             if key not in self:
                 self.order.append(key)
             super(mapfile, self).__setitem__(key, value)
         fp.close()
 
     def __setitem__(self, key, value):
         if self.fp is None:
             try:
                 self.fp = open(self.path, 'a')
-            except IOError, err:
+            except IOError as err:
                 raise util.Abort(_('could not open map file %r: %s') %
                                  (self.path, err.strerror))
         self.fp.write('%s %s\n' % (key, value))
         self.fp.flush()
         super(mapfile, self).__setitem__(key, value)
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None
 
 def makedatetimestamp(t):
     """Like util.makedate() but for time t instead of current time"""
     delta = (datetime.datetime.utcfromtimestamp(t) -
              datetime.datetime.fromtimestamp(t))
     tz = delta.days * 86400 + delta.seconds
     return t, tz

hgext/convert/convcmd.py

@@ -1,547 +1,547 b''
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil, shlex
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
-        except (NoRepo, MissingTool), inst:
+        except (NoRepo, MissingTool) as inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
-        except NoRepo, inst:
+        except NoRepo as inst:
             ui.note(_("convert: %s\n") % inst)
-        except MissingTool, inst:
+        except MissingTool as inst:
             raise util.Abort('%s\n' % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.filecount = filecount
         self.retrieved = 0
 
     def getfile(self, file, rev):
         self.retrieved += 1
         self.ui.progress(_('getting files'), self.retrieved,
                          item=file, total=self.filecount)
         return self.source.getfile(file, rev)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.ui.progress(_('getting files'), None)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authormap'):
             self.readauthormap(opts.get('authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = self.parsesplicemap(opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def parsesplicemap(self, path):
         """ check and validate the splicemap format and
             return a child/parents dictionary.
             Format checking has two parts.
             1. generic format which is same across all source types
             2. specific format checking which may be different for
                different source type.  This logic is implemented in
                checkrevformat function in source files like
                hg.py, subversion.py etc.
         """
 
         if not path:
             return {}
         m = {}
         try:
             fp = open(path, 'r')
             for i, line in enumerate(fp):
                 line = line.splitlines()[0].rstrip()
                 if not line:
                     # Ignore blank lines
                     continue
                 # split line
                 lex = shlex.shlex(line, posix=True)
                 lex.whitespace_split = True
                 lex.whitespace += ','
                 line = list(lex)
                 # check number of parents
                 if not (2 <= len(line) <= 3):
                     raise util.Abort(_('syntax error in %s(%d): child parent1'
                                        '[,parent2] expected') % (path, i + 1))
                 for part in line:
                     self.source.checkrevformat(part)
                 child, p1, p2 = line[0], line[1:2], line[2:]
                 if p1 == p2:
                     m[child] = p1
                 else:
                     m[child] = p1 + p2
          # if file does not exist or error reading, exit
         except IOError:
             raise util.Abort(_('splicemap file not found or error reading %s:')
                                % path)
         return m
 
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         numcommits = self.source.numcommits()
         while visit:
             n = visit.pop(0)
             if n in known:
                 continue
             if n in self.map:
                 m = self.map[n]
                 if m == SKIPREV or self.dest.hascommitfrommap(m):
                     continue
             known.add(n)
             self.ui.progress(_('scanning'), len(known), unit=_('revisions'),
                              total=numcommits)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         self.ui.progress(_('scanning'), None)
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in sorted(splicemap):
             if c not in parents:
                 if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(_('splice map revision %s is not being '
                                    'converted, ignoring\n') % c)
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise util.Abort(_('unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = sorted(parents)
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makeclosesorter():
             """Close order sort."""
             keyfn = lambda n: ('close' not in self.commitcache[n].extra,
                                self.commitcache[n].sortkey)
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         elif sortmode == 'closesort':
             picknext = makeclosesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         # If commit.branch is None, this commit is coming from the source
         # repository's default branch and destined for the default branch in the
         # destination repository. For such commits, passing a literal "None"
         # string to branchmap.get() below allows the user to map "None" to an
         # alternate default branch in the destination repository.
         commit.branch = self.branchmap.get(str(commit.branch), commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         full = self.opts.get('full')
         changes = self.source.getchanges(rev, full)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies, cleanp2 = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         if len(pbranches) != 2:
             cleanp2 = set()
         if len(parents) < 3:
             source = progresssource(self.ui, self.source, len(files))
         else:
             # For an octopus merge, we end up traversing the list of
             # changed files N-1 times. This tweak to the number of
             # files makes it so the progress bar doesn't overflow
             # itself.
             source = progresssource(self.ui, self.source,
                                     len(files) * (len(parents) - 1))
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       source, self.map, full, cleanp2)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.ui.progress(_('converting'), i, unit=_('revisions'),
                                  total=len(t))
                 self.copy(c)
             self.ui.progress(_('converting'), None)
 
             tags = self.source.gettags()
             ctags = {}
             for k in tags:
                 v = tags[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     ctags[k] = self.map[v]
 
             if c and ctags:
                 nrev, tagsparent = self.dest.puttags(ctags)
                 if nrev and tagsparent:
                     # write another hash correspondence to override the previous
                     # one so we don't end up with extra tag heads
                     tagsparents = [e for e in self.map.iteritems()
                                    if e[1] == tagsparent]
                     if tagsparents:
                         self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get('authormap'):
         opts['authormap'] = opts.get('authors')
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort', 'closesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     if sortmode:
         sortmode = sortmode[0]
     else:
         sortmode = defaultsort
 
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
     if sortmode == 'closesort' and not srcc.hasnativeclose():
         raise util.Abort(_('--closesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         revmapfile = destc.revmapfile()
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)

hgext/convert/cvs.py

@@ -1,277 +1,277 b''
 # cvs.py: CVS conversion code inspired by hg-cvs-import and git-cvsimport
 #
 #  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, re, socket, errno
 from cStringIO import StringIO
 from mercurial import encoding, util
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
 from common import makedatetimestamp
 import cvsps
 
 class convert_cvs(converter_source):
     def __init__(self, ui, path, rev=None):
         super(convert_cvs, self).__init__(ui, path, rev=rev)
 
         cvs = os.path.join(path, "CVS")
         if not os.path.exists(cvs):
             raise NoRepo(_("%s does not look like a CVS checkout") % path)
 
         checktool('cvs')
 
         self.changeset = None
         self.files = {}
         self.tags = {}
         self.lastbranch = {}
         self.socket = None
         self.cvsroot = open(os.path.join(cvs, "Root")).read()[:-1]
         self.cvsrepo = open(os.path.join(cvs, "Repository")).read()[:-1]
         self.encoding = encoding.encoding
 
         self._connect()
 
     def _parse(self):
         if self.changeset is not None:
             return
         self.changeset = {}
 
         maxrev = 0
         if self.rev:
             # TODO: handle tags
             try:
                 # patchset number?
                 maxrev = int(self.rev)
             except ValueError:
                 raise util.Abort(_('revision %s is not a patchset number')
                                  % self.rev)
 
         d = os.getcwd()
         try:
             os.chdir(self.path)
             id = None
 
             cache = 'update'
             if not self.ui.configbool('convert', 'cvsps.cache', True):
                 cache = None
             db = cvsps.createlog(self.ui, cache=cache)
             db = cvsps.createchangeset(self.ui, db,
                 fuzz=int(self.ui.config('convert', 'cvsps.fuzz', 60)),
                 mergeto=self.ui.config('convert', 'cvsps.mergeto', None),
                 mergefrom=self.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)
                 if self.ui.configbool('convert', 'localtimezone'):
                     cs.date = makedatetimestamp(cs.date[0])
                 date = util.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2')
                 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=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
 
             self.heads = self.lastbranch.values()
         finally:
             os.chdir(d)
 
     def _connect(self):
         root = self.cvsroot
         conntype = None
         user, host = None, None
         cmd = ['cvs', 'server']
 
         self.ui.status(_("connecting to %s\n") % root)
 
         if root.startswith(":pserver:"):
             root = root[9:]
             m = re.match(r'(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?(.*)',
                          root)
             if m:
                 conntype = "pserver"
                 user, passw, serv, port, root = m.groups()
                 if not user:
                     user = "anonymous"
                 if not port:
                     port = 2401
                 else:
                     port = int(port)
                 format0 = ":pserver:%s@%s:%s" % (user, serv, root)
                 format1 = ":pserver:%s@%s:%d%s" % (user, serv, port, root)
 
                 if not passw:
                     passw = "A"
                     cvspass = os.path.expanduser("~/.cvspass")
                     try:
                         pf = open(cvspass)
                         for line in pf.read().splitlines():
                             part1, part2 = line.split(' ', 1)
                             # /1 :pserver:[e-mail]:2401/cvsroot/foo
                             # Ah<Z
                             if part1 == '/1':
                                 part1, part2 = part2.split(' ', 1)
                                 format = format1
                             # :pserver:[e-mail]:/cvsroot/foo Ah<Z
                             else:
                                 format = format0
                             if part1 == format:
                                 passw = part2
                                 break
                         pf.close()
-                    except IOError, inst:
+                    except IOError as inst:
                         if inst.errno != errno.ENOENT:
                             if not getattr(inst, 'filename', None):
                                 inst.filename = cvspass
                             raise
 
                 sck = socket.socket()
                 sck.connect((serv, port))
                 sck.send("\n".join(["BEGIN AUTH REQUEST", root, user, passw,
                                     "END AUTH REQUEST", ""]))
                 if sck.recv(128) != "I LOVE YOU\n":
                     raise util.Abort(_("CVS pserver authentication failed"))
 
                 self.writep = self.readp = sck.makefile('r+')
 
         if not conntype and root.startswith(":local:"):
             conntype = "local"
             root = root[7:]
 
         if not conntype:
             # :ext:user@host/home/user/path/to/cvsroot
             if root.startswith(":ext:"):
                 root = root[5:]
             m = re.match(r'(?:([^@:/]+)@)?([^:/]+):?(.*)', root)
             # Do not take Windows path "c:\foo\bar" for a connection strings
             if os.path.isdir(root) or not m:
                 conntype = "local"
             else:
                 conntype = "rsh"
                 user, host, root = m.group(1), m.group(2), m.group(3)
 
         if conntype != "pserver":
             if conntype == "rsh":
                 rsh = os.environ.get("CVS_RSH") or "ssh"
                 if user:
                     cmd = [rsh, '-l', user, host] + cmd
                 else:
                     cmd = [rsh, host] + cmd
 
             # popen2 does not support argument lists under Windows
             cmd = [util.shellquote(arg) for arg in cmd]
             cmd = util.quotecommand(' '.join(cmd))
             self.writep, self.readp = util.popen2(cmd)
 
         self.realroot = root
 
         self.writep.write("Root %s\n" % root)
         self.writep.write("Valid-responses ok error Valid-requests Mode"
                           " M Mbinary E Checked-in Created Updated"
                           " Merged Removed\n")
         self.writep.write("valid-requests\n")
         self.writep.flush()
         r = self.readp.readline()
         if not r.startswith("Valid-requests"):
             raise util.Abort(_('unexpected response from CVS server '
                                '(expected "Valid-requests", but got %r)')
                              % r)
         if "UseUnchanged" in r:
             self.writep.write("UseUnchanged\n")
             self.writep.flush()
             r = self.readp.readline()
 
     def getheads(self):
         self._parse()
         return self.heads
 
     def getfile(self, name, rev):
 
         def chunkedread(fp, count):
             # file-objects returned by socket.makefile() do not handle
             # large read() requests very well.
             chunksize = 65536
             output = StringIO()
             while count > 0:
                 data = fp.read(min(count, chunksize))
                 if not data:
                     raise util.Abort(_("%d bytes missing from remote file")
                                      % count)
                 count -= len(data)
                 output.write(data)
             return output.getvalue()
 
         self._parse()
         if rev.endswith("(DEAD)"):
             return None, None
 
         args = ("-N -P -kk -r %s --" % rev).split()
         args.append(self.cvsrepo + '/' + name)
         for x in args:
             self.writep.write("Argument %s\n" % x)
         self.writep.write("Directory .\n%s\nco\n" % self.realroot)
         self.writep.flush()
 
         data = ""
         mode = None
         while True:
             line = self.readp.readline()
             if line.startswith("Created ") or line.startswith("Updated "):
                 self.readp.readline() # path
                 self.readp.readline() # entries
                 mode = self.readp.readline()[:-1]
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             elif line.startswith(" "):
                 data += line[1:]
             elif line.startswith("M "):
                 pass
             elif line.startswith("Mbinary "):
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             else:
                 if line == "ok\n":
                     if mode is None:
                         raise util.Abort(_('malformed response from CVS'))
                     return (data, "x" in mode and "x" or "")
                 elif line.startswith("E "):
                     self.ui.warn(_("cvs server: %s\n") % line[2:])
                 elif line.startswith("Remove"):
                     self.readp.readline()
                 else:
                     raise util.Abort(_("unknown CVS response: %s") % line)
 
     def getchanges(self, rev, full):
         if full:
             raise util.Abort(_("convert from cvs do not support --full"))
         self._parse()
         return sorted(self.files[rev].iteritems()), {}, set()
 
     def getcommit(self, rev):
         self._parse()
         return self.changeset[rev]
 
     def gettags(self):
         self._parse()
         return self.tags
 
     def getchangedfiles(self, rev, i):
         self._parse()
         return sorted(self.files[rev])

hgext/convert/cvsps.py

@@ -1,904 +1,904 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.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
         .commitid  - CVS commitid or None
         .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) or None
         .branchpoints - the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 class logerror(Exception):
     pass
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath('/foo/bar')
     '/foo/bar'
     >>> getrepopath('c:/foo/bar')
     '/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')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath('user@server/path/to/repository')
     '/path/to/repository'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # CVSpath is splitted into parts and then position of the first occurrence
     # of the '/' char after the '@' is located. The solution is the rest of the
     # string after that '/' sign including it
 
     parts = cvspath.split(':')
     atposition = parts[-1].find('@')
     start = 0
 
     if atposition != -1:
         start = atposition
 
     repopath = parts[-1][parts[-1].find('/', start):]
     return repopath
 
 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+.+;)?$')
     re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
                        r'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
                        r'(\s+commitid:\s+([^;]+);)?'
                        r'(.*mergepoint:\s+([^;]+);)?')
     re_70 = re.compile('branches: (.+);$')
 
     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
         # alphanumeric characters, 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))
             for e in oldlog:
                 if not (util.safehasattr(e, 'branchpoints') and
                         util.safehasattr(e, 'commitid') and
                         util.safehasattr(e, 'mergepoint')):
                     ui.status(_('ignoring old cache\n'))
                     oldlog = []
                     break
 
             ui.note(_('cache has %d log entries\n') % len(oldlog))
-        except Exception, e:
+        except Exception as 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,
                          commitid=None,
                          mergepoint=None,
                          branchpoints=set())
 
             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): # cvs 1.12 commitid
                 e.commitid = match.group(8)
 
             if match.group(9): # cvsnt mergepoint
                 myrev = match.group(10).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]
 
             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):
                 cpeek = peek
                 if cpeek.endswith('\n'):
                     cpeek = cpeek[:-1]
                 if re_50.match(cpeek):
                     state = 5
                     store = True
                 else:
                     e.comment.append(line)
             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
         .commitid  - CVS commitid or None
         .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 or None
         .branchpoints- the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.id = None
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_('creating changesets\n'))
 
     # try to order commitids by date
     mindate = {}
     for e in log:
         if e.commitid:
             mindate[e.commitid] = min(e.date, mindate.get(e.commitid))
 
     # Merge changesets
     log.sort(key=lambda x: (mindate.get(x.commitid), x.commitid, x.comment,
                             x.author, x.branch, x.date, x.branchpoints))
 
     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.branchpoints == c.branchpoints and
                 (# cvs commitids
                  (e.commitid is not None and e.commitid == c.commitid) or
                  (# no commitids, use fuzzy commit detection
                   (e.commitid is None or c.commitid is None) 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=[], mergepoint=e.mergepoint,
                           branchpoints=e.branchpoints, commitid=e.commitid)
             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
 
     def entitycompare(l, r):
         'Mimic cvsps sorting order'
         l = l.file.split('/')
         r = r.file.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
 
     for c in changesets:
         c.entries.sort(entitycompare)
 
     # Sort changesets by date
 
     odd = set()
     def cscmp(l, r, odd=odd):
         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:
                 if d:
                     odd.add((l, r))
                 d = -1
                 break
         # By this point, the changesets are sufficiently compared that
         # we don't really care about ordering. However, this leaves
         # some race conditions in the tests, so we compare on the
         # number of files modified, the files contained in each
         # changeset, and the branchpoints in the change to ensure test
         # output remains stable.
 
         # recommended replacement for cmp from
         # https://docs.python.org/3.0/whatsnew/3.0.html
         c = lambda x, y: (x > y) - (x < y)
         # Sort bigger changes first.
         if not d:
             d = c(len(l.entries), len(r.entries))
         # Try sorting by filename in the change.
         if not d:
             d = c([e.file for e in l.entries], [e.file for e in r.entries])
         # Try and put changes without a branch point before ones with
         # a branch point.
         if not d:
             d = c(len(l.branchpoints), len(r.branchpoints))
         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:
                 if m.groups():
                     m = m.group(1)
                     if m == 'HEAD':
                         m = None
                 else:
                     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
 
     if odd:
         for l, r in odd:
             if l.id is not None and r.id is not None:
                 ui.warn(_('changeset %d is both before and after %d\n')
                         % (l.id, r.id))
 
     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:
+    except logerror as 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)')))
             if cs.branchpoints:
                 ui.write(('Branchpoints: %s \n') %
                          ', '.join(sorted(cs.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/darcs.py

@@ -1,208 +1,208 b''
 # darcs.py - darcs support for the convert extension
 #
 #  Copyright 2007-2009 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.
 
 from common import NoRepo, checktool, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
 import os, shutil, tempfile, re, errno
 
 # The naming drift of ElementTree is fun!
 
 try:
     from xml.etree.cElementTree import ElementTree, XMLParser
 except ImportError:
     try:
         from xml.etree.ElementTree import ElementTree, XMLParser
     except ImportError:
         try:
             from elementtree.cElementTree import ElementTree, XMLParser
         except ImportError:
             try:
                 from elementtree.ElementTree import ElementTree, XMLParser
             except ImportError:
                 pass
 
 class darcs_source(converter_source, commandline):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev=rev)
         commandline.__init__(self, ui, 'darcs')
 
         # check for _darcs, ElementTree so that we can easily skip
         # test-convert-darcs if ElementTree is not around
         if not os.path.exists(os.path.join(path, '_darcs')):
             raise NoRepo(_("%s does not look like a darcs repository") % path)
 
         checktool('darcs')
         version = self.run0('--version').splitlines()[0].strip()
         if version < '2.1':
             raise util.Abort(_('darcs version 2.1 or newer needed (found %r)') %
                              version)
 
         if "ElementTree" not in globals():
             raise util.Abort(_("Python ElementTree module is not available"))
 
         self.path = os.path.realpath(path)
 
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
 
         # Check darcs repository format
         format = self.format()
         if format:
             if format in ('darcs-1.0', 'hashed'):
                 raise NoRepo(_("%s repository format is unsupported, "
                                "please upgrade") % format)
         else:
             self.ui.warn(_('failed to detect repository format!'))
 
     def before(self):
         self.tmppath = tempfile.mkdtemp(
             prefix='convert-' + os.path.basename(self.path) + '-')
         output, status = self.run('init', repodir=self.tmppath)
         self.checkexit(status)
 
         tree = self.xml('changes', xml_output=True, summary=True,
                         repodir=self.path)
         tagname = None
         child = None
         for elt in tree.findall('patch'):
             node = elt.get('hash')
             name = elt.findtext('name', '')
             if name.startswith('TAG '):
                 tagname = name[4:].strip()
             elif tagname is not None:
                 self.tags[tagname] = node
                 tagname = None
             self.changes[node] = elt
             self.parents[child] = [node]
             child = node
         self.parents[child] = []
 
     def after(self):
         self.ui.debug('cleaning up %s\n' % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def recode(self, s, encoding=None):
         if isinstance(s, unicode):
             # XMLParser returns unicode objects for anything it can't
             # encode into ASCII. We convert them back to str to get
             # recode's normal conversion behavior.
             s = s.encode('latin-1')
         return super(darcs_source, self).recode(s, encoding)
 
     def xml(self, cmd, **kwargs):
         # NOTE: darcs is currently encoding agnostic and will print
         # patch metadata byte-for-byte, even in the XML changelog.
         etree = ElementTree()
         # While we are decoding the XML as latin-1 to be as liberal as
         # possible, etree will still raise an exception if any
         # non-printable characters are in the XML changelog.
         parser = XMLParser(encoding='latin-1')
         p = self._run(cmd, **kwargs)
         etree.parse(p.stdout, parser=parser)
         p.wait()
         self.checkexit(p.returncode)
         return etree.getroot()
 
     def format(self):
         output, status = self.run('show', 'repo', no_files=True,
                                   repodir=self.path)
         self.checkexit(status)
         m = re.search(r'^\s*Format:\s*(.*)$', output, re.MULTILINE)
         if not m:
             return None
         return ','.join(sorted(f.strip() for f in m.group(1).split(',')))
 
     def manifest(self):
         man = []
         output, status = self.run('show', 'files', no_directories=True,
                                   repodir=self.tmppath)
         self.checkexit(status)
         for line in output.split('\n'):
             path = line[2:]
             if path:
                 man.append(path)
         return man
 
     def getheads(self):
         return self.parents[None]
 
     def getcommit(self, rev):
         elt = self.changes[rev]
         date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y')
         desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
         # etree can return unicode objects for name, comment, and author,
         # so recode() is used to ensure str objects are emitted.
         return commit(author=self.recode(elt.get('author')),
                       date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=self.recode(desc).strip(),
                       parents=self.parents[rev])
 
     def pull(self, rev):
         output, status = self.run('pull', self.path, all=True,
                                   match='hash %s' % rev,
                                   no_test=True, no_posthook=True,
                                   external_merge='/bin/false',
                                   repodir=self.tmppath)
         if status:
             if output.find('We have conflicts in') == -1:
                 self.checkexit(status, output)
             output, status = self.run('revert', all=True, repodir=self.tmppath)
             self.checkexit(status, output)
 
     def getchanges(self, rev, full):
         if full:
             raise util.Abort(_("convert from darcs do not support --full"))
         copies = {}
         changes = []
         man = None
         for elt in self.changes[rev].find('summary').getchildren():
             if elt.tag in ('add_directory', 'remove_directory'):
                 continue
             if elt.tag == 'move':
                 if man is None:
                     man = self.manifest()
                 source, dest = elt.get('from'), elt.get('to')
                 if source in man:
                     # File move
                     changes.append((source, rev))
                     changes.append((dest, rev))
                     copies[dest] = source
                 else:
                     # Directory move, deduce file moves from manifest
                     source = source + '/'
                     for f in man:
                         if not f.startswith(source):
                             continue
                         fdest = dest + '/' + f[len(source):]
                         changes.append((f, rev))
                         changes.append((fdest, rev))
                         copies[fdest] = f
             else:
                 changes.append((elt.text.strip(), rev))
         self.pull(rev)
         self.lastrev = rev
         return sorted(changes), copies, set()
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
         path = os.path.join(self.tmppath, name)
         try:
             data = util.readfile(path)
             mode = os.lstat(path).st_mode
-        except IOError, inst:
+        except IOError as inst:
             if inst.errno == errno.ENOENT:
                 return None, None
             raise
         mode = (mode & 0o111) and 'x' or ''
         return data, mode
 
     def gettags(self):
         return self.tags

hgext/convert/hg.py

@@ -1,561 +1,561 b''
 # hg.py - hg backend for 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.
 
