Show More
@@ -1,434 +1,434 b'' | |||
|
1 | 1 | # convcmd - convert extension commands definition |
|
2 | 2 | # |
|
3 | 3 | # Copyright 2005-2007 Matt Mackall <mpm@selenic.com> |
|
4 | 4 | # |
|
5 | 5 | # This software may be used and distributed according to the terms of the |
|
6 | 6 | # GNU General Public License version 2 or any later version. |
|
7 | 7 | |
|
8 | 8 | from common import NoRepo, MissingTool, SKIPREV, mapfile |
|
9 | 9 | from cvs import convert_cvs |
|
10 | 10 | from darcs import darcs_source |
|
11 | 11 | from git import convert_git |
|
12 | 12 | from hg import mercurial_source, mercurial_sink |
|
13 | 13 | from subversion import svn_source, svn_sink |
|
14 | 14 | from monotone import monotone_source |
|
15 | 15 | from gnuarch import gnuarch_source |
|
16 | 16 | from bzr import bzr_source |
|
17 | 17 | from p4 import p4_source |
|
18 | 18 | import filemap |
|
19 | 19 | |
|
20 | 20 | import os, shutil |
|
21 | 21 | from mercurial import hg, util, encoding |
|
22 | 22 | from mercurial.i18n import _ |
|
23 | 23 | |
|
24 | 24 | orig_encoding = 'ascii' |
|
25 | 25 | |
|
26 | 26 | def recode(s): |
|
27 | 27 | if isinstance(s, unicode): |
|
28 | 28 | return s.encode(orig_encoding, 'replace') |
|
29 | 29 | else: |
|
30 | 30 | return s.decode('utf-8').encode(orig_encoding, 'replace') |
|
31 | 31 | |
|
32 | 32 | source_converters = [ |
|
33 | 33 | ('cvs', convert_cvs, 'branchsort'), |
|
34 | 34 | ('git', convert_git, 'branchsort'), |
|
35 | 35 | ('svn', svn_source, 'branchsort'), |
|
36 | 36 | ('hg', mercurial_source, 'sourcesort'), |
|
37 | 37 | ('darcs', darcs_source, 'branchsort'), |
|
38 | 38 | ('mtn', monotone_source, 'branchsort'), |
|
39 | 39 | ('gnuarch', gnuarch_source, 'branchsort'), |
|
40 | 40 | ('bzr', bzr_source, 'branchsort'), |
|
41 | 41 | ('p4', p4_source, 'branchsort'), |
|
42 | 42 | ] |
|
43 | 43 | |
|
44 | 44 | sink_converters = [ |
|
45 | 45 | ('hg', mercurial_sink), |
|
46 | 46 | ('svn', svn_sink), |
|
47 | 47 | ] |
|
48 | 48 | |
|
49 | 49 | def convertsource(ui, path, type, rev): |
|
50 | 50 | exceptions = [] |
|
51 | 51 | if type and type not in [s[0] for s in source_converters]: |
|
52 | 52 | raise util.Abort(_('%s: invalid source repository type') % type) |
|
53 | 53 | for name, source, sortmode in source_converters: |
|
54 | 54 | try: |
|
55 | 55 | if not type or name == type: |
|
56 | 56 | return source(ui, path, rev), sortmode |
|
57 | 57 | except (NoRepo, MissingTool), inst: |
|
58 | 58 | exceptions.append(inst) |
|
59 | 59 | if not ui.quiet: |
|
60 | 60 | for inst in exceptions: |
|
61 | 61 | ui.write("%s\n" % inst) |
|
62 | 62 | raise util.Abort(_('%s: missing or unsupported repository') % path) |
|
63 | 63 | |
|
64 | 64 | def convertsink(ui, path, type): |
|
65 | 65 | if type and type not in [s[0] for s in sink_converters]: |
|
66 | 66 | raise util.Abort(_('%s: invalid destination repository type') % type) |
|
67 | 67 | for name, sink in sink_converters: |
|
68 | 68 | try: |
|
69 | 69 | if not type or name == type: |
|
