-
Notifications
You must be signed in to change notification settings - Fork 433
/
markdown2.py
executable file
·4054 lines (3481 loc) · 155 KB
/
markdown2.py
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
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python
# Copyright (c) 2012 Trent Mick.
# Copyright (c) 2007-2008 ActiveState Corp.
# License: MIT (http://www.opensource.org/licenses/mit-license.php)
r"""A fast and complete Python implementation of Markdown.
[from http://daringfireball.net/projects/markdown/]
> Markdown is a text-to-HTML filter; it translates an easy-to-read /
> easy-to-write structured text format into HTML. Markdown's text
> format is most similar to that of plain text email, and supports
> features such as headers, *emphasis*, code blocks, blockquotes, and
> links.
>
> Markdown's syntax is designed not as a generic markup language, but
> specifically to serve as a front-end to (X)HTML. You can use span-level
> HTML tags anywhere in a Markdown document, and you can use block level
> HTML tags (like <div> and <table> as well).
Module usage:
>>> import markdown2
>>> markdown2.markdown("*boo!*") # or use `html = markdown_path(PATH)`
u'<p><em>boo!</em></p>\n'
>>> markdowner = Markdown()
>>> markdowner.convert("*boo!*")
u'<p><em>boo!</em></p>\n'
>>> markdowner.convert("**boom!**")
u'<p><strong>boom!</strong></p>\n'
This implementation of Markdown implements the full "core" syntax plus a
number of extras (e.g., code syntax coloring, footnotes) as described on
<https://github.com/trentm/python-markdown2/wiki/Extras>.
"""
cmdln_desc = """A fast and complete Python implementation of Markdown, a
text-to-HTML conversion tool for web writers.
Supported extra syntax options (see -x|--extras option below and
see <https://github.com/trentm/python-markdown2/wiki/Extras> for details):
* admonitions: Enable parsing of RST admonitions.
* breaks: Control where hard breaks are inserted in the markdown.
Options include:
- on_newline: Replace single new line characters with <br> when True
- on_backslash: Replace backslashes at the end of a line with <br>
* break-on-newline: Alias for the on_newline option in the breaks extra.
* code-friendly: Disable _ and __ for em and strong.
* cuddled-lists: Allow lists to be cuddled to the preceding paragraph.
* fenced-code-blocks: Allows a code block to not have to be indented
by fencing it with '```' on a line before and after. Based on
<http://github.github.com/github-flavored-markdown/> with support for
syntax highlighting.
* footnotes: Support footnotes as in use on daringfireball.net and
implemented in other Markdown processors (tho not in Markdown.pl v1.0.1).
* header-ids: Adds "id" attributes to headers. The id value is a slug of
the header text.
* highlightjs-lang: Allows specifying the language which used for syntax
highlighting when using fenced-code-blocks and highlightjs.
* html-classes: Takes a dict mapping html tag names (lowercase) to a
string to use for a "class" tag attribute. Currently only supports "img",
"table", "thead", "pre", "code", "ul" and "ol" tags. Add an issue if you require
this for other tags.
* link-patterns: Auto-link given regex patterns in text (e.g. bug number
references, revision number references).
* link-shortrefs: allow shortcut reference links, not followed by `[]` or
a link label.
* markdown-in-html: Allow the use of `markdown="1"` in a block HTML tag to
have markdown processing be done on its contents. Similar to
<http://michelf.com/projects/php-markdown/extra/#markdown-attr> but with
some limitations.
* metadata: Extract metadata from a leading '---'-fenced block.
See <https://github.com/trentm/python-markdown2/issues/77> for details.
* middle-word-em: Allows or disallows emphasis syntax in the middle of words,
defaulting to allow. Disabling this means that `this_text_here` will not be
converted to `this<em>text</em>here`.
* nofollow: Add `rel="nofollow"` to add `<a>` tags with an href. See
<http://en.wikipedia.org/wiki/Nofollow>.
* numbering: Support of generic counters. Non standard extension to
allow sequential numbering of figures, tables, equations, exhibits etc.
* pyshell: Treats unindented Python interactive shell sessions as <code>
blocks.
* smarty-pants: Replaces ' and " with curly quotation marks or curly
apostrophes. Replaces --, ---, ..., and . . . with en dashes, em dashes,
and ellipses.