 # Notes for hg->hg conversion:
 #
 # * Old versions of Mercurial didn't trim the whitespace from the ends
 #   of commit messages, but new versions do.  Changesets created by
 #   those older versions, then converted, may thus have different
 #   hashes for changesets that are otherwise identical.
 #
 # * Using "--config convert.hg.saverev=true" will make the source
 #   identifier to be stored in the converted revision. This will cause
 #   the converted revision to have a different identity than the
 #   source.
 
 
 import os, time, cStringIO
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import hg, util, context, bookmarks, error, scmutil, exchange
 from mercurial import phases
 
 from common import NoRepo, commit, converter_source, converter_sink, mapfile
 
 import re
 sha1re = re.compile(r'\b[0-9a-f]{12,40}\b')
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
-            except error.RepoError, err:
+            except error.RepoError as err:
                 ui.traceback()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
                 raise NoRepo(_("could not create hg repository %s as sink")
                              % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
         self.subrevmaps = {}
 
     def before(self):
         self.ui.debug('run hg sink pre-conversion action\n')
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
 
     def after(self):
         self.ui.debug('run hg sink post-conversion action\n')
         if self.lock:
             self.lock.release()
         if self.wlock:
             self.wlock.release()
 
     def revmapfile(self):
         return self.repo.join("shamap")
 
     def authorfile(self):
         return self.repo.join("authormap")
 
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         if pbranches:
             pbranch = pbranches[0][1]
         else:
             pbranch = 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except Exception:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except Exception:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in sorted(missings.iteritems()):
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.peer(self.ui, {}, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 exchange.pull(self.repo, prepo,
                               [prepo.lookup(h) for h in heads])
             self.before()
 
     def _rewritetags(self, source, revmap, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
             revid = revmap.get(source.lookuprev(s[0]))
             if not revid:
                 if s[0] == hex(nullid):
                     revid = s[0]
                 else:
                     continue
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
     def _rewritesubstate(self, source, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
 
             revid = s[0]
             subpath = s[1]
             if revid != hex(nullid):
                 revmap = self.subrevmaps.get(subpath)
                 if revmap is None:
                     revmap = mapfile(self.ui,
                                      self.repo.wjoin(subpath, '.hg/shamap'))
                     self.subrevmaps[subpath] = revmap
 
                     # It is reasonable that one or more of the subrepos don't
                     # need to be converted, in which case they can be cloned
                     # into place instead of converted.  Therefore, only warn
                     # once.
                     msg = _('no ".hgsubstate" updates will be made for "%s"\n')
                     if len(revmap) == 0:
                         sub = self.repo.wvfs.reljoin(subpath, '.hg')
 
                         if self.repo.wvfs.exists(sub):
                             self.ui.warn(msg % subpath)
 
                 newid = revmap.get(revid)
                 if not newid:
                     if len(revmap) > 0:
                         self.ui.warn(_("%s is missing from %s/.hg/shamap\n") %
                                      (revid, subpath))
                 else:
                     revid = newid
 
             fp.write('%s %s\n' % (revid, subpath))
 
         return fp.getvalue()
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         files = dict(files)
 
         def getfilectx(repo, memctx, f):
             if p2ctx and f in cleanp2 and f not in copies:
                 self.ui.debug('reusing %s from p2\n' % f)
                 return p2ctx[f]
             try:
                 v = files[f]
             except KeyError:
                 return None
             data, mode = source.getfile(f, v)
             if data is None:
                 return None
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             if f == '.hgsubstate':
                 data = self._rewritesubstate(source, data)
             return context.memfilectx(self.repo, f, data, 'l' in mode,
                                       'x' in mode, copies.get(f))
 
         pl = []
         for p in parents:
             if p not in pl:
                 pl.append(p)
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2:
             parents.append(nullid)
         if len(parents) < 2:
             parents.append(nullid)
         p2 = parents.pop(0)
 
         text = commit.desc
 
         sha1s = re.findall(sha1re, text)
         for sha1 in sha1s:
             oldrev = source.lookuprev(sha1)
             newrev = revmap.get(oldrev)
             if newrev is not None:
                 text = text.replace(sha1, newrev[:len(sha1)])
 
         extra = commit.extra.copy()
 
         for label in ('source', 'transplant_source', 'rebase_source',
                       'intermediate-source'):
             node = extra.get(label)
 
             if node is None:
                 continue
 
             # Only transplant stores its reference in binary
             if label == 'transplant_source':
                 node = hex(node)
 
             newrev = revmap.get(node)
             if newrev is not None:
                 if label == 'transplant_source':
                     newrev = bin(newrev)
 
                 extra[label] = newrev
 
         if self.branchnames and commit.branch:
             extra['branch'] = commit.branch
         if commit.rev and commit.saverev:
             extra['convert_revision'] = commit.rev
 
         while parents:
             p1 = p2
             p2 = parents.pop(0)
             p2ctx = None
             if p2 != nullid:
                 p2ctx = self.repo[p2]
             fileset = set(files)
             if full:
                 fileset.update(self.repo[p1])
                 fileset.update(self.repo[p2])
             ctx = context.memctx(self.repo, (p1, p2), text, fileset,
                                  getfilectx, commit.author, commit.date, extra)
 
             # We won't know if the conversion changes the node until after the
             # commit, so copy the source's phase for now.
             self.repo.ui.setconfig('phases', 'new-commit',
                                    phases.phasenames[commit.phase], 'convert')
 
             tr = self.repo.transaction("convert")
 
             try:
                 node = hex(self.repo.commitctx(ctx))
 
                 # If the node value has changed, but the phase is lower than
                 # draft, set it back to draft since it hasn't been exposed
                 # anywhere.
                 if commit.rev != node:
                     ctx = self.repo[node]
                     if ctx.phase() < phases.draft:
                         phases.retractboundary(self.repo, tr, phases.draft,
                                                [ctx.node()])
                 tr.close()
             finally:
                 tr.release()
 
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             closed = 'close' in commit.extra
             if not closed and not man.cmp(m1node, man.revision(mnode)):
                 self.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback(force=True)
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         oldlines = set()
         for branch, heads in self.repo.branchmap().iteritems():
             for h in heads:
                 if '.hgtags' in self.repo[h]:
                     oldlines.update(
                         set(self.repo[h]['.hgtags'].data().splitlines(True)))
         oldlines = sorted(list(oldlines))
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
             return None, None
 
         # if the old and new tags match, then there is nothing to update
         oldtags = set()
         newtags = set()
         for line in oldlines:
             s = line.strip().split(' ', 1)
             if len(s) != 2:
                 continue
             oldtags.add(s[1])
         for line in newlines:
             s = line.strip().split(' ', 1)
             if len(s) != 2:
                 continue
             if s[1] not in oldtags:
                 newtags.add(s[1].strip())
 
         if not newtags:
             return None, None
 
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(repo, 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()), hex(tagparent)
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
     def putbookmarks(self, updatedbookmark):
         if not len(updatedbookmark):
             return
 
         self.ui.status(_("updating bookmarks\n"))
         destmarks = self.repo._bookmarks
         for bookmark in updatedbookmark:
             destmarks[bookmark] = bin(updatedbookmark[bookmark])
         destmarks.write()
 
     def hascommitfrommap(self, rev):
         # the exact semantics of clonebranches is unclear so we can't say no
         return rev in self.repo or self.clonebranches
 
     def hascommitforsplicemap(self, rev):
         if rev not in self.repo and self.clonebranches:
             raise util.Abort(_('revision %s not found in destination '
                                'repository (lookups with clonebranches=true '
                                'are not implemented)') % rev)
         return rev in self.repo
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
         self.ignoreerrors = ui.configbool('convert', 'hg.ignoreerrors', False)
         self.ignored = set()
         self.saverev = ui.configbool('convert', 'hg.saverev', False)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise error.RepoError
         except error.RepoError:
             ui.traceback()
             raise NoRepo(_("%s is not a local Mercurial repository") % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None, None
         self.convertfp = None
         # Restrict converted revisions to startrev descendants
         startnode = ui.config('convert', 'hg.startrev')
         hgrevs = ui.config('convert', 'hg.revs')
         if hgrevs is None:
             if startnode is not None:
                 try:
                     startnode = self.repo.lookup(startnode)
                 except error.RepoError:
                     raise util.Abort(_('%s is not a valid start revision')
                                      % startnode)
                 startrev = self.repo.changelog.rev(startnode)
                 children = {startnode: 1}
                 for r in self.repo.changelog.descendants([startrev]):
                     children[self.repo.changelog.node(r)] = 1
                 self.keep = children.__contains__
             else:
                 self.keep = util.always
             if rev:
                 self._heads = [self.repo[rev].node()]
             else:
                 self._heads = self.repo.heads()
         else:
             if rev or startnode is not None:
                 raise util.Abort(_('hg.revs cannot be combined with '
                                    'hg.startrev or --rev'))
             nodes = set()
             parents = set()
             for r in scmutil.revrange(self.repo, [hgrevs]):
                 ctx = self.repo[r]
                 nodes.add(ctx.node())
                 parents.update(p.node() for p in ctx.parents())
             self.keep = nodes.__contains__
             self._heads = nodes - parents
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def parents(self, ctx):
         return [p for p in ctx.parents() if p and self.keep(p.node())]
 
     def getheads(self):
         return [hex(h) for h in self._heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             fctx = self.changectx(rev)[name]
             return fctx.data(), fctx.flags()
         except error.LookupError:
             return None, None
 
     def getchanges(self, rev, full):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if full or not parents:
             files = copyfiles = ctx.manifest()
         if parents:
             if self._changescache[0] == rev:
                 m, a, r = self._changescache[1]
             else:
                 m, a, r = self.repo.status(parents[0].node(), ctx.node())[:3]
             if not full:
                 files = m + a + r
             copyfiles = m + a
         # getcopies() is also run for roots and before filtering so missing
         # revlogs are detected early
         copies = self.getcopies(ctx, parents, copyfiles)
         cleanp2 = set()
         if len(parents) == 2:
             cleanp2.update(self.repo.status(parents[1].node(), ctx.node(),
                                             clean=True).clean)
         changes = [(f, rev) for f in files if f not in self.ignored]
         changes.sort()
         return changes, copies, cleanp2
 
     def getcopies(self, ctx, parents, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
                 copysource, _copynode = ctx.filectx(name).renamed()
                 if copysource in self.ignored:
                     continue
                 # Ignore copy sources not in parent revisions
                 found = False
                 for p in parents:
                     if copysource in p:
                         found = True
                         break
                 if not found:
                     continue
                 copies[name] = copysource
             except TypeError:
                 pass
-            except error.LookupError, e:
+            except error.LookupError as e:
                 if not self.ignoreerrors:
                     raise
                 self.ignored.add(name)
                 self.ui.warn(_('ignoring: %s\n') % e)
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [p.hex() for p in self.parents(ctx)]
         crev = rev
 
         return commit(author=ctx.user(),
                       date=util.datestr(ctx.date(), '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev(), saverev=self.saverev,
                       phase=ctx.phase())
 
     def gettags(self):
         # This will get written to .hgtags, filter non global tags out.
         tags = [t for t in self.repo.tagslist()
                 if self.repo.tagtype(t[0]) == 'global']
         return dict([(name, hex(node)) for name, node in tags
                      if self.keep(node)])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents and i is None:
             i = 0
             changes = [], ctx.manifest().keys(), []
         else:
             i = i or 0
             changes = self.repo.status(parents[i].node(), ctx.node())[:3]
         changes = [[f for f in l if f not in self.ignored] for l in changes]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(self.repo.join('shamap'), 'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()
 
     def before(self):
         self.ui.debug('run hg source pre-conversion action\n')
 
     def after(self):
         self.ui.debug('run hg source post-conversion action\n')
 
     def hasnativeorder(self):
         return True
 
     def hasnativeclose(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except (error.RepoError, error.LookupError):
             return None
 
     def getbookmarks(self):
         return bookmarks.listbookmarks(self.repo)
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ Mercurial, revision string is a 40 byte hex """
         self.checkhexformat(revstr, mapname)

hgext/convert/subversion.py

@@ -1,1329 +1,1330 b''
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 
 import os, re, sys, tempfile, urllib, urllib2
 import xml.dom.minidom
 import cPickle as pickle
 
 from mercurial import strutil, scmutil, util, encoding
 from mercurial.i18n import _
 
 propertycache = util.propertycache
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 from cStringIO import StringIO
 
 from common import NoRepo, MissingTool, commit, encodeargs, decodeargs
 from common import commandline, converter_source, converter_sink, mapfile
 from common import makedatetimestamp
 
 try:
     from svn.core import SubversionException, Pool
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     import transport
     import warnings
     warnings.filterwarnings('ignore',
             module='svn.core',
             category=DeprecationWarning)
 
 except ImportError:
     svn = None
 
 class SvnPathNotFound(Exception):
     pass
 
 def revsplit(rev):
     """Parse a revision string and return (uuid, path, revnum).
     >>> revsplit('svn:a2147622-4a9f-4db4-a8d3-13562ff547b2'
     ...          '/proj%20B/mytrunk/mytrunk@1')
     ('a2147622-4a9f-4db4-a8d3-13562ff547b2', '/proj%20B/mytrunk/mytrunk', 1)
     >>> revsplit('svn:8af66a51-67f5-4354-b62c-98d67cc7be1d@1')
     ('', '', 1)
     >>> revsplit('@7')
     ('', '', 7)
     >>> revsplit('7')
     ('', '', 0)
     >>> revsplit('bad')
     ('', '', 0)
     """
     parts = rev.rsplit('@', 1)
     revnum = 0
     if len(parts) > 1:
         revnum = int(parts[1])
     parts = parts[0].split('/', 1)
     uuid = ''
     mod = ''
     if len(parts) > 1 and parts[0].startswith('svn:'):
         uuid = parts[0][4:]
         mod = '/' + parts[1]
     return uuid, mod, revnum
 
 def quote(s):
     # As of svn 1.7, many svn calls expect "canonical" paths. In
     # theory, we should call svn.core.*canonicalize() on all paths
     # before passing them to the API.  Instead, we assume the base url
     # is canonical and copy the behaviour of svn URL encoding function
     # so we can extend it safely with new components. The "safe"
     # characters were taken from the "svn_uri__char_validity" table in
     # libsvn_subr/path.c.
     return urllib.quote(s, "!$&'()*+,-./:=@_~")
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except SubversionException:
         # svn.client.url_from_path() fails with local repositories
         pass
     if os.path.isdir(path):
         path = os.path.normpath(os.path.abspath(path))
         if os.name == 'nt':
             path = '/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
         path = encoding.tolocal(path)
         path = 'file://%s' % quote(path)
     return svn.core.svn_path_canonicalize(path)
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         paths = {}
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 paths[k] = changedpath(v)
         pickle.dump((paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except IOError:
         # Caller may interrupt the iteration
         pickle.dump(None, fp, protocol)
-    except Exception, inst:
+    except Exception as inst:
         pickle.dump(str(inst), fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.close()
     # With large history, cleanup process goes crazy and suddenly
     # consumes *huge* amount of memory. The output file being closed,
     # there is no need for clean termination.
     os._exit(0)
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     if svn is None:
         raise util.Abort(_('debugsvnlog could not load Subversion python '
                            'bindings'))
 
     util.setbinary(sys.stdin)
     util.setbinary(sys.stdout)
     args = decodeargs(sys.stdin.read())
     get_log_child(sys.stdout, *args)
 
 class logstream(object):
     """Interruptible revision log iterator."""
     def __init__(self, stdout):
         self._stdout = stdout
 
     def __iter__(self):
         while True:
             try:
                 entry = pickle.load(self._stdout)
             except EOFError:
                 raise util.Abort(_('Mercurial failed to run itself, check'
                                    ' hg executable is in PATH'))
             try:
                 orig_paths, revnum, author, date, message = entry
             except (TypeError, ValueError):
                 if entry is None:
                     break
                 raise util.Abort(_("log stream exception '%s'") % entry)
             yield entry
 
     def close(self):
         if self._stdout:
             self._stdout.close()
             self._stdout = None
 
 class directlogstream(list):
     """Direct revision log iterator.
     This can be used for debugging and development but it will probably leak
     memory and is not suitable for real conversions."""
     def __init__(self, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
 
         def receiver(orig_paths, revnum, author, date, message, pool):
             paths = {}
             if orig_paths is not None:
                 for k, v in orig_paths.iteritems():
                     paths[k] = changedpath(v)
             self.append((paths, revnum, author, date, message))
 
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
 
     def close(self):
         pass
 
 # Check to see if the given path is a local Subversion repo. Verify this by
 # looking for several svn-specific files and directories in the given
 # directory.
 def filecheck(ui, path, proto):
     for x in ('locks', 'hooks', 'format', 'db'):
         if not os.path.exists(os.path.join(path, x)):
             return False
     return True
 
 # Check to see if a given path is the root of an svn repo over http. We verify
 # this by requesting a version-controlled URL we know can't exist and looking
 # for the svn-specific "not found" XML.
 def httpcheck(ui, path, proto):
     try:
         opener = urllib2.build_opener()
         rsp = opener.open('%s://%s/!svn/ver/0/.svn' % (proto, path))
         data = rsp.read()
-    except urllib2.HTTPError, inst:
+    except urllib2.HTTPError as inst:
         if inst.code != 404:
             # Except for 404 we cannot know for sure this is not an svn repo
             ui.warn(_('svn: cannot probe remote repository, assume it could '
                       'be a subversion repository. Use --source-type if you '
                       'know better.\n'))
             return True
         data = inst.fp.read()
     except Exception:
         # Could be urllib2.URLError if the URL is invalid or anything else.
         return False
     return '<m:human-readable errcode="160013">' in data
 
 protomap = {'http': httpcheck,
             'https': httpcheck,
             'file': filecheck,
             }
 def issvnurl(ui, url):
     try:
         proto, path = url.split('://', 1)
         if proto == 'file':
             if (os.name == 'nt' and path[:1] == '/' and path[1:2].isalpha()
                 and path[2:6].lower() == '%3a/'):
                 path = path[:2] + ':/' + path[6:]
             path = urllib.url2pathname(path)
     except ValueError:
         proto = 'file'
         path = os.path.abspath(url)
     if proto == 'file':
         path = util.pconvert(path)
     check = protomap.get(proto, lambda *args: False)
     while '/' in path:
         if check(ui, path, proto):
             return True
         path = path.rsplit('/', 1)[0]
     return False
 
 # SVN conversion code stolen from bzr-svn and tailor
 #
 # Subversion looks like a versioned filesystem, branches structures
 # are defined by conventions and not enforced by the tool. First,
 # we define the potential branches (modules) as "trunk" and "branches"
 # children directories. Revisions are then identified by their
 # module and revision number (and a repository identifier).
 #
 # The revision graph is really a tree (or a forest). By default, a
 # revision parent is the previous revision in the same module. If the
 # module directory is copied/moved from another module then the
 # revision is the module root and its parent the source revision in
 # the parent module. A revision has at most one parent.
 #
 class svn_source(converter_source):
     def __init__(self, ui, url, rev=None):
         super(svn_source, self).__init__(ui, url, rev=rev)
 
         if not (url.startswith('svn://') or url.startswith('svn+ssh://') or
                 (os.path.exists(url) and
                  os.path.exists(os.path.join(url, '.svn'))) or
                 issvnurl(ui, url)):
             raise NoRepo(_("%s does not look like a Subversion repository")
                          % url)
         if svn is None:
             raise MissingTool(_('could not load Subversion python bindings'))
 
         try:
             version = svn.core.SVN_VER_MAJOR, svn.core.SVN_VER_MINOR
             if version < (1, 4):
                 raise MissingTool(_('Subversion python bindings %d.%d found, '
                                     '1.4 or later required') % version)
         except AttributeError:
             raise MissingTool(_('Subversion python bindings are too old, 1.4 '
                                 'or later required'))
 
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at + 1:])
                 url = url[:at]
         except ValueError:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.baseurl = svn.ra.get_repos_root(self.ra)
             # Module is either empty or a repository path starting with
             # a slash and not ending with a slash.
             self.module = urllib.unquote(self.url[len(self.baseurl):])
             self.prevmodule = None
             self.rootmodule = self.module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra)
         except SubversionException:
             ui.traceback()
             svnversion = '%d.%d.%d' % (svn.core.SVN_VER_MAJOR,
                                        svn.core.SVN_VER_MINOR,
                                        svn.core.SVN_VER_MICRO)
             raise NoRepo(_("%s does not look like a Subversion repository "
                            "to libsvn version %s")
                          % (self.url, svnversion))
 
         if rev:
             try:
                 latest = int(rev)
             except ValueError:
                 raise util.Abort(_('svn: revision %s is not an integer') % rev)
 
         self.trunkname = self.ui.config('convert', 'svn.trunk',
                                         'trunk').strip('/')
         self.startrev = self.ui.config('convert', 'svn.startrev', default=0)
         try:
             self.startrev = int(self.startrev)
             if self.startrev < 0:
                 self.startrev = 0
         except ValueError:
             raise util.Abort(_('svn: start revision %s is not an integer')
                              % self.startrev)
 
         try:
             self.head = self.latest(self.module, latest)
         except SvnPathNotFound:
             self.head = None
         if not self.head:
             raise util.Abort(_('no revision found in module %s')
                              % self.module)
         self.last_changed = self.revnum(self.head)
 
         self._changescache = (None, None)
 
         if os.path.exists(os.path.join(url, '.svn/entries')):
             self.wc = url
         else:
             self.wc = None
         self.convertfp = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.iterkeys():
             uuid, module, revnum = revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + quote(path),
                                  optrev, False, self.ctx)
             return True
         except SubversionException:
             return False
 
     def getheads(self):
 
         def isdir(path, revnum):
             kind = self._checkpath(path, revnum)
             return kind == svn.core.svn_node_dir
 
         def getcfgpath(name, rev):
             cfgpath = self.ui.config('convert', 'svn.' + name)
             if cfgpath is not None and cfgpath.strip() == '':
                 return None
             path = (cfgpath or name).strip('/')
             if not self.exists(path, rev):
                 if self.module.endswith(path) and name == 'trunk':
                     # we are converting from inside this directory
                     return None
                 if cfgpath:
                     raise util.Abort(_('expected %s to be at %r, but not found')
                                  % (name, path))
                 return None
             self.ui.note(_('found %s at %r\n') % (name, path))
             return path
 
         rev = optrev(self.last_changed)
         oldmodule = ''
         trunk = getcfgpath('trunk', rev)
         self.tags = getcfgpath('tags', rev)
         branches = getcfgpath('branches', rev)
 
         # If the project has a trunk or branches, we will extract heads
         # from them. We keep the project root otherwise.
         if trunk:
             oldmodule = self.module or ''
             self.module += '/' + trunk
             self.head = self.latest(self.module, self.last_changed)
             if not self.head:
                 raise util.Abort(_('no revision found in module %s')
                                  % self.module)
 
         # First head in the list is the module's head
         self.heads = [self.head]
         if self.tags is not None:
             self.tags = '%s/%s' % (oldmodule , (self.tags or 'tags'))
 
         # Check if branches bring a few more heads to the list
         if branches:
             rpath = self.url.strip('/')
             branchnames = svn.client.ls(rpath + '/' + quote(branches),
                                         rev, False, self.ctx)
             for branch in sorted(branchnames):
                 module = '%s/%s/%s' % (oldmodule, branches, branch)
                 if not isdir(module, self.last_changed):
                     continue
                 brevid = self.latest(module, self.last_changed)
                 if not brevid:
                     self.ui.note(_('ignoring empty branch %s\n') % branch)
                     continue
                 self.ui.note(_('found branch %s at %d\n') %
                              (branch, self.revnum(brevid)))
                 self.heads.append(brevid)
 
         if self.startrev and self.heads:
             if len(self.heads) > 1:
                 raise util.Abort(_('svn: start revision is not supported '
                                    'with more than one branch'))
             revnum = self.revnum(self.heads[0])
             if revnum < self.startrev:
                 raise util.Abort(
                     _('svn: no revision found after start revision %d')
                                  % self.startrev)
 
         return self.heads
 
     def _getchanges(self, rev, full):
         (paths, parents) = self.paths[rev]
         copies = {}
         if parents:
             files, self.removed, copies = self.expandpaths(rev, paths, parents)
         if full or not parents:
             # Perform a full checkout on roots
             uuid, module, revnum = revsplit(rev)
             entries = svn.client.ls(self.baseurl + quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
             self.removed = set()
 
         files.sort()
         files = zip(files, [rev] * len(files))
         return (files, copies)
 
     def getchanges(self, rev, full):
         # reuse cache from getchangedfiles
         if self._changescache[0] == rev and not full:
             (files, copies) = self._changescache[1]
         else:
             (files, copies) = self._getchanges(rev, full)
             # caller caches the result, so free it here to release memory
             del self.paths[rev]
         return (files, copies, set())
 
     def getchangedfiles(self, rev, i):
         # called from filemap - cache computed values for reuse in getchanges
         (files, copies) = self._getchanges(rev, False)
         self._changescache = (rev, (files, copies))
         return [f[0] for f in files]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = revsplit(rev)
             self.module = module
             self.reparent(module)
             # We assume that:
             # - requests for revisions after "stop" come from the
             # revision graph backward traversal. Cache all of them
             # down to stop, they will be used eventually.
             # - requests for revisions before "stop" come to get
             # isolated branches parents. Just fetch what is needed.
             stop = self.lastrevs.get(module, 0)
             if revnum < stop:
                 stop = revnum + 1
             self._fetch_revisions(revnum, stop)
             if rev not in self.commits:
                 raise util.Abort(_('svn: revision %s not found') % revnum)
         revcommit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return revcommit
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ fails if revision format does not match the correct format"""
         if not re.match(r'svn:[0-9a-f]{8,8}-[0-9a-f]{4,4}-'
                               '[0-9a-f]{4,4}-[0-9a-f]{4,4}-[0-9a-f]'
                               '{12,12}(.*)\@[0-9]+$',revstr):
             raise util.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def numcommits(self):
         return int(self.head.rsplit('@', 1)[1]) - self.startrev
 
     def gettags(self):
         tags = {}
         if self.tags is None:
             return tags
 
         # svn tags are just a convention, project branches left in a
         # 'tags' directory. There is no other relationship than
         # ancestry, which is expensive to discover and makes them hard
         # to update incrementally.  Worse, past revisions may be
         # referenced by tags far away in the future, requiring a deep
         # history traversal on every calculation.  Current code
         # performs a single backward traversal, tracking moves within
         # the tags directory (tag renaming) and recording a new tag
         # everytime a project is copied from outside the tags
         # directory. It also lists deleted tags, this behaviour may
         # change in the future.
         pendings = []
         tagspath = self.tags
         start = svn.ra.get_latest_revnum(self.ra)
         stream = self._getlog([self.tags], start, self.startrev)
         try:
             for entry in stream:
                 origpaths, revnum, author, date, message = entry
                 if not origpaths:
                     origpaths = []
                 copies = [(e.copyfrom_path, e.copyfrom_rev, p) for p, e
                           in origpaths.iteritems() if e.copyfrom_path]
                 # Apply moves/copies from more specific to general
                 copies.sort(reverse=True)
 
                 srctagspath = tagspath
                 if copies and copies[-1][2] == tagspath:
                     # Track tags directory moves
                     srctagspath = copies.pop()[0]
 
                 for source, sourcerev, dest in copies:
                     if not dest.startswith(tagspath + '/'):
                         continue
                     for tag in pendings:
                         if tag[0].startswith(dest):
                             tagpath = source + tag[0][len(dest):]
                             tag[:2] = [tagpath, sourcerev]
                             break
                     else:
                         pendings.append([source, sourcerev, dest])
 
                 # Filter out tags with children coming from different
                 # parts of the repository like:
                 # /tags/tag.1 (from /trunk:10)
                 # /tags/tag.1/foo (from /branches/foo:12)
                 # Here/tags/tag.1 discarded as well as its children.
                 # It happens with tools like cvs2svn. Such tags cannot
                 # be represented in mercurial.
                 addeds = dict((p, e.copyfrom_path) for p, e
                               in origpaths.iteritems()
                               if e.action == 'A' and e.copyfrom_path)
                 badroots = set()
                 for destroot in addeds:
                     for source, sourcerev, dest in pendings:
                         if (not dest.startswith(destroot + '/')
                             or source.startswith(addeds[destroot] + '/')):
                             continue
                         badroots.add(destroot)
                         break
 
                 for badroot in badroots:
                     pendings = [p for p in pendings if p[2] != badroot
                                 and not p[2].startswith(badroot + '/')]
 
                 # Tell tag renamings from tag creations
                 renamings = []
                 for source, sourcerev, dest in pendings:
                     tagname = dest.split('/')[-1]
                     if source.startswith(srctagspath):
                         renamings.append([source, sourcerev, tagname])
                         continue
                     if tagname in tags:
                         # Keep the latest tag value
                         continue
                     # From revision may be fake, get one with changes
                     try:
                         tagid = self.latest(source, sourcerev)
                         if tagid and tagname not in tags:
                             tags[tagname] = tagid
                     except SvnPathNotFound:
                         # It happens when we are following directories
                         # we assumed were copied with their parents
                         # but were really created in the tag
                         # directory.
                         pass
                 pendings = renamings
                 tagspath = srctagspath
         finally:
             stream.close()
         return tags
 
     def converted(self, rev, destrev):
         if not self.wc:
             return
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.wc, '.svn', 'hg-shamap'),
                                   'a')
         self.convertfp.write('%s %d\n' % (destrev, self.revnum(rev)))
         self.convertfp.flush()
 
     def revid(self, revnum, module=None):
         return 'svn:%s%s@%s' % (self.uuid, module or self.module, revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def latest(self, path, stop=None):
         """Find the latest revid affecting path, up to stop revision
         number. If stop is None, default to repository latest
         revision. It may return a revision in a different module,
         since a branch may be moved without a change being
         reported. Return None if computed module does not belong to
         rootmodule subtree.
         """
         def findchanges(path, start, stop=None):
             stream = self._getlog([path], start, stop or 1)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if stop is None and paths:
                         # We do not know the latest changed revision,
                         # keep the first one with changed paths.
                         break
                     if revnum <= stop:
                         break
 
                     for p in paths:
                         if (not path.startswith(p) or
                             not paths[p].copyfrom_path):
                             continue
                         newpath = paths[p].copyfrom_path + path[len(p):]
                         self.ui.debug("branch renamed from %s to %s at %d\n" %
                                       (path, newpath, revnum))
                         path = newpath
                         break
                 if not paths:
                     revnum = None
                 return revnum, path
             finally:
                 stream.close()
 
         if not path.startswith(self.rootmodule):
             # Requests on foreign branches may be forbidden at server level
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
 
         if stop is None:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             prevmodule = self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(prevmodule)
         except SubversionException:
             dirent = None
         if not dirent:
             raise SvnPathNotFound(_('%s not found up to revision %d')
                                   % (path, stop))
 
