File: testparseutil.py

package info (click to toggle)
mercurial 6.3.2-1%2Bdeb12u1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 42,052 kB
  • sloc: python: 199,820; ansic: 46,300; tcl: 3,715; sh: 1,676; lisp: 1,483; cpp: 864; javascript: 649; makefile: 626; xml: 36; sql: 30
file content (667 lines) | stat: -rw-r--r-- 20,089 bytes parent folder | download
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
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
# testparseutil.py - utilities to parse test script for check tools
#
#  Copyright 2018 FUJIWARA Katsunori <foozy@lares.dti.ne.jp> 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 abc
import re
import sys

####################
# for Python3 compatibility (almost comes from mercurial/pycompat.py)

ispy3 = sys.version_info[0] >= 3


def identity(a):
    return a


def _rapply(f, xs):
    if xs is None:
        # assume None means non-value of optional data
        return xs
    if isinstance(xs, (list, set, tuple)):
        return type(xs)(_rapply(f, x) for x in xs)
    if isinstance(xs, dict):
        return type(xs)((_rapply(f, k), _rapply(f, v)) for k, v in xs.items())
    return f(xs)


def rapply(f, xs):
    if f is identity:
        # fast path mainly for py2
        return xs
    return _rapply(f, xs)


if ispy3:
    import builtins

    def bytestr(s):
        # tiny version of pycompat.bytestr
        return s.encode('latin1')

    def sysstr(s):
        if isinstance(s, builtins.str):
            return s
        return s.decode('latin-1')

    def opentext(f):
        return open(f, 'r')


else:
    bytestr = str
    sysstr = identity

    opentext = open


def b2s(x):
    # convert BYTES elements in "x" to SYSSTR recursively
    return rapply(sysstr, x)


def writeout(data):
    # write "data" in BYTES into stdout
    sys.stdout.write(data)


def writeerr(data):
    # write "data" in BYTES into stderr
    sys.stderr.write(data)


####################


class embeddedmatcher:  # pytype: disable=ignored-metaclass
    """Base class to detect embedded code fragments in *.t test script"""

    __metaclass__ = abc.ABCMeta

    def __init__(self, desc):
        self.desc = desc

    @abc.abstractmethod
    def startsat(self, line):
        """Examine whether embedded code starts at line

        This can return arbitrary object, and it is used as 'ctx' for
        subsequent method invocations.
        """

    @abc.abstractmethod
    def endsat(self, ctx, line):
        """Examine whether embedded code ends at line"""

    @abc.abstractmethod
    def isinside(self, ctx, line):
        """Examine whether line is inside embedded code, if not yet endsat"""

    @abc.abstractmethod
    def ignores(self, ctx):
        """Examine whether detected embedded code should be ignored"""

    @abc.abstractmethod
    def filename(self, ctx):
        """Return filename of embedded code

        If filename isn't specified for embedded code explicitly, this
        returns None.
        """

    @abc.abstractmethod
    def codeatstart(self, ctx, line):
        """Return actual code at the start line of embedded code

        This might return None, if the start line doesn't contain
        actual code.
        """

    @abc.abstractmethod
    def codeatend(self, ctx, line):
        """Return actual code at the end line of embedded code

        This might return None, if the end line doesn't contain actual
        code.
        """

    @abc.abstractmethod
    def codeinside(self, ctx, line):
        """Return actual code at line inside embedded code"""


def embedded(basefile, lines, errors, matchers):
    """pick embedded code fragments up from given lines

    This is common parsing logic, which examines specified matchers on
    given lines.

    :basefile: a name of a file, from which lines to be parsed come.
    :lines: to be parsed (might be a value returned by "open(basefile)")
    :errors: an array, into which messages for detected error are stored
    :matchers: an array of embeddedmatcher objects

    This function yields '(filename, starts, ends, code)' tuple.

