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
|
"""
sphinx.environment
~~~~~~~~~~~~~~~~~~
Global creation environment.
:copyright: Copyright 2007-2020 by the Sphinx team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import pickle
from collections import defaultdict
from copy import copy
from datetime import datetime
from os import path
from typing import Any, Callable, Dict, Generator, Iterator, List, Set, Tuple, Union
from typing import TYPE_CHECKING
from docutils import nodes
from docutils.nodes import Node
from sphinx import addnodes
from sphinx.config import Config
from sphinx.domains import Domain
from sphinx.environment.adapters.toctree import TocTree
from sphinx.errors import SphinxError, BuildEnvironmentError, DocumentError, ExtensionError
from sphinx.events import EventManager
from sphinx.locale import __
from sphinx.project import Project
from sphinx.transforms import SphinxTransformer
from sphinx.util import DownloadFiles, FilenameUniqDict
from sphinx.util import logging
from sphinx.util.docutils import LoggingReporter
from sphinx.util.i18n import CatalogRepository, docname_to_domain
from sphinx.util.nodes import is_translatable
if TYPE_CHECKING:
from sphinx.application import Sphinx
from sphinx.builders import Builder
logger = logging.getLogger(__name__)
default_settings = {
'embed_stylesheet': False,
'cloak_email_addresses': True,
'pep_base_url': 'https://www.python.org/dev/peps/',
'pep_references': None,
'rfc_base_url': 'https://tools.ietf.org/html/',
'rfc_references': None,
'input_encoding': 'utf-8-sig',
'doctitle_xform': False,
'sectsubtitle_xform': False,
'halt_level': 5,
'file_insertion_enabled': True,
'smartquotes_locales': [],
} # type: Dict[str, Any]
# This is increased every time an environment attribute is added
# or changed to properly invalidate pickle files.
ENV_VERSION = 56
# config status
CONFIG_OK = 1
CONFIG_NEW = 2
CONFIG_CHANGED = 3
CONFIG_EXTENSIONS_CHANGED = 4
CONFIG_CHANGED_REASON = {
CONFIG_NEW: __('new config'),
CONFIG_CHANGED: __('config changed'),
CONFIG_EXTENSIONS_CHANGED: __('extensions changed'),
}
versioning_conditions = {
'none': False,
'text': is_translatable,
} # type: Dict[str, Union[bool, Callable]]
class BuildEnvironment:
"""
The environment in which the ReST files are translated.
Stores an inventory of cross-file targets and provides doctree
transformations to resolve links to them.
"""
domains = None # type: Dict[str, Domain]
# --------- ENVIRONMENT INITIALIZATION -------------------------------------
def __init__(self, app: "Sphinx" = None):
self.app = None # type: Sphinx
self.doctreedir = None # type: str
self.srcdir = None # type: str
self.config = None # type: Config
self.config_status = None # type: int
self.config_status_extra = None # type: str
self.events = None # type: EventManager
self.project = None # type: Project
self.version = None # type: Dict[str, str]
# the method of doctree versioning; see set_versioning_method
self.versioning_condition = None # type: Union[bool, Callable]
self.versioning_compare = None # type: bool
# all the registered domains, set by the application
self.domains = {}
# the docutils settings for building
self.settings = default_settings.copy()
self.settings['env'] = self
# All "docnames" here are /-separated and relative and exclude
# the source suffix.
self.all_docs = {} # type: Dict[str, float]
# docname -> mtime at the time of reading
# contains all read docnames
self.dependencies = defaultdict(set) # type: Dict[str, Set[str]]
# docname -> set of dependent file
# names, relative to documentation root
self.included = defaultdict(set) # type: Dict[str, Set[str]]
# docname -> set of included file
# docnames included from other documents
self.reread_always = set() # type: Set[str]
# docnames to re-read unconditionally on
# next build
# File metadata
self.metadata = defaultdict(dict) # type: Dict[str, Dict[str, Any]]
# docname -> dict of metadata items
# TOC inventory
self.titles = {} # type: Dict[str, nodes.title]
# docname -> title node
self.longtitles = {} # type: Dict[str, nodes.title]
# docname -> title node; only different if
# set differently with title directive
self.tocs = {} # type: Dict[str, nodes.bullet_list]
# docname -> table of contents nodetree
self.toc_num_entries = {} # type: Dict[str, int]
# docname -> number of real entries
# used to determine when to show the TOC
# in a sidebar (don't show if it's only one item)
self.toc_secnumbers = {} # type: Dict[str, Dict[str, Tuple[int, ...]]]