* spoiler: A special kind of blockquote commonly hidden behind a
click on SO. Syntax per <http://meta.stackexchange.com/a/72878>.
* strike: text inside of double tilde is ~~strikethrough~~
* tag-friendly: Requires atx style headers to have a space between the # and
the header text. Useful for applications that require twitter style tags to
pass through the parser.
* tables: Tables using the same format as GFM
<https://help.github.com/articles/github-flavored-markdown#tables> and
PHP-Markdown Extra <https://michelf.ca/projects/php-markdown/extra/#table>.
* toc: The returned HTML string gets a new "toc_html" attribute which is
a Table of Contents for the document. (experimental)
* use-file-vars: Look for an Emacs-style markdown-extras file variable to turn
on Extras.
* wiki-tables: Google Code Wiki-style tables. See
<http://code.google.com/p/support/wiki/WikiSyntax#Tables>.
* wavedrom: Support for generating Wavedrom digital timing diagrams
* xml: Passes one-liner processing instructions and namespaced XML tags.
"""
# Dev Notes:
# - Python's regex syntax doesn't have '\z', so I'm using '\Z'. I'm
# not yet sure if there implications with this. Compare 'pydoc sre'
# and 'perldoc perlre'.
__version_info__ = (2, 5, 2)
__version__ = '.'.join(map(str, __version_info__))
__author__ = "Trent Mick"
import argparse
import codecs
import logging
import re
import sys
from collections import defaultdict, OrderedDict
from abc import ABC, abstractmethod
import functools
from collections.abc import Iterable
from hashlib import sha256
from random import random
from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, Type, TypedDict, Union
from collections.abc import Collection
from enum import IntEnum, auto
from os import urandom
# ---- type defs
_safe_mode = Literal['replace', 'escape']
_extras_dict = dict[str, Any]
_extras_param = Union[list[str], _extras_dict]
_link_patterns = Iterable[tuple[re.Pattern, Union[str, Callable[[re.Match], str]]]]
# ---- globals
DEBUG = False
log = logging.getLogger("markdown")
DEFAULT_TAB_WIDTH = 4
SECRET_SALT = urandom(16)
# MD5 function was previously used for this; the "md5" prefix was kept for
# backwards compatibility.
def _hash_text(s: str) -> str:
return 'md5-' + sha256(SECRET_SALT + s.encode("utf-8")).hexdigest()[32:]
# Table of hash values for escaped characters:
g_escape_table = {ch: _hash_text(ch)
for ch in '\\`*_{}[]()>#+-.!'}
# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
# http://bumppo.net/projects/amputator/
_AMPERSAND_RE = re.compile(r'&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)')
# ---- exceptions
class MarkdownError(Exception):
pass
# ---- public api
def markdown_path(
path: str,
encoding: str = "utf-8",
html4tags: bool = False,
tab_width: int = DEFAULT_TAB_WIDTH,
safe_mode: Optional[_safe_mode] = None,
extras: Optional[_extras_param] = None,
link_patterns: Optional[_link_patterns] = None,
footnote_title: Optional[str] = None,
footnote_return_symbol: Optional[str] = None,
use_file_vars: bool = False
) -> 'UnicodeWithAttrs':
fp = codecs.open(path, 'r', encoding)
text = fp.read()
fp.close()
return Markdown(html4tags=html4tags, tab_width=tab_width,
safe_mode=safe_mode, extras=extras,
link_patterns=link_patterns,
footnote_title=footnote_title,
footnote_return_symbol=footnote_return_symbol,
use_file_vars=use_file_vars).convert(text)
def markdown(
text: str,
html4tags: bool = False,
tab_width: int = DEFAULT_TAB_WIDTH,
safe_mode: Optional[_safe_mode] = None,
extras: Optional[_extras_param] = None,
link_patterns: Optional[_link_patterns] = None,
footnote_title: Optional[str] = None,
footnote_return_symbol: Optional[str] =None,
use_file_vars: bool = False,
cli: bool = False
) -> 'UnicodeWithAttrs':
return Markdown(html4tags=html4tags, tab_width=tab_width,
safe_mode=safe_mode, extras=extras,
link_patterns=link_patterns,
footnote_title=footnote_title,
footnote_return_symbol=footnote_return_symbol,
use_file_vars=use_file_vars, cli=cli).convert(text)
class Stage(IntEnum):
PREPROCESS = auto()
HASH_HTML = auto()
LINK_DEFS = auto()
BLOCK_GAMUT = auto()
HEADERS = auto()
LISTS = auto()
CODE_BLOCKS = auto()
BLOCK_QUOTES = auto()
PARAGRAPHS = auto()
SPAN_GAMUT = auto()
CODE_SPANS = auto()
ESCAPE_SPECIAL = auto()
LINKS = auto() # and auto links
ITALIC_AND_BOLD = auto()
POSTPROCESS = auto()
UNHASH_HTML = auto()
def mark_stage(stage: Stage):
'''
Decorator that handles executing relevant `Extra`s before and after this `Stage` executes.