         # stat() gives us the previous revision on this line of
         # development, but it might be in *another module*. Fetch the
         # log and detect renames down to the latest revision.
         revnum, realpath = findchanges(path, stop, dirent.created_rev)
         if revnum is None:
             # Tools like svnsync can create empty revision, when
             # synchronizing only a subtree for instance. These empty
             # revisions created_rev still have their original values
             # despite all changes having disappeared and can be
             # returned by ra.stat(), at least when stating the root
             # module. In that case, do not trust created_rev and scan
             # the whole history.
             revnum, realpath = findchanges(path, stop)
             if revnum is None:
                 self.ui.debug('ignoring empty branch %r\n' % realpath)
                 return None
 
         if not realpath.startswith(self.rootmodule):
             self.ui.debug('ignoring foreign branch %r\n' % realpath)
             return None
         return self.revid(revnum, realpath)
 
     def reparent(self, module):
         """Reparent the svn transport and return the previous parent."""
         if self.prevmodule == module:
             return module
         svnurl = self.baseurl + quote(module)
         prevmodule = self.prevmodule
         if prevmodule is None:
             prevmodule = ''
         self.ui.debug("reparent to %s\n" % svnurl)
         svn.ra.reparent(self.ra, svnurl)
         self.prevmodule = module
         return prevmodule
 
     def expandpaths(self, rev, paths, parents):
         changed, removed = set(), set()
         copies = {}
 
         new_module, revnum = revsplit(rev)[1:]
         if new_module != self.module:
             self.module = new_module
             self.reparent(self.module)
 
         for i, (path, ent) in enumerate(paths):
             self.ui.progress(_('scanning paths'), i, item=path,
                              total=len(paths))
             entrypath = self.getrelpath(path)
 
             kind = self._checkpath(entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 changed.add(self.recode(entrypath))
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrom_path = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrom_path:
                     continue
                 self.ui.debug("copied to %s from %s@%s\n" %
                               (entrypath, copyfrom_path, ent.copyfrom_rev))
                 copies[self.recode(entrypath)] = self.recode(copyfrom_path)
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 parentpath = pmodule + "/" + entrypath
                 fromkind = self._checkpath(entrypath, prevnum, pmodule)
 
                 if fromkind == svn.core.svn_node_file:
                     removed.add(self.recode(entrypath))
                 elif fromkind == svn.core.svn_node_dir:
                     oroot = parentpath.strip('/')
                     nroot = path.strip('/')
                     children = self._iterfiles(oroot, prevnum)
                     for childpath in children:
                         childpath = childpath.replace(oroot, nroot)
                         childpath = self.getrelpath("/" + childpath, pmodule)
                         if childpath:
                             removed.add(self.recode(childpath))
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 if ent.action == 'M':
                     # If the directory just had a prop change,
                     # then we shouldn't need to look for its children.
                     continue
                 if ent.action == 'R' and parents:
                     # If a directory is replacing a file, mark the previous
                     # file as deleted
                     pmodule, prevnum = revsplit(parents[0])[1:]
                     pkind = self._checkpath(entrypath, prevnum, pmodule)
                     if pkind == svn.core.svn_node_file:
                         removed.add(self.recode(entrypath))
                     elif pkind == svn.core.svn_node_dir:
                         # We do not know what files were kept or removed,
                         # mark them all as changed.
                         for childpath in self._iterfiles(pmodule, prevnum):
                             childpath = self.getrelpath("/" + childpath)
                             if childpath:
                                 changed.add(self.recode(childpath))
 
                 for childpath in self._iterfiles(path, revnum):
                     childpath = self.getrelpath("/" + childpath)
                     if childpath:
                         changed.add(self.recode(childpath))
 
                 # Handle directory copies
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrompath = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrompath:
                     continue
                 self.ui.debug("mark %s came from %s:%d\n"
                               % (path, copyfrompath, ent.copyfrom_rev))
                 children = self._iterfiles(ent.copyfrom_path, ent.copyfrom_rev)
                 for childpath in children:
                     childpath = self.getrelpath("/" + childpath, pmodule)
                     if not childpath:
                         continue
                     copytopath = path + childpath[len(copyfrompath):]
                     copytopath = self.getrelpath(copytopath)
                     copies[self.recode(copytopath)] = self.recode(childpath)
 
         self.ui.progress(_('scanning paths'), None)
         changed.update(removed)
         return (list(changed), removed, copies)
 
     def _fetch_revisions(self, from_revnum, to_revnum):
         if from_revnum < to_revnum:
             from_revnum, to_revnum = to_revnum, from_revnum
 
         self.child_cset = None
 
         def parselogentry(orig_paths, revnum, author, date, message):
             """Return the parsed commit object or None, and True if
             the revision is a branch root.
             """
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             branched = False
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
 
             if rev in self.commits or revnum < to_revnum:
                 return None, branched
 
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
             orig_paths = sorted(orig_paths.iteritems())
             root_paths = [(p, e) for p, e in orig_paths
                           if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
                 if ent.copyfrom_path:
                     branched = True
                     newpath = ent.copyfrom_path + self.module[len(path):]
                     # ent.copyfrom_rev may not be the actual last revision
                     previd = self.latest(newpath, ent.copyfrom_rev)
                     if previd is not None:
                         prevmodule, prevnum = revsplit(previd)[1:]
                         if prevnum >= self.startrev:
                             parents = [previd]
                             self.ui.note(
                                 _('found parent of branch %s at %d: %s\n') %
                                 (self.module, prevnum, prevmodule))
                 else:
                     self.ui.debug("no copyfrom path, don't know what to do.\n")
 
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if self.getrelpath(path) is None:
                     continue
                 paths.append((path, ent))
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = util.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
             if self.ui.configbool('convert', 'localtimezone'):
                 date = makedatetimestamp(date[0])
 
             if message:
                 log = self.recode(message)
             else:
                 log = ''
 
             if author:
                 author = self.recode(author)
             else:
                 author = ''
 
             try:
                 branch = self.module.split("/")[-1]
                 if branch == self.trunkname:
                     branch = None
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev)
 
             self.commits[rev] = cset
             # The parents list is *shared* among self.paths and the
             # commit object. Both will be updated below.
             self.paths[rev] = (paths, cset.parents)
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents[:] = [rev]
             self.child_cset = cset
             return cset, branched
 
         self.ui.note(_('fetching revision log for "%s" from %d to %d\n') %
                      (self.module, from_revnum, to_revnum))
 
         try:
             firstcset = None
             lastonbranch = False
             stream = self._getlog([self.module], from_revnum, to_revnum)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if revnum < self.startrev:
                         lastonbranch = True
                         break
                     if not paths:
                         self.ui.debug('revision %d has no entries\n' % revnum)
                         # If we ever leave the loop on an empty
                         # revision, do not try to get a parent branch
                         lastonbranch = lastonbranch or revnum == 0
                         continue
                     cset, lastonbranch = parselogentry(paths, revnum, author,
                                                        date, message)
                     if cset:
                         firstcset = cset
                     if lastonbranch:
                         break
             finally:
                 stream.close()
 
             if not lastonbranch and firstcset and not firstcset.parents:
                 # The first revision of the sequence (the last fetched one)
                 # has invalid parents if not a branch root. Find the parent
                 # revision now, if any.
                 try:
                     firstrevnum = self.revnum(firstcset.rev)
                     if firstrevnum > 1:
                         latest = self.latest(self.module, firstrevnum - 1)
                         if latest:
                             firstcset.parents.append(latest)
                 except SvnPathNotFound:
                     pass
-        except SubversionException, (inst, num):
+        except SubversionException as xxx_todo_changeme:
+            (inst, num) = xxx_todo_changeme.args
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise util.Abort(_('svn: branch has no revision %s')
                                  % to_revnum)
             raise
 
     def getfile(self, file, rev):
         # TODO: ra.get_file transmits the whole file instead of diffs.
         if file in self.removed:
             return None, None
         mode = ''
         try:
             new_module, revnum = revsplit(rev)[1:]
             if self.module != new_module:
                 self.module = new_module
                 self.reparent(self.module)
             io = StringIO()
             info = svn.ra.get_file(self.ra, file, revnum, io)
             data = io.getvalue()
             # ra.get_file() seems to keep a reference on the input buffer
             # preventing collection. Release it explicitly.
             io.close()
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
-        except SubversionException, e:
+        except SubversionException as e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
                 return None, None
             raise
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _iterfiles(self, path, revnum):
         """Enumerate all files in path at revnum, recursively."""
         path = path.strip('/')
         pool = Pool()
         rpath = '/'.join([self.baseurl, quote(path)]).strip('/')
         entries = svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool)
         if path:
             path += '/'
         return ((path + p) for p, e in entries.iteritems()
                 if e.kind == svn.core.svn_node_file)
 
     def getrelpath(self, path, module=None):
         if module is None:
             module = self.module
         # Given the repository url of this wc, say
         #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
         # extract the "entry" portion (a relative path) from what
         # svn log --xml says, i.e.
         #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
         # that is to say "tests/PloneTestCase.py"
         if path.startswith(module):
             relative = path.rstrip('/')[len(module):]
             if relative.startswith('/'):
                 return relative[1:]
             elif relative == '':
                 return relative
 
         # The path is outside our tracked tree...
         self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
         return None
 
     def _checkpath(self, path, revnum, module=None):
         if module is not None:
             prevmodule = self.reparent('')
             path = module + '/' + path
         try:
             # ra.check_path does not like leading slashes very much, it leads
             # to PROPFIND subversion errors
             return svn.ra.check_path(self.ra, path.strip('/'), revnum)
         finally:
             if module is not None:
                 self.reparent(prevmodule)
 
     def _getlog(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
         # Normalize path names, svn >= 1.5 only wants paths relative to
         # supplied URL
         relpaths = []
         for p in paths:
             if not p.startswith('/'):
                 p = self.module + '/' + p
             relpaths.append(p.strip('/'))
         args = [self.baseurl, relpaths, start, end, limit,
                 discover_changed_paths, strict_node_history]
         # undocumented feature: debugsvnlog can be disabled
         if not self.ui.configbool('convert', 'svn.debugsvnlog', True):
             return directlogstream(*args)
         arg = encodeargs(args)
         hgexe = util.hgexecutable()
         cmd = '%s debugsvnlog' % util.shellquote(hgexe)
         stdin, stdout = util.popen2(util.quotecommand(cmd))
         stdin.write(arg)
         try:
             stdin.close()
         except IOError:
             raise util.Abort(_('Mercurial failed to run itself, check'
                                ' hg executable is in PATH'))
         return logstream(stdout)
 
 pre_revprop_change = '''#!/bin/sh
 
 REPOS="$1"
 REV="$2"
 USER="$3"
 PROPNAME="$4"
 ACTION="$5"
 
 if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
 
 echo "Changing prohibited revision property" >&2
 exit 1
 '''
 
 class svn_sink(converter_sink, commandline):
     commit_re = re.compile(r'Committed revision (\d+).', re.M)
     uuid_re = re.compile(r'Repository UUID:\s*(\S+)', re.M)
 
     def prerun(self):
         if self.wc:
             os.chdir(self.wc)
 
     def postrun(self):
         if self.wc:
             os.chdir(self.cwd)
 
     def join(self, name):
         return os.path.join(self.wc, '.svn', name)
 
     def revmapfile(self):
         return self.join('hg-shamap')
 
     def authorfile(self):
         return self.join('hg-authormap')
 
     def __init__(self, ui, path):
 
         converter_sink.__init__(self, ui, path)
         commandline.__init__(self, ui, 'svn')
         self.delete = []
         self.setexec = []
         self.delexec = []
         self.copies = []
         self.wc = None
         self.cwd = os.getcwd()
 
         created = False
         if os.path.isfile(os.path.join(path, '.svn', 'entries')):
             self.wc = os.path.realpath(path)
             self.run0('update')
         else:
             if not re.search(r'^(file|http|https|svn|svn\+ssh)\://', path):
                 path = os.path.realpath(path)
                 if os.path.isdir(os.path.dirname(path)):
                     if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
                         ui.status(_('initializing svn repository %r\n') %
                                   os.path.basename(path))
                         commandline(ui, 'svnadmin').run0('create', path)
                         created = path
                     path = util.normpath(path)
                     if not path.startswith('/'):
                         path = '/' + path
                     path = 'file://' + path
 
             wcpath = os.path.join(os.getcwd(), os.path.basename(path) + '-wc')
             ui.status(_('initializing svn working copy %r\n')
                       % os.path.basename(wcpath))
             self.run0('checkout', path, wcpath)
 
             self.wc = wcpath
         self.opener = scmutil.opener(self.wc)
         self.wopener = scmutil.opener(self.wc)
         self.childmap = mapfile(ui, self.join('hg-childmap'))
         if util.checkexec(self.wc):
             self.is_exec = util.isexec
         else:
             self.is_exec = None
 
         if created:
             hook = os.path.join(created, 'hooks', 'pre-revprop-change')
             fp = open(hook, 'w')
             fp.write(pre_revprop_change)
             fp.close()
             util.setflags(hook, False, True)
 
         output = self.run0('info')
         self.uuid = self.uuid_re.search(output).group(1).strip()
 
     def wjoin(self, *names):
         return os.path.join(self.wc, *names)
 
     @propertycache
     def manifest(self):
         # As of svn 1.7, the "add" command fails when receiving
         # already tracked entries, so we have to track and filter them
         # ourselves.
         m = set()
         output = self.run0('ls', recursive=True, xml=True)
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             for n in e.childNodes:
                 if n.nodeType != n.ELEMENT_NODE or n.tagName != 'name':
                     continue
                 name = ''.join(c.data for c in n.childNodes
                                if c.nodeType == c.TEXT_NODE)
                 # Entries are compared with names coming from
                 # mercurial, so bytes with undefined encoding. Our
                 # best bet is to assume they are in local
                 # encoding. They will be passed to command line calls
                 # later anyway, so they better be.
                 m.add(encoding.tolocal(name.encode('utf-8')))
                 break
         return m
 
     def putfile(self, filename, flags, data):
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             try:
                 if os.path.islink(self.wjoin(filename)):
                     os.unlink(filename)
             except OSError:
                 pass
             self.wopener.write(filename, data)
 
             if self.is_exec:
                 if self.is_exec(self.wjoin(filename)):
                     if 'x' not in flags:
                         self.delexec.append(filename)
                 else:
                     if 'x' in flags:
                         self.setexec.append(filename)
                 util.setflags(self.wjoin(filename), False, 'x' in flags)
 
     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
         # already occurred.  Cross the semantic gap.
         wdest = self.wjoin(dest)
         exists = os.path.lexists(wdest)
         if exists:
             fd, tempname = tempfile.mkstemp(
                 prefix='hg-copy-', dir=os.path.dirname(wdest))
             os.close(fd)
             os.unlink(tempname)
             os.rename(wdest, tempname)
         try:
             self.run0('copy', source, dest)
         finally:
             self.manifest.add(dest)
             if exists:
                 try:
                     os.unlink(wdest)
                 except OSError:
                     pass
                 os.rename(tempname, wdest)
 
     def dirs_of(self, files):
         dirs = set()
         for f in files:
             if os.path.isdir(self.wjoin(f)):
                 dirs.add(f)
             for i in strutil.rfindall(f, '/'):
                 dirs.add(f[:i])
         return dirs
 
     def add_dirs(self, files):
         add_dirs = [d for d in sorted(self.dirs_of(files))
                     if d not in self.manifest]
         if add_dirs:
             self.manifest.update(add_dirs)
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
     def add_files(self, files):
         files = [f for f in files if f not in self.manifest]
         if files:
             self.manifest.update(files)
             self.xargs(files, 'add', quiet=True)
         return files
 
     def addchild(self, parent, child):
         self.childmap[parent] = child
 
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
             except KeyError:
                 pass
 
         # Apply changes to working copy
         for f, v in files:
             data, mode = source.getfile(f, v)
             if data is None:
                 self.delete.append(f)
             else:
                 self.putfile(f, mode, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
         if full:
             self.delete.extend(sorted(self.manifest.difference(files)))
         files = [f[0] for f in files]
 
         entries = set(self.delete)
         files = frozenset(files)
         entries.update(self.add_dirs(files.difference(entries)))
         if self.copies:
             for s, d in self.copies:
                 self._copyfile(s, d)
             self.copies = []
         if self.delete:
             self.xargs(self.delete, 'delete')
             for f in self.delete:
                 self.manifest.remove(f)
             self.delete = []
         entries.update(self.add_files(files.difference(entries)))
         if self.delexec:
             self.xargs(self.delexec, 'propdel', 'svn:executable')
             self.delexec = []
         if self.setexec:
             self.xargs(self.setexec, 'propset', 'svn:executable', '*')
             self.setexec = []
 
         fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
         fp = os.fdopen(fd, 'w')
         fp.write(commit.desc)
         fp.close()
         try:
             output = self.run0('commit',
                                username=util.shortuser(commit.author),
                                file=messagefile,
                                encoding='utf-8')
             try:
                 rev = self.commit_re.search(output).group(1)
             except AttributeError:
                 if parents and not files:
                     return parents[0]
                 self.ui.warn(_('unexpected svn output:\n'))
                 self.ui.warn(output)
                 raise util.Abort(_('unable to cope with svn output'))
             if commit.rev:
                 self.run('propset', 'hg:convert-rev', commit.rev,
                          revprop=True, revision=rev)
             if commit.branch and commit.branch != 'default':
                 self.run('propset', 'hg:convert-branch', commit.branch,
                          revprop=True, revision=rev)
             for parent in parents:
                 self.addchild(parent, rev)
             return self.revid(rev)
         finally:
             os.unlink(messagefile)
 
     def puttags(self, tags):
         self.ui.warn(_('writing Subversion tags is not yet implemented\n'))
         return None, None
 
     def hascommitfrommap(self, rev):
         # We trust that revisions referenced in a map still is present
         # TODO: implement something better if necessary and feasible
         return True
 
     def hascommitforsplicemap(self, rev):
         # This is not correct as one can convert to an existing subversion
         # repository and childmap would not list all revisions. Too bad.
         if rev in self.childmap:
             return True
         raise util.Abort(_('splice map revision %s not found in subversion '
                            'child map (revision lookups are not implemented)')
                          % rev)

hgext/convert/transport.py

@@ -1,128 +1,129 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, see <http://www.gnu.org/licenses/>.
 
 from mercurial import util
 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-dependent 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 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 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,
                     self.client, self.pool)
-            except SubversionException, (inst, num):
+            except SubversionException as xxx_todo_changeme:
+                (inst, num) = xxx_todo_changeme.args
                 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/eol.py

@@ -1,354 +1,354 b''
 """automatically manage newlines in repository files
 
 This extension allows you to manage the type of line endings (CRLF or
 LF) that are used in the repository and in the local working
 directory. That way you can get CRLF line endings on Windows and LF on
 Unix/Mac, thereby letting everybody use their OS native line endings.
 
 The extension reads its configuration from a versioned ``.hgeol``
 configuration file found in the root of the working directory. The
 ``.hgeol`` file use the same syntax as all other Mercurial
 configuration files. It uses two sections, ``[patterns]`` and
 ``[repository]``.
 
 The ``[patterns]`` section specifies how line endings should be
 converted between the working directory and the repository. The format is
 specified by a file pattern. The first match is used, so put more
 specific patterns first. The available line endings are ``LF``,
 ``CRLF``, and ``BIN``.
 
 Files with the declared format of ``CRLF`` or ``LF`` are always
 checked out and stored in the repository in that format and files
 declared to be binary (``BIN``) are left unchanged. Additionally,
 ``native`` is an alias for checking out in the platform's default line
 ending: ``LF`` on Unix (including Mac OS X) and ``CRLF`` on
 Windows. Note that ``BIN`` (do nothing to line endings) is Mercurial's
 default behaviour; it is only needed if you need to override a later,
 more general pattern.
 
 The optional ``[repository]`` section specifies the line endings to
 use for files stored in the repository. It has a single setting,
 ``native``, which determines the storage line endings for files
 declared as ``native`` in the ``[patterns]`` section. It can be set to
 ``LF`` or ``CRLF``. The default is ``LF``. For example, this means
 that on Windows, files configured as ``native`` (``CRLF`` by default)
 will be converted to ``LF`` when stored in the repository. Files
 declared as ``LF``, ``CRLF``, or ``BIN`` in the ``[patterns]`` section
 are always stored as-is in the repository.
 
 Example versioned ``.hgeol`` file::
 
   [patterns]
   **.py = native
   **.vcproj = CRLF
   **.txt = native
   Makefile = LF
   **.jpg = BIN
 
   [repository]
   native = LF
 
 .. note::
 
    The rules will first apply when files are touched in the working
    directory, e.g. by updating to null and back to tip to touch all files.
 
 The extension uses an optional ``[eol]`` section read from both the
 normal Mercurial configuration files and the ``.hgeol`` file, with the
 latter overriding the former. You can use that section to control the
 overall behavior. There are three settings:
 
 - ``eol.native`` (default ``os.linesep``) can be set to ``LF`` or
   ``CRLF`` to override the default interpretation of ``native`` for
   checkout. This can be used with :hg:`archive` on Unix, say, to
   generate an archive where files have line endings for Windows.
 
 - ``eol.only-consistent`` (default True) can be set to False to make
   the extension convert files with inconsistent EOLs. Inconsistent
   means that there is both ``CRLF`` and ``LF`` present in the file.
   Such files are normally not touched under the assumption that they
   have mixed EOLs on purpose.
 
 - ``eol.fix-trailing-newline`` (default False) can be set to True to
   ensure that converted files end with a EOL character (either ``\\n``
   or ``\\r\\n`` as per the configured patterns).
 
 The extension provides ``cleverencode:`` and ``cleverdecode:`` filters
 like the deprecated win32text extension does. This means that you can
 disable win32text and enable eol and your filters will still work. You
 only need to these filters until you have prepared a ``.hgeol`` file.
 
 The ``win32text.forbid*`` hooks provided by the win32text extension
 have been unified into a single hook named ``eol.checkheadshook``. The
 hook will lookup the expected line endings from the ``.hgeol`` file,
 which means you must migrate to a ``.hgeol`` file first before using
 the hook. ``eol.checkheadshook`` only checks heads, intermediate
 invalid revisions will be pushed. To forbid them completely, use the
 ``eol.checkallhook`` hook. These hooks are best used as
 ``pretxnchangegroup`` hooks.
 