    :filename: a name of embedded code, if it is explicitly specified
               (e.g.  "foobar" of "cat >> foobar <<EOF").
               Otherwise, this is None
    :starts: line number (1-origin), at which embedded code starts (inclusive)
    :ends: line number (1-origin), at which embedded code ends (exclusive)
    :code: extracted embedded code, which is single-stringified

    >>> class ambigmatcher:
    ...     # mock matcher class to examine implementation of
    ...     # "ambiguous matching" corner case
    ...     def __init__(self, desc, matchfunc):
    ...         self.desc = desc
    ...         self.matchfunc = matchfunc
    ...     def startsat(self, line):
    ...         return self.matchfunc(line)
    >>> ambig1 = ambigmatcher('ambiguous #1',
    ...                       lambda l: l.startswith('  $ cat '))
    >>> ambig2 = ambigmatcher('ambiguous #2',
    ...                       lambda l: l.endswith('<< EOF\\n'))
    >>> lines = ['  $ cat > foo.py << EOF\\n']
    >>> errors = []
    >>> matchers = [ambig1, ambig2]
    >>> list(t for t in embedded('<dummy>', lines, errors, matchers))
    []
    >>> b2s(errors)
    ['<dummy>:1: ambiguous line for "ambiguous #1", "ambiguous #2"']

    """
    matcher = None
    ctx = filename = code = startline = None  # for pyflakes

    for lineno, line in enumerate(lines, 1):
        if not line.endswith('\n'):
            line += '\n'  # to normalize EOF line
        if matcher:  # now, inside embedded code
            if matcher.endsat(ctx, line):
                codeatend = matcher.codeatend(ctx, line)
                if codeatend is not None:
                    code.append(codeatend)
                if not matcher.ignores(ctx):
                    yield (filename, startline, lineno, ''.join(code))
                matcher = None
                # DO NOT "continue", because line might start next fragment
            elif not matcher.isinside(ctx, line):
                # this is an error of basefile
                # (if matchers are implemented correctly)
                errors.append(
                    '%s:%d: unexpected line for "%s"'
                    % (basefile, lineno, matcher.desc)
                )
                # stop extracting embedded code by current 'matcher',
                # because appearance of unexpected line might mean
                # that expected end-of-embedded-code line might never
                # appear
                matcher = None
                # DO NOT "continue", because line might start next fragment
            else:
                code.append(matcher.codeinside(ctx, line))
                continue

        # examine whether current line starts embedded code or not
        assert not matcher

        matched = []
        for m in matchers:
            ctx = m.startsat(line)
            if ctx:
                matched.append((m, ctx))
        if matched:
            if len(matched) > 1:
                # this is an error of matchers, maybe
                errors.append(
                    '%s:%d: ambiguous line for %s'
                    % (
                        basefile,
                        lineno,
                        ', '.join(['"%s"' % m.desc for m, c in matched]),
                    )
                )
                # omit extracting embedded code, because choosing
                # arbitrary matcher from matched ones might fail to
                # detect the end of embedded code as expected.
                continue
            matcher, ctx = matched[0]
            filename = matcher.filename(ctx)
            code = []
            codeatstart = matcher.codeatstart(ctx, line)
            if codeatstart is not None:
                code.append(codeatstart)
                startline = lineno
            else:
                startline = lineno + 1

    if matcher:
        # examine whether EOF ends embedded code, because embedded
        # code isn't yet ended explicitly
        if matcher.endsat(ctx, '\n'):
            codeatend = matcher.codeatend(ctx, '\n')
            if codeatend is not None:
                code.append(codeatend)
            if not matcher.ignores(ctx):
                yield (filename, startline, lineno + 1, ''.join(code))
        else:
            # this is an error of basefile
            # (if matchers are implemented correctly)
            errors.append(
                '%s:%d: unexpected end of file for "%s"'
                % (basefile, lineno, matcher.desc)
            )


# heredoc limit mark to ignore embedded code at check-code.py or so
heredocignorelimit = 'NO_CHECK_EOF'

# the pattern to match against cases below, and to return a limit mark
# string as 'lname' group
#
# - << LIMITMARK
# - << "LIMITMARK"
# - << 'LIMITMARK'
heredoclimitpat = r'\s*<<\s*(?P<lquote>["\']?)(?P<limit>\w+)(?P=lquote)'


class fileheredocmatcher(embeddedmatcher):
    """Detect "cat > FILE << LIMIT" style embedded code

