~bzr-pqm/bzr/bzr.dev

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
# (C) 2005 Canonical Ltd

# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA


# This should really be an id randomly assigned when the tree is
# created, but it's not for now.
ROOT_ID = "TREE_ROOT"


import sys, os.path, types, re

try:
    from cElementTree import Element, ElementTree, SubElement
except ImportError:
    from elementtree.ElementTree import Element, ElementTree, SubElement

from xml import XMLMixin
from errors import bailout, BzrError, BzrCheckError

import bzrlib
from bzrlib.osutils import uuid, quotefn, splitpath, joinpath, appendpath
from bzrlib.trace import mutter

class InventoryEntry(XMLMixin):
    """Description of a versioned file.

    An InventoryEntry has the following fields, which are also
    present in the XML inventory-entry element:

    * *file_id*
    * *name*: (only the basename within the directory, must not
      contain slashes)
    * *kind*: "directory" or "file"
    * *directory_id*: (if absent/null means the branch root directory)
    * *text_sha1*: only for files
    * *text_size*: in bytes, only for files 
    * *text_id*: identifier for the text version, only for files

    InventoryEntries can also exist inside a WorkingTree
    inventory, in which case they are not yet bound to a
    particular revision of the file.  In that case the text_sha1,
    text_size and text_id are absent.


    >>> i = Inventory()
    >>> i.path2id('')
    'TREE_ROOT'
    >>> i.add(InventoryEntry('123', 'src', 'directory', ROOT_ID))
    >>> i.add(InventoryEntry('2323', 'hello.c', 'file', parent_id='123'))
    >>> for j in i.iter_entries():
    ...   print j
    ... 
    ('src', InventoryEntry('123', 'src', kind='directory', parent_id='TREE_ROOT'))
    ('src/hello.c', InventoryEntry('2323', 'hello.c', kind='file', parent_id='123'))
    >>> i.add(InventoryEntry('2323', 'bye.c', 'file', '123'))
    Traceback (most recent call last):
    ...
    BzrError: ('inventory already contains entry with id {2323}', [])
    >>> i.add(InventoryEntry('2324', 'bye.c', 'file', '123'))
    >>> i.add(InventoryEntry('2325', 'wibble', 'directory', '123'))
    >>> i.path2id('src/wibble')
    '2325'
    >>> '2325' in i
    True
    >>> i.add(InventoryEntry('2326', 'wibble.c', 'file', '2325'))
    >>> i['2326']
    InventoryEntry('2326', 'wibble.c', kind='file', parent_id='2325')
    >>> for j in i.iter_entries():
    ...     print j[0]
    ...     assert i.path2id(j[0])
    ... 
    src
    src/bye.c
    src/hello.c
    src/wibble
    src/wibble/wibble.c
    >>> i.id2path('2326')
    'src/wibble/wibble.c'

    TODO: Maybe also keep the full path of the entry, and the children?
           But those depend on its position within a particular inventory, and
           it would be nice not to need to hold the backpointer here.
    """

    # TODO: split InventoryEntry into subclasses for files,
    # directories, etc etc.

    text_sha1 = None
    text_size = None
    
    def __init__(self, file_id, name, kind, parent_id, text_id=None):
        """Create an InventoryEntry
        
        The filename must be a single component, relative to the
        parent directory; it cannot be a whole path or relative name.

        >>> e = InventoryEntry('123', 'hello.c', 'file', ROOT_ID)
        >>> e.name
        'hello.c'
        >>> e.file_id
        '123'
        >>> e = InventoryEntry('123', 'src/hello.c', 'file', ROOT_ID)
        Traceback (most recent call last):
        BzrCheckError: InventoryEntry name 'src/hello.c' is invalid
        """
        if '/' in name or '\\' in name:
            raise BzrCheckError('InventoryEntry name %r is invalid' % name)
        
        self.file_id = file_id
        self.name = name
        self.kind = kind
        self.text_id = text_id
        self.parent_id = parent_id
        if kind == 'directory':
            self.children = {}
        elif kind == 'file':
            pass
        else:
            raise BzrError("unhandled entry kind %r" % kind)



    def sorted_children(self):
        l = self.children.items()
        l.sort()
        return l


