convcmd.py
434 lines
| 14.8 KiB
| text/x-python
|
PythonLexer
|
r5621 | # convcmd - convert extension commands definition | ||
# | ||||
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com> | ||||
# | ||||
|
r8225 | # This software may be used and distributed according to the terms of the | ||
|
r10263 | # GNU General Public License version 2 or any later version. | ||
|
r5621 | |||
|
r6332 | from common import NoRepo, MissingTool, SKIPREV, mapfile | ||
|
r5621 | from cvs import convert_cvs | ||
from darcs import darcs_source | ||||
from git import convert_git | ||||
from hg import mercurial_source, mercurial_sink | ||||
|
r7873 | from subversion import svn_source, svn_sink | ||
|
r6306 | from monotone import monotone_source | ||
|
r6035 | from gnuarch import gnuarch_source | ||
|
r7053 | from bzr import bzr_source | ||
|
r7823 | from p4 import p4_source | ||
|
r5621 | import filemap | ||
import os, shutil | ||||
|
r7948 | from mercurial import hg, util, encoding | ||
|
r5621 | from mercurial.i18n import _ | ||
|
r6131 | 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') | ||||
|
r5621 | source_converters = [ | ||
|
r8692 | ('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'), | ||||
|
r5621 | ] | ||
sink_converters = [ | ||||
('hg', mercurial_sink), | ||||
|
r5631 | ('svn', svn_sink), | ||
|
r5621 | ] | ||
def convertsource(ui, path, type, rev): | ||||
exceptions = [] | ||||
|
r9962 | if type and type not in [s[0] for s in source_converters]: | ||
raise util.Abort(_('%s: invalid source repository type') % type) | ||||
|
r8692 | for name, source, sortmode in source_converters: | ||
|
r5621 | try: | ||
if not type or name == type: | ||||
|
r8692 | return source(ui, path, rev), sortmode | ||
|
r6332 | except (NoRepo, MissingTool), inst: | ||
|
r5621 | exceptions.append(inst) | ||
if not ui.quiet: | ||||
for inst in exceptions: | ||||
|
r6913 | ui.write("%s\n" % inst) | ||
|
r6976 | raise util.Abort(_('%s: missing or unsupported repository') % path) | ||
|
r5621 | |||
def convertsink(ui, path, type): | ||||
|
r9962 | if type and type not in [s[0] for s in sink_converters]: | ||
raise util.Abort(_('%s: invalid destination repository type') % type) | ||||
|
r5621 | for name, sink in sink_converters: | ||
try: | ||||
if not type or name == type: | ||||
return sink(ui, path) | ||||
except NoRepo, inst: | ||||
ui.note(_("convert: %s\n") % inst) | ||||
|
r6913 | raise util.Abort(_('%s: unknown repository type') % path) | ||
|
r5621 | |||
|
r11136 | 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 | ||||
|
r11731 | self.ui.progress(_('getting files'), self.retrieved, | ||
|
r11136 | item=file, total=self.filecount) | ||
return self.source.getfile(file, rev) | ||||
def lookuprev(self, rev): | ||||
return self.source.lookuprev(rev) | ||||
def close(self): | ||||
|
r11731 | self.ui.progress(_('getting files'), None) | ||
|
r11136 | |||
|
r5621 | 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 | ||||
|
r8444 | # Record converted revisions persistently: maps source revision | ||
|
r8843 | # ID to target revision ID (both strings). (This is how | ||
|
r8444 | # incremental conversions work.) | ||
|
r5631 | self.map = mapfile(ui, revmapfile) | ||
|
r5621 | |||
# 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 | ||||
|
r12198 | if opts.get('authormap'): | ||
self.readauthormap(opts.get('authormap')) | ||||
|
r5621 | self.authorfile = self.dest.authorfile() | ||
|
r6143 | self.splicemap = mapfile(ui, opts.get('splicemap')) | ||
|
r8377 | self.branchmap = mapfile(ui, opts.get('branchmap')) | ||
|
r5996 | |||
|
r5621 | def walktree(self, heads): | ||
'''Return a mapping that identifies the uncommitted parents of every | ||||
uncommitted changeset.''' | ||||
visit = heads | ||||
|
r8456 | known = set() | ||
|
r5621 | parents = {} | ||
while visit: | ||||
n = visit.pop(0) | ||||
|
r10282 | if n in known or n in self.map: | ||
continue | ||||
|
r8456 | known.add(n) | ||
|