    >>> matcher = fileheredocmatcher('heredoc .py file', r'[^<]+\\.py')
    >>> b2s(matcher.startsat('  $ cat > file.py << EOF\\n'))
    ('file.py', '  > EOF\\n')
    >>> b2s(matcher.startsat('  $ cat   >>file.py   <<EOF\\n'))
    ('file.py', '  > EOF\\n')
    >>> b2s(matcher.startsat('  $ cat>  \\x27any file.py\\x27<<  "EOF"\\n'))
    ('any file.py', '  > EOF\\n')
    >>> b2s(matcher.startsat("  $ cat > file.py << 'ANYLIMIT'\\n"))
    ('file.py', '  > ANYLIMIT\\n')
    >>> b2s(matcher.startsat('  $ cat<<ANYLIMIT>"file.py"\\n'))
    ('file.py', '  > ANYLIMIT\\n')
    >>> start = '  $ cat > file.py << EOF\\n'
    >>> ctx = matcher.startsat(start)
    >>> matcher.codeatstart(ctx, start)
    >>> b2s(matcher.filename(ctx))
    'file.py'
    >>> matcher.ignores(ctx)
    False
    >>> inside = '  > foo = 1\\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    'foo = 1\\n'
    >>> end = '  > EOF\\n'
    >>> matcher.endsat(ctx, end)
    True
    >>> matcher.codeatend(ctx, end)
    >>> matcher.endsat(ctx, '  > EOFEOF\\n')
    False
    >>> ctx = matcher.startsat('  $ cat > file.py << NO_CHECK_EOF\\n')
    >>> matcher.ignores(ctx)
    True
    """

    _prefix = '  > '

    def __init__(self, desc, namepat):
        super(fileheredocmatcher, self).__init__(desc)

        # build the pattern to match against cases below (and ">>"
        # variants), and to return a target filename string as 'name'
        # group
        #
        # - > NAMEPAT
        # - > "NAMEPAT"
        # - > 'NAMEPAT'
        namepat = (
            r'\s*>>?\s*(?P<nquote>["\']?)(?P<name>%s)(?P=nquote)' % namepat
        )
        self._fileres = [
            # "cat > NAME << LIMIT" case
            re.compile(r' {2}\$ \s*cat' + namepat + heredoclimitpat),
            # "cat << LIMIT > NAME" case
            re.compile(r' {2}\$ \s*cat' + heredoclimitpat + namepat),
        ]

    def startsat(self, line):
        # ctx is (filename, END-LINE-OF-EMBEDDED-CODE) tuple
        for filere in self._fileres:
            matched = filere.match(line)
            if matched:
                return (
                    matched.group('name'),
                    '  > %s\n' % matched.group('limit'),
                )

    def endsat(self, ctx, line):
        return ctx[1] == line

    def isinside(self, ctx, line):
        return line.startswith(self._prefix)

    def ignores(self, ctx):
        return '  > %s\n' % heredocignorelimit == ctx[1]

    def filename(self, ctx):
        return ctx[0]

    def codeatstart(self, ctx, line):
        return None  # no embedded code at start line

    def codeatend(self, ctx, line):
        return None  # no embedded code at end line

    def codeinside(self, ctx, line):
        return line[len(self._prefix) :]  # strip prefix


####
# for embedded python script


class pydoctestmatcher(embeddedmatcher):
    """Detect ">>> code" style embedded python code

