aboutsummaryrefslogtreecommitdiff
path: root/scripts/qapi/parser.py
blob: 6c45a00cf4d839db80636faa1176dfe82475d50b (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
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
# -*- coding: utf-8 -*-
#
# QAPI schema parser
#
# Copyright IBM, Corp. 2011
# Copyright (c) 2013-2019 Red Hat Inc.
#
# Authors:
#  Anthony Liguori <aliguori@us.ibm.com>
#  Markus Armbruster <armbru@redhat.com>
#  Marc-André Lureau <marcandre.lureau@redhat.com>
#  Kevin Wolf <kwolf@redhat.com>
#
# This work is licensed under the terms of the GNU GPL, version 2.
# See the COPYING file in the top-level directory.

import os
import re
import sys
from collections import OrderedDict

from qapi.error import QAPIParseError, QAPISemError
from qapi.source import QAPISourceInfo


class QAPISchemaParser(object):

    def __init__(self, fname, previously_included=None, incl_info=None):
        previously_included = previously_included or set()
        previously_included.add(os.path.abspath(fname))

        try:
            if sys.version_info[0] >= 3:
                fp = open(fname, 'r', encoding='utf-8')
            else:
                fp = open(fname, 'r')
            self.src = fp.read()
        except IOError as e:
            raise QAPISemError(incl_info or QAPISourceInfo(None, None, None),
                               "can't read %s file '%s': %s"
                               % ("include" if incl_info else "schema",
                                  fname,
                                  e.strerror))

        if self.src == '' or self.src[-1] != '\n':
            self.src += '\n'
        self.cursor = 0
        self.info = QAPISourceInfo(fname, 1, incl_info)
        self.line_pos = 0
        self.exprs = []
        self.docs = []
        self.accept()
        cur_doc = None

        while self.tok is not None:
            info = self.info
            if self.tok == '#':
                self.reject_expr_doc(cur_doc)
                cur_doc = self.get_doc(info)
                self.docs.append(cur_doc)
                continue

            expr = self.get_expr(False)
            if 'include' in expr:
                self.reject_expr_doc(cur_doc)
                if len(expr) != 1:
                    raise QAPISemError(info, "invalid 'include' directive")
                include = expr['include']
                if not isinstance(include, str):
                    raise QAPISemError(info,
                                       "value of 'include' must be a string")
                incl_fname = os.path.join(os.path.dirname(fname),
                                          include)
                self.exprs.append({'expr': {'include': incl_fname},
                                   'info': info})
                exprs_include = self._include(include, info, incl_fname,
                                              previously_included)
                if exprs_include:
                    self.exprs.extend(exprs_include.exprs)
                    self.docs.extend(exprs_include.docs)
            elif "pragma" in expr:
                self.reject_expr_doc(cur_doc)
                if len(expr) != 1:
                    raise QAPISemError(info, "invalid 'pragma' directive")
                pragma = expr['pragma']
                if not isinstance(pragma, dict):
                    raise QAPISemError(
                        info, "value of 'pragma' must be an object")
                for name, value in pragma.items():
                    self._pragma(name, value, info)
            else:
                expr_elem = {'expr': expr,
                             'info': info}
                if cur_doc:
                    if not cur_doc.symbol:
                        raise QAPISemError(
                            cur_doc.info, "definition documentation required")
                    expr_elem['doc'] = cur_doc
                self.exprs.append(expr_elem)
            cur_doc = None
        self.reject_expr_doc(cur_doc)

    @staticmethod
    def reject_expr_doc(doc):
        if doc and doc.symbol:
            raise QAPISemError(
                doc.info,
                "documentation for '%s' is not followed by the definition"
                % doc.symbol)

    def _include(self, include, info, incl_fname, previously_included):
        incl_abs_fname = os.path.abspath(incl_fname)
        # catch inclusion cycle
        inf = info
        while inf:
            if incl_abs_fname == os.path.abspath(inf.fname):
                raise QAPISemError(info, "inclusion loop for %s" % include)
            inf = inf.parent