    def copy(self):
        other = InventoryEntry(self.file_id, self.name, self.kind,
                               self.parent_id, text_id=self.text_id)
        other.text_sha1 = self.text_sha1
        other.text_size = self.text_size
        # note that children are *not* copied; they're pulled across when
        # others are added
        return other


    def __repr__(self):
        return ("%s(%r, %r, kind=%r, parent_id=%r)"
                % (self.__class__.__name__,
                   self.file_id,
                   self.name,
                   self.kind,
                   self.parent_id))

    
    def to_element(self):
        """Convert to XML element"""
        e = Element('entry')

        e.set('name', self.name)
        e.set('file_id', self.file_id)
        e.set('kind', self.kind)

        if self.text_size != None:
            e.set('text_size', '%d' % self.text_size)
            
        for f in ['text_id', 'text_sha1']:
            v = getattr(self, f)
            if v != None:
                e.set(f, v)

        # to be conservative, we don't externalize the root pointers
        # for now, leaving them as null in the xml form.  in a future
        # version it will be implied by nested elements.
        if self.parent_id != ROOT_ID:
            assert isinstance(self.parent_id, basestring)
            e.set('parent_id', self.parent_id)

        e.tail = '\n'
            
        return e


    def from_element(cls, elt):
        assert elt.tag == 'entry'

        ## original format inventories don't have a parent_id for
        ## nodes in the root directory, but it's cleaner to use one
        ## internally.
        parent_id = elt.get('parent_id')
        if parent_id == None:
            parent_id = ROOT_ID

        self = cls(elt.get('file_id'), elt.get('name'), elt.get('kind'), parent_id)
        self.text_id = elt.get('text_id')
        self.text_sha1 = elt.get('text_sha1')
        
        ## mutter("read inventoryentry: %r" % (elt.attrib))

        v = elt.get('text_size')
        self.text_size = v and int(v)

        return self
            

    from_element = classmethod(from_element)

    def __eq__(self, other):
        if not isinstance(other, InventoryEntry):
            return NotImplemented

        return (self.file_id == other.file_id) \
               and (self.name == other.name) \
               and (self.text_sha1 == other.text_sha1) \
               and (self.text_size == other.text_size) \
               and (self.text_id == other.text_id) \
               and (self.parent_id == other.parent_id) \
               and (self.kind == other.kind)


    def __ne__(self, other):
        return not (self == other)

    def __hash__(self):
        raise ValueError('not hashable')



class RootEntry(InventoryEntry):
    def __init__(self, file_id):
        self.file_id = file_id
        self.children = {}
        self.kind = 'root_directory'
        self.parent_id = None
        self.name = ''

    def __eq__(self, other):
        if not isinstance(other, RootEntry):
            return NotImplemented
        
        return (self.file_id == other.file_id) \
               and (self.children == other.children)



class Inventory(XMLMixin):
    """Inventory of versioned files in a tree.

    This describes which file_id is present at each point in the tree,
    and possibly the SHA-1 or other information about the file.
    Entries can be looked up either by path or by file_id.

    The inventory represents a typical unix file tree, with
    directories containing files and subdirectories.  We never store
    the full path to a file, because renaming a directory implicitly
    moves all of its contents.  This class internally maintains a
    lookup tree that allows the children under a directory to be
    returned quickly.

    InventoryEntry objects must not be modified after they are
    inserted, other than through the Inventory API.

    >>> inv = Inventory()
    >>> inv.write_xml(sys.stdout)
    <inventory>
    </inventory>
    >>> inv.add(InventoryEntry('123-123', 'hello.c', 'file', ROOT_ID))
    >>> inv['123-123'].name
    'hello.c'

    May be treated as an iterator or set to look up file ids:
    
    >>> bool(inv.path2id('hello.c'))
    True
    >>> '123-123' in inv
    True

    May also look up by name:

    >>> [x[0] for x in inv.iter_entries()]
    ['hello.c']
    
    >>> inv.write_xml(sys.stdout)
    <inventory>
    <entry file_id="123-123" kind="file" name="hello.c" />
    </inventory>

    """
    def __init__(self):
        """Create or read an inventory.

        If a working directory is specified, the inventory is read
        from there.  If the file is specified, read from that. If not,
        the inventory is created empty.