70 | 70 | return sink(ui, path) |
|
71 | 71 | except NoRepo, inst: |
|
72 | 72 | ui.note(_("convert: %s\n") % inst) |
|
73 | 73 | raise util.Abort(_('%s: unknown repository type') % path) |
|
74 | 74 | |
|
75 | 75 | class progresssource(object): |
|
76 | 76 | def __init__(self, ui, source, filecount): |
|
77 | 77 | self.ui = ui |
|
78 | 78 | self.source = source |
|
79 | 79 | self.filecount = filecount |
|
80 | 80 | self.retrieved = 0 |
|
81 | 81 | |
|
82 | 82 | def getfile(self, file, rev): |
|
83 | 83 | self.retrieved += 1 |
|
84 | 84 | self.ui.progress(_('getting files'), self.retrieved, |
|
85 | 85 | item=file, total=self.filecount) |
|
86 | 86 | return self.source.getfile(file, rev) |
|
87 | 87 | |
|
88 | 88 | def lookuprev(self, rev): |
|
89 | 89 | return self.source.lookuprev(rev) |
|
90 | 90 | |
|
91 | 91 | def close(self): |
|
92 | 92 | self.ui.progress(_('getting files'), None) |
|
93 | 93 | |
|
94 | 94 | class converter(object): |
|
95 | 95 | def __init__(self, ui, source, dest, revmapfile, opts): |
|
96 | 96 | |
|
97 | 97 | self.source = source |
|
98 | 98 | self.dest = dest |
|
99 | 99 | self.ui = ui |
|
100 | 100 | self.opts = opts |
|
101 | 101 | self.commitcache = {} |
|
102 | 102 | self.authors = {} |
|
103 | 103 | self.authorfile = None |
|
104 | 104 | |
|
105 | 105 | # Record converted revisions persistently: maps source revision |
|
106 | 106 | # ID to target revision ID (both strings). (This is how |
|
107 | 107 | # incremental conversions work.) |
|
108 | 108 | self.map = mapfile(ui, revmapfile) |
|
109 | 109 | |
|
110 | 110 | # Read first the dst author map if any |
|
111 | 111 | authorfile = self.dest.authorfile() |
|
112 | 112 | if authorfile and os.path.exists(authorfile): |
|
113 | 113 | self.readauthormap(authorfile) |
|
114 | 114 | # Extend/Override with new author map if necessary |
|
115 | 115 | if opts.get('authormap'): |
|
116 | 116 | self.readauthormap(opts.get('authormap')) |
|
117 | 117 | self.authorfile = self.dest.authorfile() |
|
118 | 118 | |
|
119 | 119 | self.splicemap = mapfile(ui, opts.get('splicemap')) |
|
120 | 120 | self.branchmap = mapfile(ui, opts.get('branchmap')) |
|
121 | 121 | |
|
122 | 122 | def walktree(self, heads): |
|
123 | 123 | '''Return a mapping that identifies the uncommitted parents of every |
|
124 | 124 | uncommitted changeset.''' |
|
125 | 125 | visit = heads |
|
126 | 126 | known = set() |
|
127 | 127 | parents = {} |
|
128 | 128 | while visit: |
|
129 | 129 | n = visit.pop(0) |
|
130 | 130 | if n in known or n in self.map: |
|
131 | 131 | continue |
|
132 | 132 | known.add(n) |
|
133 | 133 | self.ui.progress(_('scanning'), len(known), unit=_('revisions')) |
|
134 | 134 | commit = self.cachecommit(n) |
|
135 | 135 | parents[n] = [] |
|
136 | 136 | for p in commit.parents: |
|
137 | 137 | parents[n].append(p) |
|
138 | 138 | visit.append(p) |
|
139 | 139 | self.ui.progress(_('scanning'), None) |
|
140 | 140 | |
|
141 | 141 | return parents |
|
142 | 142 | |
|
143 | 143 | def toposort(self, parents, sortmode): |