        # skip multiple include of the same file
        if incl_abs_fname in previously_included:
            return None

        return QAPISchemaParser(incl_fname, previously_included, info)

    def _pragma(self, name, value, info):
        if name == 'doc-required':
            if not isinstance(value, bool):
                raise QAPISemError(info,
                                   "pragma 'doc-required' must be boolean")
            info.pragma.doc_required = value
        elif name == 'returns-whitelist':
            if (not isinstance(value, list)
                    or any([not isinstance(elt, str) for elt in value])):
                raise QAPISemError(
                    info,
                    "pragma returns-whitelist must be a list of strings")
            info.pragma.returns_whitelist = value
        elif name == 'name-case-whitelist':
            if (not isinstance(value, list)
                    or any([not isinstance(elt, str) for elt in value])):
                raise QAPISemError(
                    info,
                    "pragma name-case-whitelist must be a list of strings")
            info.pragma.name_case_whitelist = value
        else:
            raise QAPISemError(info, "unknown pragma '%s'" % name)

    def accept(self, skip_comment=True):
        while True:
            self.tok = self.src[self.cursor]
            self.pos = self.cursor
            self.cursor += 1
            self.val = None

            if self.tok == '#':
                if self.src[self.cursor] == '#':
                    # Start of doc comment
                    skip_comment = False
                self.cursor = self.src.find('\n', self.cursor)
                if not skip_comment:
                    self.val = self.src[self.pos:self.cursor]
                    return
            elif self.tok in '{}:,[]':
                return
            elif self.tok == "'":
                # Note: we accept only printable ASCII
                string = ''
                esc = False
                while True:
                    ch = self.src[self.cursor]
                    self.cursor += 1
                    if ch == '\n':
                        raise QAPIParseError(self, "missing terminating \"'\"")
                    if esc:
                        # Note: we recognize only \\ because we have
                        # no use for funny characters in strings
                        if ch != '\\':
                            raise QAPIParseError(self,
                                                 "unknown escape \\%s" % ch)
                        esc = False
                    elif ch == '\\':
                        esc = True
                        continue
                    elif ch == "'":
                        self.val = string
                        return
                    if ord(ch) < 32 or ord(ch) >= 127:
                        raise QAPIParseError(
                            self, "funny character in string")
                    string += ch
            elif self.src.startswith('true', self.pos):
                self.val = True
                self.cursor += 3
                return
            elif self.src.startswith('false', self.pos):
                self.val = False
                self.cursor += 4
                return
            elif self.tok == '\n':
                if self.cursor == len(self.src):
                    self.tok = None
                    return
                self.info = self.info.next_line()
                self.line_pos = self.cursor
            elif not self.tok.isspace():
                # Show up to next structural, whitespace or quote
                # character
                match = re.match('[^[\\]{}:,\\s\'"]+',
                                 self.src[self.cursor-1:])
                raise QAPIParseError(self, "stray '%s'" % match.group(0))

    def get_members(self):
        expr = OrderedDict()
        if self.tok == '}':
            self.accept()
            return expr
        if self.tok != "'":
            raise QAPIParseError(self, "expected string or '}'")
        while True:
            key = self.val
            self.accept()
            if self.tok != ':':
                raise QAPIParseError(self, "expected ':'")
            self.accept()
            if key in expr:
                raise QAPIParseError(self, "duplicate key '%s'" % key)
            expr[key] = self.get_expr(True)
            if self.tok == '}':
                self.accept()
                return expr
            if self.tok != ',':
                raise QAPIParseError(self, "expected ',' or '}'")
            self.accept()
            if self.tok != "'":
                raise QAPIParseError(self, "expected string")

    def get_values(self):
        expr = []
        if self.tok == ']':
            self.accept()
            return expr
        if self.tok not in "{['tfn":
            raise QAPIParseError(
                self, "expected '{', '[', ']', string, boolean or 'null'")
        while True:
            expr.append(self.get_expr(True))
            if self.tok == ']':
                self.accept()
                return expr
            if self.tok != ',':
                raise QAPIParseError(self, "expected ',' or ']'")
            self.accept()

    def get_expr(self, nested):
        if self.tok != '{' and not nested:
            raise QAPIParseError(self, "expected '{'")
        if self.tok == '{':
            self.accept()
            expr = self.get_members()
        elif self.tok == '[':
            self.accept()
            expr = self.get_values()
        elif self.tok in "'tfn":
            expr = self.val
            self.accept()
        else:
            raise QAPIParseError(
                self, "expected '{', '[', string, boolean or 'null'")
        return expr