# docname -> dict of sectionid -> number
self.toc_fignumbers = {} # type: Dict[str, Dict[str, Dict[str, Tuple[int, ...]]]]
# docname -> dict of figtype ->
# dict of figureid -> number
self.toctree_includes = {} # type: Dict[str, List[str]]
# docname -> list of toctree includefiles
self.files_to_rebuild = {} # type: Dict[str, Set[str]]
# docname -> set of files
# (containing its TOCs) to rebuild too
self.glob_toctrees = set() # type: Set[str]
# docnames that have :glob: toctrees
self.numbered_toctrees = set() # type: Set[str]
# docnames that have :numbered: toctrees
# domain-specific inventories, here to be pickled
self.domaindata = {} # type: Dict[str, Dict]
# domainname -> domain-specific dict
# these map absolute path -> (docnames, unique filename)
self.images = FilenameUniqDict() # type: FilenameUniqDict
self.dlfiles = DownloadFiles() # type: DownloadFiles
# filename -> (set of docnames, destination)
# the original URI for images
self.original_image_uri = {} # type: Dict[str, str]
# temporary data storage while reading a document
self.temp_data = {} # type: Dict[str, Any]
# context for cross-references (e.g. current module or class)
# this is similar to temp_data, but will for example be copied to
# attributes of "any" cross references
self.ref_context = {} # type: Dict[str, Any]
# set up environment
if app:
self.setup(app)
def __getstate__(self) -> Dict:
"""Obtains serializable data for pickling."""
__dict__ = self.__dict__.copy()
__dict__.update(app=None, domains={}, events=None) # clear unpickable attributes
return __dict__
def __setstate__(self, state: Dict) -> None:
self.__dict__.update(state)
def setup(self, app: "Sphinx") -> None:
"""Set up BuildEnvironment object."""
if self.version and self.version != app.registry.get_envversion(app):
raise BuildEnvironmentError(__('build environment version not current'))
elif self.srcdir and self.srcdir != app.srcdir:
raise BuildEnvironmentError(__('source directory has changed'))
if self.project:
app.project.restore(self.project)
self.app = app
self.doctreedir = app.doctreedir
self.events = app.events
self.srcdir = app.srcdir
self.project = app.project
self.version = app.registry.get_envversion(app)
# initialize domains
self.domains = {}
for domain in app.registry.create_domains(self):
self.domains[domain.name] = domain
# setup domains (must do after all initialization)
for domain in self.domains.values():
domain.setup()
# initialize config
self._update_config(app.config)
# initialie settings
self._update_settings(app.config)
def _update_config(self, config: Config) -> None:
"""Update configurations by new one."""
self.config_status = CONFIG_OK
self.config_status_extra = ''
if self.config is None:
self.config_status = CONFIG_NEW
elif self.config.extensions != config.extensions:
self.config_status = CONFIG_EXTENSIONS_CHANGED
extensions = sorted(
set(self.config.extensions) ^ set(config.extensions))
if len(extensions) == 1:
extension = extensions[0]
else:
extension = '%d' % (len(extensions),)
self.config_status_extra = ' (%r)' % (extension,)
else:
# check if a config value was changed that affects how
# doctrees are read
for item in config.filter('env'):
if self.config[item.name] != item.value:
self.config_status = CONFIG_CHANGED
self.config_status_extra = ' (%r)' % (item.name,)
break
self.config = config
def _update_settings(self, config: Config) -> None:
"""Update settings by new config."""
self.settings['input_encoding'] = config.source_encoding
self.settings['trim_footnote_reference_space'] = config.trim_footnote_reference_space
self.settings['language_code'] = config.language or 'en'
# Allow to disable by 3rd party extension (workaround)
self.settings.setdefault('smart_quotes', True)
def set_versioning_method(self, method: Union[str, Callable], compare: bool) -> None:
"""This sets the doctree versioning method for this environment.