'''
def wrapper(func):
@functools.wraps(func)
def inner(md: 'Markdown', text, *args, **kwargs):
md.stage = stage
# set "order" prop so extras can tell if they're being invoked before/after the stage
md.order = stage - 0.5
if stage in Extra._exec_order:
for klass in Extra._exec_order[stage][0]:
if klass.name not in md.extra_classes:
continue
extra = md.extra_classes[klass.name]
if extra.test(text):
text = extra.run(text)
md.order = stage
text = func(md, text, *args, **kwargs)
md.order = stage + 0.5
if stage in Extra._exec_order:
for klass in Extra._exec_order[stage][1]:
if klass.name not in md.extra_classes:
continue
extra = md.extra_classes[klass.name]
if extra.test(text):
text = extra.run(text)
return text
return inner
return wrapper
class Markdown:
# The dict of "extras" to enable in processing -- a mapping of
# extra name to argument for the extra. Most extras do not have an
# argument, in which case the value is None.
#
# This can be set via (a) subclassing and (b) the constructor
# "extras" argument.
extras: _extras_dict
# dict of `Extra` names and associated class instances, populated during _setup_extras
extra_classes: dict[str, 'Extra']
urls: dict[str, str]
titles: dict[str, str]
html_blocks: dict[str, str]
html_spans: dict[str, str]
html_removed_text: str = "{(#HTML#)}" # placeholder removed text that does not trigger bold
html_removed_text_compat: str = "[HTML_REMOVED]" # for compat with markdown.py
safe_mode: Optional[_safe_mode]
_toc: list[tuple[int, str, str]]
# Used to track when we're inside an ordered or unordered list
# (see _ProcessListItems() for details):
list_level = 0
stage: Stage
'''Current "stage" of markdown conversion taking place'''
order: float
'''
Same as `Stage` but will be +/- 0.5 of the value of `Stage`.
This allows extras to check if they are running before or after a particular stage
with `if md.order < md.stage`.
'''
_ws_only_line_re = re.compile(r"^[ \t]+$", re.M)
def __init__(
self,
html4tags: bool = False,
tab_width: int = DEFAULT_TAB_WIDTH,
safe_mode: Optional[_safe_mode] = None,
extras: Optional[_extras_param] = None,
link_patterns: Optional[_link_patterns] = None,
footnote_title: Optional[str] = None,
footnote_return_symbol: Optional[str] = None,
use_file_vars: bool = False,
cli: bool = False
):
if html4tags:
self.empty_element_suffix = ">"
else:
self.empty_element_suffix = " />"
self.tab_width = tab_width
self.tab = tab_width * " "
# For compatibility with earlier markdown2.py and with
# markdown.py's safe_mode being a boolean,
# safe_mode == True -> "replace"
if safe_mode is True:
self.safe_mode = "replace"
else:
self.safe_mode = safe_mode
# Massaging and building the "extras" info.
if getattr(self, 'extras', None) is None:
self.extras = {}
elif not isinstance(self.extras, dict):