    def get_doc(self, info):
        if self.val != '##':
            raise QAPIParseError(
                self, "junk after '##' at start of documentation comment")

        doc = QAPIDoc(self, info)
        self.accept(False)
        while self.tok == '#':
            if self.val.startswith('##'):
                # End of doc comment
                if self.val != '##':
                    raise QAPIParseError(
                        self,
                        "junk after '##' at end of documentation comment")
                doc.end_comment()
                self.accept()
                return doc
            else:
                doc.append(self.val)
            self.accept(False)

        raise QAPIParseError(self, "documentation comment must end with '##'")


class QAPIDoc(object):
    """
    A documentation comment block, either definition or free-form

    Definition documentation blocks consist of

    * a body section: one line naming the definition, followed by an
      overview (any number of lines)

    * argument sections: a description of each argument (for commands
      and events) or member (for structs, unions and alternates)

    * features sections: a description of each feature flag

    * additional (non-argument) sections, possibly tagged

    Free-form documentation blocks consist only of a body section.
    """

    class Section(object):
        def __init__(self, name=None):
            # optional section name (argument/member or section name)
            self.name = name
            # the list of lines for this section
            self.text = ''

        def append(self, line):
            self.text += line.rstrip() + '\n'

    class ArgSection(Section):
        def __init__(self, name):
            QAPIDoc.Section.__init__(self, name)
            self.member = None

        def connect(self, member):
            self.member = member

    def __init__(self, parser, info):
        # self._parser is used to report errors with QAPIParseError.  The
        # resulting error position depends on the state of the parser.
        # It happens to be the beginning of the comment.  More or less
        # servicable, but action at a distance.
        self._parser = parser
        self.info = info
        self.symbol = None
        self.body = QAPIDoc.Section()
        # dict mapping parameter name to ArgSection
        self.args = OrderedDict()
        self.features = OrderedDict()
        # a list of Section
        self.sections = []
        # the current section
        self._section = self.body
        self._append_line = self._append_body_line

    def has_section(self, name):
        """Return True if we have a section with this name."""
        for i in self.sections:
            if i.name == name:
                return True
        return False

    def append(self, line):
        """
        Parse a comment line and add it to the documentation.

        The way that the line is dealt with depends on which part of
        the documentation we're parsing right now:
        * The body section: ._append_line is ._append_body_line
        * An argument section: ._append_line is ._append_args_line
        * A features section: ._append_line is ._append_features_line
        * An additional section: ._append_line is ._append_various_line
        """
        line = line[1:]
        if not line:
            self._append_freeform(line)
            return

        if line[0] != ' ':
            raise QAPIParseError(self._parser, "missing space after #")
        line = line[1:]
        self._append_line(line)

    def end_comment(self):
        self._end_section()

    @staticmethod
    def _is_section_tag(name):
        return name in ('Returns:', 'Since:',
                        # those are often singular or plural
                        'Note:', 'Notes:',
                        'Example:', 'Examples:',
                        'TODO:')

    def _append_body_line(self, line):
        """
        Process a line of documentation text in the body section.

        If this a symbol line and it is the section's first line, this
        is a definition documentation block for that symbol.

        If it's a definition documentation block, another symbol line
        begins the argument section for the argument named by it, and
        a section tag begins an additional section.  Start that
        section and append the line to it.

        Else, append the line to the current section.
        """
        name = line.split(' ', 1)[0]
        # FIXME not nice: things like '#  @foo:' and '# @foo: ' aren't
        # recognized, and get silently treated as ordinary text
        if not self.symbol and not self.body.text and line.startswith('@'):
            if not line.endswith(':'):
                raise QAPIParseError(self._parser, "line should end with ':'")
            self.symbol = line[1:-1]
            # FIXME invalid names other than the empty string aren't flagged
            if not self.symbol:
                raise QAPIParseError(self._parser, "invalid name")
        elif self.symbol:
            # This is a definition documentation block
            if name.startswith('@') and name.endswith(':'):
                self._append_line = self._append_args_line
                self._append_args_line(line)
            elif line == 'Features:':
                self._append_line = self._append_features_line
            elif self._is_section_tag(name):
                self._append_line = self._append_various_line
                self._append_various_line(line)
            else:
                self._append_freeform(line.strip())
        else:
            # This is a free-form documentation block
            self._append_freeform(line.strip())

    def _append_args_line(self, line):
        """
        Process a line of documentation text in an argument section.

