File: gnuarch.py

package info (click to toggle)
mercurial 4.9-2
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 42,952 kB
  • sloc: python: 159,631; ansic: 40,124; tcl: 3,715; lisp: 1,448; sh: 1,388; makefile: 602; cpp: 451; xml: 36; sql: 30
file content (358 lines) | stat: -rw-r--r-- 13,191 bytes parent folder | download | duplicates (4)
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
# gnuarch.py - GNU Arch support for the convert extension
#
#  Copyright 2008, 2009 Aleix Conchillo Flaque <aleix@member.fsf.org>
#  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 __future__ import absolute_import

import email.parser as emailparser
import os
import shutil
import stat
import tempfile

from mercurial.i18n import _
from mercurial import (
    encoding,
    error,
    pycompat,
    util,
)
from mercurial.utils import (
    dateutil,
    procutil,
)
from . import common

class gnuarch_source(common.converter_source, common.commandline):

    class gnuarch_rev(object):
        def __init__(self, rev):
            self.rev = rev
            self.summary = ''
            self.date = None
            self.author = ''
            self.continuationof = None
            self.add_files = []
            self.mod_files = []
            self.del_files = []
            self.ren_files = {}
            self.ren_dirs = {}

    def __init__(self, ui, repotype, path, revs=None):
        super(gnuarch_source, self).__init__(ui, repotype, path, revs=revs)

        if not os.path.exists(os.path.join(path, '{arch}')):
            raise common.NoRepo(_("%s does not look like a GNU Arch repository")
                         % path)

        # Could use checktool, but we want to check for baz or tla.
        self.execmd = None
        if procutil.findexe('baz'):
            self.execmd = 'baz'
        else:
            if procutil.findexe('tla'):
                self.execmd = 'tla'
            else:
                raise error.Abort(_('cannot find a GNU Arch tool') +
                                  _(' (try installing the %s package)') % 'tla')

        common.commandline.__init__(self, ui, self.execmd)

        self.path = os.path.realpath(path)
        self.tmppath = None

        self.treeversion = None
        self.lastrev = None
        self.changes = {}
        self.parents = {}
        self.tags = {}
        self.catlogparser = emailparser.Parser()
        self.encoding = encoding.encoding
        self.archives = []

    def before(self):
        # Get registered archives
        self.archives = [i.rstrip('\n')
                         for i in self.runlines0('archives', '-n')]

        if self.execmd == 'tla':
            output = self.run0('tree-version', self.path)
        else:
            output = self.run0('tree-version', '-d', self.path)
        self.treeversion = output.strip()

        # Get name of temporary directory
        version = self.treeversion.split('/')
        self.tmppath = os.path.join(tempfile.gettempdir(),
                                    'hg-%s' % version[1])

        # Generate parents dictionary
        self.parents[None] = []
        treeversion = self.treeversion
        child = None
        while treeversion:
            self.ui.status(_('analyzing tree version %s...\n') % treeversion)

            archive = treeversion.split('/')[0]
            if archive not in self.archives:
                self.ui.status(_('tree analysis stopped because it points to '
                                 'an unregistered archive %s...\n') % archive)
                break

            # Get the complete list of revisions for that tree version
            output, status = self.runlines('revisions', '-r', '-f', treeversion)
            self.checkexit(status, 'failed retrieving revisions for %s'
                           % treeversion)

            # No new iteration unless a revision has a continuation-of header
            treeversion = None

            for l in output:
                rev = l.strip()
                self.changes[rev] = self.gnuarch_rev(rev)
                self.parents[rev] = []

                # Read author, date and summary
                catlog, status = self.run('cat-log', '-d', self.path, rev)
                if status:
                    catlog  = self.run0('cat-archive-log', rev)
                self._parsecatlog(catlog, rev)

                # Populate the parents map
                self.parents[child].append(rev)

                # Keep track of the current revision as the child of the next
                # revision scanned
                child = rev

                # Check if we have to follow the usual incremental history
                # or if we have to 'jump' to a different treeversion given
                # by the continuation-of header.
                if self.changes[rev].continuationof:
                    treeversion = '--'.join(
                        self.changes[rev].continuationof.split('--')[:-1])
                    break

                # If we reached a base-0 revision w/o any continuation-of
                # header, it means the tree history ends here.
                if rev[-6:] == 'base-0':
                    break

    def after(self):
        self.ui.debug('cleaning up %s\n' % self.tmppath)
        shutil.rmtree(self.tmppath, ignore_errors=True)

    def getheads(self):
        return self.parents[None]

    def getfile(self, name, rev):
        if rev != self.lastrev:
            raise error.Abort(_('internal calling inconsistency'))

        if not os.path.lexists(os.path.join(self.tmppath, name)):
            return None, None

        return self._getfile(name, rev)

    def getchanges(self, rev, full):
        if full:
            raise error.Abort(_("convert from arch does not support --full"))
        self._update(rev)
        changes = []
        copies = {}

        for f in self.changes[rev].add_files:
            changes.append((f, rev))

        for f in self.changes[rev].mod_files:
            changes.append((f, rev))

        for f in self.changes[rev].del_files:
            changes.append((f, rev))

        for src in self.changes[rev].ren_files:
            to = self.changes[rev].ren_files[src]
            changes.append((src, rev))
            changes.append((to, rev))
            copies[to] = src

        for src in self.changes[rev].ren_dirs:
            to = self.changes[rev].ren_dirs[src]
            chgs, cps = self._rendirchanges(src, to)
            changes += [(f, rev) for f in chgs]
            copies.update(cps)

