File: upstream_import.py

package info (click to toggle)
bzrtools 2.6.0-4
  • links: PTS, VCS
  • area: main
  • in suites: buster, sid
  • size: 740 kB
  • sloc: python: 4,299; sh: 13; makefile: 10
file content (335 lines) | stat: -rw-r--r-- 10,553 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
"""Import upstream source into a branch"""

import errno
import os
import re
from StringIO import StringIO
import stat
import tarfile
import zipfile

from bzrlib import generate_ids
from bzrlib.bzrdir import BzrDir
from bzrlib.errors import NoSuchFile, BzrCommandError, NotBranchError
from bzrlib.osutils import (pathjoin, isdir, file_iterator, basename,
                            file_kind, splitpath)
from bzrlib.trace import warning
from bzrlib.transform import TreeTransform, resolve_conflicts, cook_conflicts
from bzrlib.workingtree import WorkingTree
from bzrlib.plugins.bzrtools.bzrtools import open_from_url
from bzrlib.plugins.bzrtools import errors

class ZipFileWrapper(object):

    def __init__(self, fileobj, mode):
        self.zipfile = zipfile.ZipFile(fileobj, mode)

    def getmembers(self):
        for info in self.zipfile.infolist():
            yield ZipInfoWrapper(self.zipfile, info)

    def extractfile(self, infowrapper):
        return StringIO(self.zipfile.read(infowrapper.name))

    def add(self, filename):
        if isdir(filename):
            self.zipfile.writestr(filename+'/', '')
        else:
            self.zipfile.write(filename)

    def close(self):
        self.zipfile.close()


class ZipInfoWrapper(object):

    def __init__(self, zipfile, info):
        self.info = info
        self.type = None
        self.name = info.filename
        self.zipfile = zipfile
        self.mode = 0666

    def isdir(self):
        # Really? Eeeew!
        return bool(self.name.endswith('/'))

    def isreg(self):
        # Really? Eeeew!
        return not self.isdir()


class DirWrapper(object):
    def __init__(self, fileobj, mode='r'):
        assert mode == 'r', mode
        self.root = os.path.realpath(fileobj.read())

    def __repr__(self):
        return 'DirWrapper(%r)' % self.root

    def getmembers(self, subdir=None):
        if subdir is not None:
            mydir = pathjoin(self.root, subdir)
        else:
            mydir = self.root
        for child in os.listdir(mydir):
            if subdir is not None:
                child = pathjoin(subdir, child)
            fi = FileInfo(self.root, child)
            yield fi
            if fi.isdir():
                for v in self.getmembers(child):
                    yield v

    def extractfile(self, member):
        return open(member.fullpath)


class FileInfo(object):

    def __init__(self, root, filepath):
        self.fullpath = pathjoin(root, filepath)
        self.root = root
        if filepath != '':
            self.name = pathjoin(basename(root), filepath)
        else:
            print 'root %r' % root
            self.name = basename(root)
        self.type = None
        stat = os.lstat(self.fullpath)
        self.mode = stat.st_mode
        if self.isdir():
            self.name += '/'

    def __repr__(self):
        return 'FileInfo(%r)' % self.name

    def isreg(self):
        return stat.S_ISREG(self.mode)

    def isdir(self):
        return stat.S_ISDIR(self.mode)

    def issym(self):
        if stat.S_ISLNK(self.mode):
            self.linkname = os.readlink(self.fullpath)
            return True
        else:
            return False


def top_path(path):
    """Return the top directory given in a path."""
    components = splitpath(path)
    if len(components) > 0:
        return components[0]
    else:
        return ''


def common_directory(names):
    """Determine a single directory prefix from a list of names"""
    possible_prefix = None
    for name in names:
        name_top = top_path(name)
        if name_top == '':
            return None
        if possible_prefix is None:
            possible_prefix = name_top
        else:
            if name_top != possible_prefix:
                return None
    return possible_prefix


def do_directory(tt, trans_id, tree, relative_path, path):
    if isdir(path) and tree.path2id(relative_path) is not None:
        tt.cancel_deletion(trans_id)
    else:
        tt.create_directory(trans_id)


def add_implied_parents(implied_parents, path):
    """Update the set of implied parents from a path"""
    parent = os.path.dirname(path)
    if parent in implied_parents:
        return
    implied_parents.add(parent)
    add_implied_parents(implied_parents, parent)


def names_of_files(tar_file):
    for member in tar_file.getmembers():
        if member.type != "g":
            yield member.name


def should_ignore(relative_path):
    return top_path(relative_path) == '.bzr'


def import_tar(tree, tar_input):
    """Replace the contents of a working directory with tarfile contents.
    The tarfile may be a gzipped stream.  File ids will be updated.
    """
    tar_file = tarfile.open('lala', 'r', tar_input)
    import_archive(tree, tar_file)

def import_zip(tree, zip_input):
    zip_file = ZipFileWrapper(zip_input, 'r')
    import_archive(tree, zip_file)

def import_dir(tree, dir_input):
    dir_file = DirWrapper(dir_input)
    import_archive(tree, dir_file)