|
144 | 144 | '''Return an ordering such that every uncommitted changeset is |
|
145 | 145 | preceeded by all its uncommitted ancestors.''' |
|
146 | 146 | |
|
147 | 147 | def mapchildren(parents): |
|
148 | 148 | """Return a (children, roots) tuple where 'children' maps parent |
|
149 | 149 | revision identifiers to children ones, and 'roots' is the list of |
|
150 | 150 | revisions without parents. 'parents' must be a mapping of revision |
|
151 | 151 | identifier to its parents ones. |
|
152 | 152 | """ |
|
153 | 153 | visit = parents.keys() |
|
154 | 154 | seen = set() |
|
155 | 155 | children = {} |
|
156 | 156 | roots = [] |
|
157 | 157 | |
|
158 | 158 | while visit: |
|
159 | 159 | n = visit.pop(0) |
|
160 | 160 | if n in seen: |
|
161 | 161 | continue |
|
162 | 162 | seen.add(n) |
|
163 | 163 | # Ensure that nodes without parents are present in the |
|
164 | 164 | # 'children' mapping. |
|
165 | 165 | children.setdefault(n, []) |
|
166 | 166 | hasparent = False |
|
167 | 167 | for p in parents[n]: |
|
168 | 168 | if not p in self.map: |
|
169 | 169 | visit.append(p) |
|
170 | 170 | hasparent = True |
|
171 | 171 | children.setdefault(p, []).append(n) |
|
172 | 172 | if not hasparent: |
|
173 | 173 | roots.append(n) |
|
174 | 174 | |
|
175 | 175 | return children, roots |
|
176 | 176 | |
|
177 | 177 | # Sort functions are supposed to take a list of revisions which |
|
178 | 178 | # can be converted immediately and pick one |
|
179 | 179 | |
|
180 | 180 | def makebranchsorter(): |
|
181 | 181 | """If the previously converted revision has a child in the |
|
182 | 182 | eligible revisions list, pick it. Return the list head |
|
183 | 183 | otherwise. Branch sort attempts to minimize branch |
|
184 | 184 | switching, which is harmful for Mercurial backend |
|
185 | 185 | compression. |
|
186 | 186 | """ |
|
187 | 187 | prev = [None] |
|
188 | 188 | def picknext(nodes): |
|
189 | 189 | next = nodes[0] |
|
190 | 190 | for n in nodes: |
|
191 | 191 | if prev[0] in parents[n]: |
|
192 | 192 | next = n |
|
193 | 193 | break |
|
194 | 194 | prev[0] = next |
|
195 | 195 | return next |
|
196 | 196 | return picknext |
|
197 | 197 | |
|
198 | 198 | def makesourcesorter(): |
|
199 | 199 | """Source specific sort.""" |
|
200 | 200 | keyfn = lambda n: self.commitcache[n].sortkey |
|
201 | 201 | def picknext(nodes): |
|
202 | 202 | return sorted(nodes, key=keyfn)[0] |
|
203 | 203 | return picknext |
|
204 | 204 | |
|
205 | 205 | def makedatesorter(): |
|
206 | 206 | """Sort revisions by date.""" |
|
207 | 207 | dates = {} |
|
208 | 208 | def getdate(n): |
|
209 | 209 | if n not in dates: |
|
210 | 210 | dates[n] = util.parsedate(self.commitcache[n].date) |
|
211 | 211 | return dates[n] |
|
212 | 212 | |
|
213 | 213 | def picknext(nodes): |
|
214 | 214 | return min([(getdate(n), n) for n in nodes])[1] |
|
215 | 215 | |
|
216 | 216 | return picknext |
|
217 | 217 | |
|
218 | 218 | if sortmode == 'branchsort': |
|
219 | 219 | picknext = makebranchsorter() |
|