r11135 | self.ui.progress(_('scanning'), len(known), unit=_('revisions')) | ||
|
r5621 | commit = self.cachecommit(n) | ||
parents[n] = [] | ||||
for p in commit.parents: | ||||
parents[n].append(p) | ||||
visit.append(p) | ||||
|
r11135 | self.ui.progress(_('scanning'), None) | ||
|
r5621 | |||
return parents | ||||
|
r8689 | def toposort(self, parents, sortmode): | ||
|
r5621 | '''Return an ordering such that every uncommitted changeset is | ||
preceeded by all its uncommitted ancestors.''' | ||||
|
r8688 | |||
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 = parents.keys() | ||||
seen = set() | ||||
children = {} | ||||
roots = [] | ||||
|
r5621 | |||
|
r8688 | 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 not p in self.map: | ||||
visit.append(p) | ||||
hasparent = True | ||||
children.setdefault(p, []).append(n) | ||||
if not hasparent: | ||||
roots.append(n) | ||||
return children, roots | ||||
|
r6100 | |||
|
r8688 | # Sort functions are supposed to take a list of revisions which | ||
# can be converted immediately and pick one | ||||
|
r6100 | |||
|
r8688 | 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 | ||||
|
r8690 | def makesourcesorter(): | ||
"""Source specific sort.""" | ||||
keyfn = lambda n: self.commitcache[n].sortkey | ||||
def picknext(nodes): | ||||
return sorted(nodes, key=keyfn)[0] | ||||
return picknext | ||||
|
r8688 | def makedatesorter(): | ||
"""Sort revisions by date.""" | ||||
|
r6100 | 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] | ||||
|
r8688 | |||
return picknext | ||||
|
r8689 | if sortmode == 'branchsort': | ||
picknext = makebranchsorter() | ||||
elif sortmode == 'datesort': | ||||
|
r8688 | picknext = makedatesorter() | ||
|
r8690 | elif sortmode == 'sourcesort': | ||
picknext = makesourcesorter() | ||||
|
r6100 | else: | ||
|
r8689 | raise util.Abort(_('unknown sort mode: %s') % sortmode) | ||
|
r8688 | |||
children, actives = mapchildren(parents) | ||||
|
r5621 | |||
s = [] | ||||
|
r6100 | pendings = {} | ||
while actives: | ||||
n = picknext(actives) | ||||
actives.remove(n) | ||||
s.append(n) | ||||
|
r5621 | |||
|
r6100 | # 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] | ||||
|
r6131 | try: | ||
pendings[c].remove(n) | ||||
except ValueError: | ||||
raise util.Abort(_('cycle detected between %s and %s') | ||||
% (recode(c), recode(n))) | ||||
|
r6100 | if not pendings[c]: | ||
# Parents are converted, node is eligible | ||||
actives.insert(0, c) | ||||
pendings[c] = None | ||||
|
r5621 | |||
|
r6100 | if len(s) != len(parents): | ||
raise util.Abort(_("not all revisions were sorted")) | ||||
|
r5621 | |||
return s | ||||
def writeauthormap(self): | ||||
authorfile = self.authorfile | ||||
if authorfile: | ||||
|
r7877 | 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() | ||||
|
r5621 | |||
def readauthormap(self, authorfile): | ||||
afile = open(authorfile, 'r') | ||||
for line in afile: | ||||
|
r7962 | |||
|
r7968 | line = line.strip() | ||
if not line or line.startswith('#'): | ||||
|
r6184 | continue | ||
|
r7962 | |||
|
r5621 | try: | ||
|
r6186 | srcauthor, dstauthor = line.split('=', 1) | ||
|
r7962 | 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)) | ||||
|
r5621 | afile.close() | ||
def cachecommit(self, rev): | ||||
commit = self.source.getcommit(rev) | ||||
commit.author = self.authors.get(commit.author, commit.author) | ||||
|
r8377 | commit.branch = self.branchmap.get(commit.branch, commit.branch) | ||
|
r5621 | self.commitcache[rev] = commit | ||
return commit | ||||
def copy(self, rev): | ||||
commit = self.commitcache[rev] | ||||
changes = self.source.getchanges(rev) | ||||
if isinstance(changes, basestring): | ||||
if changes == SKIPREV: | ||||
dest = SKIPREV | ||||
else: | ||||
dest = self.map[changes] | ||||
|
r5631 | self.map[rev] = dest | ||
|
r5621 | return | ||
files, copies = changes | ||||
|
r5934 | pbranches = [] | ||
|
r5621 | if commit.parents: | ||
|
r5934 | for prev in commit.parents: | ||