# inheriting classes may set `self.extras` as List[str].
# we can't allow it through type hints but we can convert it
self.extras = {e: None for e in self.extras} # type:ignore
if extras:
if not isinstance(extras, dict):
extras = {e: None for e in extras}
self.extras.update(extras)
assert isinstance(self.extras, dict)
if "toc" in self.extras:
if "header-ids" not in self.extras:
self.extras["header-ids"] = None # "toc" implies "header-ids"
if self.extras["toc"] is None:
self._toc_depth = 6
else:
self._toc_depth = self.extras["toc"].get("depth", 6)
if 'header-ids' in self.extras:
if not isinstance(self.extras['header-ids'], dict):
self.extras['header-ids'] = {
'mixed': False,
'prefix': self.extras['header-ids'],
'reset-count': True
}
if 'break-on-newline' in self.extras:
self.extras.setdefault('breaks', {})
self.extras['breaks']['on_newline'] = True
if 'link-patterns' in self.extras:
# allow link patterns via extras dict without kwarg explicitly set
link_patterns = link_patterns or self.extras['link-patterns']
if link_patterns is None:
# if you have specified that the link-patterns extra SHOULD
# be used (via self.extras) but you haven't provided anything
# via the link_patterns argument then an error is raised
raise MarkdownError("If the 'link-patterns' extra is used, an argument for 'link_patterns' is required")
self.extras['link-patterns'] = link_patterns
self._instance_extras = self.extras.copy()
self.link_patterns = link_patterns
self.footnote_title = footnote_title
self.footnote_return_symbol = footnote_return_symbol
self.use_file_vars = use_file_vars
self._outdent_re = re.compile(r'^(\t|[ ]{1,%d})' % tab_width, re.M)
self.cli = cli
self._escape_table = g_escape_table.copy()
self._code_table = {}
if "smarty-pants" in self.extras:
self._escape_table['"'] = _hash_text('"')
self._escape_table["'"] = _hash_text("'")
def reset(self):
self.urls = {}
self.titles = {}
self.html_blocks = {}
self.html_spans = {}
self.list_level = 0
self.extras = self._instance_extras.copy()
self._setup_extras()
self._toc = []
def _setup_extras(self):
if "footnotes" in self.extras:
# order of insertion matters for footnotes. Use ordered dict for Python < 3.7
# https://docs.python.org/3/whatsnew/3.7.html#summary-release-highlights
self.footnotes = OrderedDict()
self.footnote_ids = []
if "header-ids" in self.extras:
if not hasattr(self, '_count_from_header_id') or self.extras['header-ids'].get('reset-count', False):
self._count_from_header_id = defaultdict(int)
if "metadata" in self.extras:
self.metadata: dict[str, Any] = {}
self.extra_classes = {}
for name, klass in Extra._registry.items():
if name not in self.extras:
continue
self.extra_classes[name] = klass(self, (self.extras.get(name, {})))
# Per <https://developer.mozilla.org/en-US/docs/HTML/Element/a> "rel"
# should only be used in <a> tags with an "href" attribute.
# Opens the linked document in a new window or tab
# should only used in <a> tags with an "href" attribute.
# same with _a_nofollow
_a_nofollow_or_blank_links = re.compile(r"""
<(a)
(
[^>]*
href= # href is required
['"]? # HTML5 attribute values do not have to be quoted
[^#'"] # We don't want to match href values that start with # (like footnotes)
)
""",
re.IGNORECASE | re.VERBOSE
)
def convert(self, text: str) -> 'UnicodeWithAttrs':
"""Convert the given text."""
# Main function. The order in which other subs are called here is
# essential. Link and image substitutions need to happen before
# _EscapeSpecialChars(), so that any *'s or _'s in the <a>
# and <img> tags get encoded.
# Clear the global hashes. If we don't clear these, you get conflicts
# from other articles when generating a page which contains more than
# one article (e.g. an index page that shows the N most recent
# articles):
self.reset()
if not isinstance(text, str):
# TODO: perhaps shouldn't presume UTF-8 for string input?
text = str(text, 'utf-8')
if self.use_file_vars:
# Look for emacs-style file variable hints.
text = self._emacs_oneliner_vars_pat.sub(self._emacs_vars_oneliner_sub, text)
emacs_vars = self._get_emacs_vars(text)
if "markdown-extras" in emacs_vars:
splitter = re.compile("[ ,]+")
for e in splitter.split(emacs_vars["markdown-extras"]):
if '=' in e:
ename, earg = e.split('=', 1)
try:
earg = int(earg)
except ValueError:
pass
else:
ename, earg = e, None
self.extras[ename] = earg
self._setup_extras()
# Standardize line endings:
text = text.replace("\r\n", "\n")
text = text.replace("\r", "\n")
# Make sure $text ends with a couple of newlines:
text += "\n\n"
# Convert all tabs to spaces.
text = self._detab(text)
