/usr/lib/python2.7/dist-packages/hgext/convert/cvsps.py is in mercurial-common 4.5.3-1ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 | # Mercurial built-in replacement for cvsps.
#
# Copyright 2008, Frank Kingswood <frank@kingswood-consulting.co.uk>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import os
import re
from mercurial.i18n import _
from mercurial import (
encoding,
error,
hook,
pycompat,
util,
)
pickle = util.pickle
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(b'/foo/bar')
'/foo/bar'
>>> getrepopath(b'c:/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:10/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:10c:/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:c:/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:truc@foo.bar:/foo/bar')
'/foo/bar'
>>> getrepopath(b':pserver:truc@foo.bar:c:/foo/bar')
'/foo/bar'
>>> getrepopath(b'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(pycompat.ossep):
prefix += pycompat.ossep
# 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 = encoding.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 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
rcsmap = {}
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)
rcsmap[e.rcs.replace('/Attic/', '/')] = e.rcs
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 sorted(oldlog, key=lambda x: (x.rcs, x.revision)):
rcs = e.rcs.replace('/Attic/', '/')
if rcs in rcsmap:
e.rcs = rcsmap[rcs]
branch = e.revision[:-1]
versions[(e.rcs, branch)] = e.revision
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))
encodings = ui.configlist('convert', 'cvsps.logencoding')
if encodings:
def revstr(r):
# this is needed, because logentry.revision is a tuple of "int"
# (e.g. (1, 2) for "1.2")
return '.'.join(pycompat.maplist(pycompat.bytestr, r))
for entry in log:
comment = entry.comment
for e in encodings:
try:
entry.comment = comment.decode(e).encode('utf-8')
if ui.debugflag:
ui.debug("transcoding by %s: %s of %s\n" %
(e, revstr(entry.revision), entry.file))
break
except UnicodeDecodeError:
pass # try next encoding
except LookupError as inst: # unknown encoding, maybe
raise error.Abort(inst,
hint=_('check convert.cvsps.logencoding'
' configuration'))
else:
raise error.Abort(_("no encoding can transcode"
" CVS log message for %s of %s")
% (revstr(entry.revision), entry.file),
hint=_('check convert.cvsps.logencoding'
' configuration'))
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):
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 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
|