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
|
"""Docutils transforms used by Sphinx when reading documents."""
from __future__ import annotations
import re
import unicodedata
from typing import TYPE_CHECKING, Any, cast
from docutils import nodes
from docutils.transforms import Transform, Transformer
from docutils.transforms.parts import ContentsFilter
from docutils.transforms.universal import SmartQuotes
from docutils.utils import normalize_language_tag
from docutils.utils.smartquotes import smartchars
from sphinx import addnodes
from sphinx.locale import _, __
from sphinx.util import logging
from sphinx.util.docutils import new_document
from sphinx.util.i18n import format_date
from sphinx.util.nodes import apply_source_workaround, is_smartquotable
if TYPE_CHECKING:
from collections.abc import Generator
from docutils.nodes import Node, Text
from sphinx.application import Sphinx
from sphinx.config import Config
from sphinx.domains.std import StandardDomain
from sphinx.environment import BuildEnvironment
logger = logging.getLogger(__name__)
default_substitutions = {
'version',
'release',
'today',
'translation progress',
}
class SphinxTransform(Transform):
"""A base class of Transforms.
Compared with ``docutils.transforms.Transform``, this class improves accessibility to
Sphinx APIs.
"""
@property
def app(self) -> Sphinx:
"""Reference to the :class:`.Sphinx` object."""
return self.env.app
@property
def env(self) -> BuildEnvironment:
"""Reference to the :class:`.BuildEnvironment` object."""
return self.document.settings.env
@property
def config(self) -> Config:
"""Reference to the :class:`.Config` object."""
return self.env.config
class SphinxTransformer(Transformer):
"""
A transformer for Sphinx.
"""
document: nodes.document
env: BuildEnvironment | None = None
def set_environment(self, env: BuildEnvironment) -> None:
self.env = env
def apply_transforms(self) -> None:
if isinstance(self.document, nodes.document):
if not hasattr(self.document.settings, 'env') and self.env:
self.document.settings.env = self.env
super().apply_transforms()
else:
# wrap the target node by document node during transforming
try:
document = new_document('')
if self.env:
document.settings.env = self.env
document += self.document
self.document = document
super().apply_transforms()
finally:
self.document = self.document[0]
class DefaultSubstitutions(SphinxTransform):
"""
Replace some substitutions if they aren't defined in the document.
"""
# run before the default Substitutions
default_priority = 210
def apply(self, **kwargs: Any) -> None:
# only handle those not otherwise defined in the document
to_handle = default_substitutions - set(self.document.substitution_defs)
for ref in self.document.findall(nodes.substitution_reference):
refname = ref['refname']
if refname in to_handle:
if refname == 'translation progress':
# special handling: calculate translation progress
text = _calculate_translation_progress(self.document)
else:
text = self.config[refname]
if refname == 'today' and not text:
# special handling: can also specify a strftime format
text = format_date(self.config.today_fmt or _('%b %d, %Y'),
language=self.config.language)
ref.replace_self(nodes.Text(text))
def _calculate_translation_progress(document: nodes.document) -> str:
try:
translation_progress = document['translation_progress']
except KeyError:
return _('could not calculate translation progress!')
total = translation_progress['total']
translated = translation_progress['translated']
if total <= 0:
return _('no translated elements!')
return f'{translated / total:.2%}'
class MoveModuleTargets(SphinxTransform):
"""
Move module targets that are the first thing in a section to the section
title.
XXX Python specific
"""
default_priority = 210
def apply(self, **kwargs: Any) -> None:
for node in list(self.document.findall(nodes.target)):
if not node['ids']:
continue
if (
'ismod' in node
and type(node.parent) is nodes.section
# index 0: section title node
# index 1: index node
# index 2: target node
and node.parent.index(node) == 2
):
node.parent['ids'][0:0] = node['ids']
node.parent.remove(node)
class HandleCodeBlocks(SphinxTransform):
"""
Several code block related transformations.
"""
default_priority = 210
def apply(self, **kwargs: Any) -> None:
# move doctest blocks out of blockquotes
for node in self.document.findall(nodes.block_quote):
if all(isinstance(child, nodes.doctest_block) for child
in node.children):
node.replace_self(node.children)
# combine successive doctest blocks
# for node in self.document.findall(nodes.doctest_block):
# if node not in node.parent.children:
# continue
# parindex = node.parent.index(node)
# while len(node.parent) > parindex+1 and \
# isinstance(node.parent[parindex+1], nodes.doctest_block):
# node[0] = nodes.Text(node[0] + '\n\n' +
# node.parent[parindex+1][0])
# del node.parent[parindex+1]
class AutoNumbering(SphinxTransform):
"""
Register IDs of tables, figures and literal_blocks to assign numbers.
"""
default_priority = 210
def apply(self, **kwargs: Any) -> None:
domain: StandardDomain = self.env.domains['std']
for node in self.document.findall(nodes.Element):
if (domain.is_enumerable_node(node) and
domain.get_numfig_title(node) is not None and
node['ids'] == []):
self.document.note_implicit_target(node)
class SortIds(SphinxTransform):
"""
Sort section IDs so that the "id[0-9]+" one comes last.
