File size: 19,070 Bytes
d1ceb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from itertools import chain

from .ast import AtRule, Declaration, ParseError, QualifiedRule
from .tokenizer import parse_component_value_list


def _to_token_iterator(input, skip_comments=False):
    """Iterate component values out of string or component values iterable.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments: If the input is a string, ignore all CSS comments.
    :returns: An iterator yielding :term:`component values`.

    """
    if isinstance(input, str):
        input = parse_component_value_list(input, skip_comments)
    return iter(input)


def _next_significant(tokens):
    """Return the next significant (neither whitespace or comment) token.

    :type tokens: :term:`iterator`
    :param tokens: An iterator yielding :term:`component values`.
    :returns: A :term:`component value`, or :obj:`None`.

    """
    for token in tokens:
        if token.type not in ('whitespace', 'comment'):
            return token


def parse_one_component_value(input, skip_comments=False):
    """Parse a single :diagram:`component value`.

    This is used e.g. for an attribute value
    referred to by ``attr(foo length)``.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments: If the input is a string, ignore all CSS comments.
    :returns:
        A :term:`component value` (that is neither whitespace or comment),
        or a :class:`~tinycss2.ast.ParseError`.

    """
    tokens = _to_token_iterator(input, skip_comments)
    first = _next_significant(tokens)
    second = _next_significant(tokens)
    if first is None:
        return ParseError(1, 1, 'empty', 'Input is empty')
    if second is not None:
        return ParseError(
            second.source_line, second.source_column, 'extra-input',
            'Got more than one token')
    else:
        return first


def parse_one_declaration(input, skip_comments=False):
    """Parse a single :diagram:`declaration`.

    This is used e.g. for a declaration in an `@supports
    <https://drafts.csswg.org/css-conditional/#at-supports>`_ test.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments: If the input is a string, ignore all CSS comments.
    :returns:
        A :class:`~tinycss2.ast.Declaration`
        or :class:`~tinycss2.ast.ParseError`.

    Any whitespace or comment before the ``:`` colon is dropped.

    """
    tokens = _to_token_iterator(input, skip_comments)
    first_token = _next_significant(tokens)
    if first_token is None:
        return ParseError(1, 1, 'empty', 'Input is empty')
    return _parse_declaration(first_token, tokens)


def _consume_remnants(input, nested):
    for token in input:
        if token == ';':
            return
        elif nested and token == '}':
            return


def _parse_declaration(first_token, tokens, nested=True):
    """Parse a declaration.

    Consume :obj:`tokens` until the end of the declaration or the first error.

    :type first_token: :term:`component value`
    :param first_token: The first component value of the rule.
    :type tokens: :term:`iterator`
    :param tokens: An iterator yielding :term:`component values`.
    :type nested: :obj:`bool`
    :param nested: Whether the declaration is nested or top-level.
    :returns:
        A :class:`~tinycss2.ast.Declaration`
        or :class:`~tinycss2.ast.ParseError`.

    """
    name = first_token
    if name.type != 'ident':
        _consume_remnants(tokens, nested)
        return ParseError(
            name.source_line, name.source_column, 'invalid',
            f'Expected <ident> for declaration name, got {name.type}.')

    colon = _next_significant(tokens)
    if colon is None:
        _consume_remnants(tokens, nested)
        return ParseError(
            name.source_line, name.source_column, 'invalid',
            "Expected ':' after declaration name, got EOF")
    elif colon != ':':
        _consume_remnants(tokens, nested)
        return ParseError(
            colon.source_line, colon.source_column, 'invalid',
            "Expected ':' after declaration name, got {colon.type}.")

    value = []
    state = 'value'
    contains_non_whitespace = False
    contains_simple_block = False
    for i, token in enumerate(tokens):
        if state == 'value' and token == '!':
            state = 'bang'
            bang_position = i
        elif (state == 'bang' and token.type == 'ident'
                and token.lower_value == 'important'):
            state = 'important'
        elif token.type not in ('whitespace', 'comment'):
            state = 'value'
            if token.type == '{} block':
                if contains_non_whitespace:
                    contains_simple_block = True
                else:
                    contains_non_whitespace = True
            else:
                contains_non_whitespace = True
        value.append(token)

    if state == 'important':
        del value[bang_position:]