    >>> matcher = pydoctestmatcher()
    >>> startline = '  >>> foo = 1\\n'
    >>> matcher.startsat(startline)
    True
    >>> matcher.startsat('  ... foo = 1\\n')
    False
    >>> ctx = matcher.startsat(startline)
    >>> matcher.filename(ctx)
    >>> matcher.ignores(ctx)
    False
    >>> b2s(matcher.codeatstart(ctx, startline))
    'foo = 1\\n'
    >>> inside = '  >>> foo = 1\\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    'foo = 1\\n'
    >>> inside = '  ... foo = 1\\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    'foo = 1\\n'
    >>> inside = '  expected output\\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    '\\n'
    >>> inside = '  \\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    '\\n'
    >>> end = '  $ foo bar\\n'
    >>> matcher.endsat(ctx, end)
    True
    >>> matcher.codeatend(ctx, end)
    >>> end = '\\n'
    >>> matcher.endsat(ctx, end)
    True
    >>> matcher.codeatend(ctx, end)
    """

    _prefix = '  >>> '
    _prefixre = re.compile(r' {2}(>>>|\.\.\.) ')

    # If a line matches against not _prefixre but _outputre, that line
    # is "an expected output line" (= not a part of code fragment).
    #
    # Strictly speaking, a line matching against "(#if|#else|#endif)"
    # is also treated similarly in "inline python code" semantics by
    # run-tests.py. But "directive line inside inline python code"
    # should be rejected by Mercurial reviewers. Therefore, this
    # regexp does not matche against such directive lines.
    _outputre = re.compile(r' {2}$| {2}[^$]')

    def __init__(self):
        super(pydoctestmatcher, self).__init__("doctest style python code")

    def startsat(self, line):
        # ctx is "True"
        return line.startswith(self._prefix)

    def endsat(self, ctx, line):
        return not (self._prefixre.match(line) or self._outputre.match(line))

    def isinside(self, ctx, line):
        return True  # always true, if not yet ended

    def ignores(self, ctx):
        return False  # should be checked always

    def filename(self, ctx):
        return None  # no filename

    def codeatstart(self, ctx, line):
        return line[len(self._prefix) :]  # strip prefix '  >>> '/'  ... '

    def codeatend(self, ctx, line):
        return None  # no embedded code at end line

    def codeinside(self, ctx, line):
        if self._prefixre.match(line):
            return line[len(self._prefix) :]  # strip prefix '  >>> '/'  ... '
        return '\n'  # an expected output line is treated as an empty line


class pyheredocmatcher(embeddedmatcher):
    """Detect "python << LIMIT" style embedded python code

    >>> matcher = pyheredocmatcher()
    >>> b2s(matcher.startsat('  $ python << EOF\\n'))
    '  > EOF\\n'
    >>> b2s(matcher.startsat('  $ $PYTHON   <<EOF\\n'))
    '  > EOF\\n'
    >>> b2s(matcher.startsat('  $ "$PYTHON"<<  "EOF"\\n'))
    '  > EOF\\n'
    >>> b2s(matcher.startsat("  $ $PYTHON << 'ANYLIMIT'\\n"))
    '  > ANYLIMIT\\n'
    >>> matcher.startsat('  $ "$PYTHON" < EOF\\n')
    >>> start = '  $ python << EOF\\n'
    >>> ctx = matcher.startsat(start)
    >>> matcher.codeatstart(ctx, start)
    >>> matcher.filename(ctx)
    >>> matcher.ignores(ctx)
    False
    >>> inside = '  > foo = 1\\n'
    >>> matcher.endsat(ctx, inside)
    False
    >>> matcher.isinside(ctx, inside)
    True
    >>> b2s(matcher.codeinside(ctx, inside))
    'foo = 1\\n'
    >>> end = '  > EOF\\n'
    >>> matcher.endsat(ctx, end)
    True
    >>> matcher.codeatend(ctx, end)
    >>> matcher.endsat(ctx, '  > EOFEOF\\n')
    False
    >>> ctx = matcher.startsat('  $ python << NO_CHECK_EOF\\n')
    >>> matcher.ignores(ctx)
    True
    """

    _prefix = '  > '

