summaryrefslogtreecommitdiff
path: root/git/db/py/resolve.py
blob: 4301c2ad1812aadc88ab4b4ddd2d138358111f68 (plain)
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
"""Module with an implementation for refspec parsing. It is the pure-python
version assuming compatible interface for reference and object types"""

from git.db.interface import ReferencesMixin
from git.exc import BadObject
from git.refs import (
    SymbolicReference,
    Reference,
    HEAD,
    Head,
    TagReference
)
from git.refs.head import HEAD
from git.refs.headref import Head
from git.refs.tag import TagReference

from git.objects.base import Object
from git.objects.commit import Commit
from git.util import (
    join,
    isdir,
    isfile,
    hex_to_bin,
    bin_to_hex,
    is_git_dir
)
from string import digits
import os
import re

__all__ = ["PureReferencesMixin"]

#{ Utilities


def short_to_long(odb, hexsha):
    """:return: long hexadecimal sha1 from the given less-than-40 byte hexsha
        or None if no candidate could be found.
    :param hexsha: hexsha with less than 40 byte"""
    try:
        return bin_to_hex(odb.partial_to_complete_sha_hex(hexsha))
    except BadObject:
        return None
    # END exception handling


def name_to_object(repo, name, return_ref=False):
    """
    :return: object specified by the given name, hexshas ( short and long )
        as well as references are supported
    :param return_ref: if name specifies a reference, we will return the reference
        instead of the object. Otherwise it will raise BadObject
    """
    hexsha = None

    # is it a hexsha ? Try the most common ones, which is 7 to 40
    if repo.re_hexsha_shortened.match(name):
        if len(name) != 40:
            # find long sha for short sha
            hexsha = short_to_long(repo.odb, name)
        else:
            hexsha = name
        # END handle short shas
    # END find sha if it matches

    # if we couldn't find an object for what seemed to be a short hexsha
    # try to find it as reference anyway, it could be named 'aaa' for instance
    if hexsha is None:
        for base in ('%s', 'refs/%s', 'refs/tags/%s', 'refs/heads/%s', 'refs/remotes/%s', 'refs/remotes/%s/HEAD'):
            try:
                hexsha = SymbolicReference.dereference_recursive(repo, base % name)
                if return_ref:
                    return SymbolicReference(repo, base % name)
                # END handle symbolic ref
                break
            except ValueError:
                pass
        # END for each base
    # END handle hexsha

    # didn't find any ref, this is an error
    if return_ref:
        raise BadObject("Couldn't find reference named %r" % name)
    # END handle return ref

    # tried everything ? fail
    if hexsha is None:
        raise BadObject(name)
    # END assert hexsha was found

    return Object.new_from_sha(repo, hex_to_bin(hexsha))


def deref_tag(tag):
    """Recursively dereference a tag and return the resulting object"""
    while True:
        try:
            tag = tag.object
        except AttributeError:
            break
    # END dereference tag
    return tag


def to_commit(obj):
    """Convert the given object to a commit if possible and return it"""
    if obj.type == 'tag':
        obj = deref_tag(obj)

    if obj.type != "commit":
        raise ValueError("Cannot convert object %r to type commit" % obj)
    # END verify type
    return obj


def rev_parse(repo, rev):
    """
    :return: Object at the given revision, either Commit, Tag, Tree or Blob
    :param rev: git-rev-parse compatible revision specification, please see
        http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
        for details
    :note: Currently there is no access to the rev-log, rev-specs may only contain
        topological tokens such ~ and ^.
    :raise BadObject: if the given revision could not be found
    :raise ValueError: If rev couldn't be parsed
    :raise IndexError: If invalid reflog index is specified"""

    # colon search mode ?
    if rev.startswith(':/'):
        # colon search mode
        raise NotImplementedError("commit by message search ( regex )")
    # END handle search

    obj = None
    ref = None
    output_type = "commit"
    start = 0
    parsed_to = 0
    lr = len(rev)
    while start < lr:
        if rev[start] not in "^~:@":
            start += 1
            continue
        # END handle start

        token = rev[start]

        if obj is None:
            # token is a rev name
            if start == 0:
                ref = repo.head.ref
            else:
                if token == '@':
                    ref = name_to_object(repo, rev[:start], return_ref=True)
                else:
                    obj = name_to_object(repo, rev[:start])
                # END handle token
            # END handle refname

            if ref is not None:
                obj = ref.commit
            # END handle ref
        # END initialize obj on first token

        start += 1

        # try to parse {type}
        if start < lr and rev[start] == '{':
            end = rev.find('}', start)
            if end == -1:
                raise ValueError("Missing closing brace to define type in %s" % rev)
            output_type = rev[start + 1:end]  # exclude brace