 See :hg:`help patterns` for more information about the glob patterns
 used.
 """
 
 from mercurial.i18n import _
 from mercurial import util, config, extensions, match, error
 import re, os
 
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 # Matches a lone LF, i.e., one that is not part of CRLF.
 singlelf = re.compile('(^|[^\r])\n')
 # Matches a single EOL which can either be a CRLF where repeated CR
 # are removed or a LF. We do not care about old Macintosh files, so a
 # stray CR is an error.
 eolre = re.compile('\r*\n')
 
 
 def inconsistenteol(data):
     return '\r\n' in data and singlelf.search(data)
 
 def tolf(s, params, ui, **kwargs):
     """Filter to convert to LF EOLs."""
     if util.binary(s):
         return s
     if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s):
         return s
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     return eolre.sub('\n', s)
 
 def tocrlf(s, params, ui, **kwargs):
     """Filter to convert to CRLF EOLs."""
     if util.binary(s):
         return s
     if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s):
         return s
     if (ui.configbool('eol', 'fix-trailing-newline', False)
         and s and s[-1] != '\n'):
         s = s + '\n'
     return eolre.sub('\r\n', s)
 
 def isbinary(s, params):
     """Filter to do nothing with the file."""
     return s
 
 filters = {
     'to-lf': tolf,
     'to-crlf': tocrlf,
     'is-binary': isbinary,
     # The following provide backwards compatibility with win32text
     'cleverencode:': tolf,
     'cleverdecode:': tocrlf
 }
 
 class eolfile(object):
     def __init__(self, ui, root, data):
         self._decode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
         self._encode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'}
 
         self.cfg = config.config()
         # Our files should not be touched. The pattern must be
         # inserted first override a '** = native' pattern.
         self.cfg.set('patterns', '.hg*', 'BIN', 'eol')
         # We can then parse the user's patterns.
         self.cfg.parse('.hgeol', data)
 
         isrepolf = self.cfg.get('repository', 'native') != 'CRLF'
         self._encode['NATIVE'] = isrepolf and 'to-lf' or 'to-crlf'
         iswdlf = ui.config('eol', 'native', os.linesep) in ('LF', '\n')
         self._decode['NATIVE'] = iswdlf and 'to-lf' or 'to-crlf'
 
         include = []
         exclude = []
         for pattern, style in self.cfg.items('patterns'):
             key = style.upper()
             if key == 'BIN':
                 exclude.append(pattern)
             else:
                 include.append(pattern)
         # This will match the files for which we need to care
         # about inconsistent newlines.
         self.match = match.match(root, '', [], include, exclude)
 
     def copytoui(self, ui):
         for pattern, style in self.cfg.items('patterns'):
             key = style.upper()
             try:
                 ui.setconfig('decode', pattern, self._decode[key], 'eol')
                 ui.setconfig('encode', pattern, self._encode[key], 'eol')
             except KeyError:
                 ui.warn(_("ignoring unknown EOL style '%s' from %s\n")
                         % (style, self.cfg.source('patterns', pattern)))
         # eol.only-consistent can be specified in ~/.hgrc or .hgeol
         for k, v in self.cfg.items('eol'):
             ui.setconfig('eol', k, v, 'eol')
 
     def checkrev(self, repo, ctx, files):
         failed = []
         for f in (files or ctx.files()):
             if f not in ctx:
                 continue
             for pattern, style in self.cfg.items('patterns'):
                 if not match.match(repo.root, '', [pattern])(f):
                     continue
                 target = self._encode[style.upper()]
                 data = ctx[f].data()
                 if (target == "to-lf" and "\r\n" in data
                     or target == "to-crlf" and singlelf.search(data)):
                     failed.append((str(ctx), target, f))
                 break
         return failed
 
 def parseeol(ui, repo, nodes):
     try:
         for node in nodes:
             try:
                 if node is None:
                     # Cannot use workingctx.data() since it would load
                     # and cache the filters before we configure them.
                     data = repo.wfile('.hgeol').read()
                 else:
                     data = repo[node]['.hgeol'].data()
                 return eolfile(ui, repo.root, data)
             except (IOError, LookupError):
                 pass
-    except error.ParseError, inst:
+    except error.ParseError as inst:
         ui.warn(_("warning: ignoring .hgeol file due to parse error "
                   "at %s: %s\n") % (inst.args[1], inst.args[0]))
     return None
 
 def _checkhook(ui, repo, node, headsonly):
     # Get revisions to check and touched files at the same time
     files = set()
     revs = set()
     for rev in xrange(repo[node].rev(), len(repo)):
         revs.add(rev)
         if headsonly:
             ctx = repo[rev]
             files.update(ctx.files())
             for pctx in ctx.parents():
                 revs.discard(pctx.rev())
     failed = []
     for rev in revs:
         ctx = repo[rev]
         eol = parseeol(ui, repo, [ctx.node()])
         if eol:
             failed.extend(eol.checkrev(repo, ctx, files))
 
     if failed:
         eols = {'to-lf': 'CRLF', 'to-crlf': 'LF'}
         msgs = []
         for node, target, f in failed:
             msgs.append(_("  %s in %s should not have %s line endings") %
                         (f, node, eols[target]))
         raise util.Abort(_("end-of-line check failed:\n") + "\n".join(msgs))
 
 def checkallhook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, False)
 
 def checkheadshook(ui, repo, node, hooktype, **kwargs):
     """verify that files have expected EOLs"""
     _checkhook(ui, repo, node, True)
 
 # "checkheadshook" used to be called "hook"
 hook = checkheadshook
 
 def preupdate(ui, repo, hooktype, parent1, parent2):
     repo.loadeol([parent1])
     return False
 
 def uisetup(ui):
     ui.setconfig('hooks', 'preupdate.eol', preupdate, 'eol')
 
 def extsetup(ui):
     try:
         extensions.find('win32text')
         ui.warn(_("the eol extension is incompatible with the "
                   "win32text extension\n"))
     except KeyError:
         pass
 
 
 def reposetup(ui, repo):
     uisetup(repo.ui)
 
     if not repo.local():
         return
     for name, fn in filters.iteritems():
         repo.adddatafilter(name, fn)
 
     ui.setconfig('patch', 'eol', 'auto', 'eol')
 
     class eolrepo(repo.__class__):
 
         def loadeol(self, nodes):
             eol = parseeol(self.ui, self, nodes)
             if eol is None:
                 return None
             eol.copytoui(self.ui)
             return eol.match
 
         def _hgcleardirstate(self):
             self._eolfile = self.loadeol([None, 'tip'])
             if not self._eolfile:
                 self._eolfile = util.never
                 return
 
             try:
                 cachemtime = os.path.getmtime(self.join("eol.cache"))
             except OSError:
                 cachemtime = 0
 
             try:
                 eolmtime = os.path.getmtime(self.wjoin(".hgeol"))
             except OSError:
                 eolmtime = 0
 
             if eolmtime > cachemtime:
                 self.ui.debug("eol: detected change in .hgeol\n")
                 wlock = None
                 try:
                     wlock = self.wlock()
                     for f in self.dirstate:
                         if self.dirstate[f] == 'n':
                             # all normal files need to be looked at
                             # again since the new .hgeol file might no
                             # longer match a file it matched before
                             self.dirstate.normallookup(f)
                     # Create or touch the cache to update mtime
                     self.vfs("eol.cache", "w").close()
                     wlock.release()
                 except error.LockUnavailable:
                     # If we cannot lock the repository and clear the
                     # dirstate, then a commit might not see all files
                     # as modified. But if we cannot lock the
                     # repository, then we can also not make a commit,
                     # so ignore the error.
                     pass
 
         def commitctx(self, ctx, error=False):
             for f in sorted(ctx.added() + ctx.modified()):
                 if not self._eolfile(f):
                     continue
                 fctx = ctx[f]
                 if fctx is None:
                     continue
                 data = fctx.data()
                 if util.binary(data):
                     # We should not abort here, since the user should
                     # be able to say "** = native" to automatically
                     # have all non-binary files taken care of.
                     continue
                 if inconsistenteol(data):
                     raise util.Abort(_("inconsistent newline style "
                                        "in %s\n") % f)
             return super(eolrepo, self).commitctx(ctx, error)
     repo.__class__ = eolrepo
     repo._hgcleardirstate()

hgext/gpg.py

@@ -1,301 +1,301 b''
 # Copyright 2005, 2006 Benoit Boissinot <[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.
 
 '''commands to sign and verify changesets'''
 
 import os, tempfile, binascii
 from mercurial import util, commands, match, cmdutil
 from mercurial import node as hgnode
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 class gpg(object):
     def __init__(self, path, key=None):
         self.path = path
         self.key = (key and " --local-user \"%s\"" % key) or ""
 
     def sign(self, data):
         gpgcmd = "%s --sign --detach-sign%s" % (self.path, self.key)
         return util.filter(data, gpgcmd)
 
     def verify(self, data, sig):
         """ returns of the good and bad signatures"""
         sigfile = datafile = None
         try:
             # create temporary files
             fd, sigfile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".sig")
             fp = os.fdopen(fd, 'wb')
             fp.write(sig)
             fp.close()
             fd, datafile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".txt")
             fp = os.fdopen(fd, 'wb')
             fp.write(data)
             fp.close()
             gpgcmd = ("%s --logger-fd 1 --status-fd 1 --verify "
                       "\"%s\" \"%s\"" % (self.path, sigfile, datafile))
             ret = util.filter("", gpgcmd)
         finally:
             for f in (sigfile, datafile):
                 try:
                     if f:
                         os.unlink(f)
                 except OSError:
                     pass
         keys = []
         key, fingerprint = None, None
         for l in ret.splitlines():
             # see DETAILS in the gnupg documentation
             # filter the logger output
             if not l.startswith("[GNUPG:]"):
                 continue
             l = l[9:]
             if l.startswith("VALIDSIG"):
                 # fingerprint of the primary key
                 fingerprint = l.split()[10]
             elif l.startswith("ERRSIG"):
                 key = l.split(" ", 3)[:2]
                 key.append("")
                 fingerprint = None
             elif (l.startswith("GOODSIG") or
                   l.startswith("EXPSIG") or
                   l.startswith("EXPKEYSIG") or
                   l.startswith("BADSIG")):
                 if key is not None:
                     keys.append(key + [fingerprint])
                 key = l.split(" ", 2)
                 fingerprint = None
         if key is not None:
             keys.append(key + [fingerprint])
         return keys
 
 def newgpg(ui, **opts):
     """create a new gpg instance"""
     gpgpath = ui.config("gpg", "cmd", "gpg")
     gpgkey = opts.get('key')
     if not gpgkey:
         gpgkey = ui.config("gpg", "key", None)
     return gpg(gpgpath, gpgkey)
 
 def sigwalk(repo):
     """
     walk over every sigs, yields a couple
     ((node, version, sig), (filename, linenumber))
     """
     def parsefile(fileiter, context):
         ln = 1
         for l in fileiter:
             if not l:
                 continue
             yield (l.split(" ", 2), (context, ln))
             ln += 1
 
     # read the heads
     fl = repo.file(".hgsigs")
     for r in reversed(fl.heads()):
         fn = ".hgsigs|%s" % hgnode.short(r)
         for item in parsefile(fl.read(r).splitlines(), fn):
             yield item
     try:
         # read local signatures
         fn = "localsigs"
         for item in parsefile(repo.vfs(fn), fn):
             yield item
     except IOError:
         pass
 
 def getkeys(ui, repo, mygpg, sigdata, context):
     """get the keys who signed a data"""
     fn, ln = context
     node, version, sig = sigdata
     prefix = "%s:%d" % (fn, ln)
     node = hgnode.bin(node)
 
     data = node2txt(repo, node, version)
     sig = binascii.a2b_base64(sig)
     keys = mygpg.verify(data, sig)
 
     validkeys = []
     # warn for expired key and/or sigs
     for key in keys:
         if key[0] == "ERRSIG":
             ui.write(_("%s Unknown key ID \"%s\"\n")
                      % (prefix, shortkey(ui, key[1][:15])))
             continue
         if key[0] == "BADSIG":
             ui.write(_("%s Bad signature from \"%s\"\n") % (prefix, key[2]))
             continue
         if key[0] == "EXPSIG":
             ui.write(_("%s Note: Signature has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         elif key[0] == "EXPKEYSIG":
             ui.write(_("%s Note: This key has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         validkeys.append((key[1], key[2], key[3]))
     return validkeys
 
 @command("sigs", [], _('hg sigs'))
 def sigs(ui, repo):
     """list signed changesets"""
     mygpg = newgpg(ui)
     revs = {}
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         fn, ln = context
         try:
             n = repo.lookup(node)
         except KeyError:
             ui.warn(_("%s:%d node does not exist\n") % (fn, ln))
             continue
         r = repo.changelog.rev(n)
         keys = getkeys(ui, repo, mygpg, data, context)
         if not keys:
             continue
         revs.setdefault(r, [])
         revs[r].extend(keys)
     for rev in sorted(revs, reverse=True):
         for k in revs[rev]:
             r = "%5d:%s" % (rev, hgnode.hex(repo.changelog.node(rev)))
             ui.write("%-30s %s\n" % (keystr(ui, k), r))
 
 @command("sigcheck", [], _('hg sigcheck REV'))
 def check(ui, repo, rev):
     """verify all the signatures there may be for a particular revision"""
     mygpg = newgpg(ui)
     rev = repo.lookup(rev)
     hexrev = hgnode.hex(rev)
     keys = []
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         if node == hexrev:
             k = getkeys(ui, repo, mygpg, data, context)
             if k:
                 keys.extend(k)
 
     if not keys:
         ui.write(_("no valid signature for %s\n") % hgnode.short(rev))
         return
 
     # print summary
     ui.write("%s is signed by:\n" % hgnode.short(rev))
     for key in keys:
         ui.write(" %s\n" % keystr(ui, key))
 
 def keystr(ui, key):
     """associate a string to a key (username, comment)"""
     keyid, user, fingerprint = key
     comment = ui.config("gpg", fingerprint, None)
     if comment:
         return "%s (%s)" % (user, comment)
     else:
         return user
 
 @command("sign",
          [('l', 'local', None, _('make the signature local')),
           ('f', 'force', None, _('sign even if the sigfile is modified')),
           ('', 'no-commit', None, _('do not commit the sigfile after signing')),
           ('k', 'key', '',
            _('the key id to sign with'), _('ID')),
           ('m', 'message', '',
            _('use text as commit message'), _('TEXT')),
           ('e', 'edit', False, _('invoke editor on commit messages')),
          ] + commands.commitopts2,
          _('hg sign [OPTION]... [REV]...'))
 def sign(ui, repo, *revs, **opts):
     """add a signature for the current or given revision
 
     If no revision is given, the parent of the working directory is used,
     or tip if no revision is checked out.
 
     See :hg:`help dates` for a list of formats valid for -d/--date.
     """
 
     mygpg = newgpg(ui, **opts)
     sigver = "0"
     sigmessage = ""
 
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
 
     if revs:
         nodes = [repo.lookup(n) for n in revs]
     else:
         nodes = [node for node in repo.dirstate.parents()
                  if node != hgnode.nullid]
         if len(nodes) > 1:
             raise util.Abort(_('uncommitted merge - please provide a '
                                'specific revision'))
         if not nodes:
             nodes = [repo.changelog.tip()]
 
     for n in nodes:
         hexnode = hgnode.hex(n)
         ui.write(_("signing %d:%s\n") % (repo.changelog.rev(n),
                                          hgnode.short(n)))
         # build data
         data = node2txt(repo, n, sigver)
         sig = mygpg.sign(data)
         if not sig:
             raise util.Abort(_("error while signing"))
         sig = binascii.b2a_base64(sig)
         sig = sig.replace("\n", "")
         sigmessage += "%s %s %s\n" % (hexnode, sigver, sig)
 
     # write it
     if opts['local']:
         repo.vfs.append("localsigs", sigmessage)
         return
 
     if not opts["force"]:
         msigs = match.exact(repo.root, '', ['.hgsigs'])
         if any(repo.status(match=msigs, unknown=True, ignored=True)):
             raise util.Abort(_("working copy of .hgsigs is changed "),
                              hint=_("please commit .hgsigs manually"))
 
     sigsfile = repo.wfile(".hgsigs", "ab")
     sigsfile.write(sigmessage)
     sigsfile.close()
 
     if '.hgsigs' not in repo.dirstate:
         repo[None].add([".hgsigs"])
 
     if opts["no_commit"]:
         return
 
     message = opts['message']
     if not message:
         # we don't translate commit messages
         message = "\n".join(["Added signature for changeset %s"
                              % hgnode.short(n)
                              for n in nodes])
     try:
         editor = cmdutil.getcommiteditor(editform='gpg.sign', **opts)
         repo.commit(message, opts['user'], opts['date'], match=msigs,
                     editor=editor)
-    except ValueError, inst:
+    except ValueError as inst:
         raise util.Abort(str(inst))
 
 def shortkey(ui, key):
     if len(key) != 16:
         ui.debug("key ID \"%s\" format error\n" % key)
         return key
 
     return key[-8:]
 
 def node2txt(repo, node, ver):
     """map a manifest into some text"""
     if ver == "0":
         return "%s\n" % hgnode.hex(node)
     else:
         raise util.Abort(_("unknown signature version"))

hgext/histedit.py

@@ -1,1159 +1,1159 b''
 # histedit.py - interactive history editing for mercurial
 #
 # Copyright 2009 Augie Fackler <[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.
 """interactive history editing
 
 With this extension installed, Mercurial gains one new command: histedit. Usage
 is as follows, assuming the following history::
 
  @  3[tip]   7c2fd3b9020c   2009-04-27 18:04 -0500   durin42
  |    Add delta
  |
  o  2   030b686bedc4   2009-04-27 18:04 -0500   durin42
  |    Add gamma
  |
  o  1   c561b4e977df   2009-04-27 18:04 -0500   durin42
  |    Add beta
  |
  o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
       Add alpha
 
 If you were to run ``hg histedit c561b4e977df``, you would see the following
 file open in your editor::
 
  pick c561b4e977df Add beta
  pick 030b686bedc4 Add gamma
  pick 7c2fd3b9020c Add delta
 
  # Edit history between c561b4e977df and 7c2fd3b9020c
  #
  # Commits are listed from least to most recent
  #
  # Commands:
  #  p, pick = use commit
  #  e, edit = use commit, but stop for amending
  #  f, fold = use commit, but combine it with the one above
  #  r, roll = like fold, but discard this commit's description
  #  d, drop = remove commit from history
  #  m, mess = edit message without changing commit content
  #
 
 In this file, lines beginning with ``#`` are ignored. You must specify a rule
 for each revision in your history. For example, if you had meant to add gamma
 before beta, and then wanted to add delta in the same revision as beta, you
 would reorganize the file to look like this::
 
  pick 030b686bedc4 Add gamma
  pick c561b4e977df Add beta
  fold 7c2fd3b9020c Add delta
 
  # Edit history between c561b4e977df and 7c2fd3b9020c
  #
  # Commits are listed from least to most recent
  #
  # Commands:
  #  p, pick = use commit
  #  e, edit = use commit, but stop for amending
  #  f, fold = use commit, but combine it with the one above
  #  r, roll = like fold, but discard this commit's description
  #  d, drop = remove commit from history
  #  m, mess = edit message without changing commit content
  #
 
 At which point you close the editor and ``histedit`` starts working. When you
 specify a ``fold`` operation, ``histedit`` will open an editor when it folds
 those revisions together, offering you a chance to clean up the commit message::
 
  Add beta
  ***
  Add delta
 
 Edit the commit message to your liking, then close the editor. For
 this example, let's assume that the commit message was changed to
 ``Add beta and delta.`` After histedit has run and had a chance to
 remove any old or temporary revisions it needed, the history looks
 like this::
 
  @  2[tip]   989b4d060121   2009-04-27 18:04 -0500   durin42
  |    Add beta and delta.
  |
  o  1   081603921c3f   2009-04-27 18:04 -0500   durin42
  |    Add gamma
  |
  o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
       Add alpha
 
 Note that ``histedit`` does *not* remove any revisions (even its own temporary
 ones) until after it has completed all the editing operations, so it will
 probably perform several strip operations when it's done. For the above example,
 it had to run strip twice. Strip can be slow depending on a variety of factors,
 so you might need to be a little patient. You can choose to keep the original
 revisions by passing the ``--keep`` flag.
 
 The ``edit`` operation will drop you back to a command prompt,
 allowing you to edit files freely, or even use ``hg record`` to commit
 some changes as a separate commit. When you're done, any remaining
 uncommitted changes will be committed as well. When done, run ``hg
 histedit --continue`` to finish this step. You'll be prompted for a
 new commit message, but the default commit message will be the
 original message for the ``edit`` ed revision.
 
 The ``message`` operation will give you a chance to revise a commit
 message without changing the contents. It's a shortcut for doing
 ``edit`` immediately followed by `hg histedit --continue``.
 
 If ``histedit`` encounters a conflict when moving a revision (while
 handling ``pick`` or ``fold``), it'll stop in a similar manner to
 ``edit`` with the difference that it won't prompt you for a commit
 message when done. If you decide at this point that you don't like how
 much work it will be to rearrange history, or that you made a mistake,
 you can use ``hg histedit --abort`` to abandon the new changes you
 have made and return to the state before you attempted to edit your
 history.
 
 If we clone the histedit-ed example repository above and add four more
 changes, such that we have the following history::
 
    @  6[tip]   038383181893   2009-04-27 18:04 -0500   stefan
    |    Add theta
    |
    o  5   140988835471   2009-04-27 18:04 -0500   stefan
    |    Add eta
    |
    o  4   122930637314   2009-04-27 18:04 -0500   stefan
    |    Add zeta
    |
    o  3   836302820282   2009-04-27 18:04 -0500   stefan
    |    Add epsilon
    |
    o  2   989b4d060121   2009-04-27 18:04 -0500   durin42
    |    Add beta and delta.
    |
    o  1   081603921c3f   2009-04-27 18:04 -0500   durin42
    |    Add gamma
    |
    o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
         Add alpha
 
 If you run ``hg histedit --outgoing`` on the clone then it is the same
 as running ``hg histedit 836302820282``. If you need plan to push to a
 repository that Mercurial does not detect to be related to the source
 repo, you can add a ``--force`` option.
 
 Histedit rule lines are truncated to 80 characters by default. You
 can customise this behaviour by setting a different length in your
 configuration file::
 
   [histedit]
   linelen = 120      # truncate rule lines at 120 characters
 """
 
 try:
     import cPickle as pickle
     pickle.dump # import now
 except ImportError:
     import pickle
 import errno
 import os
 import sys
 
 from mercurial import cmdutil
 from mercurial import discovery
 from mercurial import error
 from mercurial import changegroup
 from mercurial import copies
 from mercurial import context
 from mercurial import exchange
 from mercurial import extensions
 from mercurial import hg
 from mercurial import node
 from mercurial import repair
 from mercurial import scmutil
 from mercurial import util
 from mercurial import obsolete
 from mercurial import merge as mergemod
 from mercurial.lock import release
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 # Note for extension authors: ONLY specify testedwith = 'internal' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'internal'
 
 # i18n: command names and abbreviations must remain untranslated
 editcomment = _("""# Edit history between %s and %s
 #
 # Commits are listed from least to most recent
 #
 # Commands:
 #  p, pick = use commit
 #  e, edit = use commit, but stop for amending
 #  f, fold = use commit, but combine it with the one above
 #  r, roll = like fold, but discard this commit's description
 #  d, drop = remove commit from history
 #  m, mess = edit message without changing commit content
 #
 """)
 
 class histeditstate(object):
     def __init__(self, repo, parentctxnode=None, rules=None, keep=None,
             topmost=None, replacements=None, lock=None, wlock=None):
         self.repo = repo
         self.rules = rules
         self.keep = keep
         self.topmost = topmost
         self.parentctxnode = parentctxnode
         self.lock = lock
         self.wlock = wlock
         self.backupfile = None
         if replacements is None:
             self.replacements = []
         else:
             self.replacements = replacements
 
     def read(self):
         """Load histedit state from disk and set fields appropriately."""
         try:
             fp = self.repo.vfs('histedit-state', 'r')
-        except IOError, err:
+        except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             raise util.Abort(_('no histedit in progress'))
 
         try:
             data = pickle.load(fp)
             parentctxnode, rules, keep, topmost, replacements = data
             backupfile = None
         except pickle.UnpicklingError:
             data = self._load()
             parentctxnode, rules, keep, topmost, replacements, backupfile = data
 
         self.parentctxnode = parentctxnode
         self.rules = rules
         self.keep = keep
         self.topmost = topmost
         self.replacements = replacements
         self.backupfile = backupfile
 
     def write(self):
         fp = self.repo.vfs('histedit-state', 'w')
         fp.write('v1\n')
         fp.write('%s\n' % node.hex(self.parentctxnode))
         fp.write('%s\n' % node.hex(self.topmost))
         fp.write('%s\n' % self.keep)
         fp.write('%d\n' % len(self.rules))
         for rule in self.rules:
             fp.write('%s\n' % rule[0]) # action
             fp.write('%s\n' % rule[1]) # remainder
         fp.write('%d\n' % len(self.replacements))
         for replacement in self.replacements:
             fp.write('%s%s\n' % (node.hex(replacement[0]), ''.join(node.hex(r)
                 for r in replacement[1])))
         backupfile = self.backupfile
         if not backupfile:
             backupfile = ''
         fp.write('%s\n' % backupfile)
         fp.close()
 
     def _load(self):
         fp = self.repo.vfs('histedit-state', 'r')
         lines = [l[:-1] for l in fp.readlines()]
 
         index = 0
         lines[index] # version number
         index += 1
 
         parentctxnode = node.bin(lines[index])
         index += 1
 
         topmost = node.bin(lines[index])
         index += 1
 
         keep = lines[index] == 'True'
         index += 1
 
         # Rules
         rules = []
         rulelen = int(lines[index])
         index += 1
         for i in xrange(rulelen):
             ruleaction = lines[index]
             index += 1
             rule = lines[index]
             index += 1
             rules.append((ruleaction, rule))
 
         # Replacements
         replacements = []
         replacementlen = int(lines[index])
         index += 1
         for i in xrange(replacementlen):
             replacement = lines[index]
             original = node.bin(replacement[:40])
             succ = [node.bin(replacement[i:i + 40]) for i in
                     range(40, len(replacement), 40)]
             replacements.append((original, succ))
             index += 1
 
         backupfile = lines[index]
         index += 1
 
         fp.close()
 
         return parentctxnode, rules, keep, topmost, replacements, backupfile
 
     def clear(self):
         self.repo.vfs.unlink('histedit-state')
 
 class histeditaction(object):
     def __init__(self, state, node):
         self.state = state
         self.repo = state.repo
         self.node = node
 
     @classmethod
     def fromrule(cls, state, rule):
         """Parses the given rule, returning an instance of the histeditaction.
         """
         repo = state.repo
         rulehash = rule.strip().split(' ', 1)[0]
         try:
             node = repo[rulehash].node()
         except error.RepoError:
             raise util.Abort(_('unknown changeset %s listed') % rulehash[:12])
         return cls(state, node)
 
     def run(self):
         """Runs the action. The default behavior is simply apply the action's
         rulectx onto the current parentctx."""
         self.applychange()
         self.continuedirty()
         return self.continueclean()
 
     def applychange(self):
         """Applies the changes from this action's rulectx onto the current
         parentctx, but does not commit them."""
         repo = self.repo
         rulectx = repo[self.node]
         hg.update(repo, self.state.parentctxnode)
         stats = applychanges(repo.ui, repo, rulectx, {})
         if stats and stats[3] > 0:
             raise error.InterventionRequired(_('Fix up the change and run '
                                             'hg histedit --continue'))
 
     def continuedirty(self):
         """Continues the action when changes have been applied to the working
         copy. The default behavior is to commit the dirty changes."""
         repo = self.repo
         rulectx = repo[self.node]
 
         editor = self.commiteditor()
         commit = commitfuncfor(repo, rulectx)
 
         commit(text=rulectx.description(), user=rulectx.user(),
                date=rulectx.date(), extra=rulectx.extra(), editor=editor)
 
     def commiteditor(self):
         """The editor to be used to edit the commit message."""
         return False
 
     def continueclean(self):
         """Continues the action when the working copy is clean. The default
         behavior is to accept the current commit as the new version of the
         rulectx."""
         ctx = self.repo['.']
         if ctx.node() == self.state.parentctxnode:
             self.repo.ui.warn(_('%s: empty changeset\n') %
                               node.short(self.node))
             return ctx, [(self.node, tuple())]
         if ctx.node() == self.node:
             # Nothing changed
             return ctx, []
         return ctx, [(self.node, (ctx.node(),))]
 
 def commitfuncfor(repo, src):
     """Build a commit function for the replacement of <src>
 
     This function ensure we apply the same treatment to all changesets.
 
     - Add a 'histedit_source' entry in extra.
 
     Note that fold has its own separated logic because its handling is a bit
     different and not easily factored out of the fold method.
     """
     phasemin = src.phase()
     def commitfunc(**kwargs):
         phasebackup = repo.ui.backupconfig('phases', 'new-commit')
         try:
             repo.ui.setconfig('phases', 'new-commit', phasemin,
                               'histedit')
             extra = kwargs.get('extra', {}).copy()
             extra['histedit_source'] = src.hex()
             kwargs['extra'] = extra
             return repo.commit(**kwargs)
         finally:
             repo.ui.restoreconfig(phasebackup)
     return commitfunc
 
 def applychanges(ui, repo, ctx, opts):
     """Merge changeset from ctx (only) in the current working directory"""
     wcpar = repo.dirstate.parents()[0]
     if ctx.p1().node() == wcpar:
         # edition ar "in place" we do not need to make any merge,
         # just applies changes on parent for edition
         cmdutil.revert(ui, repo, ctx, (wcpar, node.nullid), all=True)
         stats = None
     else:
         try:
             # ui.forcemerge is an internal variable, do not document
             repo.ui.setconfig('ui', 'forcemerge', opts.get('tool', ''),
                               'histedit')
             stats = mergemod.graft(repo, ctx, ctx.p1(), ['local', 'histedit'])
         finally:
             repo.ui.setconfig('ui', 'forcemerge', '', 'histedit')
     return stats
 
 def collapse(repo, first, last, commitopts, skipprompt=False):
     """collapse the set of revisions from first to last as new one.
 