"""
default_priority = 261
def apply(self, **kwargs: Any) -> None:
for node in self.document.findall(nodes.section):
if len(node['ids']) > 1 and node['ids'][0].startswith('id'):
node['ids'] = node['ids'][1:] + [node['ids'][0]]
TRANSLATABLE_NODES = {
'literal-block': nodes.literal_block,
'doctest-block': nodes.doctest_block,
'raw': nodes.raw,
'index': addnodes.index,
'image': nodes.image,
}
class ApplySourceWorkaround(SphinxTransform):
"""
Update source and rawsource attributes
"""
default_priority = 10
def apply(self, **kwargs: Any) -> None:
for node in self.document.findall(): # type: Node
if isinstance(node, (nodes.TextElement, nodes.image, nodes.topic)):
apply_source_workaround(node)
class AutoIndexUpgrader(SphinxTransform):
"""
Detect old style (4 column based indices) and automatically upgrade to new style.
"""
default_priority = 210
def apply(self, **kwargs: Any) -> None:
for node in self.document.findall(addnodes.index):
if 'entries' in node and any(len(entry) == 4 for entry in node['entries']):
msg = __('4 column based index found. '
'It might be a bug of extensions you use: %r') % node['entries']
logger.warning(msg, location=node)
for i, entry in enumerate(node['entries']):
if len(entry) == 4:
node['entries'][i] = entry + (None,)
class ExtraTranslatableNodes(SphinxTransform):
"""
Make nodes translatable
"""
default_priority = 10
def apply(self, **kwargs: Any) -> None:
targets = self.config.gettext_additional_targets
target_nodes = [v for k, v in TRANSLATABLE_NODES.items() if k in targets]
if not target_nodes:
return
def is_translatable_node(node: Node) -> bool:
return isinstance(node, tuple(target_nodes))
for node in self.document.findall(is_translatable_node): # type: nodes.Element
node['translatable'] = True
class UnreferencedFootnotesDetector(SphinxTransform):
"""
Detect unreferenced footnotes and emit warnings
"""
default_priority = 200
def apply(self, **kwargs: Any) -> None:
for node in self.document.footnotes:
if node['names'] == []:
# footnote having duplicated number. It is already warned at parser.
pass
elif node['names'][0] not in self.document.footnote_refs:
logger.warning(__('Footnote [%s] is not referenced.'), node['names'][0],
type='ref', subtype='footnote',
location=node)
for node in self.document.autofootnotes:
if not any(ref['auto'] == node['auto'] for ref in self.document.autofootnote_refs):
logger.warning(__('Footnote [#] is not referenced.'),
type='ref', subtype='footnote',
location=node)
class DoctestTransform(SphinxTransform):
"""Set "doctest" style to each doctest_block node"""
default_priority = 500
def apply(self, **kwargs: Any) -> None:
for node in self.document.findall(nodes.doctest_block):
node['classes'].append('doctest')
class FilterSystemMessages(SphinxTransform):
"""Filter system messages from a doctree."""
default_priority = 999
def apply(self, **kwargs: Any) -> None:
filterlevel = 2 if self.config.keep_warnings else 5
for node in list(self.document.findall(nodes.system_message)):
if node['level'] < filterlevel:
logger.debug('%s [filtered system message]', node.astext())
node.parent.remove(node)
class SphinxContentsFilter(ContentsFilter):
"""
Used with BuildEnvironment.add_toc_from() to discard cross-file links
within table-of-contents link nodes.
"""
visit_pending_xref = ContentsFilter.ignore_node_but_process_children
def visit_image(self, node: nodes.image) -> None:
raise nodes.SkipNode
class SphinxSmartQuotes(SmartQuotes, SphinxTransform):
"""
Customized SmartQuotes to avoid transform for some extra node types.
refs: sphinx.parsers.RSTParser
"""
default_priority = 750
def apply(self, **kwargs: Any) -> None:
if not self.is_available():
return
# override default settings with :confval:`smartquotes_action`
self.smartquotes_action = self.config.smartquotes_action
super().apply()
def is_available(self) -> bool:
builders = self.config.smartquotes_excludes.get('builders', [])
languages = self.config.smartquotes_excludes.get('languages', [])
if self.document.settings.smart_quotes is False:
# disabled by 3rd party extension (workaround)
return False
if self.config.smartquotes is False:
# disabled by confval smartquotes
return False
if self.app.builder.name in builders:
# disabled by confval smartquotes_excludes['builders']
return False
if self.config.language in languages:
# disabled by confval smartquotes_excludes['languages']
return False
# confirm selected language supports smart_quotes or not
language = self.env.settings['language_code']
return any(
tag in smartchars.quotes
for tag in normalize_language_tag(language)
)
def get_tokens(self, txtnodes: list[Text]) -> Generator[tuple[str, str], None, None]:
# A generator that yields ``(texttype, nodetext)`` tuples for a list
# of "Text" nodes (interface to ``smartquotes.educate_tokens()``).
for txtnode in txtnodes:
if is_smartquotable(txtnode):
# SmartQuotes uses backslash escapes instead of null-escapes
text = re.sub(r'(?<=\x00)([-\\\'".`])', r'\\\1', str(txtnode))
yield 'plain', text
else:
# skip smart quotes
yield 'literal', txtnode.astext()
class DoctreeReadEvent(SphinxTransform):
"""Emit :event:`doctree-read` event."""