220 | 220 | elif sortmode == 'datesort': |
|
221 | 221 | picknext = makedatesorter() |
|
222 | 222 | elif sortmode == 'sourcesort': |
|
223 | 223 | picknext = makesourcesorter() |
|
224 | 224 | else: |
|
225 | 225 | raise util.Abort(_('unknown sort mode: %s') % sortmode) |
|
226 | 226 | |
|
227 | 227 | children, actives = mapchildren(parents) |
|
228 | 228 | |
|
229 | 229 | s = [] |
|
230 | 230 | pendings = {} |
|
231 | 231 | while actives: |
|
232 | 232 | n = picknext(actives) |
|
233 | 233 | actives.remove(n) |
|
234 | 234 | s.append(n) |
|
235 | 235 | |
|
236 | 236 | # Update dependents list |
|
237 | 237 | for c in children.get(n, []): |
|
238 | 238 | if c not in pendings: |
|
239 | 239 | pendings[c] = [p for p in parents[c] if p not in self.map] |
|
240 | 240 | try: |
|
241 | 241 | pendings[c].remove(n) |
|
242 | 242 | except ValueError: |
|
243 | 243 | raise util.Abort(_('cycle detected between %s and %s') |
|
244 | 244 | % (recode(c), recode(n))) |
|
245 | 245 | if not pendings[c]: |
|
246 | 246 | # Parents are converted, node is eligible |
|
247 | 247 | actives.insert(0, c) |
|
248 | 248 | pendings[c] = None |
|
249 | 249 | |
|
250 | 250 | if len(s) != len(parents): |
|
251 | 251 | raise util.Abort(_("not all revisions were sorted")) |
|
252 | 252 | |
|
253 | 253 | return s |
|
254 | 254 | |
|
255 | 255 | def writeauthormap(self): |
|
256 | 256 | authorfile = self.authorfile |
|
257 | 257 | if authorfile: |
|
258 | 258 | self.ui.status(_('Writing author map file %s\n') % authorfile) |
|
259 | 259 | ofile = open(authorfile, 'w+') |
|
260 | 260 | for author in self.authors: |
|
261 | 261 | ofile.write("%s=%s\n" % (author, self.authors[author])) |
|
262 | 262 | ofile.close() |
|
263 | 263 | |
|
264 | 264 | def readauthormap(self, authorfile): |
|
265 | 265 | afile = open(authorfile, 'r') |
|
266 | 266 | for line in afile: |
|
267 | 267 | |
|
268 | 268 | line = line.strip() |
|
269 | 269 | if not line or line.startswith('#'): |
|
270 | 270 | continue |
|
271 | 271 | |
|
272 | 272 | try: |
|
273 | 273 | srcauthor, dstauthor = line.split('=', 1) |
|
274 | 274 | except ValueError: |
|
275 | 275 | msg = _('Ignoring bad line in author map file %s: %s\n') |
|
276 | 276 | self.ui.warn(msg % (authorfile, line.rstrip())) |
|
277 | 277 | continue |
|
278 | 278 | |
|
279 | 279 | srcauthor = srcauthor.strip() |
|
280 | 280 | dstauthor = dstauthor.strip() |
|
281 | 281 | if self.authors.get(srcauthor) in (None, dstauthor): |
|
282 | 282 | msg = _('mapping author %s to %s\n') |
|
283 | 283 | self.ui.debug(msg % (srcauthor, dstauthor)) |
|
284 | 284 | self.authors[srcauthor] = dstauthor |
|
285 | 285 | continue |
|
286 | 286 | |
|
287 | 287 | m = _('overriding mapping for author %s, was %s, will be %s\n') |
|
288 | 288 | self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor)) |
|
289 | 289 | |
|
290 | 290 | afile.close() |
|
291 | 291 | |
|
292 | 292 | def cachecommit(self, rev): |
|
293 | 293 | commit = self.source.getcommit(rev) |
|
294 | 294 | commit.author = self.authors.get(commit.author, commit.author) |