if prev not in self.commitcache: | ||||
self.cachecommit(prev) | ||||
|
r6210 | pbranches.append((self.map[prev], | ||
|
r5934 | self.commitcache[prev].branch)) | ||
self.dest.setbranch(commit.branch, pbranches) | ||||
|
r5996 | try: | ||
|
r6143 | parents = self.splicemap[rev].replace(',', ' ').split() | ||
|
r6956 | self.ui.status(_('spliced in %s as parents of %s\n') % | ||
|
r6143 | (parents, rev)) | ||
parents = [self.map.get(p, p) for p in parents] | ||||
|
r5996 | except KeyError: | ||
parents = [b[0] for b in pbranches] | ||||
|
r11136 | source = progresssource(self.ui, self.source, len(files)) | ||
|
r8843 | newnode = self.dest.putcommit(files, copies, parents, commit, | ||
|
r11136 | source, self.map) | ||
source.close() | ||||
|
r5631 | self.source.converted(rev, newnode) | ||
self.map[rev] = newnode | ||||
|
r5621 | |||
|
r8689 | def convert(self, sortmode): | ||
|
r5621 | try: | ||
self.source.before() | ||||
self.dest.before() | ||||
|
r5631 | self.source.setrevmap(self.map) | ||
|
r6956 | self.ui.status(_("scanning source...\n")) | ||
|
r5621 | heads = self.source.getheads() | ||
parents = self.walktree(heads) | ||||
|
r6956 | self.ui.status(_("sorting...\n")) | ||
|
r8689 | t = self.toposort(parents, sortmode) | ||
|
r5621 | num = len(t) | ||
c = None | ||||
|
r6956 | self.ui.status(_("converting...\n")) | ||
|
r11135 | for i, c in enumerate(t): | ||
|
r5621 | num -= 1 | ||
desc = self.commitcache[c].desc | ||||
if "\n" in desc: | ||||
desc = desc.splitlines()[0] | ||||
|
r5794 | # convert log message to local encoding without using | ||
|
r7948 | # tolocal() because encoding.encoding conver() use it as | ||
|
r5794 | # 'utf-8' | ||
|
r5954 | self.ui.status("%d %s\n" % (num, recode(desc))) | ||
|
r6913 | self.ui.note(_("source: %s\n") % recode(c)) | ||
|
r11135 | self.ui.progress(_('converting'), i, unit=_('revisions'), | ||
total=len(t)) | ||||
|
r5621 | self.copy(c) | ||
|
r11135 | self.ui.progress(_('converting'), None) | ||
|
r5621 | |||
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: | ||||
|
r9431 | 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 | ||||
|
r5621 | |||
self.writeauthormap() | ||||
finally: | ||||
self.cleanup() | ||||
def cleanup(self): | ||||
try: | ||||
self.dest.after() | ||||
finally: | ||||
self.source.after() | ||||
|
r5631 | self.map.close() | ||
|
r5621 | |||
def convert(ui, src, dest=None, revmapfile=None, **opts): | ||||
|
r5794 | global orig_encoding | ||
|
r7948 | orig_encoding = encoding.encoding | ||
encoding.encoding = 'UTF-8' | ||||
|
r5621 | |||
|
r12198 | # support --authors as an alias for --authormap | ||
if not opts.get('authormap'): | ||||
opts['authormap'] = opts.get('authors') | ||||
|
r5621 | if not dest: | ||
dest = hg.defaultdest(src) + "-hg" | ||||
|
r6956 | ui.status(_("assuming destination %s\n") % dest) | ||
|
r5621 | |||
destc = convertsink(ui, dest, opts.get('dest_type')) | ||||
try: | ||||
|
r8692 | srcc, defaultsort = convertsource(ui, src, opts.get('source_type'), | ||
opts.get('rev')) | ||||
|
r5621 | except Exception: | ||
for path in destc.created: | ||||
shutil.rmtree(path, True) | ||||
raise | ||||
|
r8692 | sortmodes = ('branchsort', 'datesort', 'sourcesort') | ||
|
r8690 | sortmode = [m for m in sortmodes if opts.get(m)] | ||
if len(sortmode) > 1: | ||||
raise util.Abort(_('more than one sort mode specified')) | ||||
|
r8692 | sortmode = sortmode and sortmode[0] or defaultsort | ||
|
r8691 | if sortmode == 'sourcesort' and not srcc.hasnativeorder(): | ||
raise util.Abort(_('--sourcesort is not supported by this data source')) | ||||
|
r8689 | |||
|
r5621 | fmap = opts.get('filemap') | ||
if fmap: | ||||
srcc = filemap.filemap_source(ui, srcc, fmap) | ||||
destc.setfilemapmode(True) | ||||
if not revmapfile: | ||||
try: | ||||
revmapfile = destc.revmapfile() | ||||
except: | ||||
revmapfile = os.path.join(destc, "map") | ||||
c = converter(ui, srcc, destc, revmapfile, opts) | ||||
|
r8689 | c.convert(sortmode) | ||
|
r5621 | |||