def import_archive(tree, archive_file):
    tt = TreeTransform(tree)
    try:
        import_archive_to_transform(tree, archive_file, tt)
        tt.apply()
    finally:
        tt.finalize()


def import_archive_to_transform(tree, archive_file, tt):
    prefix = common_directory(names_of_files(archive_file))
    removed = set()
    for path, entry in tree.iter_entries_by_dir():
        if entry.parent_id is None:
            continue
        trans_id = tt.trans_id_tree_path(path)
        tt.delete_contents(trans_id)
        removed.add(path)

    added = set()
    implied_parents = set()
    seen = set()
    for member in archive_file.getmembers():
        if member.type == 'g':
            # type 'g' is a header
            continue
        # Inverse functionality in bzr uses utf-8.  We could also
        # interpret relative to fs encoding, which would match native
        # behaviour better.
        relative_path = member.name.decode('utf-8')
        if prefix is not None:
            relative_path = relative_path[len(prefix)+1:]
            relative_path = relative_path.rstrip('/')
        if relative_path == '':
            continue
        if should_ignore(relative_path):
            continue
        add_implied_parents(implied_parents, relative_path)
        trans_id = tt.trans_id_tree_path(relative_path)
        added.add(relative_path.rstrip('/'))
        path = tree.abspath(relative_path)
        if member.name in seen:
            if tt.final_kind(trans_id) == 'file':
                tt.set_executability(None, trans_id)
            tt.cancel_creation(trans_id)
        seen.add(member.name)
        if member.isreg():
            tt.create_file(file_iterator(archive_file.extractfile(member)),
                           trans_id)
            executable = (member.mode & 0111) != 0
            tt.set_executability(executable, trans_id)
        elif member.isdir():
            do_directory(tt, trans_id, tree, relative_path, path)
        elif member.issym():
            tt.create_symlink(member.linkname, trans_id)
        else:
            continue
        if tt.tree_file_id(trans_id) is None:
            name = basename(member.name.rstrip('/'))
            file_id = generate_ids.gen_file_id(name)
            tt.version_file(file_id, trans_id)

    for relative_path in implied_parents.difference(added):
        if relative_path == "":
            continue
        trans_id = tt.trans_id_tree_path(relative_path)
        path = tree.abspath(relative_path)
        do_directory(tt, trans_id, tree, relative_path, path)
        if tt.tree_file_id(trans_id) is None:
            tt.version_file(trans_id, trans_id)
        added.add(relative_path)

    for path in removed.difference(added):
        tt.unversion_file(tt.trans_id_tree_path(path))

    for conflict in cook_conflicts(resolve_conflicts(tt), tt):
        warning(conflict)


def do_import(source, tree_directory=None):
    """Implementation of import command.  Intended for UI only"""
    if tree_directory is not None:
        try:
            tree = WorkingTree.open(tree_directory)
        except NotBranchError:
            if not os.path.exists(tree_directory):
                os.mkdir(tree_directory)
            branch = BzrDir.create_branch_convenience(tree_directory)
            tree = branch.bzrdir.open_workingtree()
    else:
        tree = WorkingTree.open_containing('.')[0]
    tree.lock_write()
    try:
        if tree.changes_from(tree.basis_tree()).has_changed():
            raise BzrCommandError("Working tree has uncommitted changes.")

        try:
            archive, external_compressor = get_archive_type(source)
        except errors.NotArchiveType:
            if file_kind(source) == 'directory':
                s = StringIO(source)
                s.seek(0)
                import_dir(tree, s)
            else:
                raise BzrCommandError('Unhandled import source')
        else:
            if archive == 'zip':
                import_zip(tree, open_from_url(source))
            elif archive == 'tar':
                try:
                    tar_input = open_from_url(source)
                    if external_compressor == 'bz2':
                        import bz2
                        tar_input = StringIO(bz2.decompress(tar_input.read()))
                    elif external_compressor == 'lzma':
                        import lzma
                        tar_input = StringIO(lzma.decompress(tar_input.read()))
                except IOError, e:
                    if e.errno == errno.ENOENT:
                        raise NoSuchFile(source)
                try:
                    import_tar(tree, tar_input)
                finally:
                    tar_input.close()
    finally:
        tree.unlock()


def get_archive_type(path):
    """Return the type of archive and compressor indicated by path name.

    Only external compressors are returned, so zip files are only
    ('zip', None).  .tgz is treated as ('tar', 'gz') and '.tar.xz' is treated
    as ('tar', 'lzma').
    """
    matches = re.match(r'.*\.(zip|tgz|tar(.(gz|bz2|lzma|xz))?)$', path)
    if not matches:
        raise errors.NotArchiveType(path)
    external_compressor = None
    if matches.group(3) is not None:
        archive = 'tar'
        external_compressor = matches.group(3)
        if external_compressor == 'xz':
            external_compressor = 'lzma'
    elif matches.group(1) == 'tgz':
        return 'tar', 'gz'
    else:
        archive = matches.group(1)
    return archive, external_compressor