        self.lastrev = rev
        return sorted(set(changes)), copies, set()

    def getcommit(self, rev):
        changes = self.changes[rev]
        return common.commit(author=changes.author, date=changes.date,
                             desc=changes.summary, parents=self.parents[rev],
                             rev=rev)

    def gettags(self):
        return self.tags

    def _execute(self, cmd, *args, **kwargs):
        cmdline = [self.execmd, cmd]
        cmdline += args
        cmdline = [procutil.shellquote(arg) for arg in cmdline]
        cmdline += ['>', os.devnull, '2>', os.devnull]
        cmdline = procutil.quotecommand(' '.join(cmdline))
        self.ui.debug(cmdline, '\n')
        return os.system(pycompat.rapply(procutil.tonativestr, cmdline))

    def _update(self, rev):
        self.ui.debug('applying revision %s...\n' % rev)
        changeset, status = self.runlines('replay', '-d', self.tmppath,
                                              rev)
        if status:
            # Something went wrong while merging (baz or tla
            # issue?), get latest revision and try from there
            shutil.rmtree(self.tmppath, ignore_errors=True)
            self._obtainrevision(rev)
        else:
            old_rev = self.parents[rev][0]
            self.ui.debug('computing changeset between %s and %s...\n'
                          % (old_rev, rev))
            self._parsechangeset(changeset, rev)

    def _getfile(self, name, rev):
        mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
        if stat.S_ISLNK(mode):
            data = util.readlink(os.path.join(self.tmppath, name))
            if mode:
                mode = 'l'
            else:
                mode = ''
        else:
            data = util.readfile(os.path.join(self.tmppath, name))
            mode = (mode & 0o111) and 'x' or ''
        return data, mode

    def _exclude(self, name):
        exclude = ['{arch}', '.arch-ids', '.arch-inventory']
        for exc in exclude:
            if name.find(exc) != -1:
                return True
        return False

    def _readcontents(self, path):
        files = []
        contents = os.listdir(path)
        while len(contents) > 0:
            c = contents.pop()
            p = os.path.join(path, c)
            # os.walk could be used, but here we avoid internal GNU
            # Arch files and directories, thus saving a lot time.
            if not self._exclude(p):
                if os.path.isdir(p):
                    contents += [os.path.join(c, f) for f in os.listdir(p)]
                else:
                    files.append(c)
        return files

    def _rendirchanges(self, src, dest):
        changes = []
        copies = {}
        files = self._readcontents(os.path.join(self.tmppath, dest))
        for f in files:
            s = os.path.join(src, f)
            d = os.path.join(dest, f)
            changes.append(s)
            changes.append(d)
            copies[d] = s
        return changes, copies

    def _obtainrevision(self, rev):
        self.ui.debug('obtaining revision %s...\n' % rev)
        output = self._execute('get', rev, self.tmppath)
        self.checkexit(output)
        self.ui.debug('analyzing revision %s...\n' % rev)
        files = self._readcontents(self.tmppath)
        self.changes[rev].add_files += files

    def _stripbasepath(self, path):
        if path.startswith('./'):
            return path[2:]
        return path

    def _parsecatlog(self, data, rev):
        try:
            catlog = self.catlogparser.parsestr(data)

            # Commit date
            self.changes[rev].date = dateutil.datestr(
                dateutil.strdate(catlog['Standard-date'],
                             '%Y-%m-%d %H:%M:%S'))

            # Commit author
            self.changes[rev].author = self.recode(catlog['Creator'])

            # Commit description
            self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
                                                    catlog.get_payload()))
            self.changes[rev].summary = self.recode(self.changes[rev].summary)

            # Commit revision origin when dealing with a branch or tag
            if 'Continuation-of' in catlog:
                self.changes[rev].continuationof = self.recode(
                    catlog['Continuation-of'])
        except Exception:
            raise error.Abort(_('could not parse cat-log of %s') % rev)

    def _parsechangeset(self, data, rev):
        for l in data:
            l = l.strip()
            # Added file (ignore added directory)
            if l.startswith('A') and not l.startswith('A/'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].add_files.append(file)
            # Deleted file (ignore deleted directory)
            elif l.startswith('D') and not l.startswith('D/'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].del_files.append(file)
            # Modified binary file
            elif l.startswith('Mb'):
                file = self._stripbasepath(l[2:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Modified link
            elif l.startswith('M->'):
                file = self._stripbasepath(l[3:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Modified file
            elif l.startswith('M'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Renamed file (or link)
            elif l.startswith('=>'):
                files = l[2:].strip().split(' ')
                if len(files) == 1:
                    files = l[2:].strip().split('\t')
                src = self._stripbasepath(files[0])
                dst = self._stripbasepath(files[1])
                if not self._exclude(src) and not self._exclude(dst):
                    self.changes[rev].ren_files[src] = dst
            # Conversion from file to link or from link to file (modified)
            elif l.startswith('ch'):
                file = self._stripbasepath(l[2:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Renamed directory
            elif l.startswith('/>'):
                dirs = l[2:].strip().split(' ')
                if len(dirs) == 1:
                    dirs = l[2:].strip().split('\t')
                src = self._stripbasepath(dirs[0])
                dst = self._stripbasepath(dirs[1])
                if not self._exclude(src) and not self._exclude(dst):
                    self.changes[rev].ren_dirs[src] = dst