Versioning methods are a builder property; only builders with the same
versioning method can share the same doctree directory. Therefore, we
raise an exception if the user tries to use an environment with an
incompatible versioning method.
"""
condition = None # type: Union[bool, Callable]
if callable(method):
condition = method
else:
if method not in versioning_conditions:
raise ValueError('invalid versioning method: %r' % method)
condition = versioning_conditions[method]
if self.versioning_condition not in (None, condition):
raise SphinxError(__('This environment is incompatible with the '
'selected builder, please choose another '
'doctree directory.'))
self.versioning_condition = condition
self.versioning_compare = compare
def clear_doc(self, docname: str) -> None:
"""Remove all traces of a source file in the inventory."""
if docname in self.all_docs:
self.all_docs.pop(docname, None)
self.included.pop(docname, None)
self.reread_always.discard(docname)
for domain in self.domains.values():
domain.clear_doc(docname)
def merge_info_from(self, docnames: List[str], other: "BuildEnvironment",
app: "Sphinx") -> None:
"""Merge global information gathered about *docnames* while reading them
from the *other* environment.
This possibly comes from a parallel build process.
"""
docnames = set(docnames) # type: ignore
for docname in docnames:
self.all_docs[docname] = other.all_docs[docname]
self.included[docname] = other.included[docname]
if docname in other.reread_always:
self.reread_always.add(docname)
for domainname, domain in self.domains.items():
domain.merge_domaindata(docnames, other.domaindata[domainname])
self.events.emit('env-merge-info', self, docnames, other)
def path2doc(self, filename: str) -> str:
"""Return the docname for the filename if the file is document.
*filename* should be absolute or relative to the source directory.
"""
return self.project.path2doc(filename)
def doc2path(self, docname: str, base: bool = True) -> str:
"""Return the filename for the document name.
If *base* is True, return absolute path under self.srcdir.
If *base* is False, return relative path to self.srcdir.
"""
return self.project.doc2path(docname, base)
def relfn2path(self, filename: str, docname: str = None) -> Tuple[str, str]:
"""Return paths to a file referenced from a document, relative to
documentation root and absolute.
In the input "filename", absolute filenames are taken as relative to the
source dir, while relative filenames are relative to the dir of the
containing document.
"""
if filename.startswith('/') or filename.startswith(os.sep):
rel_fn = filename[1:]
else:
docdir = path.dirname(self.doc2path(docname or self.docname,
base=None))
rel_fn = path.join(docdir, filename)
# the path.abspath() might seem redundant, but otherwise artifacts
# such as ".." will remain in the path
return rel_fn, path.abspath(path.join(self.srcdir, rel_fn))
@property
def found_docs(self) -> Set[str]:
"""contains all existing docnames."""
return self.project.docnames
def find_files(self, config: Config, builder: "Builder") -> None:
"""Find all source files in the source dir and put them in
self.found_docs.
"""
try:
exclude_paths = (self.config.exclude_patterns +
self.config.templates_path +
builder.get_asset_paths())
self.project.discover(exclude_paths)
# Current implementation is applying translated messages in the reading
# phase.Therefore, in order to apply the updated message catalog, it is
# necessary to re-process from the reading phase. Here, if dependency
# is set for the doc source and the mo file, it is processed again from
# the reading phase when mo is updated. In the future, we would like to
# move i18n process into the writing phase, and remove these lines.
if builder.use_message_catalog:
# add catalog mo file dependency
repo = CatalogRepository(self.srcdir, self.config.locale_dirs,
self.config.language, self.config.source_encoding)
mo_paths = {c.domain: c.mo_path for c in repo.catalogs}
for docname in self.found_docs:
domain = docname_to_domain(docname, self.config.gettext_compact)
if domain in mo_paths:
self.dependencies[docname].add(mo_paths[domain])
except OSError as exc:
raise DocumentError(__('Failed to scan documents in %s: %r') %
(self.srcdir, exc)) from exc
def get_outdated_files(self, config_changed: bool) -> Tuple[Set[str], Set[str], Set[str]]:
"""Return (added, changed, removed) sets."""