        The inventory is created with a default root directory, with
        an id of None.
        """
        self.root = RootEntry(ROOT_ID)
        self._byid = {self.root.file_id: self.root}


    def __iter__(self):
        return iter(self._byid)


    def __len__(self):
        """Returns number of entries."""
        return len(self._byid)


    def iter_entries(self, from_dir=None):
        """Return (path, entry) pairs, in order by name."""
        if from_dir == None:
            assert self.root
            from_dir = self.root
        elif isinstance(from_dir, basestring):
            from_dir = self._byid[from_dir]
            
        kids = from_dir.children.items()
        kids.sort()
        for name, ie in kids:
            yield name, ie
            if ie.kind == 'directory':
                for cn, cie in self.iter_entries(from_dir=ie.file_id):
                    yield os.path.join(name, cn), cie


    def entries(self):
        """Return list of (path, ie) for all entries except the root.

        This may be faster than iter_entries.
        """
        accum = []
        def descend(dir_ie, dir_path):
            kids = dir_ie.children.items()
            kids.sort()
            for name, ie in kids:
                child_path = os.path.join(dir_path, name)
                accum.append((child_path, ie))
                if ie.kind == 'directory':
                    descend(ie, child_path)

        descend(self.root, '')
        return accum


    def directories(self):
        """Return (path, entry) pairs for all directories, including the root.
        """
        accum = []
        def descend(parent_ie, parent_path):
            accum.append((parent_path, parent_ie))
            
            kids = [(ie.name, ie) for ie in parent_ie.children.itervalues() if ie.kind == 'directory']
            kids.sort()

            for name, child_ie in kids:
                child_path = os.path.join(parent_path, name)
                descend(child_ie, child_path)
        descend(self.root, '')
        return accum
        


    def __contains__(self, file_id):
        """True if this entry contains a file with given id.

        >>> inv = Inventory()
        >>> inv.add(InventoryEntry('123', 'foo.c', 'file', ROOT_ID))
        >>> '123' in inv
        True
        >>> '456' in inv
        False
        """
        return file_id in self._byid


    def __getitem__(self, file_id):
        """Return the entry for given file_id.

        >>> inv = Inventory()
        >>> inv.add(InventoryEntry('123123', 'hello.c', 'file', ROOT_ID))
        >>> inv['123123'].name
        'hello.c'
        """
        try:
            return self._byid[file_id]
        except KeyError:
            if file_id == None:
                raise BzrError("can't look up file_id None")
            else:
                raise BzrError("file_id {%s} not in inventory" % file_id)


    def get_file_kind(self, file_id):
        return self._byid[file_id].kind

    def get_child(self, parent_id, filename):
        return self[parent_id].children.get(filename)


    def add(self, entry):
        """Add entry to inventory.

        To add  a file to a branch ready to be committed, use Branch.add,
        which calls this."""
        if entry.file_id in self._byid:
            bailout("inventory already contains entry with id {%s}" % entry.file_id)

        try:
            parent = self._byid[entry.parent_id]
        except KeyError:
            bailout("parent_id {%s} not in inventory" % entry.parent_id)

        if parent.children.has_key(entry.name):
            bailout("%s is already versioned" %
                    appendpath(self.id2path(parent.file_id), entry.name))

        self._byid[entry.file_id] = entry
        parent.children[entry.name] = entry


    def add_path(self, relpath, kind, file_id=None):
        """Add entry from a path.

        The immediate parent must already be versioned"""
        parts = bzrlib.osutils.splitpath(relpath)
        if len(parts) == 0:
            bailout("cannot re-add root of inventory")

        if file_id == None:
            file_id = bzrlib.branch.gen_file_id(relpath)

        parent_id = self.path2id(parts[:-1])
        assert parent_id != None
        ie = InventoryEntry(file_id, parts[-1],
                            kind=kind, parent_id=parent_id)
        return self.add(ie)


    def __delitem__(self, file_id):
        """Remove entry by id.