# Strip any lines consisting only of spaces and tabs.
# This makes subsequent regexen easier to write, because we can
# match consecutive blank lines with /\n+/ instead of something
# contorted like /[ \t]*\n+/ .
text = self._ws_only_line_re.sub("", text)
# strip metadata from head and extract
if "metadata" in self.extras:
text = self._extract_metadata(text)
text = self.preprocess(text)
if self.safe_mode:
text = self._hash_html_spans(text)
# Turn block-level HTML blocks into hash entries
text = self._hash_html_blocks(text, raw=True)
# Strip link definitions, store in hashes.
if "footnotes" in self.extras:
# Must do footnotes first because an unlucky footnote defn
# looks like a link defn:
# [^4]: this "looks like a link defn"
text = self._strip_footnote_definitions(text)
text = self._strip_link_definitions(text)
text = self._run_block_gamut(text)
if "footnotes" in self.extras:
text = self._add_footnotes(text)
text = self.postprocess(text)
text = self._unescape_special_chars(text)
text = self._unhash_html_spans(text)
if self.safe_mode:
# return the removed text warning to its markdown.py compatible form
text = text.replace(self.html_removed_text, self.html_removed_text_compat)
do_target_blank_links = "target-blank-links" in self.extras
do_nofollow_links = "nofollow" in self.extras
if do_target_blank_links and do_nofollow_links:
text = self._a_nofollow_or_blank_links.sub(r'<\1 rel="nofollow noopener" target="_blank"\2', text)
elif do_target_blank_links:
text = self._a_nofollow_or_blank_links.sub(r'<\1 rel="noopener" target="_blank"\2', text)
elif do_nofollow_links:
text = self._a_nofollow_or_blank_links.sub(r'<\1 rel="nofollow"\2', text)
if "toc" in self.extras and self._toc:
if self.extras['header-ids'].get('mixed'):
# TOC will only be out of order if mixed headers is enabled
def toc_sort(entry):
'''Sort the TOC by order of appearance in text'''
match = re.search(
# header tag, any attrs, the ID, any attrs, the text, close tag
r'^<(h%d).*?id=(["\'])%s\2.*>%s</\1>$' % (entry[0], entry[1], re.escape(entry[2])),
text, re.M
)
return match.start() if match else 0
self._toc.sort(key=toc_sort)
self._toc_html = calculate_toc_html(self._toc)
# Prepend toc html to output
if self.cli or (self.extras['toc'] is not None and self.extras['toc'].get('prepend', False)):
text = f'{self._toc_html}\n{text}'
text += "\n"
# Attach attrs to output
rv = UnicodeWithAttrs(text)
if "toc" in self.extras and self._toc:
rv.toc_html = self._toc_html
if "metadata" in self.extras:
rv.metadata = self.metadata
return rv
@mark_stage(Stage.POSTPROCESS)
def postprocess(self, text: str) -> str:
"""A hook for subclasses to do some postprocessing of the html, if
desired. This is called before unescaping of special chars and
unhashing of raw HTML spans.
"""
return text
@mark_stage(Stage.PREPROCESS)
def preprocess(self, text: str) -> str:
"""A hook for subclasses to do some preprocessing of the Markdown, if
desired. This is called after basic formatting of the text, but prior
to any extras, safe mode, etc. processing.