|
295 | 295 | commit.branch = self.branchmap.get(commit.branch, commit.branch) |
|
296 | 296 | self.commitcache[rev] = commit |
|
297 | 297 | return commit |
|
298 | 298 | |
|
299 | 299 | def copy(self, rev): |
|
300 | 300 | commit = self.commitcache[rev] |
|
301 | 301 | |
|
302 | 302 | changes = self.source.getchanges(rev) |
|
303 | 303 | if isinstance(changes, basestring): |
|
304 | 304 | if changes == SKIPREV: |
|
305 | 305 | dest = SKIPREV |
|
306 | 306 | else: |
|
307 | 307 | dest = self.map[changes] |
|
308 | 308 | self.map[rev] = dest |
|
309 | 309 | return |
|
310 | 310 | files, copies = changes |
|
311 | 311 | pbranches = [] |
|
312 | 312 | if commit.parents: |
|
313 | 313 | for prev in commit.parents: |
|
314 | 314 | if prev not in self.commitcache: |
|
315 | 315 | self.cachecommit(prev) |
|
316 | 316 | pbranches.append((self.map[prev], |
|
317 | 317 | self.commitcache[prev].branch)) |
|
318 | 318 | self.dest.setbranch(commit.branch, pbranches) |
|
319 | 319 | try: |
|
320 | 320 | parents = self.splicemap[rev].replace(',', ' ').split() |
|
321 | 321 | self.ui.status(_('spliced in %s as parents of %s\n') % |
|
322 | 322 | (parents, rev)) |
|
323 | 323 | parents = [self.map.get(p, p) for p in parents] |
|
324 | 324 | except KeyError: |
|
325 | 325 | parents = [b[0] for b in pbranches] |
|
326 | 326 | source = progresssource(self.ui, self.source, len(files)) |
|
327 | 327 | newnode = self.dest.putcommit(files, copies, parents, commit, |
|
328 | 328 | source, self.map) |
|
329 | 329 | source.close() |
|
330 | 330 | self.source.converted(rev, newnode) |
|
331 | 331 | self.map[rev] = newnode |
|
332 | 332 | |
|
333 | 333 | def convert(self, sortmode): |
|
334 | 334 | try: |
|
335 | 335 | self.source.before() |
|
336 | 336 | self.dest.before() |
|
337 | 337 | self.source.setrevmap(self.map) |
|
338 | 338 | self.ui.status(_("scanning source...\n")) |
|
339 | 339 | heads = self.source.getheads() |
|
340 | 340 | parents = self.walktree(heads) |
|
341 | 341 | self.ui.status(_("sorting...\n")) |
|
342 | 342 | t = self.toposort(parents, sortmode) |
|
343 | 343 | num = len(t) |
|
344 | 344 | c = None |
|
345 | 345 | |
|
346 | 346 | self.ui.status(_("converting...\n")) |
|
347 | 347 | for i, c in enumerate(t): |
|
348 | 348 | num -= 1 |
|
349 | 349 | desc = self.commitcache[c].desc |
|
350 | 350 | if "\n" in desc: |
|
351 | 351 | desc = desc.splitlines()[0] |
|
352 | 352 | # convert log message to local encoding without using |
|
353 |
# tolocal() because encoding.encoding conver() |
|
|
354 | # 'utf-8' | |
|
353 | # tolocal() because the encoding.encoding convert() | |
|
354 | # uses is 'utf-8' | |
|
355 | 355 | self.ui.status("%d %s\n" % (num, recode(desc))) |
|
356 | 356 | self.ui.note(_("source: %s\n") % recode(c)) |
|
357 | 357 | self.ui.progress(_('converting'), i, unit=_('revisions'), |
|
358 | 358 | total=len(t)) |
|
359 | 359 | self.copy(c) |
|
360 | 360 | self.ui.progress(_('converting'), None) |
|
361 | 361 | |
|
