forked from open-machine-learning/mloss
-
Notifications
You must be signed in to change notification settings - Fork 0
/
markdown.py
1929 lines (1401 loc) · 60.2 KB
/
markdown.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
version = "1.7"
version_info = (1,7,0,"rc-2")
__revision__ = "$Rev: 72 $"
"""
Python-Markdown
===============
Converts Markdown to HTML. Basic usage as a module:
import markdown
md = Markdown()
html = md.convert(your_text_string)
See http://www.freewisdom.org/projects/python-markdown/ for more
information and instructions on how to extend the functionality of the
script. (You might want to read that before you try modifying this
file.)
Started by [Manfred Stienstra](http://www.dwerg.net/). Continued and
maintained by [Yuri Takhteyev](http://www.freewisdom.org) and [Waylan
Limberg](http://achinghead.com/).
Contact: yuri [at] freewisdom.org
waylan [at] gmail.com
License: GPL 2 (http://www.gnu.org/copyleft/gpl.html) or BSD
"""
import re, sys, codecs
from logging import getLogger, StreamHandler, Formatter, \
DEBUG, INFO, WARN, ERROR, CRITICAL
MESSAGE_THRESHOLD = CRITICAL
# Configure debug message logger (the hard way - to support python 2.3)
logger = getLogger('MARKDOWN')
logger.setLevel(DEBUG) # This is restricted by handlers later
console_hndlr = StreamHandler()
formatter = Formatter('%(name)s-%(levelname)s: "%(message)s"')
console_hndlr.setFormatter(formatter)
console_hndlr.setLevel(MESSAGE_THRESHOLD)
logger.addHandler(console_hndlr)
def message(level, text):
''' A wrapper method for logging debug messages. '''
logger.log(level, text)
# --------------- CONSTANTS YOU MIGHT WANT TO MODIFY -----------------
TAB_LENGTH = 4 # expand tabs to this many spaces
ENABLE_ATTRIBUTES = True # @id = xyz -> <... id="xyz">
SMART_EMPHASIS = 1 # this_or_that does not become this<i>or</i>that
HTML_REMOVED_TEXT = "[HTML_REMOVED]" # text used instead of HTML in safe mode
RTL_BIDI_RANGES = ( (u'\u0590', u'\u07FF'),
# from Hebrew to Nko (includes Arabic, Syriac and Thaana)
(u'\u2D30', u'\u2D7F'),
# Tifinagh
)
# Unicode Reference Table:
# 0590-05FF - Hebrew
# 0600-06FF - Arabic
# 0700-074F - Syriac
# 0750-077F - Arabic Supplement
# 0780-07BF - Thaana
# 07C0-07FF - Nko
BOMS = { 'utf-8': (codecs.BOM_UTF8, ),
'utf-16': (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE),
#'utf-32': (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE)
}
def removeBOM(text, encoding):
convert = isinstance(text, unicode)
for bom in BOMS[encoding]:
bom = convert and bom.decode(encoding) or bom
if text.startswith(bom):
return text.lstrip(bom)
return text
# The following constant specifies the name used in the usage
# statement displayed for python versions lower than 2.3. (With
# python2.3 and higher the usage statement is generated by optparse
# and uses the actual name of the executable called.)
EXECUTABLE_NAME_FOR_USAGE = "python markdown.py"
# --------------- CONSTANTS YOU _SHOULD NOT_ HAVE TO CHANGE ----------
# a template for html placeholders
HTML_PLACEHOLDER_PREFIX = "qaodmasdkwaspemas"
HTML_PLACEHOLDER = HTML_PLACEHOLDER_PREFIX + "%dajkqlsmdqpakldnzsdfls"
BLOCK_LEVEL_ELEMENTS = ['p', 'div', 'blockquote', 'pre', 'table',
'dl', 'ol', 'ul', 'script', 'noscript',
'form', 'fieldset', 'iframe', 'math', 'ins',
'del', 'hr', 'hr/', 'style']
def isBlockLevel (tag):
return ( (tag in BLOCK_LEVEL_ELEMENTS) or
(tag[0] == 'h' and tag[1] in "0123456789") )
"""
======================================================================
========================== NANODOM ===================================
======================================================================
The three classes below implement some of the most basic DOM
methods. I use this instead of minidom because I need a simpler
functionality and do not want to require additional libraries.