    # TODO: Handle custom property names

    if contains_simple_block and contains_non_whitespace:
        return ParseError(
            colon.source_line, colon.source_column, 'invalid',
            'Declaration contains {} block')

    # TODO: Handle unicode-range

    return Declaration(
        name.source_line, name.source_column, name.value, name.lower_value,
        value, state == 'important')


def _consume_blocks_content(first_token, tokens):
    """Consume declaration or nested rule."""
    declaration_tokens = []
    semicolon_token = []
    if first_token != ';' and first_token.type != '{} block':
        for token in tokens:
            if token == ';':
                semicolon_token.append(token)
                break
            declaration_tokens.append(token)
            if token.type == '{} block':
                break
    declaration = _parse_declaration(
        first_token, iter(declaration_tokens), nested=True)
    if declaration.type == 'declaration':
        return declaration
    else:
        tokens = chain(declaration_tokens, semicolon_token, tokens)
        return _consume_qualified_rule(first_token, tokens, stop_token=';', nested=True)


def _consume_declaration_in_list(first_token, tokens):
    """Like :func:`_parse_declaration`, but stop at the first ``;``.

    Deprecated, use :func:`_consume_blocks_content` instead.

    """
    other_declaration_tokens = []
    for token in tokens:
        if token == ';':
            break
        other_declaration_tokens.append(token)
    return _parse_declaration(first_token, iter(other_declaration_tokens))


def parse_blocks_contents(input, skip_comments=False, skip_whitespace=False):
    """Parse a block’s contents.

    This is used e.g. for the :attr:`~tinycss2.ast.QualifiedRule.content`
    of a style rule or ``@page`` rule, or for the ``style`` attribute of an
    HTML element.

    In contexts that don’t expect any at-rule and/or qualified rule,
    all :class:`~tinycss2.ast.AtRule` and/or
    :class:`~tinycss2.ast.QualifiedRule` objects should simply be rejected as
    invalid.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments:
        Ignore CSS comments at the top-level of the list.
        If the input is a string, ignore all comments.
    :type skip_whitespace: :obj:`bool`
    :param skip_whitespace:
        Ignore whitespace at the top-level of the list.
        Whitespace is still preserved
        in the :attr:`~tinycss2.ast.Declaration.value` of declarations
        and the :attr:`~tinycss2.ast.AtRule.prelude`
        and :attr:`~tinycss2.ast.AtRule.content` of at-rules.
    :returns:
        A list of
        :class:`~tinycss2.ast.Declaration`,
        :class:`~tinycss2.ast.AtRule`,
        :class:`~tinycss2.ast.QualifiedRule`,
        :class:`~tinycss2.ast.Comment` (if ``skip_comments`` is false),
        :class:`~tinycss2.ast.WhitespaceToken`
        (if ``skip_whitespace`` is false),
        and :class:`~tinycss2.ast.ParseError` objects

    """
    tokens = _to_token_iterator(input, skip_comments)
    result = []
    for token in tokens:
        if token.type == 'whitespace':
            if not skip_whitespace:
                result.append(token)
        elif token.type == 'comment':
            if not skip_comments:
                result.append(token)
        elif token.type == 'at-keyword':
            result.append(_consume_at_rule(token, tokens))
        elif token != ';':
            result.append(_consume_blocks_content(token, tokens))
    return result


def parse_declaration_list(input, skip_comments=False, skip_whitespace=False):
    """Parse a :diagram:`declaration list` (which may also contain at-rules).

    Deprecated and removed from CSS Syntax Level 3. Use
    :func:`parse_blocks_contents` instead.

    This is used e.g. for the :attr:`~tinycss2.ast.QualifiedRule.content`
    of a style rule or ``@page`` rule, or for the ``style`` attribute of an
    HTML element.

