summaryrefslogtreecommitdiff
path: root/mercurial/match.py
blob: 927cd59233f385bbe8d04d786f78463ebd686069 (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
# match.py - filename matching
#
#  Copyright 2008, 2009 Matt Mackall <mpm@selenic.com> 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.

import re
import scmutil, util, fileset
from i18n import _

def _rematcher(pat):
    m = util.compilere(pat)
    try:
        # slightly faster, provided by facebook's re2 bindings
        return m.test_match
    except AttributeError:
        return m.match

def _expandsets(pats, ctx):
    '''convert set: patterns into a list of files in the given context'''
    fset = set()
    other = []

    for kind, expr in pats:
        if kind == 'set':
            if not ctx:
                raise util.Abort("fileset expression with no context")
            s = fileset.getfileset(ctx, expr)
            fset.update(s)
            continue
        other.append((kind, expr))
    return fset, other

class match(object):
    def __init__(self, root, cwd, patterns, include=[], exclude=[],
                 default='glob', exact=False, auditor=None, ctx=None):
        """build an object to match a set of file patterns

        arguments:
        root - the canonical root of the tree you're matching against
        cwd - the current working directory, if relevant
        patterns - patterns to find
        include - patterns to include
        exclude - patterns to exclude
        default - if a pattern in names has no explicit type, assume this one
        exact - patterns are actually literals

        a pattern is one of:
        'glob:<glob>' - a glob relative to cwd
        're:<regexp>' - a regular expression
        'path:<path>' - a path relative to canonroot
        'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
        'relpath:<path>' - a path relative to cwd
        'relre:<regexp>' - a regexp that needn't match the start of a name
        'set:<fileset>' - a fileset expression
        '<something>' - a pattern of the specified default type
        """

        self._root = root
        self._cwd = cwd
        self._files = []
        self._anypats = bool(include or exclude)
        self._ctx = ctx

        if include:
            pats = _normalize(include, 'glob', root, cwd, auditor)
            self.includepat, im = _buildmatch(ctx, pats, '(?:/|$)')
        if exclude:
            pats = _normalize(exclude, 'glob', root, cwd, auditor)
            self.excludepat, em = _buildmatch(ctx, pats, '(?:/|$)')
        if exact:
            if isinstance(patterns, list):
                self._files = patterns
            else:
                self._files = list(patterns)
            pm = self.exact
        elif patterns:
            pats = _normalize(patterns, default, root, cwd, auditor)
            self._files = _roots(pats)
            self._anypats = self._anypats or _anypats(pats)
            self.patternspat, pm = _buildmatch(ctx, pats, '$')

        if patterns or exact:
            if include:
                if exclude:
                    m = lambda f: im(f) and not em(f) and pm(f)
                else:
                    m = lambda f: im(f) and pm(f)
            else:
                if exclude:
                    m = lambda f: not em(f) and pm(f)
                else:
                    m = pm
        else:
            if include:
                if exclude:
                    m = lambda f: im(f) and not em(f)
                else:
                    m = im
            else:
                if exclude:
                    m = lambda f: not em(f)
                else:
                    m = lambda f: True

        self.matchfn = m
        self._fmap = set(self._files)

    def __call__(self, fn):
        return self.matchfn(fn)
    def __iter__(self):
        for f in self._files:
            yield f
    def bad(self, f, msg):
        '''callback for each explicit file that can't be
        found/accessed, with an error message
        '''
        pass
    def dir(self, f):
        pass
    def missing(self, f):
        pass
    def exact(self, f):
        return f in self._fmap
    def rel(self, f):
        return util.pathto(self._root, self._cwd, f)
    def files(self):
        return self._files
    def anypats(self):
        return self._anypats
    def always(self):
        return False

class exact(match):
    def __init__(self, root, cwd, files):
        match.__init__(self, root, cwd, files, exact = True)

class always(match):
    def __init__(self, root, cwd):
        match.__init__(self, root, cwd, [])
    def always(self):
        return True

class narrowmatcher(match):
    """Adapt a matcher to work on a subdirectory only.

    The paths are remapped to remove/insert the path as needed:

    >>> m1 = match('root', '', ['a.txt', 'sub/b.txt'])
    >>> m2 = narrowmatcher('sub', m1)
    >>> bool(m2('a.txt'))
    False
    >>> bool(m2('b.txt'))
    True
    >>> bool(m2.matchfn('a.txt'))
    False
    >>> bool(m2.matchfn('b.txt'))
    True
    >>> m2.files()
    ['b.txt']
    >>> m2.exact('b.txt')
    True
    >>> m2.rel('b.txt')
    'b.txt'
    >>> def bad(f, msg):
    ...     print "%s: %s" % (f, msg)
    >>> m1.bad = bad
    >>> m2.bad('x.txt', 'No such file')
    sub/x.txt: No such file
    """

    def __init__(self, path, matcher):
        self._root = matcher._root
        self._cwd = matcher._cwd
        self._path = path
        self._matcher = matcher