default_priority = 880
def apply(self, **kwargs: Any) -> None:
self.app.emit('doctree-read', self.document)
class ManpageLink(SphinxTransform):
"""Find manpage section numbers and names"""
default_priority = 999
def apply(self, **kwargs: Any) -> None:
for node in self.document.findall(addnodes.manpage):
manpage = ' '.join([str(x) for x in node.children
if isinstance(x, nodes.Text)])
pattern = r'^(?P<path>(?P<page>.+)[\(\.](?P<section>[1-9]\w*)?\)?)$'
info = {'path': manpage,
'page': manpage,
'section': ''}
r = re.match(pattern, manpage)
if r:
info = r.groupdict()
node.attributes.update(info)
class GlossarySorter(SphinxTransform):
"""Sort glossaries that have the ``sorted`` flag."""
# This must be done after i18n, therefore not right
# away in the glossary directive.
default_priority = 500
def apply(self, **kwargs: Any) -> None:
for glossary in self.document.findall(addnodes.glossary):
if glossary["sorted"]:
definition_list = cast(nodes.definition_list, glossary[0])
definition_list[:] = sorted(
definition_list,
key=lambda item: unicodedata.normalize(
'NFD',
cast(nodes.term, item)[0].astext().lower()),
)
class ReorderConsecutiveTargetAndIndexNodes(SphinxTransform):
"""Index nodes interspersed between target nodes prevent other
Transformations from combining those target nodes,
e.g. ``PropagateTargets``. This transformation reorders them:
Given the following ``document`` as input::
<document>
<target ids="id1" ...>
<index entries="...1...">
<target ids="id2" ...>
<target ids="id3" ...>
<index entries="...2...">
<target ids="id4" ...>
The transformed result will be::
<document>
<index entries="...1...">
<index entries="...2...">
<target ids="id1" ...>
<target ids="id2" ...>
<target ids="id3" ...>
<target ids="id4" ...>
"""
# This transform MUST run before ``PropagateTargets``.
default_priority = 220
def apply(self, **kwargs: Any) -> None:
for target in self.document.findall(nodes.target):
_reorder_index_target_nodes(target)
def _reorder_index_target_nodes(start_node: nodes.target) -> None:
"""Sort target and index nodes.
Find all consecutive target and index nodes starting from ``start_node``,
and move all index nodes to before the first target node.
"""
nodes_to_reorder: list[nodes.target | addnodes.index] = []
# Note that we cannot use 'condition' to filter,
# as we want *consecutive* target & index nodes.
node: nodes.Node
for node in start_node.findall(descend=False, siblings=True):
if isinstance(node, (nodes.target, addnodes.index)):
nodes_to_reorder.append(node)
continue
break # must be a consecutive run of target or index nodes
if len(nodes_to_reorder) < 2:
return # Nothing to reorder
parent = nodes_to_reorder[0].parent
if parent == nodes_to_reorder[-1].parent:
first_idx = parent.index(nodes_to_reorder[0])
last_idx = parent.index(nodes_to_reorder[-1])
if first_idx + len(nodes_to_reorder) - 1 == last_idx:
parent[first_idx:last_idx + 1] = sorted(nodes_to_reorder, key=_sort_key)
def _sort_key(node: nodes.Node) -> int:
# Must be a stable sort.
if isinstance(node, addnodes.index):
return 0
if isinstance(node, nodes.target):
return 1
msg = f'_sort_key called with unexpected node type {type(node)!r}'
raise ValueError(msg)
def setup(app: Sphinx) -> dict[str, Any]:
app.add_transform(ApplySourceWorkaround)
app.add_transform(ExtraTranslatableNodes)
app.add_transform(DefaultSubstitutions)
app.add_transform(MoveModuleTargets)
app.add_transform(HandleCodeBlocks)
app.add_transform(SortIds)
app.add_transform(DoctestTransform)
app.add_transform(AutoNumbering)
app.add_transform(AutoIndexUpgrader)
app.add_transform(FilterSystemMessages)
app.add_transform(UnreferencedFootnotesDetector)
app.add_transform(SphinxSmartQuotes)
app.add_transform(DoctreeReadEvent)
app.add_transform(ManpageLink)
app.add_transform(GlossarySorter)
app.add_transform(ReorderConsecutiveTargetAndIndexNodes)
return {
'version': 'builtin',
'parallel_read_safe': True,
'parallel_write_safe': True,
}
|