"""
return text
# Is metadata if the content starts with optional '---'-fenced `key: value`
# pairs. E.g. (indented for presentation):
# ---
# foo: bar
# another-var: blah blah
# ---
# # header
# or:
# foo: bar
# another-var: blah blah
#
# # header
_meta_data_pattern = re.compile(r'''
^{0}( # optional opening fence
(?:
{1}:(?:\n+[ \t]+.*)+ # indented lists
)|(?:
(?:{1}:\s+>(?:\n\s+.*)+?) # multiline long descriptions
(?=\n{1}:\s*.*\n|\s*\Z) # match up until the start of the next key:value definition or the end of the input text
)|(?:
{1}:(?! >).*\n? # simple key:value pair, leading spaces allowed
)
){0} # optional closing fence
'''.format(r'(?:---[\ \t]*\n)?', r'[\S \t]*\w[\S \t]*\s*'), re.MULTILINE | re.VERBOSE
)
_key_val_list_pat = re.compile(
r"^-(?:[ \t]*([^\n]*)(?:[ \t]*[:-][ \t]*(\S+))?)(?:\n((?:[ \t]+[^\n]+\n?)+))?",
re.MULTILINE,
)
_key_val_dict_pat = re.compile(
r"^([^:\n]+)[ \t]*:[ \t]*([^\n]*)(?:((?:\n[ \t]+[^\n]+)+))?", re.MULTILINE
) # grp0: key, grp1: value, grp2: multiline value
_meta_data_fence_pattern = re.compile(r'^---[\ \t]*\n', re.MULTILINE)
_meta_data_newline = re.compile("^\n", re.MULTILINE)
def _extract_metadata(self, text: str) -> str:
if text.startswith("---"):
fence_splits = re.split(self._meta_data_fence_pattern, text, maxsplit=2)
metadata_content = fence_splits[1]
tail = fence_splits[2]
else:
metadata_split = re.split(self._meta_data_newline, text, maxsplit=1)
metadata_content = metadata_split[0]
tail = metadata_split[1]
# _meta_data_pattern only has one capturing group, so we can assume
# the returned type to be list[str]
match: list[str] = re.findall(self._meta_data_pattern, metadata_content)
if not match:
return text
def parse_structured_value(value: str) -> Union[list[Any], dict[str, Any]]:
vs = value.lstrip()
vs = value.replace(v[: len(value) - len(vs)], "\n")[1:]
# List
if vs.startswith("-"):
r: list[Any] = []
# the regex used has multiple capturing groups, so
# returned type from findall will be List[List[str]]
match: list[str]
for match in re.findall(self._key_val_list_pat, vs):
if match[0] and not match[1] and not match[2]:
r.append(match[0].strip())
elif match[0] == ">" and not match[1] and match[2]:
r.append(match[2].strip())
elif match[0] and match[1]:
r.append({match[0].strip(): match[1].strip()})
elif not match[0] and not match[1] and match[2]:
r.append(parse_structured_value(match[2]))
else:
# Broken case
pass
return r
# Dict
else:
return {
match[0].strip(): (
match[1].strip()
if match[1]
else parse_structured_value(match[2])
)
for match in re.findall(self._key_val_dict_pat, vs)
}
for item in match:
k, v = item.split(":", 1)
# Multiline value
if v[:3] == " >\n":
self.metadata[k.strip()] = _dedent(v[3:]).strip()
# Empty value
elif v == "\n":
self.metadata[k.strip()] = ""
# Structured value
elif v[0] == "\n":
self.metadata[k.strip()] = parse_structured_value(v)
# Simple value
else:
self.metadata[k.strip()] = v.strip()
return tail
_emacs_oneliner_vars_pat = re.compile(r"((?:<!--)?\s*-\*-)\s*(?:(\S[^\r\n]*?)([\r\n]\s*)?)?(-\*-\s*(?:-->)?)", re.UNICODE)
# This regular expression is intended to match blocks like this:
# PREFIX Local Variables: SUFFIX
# PREFIX mode: Tcl SUFFIX
# PREFIX End: SUFFIX
# Some notes:
# - "[ \t]" is used instead of "\s" to specifically exclude newlines
# - "(\r\n|\n|\r)" is used instead of "$" because the sre engine does
# not like anything other than Unix-style line terminators.
_emacs_local_vars_pat = re.compile(r"""^
(?P<prefix>(?:[^\r\n|\n|\r])*?)
[\ \t]*Local\ Variables:[\ \t]*
(?P<suffix>.*?)(?:\r\n|\n|\r)
(?P<content>.*?\1End:)
""", re.IGNORECASE | re.MULTILINE | re.DOTALL | re.VERBOSE)
def _emacs_vars_oneliner_sub(self, match: re.Match) -> str:
if match.group(1).strip() == '-*-' and match.group(4).strip() == '-*-':
lead_ws = re.findall(r'^\s*', match.group(1))[0]
tail_ws = re.findall(r'\s*$', match.group(4))[0]
return '{}<!-- {} {} {} -->{}'.format(lead_ws, '-*-', match.group(2).strip(), '-*-', tail_ws)
start, end = match.span()
return match.string[start: end]
def _get_emacs_vars(self, text: str) -> dict[str, str]:
"""Return a dictionary of emacs-style local variables.