     Expected commit options are:
         - message
         - date
         - username
     Commit message is edited in all cases.
 
     This function works in memory."""
     ctxs = list(repo.set('%d::%d', first, last))
     if not ctxs:
         return None
     for c in ctxs:
         if not c.mutable():
             raise util.Abort(
                 _("cannot fold into public change %s") % node.short(c.node()))
     base = first.parents()[0]
 
     # commit a new version of the old changeset, including the update
     # collect all files which might be affected
     files = set()
     for ctx in ctxs:
         files.update(ctx.files())
 
     # Recompute copies (avoid recording a -> b -> a)
     copied = copies.pathcopies(base, last)
 
     # prune files which were reverted by the updates
     def samefile(f):
         if f in last.manifest():
             a = last.filectx(f)
             if f in base.manifest():
                 b = base.filectx(f)
                 return (a.data() == b.data()
                         and a.flags() == b.flags())
             else:
                 return False
         else:
             return f not in base.manifest()
     files = [f for f in files if not samefile(f)]
     # commit version of these files as defined by head
     headmf = last.manifest()
     def filectxfn(repo, ctx, path):
         if path in headmf:
             fctx = last[path]
             flags = fctx.flags()
             mctx = context.memfilectx(repo,
                                       fctx.path(), fctx.data(),
                                       islink='l' in flags,
                                       isexec='x' in flags,
                                       copied=copied.get(path))
             return mctx
         return None
 
     if commitopts.get('message'):
         message = commitopts['message']
     else:
         message = first.description()
     user = commitopts.get('user')
     date = commitopts.get('date')
     extra = commitopts.get('extra')
 
     parents = (first.p1().node(), first.p2().node())
     editor = None
     if not skipprompt:
         editor = cmdutil.getcommiteditor(edit=True, editform='histedit.fold')
     new = context.memctx(repo,
                          parents=parents,
                          text=message,
                          files=files,
                          filectxfn=filectxfn,
                          user=user,
                          date=date,
                          extra=extra,
                          editor=editor)
     return repo.commitctx(new)
 
 class pick(histeditaction):
     def run(self):
         rulectx = self.repo[self.node]
         if rulectx.parents()[0].node() == self.state.parentctxnode:
             self.repo.ui.debug('node %s unchanged\n' % node.short(self.node))
             return rulectx, []
 
         return super(pick, self).run()
 
 class edit(histeditaction):
     def run(self):
         repo = self.repo
         rulectx = repo[self.node]
         hg.update(repo, self.state.parentctxnode)
         applychanges(repo.ui, repo, rulectx, {})
         raise error.InterventionRequired(
             _('Make changes as needed, you may commit or record as needed '
               'now.\nWhen you are finished, run hg histedit --continue to '
               'resume.'))
 
     def commiteditor(self):
         return cmdutil.getcommiteditor(edit=True, editform='histedit.edit')
 
 class fold(histeditaction):
     def continuedirty(self):
         repo = self.repo
         rulectx = repo[self.node]
 
         commit = commitfuncfor(repo, rulectx)
         commit(text='fold-temp-revision %s' % node.short(self.node),
                user=rulectx.user(), date=rulectx.date(),
                extra=rulectx.extra())
 
     def continueclean(self):
         repo = self.repo
         ctx = repo['.']
         rulectx = repo[self.node]
         parentctxnode = self.state.parentctxnode
         if ctx.node() == parentctxnode:
             repo.ui.warn(_('%s: empty changeset\n') %
                               node.short(self.node))
             return ctx, [(self.node, (parentctxnode,))]
 
         parentctx = repo[parentctxnode]
         newcommits = set(c.node() for c in repo.set('(%d::. - %d)', parentctx,
                                                  parentctx))
         if not newcommits:
             repo.ui.warn(_('%s: cannot fold - working copy is not a '
                            'descendant of previous commit %s\n') %
                            (node.short(self.node), node.short(parentctxnode)))
             return ctx, [(self.node, (ctx.node(),))]
 
         middlecommits = newcommits.copy()
         middlecommits.discard(ctx.node())
 
         return self.finishfold(repo.ui, repo, parentctx, rulectx, ctx.node(),
                                middlecommits)
 
     def skipprompt(self):
         return False
 
     def finishfold(self, ui, repo, ctx, oldctx, newnode, internalchanges):
         parent = ctx.parents()[0].node()
         hg.update(repo, parent)
         ### prepare new commit data
         commitopts = {}
         commitopts['user'] = ctx.user()
         # commit message
         if self.skipprompt():
             newmessage = ctx.description()
         else:
             newmessage = '\n***\n'.join(
                 [ctx.description()] +
                 [repo[r].description() for r in internalchanges] +
                 [oldctx.description()]) + '\n'
         commitopts['message'] = newmessage
         # date
         commitopts['date'] = max(ctx.date(), oldctx.date())
         extra = ctx.extra().copy()
         # histedit_source
         # note: ctx is likely a temporary commit but that the best we can do
         #       here. This is sufficient to solve issue3681 anyway.
         extra['histedit_source'] = '%s,%s' % (ctx.hex(), oldctx.hex())
         commitopts['extra'] = extra
         phasebackup = repo.ui.backupconfig('phases', 'new-commit')
         try:
             phasemin = max(ctx.phase(), oldctx.phase())
             repo.ui.setconfig('phases', 'new-commit', phasemin, 'histedit')
             n = collapse(repo, ctx, repo[newnode], commitopts,
                          skipprompt=self.skipprompt())
         finally:
             repo.ui.restoreconfig(phasebackup)
         if n is None:
             return ctx, []
         hg.update(repo, n)
         replacements = [(oldctx.node(), (newnode,)),
                         (ctx.node(), (n,)),
                         (newnode, (n,)),
                        ]
         for ich in internalchanges:
             replacements.append((ich, (n,)))
         return repo[n], replacements
 
 class rollup(fold):
     def skipprompt(self):
         return True
 
 class drop(histeditaction):
     def run(self):
         parentctx = self.repo[self.state.parentctxnode]
         return parentctx, [(self.node, tuple())]
 
 class message(histeditaction):
     def commiteditor(self):
         return cmdutil.getcommiteditor(edit=True, editform='histedit.mess')
 
 def findoutgoing(ui, repo, remote=None, force=False, opts={}):
     """utility function to find the first outgoing changeset
 
     Used by initialisation code"""
     dest = ui.expandpath(remote or 'default-push', remote or 'default')
     dest, revs = hg.parseurl(dest, None)[:2]
     ui.status(_('comparing with %s\n') % util.hidepassword(dest))
 
     revs, checkout = hg.addbranchrevs(repo, repo, revs, None)
     other = hg.peer(repo, opts, dest)
 
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
 
     outgoing = discovery.findcommonoutgoing(repo, other, revs, force=force)
     if not outgoing.missing:
         raise util.Abort(_('no outgoing ancestors'))
     roots = list(repo.revs("roots(%ln)", outgoing.missing))
     if 1 < len(roots):
         msg = _('there are ambiguous outgoing revisions')
         hint = _('see "hg help histedit" for more detail')
         raise util.Abort(msg, hint=hint)
     return repo.lookup(roots[0])
 
 actiontable = {'p': pick,
                'pick': pick,
                'e': edit,
                'edit': edit,
                'f': fold,
                'fold': fold,
                'r': rollup,
                'roll': rollup,
                'd': drop,
                'drop': drop,
                'm': message,
                'mess': message,
                }
 
 @command('histedit',
     [('', 'commands', '',
       _('read history edits from the specified file'), _('FILE')),
      ('c', 'continue', False, _('continue an edit already in progress')),
      ('', 'edit-plan', False, _('edit remaining actions list')),
      ('k', 'keep', False,
       _("don't strip old nodes after edit is complete")),
      ('', 'abort', False, _('abort an edit in progress')),
      ('o', 'outgoing', False, _('changesets not found in destination')),
      ('f', 'force', False,
       _('force outgoing even for unrelated repositories')),
      ('r', 'rev', [], _('first revision to be edited'), _('REV'))],
      _("ANCESTOR | --outgoing [URL]"))
 def histedit(ui, repo, *freeargs, **opts):
     """interactively edit changeset history
 
     This command edits changesets between ANCESTOR and the parent of
     the working directory.
 
     With --outgoing, this edits changesets not found in the
     destination repository. If URL of the destination is omitted, the
     'default-push' (or 'default') path will be used.
 
     For safety, this command is aborted, also if there are ambiguous
     outgoing revisions which may confuse users: for example, there are
     multiple branches containing outgoing revisions.
 
     Use "min(outgoing() and ::.)" or similar revset specification
     instead of --outgoing to specify edit target revision exactly in
     such ambiguous situation. See :hg:`help revsets` for detail about
     selecting revisions.
 
     Returns 0 on success, 1 if user intervention is required (not only
     for intentional "edit" command, but also for resolving unexpected
     conflicts).
     """
     state = histeditstate(repo)
     try:
         state.wlock = repo.wlock()
         state.lock = repo.lock()
         _histedit(ui, repo, state, *freeargs, **opts)
     finally:
         release(state.lock, state.wlock)
 
 def _histedit(ui, repo, state, *freeargs, **opts):
     # TODO only abort if we try and histedit mq patches, not just
     # blanket if mq patches are applied somewhere
     mq = getattr(repo, 'mq', None)
     if mq and mq.applied:
         raise util.Abort(_('source has mq patches applied'))
 
     # basic argument incompatibility processing
     outg = opts.get('outgoing')
     cont = opts.get('continue')
     editplan = opts.get('edit_plan')
     abort = opts.get('abort')
     force = opts.get('force')
     rules = opts.get('commands', '')
     revs = opts.get('rev', [])
     goal = 'new' # This invocation goal, in new, continue, abort
     if force and not outg:
         raise util.Abort(_('--force only allowed with --outgoing'))
     if cont:
         if any((outg, abort, revs, freeargs, rules, editplan)):
             raise util.Abort(_('no arguments allowed with --continue'))
         goal = 'continue'
     elif abort:
         if any((outg, revs, freeargs, rules, editplan)):
             raise util.Abort(_('no arguments allowed with --abort'))
         goal = 'abort'
     elif editplan:
         if any((outg, revs, freeargs)):
             raise util.Abort(_('only --commands argument allowed with '
                                '--edit-plan'))
         goal = 'edit-plan'
     else:
         if os.path.exists(os.path.join(repo.path, 'histedit-state')):
             raise util.Abort(_('history edit already in progress, try '
                                '--continue or --abort'))
         if outg:
             if revs:
                 raise util.Abort(_('no revisions allowed with --outgoing'))
             if len(freeargs) > 1:
                 raise util.Abort(
                     _('only one repo argument allowed with --outgoing'))
         else:
             revs.extend(freeargs)
             if len(revs) == 0:
                 histeditdefault = ui.config('histedit', 'defaultrev')
                 if histeditdefault:
                     revs.append(histeditdefault)
             if len(revs) != 1:
                 raise util.Abort(
                     _('histedit requires exactly one ancestor revision'))
 
 
     replacements = []
     state.keep = opts.get('keep', False)
 
     # rebuild state
     if goal == 'continue':
         state.read()
         state = bootstrapcontinue(ui, state, opts)
     elif goal == 'edit-plan':
         state.read()
         if not rules:
             comment = editcomment % (node.short(state.parentctxnode),
                                      node.short(state.topmost))
             rules = ruleeditor(repo, ui, state.rules, comment)
         else:
             if rules == '-':
                 f = sys.stdin
             else:
                 f = open(rules)
             rules = f.read()
             f.close()
         rules = [l for l in (r.strip() for r in rules.splitlines())
                  if l and not l.startswith('#')]
         rules = verifyrules(rules, repo, [repo[c] for [_a, c] in state.rules])
         state.rules = rules
         state.write()
         return
     elif goal == 'abort':
         state.read()
         mapping, tmpnodes, leafs, _ntm = processreplacement(state)
         ui.debug('restore wc to old parent %s\n' % node.short(state.topmost))
 
         # Recover our old commits if necessary
         if not state.topmost in repo and state.backupfile:
             backupfile = repo.join(state.backupfile)
             f = hg.openpath(ui, backupfile)
             gen = exchange.readbundle(ui, f, backupfile)
             changegroup.addchangegroup(repo, gen, 'histedit',
                                        'bundle:' + backupfile)
             os.remove(backupfile)
 
         # check whether we should update away
         parentnodes = [c.node() for c in repo[None].parents()]
         for n in leafs | set([state.parentctxnode]):
             if n in parentnodes:
                 hg.clean(repo, state.topmost)
                 break
         else:
             pass
         cleanupnode(ui, repo, 'created', tmpnodes)
         cleanupnode(ui, repo, 'temp', leafs)
         state.clear()
         return
     else:
         cmdutil.checkunfinished(repo)
         cmdutil.bailifchanged(repo)
 
         topmost, empty = repo.dirstate.parents()
         if outg:
             if freeargs:
                 remote = freeargs[0]
             else:
                 remote = None
             root = findoutgoing(ui, repo, remote, force, opts)
         else:
             rr = list(repo.set('roots(%ld)', scmutil.revrange(repo, revs)))
             if len(rr) != 1:
                 raise util.Abort(_('The specified revisions must have '
                     'exactly one common root'))
             root = rr[0].node()
 
         revs = between(repo, root, topmost, state.keep)
         if not revs:
             raise util.Abort(_('%s is not an ancestor of working directory') %
                              node.short(root))
 
         ctxs = [repo[r] for r in revs]
         if not rules:
             comment = editcomment % (node.short(root), node.short(topmost))
             rules = ruleeditor(repo, ui, [['pick', c] for c in ctxs], comment)
         else:
             if rules == '-':
                 f = sys.stdin
             else:
                 f = open(rules)
             rules = f.read()
             f.close()
         rules = [l for l in (r.strip() for r in rules.splitlines())
                  if l and not l.startswith('#')]
         rules = verifyrules(rules, repo, ctxs)
 
         parentctxnode = repo[root].parents()[0].node()
 
         state.parentctxnode = parentctxnode
         state.rules = rules
         state.topmost = topmost
         state.replacements = replacements
 
         # Create a backup so we can always abort completely.
         backupfile = None
         if not obsolete.isenabled(repo, obsolete.createmarkersopt):
             backupfile = repair._bundle(repo, [parentctxnode], [topmost], root,
                                         'histedit')
         state.backupfile = backupfile
 
     while state.rules:
         state.write()
         action, ha = state.rules.pop(0)
         ui.debug('histedit: processing %s %s\n' % (action, ha[:12]))
         actobj = actiontable[action].fromrule(state, ha)
         parentctx, replacement_ = actobj.run()
         state.parentctxnode = parentctx.node()
         state.replacements.extend(replacement_)
     state.write()
 
     hg.update(repo, state.parentctxnode)
 
     mapping, tmpnodes, created, ntm = processreplacement(state)
     if mapping:
         for prec, succs in mapping.iteritems():
             if not succs:
                 ui.debug('histedit: %s is dropped\n' % node.short(prec))
             else:
                 ui.debug('histedit: %s is replaced by %s\n' % (
                     node.short(prec), node.short(succs[0])))
                 if len(succs) > 1:
                     m = 'histedit:                            %s'
                     for n in succs[1:]:
                         ui.debug(m % node.short(n))
 
     if not state.keep:
         if mapping:
             movebookmarks(ui, repo, mapping, state.topmost, ntm)
             # TODO update mq state
         if obsolete.isenabled(repo, obsolete.createmarkersopt):
             markers = []
             # sort by revision number because it sound "right"
             for prec in sorted(mapping, key=repo.changelog.rev):
                 succs = mapping[prec]
                 markers.append((repo[prec],
                                 tuple(repo[s] for s in succs)))
             if markers:
                 obsolete.createmarkers(repo, markers)
         else:
             cleanupnode(ui, repo, 'replaced', mapping)
 
     cleanupnode(ui, repo, 'temp', tmpnodes)
     state.clear()
     if os.path.exists(repo.sjoin('undo')):
         os.unlink(repo.sjoin('undo'))
 
 def bootstrapcontinue(ui, state, opts):
     repo = state.repo
     if state.rules:
         action, currentnode = state.rules.pop(0)
 
         actobj = actiontable[action].fromrule(state, currentnode)
 
         s = repo.status()
         if s.modified or s.added or s.removed or s.deleted:
             actobj.continuedirty()
             s = repo.status()
             if s.modified or s.added or s.removed or s.deleted:
                 raise util.Abort(_("working copy still dirty"))
 
         parentctx, replacements = actobj.continueclean()
 
         state.parentctxnode = parentctx.node()
         state.replacements.extend(replacements)
 
     return state
 
 def between(repo, old, new, keep):
     """select and validate the set of revision to edit
 
     When keep is false, the specified set can't have children."""
     ctxs = list(repo.set('%n::%n', old, new))
     if ctxs and not keep:
         if (not obsolete.isenabled(repo, obsolete.allowunstableopt) and
             repo.revs('(%ld::) - (%ld)', ctxs, ctxs)):
             raise util.Abort(_('cannot edit history that would orphan nodes'))
         if repo.revs('(%ld) and merge()', ctxs):
             raise util.Abort(_('cannot edit history that contains merges'))
         root = ctxs[0] # list is already sorted by repo.set
         if not root.mutable():
             raise util.Abort(_('cannot edit public changeset: %s') % root,
                              hint=_('see "hg help phases" for details'))
     return [c.node() for c in ctxs]
 
 def makedesc(repo, action, rev):
     """build a initial action line for a ctx
 
     line are in the form:
 
       <action> <hash> <rev> <summary>
     """
     ctx = repo[rev]
     summary = ''
     if ctx.description():
         summary = ctx.description().splitlines()[0]
     line = '%s %s %d %s' % (action, ctx, ctx.rev(), summary)
     # trim to 80 columns so it's not stupidly wide in my editor
     maxlen = repo.ui.configint('histedit', 'linelen', default=80)
     maxlen = max(maxlen, 22) # avoid truncating hash
     return util.ellipsis(line, maxlen)
 
 def ruleeditor(repo, ui, rules, editcomment=""):
     """open an editor to edit rules
 
     rules are in the format [ [act, ctx], ...] like in state.rules
     """
     rules = '\n'.join([makedesc(repo, act, rev) for [act, rev] in rules])
     rules += '\n\n'
     rules += editcomment
     rules = ui.edit(rules, ui.username())
 
     # Save edit rules in .hg/histedit-last-edit.txt in case
     # the user needs to ask for help after something
     # surprising happens.
     f = open(repo.join('histedit-last-edit.txt'), 'w')
     f.write(rules)
     f.close()
 
     return rules
 
 def verifyrules(rules, repo, ctxs):
     """Verify that there exists exactly one edit rule per given changeset.
 
     Will abort if there are to many or too few rules, a malformed rule,
     or a rule on a changeset outside of the user-given range.
     """
     parsed = []
     expected = set(c.hex() for c in ctxs)
     seen = set()
     for r in rules:
         if ' ' not in r:
             raise util.Abort(_('malformed line "%s"') % r)
         action, rest = r.split(' ', 1)
         ha = rest.strip().split(' ', 1)[0]
         try:
             ha = repo[ha].hex()
         except error.RepoError:
             raise util.Abort(_('unknown changeset %s listed') % ha[:12])
         if ha not in expected:
             raise util.Abort(
                 _('may not use changesets other than the ones listed'))
         if ha in seen:
             raise util.Abort(_('duplicated command for changeset %s') %
                     ha[:12])
         seen.add(ha)
         if action not in actiontable:
             raise util.Abort(_('unknown action "%s"') % action)
         parsed.append([action, ha])
     missing = sorted(expected - seen)  # sort to stabilize output
     if missing:
         raise util.Abort(_('missing rules for changeset %s') %
                 missing[0][:12],
                 hint=_('do you want to use the drop action?'))
     return parsed
 
 def processreplacement(state):
     """process the list of replacements to return
 
     1) the final mapping between original and created nodes
     2) the list of temporary node created by histedit
     3) the list of new commit created by histedit"""
     replacements = state.replacements
     allsuccs = set()
     replaced = set()
     fullmapping = {}
     # initialise basic set
     # fullmapping record all operation recorded in replacement
     for rep in replacements:
         allsuccs.update(rep[1])
         replaced.add(rep[0])
         fullmapping.setdefault(rep[0], set()).update(rep[1])
     new = allsuccs - replaced
     tmpnodes = allsuccs & replaced
     # Reduce content fullmapping  into direct relation between original nodes
     # and final node created during history edition
     # Dropped changeset are replaced by an empty list
     toproceed = set(fullmapping)
     final = {}
     while toproceed:
         for x in list(toproceed):
             succs = fullmapping[x]
             for s in list(succs):
                 if s in toproceed:
                     # non final node with unknown closure
                     # We can't process this now
                     break
                 elif s in final:
                     # non final node, replace with closure
                     succs.remove(s)
                     succs.update(final[s])
             else:
                 final[x] = succs
                 toproceed.remove(x)
     # remove tmpnodes from final mapping
     for n in tmpnodes:
         del final[n]
     # we expect all changes involved in final to exist in the repo
     # turn `final` into list (topologically sorted)
     nm = state.repo.changelog.nodemap
     for prec, succs in final.items():
         final[prec] = sorted(succs, key=nm.get)
 
     # computed topmost element (necessary for bookmark)
     if new:
         newtopmost = sorted(new, key=state.repo.changelog.rev)[-1]
     elif not final:
         # Nothing rewritten at all. we won't need `newtopmost`
         # It is the same as `oldtopmost` and `processreplacement` know it
         newtopmost = None
     else:
         # every body died. The newtopmost is the parent of the root.
         r = state.repo.changelog.rev
         newtopmost = state.repo[sorted(final, key=r)[0]].p1().node()
 
     return final, tmpnodes, new, newtopmost
 
 def movebookmarks(ui, repo, mapping, oldtopmost, newtopmost):
     """Move bookmark from old to newly created node"""
     if not mapping:
         # if nothing got rewritten there is not purpose for this function
         return
     moves = []
     for bk, old in sorted(repo._bookmarks.iteritems()):
         if old == oldtopmost:
             # special case ensure bookmark stay on tip.
             #
             # This is arguably a feature and we may only want that for the
             # active bookmark. But the behavior is kept compatible with the old
             # version for now.
             moves.append((bk, newtopmost))
             continue
         base = old
         new = mapping.get(base, None)
         if new is None:
             continue
         while not new:
             # base is killed, trying with parent
             base = repo[base].p1().node()
             new = mapping.get(base, (base,))
             # nothing to move
         moves.append((bk, new[-1]))
     if moves:
         marks = repo._bookmarks
         for mark, new in moves:
             old = marks[mark]
             ui.note(_('histedit: moving bookmarks %s from %s to %s\n')
                     % (mark, node.short(old), node.short(new)))
             marks[mark] = new
         marks.write()
 
 def cleanupnode(ui, repo, name, nodes):
     """strip a group of nodes from the repository
 