    In contexts that don’t expect any at-rule, all
    :class:`~tinycss2.ast.AtRule` objects should simply be rejected as invalid.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments:
        Ignore CSS comments at the top-level of the list.
        If the input is a string, ignore all comments.
    :type skip_whitespace: :obj:`bool`
    :param skip_whitespace:
        Ignore whitespace at the top-level of the list.
        Whitespace is still preserved
        in the :attr:`~tinycss2.ast.Declaration.value` of declarations
        and the :attr:`~tinycss2.ast.AtRule.prelude`
        and :attr:`~tinycss2.ast.AtRule.content` of at-rules.
    :returns:
        A list of
        :class:`~tinycss2.ast.Declaration`,
        :class:`~tinycss2.ast.AtRule`,
        :class:`~tinycss2.ast.Comment` (if ``skip_comments`` is false),
        :class:`~tinycss2.ast.WhitespaceToken`
        (if ``skip_whitespace`` is false),
        and :class:`~tinycss2.ast.ParseError` objects

    """
    tokens = _to_token_iterator(input, skip_comments)
    result = []
    for token in tokens:
        if token.type == 'whitespace':
            if not skip_whitespace:
                result.append(token)
        elif token.type == 'comment':
            if not skip_comments:
                result.append(token)
        elif token.type == 'at-keyword':
            result.append(_consume_at_rule(token, tokens))
        elif token != ';':
            result.append(_consume_declaration_in_list(token, tokens))
    return result


def parse_one_rule(input, skip_comments=False):
    """Parse a single :diagram:`qualified rule` or :diagram:`at-rule`.

    This would be used e.g. by `insertRule()
    <https://drafts.csswg.org/cssom/#dom-cssstylesheet-insertrule>`_
    in an implementation of CSSOM.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments:
        If the input is a string, ignore all CSS comments.
    :returns:
        A :class:`~tinycss2.ast.QualifiedRule`,
        :class:`~tinycss2.ast.AtRule`,
        or :class:`~tinycss2.ast.ParseError` objects.

    Any whitespace or comment before or after the rule is dropped.

    """
    tokens = _to_token_iterator(input, skip_comments)
    first = _next_significant(tokens)
    if first is None:
        return ParseError(1, 1, 'empty', 'Input is empty')

    rule = _consume_rule(first, tokens)
    next = _next_significant(tokens)
    if next is not None:
        return ParseError(
            next.source_line, next.source_column, 'extra-input',
            'Expected a single rule, got %s after the first rule.' % next.type)
    return rule


def parse_rule_list(input, skip_comments=False, skip_whitespace=False):
    """Parse a non-top-level :diagram:`rule list`.

    Deprecated and removed from CSS Syntax. Use :func:`parse_blocks_content`
    instead.

    This is used for parsing the :attr:`~tinycss2.ast.AtRule.content`
    of nested rules like ``@media``.
    This differs from :func:`parse_stylesheet` in that
    top-level ``<!--`` and ``-->`` tokens are not ignored.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments:
        Ignore CSS comments at the top-level of the list.
        If the input is a string, ignore all comments.
    :type skip_whitespace: :obj:`bool`
    :param skip_whitespace:
        Ignore whitespace at the top-level of the list.
        Whitespace is still preserved
        in the :attr:`~tinycss2.ast.QualifiedRule.prelude`
        and the :attr:`~tinycss2.ast.QualifiedRule.content` of rules.
    :returns:
        A list of
        :class:`~tinycss2.ast.QualifiedRule`,
        :class:`~tinycss2.ast.AtRule`,
        :class:`~tinycss2.ast.Comment` (if ``skip_comments`` is false),
        :class:`~tinycss2.ast.WhitespaceToken`
        (if ``skip_whitespace`` is false),
        and :class:`~tinycss2.ast.ParseError` objects.

    """
    tokens = _to_token_iterator(input, skip_comments)
    result = []
    for token in tokens:
        if token.type == 'whitespace':
            if not skip_whitespace:
                result.append(token)
        elif token.type == 'comment':
            if not skip_comments:
                result.append(token)
        else:
            result.append(_consume_rule(token, tokens))
    return result


def parse_stylesheet(input, skip_comments=False, skip_whitespace=False):
    """Parse :diagram:`stylesheet` from text.

    This is used e.g. for a ``<style>`` HTML element.

    This differs from :func:`parse_rule_list` in that
    top-level ``<!--`` and ``-->`` tokens are ignored.
    This is a legacy quirk for the ``<style>`` HTML element.