            # handle type
            if output_type == 'commit':
                pass  # default
            elif output_type == 'tree':
                try:
                    obj = to_commit(obj).tree
                except (AttributeError, ValueError):
                    pass    # error raised later
                # END exception handling
            elif output_type in ('', 'blob'):
                if obj.type == 'tag':
                    obj = deref_tag(obj)
                else:
                    # cannot do anything for non-tags
                    pass
                # END handle tag
            elif token == '@':
                # try single int
                assert ref is not None, "Require Reference to access reflog"
                revlog_index = None
                try:
                    # transform reversed index into the format of our revlog
                    revlog_index = -(int(output_type) + 1)
                except ValueError:
                    # TODO: Try to parse the other date options, using parse_date
                    # maybe
                    raise NotImplementedError("Support for additional @{...} modes not implemented")
                # END handle revlog index

                try:
                    entry = ref.log_entry(revlog_index)
                except IndexError:
                    raise IndexError("Invalid revlog index: %i" % revlog_index)
                # END handle index out of bound

                obj = Object.new_from_sha(repo, hex_to_bin(entry.newhexsha))

                # make it pass the following checks
                output_type = None
            else:
                raise ValueError("Invalid output type: %s ( in %s )" % (output_type, rev))
            # END handle output type

            # empty output types don't require any specific type, its just about dereferencing tags
            if output_type and obj.type != output_type:
                raise ValueError("Could not accomodate requested object type %r, got %s" % (output_type, obj.type))
            # END verify ouput type

            start = end + 1                   # skip brace
            parsed_to = start
            continue
        # END parse type

        # try to parse a number
        num = 0
        if token != ":":
            found_digit = False
            while start < lr:
                if rev[start] in digits:
                    num = num * 10 + int(rev[start])
                    start += 1
                    found_digit = True
                else:
                    break
                # END handle number
            # END number parse loop

            # no explicit number given, 1 is the default
            # It could be 0 though
            if not found_digit:
                num = 1
            # END set default num
        # END number parsing only if non-blob mode

        parsed_to = start
        # handle hiererarchy walk
        try:
            if token == "~":
                obj = to_commit(obj)
                for item in xrange(num):
                    obj = obj.parents[0]
                # END for each history item to walk
            elif token == "^":
                obj = to_commit(obj)
                # must be n'th parent
                if num:
                    obj = obj.parents[num - 1]
            elif token == ":":
                if obj.type != "tree":
                    obj = obj.tree
                # END get tree type
                obj = obj[rev[start:]]
                parsed_to = lr
            else:
                raise ValueError("Invalid token: %r" % token)
            # END end handle tag
        except (IndexError, AttributeError):
            raise BadObject("Invalid Revision in %s" % rev)
        # END exception handling
    # END parse loop

    # still no obj ? Its probably a simple name
    if obj is None:
        obj = name_to_object(repo, rev)
        parsed_to = lr
    # END handle simple name

    if obj is None:
        raise ValueError("Revision specifier could not be parsed: %s" % rev)

    if parsed_to != lr:
        raise ValueError("Didn't consume complete rev spec %s, consumed part: %s" % (rev, rev[:parsed_to]))

    return obj

#} END utilities


class PureReferencesMixin(ReferencesMixin):

    """Pure-Python refparse implementation"""

    re_hexsha_only = re.compile('^[0-9A-Fa-f]{40}$')
    re_hexsha_shortened = re.compile('^[0-9A-Fa-f]{4,40}$')

    #{ Configuration
    # Types to use when instatiating references
    TagReferenceCls = TagReference
    HeadCls = Head
    ReferenceCls = Reference
    HEADCls = HEAD
    CommitCls = Commit
    #} END configuration

    def resolve(self, name):
        return self.resolve_object(name).binsha

    def resolve_object(self, name):
        return rev_parse(self, name)

    @property
    def references(self):
        return self.ReferenceCls.list_items(self)

    @property
    def heads(self):
        return self.HeadCls.list_items(self)

    @property
    def tags(self):
        return self.TagReferenceCls.list_items(self)

    def tag(self, name):
        return self.TagReferenceCls(self, self.TagReferenceCls.to_full_path(name))

    def commit(self, rev=None):
        if rev is None:
            return self.head.commit
        else:
            return self.resolve_object(str(rev) + "^0")
        # END handle revision

    def iter_trees(self, *args, **kwargs):
        return (c.tree for c in self.iter_commits(*args, **kwargs))

    def tree(self, rev=None):
        if rev is None:
            return self.head.commit.tree
        else:
            return self.resolve_object(str(rev) + "^{tree}")

    def iter_commits(self, rev=None, paths='', **kwargs):
        if rev is None:
            rev = self.head.commit

        return self.CommitCls.iter_items(self, rev, paths, **kwargs)

    @property
    def head(self):
        return self.HEADCls(self, 'HEAD')

    def create_head(self, path, commit='HEAD', force=False, logmsg=None):
        return self.HeadCls.create(self, path, commit, force, logmsg)

    def delete_head(self, *heads, **kwargs):
        return self.HeadCls.delete(self, *heads, **kwargs)

    def create_tag(self, path, ref='HEAD', message=None, force=False, **kwargs):
        return self.TagReferenceCls.create(self, path, ref, message, force, **kwargs)

    def delete_tag(self, *tags):
        return self.TagReferenceCls.delete(self, *tags)