        self._files = [f[len(path) + 1:] for f in matcher._files
                       if f.startswith(path + "/")]
        self._anypats = matcher._anypats
        self.matchfn = lambda fn: matcher.matchfn(self._path + "/" + fn)
        self._fmap = set(self._files)

    def bad(self, f, msg):
        self._matcher.bad(self._path + "/" + f, msg)

def patkind(pat):
    return _patsplit(pat, None)[0]

def _patsplit(pat, default):
    """Split a string into an optional pattern kind prefix and the
    actual pattern."""
    if ':' in pat:
        kind, val = pat.split(':', 1)
        if kind in ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                    'listfile', 'listfile0', 'set'):
            return kind, val
    return default, pat

def _globre(pat):
    "convert a glob pattern into a regexp"
    i, n = 0, len(pat)
    res = ''
    group = 0
    escape = re.escape
    def peek():
        return i < n and pat[i]
    while i < n:
        c = pat[i]
        i += 1
        if c not in '*?[{},\\':
            res += escape(c)
        elif c == '*':
            if peek() == '*':
                i += 1
                res += '.*'
            else:
                res += '[^/]*'
        elif c == '?':
            res += '.'
        elif c == '[':
            j = i
            if j < n and pat[j] in '!]':
                j += 1
            while j < n and pat[j] != ']':
                j += 1
            if j >= n:
                res += '\\['
            else:
                stuff = pat[i:j].replace('\\','\\\\')
                i = j + 1
                if stuff[0] == '!':
                    stuff = '^' + stuff[1:]
                elif stuff[0] == '^':
                    stuff = '\\' + stuff
                res = '%s[%s]' % (res, stuff)
        elif c == '{':
            group += 1
            res += '(?:'
        elif c == '}' and group:
            res += ')'
            group -= 1
        elif c == ',' and group:
            res += '|'
        elif c == '\\':
            p = peek()
            if p:
                i += 1
                res += escape(p)
            else:
                res += escape(c)
        else:
            res += escape(c)
    return res

def _regex(kind, name, tail):
    '''convert a pattern into a regular expression'''
    if not name:
        return ''
    if kind == 're':
        return name
    elif kind == 'path':
        return '^' + re.escape(name) + '(?:/|$)'
    elif kind == 'relglob':
        return '(?:|.*/)' + _globre(name) + tail
    elif kind == 'relpath':
        return re.escape(name) + '(?:/|$)'
    elif kind == 'relre':
        if name.startswith('^'):
            return name
        return '.*' + name
    return _globre(name) + tail

def _buildmatch(ctx, pats, tail):
    fset, pats = _expandsets(pats, ctx)
    if not pats:
        return "", fset.__contains__

    pat, mf = _buildregexmatch(pats, tail)
    if fset:
        return pat, lambda f: f in fset or mf(f)
    return pat, mf

def _buildregexmatch(pats, tail):
    """build a matching function from a set of patterns"""
    try:
        pat = '(?:%s)' % '|'.join([_regex(k, p, tail) for (k, p) in pats])
        if len(pat) > 20000:
            raise OverflowError
        return pat, _rematcher(pat)
    except OverflowError:
        # We're using a Python with a tiny regex engine and we
        # made it explode, so we'll divide the pattern list in two
        # until it works
        l = len(pats)
        if l < 2:
            raise
        pata, a = _buildregexmatch(pats[:l//2], tail)
        patb, b = _buildregexmatch(pats[l//2:], tail)
        return pat, lambda s: a(s) or b(s)
    except re.error:
        for k, p in pats:
            try:
                _rematcher('(?:%s)' % _regex(k, p, tail))
            except re.error:
                raise util.Abort(_("invalid pattern (%s): %s") % (k, p))
        raise util.Abort(_("invalid pattern"))

def _normalize(names, default, root, cwd, auditor):
    pats = []
    for kind, name in [_patsplit(p, default) for p in names]:
        if kind in ('glob', 'relpath'):
            name = scmutil.canonpath(root, cwd, name, auditor)
        elif kind in ('relglob', 'path'):
            name = util.normpath(name)
        elif kind in ('listfile', 'listfile0'):
            try:
                files = util.readfile(name)
                if kind == 'listfile0':
                    files = files.split('\0')
                else:
                    files = files.splitlines()
                files = [f for f in files if f]
            except EnvironmentError:
                raise util.Abort(_("unable to read file list (%s)") % name)
            pats += _normalize(files, default, root, cwd, auditor)
            continue

        pats.append((kind, name))
    return pats

def _roots(patterns):
    r = []
    for kind, name in patterns:
        if kind == 'glob': # find the non-glob prefix
            root = []
            for p in name.split('/'):
                if '[' in p or '{' in p or '*' in p or '?' in p:
                    break
                root.append(p)
            r.append('/'.join(root) or '.')
        elif kind in ('relpath', 'path'):
            r.append(name or '.')
        elif kind == 'relglob':
            r.append('.')
    return r

def _anypats(patterns):
    for kind, name in patterns:
        if kind in ('glob', 're', 'relglob', 'relre', 'set'):
            return True