        A symbol line begins the next argument section, a section tag
        section or a non-indented line after a blank line begins an
        additional section.  Start that section and append the line to
        it.

        Else, append the line to the current section.

        """
        name = line.split(' ', 1)[0]

        if name.startswith('@') and name.endswith(':'):
            line = line[len(name)+1:]
            self._start_args_section(name[1:-1])
        elif self._is_section_tag(name):
            self._append_line = self._append_various_line
            self._append_various_line(line)
            return
        elif (self._section.text.endswith('\n\n')
              and line and not line[0].isspace()):
            if line == 'Features:':
                self._append_line = self._append_features_line
            else:
                self._start_section()
                self._append_line = self._append_various_line
                self._append_various_line(line)
            return

        self._append_freeform(line.strip())

    def _append_features_line(self, line):
        name = line.split(' ', 1)[0]

        if name.startswith('@') and name.endswith(':'):
            line = line[len(name)+1:]
            self._start_features_section(name[1:-1])
        elif self._is_section_tag(name):
            self._append_line = self._append_various_line
            self._append_various_line(line)
            return
        elif (self._section.text.endswith('\n\n')
              and line and not line[0].isspace()):
            self._start_section()
            self._append_line = self._append_various_line
            self._append_various_line(line)
            return

        self._append_freeform(line.strip())

    def _append_various_line(self, line):
        """
        Process a line of documentation text in an additional section.

        A symbol line is an error.

        A section tag begins an additional section.  Start that
        section and append the line to it.

        Else, append the line to the current section.
        """
        name = line.split(' ', 1)[0]

        if name.startswith('@') and name.endswith(':'):
            raise QAPIParseError(self._parser,
                                 "'%s' can't follow '%s' section"
                                 % (name, self.sections[0].name))
        elif self._is_section_tag(name):
            line = line[len(name)+1:]
            self._start_section(name[:-1])

        if (not self._section.name or
                not self._section.name.startswith('Example')):
            line = line.strip()

        self._append_freeform(line)

    def _start_symbol_section(self, symbols_dict, name):
        # FIXME invalid names other than the empty string aren't flagged
        if not name:
            raise QAPIParseError(self._parser, "invalid parameter name")
        if name in symbols_dict:
            raise QAPIParseError(self._parser,
                                 "'%s' parameter name duplicated" % name)
        assert not self.sections
        self._end_section()
        self._section = QAPIDoc.ArgSection(name)
        symbols_dict[name] = self._section

    def _start_args_section(self, name):
        self._start_symbol_section(self.args, name)

    def _start_features_section(self, name):
        self._start_symbol_section(self.features, name)

    def _start_section(self, name=None):
        if name in ('Returns', 'Since') and self.has_section(name):
            raise QAPIParseError(self._parser,
                                 "duplicated '%s' section" % name)
        self._end_section()
        self._section = QAPIDoc.Section(name)
        self.sections.append(self._section)

    def _end_section(self):
        if self._section:
            text = self._section.text = self._section.text.strip()
            if self._section.name and (not text or text.isspace()):
                raise QAPIParseError(
                    self._parser,
                    "empty doc section '%s'" % self._section.name)
            self._section = None

    def _append_freeform(self, line):
        match = re.match(r'(@\S+:)', line)
        if match:
            raise QAPIParseError(self._parser,
                                 "'%s' not allowed in free-form documentation"
                                 % match.group(1))
        self._section.append(line)

    def connect_member(self, member):
        if member.name not in self.args:
            # Undocumented TODO outlaw
            self.args[member.name] = QAPIDoc.ArgSection(member.name)
        self.args[member.name].connect(member)

    def check_expr(self, expr):
        if self.has_section('Returns') and 'command' not in expr:
            raise QAPISemError(self.info,
                               "'Returns:' is only valid for commands")

    def check(self):
        bogus = [name for name, section in self.args.items()
                 if not section.member]
        if bogus:
            raise QAPISemError(
                self.info,
                "documented member%s '%s' %s not exist"
                % ("s" if len(bogus) > 1 else "",
                   "', '".join(bogus),
                   "do" if len(bogus) > 1 else "does"))