Parsing is done loosely according to this spec (and according to
some in-practice deviations from this):
http://www.gnu.org/software/emacs/manual/html_node/emacs/Specifying-File-Variables.html#Specifying-File-Variables
"""
emacs_vars = {}
SIZE = pow(2, 13) # 8kB
# Search near the start for a '-*-'-style one-liner of variables.
head = text[:SIZE]
if "-*-" in head:
match = self._emacs_oneliner_vars_pat.search(head)
if match:
emacs_vars_str = match.group(2)
assert '\n' not in emacs_vars_str
emacs_var_strs = [s.strip() for s in emacs_vars_str.split(';')
if s.strip()]
if len(emacs_var_strs) == 1 and ':' not in emacs_var_strs[0]:
# While not in the spec, this form is allowed by emacs:
# -*- Tcl -*-
# where the implied "variable" is "mode". This form
# is only allowed if there are no other variables.
emacs_vars["mode"] = emacs_var_strs[0].strip()
else:
for emacs_var_str in emacs_var_strs:
try:
variable, value = emacs_var_str.strip().split(':', 1)
except ValueError:
log.debug("emacs variables error: malformed -*- "
"line: %r", emacs_var_str)
continue
# Lowercase the variable name because Emacs allows "Mode"
# or "mode" or "MoDe", etc.
emacs_vars[variable.lower()] = value.strip()
tail = text[-SIZE:]
if "Local Variables" in tail:
match = self._emacs_local_vars_pat.search(tail)
if match:
prefix = match.group("prefix")
suffix = match.group("suffix")
lines = match.group("content").splitlines(False)
# print "prefix=%r, suffix=%r, content=%r, lines: %s"\
# % (prefix, suffix, match.group("content"), lines)
# Validate the Local Variables block: proper prefix and suffix
# usage.
for i, line in enumerate(lines):
if not line.startswith(prefix):
log.debug("emacs variables error: line '%s' "
"does not use proper prefix '%s'"
% (line, prefix))
return {}
# Don't validate suffix on last line. Emacs doesn't care,
# neither should we.
if i != len(lines)-1 and not line.endswith(suffix):
log.debug("emacs variables error: line '%s' "
"does not use proper suffix '%s'"
% (line, suffix))
return {}
# Parse out one emacs var per line.
continued_for = None
for line in lines[:-1]: # no var on the last line ("PREFIX End:")
if prefix:
line = line[len(prefix):] # strip prefix
if suffix:
line = line[:-len(suffix)] # strip suffix
line = line.strip()
if continued_for:
variable = continued_for
if line.endswith('\\'):
line = line[:-1].rstrip()
else:
continued_for = None
emacs_vars[variable] += ' ' + line
else:
try:
variable, value = line.split(':', 1)
except ValueError:
log.debug("local variables error: missing colon "
"in local variables entry: '%s'" % line)
continue
# Do NOT lowercase the variable name, because Emacs only
# allows "mode" (and not "Mode", "MoDe", etc.) in this block.
value = value.strip()
if value.endswith('\\'):
value = value[:-1].rstrip()
continued_for = variable
else:
continued_for = None
emacs_vars[variable] = value
# Unquote values.
for var, val in list(emacs_vars.items()):
if len(val) > 1 and (val.startswith('"') and val.endswith('"')
or val.startswith('"') and val.endswith('"')):
emacs_vars[var] = val[1:-1]
return emacs_vars
def _detab_line(self, line: str) -> str:
r"""Recusively convert tabs to spaces in a single line.
Called from _detab()."""
if '\t' not in line:
return line
chunk1, chunk2 = line.split('\t', 1)
chunk1 += (' ' * (self.tab_width - len(chunk1) % self.tab_width))
output = chunk1 + chunk2
return self._detab_line(output)
def _detab(self, text: str) -> str:
r"""Iterate text line by line and convert tabs to spaces.
>>> m = Markdown()
>>> m._detab("\tfoo")
' foo'
>>> m._detab(" \tfoo")
' foo'
>>> m._detab("\t foo")
' foo'
>>> m._detab(" foo")
' foo'
>>> m._detab(" foo\n\tbar\tblam")
' foo\n bar blam'
"""
if '\t' not in text:
return text
output = []
for line in text.splitlines():
output.append(self._detab_line(line))
return '\n'.join(output)