    _startre = re.compile(
        r' {2}\$ (\$PYTHON|"\$PYTHON"|python).*' + heredoclimitpat
    )

    def __init__(self):
        super(pyheredocmatcher, self).__init__("heredoc python invocation")

    def startsat(self, line):
        # ctx is END-LINE-OF-EMBEDDED-CODE
        matched = self._startre.match(line)
        if matched:
            return '  > %s\n' % matched.group('limit')

    def endsat(self, ctx, line):
        return ctx == line

    def isinside(self, ctx, line):
        return line.startswith(self._prefix)

    def ignores(self, ctx):
        return '  > %s\n' % heredocignorelimit == ctx

    def filename(self, ctx):
        return None  # no filename

    def codeatstart(self, ctx, line):
        return None  # no embedded code at start line

    def codeatend(self, ctx, line):
        return None  # no embedded code at end line

    def codeinside(self, ctx, line):
        return line[len(self._prefix) :]  # strip prefix


_pymatchers = [
    pydoctestmatcher(),
    pyheredocmatcher(),
    # use '[^<]+' instead of '\S+', in order to match against
    # paths including whitespaces
    fileheredocmatcher('heredoc .py file', r'[^<]+\.py'),
]


def pyembedded(basefile, lines, errors):
    return embedded(basefile, lines, errors, _pymatchers)


####
# for embedded shell script

_shmatchers = [
    # use '[^<]+' instead of '\S+', in order to match against
    # paths including whitespaces
    fileheredocmatcher('heredoc .sh file', r'[^<]+\.sh'),
]


def shembedded(basefile, lines, errors):
    return embedded(basefile, lines, errors, _shmatchers)


####
# for embedded hgrc configuration

_hgrcmatchers = [
    # use '[^<]+' instead of '\S+', in order to match against
    # paths including whitespaces
    fileheredocmatcher(
        'heredoc hgrc file', r'(([^/<]+/)+hgrc|\$HGRCPATH|\${HGRCPATH})'
    ),
]


def hgrcembedded(basefile, lines, errors):
    return embedded(basefile, lines, errors, _hgrcmatchers)


####

if __name__ == "__main__":
    import optparse
    import sys

    def showembedded(basefile, lines, embeddedfunc, opts):
        errors = []
        for name, starts, ends, code in embeddedfunc(basefile, lines, errors):
            if not name:
                name = '<anonymous>'
            writeout("%s:%d: %s starts\n" % (basefile, starts, name))
            if opts.verbose and code:
                writeout("  |%s\n" % "\n  |".join(l for l in code.splitlines()))
            writeout("%s:%d: %s ends\n" % (basefile, ends, name))
        for e in errors:
            writeerr("%s\n" % e)
        return len(errors)

    def applyembedded(args, embeddedfunc, opts):
        ret = 0
        if args:
            for f in args:
                with opentext(f) as fp:
                    if showembedded(f, fp, embeddedfunc, opts):
                        ret = 1
        else:
            lines = [l for l in sys.stdin.readlines()]
            if showembedded('<stdin>', lines, embeddedfunc, opts):
                ret = 1
        return ret

    commands = {}

    def command(name, desc):
        def wrap(func):
            commands[name] = (desc, func)

        return wrap

    @command("pyembedded", "detect embedded python script")
    def pyembeddedcmd(args, opts):
        return applyembedded(args, pyembedded, opts)

    @command("shembedded", "detect embedded shell script")
    def shembeddedcmd(args, opts):
        return applyembedded(args, shembedded, opts)

    @command("hgrcembedded", "detect embedded hgrc configuration")
    def hgrcembeddedcmd(args, opts):
        return applyembedded(args, hgrcembedded, opts)

    availablecommands = "\n".join(
        ["  - %s: %s" % (key, value[0]) for key, value in commands.items()]
    )

    parser = optparse.OptionParser(
        """%prog COMMAND [file ...]

Pick up embedded code fragments from given file(s) or stdin, and list
up start/end lines of them in standard compiler format
("FILENAME:LINENO:").

Available commands are:
"""
        + availablecommands
        + """
"""
    )
    parser.add_option(
        "-v",
        "--verbose",
        help="enable additional output (e.g. actual code)",
        action="store_true",
    )
    (opts, args) = parser.parse_args()

    if not args or args[0] not in commands:
        parser.print_help()
        sys.exit(255)

    sys.exit(commands[args[0]][1](args[1:], opts))