# clear all files no longer present
removed = set(self.all_docs) - self.found_docs
added = set() # type: Set[str]
changed = set() # type: Set[str]
if config_changed:
# config values affect e.g. substitutions
added = self.found_docs
else:
for docname in self.found_docs:
if docname not in self.all_docs:
logger.debug('[build target] added %r', docname)
added.add(docname)
continue
# if the doctree file is not there, rebuild
filename = path.join(self.doctreedir, docname + '.doctree')
if not path.isfile(filename):
logger.debug('[build target] changed %r', docname)
changed.add(docname)
continue
# check the "reread always" list
if docname in self.reread_always:
logger.debug('[build target] changed %r', docname)
changed.add(docname)
continue
# check the mtime of the document
mtime = self.all_docs[docname]
newmtime = path.getmtime(self.doc2path(docname))
if newmtime > mtime:
logger.debug('[build target] outdated %r: %s -> %s',
docname,
datetime.utcfromtimestamp(mtime),
datetime.utcfromtimestamp(newmtime))
changed.add(docname)
continue
# finally, check the mtime of dependencies
for dep in self.dependencies[docname]:
try:
# this will do the right thing when dep is absolute too
deppath = path.join(self.srcdir, dep)
if not path.isfile(deppath):
changed.add(docname)
break
depmtime = path.getmtime(deppath)
if depmtime > mtime:
changed.add(docname)
break
except OSError:
# give it another chance
changed.add(docname)
break
return added, changed, removed
def check_dependents(self, app: "Sphinx", already: Set[str]) -> Generator[str, None, None]:
to_rewrite = [] # type: List[str]
for docnames in self.events.emit('env-get-updated', self):
to_rewrite.extend(docnames)
for docname in set(to_rewrite):
if docname not in already:
yield docname
# --------- SINGLE FILE READING --------------------------------------------
def prepare_settings(self, docname: str) -> None:
"""Prepare to set up environment for reading."""
self.temp_data['docname'] = docname
# defaults to the global default, but can be re-set in a document
self.temp_data['default_role'] = self.config.default_role
self.temp_data['default_domain'] = \
self.domains.get(self.config.primary_domain)
# utilities to use while reading a document
@property
def docname(self) -> str:
"""Returns the docname of the document currently being parsed."""
return self.temp_data['docname']
def new_serialno(self, category: str = '') -> int:
"""Return a serial number, e.g. for index entry targets.
The number is guaranteed to be unique in the current document.
"""
key = category + 'serialno'
cur = self.temp_data.get(key, 0)
self.temp_data[key] = cur + 1
return cur
def note_dependency(self, filename: str) -> None:
"""Add *filename* as a dependency of the current document.
This means that the document will be rebuilt if this file changes.
*filename* should be absolute or relative to the source directory.
"""
self.dependencies[self.docname].add(filename)
def note_included(self, filename: str) -> None:
"""Add *filename* as a included from other document.
This means the document is not orphaned.
*filename* should be absolute or relative to the source directory.
"""
self.included[self.docname].add(self.path2doc(filename))
def note_reread(self) -> None:
"""Add the current document to the list of documents that will
automatically be re-read at the next build.
"""
self.reread_always.add(self.docname)
def get_domain(self, domainname: str) -> Domain:
"""Return the domain instance with the specified name.
Raises an ExtensionError if the domain is not registered.