     The set of node to strip may contains unknown nodes."""
     ui.debug('should strip %s nodes %s\n' %
              (name, ', '.join([node.short(n) for n in nodes])))
     lock = None
     try:
         lock = repo.lock()
         # Find all node that need to be stripped
         # (we hg %lr instead of %ln to silently ignore unknown item
         nm = repo.changelog.nodemap
         nodes = sorted(n for n in nodes if n in nm)
         roots = [c.node() for c in repo.set("roots(%ln)", nodes)]
         for c in roots:
             # We should process node in reverse order to strip tip most first.
             # but this trigger a bug in changegroup hook.
             # This would reduce bundle overhead
             repair.strip(ui, repo, c)
     finally:
         release(lock)
 
 def stripwrapper(orig, ui, repo, nodelist, *args, **kwargs):
     if isinstance(nodelist, str):
         nodelist = [nodelist]
     if os.path.exists(os.path.join(repo.path, 'histedit-state')):
         state = histeditstate(repo)
         state.read()
         histedit_nodes = set([repo[rulehash].node() for (action, rulehash)
                              in state.rules if rulehash in repo])
         strip_nodes = set([repo[n].node() for n in nodelist])
         common_nodes = histedit_nodes & strip_nodes
         if common_nodes:
             raise util.Abort(_("histedit in progress, can't strip %s")
                              % ', '.join(node.short(x) for x in common_nodes))
     return orig(ui, repo, nodelist, *args, **kwargs)
 
 extensions.wrapfunction(repair, 'strip', stripwrapper)
 
 def summaryhook(ui, repo):
     if not os.path.exists(repo.join('histedit-state')):
         return
     state = histeditstate(repo)
     state.read()
     if state.rules:
         # i18n: column positioning for "hg summary"
         ui.write(_('hist:   %s (histedit --continue)\n') %
                  (ui.label(_('%d remaining'), 'histedit.remaining') %
                   len(state.rules)))
 
 def extsetup(ui):
     cmdutil.summaryhooks.add('histedit', summaryhook)
     cmdutil.unfinishedstates.append(
         ['histedit-state', False, True, _('histedit in progress'),
          _("use 'hg histedit --continue' or 'hg histedit --abort'")])

hgext/largefiles/basestore.py

@@ -1,221 +1,221 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''base class for store implementations and store-related utility code'''
 
 import re
 
 from mercurial import util, node, hg
 from mercurial.i18n import _
 
 import lfutil
 
 class StoreError(Exception):
     '''Raised when there is a problem getting files from or putting
     files to a central store.'''
     def __init__(self, filename, hash, url, detail):
         self.filename = filename
         self.hash = hash
         self.url = url
         self.detail = detail
 
     def longmessage(self):
         return (_("error getting id %s from url %s for file %s: %s\n") %
                  (self.hash, util.hidepassword(self.url), self.filename,
                   self.detail))
 
     def __str__(self):
         return "%s: %s" % (util.hidepassword(self.url), self.detail)
 
 class basestore(object):
     def __init__(self, ui, repo, url):
         self.ui = ui
         self.repo = repo
         self.url = url
 
     def put(self, source, hash):
         '''Put source file into the store so it can be retrieved by hash.'''
         raise NotImplementedError('abstract method')
 
     def exists(self, hashes):
         '''Check to see if the store contains the given hashes. Given an
         iterable of hashes it returns a mapping from hash to bool.'''
         raise NotImplementedError('abstract method')
 
     def get(self, files):
         '''Get the specified largefiles from the store and write to local
         files under repo.root.  files is a list of (filename, hash)
         tuples.  Return (success, missing), lists of files successfully
         downloaded and those not found in the store.  success is a list
         of (filename, hash) tuples; missing is a list of filenames that
         we could not get.  (The detailed error message will already have
         been presented to the user, so missing is just supplied as a
         summary.)'''
         success = []
         missing = []
         ui = self.ui
 
         at = 0
         available = self.exists(set(hash for (_filename, hash) in files))
         for filename, hash in files:
             ui.progress(_('getting largefiles'), at, unit='lfile',
                 total=len(files))
             at += 1
             ui.note(_('getting %s:%s\n') % (filename, hash))
 
             if not available.get(hash):
                 ui.warn(_('%s: largefile %s not available from %s\n')
                         % (filename, hash, util.hidepassword(self.url)))
                 missing.append(filename)
                 continue
 
             if self._gethash(filename, hash):
                 success.append((filename, hash))
             else:
                 missing.append(filename)
 
         ui.progress(_('getting largefiles'), None)
         return (success, missing)
 
     def _gethash(self, filename, hash):
         """Get file with the provided hash and store it in the local repo's
         store and in the usercache.
         filename is for informational messages only.
         """
         util.makedirs(lfutil.storepath(self.repo, ''))
         storefilename = lfutil.storepath(self.repo, hash)
 
         tmpname = storefilename + '.tmp'
         tmpfile = util.atomictempfile(tmpname,
                                       createmode=self.repo.store.createmode)
 
         try:
             gothash = self._getfile(tmpfile, filename, hash)
-        except StoreError, err:
+        except StoreError as err:
             self.ui.warn(err.longmessage())
             gothash = ""
         tmpfile.close()
 
         if gothash != hash:
             if gothash != "":
                 self.ui.warn(_('%s: data corruption (expected %s, got %s)\n')
                              % (filename, hash, gothash))
             util.unlink(tmpname)
             return False
 
         util.rename(tmpname, storefilename)
         lfutil.linktousercache(self.repo, hash)
         return True
 
     def verify(self, revs, contents=False):
         '''Verify the existence (and, optionally, contents) of every big
         file revision referenced by every changeset in revs.
         Return 0 if all is well, non-zero on any errors.'''
         failed = False
 
         self.ui.status(_('searching %d changesets for largefiles\n') %
                        len(revs))
         verified = set()                # set of (filename, filenode) tuples
 
         for rev in revs:
             cctx = self.repo[rev]
             cset = "%d:%s" % (cctx.rev(), node.short(cctx.node()))
 
             for standin in cctx:
                 if self._verifyfile(cctx, cset, contents, standin, verified):
                     failed = True
 
         numrevs = len(verified)
         numlfiles = len(set([fname for (fname, fnode) in verified]))
         if contents:
             self.ui.status(
                 _('verified contents of %d revisions of %d largefiles\n')
                 % (numrevs, numlfiles))
         else:
             self.ui.status(
                 _('verified existence of %d revisions of %d largefiles\n')
                 % (numrevs, numlfiles))
         return int(failed)
 
     def _getfile(self, tmpfile, filename, hash):
         '''Fetch one revision of one file from the store and write it
         to tmpfile.  Compute the hash of the file on-the-fly as it
         downloads and return the hash.  Close tmpfile.  Raise
         StoreError if unable to download the file (e.g. it does not
         exist in the store).'''
         raise NotImplementedError('abstract method')
 
     def _verifyfile(self, cctx, cset, contents, standin, verified):
         '''Perform the actual verification of a file in the store.
         'cset' is only used in warnings.
         'contents' controls verification of content hash.
         'standin' is the standin path of the largefile to verify.
         'verified' is maintained as a set of already verified files.
         Returns _true_ if it is a standin and any problems are found!
         '''
         raise NotImplementedError('abstract method')
 
 import localstore, wirestore
 
 _storeprovider = {
     'file':  [localstore.localstore],
     'http':  [wirestore.wirestore],
     'https': [wirestore.wirestore],
     'ssh': [wirestore.wirestore],
     }
 
 _scheme_re = re.compile(r'^([a-zA-Z0-9+-.]+)://')
 
 # During clone this function is passed the src's ui object
 # but it needs the dest's ui object so it can read out of
 # the config file. Use repo.ui instead.
 def _openstore(repo, remote=None, put=False):
     ui = repo.ui
 
     if not remote:
         lfpullsource = getattr(repo, 'lfpullsource', None)
         if lfpullsource:
             path = ui.expandpath(lfpullsource)
         elif put:
             path = ui.expandpath('default-push', 'default')
         else:
             path = ui.expandpath('default')
 
         # ui.expandpath() leaves 'default-push' and 'default' alone if
         # they cannot be expanded: fallback to the empty string,
         # meaning the current directory.
         if path == 'default-push' or path == 'default':
             path = ''
             remote = repo
         else:
             path, _branches = hg.parseurl(path)
             remote = hg.peer(repo, {}, path)
 
     # The path could be a scheme so use Mercurial's normal functionality
     # to resolve the scheme to a repository and use its path
     path = util.safehasattr(remote, 'url') and remote.url() or remote.path
 
     match = _scheme_re.match(path)
     if not match:                       # regular filesystem path
         scheme = 'file'
     else:
         scheme = match.group(1)
 
     try:
         storeproviders = _storeprovider[scheme]
     except KeyError:
         raise util.Abort(_('unsupported URL scheme %r') % scheme)
 
     for classobj in storeproviders:
         try:
             return classobj(ui, repo, remote)
         except lfutil.storeprotonotcapable:
             pass
 
     raise util.Abort(_('%s does not appear to be a largefile store') %
                      util.hidepassword(path))

hgext/largefiles/lfcommands.py

@@ -1,550 +1,550 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''High-level command function for lfconvert, plus the cmdtable.'''
 
 import os, errno
 import shutil
 
 from mercurial import util, match as match_, hg, node, context, error, \
     cmdutil, scmutil, commands
 from mercurial.i18n import _
 from mercurial.lock import release
 
 from hgext.convert import convcmd
 from hgext.convert import filemap
 
 import lfutil
 import basestore
 
 # -- Commands ----------------------------------------------------------
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 @command('lfconvert',
     [('s', 'size', '',
       _('minimum size (MB) for files to be converted as largefiles'), 'SIZE'),
     ('', 'to-normal', False,
      _('convert from a largefiles repo to a normal repo')),
     ],
     _('hg lfconvert SOURCE DEST [FILE ...]'),
     norepo=True,
     inferrepo=True)
 def lfconvert(ui, src, dest, *pats, **opts):
     '''convert a normal repository to a largefiles repository
 
     Convert repository SOURCE to a new repository DEST, identical to
     SOURCE except that certain files will be converted as largefiles:
     specifically, any file that matches any PATTERN *or* whose size is
     above the minimum size threshold is converted as a largefile. The
     size used to determine whether or not to track a file as a
     largefile is the size of the first version of the file. The
     minimum size can be specified either with --size or in
     configuration as ``largefiles.size``.
 
     After running this command you will need to make sure that
     largefiles is enabled anywhere you intend to push the new
     repository.
 
     Use --to-normal to convert largefiles back to normal files; after
     this, the DEST repository can be used without largefiles at all.'''
 
     if opts['to_normal']:
         tolfile = False
     else:
         tolfile = True
         size = lfutil.getminsize(ui, True, opts.get('size'), default=None)
 
     if not hg.islocal(src):
         raise util.Abort(_('%s is not a local Mercurial repo') % src)
     if not hg.islocal(dest):
         raise util.Abort(_('%s is not a local Mercurial repo') % dest)
 
     rsrc = hg.repository(ui, src)
     ui.status(_('initializing destination %s\n') % dest)
     rdst = hg.repository(ui, dest, create=True)
 
     success = False
     dstwlock = dstlock = None
     try:
         # Get a list of all changesets in the source.  The easy way to do this
         # is to simply walk the changelog, using changelog.nodesbetween().
         # Take a look at mercurial/revlog.py:639 for more details.
         # Use a generator instead of a list to decrease memory usage
         ctxs = (rsrc[ctx] for ctx in rsrc.changelog.nodesbetween(None,
             rsrc.heads())[0])
         revmap = {node.nullid: node.nullid}
         if tolfile:
             # Lock destination to prevent modification while it is converted to.
             # Don't need to lock src because we are just reading from its
             # history which can't change.
             dstwlock = rdst.wlock()
             dstlock = rdst.lock()
 
             lfiles = set()
             normalfiles = set()
             if not pats:
                 pats = ui.configlist(lfutil.longname, 'patterns', default=[])
             if pats:
                 matcher = match_.match(rsrc.root, '', list(pats))
             else:
                 matcher = None
 
             lfiletohash = {}
             for ctx in ctxs:
                 ui.progress(_('converting revisions'), ctx.rev(),
                     unit=_('revision'), total=rsrc['tip'].rev())
                 _lfconvert_addchangeset(rsrc, rdst, ctx, revmap,
                     lfiles, normalfiles, matcher, size, lfiletohash)
             ui.progress(_('converting revisions'), None)
 
             if os.path.exists(rdst.wjoin(lfutil.shortname)):
                 shutil.rmtree(rdst.wjoin(lfutil.shortname))
 
             for f in lfiletohash.keys():
                 if os.path.isfile(rdst.wjoin(f)):
                     os.unlink(rdst.wjoin(f))
                 try:
                     os.removedirs(os.path.dirname(rdst.wjoin(f)))
                 except OSError:
                     pass
 
             # If there were any files converted to largefiles, add largefiles
             # to the destination repository's requirements.
             if lfiles:
                 rdst.requirements.add('largefiles')
                 rdst._writerequirements()
         else:
             class lfsource(filemap.filemap_source):
                 def __init__(self, ui, source):
                     super(lfsource, self).__init__(ui, source, None)
                     self.filemapper.rename[lfutil.shortname] = '.'
 
                 def getfile(self, name, rev):
                     realname, realrev = rev
                     f = super(lfsource, self).getfile(name, rev)
 
                     if (not realname.startswith(lfutil.shortnameslash)
                             or f[0] is None):
                         return f
 
                     # Substitute in the largefile data for the hash
                     hash = f[0].strip()
                     path = lfutil.findfile(rsrc, hash)
 
                     if path is None:
                         raise util.Abort(_("missing largefile for \'%s\' in %s")
                                           % (realname, realrev))
                     fp = open(path, 'rb')
 
                     try:
                         return (fp.read(), f[1])
                     finally:
                         fp.close()
 
             class converter(convcmd.converter):
                 def __init__(self, ui, source, dest, revmapfile, opts):
                     src = lfsource(ui, source)
 
                     super(converter, self).__init__(ui, src, dest, revmapfile,
                                                     opts)
 
             found, missing = downloadlfiles(ui, rsrc)
             if missing != 0:
                 raise util.Abort(_("all largefiles must be present locally"))
 
             orig = convcmd.converter
             convcmd.converter = converter
 
             try:
                 convcmd.convert(ui, src, dest)
             finally:
                 convcmd.converter = orig
         success = True
     finally:
         if tolfile:
             rdst.dirstate.clear()
             release(dstlock, dstwlock)
         if not success:
             # we failed, remove the new directory
             shutil.rmtree(rdst.root)
 
 def _lfconvert_addchangeset(rsrc, rdst, ctx, revmap, lfiles, normalfiles,
         matcher, size, lfiletohash):
     # Convert src parents to dst parents
     parents = _convertparents(ctx, revmap)
 
     # Generate list of changed files
     files = _getchangedfiles(ctx, parents)
 
     dstfiles = []
     for f in files:
         if f not in lfiles and f not in normalfiles:
             islfile = _islfile(f, ctx, matcher, size)
             # If this file was renamed or copied then copy
             # the largefile-ness of its predecessor
             if f in ctx.manifest():
                 fctx = ctx.filectx(f)
                 renamed = fctx.renamed()
                 renamedlfile = renamed and renamed[0] in lfiles
                 islfile |= renamedlfile
                 if 'l' in fctx.flags():
                     if renamedlfile:
                         raise util.Abort(
                             _('renamed/copied largefile %s becomes symlink')
                             % f)
                     islfile = False
             if islfile:
                 lfiles.add(f)
             else:
                 normalfiles.add(f)
 
         if f in lfiles:
             dstfiles.append(lfutil.standin(f))
             # largefile in manifest if it has not been removed/renamed
             if f in ctx.manifest():
                 fctx = ctx.filectx(f)
                 if 'l' in fctx.flags():
                     renamed = fctx.renamed()
                     if renamed and renamed[0] in lfiles:
                         raise util.Abort(_('largefile %s becomes symlink') % f)
 
                 # largefile was modified, update standins
                 m = util.sha1('')
                 m.update(ctx[f].data())
                 hash = m.hexdigest()
                 if f not in lfiletohash or lfiletohash[f] != hash:
                     rdst.wwrite(f, ctx[f].data(), ctx[f].flags())
                     executable = 'x' in ctx[f].flags()
                     lfutil.writestandin(rdst, lfutil.standin(f), hash,
                         executable)
                     lfiletohash[f] = hash
         else:
             # normal file
             dstfiles.append(f)
 
     def getfilectx(repo, memctx, f):
         if lfutil.isstandin(f):
             # if the file isn't in the manifest then it was removed
             # or renamed, raise IOError to indicate this
             srcfname = lfutil.splitstandin(f)
             try:
                 fctx = ctx.filectx(srcfname)
             except error.LookupError:
                 return None
             renamed = fctx.renamed()
             if renamed:
                 # standin is always a largefile because largefile-ness
                 # doesn't change after rename or copy
                 renamed = lfutil.standin(renamed[0])
 
             return context.memfilectx(repo, f, lfiletohash[srcfname] + '\n',
                                       'l' in fctx.flags(), 'x' in fctx.flags(),
                                       renamed)
         else:
             return _getnormalcontext(repo, ctx, f, revmap)
 
     # Commit
     _commitcontext(rdst, parents, ctx, dstfiles, getfilectx, revmap)
 
 def _commitcontext(rdst, parents, ctx, dstfiles, getfilectx, revmap):
     mctx = context.memctx(rdst, parents, ctx.description(), dstfiles,
                           getfilectx, ctx.user(), ctx.date(), ctx.extra())
     ret = rdst.commitctx(mctx)
     lfutil.copyalltostore(rdst, ret)
     rdst.setparents(ret)
     revmap[ctx.node()] = rdst.changelog.tip()
 
 # Generate list of changed files
 def _getchangedfiles(ctx, parents):
     files = set(ctx.files())
     if node.nullid not in parents:
         mc = ctx.manifest()
         mp1 = ctx.parents()[0].manifest()
         mp2 = ctx.parents()[1].manifest()
         files |= (set(mp1) | set(mp2)) - set(mc)
         for f in mc:
             if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                 files.add(f)
     return files
 
 # Convert src parents to dst parents
 def _convertparents(ctx, revmap):
     parents = []
     for p in ctx.parents():
         parents.append(revmap[p.node()])
     while len(parents) < 2:
         parents.append(node.nullid)
     return parents
 
 # Get memfilectx for a normal file
 def _getnormalcontext(repo, ctx, f, revmap):
     try:
         fctx = ctx.filectx(f)
     except error.LookupError:
         return None
     renamed = fctx.renamed()
     if renamed:
         renamed = renamed[0]
 
     data = fctx.data()
     if f == '.hgtags':
         data = _converttags (repo.ui, revmap, data)
     return context.memfilectx(repo, f, data, 'l' in fctx.flags(),
                               'x' in fctx.flags(), renamed)
 
 # Remap tag data using a revision map
 def _converttags(ui, revmap, data):
     newdata = []
     for line in data.splitlines():
         try:
             id, name = line.split(' ', 1)
         except ValueError:
             ui.warn(_('skipping incorrectly formatted tag %s\n')
                 % line)
             continue
         try:
             newid = node.bin(id)
         except TypeError:
             ui.warn(_('skipping incorrectly formatted id %s\n')
                 % id)
             continue
         try:
             newdata.append('%s %s\n' % (node.hex(revmap[newid]),
                 name))
         except KeyError:
             ui.warn(_('no mapping for id %s\n') % id)
             continue
     return ''.join(newdata)
 
 def _islfile(file, ctx, matcher, size):
     '''Return true if file should be considered a largefile, i.e.
     matcher matches it or it is larger than size.'''
     # never store special .hg* files as largefiles
     if file == '.hgtags' or file == '.hgignore' or file == '.hgsigs':
         return False
     if matcher and matcher(file):
         return True
     try:
         return ctx.filectx(file).size() >= size * 1024 * 1024
     except error.LookupError:
         return False
 
 def uploadlfiles(ui, rsrc, rdst, files):
     '''upload largefiles to the central store'''
 
     if not files:
         return
 
     store = basestore._openstore(rsrc, rdst, put=True)
 
     at = 0
     ui.debug("sending statlfile command for %d largefiles\n" % len(files))
     retval = store.exists(files)
     files = filter(lambda h: not retval[h], files)
     ui.debug("%d largefiles need to be uploaded\n" % len(files))
 
     for hash in files:
         ui.progress(_('uploading largefiles'), at, unit='largefile',
                     total=len(files))
         source = lfutil.findfile(rsrc, hash)
         if not source:
             raise util.Abort(_('largefile %s missing from store'
                                ' (needs to be uploaded)') % hash)
         # XXX check for errors here
         store.put(source, hash)
         at += 1
     ui.progress(_('uploading largefiles'), None)
 
 def verifylfiles(ui, repo, all=False, contents=False):
     '''Verify that every largefile revision in the current changeset
     exists in the central store.  With --contents, also verify that
     the contents of each local largefile file revision are correct (SHA-1 hash
     matches the revision ID).  With --all, check every changeset in
     this repository.'''
     if all:
         revs = repo.revs('all()')
     else:
         revs = ['.']
 
     store = basestore._openstore(repo)
     return store.verify(revs, contents=contents)
 
 def cachelfiles(ui, repo, node, filelist=None):
     '''cachelfiles ensures that all largefiles needed by the specified revision
     are present in the repository's largefile cache.
 
     returns a tuple (cached, missing).  cached is the list of files downloaded
     by this operation; missing is the list of files that were needed but could
     not be found.'''
     lfiles = lfutil.listlfiles(repo, node)
     if filelist:
         lfiles = set(lfiles) & set(filelist)
     toget = []
 
     for lfile in lfiles:
         try:
             expectedhash = repo[node][lfutil.standin(lfile)].data().strip()
-        except IOError, err:
+        except IOError as err:
             if err.errno == errno.ENOENT:
                 continue # node must be None and standin wasn't found in wctx
             raise
         if not lfutil.findfile(repo, expectedhash):
             toget.append((lfile, expectedhash))
 
     if toget:
         store = basestore._openstore(repo)
         ret = store.get(toget)
         return ret
 
     return ([], [])
 
 def downloadlfiles(ui, repo, rev=None):
     matchfn = scmutil.match(repo[None],
                             [repo.wjoin(lfutil.shortname)], {})
     def prepare(ctx, fns):
         pass
     totalsuccess = 0
     totalmissing = 0
     if rev != []: # walkchangerevs on empty list would return all revs
         for ctx in cmdutil.walkchangerevs(repo, matchfn, {'rev' : rev},
                                           prepare):
             success, missing = cachelfiles(ui, repo, ctx.node())
             totalsuccess += len(success)
             totalmissing += len(missing)
     ui.status(_("%d additional largefiles cached\n") % totalsuccess)
     if totalmissing > 0:
         ui.status(_("%d largefiles failed to download\n") % totalmissing)
     return totalsuccess, totalmissing
 
 def updatelfiles(ui, repo, filelist=None, printmessage=None,
                  normallookup=False):
     '''Update largefiles according to standins in the working directory
 
     If ``printmessage`` is other than ``None``, it means "print (or
     ignore, for false) message forcibly".
     '''
     statuswriter = lfutil.getstatuswriter(ui, repo, printmessage)
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         lfiles = set(lfutil.listlfiles(repo)) | set(lfdirstate)
 
         if filelist is not None:
             filelist = set(filelist)
             lfiles = [f for f in lfiles if f in filelist]
 
         update = {}
         updated, removed = 0, 0
         for lfile in lfiles:
             abslfile = repo.wjoin(lfile)
             absstandin = repo.wjoin(lfutil.standin(lfile))
             if os.path.exists(absstandin):
                 if (os.path.exists(absstandin + '.orig') and
                     os.path.exists(abslfile)):
                     shutil.copyfile(abslfile, abslfile + '.orig')
                     util.unlinkpath(absstandin + '.orig')
                 expecthash = lfutil.readstandin(repo, lfile)
                 if expecthash != '':
                     if lfile not in repo[None]: # not switched to normal file
                         util.unlinkpath(abslfile, ignoremissing=True)
                     # use normallookup() to allocate an entry in largefiles
                     # dirstate to prevent lfilesrepo.status() from reporting
                     # missing files as removed.
                     lfdirstate.normallookup(lfile)
                     update[lfile] = expecthash
             else:
                 # Remove lfiles for which the standin is deleted, unless the
                 # lfile is added to the repository again. This happens when a
                 # largefile is converted back to a normal file: the standin
                 # disappears, but a new (normal) file appears as the lfile.
                 if (os.path.exists(abslfile) and
                     repo.dirstate.normalize(lfile) not in repo[None]):
                     util.unlinkpath(abslfile)
                     removed += 1
 
         # largefile processing might be slow and be interrupted - be prepared
         lfdirstate.write()
 
         if lfiles:
             statuswriter(_('getting changed largefiles\n'))
             cachelfiles(ui, repo, None, lfiles)
 
         for lfile in lfiles:
             update1 = 0
 
             expecthash = update.get(lfile)
             if expecthash:
                 if not lfutil.copyfromcache(repo, expecthash, lfile):
                     # failed ... but already removed and set to normallookup
                     continue
                 # Synchronize largefile dirstate to the last modified
                 # time of the file
                 lfdirstate.normal(lfile)
                 update1 = 1
 
             # copy the state of largefile standin from the repository's
             # dirstate to its state in the lfdirstate.
             abslfile = repo.wjoin(lfile)
             absstandin = repo.wjoin(lfutil.standin(lfile))
             if os.path.exists(absstandin):
                 mode = os.stat(absstandin).st_mode
                 if mode != os.stat(abslfile).st_mode:
                     os.chmod(abslfile, mode)
                     update1 = 1
 
             updated += update1
 
             lfutil.synclfdirstate(repo, lfdirstate, lfile, normallookup)
 
         lfdirstate.write()
         if lfiles:
             statuswriter(_('%d largefiles updated, %d removed\n') % (updated,
                 removed))
     finally:
         wlock.release()
 
 @command('lfpull',
     [('r', 'rev', [], _('pull largefiles for these revisions'))
     ] + commands.remoteopts,
     _('-r REV... [-e CMD] [--remotecmd CMD] [SOURCE]'))
 def lfpull(ui, repo, source="default", **opts):
     """pull largefiles for the specified revisions from the specified source
 
     Pull largefiles that are referenced from local changesets but missing
     locally, pulling from a remote repository to the local cache.
 
     If SOURCE is omitted, the 'default' path will be used.
     See :hg:`help urls` for more information.
 
     .. container:: verbose
 
       Some examples:
 
       - pull largefiles for all branch heads::
 
           hg lfpull -r "head() and not closed()"
 
       - pull largefiles on the default branch::
 
           hg lfpull -r "branch(default)"
     """
     repo.lfpullsource = source
 
     revs = opts.get('rev', [])
     if not revs:
         raise util.Abort(_('no revisions specified'))
     revs = scmutil.revrange(repo, revs)
 
     numcached = 0
     for rev in revs:
         ui.note(_('pulling largefiles for revision %s\n') % rev)
         (cached, missing) = cachelfiles(ui, repo, rev)
         numcached += len(cached)
     ui.status(_("%d largefiles cached\n") % numcached)

hgext/largefiles/overrides.py

@@ -1,1385 +1,1385 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''Overridden Mercurial commands and functions for the largefiles extension'''
 
 import os
 import copy
 
 from mercurial import hg, util, cmdutil, scmutil, match as match_, \
         archival, pathutil, revset
 from mercurial.i18n import _
 
 import lfutil
 import lfcommands
 import basestore
 
 # -- Utility functions: commonly/repeatedly needed functionality ---------------
 
 def composelargefilematcher(match, manifest):
     '''create a matcher that matches only the largefiles in the original
     matcher'''
     m = copy.copy(match)
     lfile = lambda f: lfutil.standin(f) in manifest
     m._files = filter(lfile, m._files)
     m._fileroots = set(m._files)
     m._always = False
     origmatchfn = m.matchfn
     m.matchfn = lambda f: lfile(f) and origmatchfn(f)
     return m
 
 def composenormalfilematcher(match, manifest, exclude=None):
     excluded = set()
     if exclude is not None:
         excluded.update(exclude)
 
     m = copy.copy(match)
     notlfile = lambda f: not (lfutil.isstandin(f) or lfutil.standin(f) in
             manifest or f in excluded)
     m._files = filter(notlfile, m._files)
     m._fileroots = set(m._files)
     m._always = False
     origmatchfn = m.matchfn
     m.matchfn = lambda f: notlfile(f) and origmatchfn(f)
     return m
 
 def installnormalfilesmatchfn(manifest):
     '''installmatchfn with a matchfn that ignores all largefiles'''
     def overridematch(ctx, pats=[], opts={}, globbed=False,
             default='relpath', badfn=None):
         match = oldmatch(ctx, pats, opts, globbed, default, badfn=badfn)
         return composenormalfilematcher(match, manifest)
     oldmatch = installmatchfn(overridematch)
 
 def installmatchfn(f):
     '''monkey patch the scmutil module with a custom match function.
     Warning: it is monkey patching the _module_ on runtime! Not thread safe!'''
     oldmatch = scmutil.match
     setattr(f, 'oldmatch', oldmatch)
     scmutil.match = f
     return oldmatch
 
 def restorematchfn():
     '''restores scmutil.match to what it was before installmatchfn
     was called.  no-op if scmutil.match is its original function.
 
     Note that n calls to installmatchfn will require n calls to
     restore the original matchfn.'''
     scmutil.match = getattr(scmutil.match, 'oldmatch')
 
 def installmatchandpatsfn(f):
     oldmatchandpats = scmutil.matchandpats
     setattr(f, 'oldmatchandpats', oldmatchandpats)
     scmutil.matchandpats = f
     return oldmatchandpats
 
 def restorematchandpatsfn():
     '''restores scmutil.matchandpats to what it was before
     installmatchandpatsfn was called. No-op if scmutil.matchandpats
     is its original function.
 