Importantly, NanoDom does not do normalization, which is what we
want. It also adds extra white space when converting DOM to string
"""
ENTITY_NORMALIZATION_EXPRESSIONS = [ (re.compile("&"), "&"),
(re.compile("<"), "<"),
(re.compile(">"), ">")]
ENTITY_NORMALIZATION_EXPRESSIONS_SOFT = [ (re.compile("&(?!\#)"), "&"),
(re.compile("<"), "<"),
(re.compile(">"), ">"),
(re.compile("\""), """)]
def getBidiType(text):
if not text: return None
ch = text[0]
if not isinstance(ch, unicode) or not ch.isalpha():
return None
else:
for min, max in RTL_BIDI_RANGES:
if ( ch >= min and ch <= max ):
return "rtl"
else:
return "ltr"
class Document:
def __init__ (self):
self.bidi = "ltr"
def appendChild(self, child):
self.documentElement = child
child.isDocumentElement = True
child.parent = self
self.entities = {}
def setBidi(self, bidi):
if bidi:
self.bidi = bidi
def createElement(self, tag, textNode=None):
el = Element(tag)
el.doc = self
if textNode:
el.appendChild(self.createTextNode(textNode))
return el
def createTextNode(self, text):
node = TextNode(text)
node.doc = self
return node
def createEntityReference(self, entity):
if entity not in self.entities:
self.entities[entity] = EntityReference(entity)
return self.entities[entity]
def createCDATA(self, text):
node = CDATA(text)
node.doc = self
return node
def toxml (self):
return self.documentElement.toxml()
def normalizeEntities(self, text, avoidDoubleNormalizing=False):
if avoidDoubleNormalizing:
regexps = ENTITY_NORMALIZATION_EXPRESSIONS_SOFT
else:
regexps = ENTITY_NORMALIZATION_EXPRESSIONS
for regexp, substitution in regexps:
text = regexp.sub(substitution, text)
return text
def find(self, test):
return self.documentElement.find(test)
def unlink(self):
self.documentElement.unlink()
self.documentElement = None
class CDATA:
type = "cdata"
def __init__ (self, text):
self.text = text
def handleAttributes(self):
pass
def toxml (self):
return "<![CDATA[" + self.text + "]]>"
class Element:
type = "element"
def __init__ (self, tag):
self.nodeName = tag
self.attributes = []
self.attribute_values = {}
self.childNodes = []
self.bidi = None
self.isDocumentElement = False
def setBidi(self, bidi):
if bidi:
orig_bidi = self.bidi
if not self.bidi or self.isDocumentElement:
# Once the bidi is set don't change it (except for doc element)
self.bidi = bidi
self.parent.setBidi(bidi)
def unlink(self):
for child in self.childNodes:
if child.type == "element":
child.unlink()
self.childNodes = None
def setAttribute(self, attr, value):
if not attr in self.attributes:
self.attributes.append(attr)
self.attribute_values[attr] = value
def insertChild(self, position, child):
self.childNodes.insert(position, child)
child.parent = self
def removeChild(self, child):
self.childNodes.remove(child)
def replaceChild(self, oldChild, newChild):
position = self.childNodes.index(oldChild)
self.removeChild(oldChild)
self.insertChild(position, newChild)
def appendChild(self, child):
self.childNodes.append(child)
child.parent = self
def handleAttributes(self):
pass
def find(self, test, depth=0):
""" Returns a list of descendants that pass the test function """
matched_nodes = []
for child in self.childNodes:
if test(child):
matched_nodes.append(child)
if child.type == "element":
matched_nodes += child.find(test, depth+1)
return matched_nodes
def toxml(self):
if ENABLE_ATTRIBUTES:
for child in self.childNodes:
child.handleAttributes()
buffer = ""
if self.nodeName in ['h1', 'h2', 'h3', 'h4']:
buffer += "\n"
elif self.nodeName in ['li']:
buffer += "\n "
# Process children FIRST, then do the attributes
childBuffer = ""
if self.childNodes or self.nodeName in ['blockquote']:
childBuffer += ">"
for child in self.childNodes:
childBuffer += child.toxml()
if self.nodeName == 'p':
childBuffer += "\n"
elif self.nodeName == 'li':
childBuffer += "\n "
childBuffer += "</%s>" % self.nodeName
else:
childBuffer += "/>"
buffer += "<" + self.nodeName
if self.nodeName in ['p', 'li', 'ul', 'ol',
'h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
if not self.attribute_values.has_key("dir"):
if self.bidi:
bidi = self.bidi
else:
bidi = self.doc.bidi
if bidi=="rtl":
self.setAttribute("dir", "rtl")
for attr in self.attributes:
value = self.attribute_values[attr]
value = self.doc.normalizeEntities(value,
avoidDoubleNormalizing=True)
buffer += ' %s="%s"' % (attr, value)
# Now let's actually append the children
buffer += childBuffer
if self.nodeName in ['p', 'br ', 'li', 'ul', 'ol',
'h1', 'h2', 'h3', 'h4'] :
buffer += "\n"
return buffer
class TextNode:
type = "text"
attrRegExp = re.compile(r'\{@([^\}]*)=([^\}]*)}') # {@id=123}
def __init__ (self, text):
self.value = text
def attributeCallback(self, match):
self.parent.setAttribute(match.group(1), match.group(2))
def handleAttributes(self):
self.value = self.attrRegExp.sub(self.attributeCallback, self.value)
def toxml(self):
text = self.value
self.parent.setBidi(getBidiType(text))
if not text.startswith(HTML_PLACEHOLDER_PREFIX):
if self.parent.nodeName == "p":
text = text.replace("\n", "\n ")
elif (self.parent.nodeName == "li"
and self.parent.childNodes[0]==self):
text = "\n " + text.replace("\n", "\n ")
text = self.doc.normalizeEntities(text)
return text
class EntityReference:
type = "entity_ref"
def __init__(self, entity):
self.entity = entity
def handleAttributes(self):
pass
def toxml(self):
return "&" + self.entity + ";"
"""
======================================================================
========================== PRE-PROCESSORS ============================
======================================================================
Preprocessors munge source text before we start doing anything too
complicated.