# I broke out the html5 tags here and add them to _block_tags_a and
# _block_tags_b. This way html5 tags are easy to keep track of.
_html5tags = '|article|aside|header|hgroup|footer|nav|section|figure|figcaption'
_block_tags_a = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del|style|html|head|body'
_block_tags_a += _html5tags
_strict_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
</\2> # the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_a,
re.X | re.M)
_block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math'
_block_tags_b += _html5tags
_span_tags = (
'a|abbr|acronym|b|bdo|big|br|button|cite|code|dfn|em|i|img|input|kbd|label|map|object|output|q'
'|samp|script|select|small|span|strong|sub|sup|textarea|time|tt|var'
)
_liberal_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
.*</\2> # the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_b,
re.X | re.M)
_html_markdown_attr_re = re.compile(
r'''\s+markdown=("1"|'1')''')
def _hash_html_block_sub(
self,
match: Union[re.Match, str],
raw: bool = False
) -> str:
if isinstance(match, str):
html = match
tag = None
else:
html = match.group(1)
try:
tag = match.group(2)
except IndexError:
tag = None
if not tag:
m = re.match(r'.*?<(\S).*?\s*>', html)
# tag shouldn't be none but make the assertion for type checker
assert m is not None
tag = m.group(1)
if raw and self.safe_mode:
html = self._sanitize_html(html)
elif 'markdown-in-html' in self.extras and 'markdown=' in html:
first_line = html.split('\n', 1)[0]
m = self._html_markdown_attr_re.search(first_line)
if m:
lines = html.split('\n')
# if MD is on same line as opening tag then split across two lines
lines = list(filter(None, (re.split(r'(.*?<%s.*markdown=.*?>)' % tag, lines[0])))) + lines[1:]
# if MD on same line as closing tag, split across two lines
lines = lines[:-1] + list(filter(None, re.split(r'(\s*?</%s>.*?$)' % tag, lines[-1])))
# extract key sections of the match
first_line = lines[0]
middle = '\n'.join(lines[1:-1])
last_line = lines[-1]
# remove `markdown="1"` attr from tag
first_line = first_line[:m.start()] + first_line[m.end():]
# hash the HTML segments to protect them
f_key = _hash_text(first_line)
self.html_blocks[f_key] = first_line
l_key = _hash_text(last_line)
self.html_blocks[l_key] = last_line
return ''.join(["\n\n", f_key,
"\n\n", middle, "\n\n",
l_key, "\n\n"])
elif self.extras.get('header-ids', {}).get('mixed') and self._h_tag_re.match(html):
html = self._h_tag_re.sub(self._h_tag_sub, html)
key = _hash_text(html)
self.html_blocks[key] = html
return "\n\n" + key + "\n\n"
@mark_stage(Stage.HASH_HTML)
def _hash_html_blocks(self, text: str, raw: bool = False) -> str:
"""Hashify HTML blocks
We only want to do this for block-level HTML tags, such as headers,
lists, and tables. That's because we still want to wrap <p>s around
"paragraphs" that are wrapped in non-block-level tags, such as anchors,
phrase emphasis, and spans. The list of tags we're looking for is
hard-coded.
@param raw {boolean} indicates if these are raw HTML blocks in
the original source. It makes a difference in "safe" mode.
"""
if '<' not in text:
return text
# Pass `raw` value into our calls to self._hash_html_block_sub.
hash_html_block_sub = _curry(self._hash_html_block_sub, raw=raw)
# First, look for nested blocks, e.g.:
# <div>
# <div>
# tags for inner block must be indented.
# </div>
# </div>
#
# The outermost tags must start at the left margin for this to match, and
# the inner nested divs must be indented.
# We need to do this before the next, more liberal match, because the next
# match will start at the first `<div>` and stop at the first `</div>`.
text = self._strict_tag_block_sub(text, self._block_tags_a, hash_html_block_sub)
# Now match more liberally, simply from `\n<tag>` to `</tag>\n`
text = self._liberal_tag_block_re.sub(hash_html_block_sub, text)
# now do the same for spans that are acting like blocks
# eg: an anchor split over multiple lines for readability
text = self._strict_tag_block_sub(
text, self._span_tags,
# inline elements can't contain block level elements, so only span gamut is required
lambda t: hash_html_block_sub(self._run_span_gamut(t))
)
# Special case just for <hr />. It was easier to make a special
# case than to make the other regex more complicated.
if "<hr" in text:
_hr_tag_re = _hr_tag_re_from_tab_width(self.tab_width)
text = _hr_tag_re.sub(hash_html_block_sub, text)
# Special case for standalone HTML comments:
if "<!--" in text:
start = 0
while True:
# Delimiters for next comment block.