        >>> inv = Inventory()
        >>> inv.add(InventoryEntry('123', 'foo.c', 'file', ROOT_ID))
        >>> '123' in inv
        True
        >>> del inv['123']
        >>> '123' in inv
        False
        """
        ie = self[file_id]

        assert self[ie.parent_id].children[ie.name] == ie
        
        # TODO: Test deleting all children; maybe hoist to a separate
        # deltree method?
        if ie.kind == 'directory':
            for cie in ie.children.values():
                del self[cie.file_id]
            del ie.children

        del self._byid[file_id]
        del self[ie.parent_id].children[ie.name]


    def to_element(self):
        """Convert to XML Element"""
        e = Element('inventory')
        e.text = '\n'
        for path, ie in self.iter_entries():
            e.append(ie.to_element())
        return e
    

    def from_element(cls, elt):
        """Construct from XML Element

        >>> inv = Inventory()
        >>> inv.add(InventoryEntry('foo.c-123981239', 'foo.c', 'file', ROOT_ID))
        >>> elt = inv.to_element()
        >>> inv2 = Inventory.from_element(elt)
        >>> inv2 == inv
        True
        """
        assert elt.tag == 'inventory'
        o = cls()
        for e in elt:
            o.add(InventoryEntry.from_element(e))
        return o
        
    from_element = classmethod(from_element)


    def __eq__(self, other):
        """Compare two sets by comparing their contents.

        >>> i1 = Inventory()
        >>> i2 = Inventory()
        >>> i1 == i2
        True
        >>> i1.add(InventoryEntry('123', 'foo', 'file', ROOT_ID))
        >>> i1 == i2
        False
        >>> i2.add(InventoryEntry('123', 'foo', 'file', ROOT_ID))
        >>> i1 == i2
        True
        """
        if not isinstance(other, Inventory):
            return NotImplemented

        if len(self._byid) != len(other._byid):
            # shortcut: obviously not the same
            return False

        return self._byid == other._byid


    def __ne__(self, other):
        return not (self == other)


    def __hash__(self):
        raise ValueError('not hashable')



    def get_idpath(self, file_id):
        """Return a list of file_ids for the path to an entry.

        The list contains one element for each directory followed by
        the id of the file itself.  So the length of the returned list
        is equal to the depth of the file in the tree, counting the
        root directory as depth 1.
        """
        p = []
        while file_id != None:
            try:
                ie = self._byid[file_id]
            except KeyError:
                bailout("file_id {%s} not found in inventory" % file_id)
            p.insert(0, ie.file_id)
            file_id = ie.parent_id
        return p


    def id2path(self, file_id):
        """Return as a list the path to file_id."""

        # get all names, skipping root
        p = [self[fid].name for fid in self.get_idpath(file_id)[1:]]
        return os.sep.join(p)
            


    def path2id(self, name):
        """Walk down through directories to return entry of last component.

        names may be either a list of path components, or a single
        string, in which case it is automatically split.

        This returns the entry of the last component in the path,
        which may be either a file or a directory.

        Returns None iff the path is not found.
        """
        if isinstance(name, types.StringTypes):
            name = splitpath(name)

        mutter("lookup path %r" % name)

        parent = self.root
        for f in name:
            try:
                cie = parent.children[f]
                assert cie.name == f
                assert cie.parent_id == parent.file_id
                parent = cie
            except KeyError:
                # or raise an error?
                return None

        return parent.file_id


    def has_filename(self, names):
        return bool(self.path2id(names))


    def has_id(self, file_id):
        return self._byid.has_key(file_id)


    def rename(self, file_id, new_parent_id, new_name):
        """Move a file within the inventory.

        This can change either the name, or the parent, or both.

        This does not move the working file."""
        if not is_valid_name(new_name):
            bailout("not an acceptable filename: %r" % new_name)

        new_parent = self._byid[new_parent_id]
        if new_name in new_parent.children:
            bailout("%r already exists in %r" % (new_name, self.id2path(new_parent_id)))

        new_parent_idpath = self.get_idpath(new_parent_id)
        if file_id in new_parent_idpath:
            bailout("cannot move directory %r into a subdirectory of itself, %r"
                    % (self.id2path(file_id), self.id2path(new_parent_id)))

        file_ie = self._byid[file_id]
        old_parent = self._byid[file_ie.parent_id]

        # TODO: Don't leave things messed up if this fails

        del old_parent.children[file_ie.name]
        new_parent.children[new_name] = file_ie
        
        file_ie.name = new_name
        file_ie.parent_id = new_parent_id




_NAME_RE = re.compile(r'^[^/\\]+$')

def is_valid_name(name):
    return bool(_NAME_RE.match(name))