"""
try:
return self.domains[domainname]
except KeyError as exc:
raise ExtensionError(__('Domain %r is not registered') % domainname) from exc
# --------- RESOLVING REFERENCES AND TOCTREES ------------------------------
def get_doctree(self, docname: str) -> nodes.document:
"""Read the doctree for a file from the pickle and return it."""
filename = path.join(self.doctreedir, docname + '.doctree')
with open(filename, 'rb') as f:
doctree = pickle.load(f)
doctree.settings.env = self
doctree.reporter = LoggingReporter(self.doc2path(docname))
return doctree
def get_and_resolve_doctree(self, docname: str, builder: "Builder",
doctree: nodes.document = None, prune_toctrees: bool = True,
includehidden: bool = False) -> nodes.document:
"""Read the doctree from the pickle, resolve cross-references and
toctrees and return it.
"""
if doctree is None:
doctree = self.get_doctree(docname)
# resolve all pending cross-references
self.apply_post_transforms(doctree, docname)
# now, resolve all toctree nodes
for toctreenode in doctree.traverse(addnodes.toctree):
result = TocTree(self).resolve(docname, builder, toctreenode,
prune=prune_toctrees,
includehidden=includehidden)
if result is None:
toctreenode.replace_self([])
else:
toctreenode.replace_self(result)
return doctree
def resolve_toctree(self, docname: str, builder: "Builder", toctree: addnodes.toctree,
prune: bool = True, maxdepth: int = 0, titles_only: bool = False,
collapse: bool = False, includehidden: bool = False) -> Node:
"""Resolve a *toctree* node into individual bullet lists with titles
as items, returning None (if no containing titles are found) or
a new node.
If *prune* is True, the tree is pruned to *maxdepth*, or if that is 0,
to the value of the *maxdepth* option on the *toctree* node.
If *titles_only* is True, only toplevel document titles will be in the
resulting tree.
If *collapse* is True, all branches not containing docname will
be collapsed.
"""
return TocTree(self).resolve(docname, builder, toctree, prune,
maxdepth, titles_only, collapse,
includehidden)
def resolve_references(self, doctree: nodes.document, fromdocname: str,
builder: "Builder") -> None:
self.apply_post_transforms(doctree, fromdocname)
def apply_post_transforms(self, doctree: nodes.document, docname: str) -> None:
"""Apply all post-transforms."""
try:
# set env.docname during applying post-transforms
backup = copy(self.temp_data)
self.temp_data['docname'] = docname
transformer = SphinxTransformer(doctree)
transformer.set_environment(self)
transformer.add_transforms(self.app.registry.get_post_transforms())
transformer.apply_transforms()
finally:
self.temp_data = backup
# allow custom references to be resolved
self.events.emit('doctree-resolved', doctree, docname)
def collect_relations(self) -> Dict[str, List[str]]:
traversed = set()
def traverse_toctree(parent: str, docname: str) -> Iterator[Tuple[str, str]]:
if parent == docname:
logger.warning(__('self referenced toctree found. Ignored.'), location=docname)
return
# traverse toctree by pre-order
yield parent, docname
traversed.add(docname)
for child in (self.toctree_includes.get(docname) or []):
for subparent, subdocname in traverse_toctree(docname, child):
if subdocname not in traversed:
yield subparent, subdocname
traversed.add(subdocname)
relations = {}
docnames = traverse_toctree(None, self.config.master_doc)
prevdoc = None
parent, docname = next(docnames)
for nextparent, nextdoc in docnames:
relations[docname] = [parent, prevdoc, nextdoc]
prevdoc = docname
docname = nextdoc
parent = nextparent
relations[docname] = [parent, prevdoc, None]
return relations
def check_consistency(self) -> None:
"""Do consistency checks."""
included = set().union(*self.included.values()) # type: ignore
for docname in sorted(self.all_docs):
if docname not in self.files_to_rebuild:
if docname == self.config.master_doc:
# the master file is not included anywhere ;)
continue
if docname in included:
# the document is included from other documents
continue
if 'orphan' in self.metadata[docname]:
continue
logger.warning(__('document isn\'t included in any toctree'),
location=docname)
# call check-consistency for all extensions
for domain in self.domains.values():
domain.check_consistency()
self.events.emit('env-check-consistency', self)
|