     Note that n calls to installmatchandpatsfn will require n calls
     to restore the original matchfn.'''
     scmutil.matchandpats = getattr(scmutil.matchandpats, 'oldmatchandpats',
             scmutil.matchandpats)
 
 def addlargefiles(ui, repo, isaddremove, matcher, **opts):
     large = opts.get('large')
     lfsize = lfutil.getminsize(
         ui, lfutil.islfilesrepo(repo), opts.get('lfsize'))
 
     lfmatcher = None
     if lfutil.islfilesrepo(repo):
         lfpats = ui.configlist(lfutil.longname, 'patterns', default=[])
         if lfpats:
             lfmatcher = match_.match(repo.root, '', list(lfpats))
 
     lfnames = []
     m = matcher
 
     wctx = repo[None]
     for f in repo.walk(match_.badmatch(m, lambda x, y: None)):
         exact = m.exact(f)
         lfile = lfutil.standin(f) in wctx
         nfile = f in wctx
         exists = lfile or nfile
 
         # addremove in core gets fancy with the name, add doesn't
         if isaddremove:
             name = m.uipath(f)
         else:
             name = m.rel(f)
 
         # Don't warn the user when they attempt to add a normal tracked file.
         # The normal add code will do that for us.
         if exact and exists:
             if lfile:
                 ui.warn(_('%s already a largefile\n') % name)
             continue
 
         if (exact or not exists) and not lfutil.isstandin(f):
             # In case the file was removed previously, but not committed
             # (issue3507)
             if not repo.wvfs.exists(f):
                 continue
 
             abovemin = (lfsize and
                         repo.wvfs.lstat(f).st_size >= lfsize * 1024 * 1024)
             if large or abovemin or (lfmatcher and lfmatcher(f)):
                 lfnames.append(f)
                 if ui.verbose or not exact:
                     ui.status(_('adding %s as a largefile\n') % name)
 
     bad = []
 
     # Need to lock, otherwise there could be a race condition between
     # when standins are created and added to the repo.
     wlock = repo.wlock()
     try:
         if not opts.get('dry_run'):
             standins = []
             lfdirstate = lfutil.openlfdirstate(ui, repo)
             for f in lfnames:
                 standinname = lfutil.standin(f)
                 lfutil.writestandin(repo, standinname, hash='',
                     executable=lfutil.getexecutable(repo.wjoin(f)))
                 standins.append(standinname)
                 if lfdirstate[f] == 'r':
                     lfdirstate.normallookup(f)
                 else:
                     lfdirstate.add(f)
             lfdirstate.write()
             bad += [lfutil.splitstandin(f)
                     for f in repo[None].add(standins)
                     if f in m.files()]
 
         added = [f for f in lfnames if f not in bad]
     finally:
         wlock.release()
     return added, bad
 
 def removelargefiles(ui, repo, isaddremove, matcher, **opts):
     after = opts.get('after')
     m = composelargefilematcher(matcher, repo[None].manifest())
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=not isaddremove)
     finally:
         repo.lfstatus = False
     manifest = repo[None].manifest()
     modified, added, deleted, clean = [[f for f in list
                                         if lfutil.standin(f) in manifest]
                                        for list in (s.modified, s.added,
                                                     s.deleted, s.clean)]
 
     def warn(files, msg):
         for f in files:
             ui.warn(msg % m.rel(f))
         return int(len(files) > 0)
 
     result = 0
 
     if after:
         remove = deleted
         result = warn(modified + added + clean,
                       _('not removing %s: file still exists\n'))
     else:
         remove = deleted + clean
         result = warn(modified, _('not removing %s: file is modified (use -f'
                                   ' to force removal)\n'))
         result = warn(added, _('not removing %s: file has been marked for add'
                                ' (use forget to undo)\n')) or result
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in sorted(remove):
             if ui.verbose or not m.exact(f):
                 # addremove in core gets fancy with the name, remove doesn't
                 if isaddremove:
                     name = m.uipath(f)
                 else:
                     name = m.rel(f)
                 ui.status(_('removing %s\n') % name)
 
             if not opts.get('dry_run'):
                 if not after:
                     util.unlinkpath(repo.wjoin(f), ignoremissing=True)
 
         if opts.get('dry_run'):
             return result
 
         remove = [lfutil.standin(f) for f in remove]
         # If this is being called by addremove, let the original addremove
         # function handle this.
         if not isaddremove:
             for f in remove:
                 util.unlinkpath(repo.wjoin(f), ignoremissing=True)
         repo[None].forget(remove)
 
         for f in remove:
             lfutil.synclfdirstate(repo, lfdirstate, lfutil.splitstandin(f),
                                   False)
 
         lfdirstate.write()
     finally:
         wlock.release()
 
     return result
 
 # For overriding mercurial.hgweb.webcommands so that largefiles will
 # appear at their right place in the manifests.
 def decodepath(orig, path):
     return lfutil.splitstandin(path) or path
 
 # -- Wrappers: modify existing commands --------------------------------
 
 def overrideadd(orig, ui, repo, *pats, **opts):
     if opts.get('normal') and opts.get('large'):
         raise util.Abort(_('--normal cannot be used with --large'))
     return orig(ui, repo, *pats, **opts)
 
 def cmdutiladd(orig, ui, repo, matcher, prefix, explicitonly, **opts):
     # The --normal flag short circuits this override
     if opts.get('normal'):
         return orig(ui, repo, matcher, prefix, explicitonly, **opts)
 
     ladded, lbad = addlargefiles(ui, repo, False, matcher, **opts)
     normalmatcher = composenormalfilematcher(matcher, repo[None].manifest(),
                                              ladded)
     bad = orig(ui, repo, normalmatcher, prefix, explicitonly, **opts)
 
     bad.extend(f for f in lbad)
     return bad
 
 def cmdutilremove(orig, ui, repo, matcher, prefix, after, force, subrepos):
     normalmatcher = composenormalfilematcher(matcher, repo[None].manifest())
     result = orig(ui, repo, normalmatcher, prefix, after, force, subrepos)
     return removelargefiles(ui, repo, False, matcher, after=after,
                             force=force) or result
 
 def overridestatusfn(orig, repo, rev2, **opts):
     try:
         repo._repo.lfstatus = True
         return orig(repo, rev2, **opts)
     finally:
         repo._repo.lfstatus = False
 
 def overridestatus(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         return orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
 def overridedirty(orig, repo, ignoreupdate=False):
     try:
         repo._repo.lfstatus = True
         return orig(repo, ignoreupdate)
     finally:
         repo._repo.lfstatus = False
 
 def overridelog(orig, ui, repo, *pats, **opts):
     def overridematchandpats(ctx, pats=[], opts={}, globbed=False,
             default='relpath', badfn=None):
         """Matcher that merges root directory with .hglf, suitable for log.
         It is still possible to match .hglf directly.
         For any listed files run log on the standin too.
         matchfn tries both the given filename and with .hglf stripped.
         """
         matchandpats = oldmatchandpats(ctx, pats, opts, globbed, default,
                                        badfn=badfn)
         m, p = copy.copy(matchandpats)
 
         if m.always():
             # We want to match everything anyway, so there's no benefit trying
             # to add standins.
             return matchandpats
 
         pats = set(p)
 
         def fixpats(pat, tostandin=lfutil.standin):
             if pat.startswith('set:'):
                 return pat
 
             kindpat = match_._patsplit(pat, None)
 
             if kindpat[0] is not None:
                 return kindpat[0] + ':' + tostandin(kindpat[1])
             return tostandin(kindpat[1])
 
         if m._cwd:
             hglf = lfutil.shortname
             back = util.pconvert(m.rel(hglf)[:-len(hglf)])
 
             def tostandin(f):
                 # The file may already be a standin, so trucate the back
                 # prefix and test before mangling it.  This avoids turning
                 # 'glob:../.hglf/foo*' into 'glob:../.hglf/../.hglf/foo*'.
                 if f.startswith(back) and lfutil.splitstandin(f[len(back):]):
                     return f
 
                 # An absolute path is from outside the repo, so truncate the
                 # path to the root before building the standin.  Otherwise cwd
                 # is somewhere in the repo, relative to root, and needs to be
                 # prepended before building the standin.
                 if os.path.isabs(m._cwd):
                     f = f[len(back):]
                 else:
                     f = m._cwd + '/' + f
                 return back + lfutil.standin(f)
 
             pats.update(fixpats(f, tostandin) for f in p)
         else:
             def tostandin(f):
                 if lfutil.splitstandin(f):
                     return f
                 return lfutil.standin(f)
             pats.update(fixpats(f, tostandin) for f in p)
 
         for i in range(0, len(m._files)):
             # Don't add '.hglf' to m.files, since that is already covered by '.'
             if m._files[i] == '.':
                 continue
             standin = lfutil.standin(m._files[i])
             # If the "standin" is a directory, append instead of replace to
             # support naming a directory on the command line with only
             # largefiles.  The original directory is kept to support normal
             # files.
             if standin in repo[ctx.node()]:
                 m._files[i] = standin
             elif m._files[i] not in repo[ctx.node()] \
                     and repo.wvfs.isdir(standin):
                 m._files.append(standin)
 
         m._fileroots = set(m._files)
         m._always = False
         origmatchfn = m.matchfn
         def lfmatchfn(f):
             lf = lfutil.splitstandin(f)
             if lf is not None and origmatchfn(lf):
                 return True
             r = origmatchfn(f)
             return r
         m.matchfn = lfmatchfn
 
         ui.debug('updated patterns: %s\n' % sorted(pats))
         return m, pats
 
     # For hg log --patch, the match object is used in two different senses:
     # (1) to determine what revisions should be printed out, and
     # (2) to determine what files to print out diffs for.
     # The magic matchandpats override should be used for case (1) but not for
     # case (2).
     def overridemakelogfilematcher(repo, pats, opts, badfn=None):
         wctx = repo[None]
         match, pats = oldmatchandpats(wctx, pats, opts, badfn=badfn)
         return lambda rev: match
 
     oldmatchandpats = installmatchandpatsfn(overridematchandpats)
     oldmakelogfilematcher = cmdutil._makenofollowlogfilematcher
     setattr(cmdutil, '_makenofollowlogfilematcher', overridemakelogfilematcher)
 
     try:
         return orig(ui, repo, *pats, **opts)
     finally:
         restorematchandpatsfn()
         setattr(cmdutil, '_makenofollowlogfilematcher', oldmakelogfilematcher)
 
 def overrideverify(orig, ui, repo, *pats, **opts):
     large = opts.pop('large', False)
     all = opts.pop('lfa', False)
     contents = opts.pop('lfc', False)
 
     result = orig(ui, repo, *pats, **opts)
     if large or all or contents:
         result = result or lfcommands.verifylfiles(ui, repo, all, contents)
     return result
 
 def overridedebugstate(orig, ui, repo, *pats, **opts):
     large = opts.pop('large', False)
     if large:
         class fakerepo(object):
             dirstate = lfutil.openlfdirstate(ui, repo)
         orig(ui, fakerepo, *pats, **opts)
     else:
         orig(ui, repo, *pats, **opts)
 
 # Before starting the manifest merge, merge.updates will call
 # _checkunknownfile to check if there are any files in the merged-in
 # changeset that collide with unknown files in the working copy.
 #
 # The largefiles are seen as unknown, so this prevents us from merging
 # in a file 'foo' if we already have a largefile with the same name.
 #
 # The overridden function filters the unknown files by removing any
 # largefiles. This makes the merge proceed and we can then handle this
 # case further in the overridden calculateupdates function below.
 def overridecheckunknownfile(origfn, repo, wctx, mctx, f, f2=None):
     if lfutil.standin(repo.dirstate.normalize(f)) in wctx:
         return False
     return origfn(repo, wctx, mctx, f, f2)
 
 # The manifest merge handles conflicts on the manifest level. We want
 # to handle changes in largefile-ness of files at this level too.
 #
 # The strategy is to run the original calculateupdates and then process
 # the action list it outputs. There are two cases we need to deal with:
 #
 # 1. Normal file in p1, largefile in p2. Here the largefile is
 #    detected via its standin file, which will enter the working copy
 #    with a "get" action. It is not "merge" since the standin is all
 #    Mercurial is concerned with at this level -- the link to the
 #    existing normal file is not relevant here.
 #
 # 2. Largefile in p1, normal file in p2. Here we get a "merge" action
 #    since the largefile will be present in the working copy and
 #    different from the normal file in p2. Mercurial therefore
 #    triggers a merge action.
 #
 # In both cases, we prompt the user and emit new actions to either
 # remove the standin (if the normal file was kept) or to remove the
 # normal file and get the standin (if the largefile was kept). The
 # default prompt answer is to use the largefile version since it was
 # presumably changed on purpose.
 #
 # Finally, the merge.applyupdates function will then take care of
 # writing the files into the working copy and lfcommands.updatelfiles
 # will update the largefiles.
 def overridecalculateupdates(origfn, repo, p1, p2, pas, branchmerge, force,
                              partial, acceptremote, followcopies):
     overwrite = force and not branchmerge
     actions, diverge, renamedelete = origfn(
         repo, p1, p2, pas, branchmerge, force, partial, acceptremote,
         followcopies)
 
     if overwrite:
         return actions, diverge, renamedelete
 
     # Convert to dictionary with filename as key and action as value.
     lfiles = set()
     for f in actions:
         splitstandin = f and lfutil.splitstandin(f)
         if splitstandin in p1:
             lfiles.add(splitstandin)
         elif lfutil.standin(f) in p1:
             lfiles.add(f)
 
     for lfile in lfiles:
         standin = lfutil.standin(lfile)
         (lm, largs, lmsg) = actions.get(lfile, (None, None, None))
         (sm, sargs, smsg) = actions.get(standin, (None, None, None))
         if sm in ('g', 'dc') and lm != 'r':
             # Case 1: normal file in the working copy, largefile in
             # the second parent
             usermsg = _('remote turned local normal file %s into a largefile\n'
                         'use (l)argefile or keep (n)ormal file?'
                         '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(usermsg, 0) == 0: # pick remote largefile
                 actions[lfile] = ('r', None, 'replaced by standin')
                 actions[standin] = ('g', sargs, 'replaces standin')
             else: # keep local normal file
                 actions[lfile] = ('k', None, 'replaces standin')
                 if branchmerge:
                     actions[standin] = ('k', None, 'replaced by non-standin')
                 else:
                     actions[standin] = ('r', None, 'replaced by non-standin')
         elif lm in ('g', 'dc') and sm != 'r':
             # Case 2: largefile in the working copy, normal file in
             # the second parent
             usermsg = _('remote turned local largefile %s into a normal file\n'
                     'keep (l)argefile or use (n)ormal file?'
                     '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(usermsg, 0) == 0: # keep local largefile
                 if branchmerge:
                     # largefile can be restored from standin safely
                     actions[lfile] = ('k', None, 'replaced by standin')
                     actions[standin] = ('k', None, 'replaces standin')
                 else:
                     # "lfile" should be marked as "removed" without
                     # removal of itself
                     actions[lfile] = ('lfmr', None,
                                       'forget non-standin largefile')
 
                     # linear-merge should treat this largefile as 're-added'
                     actions[standin] = ('a', None, 'keep standin')
             else: # pick remote normal file
                 actions[lfile] = ('g', largs, 'replaces standin')
                 actions[standin] = ('r', None, 'replaced by non-standin')
 
     return actions, diverge, renamedelete
 
 def mergerecordupdates(orig, repo, actions, branchmerge):
     if 'lfmr' in actions:
         lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
         for lfile, args, msg in actions['lfmr']:
             # this should be executed before 'orig', to execute 'remove'
             # before all other actions
             repo.dirstate.remove(lfile)
             # make sure lfile doesn't get synclfdirstate'd as normal
             lfdirstate.add(lfile)
         lfdirstate.write()
 
     return orig(repo, actions, branchmerge)
 
 
 # Override filemerge to prompt the user about how they wish to merge
 # largefiles. This will handle identical edits without prompting the user.
 def overridefilemerge(origfn, repo, mynode, orig, fcd, fco, fca, labels=None):
     if not lfutil.isstandin(orig):
         return origfn(repo, mynode, orig, fcd, fco, fca, labels=labels)
 
     ahash = fca.data().strip().lower()
     dhash = fcd.data().strip().lower()
     ohash = fco.data().strip().lower()
     if (ohash != ahash and
         ohash != dhash and
         (dhash == ahash or
          repo.ui.promptchoice(
              _('largefile %s has a merge conflict\nancestor was %s\n'
                'keep (l)ocal %s or\ntake (o)ther %s?'
                '$$ &Local $$ &Other') %
                (lfutil.splitstandin(orig), ahash, dhash, ohash),
              0) == 1)):
         repo.wwrite(fcd.path(), fco.data(), fco.flags())
     return 0
 
 def copiespathcopies(orig, ctx1, ctx2, match=None):
     copies = orig(ctx1, ctx2, match=match)
     updated = {}
 
     for k, v in copies.iteritems():
         updated[lfutil.splitstandin(k) or k] = lfutil.splitstandin(v) or v
 
     return updated
 
 # Copy first changes the matchers to match standins instead of
 # largefiles.  Then it overrides util.copyfile in that function it
 # checks if the destination largefile already exists. It also keeps a
 # list of copied files so that the largefiles can be copied and the
 # dirstate updated.
 def overridecopy(orig, ui, repo, pats, opts, rename=False):
     # doesn't remove largefile on rename
     if len(pats) < 2:
         # this isn't legal, let the original function deal with it
         return orig(ui, repo, pats, opts, rename)
 
     # This could copy both lfiles and normal files in one command,
     # but we don't want to do that. First replace their matcher to
     # only match normal files and run it, then replace it to just
     # match largefiles and run it again.
     nonormalfiles = False
     nolfiles = False
     installnormalfilesmatchfn(repo[None].manifest())
     try:
         result = orig(ui, repo, pats, opts, rename)
-    except util.Abort, e:
+    except util.Abort as e:
         if str(e) != _('no files to copy'):
             raise e
         else:
             nonormalfiles = True
         result = 0
     finally:
         restorematchfn()
 
     # The first rename can cause our current working directory to be removed.
     # In that case there is nothing left to copy/rename so just quit.
     try:
         repo.getcwd()
     except OSError:
         return result
 
     def makestandin(relpath):
         path = pathutil.canonpath(repo.root, repo.getcwd(), relpath)
         return os.path.join(repo.wjoin(lfutil.standin(path)))
 
     fullpats = scmutil.expandpats(pats)
     dest = fullpats[-1]
 
     if os.path.isdir(dest):
         if not os.path.isdir(makestandin(dest)):
             os.makedirs(makestandin(dest))
 
     try:
         # When we call orig below it creates the standins but we don't add
         # them to the dir state until later so lock during that time.
         wlock = repo.wlock()
 
         manifest = repo[None].manifest()
         def overridematch(ctx, pats=[], opts={}, globbed=False,
                 default='relpath', badfn=None):
             newpats = []
             # The patterns were previously mangled to add the standin
             # directory; we need to remove that now
             for pat in pats:
                 if match_.patkind(pat) is None and lfutil.shortname in pat:
                     newpats.append(pat.replace(lfutil.shortname, ''))
                 else:
                     newpats.append(pat)
             match = oldmatch(ctx, newpats, opts, globbed, default, badfn=badfn)
             m = copy.copy(match)
             lfile = lambda f: lfutil.standin(f) in manifest
             m._files = [lfutil.standin(f) for f in m._files if lfile(f)]
             m._fileroots = set(m._files)
             origmatchfn = m.matchfn
             m.matchfn = lambda f: (lfutil.isstandin(f) and
                                 (f in manifest) and
                                 origmatchfn(lfutil.splitstandin(f)) or
                                 None)
             return m
         oldmatch = installmatchfn(overridematch)
         listpats = []
         for pat in pats:
             if match_.patkind(pat) is not None:
                 listpats.append(pat)
             else:
                 listpats.append(makestandin(pat))
 
         try:
             origcopyfile = util.copyfile
             copiedfiles = []
             def overridecopyfile(src, dest):
                 if (lfutil.shortname in src and
                     dest.startswith(repo.wjoin(lfutil.shortname))):
                     destlfile = dest.replace(lfutil.shortname, '')
                     if not opts['force'] and os.path.exists(destlfile):
                         raise IOError('',
                             _('destination largefile already exists'))
                 copiedfiles.append((src, dest))
                 origcopyfile(src, dest)
 
             util.copyfile = overridecopyfile
             result += orig(ui, repo, listpats, opts, rename)
         finally:
             util.copyfile = origcopyfile
 
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for (src, dest) in copiedfiles:
             if (lfutil.shortname in src and
                 dest.startswith(repo.wjoin(lfutil.shortname))):
                 srclfile = src.replace(repo.wjoin(lfutil.standin('')), '')
                 destlfile = dest.replace(repo.wjoin(lfutil.standin('')), '')
                 destlfiledir = os.path.dirname(repo.wjoin(destlfile)) or '.'
                 if not os.path.isdir(destlfiledir):
                     os.makedirs(destlfiledir)
                 if rename:
                     os.rename(repo.wjoin(srclfile), repo.wjoin(destlfile))
 
                     # The file is gone, but this deletes any empty parent
                     # directories as a side-effect.
                     util.unlinkpath(repo.wjoin(srclfile), True)
                     lfdirstate.remove(srclfile)
                 else:
                     util.copyfile(repo.wjoin(srclfile),
                                   repo.wjoin(destlfile))
 
                 lfdirstate.add(destlfile)
         lfdirstate.write()
-    except util.Abort, e:
+    except util.Abort as e:
         if str(e) != _('no files to copy'):
             raise e
         else:
             nolfiles = True
     finally:
         restorematchfn()
         wlock.release()
 
     if nolfiles and nonormalfiles:
         raise util.Abort(_('no files to copy'))
 
     return result
 
 # When the user calls revert, we have to be careful to not revert any
 # changes to other largefiles accidentally. This means we have to keep
 # track of the largefiles that are being reverted so we only pull down
 # the necessary largefiles.
 #
 # Standins are only updated (to match the hash of largefiles) before
 # commits. Update the standins then run the original revert, changing
 # the matcher to hit standins instead of largefiles. Based on the
 # resulting standins update the largefiles.
 def overriderevert(orig, ui, repo, ctx, parents, *pats, **opts):
     # Because we put the standins in a bad state (by updating them)
     # and then return them to a correct state we need to lock to
     # prevent others from changing them in their incorrect state.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         s = lfutil.lfdirstatestatus(lfdirstate, repo)
         lfdirstate.write()
         for lfile in s.modified:
             lfutil.updatestandin(repo, lfutil.standin(lfile))
         for lfile in s.deleted:
             if (os.path.exists(repo.wjoin(lfutil.standin(lfile)))):
                 os.unlink(repo.wjoin(lfutil.standin(lfile)))
 
         oldstandins = lfutil.getstandinsstate(repo)
 
         def overridematch(mctx, pats=[], opts={}, globbed=False,
                 default='relpath', badfn=None):
             match = oldmatch(mctx, pats, opts, globbed, default, badfn=badfn)
             m = copy.copy(match)
 
             # revert supports recursing into subrepos, and though largefiles
             # currently doesn't work correctly in that case, this match is
             # called, so the lfdirstate above may not be the correct one for
             # this invocation of match.
             lfdirstate = lfutil.openlfdirstate(mctx.repo().ui, mctx.repo(),
                                                False)
 
             def tostandin(f):
                 standin = lfutil.standin(f)
                 if standin in ctx or standin in mctx:
                     return standin
                 elif standin in repo[None] or lfdirstate[f] == 'r':
                     return None
                 return f
             m._files = [tostandin(f) for f in m._files]
             m._files = [f for f in m._files if f is not None]
             m._fileroots = set(m._files)
             origmatchfn = m.matchfn
             def matchfn(f):
                 if lfutil.isstandin(f):
                     return (origmatchfn(lfutil.splitstandin(f)) and
                             (f in ctx or f in mctx))
                 return origmatchfn(f)
             m.matchfn = matchfn
             return m
         oldmatch = installmatchfn(overridematch)
         try:
             orig(ui, repo, ctx, parents, *pats, **opts)
         finally:
             restorematchfn()
 
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
         # lfdirstate should be 'normallookup'-ed for updated files,
         # because reverting doesn't touch dirstate for 'normal' files
         # when target revision is explicitly specified: in such case,
         # 'n' and valid timestamp in dirstate doesn't ensure 'clean'
         # of target (standin) file.
         lfcommands.updatelfiles(ui, repo, filelist, printmessage=False,
                                 normallookup=True)
 
     finally:
         wlock.release()
 
 # after pulling changesets, we need to take some extra care to get
 # largefiles updated remotely
 def overridepull(orig, ui, repo, source=None, **opts):
     revsprepull = len(repo)
     if not source:
         source = 'default'
     repo.lfpullsource = source
     result = orig(ui, repo, source, **opts)
     revspostpull = len(repo)
     lfrevs = opts.get('lfrev', [])
     if opts.get('all_largefiles'):
         lfrevs.append('pulled()')
     if lfrevs and revspostpull > revsprepull:
         numcached = 0
         repo.firstpulled = revsprepull # for pulled() revset expression
         try:
             for rev in scmutil.revrange(repo, lfrevs):
                 ui.note(_('pulling largefiles for revision %s\n') % rev)
                 (cached, missing) = lfcommands.cachelfiles(ui, repo, rev)
                 numcached += len(cached)
         finally:
             del repo.firstpulled
         ui.status(_("%d largefiles cached\n") % numcached)
     return result
 
 def pulledrevsetsymbol(repo, subset, x):
     """``pulled()``
     Changesets that just has been pulled.
 
     Only available with largefiles from pull --lfrev expressions.
 