    :type input: :obj:`str` or :term:`iterable`
    :param input: A string or an iterable of :term:`component values`.
    :type skip_comments: :obj:`bool`
    :param skip_comments:
        Ignore CSS comments at the top-level of the stylesheet.
        If the input is a string, ignore all comments.
    :type skip_whitespace: :obj:`bool`
    :param skip_whitespace:
        Ignore whitespace at the top-level of the stylesheet.
        Whitespace is still preserved
        in the :attr:`~tinycss2.ast.QualifiedRule.prelude`
        and the :attr:`~tinycss2.ast.QualifiedRule.content` of rules.
    :returns:
        A list of
        :class:`~tinycss2.ast.QualifiedRule`,
        :class:`~tinycss2.ast.AtRule`,
        :class:`~tinycss2.ast.Comment` (if ``skip_comments`` is false),
        :class:`~tinycss2.ast.WhitespaceToken`
        (if ``skip_whitespace`` is false),
        and :class:`~tinycss2.ast.ParseError` objects.

    """
    tokens = _to_token_iterator(input, skip_comments)
    result = []
    for token in tokens:
        if token.type == 'whitespace':
            if not skip_whitespace:
                result.append(token)
        elif token.type == 'comment':
            if not skip_comments:
                result.append(token)
        elif token not in ('<!--', '-->'):
            result.append(_consume_rule(token, tokens))
    return result


def _consume_rule(first_token, tokens):
    """Parse a qualified rule or at-rule.

    Consume just enough of :obj:`tokens` for this rule.

    :type first_token: :term:`component value`
    :param first_token: The first component value of the rule.
    :type tokens: :term:`iterator`
    :param tokens: An iterator yielding :term:`component values`.
    :returns:
        A :class:`~tinycss2.ast.QualifiedRule`,
        :class:`~tinycss2.ast.AtRule`,
        or :class:`~tinycss2.ast.ParseError`.

    """
    if first_token.type == 'at-keyword':
        return _consume_at_rule(first_token, tokens)
    return _consume_qualified_rule(first_token, tokens)


def _consume_at_rule(at_keyword, tokens):
    """Parse an at-rule.

    Consume just enough of :obj:`tokens` for this rule.

    :type at_keyword: :class:`AtKeywordToken`
    :param at_keyword: The at-rule keyword token starting this rule.
    :type tokens: :term:`iterator`
    :param tokens: An iterator yielding :term:`component values`.
    :type nested: :obj:`bool`
    :param nested: Whether the at-rule is nested or top-level.
    :returns:
        A :class:`~tinycss2.ast.QualifiedRule`,
        or :class:`~tinycss2.ast.ParseError`.

    """
    prelude = []
    content = None
    for token in tokens:
        if token.type == '{} block':
            # TODO: handle nested at-rules
            # https://drafts.csswg.org/css-syntax-3/#consume-at-rule
            content = token.content
            break
        elif token == ';':
            break
        prelude.append(token)
    return AtRule(
        at_keyword.source_line, at_keyword.source_column, at_keyword.value,
        at_keyword.lower_value, prelude, content)


def _rule_error(token, name):
    """Create rule parse error raised because of given token."""
    return ParseError(
        token.source_line, token.source_column, 'invalid',
        f'{name} reached before {{}} block for a qualified rule.')


def _consume_qualified_rule(first_token, tokens, nested=False,
                            stop_token=None):
    """Consume a qualified rule.

    Consume just enough of :obj:`tokens` for this rule.

    :type first_token: :term:`component value`
    :param first_token: The first component value of the rule.
    :type tokens: :term:`iterator`
    :param tokens: An iterator yielding :term:`component values`.
    :type nested: :obj:`bool`
    :param nested: Whether the rule is nested or top-level.
    :type stop_token: :class:`~tinycss2.ast.Node`
    :param stop_token: A token that ends rule parsing when met.

    """
    if first_token == stop_token:
        return _rule_error(first_token, 'Stop token')
    if first_token.type == '{} block':
        prelude = []
        block = first_token
    else:
        prelude = [first_token]
        for token in tokens:
            if token == stop_token:
                return _rule_error(token, 'Stop token')
            if token.type == '{} block':
                block = token
                # TODO: handle special case for CSS variables (using "nested")
                # https://drafts.csswg.org/css-syntax-3/#consume-qualified-rule
                break
            prelude.append(token)
        else:
            return _rule_error(prelude[-1], 'EOF')
    return QualifiedRule(
        first_token.source_line, first_token.source_column, prelude, block.content)