362 | 362 | tags = self.source.gettags() |
|
363 | 363 | ctags = {} |
|
364 | 364 | for k in tags: |
|
365 | 365 | v = tags[k] |
|
366 | 366 | if self.map.get(v, SKIPREV) != SKIPREV: |
|
367 | 367 | ctags[k] = self.map[v] |
|
368 | 368 | |
|
369 | 369 | if c and ctags: |
|
370 | 370 | nrev, tagsparent = self.dest.puttags(ctags) |
|
371 | 371 | if nrev and tagsparent: |
|
372 | 372 | # write another hash correspondence to override the previous |
|
373 | 373 | # one so we don't end up with extra tag heads |
|
374 | 374 | tagsparents = [e for e in self.map.iteritems() |
|
375 | 375 | if e[1] == tagsparent] |
|
376 | 376 | if tagsparents: |
|
377 | 377 | self.map[tagsparents[0][0]] = nrev |
|
378 | 378 | |
|
379 | 379 | self.writeauthormap() |
|
380 | 380 | finally: |
|
381 | 381 | self.cleanup() |
|
382 | 382 | |
|
383 | 383 | def cleanup(self): |
|
384 | 384 | try: |
|
385 | 385 | self.dest.after() |
|
386 | 386 | finally: |
|
387 | 387 | self.source.after() |
|
388 | 388 | self.map.close() |
|
389 | 389 | |
|
390 | 390 | def convert(ui, src, dest=None, revmapfile=None, **opts): |
|
391 | 391 | global orig_encoding |
|
392 | 392 | orig_encoding = encoding.encoding |
|
393 | 393 | encoding.encoding = 'UTF-8' |
|
394 | 394 | |
|
395 | 395 | # support --authors as an alias for --authormap |
|
396 | 396 | if not opts.get('authormap'): |
|
397 | 397 | opts['authormap'] = opts.get('authors') |
|
398 | 398 | |
|
399 | 399 | if not dest: |
|
400 | 400 | dest = hg.defaultdest(src) + "-hg" |
|
401 | 401 | ui.status(_("assuming destination %s\n") % dest) |
|
402 | 402 | |
|
403 | 403 | destc = convertsink(ui, dest, opts.get('dest_type')) |
|
404 | 404 | |
|
405 | 405 | try: |
|
406 | 406 | srcc, defaultsort = convertsource(ui, src, opts.get('source_type'), |
|
407 | 407 | opts.get('rev')) |
|
408 | 408 | except Exception: |
|
409 | 409 | for path in destc.created: |
|
410 | 410 | shutil.rmtree(path, True) |
|
411 | 411 | raise |
|
412 | 412 | |
|
413 | 413 | sortmodes = ('branchsort', 'datesort', 'sourcesort') |
|
414 | 414 | sortmode = [m for m in sortmodes if opts.get(m)] |
|
415 | 415 | if len(sortmode) > 1: |
|
416 | 416 | raise util.Abort(_('more than one sort mode specified')) |
|
417 | 417 | sortmode = sortmode and sortmode[0] or defaultsort |
|
418 | 418 | if sortmode == 'sourcesort' and not srcc.hasnativeorder(): |
|
419 | 419 | raise util.Abort(_('--sourcesort is not supported by this data source')) |
|
420 | 420 | |
|
421 | 421 | fmap = opts.get('filemap') |
|
422 | 422 | if fmap: |
|
423 | 423 | srcc = filemap.filemap_source(ui, srcc, fmap) |
|
424 | 424 | destc.setfilemapmode(True) |
|
425 | 425 | |
|
426 | 426 | if not revmapfile: |
|
427 | 427 | try: |
|
428 | 428 | revmapfile = destc.revmapfile() |
|
429 | 429 | except: |
|
430 | 430 | revmapfile = os.path.join(destc, "map") |
|
431 | 431 | |
|
432 | 432 | c = converter(ui, srcc, destc, revmapfile, opts) |
|
433 | 433 | c.convert(sortmode) |
|
434 | 434 |
General Comments 0
You need to be logged in to leave comments.
Login now