     .. container:: verbose
 
       Some examples:
 
       - pull largefiles for all new changesets::
 
           hg pull -lfrev "pulled()"
 
       - pull largefiles for all new branch heads::
 
           hg pull -lfrev "head(pulled()) and not closed()"
 
     """
 
     try:
         firstpulled = repo.firstpulled
     except AttributeError:
         raise util.Abort(_("pulled() only available in --lfrev"))
     return revset.baseset([r for r in subset if r >= firstpulled])
 
 def overrideclone(orig, ui, source, dest=None, **opts):
     d = dest
     if d is None:
         d = hg.defaultdest(source)
     if opts.get('all_largefiles') and not hg.islocal(d):
             raise util.Abort(_(
             '--all-largefiles is incompatible with non-local destination %s') %
             d)
 
     return orig(ui, source, dest, **opts)
 
 def hgclone(orig, ui, opts, *args, **kwargs):
     result = orig(ui, opts, *args, **kwargs)
 
     if result is not None:
         sourcerepo, destrepo = result
         repo = destrepo.local()
 
         # When cloning to a remote repo (like through SSH), no repo is available
         # from the peer.   Therefore the largefiles can't be downloaded and the
         # hgrc can't be updated.
         if not repo:
             return result
 
         # If largefiles is required for this repo, permanently enable it locally
         if 'largefiles' in repo.requirements:
             fp = repo.vfs('hgrc', 'a', text=True)
             try:
                 fp.write('\n[extensions]\nlargefiles=\n')
             finally:
                 fp.close()
 
         # Caching is implicitly limited to 'rev' option, since the dest repo was
         # truncated at that point.  The user may expect a download count with
         # this option, so attempt whether or not this is a largefile repo.
         if opts.get('all_largefiles'):
             success, missing = lfcommands.downloadlfiles(ui, repo, None)
 
             if missing != 0:
                 return None
 
     return result
 
 def overriderebase(orig, ui, repo, **opts):
     if not util.safehasattr(repo, '_largefilesenabled'):
         return orig(ui, repo, **opts)
 
     resuming = opts.get('continue')
     repo._lfcommithooks.append(lfutil.automatedcommithook(resuming))
     repo._lfstatuswriters.append(lambda *msg, **opts: None)
     try:
         return orig(ui, repo, **opts)
     finally:
         repo._lfstatuswriters.pop()
         repo._lfcommithooks.pop()
 
 def overridearchive(orig, repo, dest, node, kind, decode=True, matchfn=None,
             prefix='', mtime=None, subrepos=None):
     # No need to lock because we are only reading history and
     # largefile caches, neither of which are modified.
     if node is not None:
         lfcommands.cachelfiles(repo.ui, repo, node)
 
     if kind not in archival.archivers:
         raise util.Abort(_("unknown archive type '%s'") % kind)
 
     ctx = repo[node]
 
     if kind == 'files':
         if prefix:
             raise util.Abort(
                 _('cannot give prefix when archiving to files'))
     else:
         prefix = archival.tidyprefix(dest, kind, prefix)
 
     def write(name, mode, islink, getdata):
         if matchfn and not matchfn(name):
             return
         data = getdata()
         if decode:
             data = repo.wwritedata(name, data)
         archiver.addfile(prefix + name, mode, islink, data)
 
     archiver = archival.archivers[kind](dest, mtime or ctx.date()[0])
 
     if repo.ui.configbool("ui", "archivemeta", True):
         write('.hg_archival.txt', 0o644, False,
               lambda: archival.buildmetadata(ctx))
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         if lfutil.isstandin(f):
             if node is not None:
                 path = lfutil.findfile(repo, getdata().strip())
 
                 if path is None:
                     raise util.Abort(
                        _('largefile %s not found in repo store or system cache')
                        % lfutil.splitstandin(f))
             else:
                 path = lfutil.splitstandin(f)
 
             f = lfutil.splitstandin(f)
 
             def getdatafn():
                 fd = None
                 try:
                     fd = open(path, 'rb')
                     return fd.read()
                 finally:
                     if fd:
                         fd.close()
 
             getdata = getdatafn
         write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, getdata)
 
     if subrepos:
         for subpath in sorted(ctx.substate):
             sub = ctx.workingsub(subpath)
             submatch = match_.narrowmatcher(subpath, matchfn)
             sub.archive(archiver, prefix, submatch)
 
     archiver.done()
 
 def hgsubrepoarchive(orig, repo, archiver, prefix, match=None):
     repo._get(repo._state + ('hg',))
     rev = repo._state[1]
     ctx = repo._repo[rev]
 
     if ctx.node() is not None:
         lfcommands.cachelfiles(repo.ui, repo._repo, ctx.node())
 
     def write(name, mode, islink, getdata):
         # At this point, the standin has been replaced with the largefile name,
         # so the normal matcher works here without the lfutil variants.
         if match and not match(f):
             return
         data = getdata()
 
         archiver.addfile(prefix + repo._path + '/' + name, mode, islink, data)
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         if lfutil.isstandin(f):
             if ctx.node() is not None:
                 path = lfutil.findfile(repo._repo, getdata().strip())
 
                 if path is None:
                     raise util.Abort(
                        _('largefile %s not found in repo store or system cache')
                        % lfutil.splitstandin(f))
             else:
                 path = lfutil.splitstandin(f)
 
             f = lfutil.splitstandin(f)
 
             def getdatafn():
                 fd = None
                 try:
                     fd = open(os.path.join(prefix, path), 'rb')
                     return fd.read()
                 finally:
                     if fd:
                         fd.close()
 
             getdata = getdatafn
 
         write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, getdata)
 
     for subpath in sorted(ctx.substate):
         sub = ctx.workingsub(subpath)
         submatch = match_.narrowmatcher(subpath, match)
         sub.archive(archiver, prefix + repo._path + '/', submatch)
 
 # If a largefile is modified, the change is not reflected in its
 # standin until a commit. cmdutil.bailifchanged() raises an exception
 # if the repo has uncommitted changes. Wrap it to also check if
 # largefiles were changed. This is used by bisect, backout and fetch.
 def overridebailifchanged(orig, repo, *args, **kwargs):
     orig(repo, *args, **kwargs)
     repo.lfstatus = True
     s = repo.status()
     repo.lfstatus = False
     if s.modified or s.added or s.removed or s.deleted:
         raise util.Abort(_('uncommitted changes'))
 
 def cmdutilforget(orig, ui, repo, match, prefix, explicitonly):
     normalmatcher = composenormalfilematcher(match, repo[None].manifest())
     bad, forgot = orig(ui, repo, normalmatcher, prefix, explicitonly)
     m = composelargefilematcher(match, repo[None].manifest())
 
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=True)
     finally:
         repo.lfstatus = False
     forget = sorted(s.modified + s.added + s.deleted + s.clean)
     forget = [f for f in forget if lfutil.standin(f) in repo[None].manifest()]
 
     for f in forget:
         if lfutil.standin(f) not in repo.dirstate and not \
                 repo.wvfs.isdir(lfutil.standin(f)):
             ui.warn(_('not removing %s: file is already untracked\n')
                     % m.rel(f))
             bad.append(f)
 
     for f in forget:
         if ui.verbose or not m.exact(f):
             ui.status(_('removing %s\n') % m.rel(f))
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in forget:
             if lfdirstate[f] == 'a':
                 lfdirstate.drop(f)
             else:
                 lfdirstate.remove(f)
         lfdirstate.write()
         standins = [lfutil.standin(f) for f in forget]
         for f in standins:
             util.unlinkpath(repo.wjoin(f), ignoremissing=True)
         rejected = repo[None].forget(standins)
     finally:
         wlock.release()
 
     bad.extend(f for f in rejected if f in m.files())
     forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 def _getoutgoings(repo, other, missing, addfunc):
     """get pairs of filename and largefile hash in outgoing revisions
     in 'missing'.
 
     largefiles already existing on 'other' repository are ignored.
 
     'addfunc' is invoked with each unique pairs of filename and
     largefile hash value.
     """
     knowns = set()
     lfhashes = set()
     def dedup(fn, lfhash):
         k = (fn, lfhash)
         if k not in knowns:
             knowns.add(k)
             lfhashes.add(lfhash)
     lfutil.getlfilestoupload(repo, missing, dedup)
     if lfhashes:
         lfexists = basestore._openstore(repo, other).exists(lfhashes)
         for fn, lfhash in knowns:
             if not lfexists[lfhash]: # lfhash doesn't exist on "other"
                 addfunc(fn, lfhash)
 
 def outgoinghook(ui, repo, other, opts, missing):
     if opts.pop('large', None):
         lfhashes = set()
         if ui.debugflag:
             toupload = {}
             def addfunc(fn, lfhash):
                 if fn not in toupload:
                     toupload[fn] = []
                 toupload[fn].append(lfhash)
                 lfhashes.add(lfhash)
             def showhashes(fn):
                 for lfhash in sorted(toupload[fn]):
                     ui.debug('    %s\n' % (lfhash))
         else:
             toupload = set()
             def addfunc(fn, lfhash):
                 toupload.add(fn)
                 lfhashes.add(lfhash)
             def showhashes(fn):
                 pass
         _getoutgoings(repo, other, missing, addfunc)
 
         if not toupload:
             ui.status(_('largefiles: no files to upload\n'))
         else:
             ui.status(_('largefiles to upload (%d entities):\n')
                       % (len(lfhashes)))
             for file in sorted(toupload):
                 ui.status(lfutil.splitstandin(file) + '\n')
                 showhashes(file)
             ui.status('\n')
 
 def summaryremotehook(ui, repo, opts, changes):
     largeopt = opts.get('large', False)
     if changes is None:
         if largeopt:
             return (False, True) # only outgoing check is needed
         else:
             return (False, False)
     elif largeopt:
         url, branch, peer, outgoing = changes[1]
         if peer is None:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no remote repo)\n'))
             return
 
         toupload = set()
         lfhashes = set()
         def addfunc(fn, lfhash):
             toupload.add(fn)
             lfhashes.add(lfhash)
         _getoutgoings(repo, peer, outgoing.missing, addfunc)
 
         if not toupload:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no files to upload)\n'))
         else:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: %d entities for %d files to upload\n')
                       % (len(lfhashes), len(toupload)))
 
 def overridesummary(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
 def scmutiladdremove(orig, repo, matcher, prefix, opts={}, dry_run=None,
                      similarity=None):
     if not lfutil.islfilesrepo(repo):
         return orig(repo, matcher, prefix, opts, dry_run, similarity)
     # Get the list of missing largefiles so we can remove them
     lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
     unsure, s = lfdirstate.status(match_.always(repo.root, repo.getcwd()), [],
                                   False, False, False)
 
     # Call into the normal remove code, but the removing of the standin, we want
     # to have handled by original addremove.  Monkey patching here makes sure
     # we don't remove the standin in the largefiles code, preventing a very
     # confused state later.
     if s.deleted:
         m = copy.copy(matcher)
 
         # The m._files and m._map attributes are not changed to the deleted list
         # because that affects the m.exact() test, which in turn governs whether
         # or not the file name is printed, and how.  Simply limit the original
         # matches to those in the deleted status list.
         matchfn = m.matchfn
         m.matchfn = lambda f: f in s.deleted and matchfn(f)
 
         removelargefiles(repo.ui, repo, True, m, **opts)
     # Call into the normal add code, and any files that *should* be added as
     # largefiles will be
     added, bad = addlargefiles(repo.ui, repo, True, matcher, **opts)
     # Now that we've handled largefiles, hand off to the original addremove
     # function to take care of the rest.  Make sure it doesn't do anything with
     # largefiles by passing a matcher that will ignore them.
     matcher = composenormalfilematcher(matcher, repo[None].manifest(), added)
     return orig(repo, matcher, prefix, opts, dry_run, similarity)
 
 # Calling purge with --all will cause the largefiles to be deleted.
 # Override repo.status to prevent this from happening.
 def overridepurge(orig, ui, repo, *dirs, **opts):
     # XXX Monkey patching a repoview will not work. The assigned attribute will
     # be set on the unfiltered repo, but we will only lookup attributes in the
     # unfiltered repo if the lookup in the repoview object itself fails. As the
     # monkey patched method exists on the repoview class the lookup will not
     # fail. As a result, the original version will shadow the monkey patched
     # one, defeating the monkey patch.
     #
     # As a work around we use an unfiltered repo here. We should do something
     # cleaner instead.
     repo = repo.unfiltered()
     oldstatus = repo.status
     def overridestatus(node1='.', node2=None, match=None, ignored=False,
                         clean=False, unknown=False, listsubrepos=False):
         r = oldstatus(node1, node2, match, ignored, clean, unknown,
                       listsubrepos)
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         unknown = [f for f in r.unknown if lfdirstate[f] == '?']
         ignored = [f for f in r.ignored if lfdirstate[f] == '?']
         return scmutil.status(r.modified, r.added, r.removed, r.deleted,
                               unknown, ignored, r.clean)
     repo.status = overridestatus
     orig(ui, repo, *dirs, **opts)
     repo.status = oldstatus
 def overriderollback(orig, ui, repo, **opts):
     wlock = repo.wlock()
     try:
         before = repo.dirstate.parents()
         orphans = set(f for f in repo.dirstate
                       if lfutil.isstandin(f) and repo.dirstate[f] != 'r')
         result = orig(ui, repo, **opts)
         after = repo.dirstate.parents()
         if before == after:
             return result # no need to restore standins
 
         pctx = repo['.']
         for f in repo.dirstate:
             if lfutil.isstandin(f):
                 orphans.discard(f)
                 if repo.dirstate[f] == 'r':
                     repo.wvfs.unlinkpath(f, ignoremissing=True)
                 elif f in pctx:
                     fctx = pctx[f]
                     repo.wwrite(f, fctx.data(), fctx.flags())
                 else:
                     # content of standin is not so important in 'a',
                     # 'm' or 'n' (coming from the 2nd parent) cases
                     lfutil.writestandin(repo, f, '', False)
         for standin in orphans:
             repo.wvfs.unlinkpath(standin, ignoremissing=True)
 
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         orphans = set(lfdirstate)
         lfiles = lfutil.listlfiles(repo)
         for file in lfiles:
             lfutil.synclfdirstate(repo, lfdirstate, file, True)
             orphans.discard(file)
         for lfile in orphans:
             lfdirstate.drop(lfile)
         lfdirstate.write()
     finally:
         wlock.release()
     return result
 
 def overridetransplant(orig, ui, repo, *revs, **opts):
     resuming = opts.get('continue')
     repo._lfcommithooks.append(lfutil.automatedcommithook(resuming))
     repo._lfstatuswriters.append(lambda *msg, **opts: None)
     try:
         result = orig(ui, repo, *revs, **opts)
     finally:
         repo._lfstatuswriters.pop()
         repo._lfcommithooks.pop()
     return result
 
 def overridecat(orig, ui, repo, file1, *pats, **opts):
     ctx = scmutil.revsingle(repo, opts.get('rev'))
     err = 1
     notbad = set()
     m = scmutil.match(ctx, (file1,) + pats, opts)
     origmatchfn = m.matchfn
     def lfmatchfn(f):
         if origmatchfn(f):
             return True
         lf = lfutil.splitstandin(f)
         if lf is None:
             return False
         notbad.add(lf)
         return origmatchfn(lf)
     m.matchfn = lfmatchfn
     origbadfn = m.bad
     def lfbadfn(f, msg):
         if not f in notbad:
             origbadfn(f, msg)
     m.bad = lfbadfn
 
     origvisitdirfn = m.visitdir
     def lfvisitdirfn(dir):
         if dir == lfutil.shortname:
             return True
         ret = origvisitdirfn(dir)
         if ret:
             return ret
         lf = lfutil.splitstandin(dir)
         if lf is None:
             return False
         return origvisitdirfn(lf)
     m.visitdir = lfvisitdirfn
 
     for f in ctx.walk(m):
         fp = cmdutil.makefileobj(repo, opts.get('output'), ctx.node(),
                                  pathname=f)
         lf = lfutil.splitstandin(f)
         if lf is None or origmatchfn(f):
             # duplicating unreachable code from commands.cat
             data = ctx[f].data()
             if opts.get('decode'):
                 data = repo.wwritedata(f, data)
             fp.write(data)
         else:
             hash = lfutil.readstandin(repo, lf, ctx.rev())
             if not lfutil.inusercache(repo.ui, hash):
                 store = basestore._openstore(repo)
                 success, missing = store.get([(lf, hash)])
                 if len(success) != 1:
                     raise util.Abort(
                         _('largefile %s is not in cache and could not be '
                           'downloaded')  % lf)
             path = lfutil.usercachepath(repo.ui, hash)
             fpin = open(path, "rb")
             for chunk in util.filechunkiter(fpin, 128 * 1024):
                 fp.write(chunk)
             fpin.close()
         fp.close()
         err = 0
     return err
 
 def mergeupdate(orig, repo, node, branchmerge, force, partial,
                 *args, **kwargs):
     wlock = repo.wlock()
     try:
         # branch |       |         |
         #  merge | force | partial | action
         # -------+-------+---------+--------------
         #    x   |   x   |    x    | linear-merge
         #    o   |   x   |    x    | branch-merge
         #    x   |   o   |    x    | overwrite (as clean update)
         #    o   |   o   |    x    | force-branch-merge (*1)
         #    x   |   x   |    o    |   (*)
         #    o   |   x   |    o    |   (*)
         #    x   |   o   |    o    | overwrite (as revert)
         #    o   |   o   |    o    |   (*)
         #
         # (*) don't care
         # (*1) deprecated, but used internally (e.g: "rebase --collapse")
 
         lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
         unsure, s = lfdirstate.status(match_.always(repo.root,
                                                     repo.getcwd()),
                                       [], False, False, False)
         pctx = repo['.']
         for lfile in unsure + s.modified:
             lfileabs = repo.wvfs.join(lfile)
             if not os.path.exists(lfileabs):
                 continue
             lfhash = lfutil.hashrepofile(repo, lfile)
             standin = lfutil.standin(lfile)
             lfutil.writestandin(repo, standin, lfhash,
                                 lfutil.getexecutable(lfileabs))
             if (standin in pctx and
                 lfhash == lfutil.readstandin(repo, lfile, '.')):
                 lfdirstate.normal(lfile)
         for lfile in s.added:
             lfutil.updatestandin(repo, lfutil.standin(lfile))
         lfdirstate.write()
 
         oldstandins = lfutil.getstandinsstate(repo)
 
         result = orig(repo, node, branchmerge, force, partial, *args, **kwargs)
 
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
         if branchmerge or force or partial:
             filelist.extend(s.deleted + s.removed)
 
         lfcommands.updatelfiles(repo.ui, repo, filelist=filelist,
                                 normallookup=partial)
 
         return result
     finally:
         wlock.release()
 
 def scmutilmarktouched(orig, repo, files, *args, **kwargs):
     result = orig(repo, files, *args, **kwargs)
 
     filelist = [lfutil.splitstandin(f) for f in files if lfutil.isstandin(f)]
     if filelist:
         lfcommands.updatelfiles(repo.ui, repo, filelist=filelist,
                                 printmessage=False, normallookup=True)
 
     return result

hgext/largefiles/proto.py

@@ -1,175 +1,175 b''
 # Copyright 2011 Fog Creek Software
 #
 # 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 urllib2
 import re
 
 from mercurial import error, httppeer, util, wireproto
 from mercurial.i18n import _
 
 import lfutil
 
 LARGEFILES_REQUIRED_MSG = ('\nThis repository uses the largefiles extension.'
                            '\n\nPlease enable it in your Mercurial config '
                            'file.\n')
 
 # these will all be replaced by largefiles.uisetup
 capabilitiesorig = None
 ssholdcallstream = None
 httpoldcallstream = None
 
 def putlfile(repo, proto, sha):
     '''Put a largefile into a repository's local store and into the
     user cache.'''
     proto.redirect()
 
     path = lfutil.storepath(repo, sha)
     util.makedirs(os.path.dirname(path))
     tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)
 
     try:
         proto.getfile(tmpfp)
         tmpfp._fp.seek(0)
         if sha != lfutil.hexsha1(tmpfp._fp):
             raise IOError(0, _('largefile contents do not match hash'))
         tmpfp.close()
         lfutil.linktousercache(repo, sha)
-    except IOError, e:
+    except IOError as e:
         repo.ui.warn(_('largefiles: failed to put %s into store: %s\n') %
                      (sha, e.strerror))
         return wireproto.pushres(1)
     finally:
         tmpfp.discard()
 
     return wireproto.pushres(0)
 
 def getlfile(repo, proto, sha):
     '''Retrieve a largefile from the repository-local cache or system
     cache.'''
     filename = lfutil.findfile(repo, sha)
     if not filename:
         raise util.Abort(_('requested largefile %s not present in cache') % sha)
     f = open(filename, 'rb')
     length = os.fstat(f.fileno())[6]
 
     # Since we can't set an HTTP content-length header here, and
     # Mercurial core provides no way to give the length of a streamres
     # (and reading the entire file into RAM would be ill-advised), we
     # just send the length on the first line of the response, like the
     # ssh proto does for string responses.
     def generator():
         yield '%d\n' % length
         for chunk in util.filechunkiter(f):
             yield chunk
     return wireproto.streamres(generator())
 
 def statlfile(repo, proto, sha):
     '''Return '2\n' if the largefile is missing, '0\n' if it seems to be in
     good condition.
 
     The value 1 is reserved for mismatched checksum, but that is too expensive
     to be verified on every stat and must be caught be running 'hg verify'
     server side.'''
     filename = lfutil.findfile(repo, sha)
     if not filename:
         return '2\n'
     return '0\n'
 
 def wirereposetup(ui, repo):
     class lfileswirerepository(repo.__class__):
         def putlfile(self, sha, fd):
             # unfortunately, httprepository._callpush tries to convert its
             # input file-like into a bundle before sending it, so we can't use
             # it ...
             if issubclass(self.__class__, httppeer.httppeer):
                 res = None
                 try:
                     res = self._call('putlfile', data=fd, sha=sha,
                         headers={'content-type':'application/mercurial-0.1'})
                     d, output = res.split('\n', 1)
                     for l in output.splitlines(True):
                         self.ui.warn(_('remote: '), l) # assume l ends with \n
                     return int(d)
                 except (ValueError, urllib2.HTTPError):
                     self.ui.warn(_('unexpected putlfile response: %r\n') % res)
                     return 1
             # ... but we can't use sshrepository._call because the data=
             # argument won't get sent, and _callpush does exactly what we want
             # in this case: send the data straight through
             else:
                 try:
                     ret, output = self._callpush("putlfile", fd, sha=sha)
                     if ret == "":
                         raise error.ResponseError(_('putlfile failed:'),
                                 output)
                     return int(ret)
                 except IOError:
                     return 1
                 except ValueError:
                     raise error.ResponseError(
                         _('putlfile failed (unexpected response):'), ret)
 
         def getlfile(self, sha):
             """returns an iterable with the chunks of the file with sha sha"""
             stream = self._callstream("getlfile", sha=sha)
             length = stream.readline()
             try:
                 length = int(length)
             except ValueError:
                 self._abort(error.ResponseError(_("unexpected response:"),
                                                 length))
 
             # SSH streams will block if reading more than length
             for chunk in util.filechunkiter(stream, 128 * 1024, length):
                 yield chunk
             # HTTP streams must hit the end to process the last empty
             # chunk of Chunked-Encoding so the connection can be reused.
             if issubclass(self.__class__, httppeer.httppeer):
                 chunk = stream.read(1)
                 if chunk:
                     self._abort(error.ResponseError(_("unexpected response:"),
                                                     chunk))
 
         @wireproto.batchable
         def statlfile(self, sha):
             f = wireproto.future()
             result = {'sha': sha}
             yield result, f
             try:
                 yield int(f.value)
             except (ValueError, urllib2.HTTPError):
                 # If the server returns anything but an integer followed by a
                 # newline, newline, it's not speaking our language; if we get
                 # an HTTP error, we can't be sure the largefile is present;
                 # either way, consider it missing.
                 yield 2
 
     repo.__class__ = lfileswirerepository
 
 # advertise the largefiles=serve capability
 def capabilities(repo, proto):
     return capabilitiesorig(repo, proto) + ' largefiles=serve'
 
 def heads(repo, proto):
     if lfutil.islfilesrepo(repo):
         return wireproto.ooberror(LARGEFILES_REQUIRED_MSG)
     return wireproto.heads(repo, proto)
 
 def sshrepocallstream(self, cmd, **args):
     if cmd == 'heads' and self.capable('largefiles'):
         cmd = 'lheads'
     if cmd == 'batch' and self.capable('largefiles'):
         args['cmds'] = args['cmds'].replace('heads ', 'lheads ')
     return ssholdcallstream(self, cmd, **args)
 
 headsre = re.compile(r'(^|;)heads\b')
 
 def httprepocallstream(self, cmd, **args):
     if cmd == 'heads' and self.capable('largefiles'):
         cmd = 'lheads'
     if cmd == 'batch' and self.capable('largefiles'):
         args['cmds'] = headsre.sub('lheads', args['cmds'])
     return httpoldcallstream(self, cmd, **args)

hgext/largefiles/remotestore.py

@@ -1,98 +1,98 b''
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''remote largefile store; the base class for wirestore'''
 
 import urllib2
 
 from mercurial import util, wireproto
 from mercurial.i18n import _
 
 import lfutil
 import basestore
 
 class remotestore(basestore.basestore):
     '''a largefile store accessed over a network'''
     def __init__(self, ui, repo, url):
         super(remotestore, self).__init__(ui, repo, url)
 
     def put(self, source, hash):
         if self.sendfile(source, hash):
             raise util.Abort(
                 _('remotestore: could not put %s to remote store %s')
                 % (source, util.hidepassword(self.url)))
         self.ui.debug(
             _('remotestore: put %s to remote store %s\n')
             % (source, util.hidepassword(self.url)))
 
     def exists(self, hashes):
         return dict((h, s == 0) for (h, s) in # dict-from-generator
                     self._stat(hashes).iteritems())
 
     def sendfile(self, filename, hash):
         self.ui.debug('remotestore: sendfile(%s, %s)\n' % (filename, hash))
         fd = None
         try:
             fd = lfutil.httpsendfile(self.ui, filename)
             return self._put(hash, fd)
-        except IOError, e:
+        except IOError as e:
             raise util.Abort(
                 _('remotestore: could not open file %s: %s')
                 % (filename, str(e)))
         finally:
             if fd:
                 fd.close()
 
     def _getfile(self, tmpfile, filename, hash):
         try:
             chunks = self._get(hash)
-        except urllib2.HTTPError, e:
+        except urllib2.HTTPError as e:
             # 401s get converted to util.Aborts; everything else is fine being
             # turned into a StoreError
             raise basestore.StoreError(filename, hash, self.url, str(e))
-        except urllib2.URLError, e:
+        except urllib2.URLError as e:
             # This usually indicates a connection problem, so don't
             # keep trying with the other files... they will probably
             # all fail too.
             raise util.Abort('%s: %s' %
                              (util.hidepassword(self.url), e.reason))
-        except IOError, e:
+        except IOError as e:
             raise basestore.StoreError(filename, hash, self.url, str(e))
 
         return lfutil.copyandhash(chunks, tmpfile)
 
     def _verifyfile(self, cctx, cset, contents, standin, verified):
         filename = lfutil.splitstandin(standin)
         if not filename:
             return False
         fctx = cctx[standin]
         key = (filename, fctx.filenode())
         if key in verified:
             return False
 
         verified.add(key)
 
         expecthash = fctx.data()[0:40]
         stat = self._stat([expecthash])[expecthash]
         if not stat:
             return False
         elif stat == 1:
             self.ui.warn(
                 _('changeset %s: %s: contents differ\n')
                 % (cset, filename))
             return True # failed
         elif stat == 2:
             self.ui.warn(
                 _('changeset %s: %s missing\n')
                 % (cset, filename))
             return True # failed
         else:
             raise RuntimeError('verify failed: unexpected response from '
                                'statlfile (%r)' % stat)
 
     def batch(self):
         '''Support for remote batching.'''
         return wireproto.remotebatch(self)