There are two types of preprocessors: TextPreprocessor and Preprocessor.
"""
class TextPreprocessor:
'''
TextPreprocessors are run before the text is broken into lines.
Each TextPreprocessor implements a "run" method that takes a pointer to a
text string of the document, modifies it as necessary and returns
either the same pointer or a pointer to a new string.
TextPreprocessors must extend markdown.TextPreprocessor.
'''
def run(self, text):
pass
class Preprocessor:
'''
Preprocessors are run after the text is broken into lines.
Each preprocessor implements a "run" method that takes a pointer to a
list of lines of the document, modifies it as necessary and returns
either the same pointer or a pointer to a new list.
Preprocessors must extend markdown.Preprocessor.
'''
def run(self, lines):
pass
class HtmlBlockPreprocessor(TextPreprocessor):
"""Removes html blocks from the source text and stores it."""
def _get_left_tag(self, block):
return block[1:].replace(">", " ", 1).split()[0].lower()
def _get_right_tag(self, left_tag, block):
return block.rstrip()[-len(left_tag)-2:-1].lower()
def _equal_tags(self, left_tag, right_tag):
if left_tag == 'div' or left_tag[0] in ['?', '@', '%']: # handle PHP, etc.
return True
if ("/" + left_tag) == right_tag:
return True
if (right_tag == "--" and left_tag == "--"):
return True
elif left_tag == right_tag[1:] \
and right_tag[0] != "<":
return True
else:
return False
def _is_oneliner(self, tag):
return (tag in ['hr', 'hr/'])
def run(self, text):
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
for block in text:
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag = self._get_left_tag(block)
right_tag = self._get_right_tag(left_tag, block)
if not (isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag = self._get_right_tag(left_tag, block)
# keep checking conditions below and maybe just append
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
new_blocks.append(
self.stash.store(block.strip()))
continue
else: #if not block[1] == "!":
# if is block level tag and is not complete
items.append(block.strip())
in_tag = True
continue
new_blocks.append(block)
else:
items.append(block.strip())
right_tag = self._get_right_tag(left_tag, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
new_blocks.append(
self.stash.store('\n\n'.join(items)))
items = []
if items:
new_blocks.append(self.stash.store('\n\n'.join(items)))
new_blocks.append('\n')
return "\n\n".join(new_blocks)
HTML_BLOCK_PREPROCESSOR = HtmlBlockPreprocessor()
class HeaderPreprocessor(Preprocessor):
"""
Replaces underlined headers with hashed headers to avoid
the nead for lookahead later.
"""
def run (self, lines):
i = -1
while i+1 < len(lines):
i = i+1
if not lines[i].strip():
continue
if lines[i].startswith("#"):
lines.insert(i+1, "\n")
if (i+1 <= len(lines)
and lines[i+1]
and lines[i+1][0] in ['-', '=']):
underline = lines[i+1].strip()
if underline == "="*len(underline):
lines[i] = "# " + lines[i].strip()
lines[i+1] = ""
elif underline == "-"*len(underline):
lines[i] = "## " + lines[i].strip()
lines[i+1] = ""
return lines
HEADER_PREPROCESSOR = HeaderPreprocessor()
class LinePreprocessor(Preprocessor):
"""Deals with HR lines (needs to be done before processing lists)"""
blockquote_re = re.compile(r'^(> )+')
def run (self, lines):
for i in range(len(lines)):
prefix = ''
m = self.blockquote_re.search(lines[i])
if m : prefix = m.group(0)
if self._isLine(lines[i][len(prefix):]):
lines[i] = prefix + self.stash.store("<hr />", safe=True)
return lines
def _isLine(self, block):
"""Determines if a block should be replaced with an <HR>"""
if block.startswith(" "): return 0 # a code block
text = "".join([x for x in block if not x.isspace()])
if len(text) <= 2:
return 0
for pattern in ['isline1', 'isline2', 'isline3']:
m = RE.regExp[pattern].match(text)
if (m and m.group(1)):
return 1
else:
return 0
LINE_PREPROCESSOR = LinePreprocessor()
class ReferencePreprocessor(Preprocessor):
'''
Removes reference definitions from the text and stores them for later use.
'''
def run (self, lines):
new_text = [];
for line in lines:
m = RE.regExp['reference-def'].match(line)
if m:
id = m.group(2).strip().lower()
t = m.group(4).strip() # potential title
if not t:
self.references[id] = (m.group(3), t)
elif (len(t) >= 2
and (t[0] == t[-1] == "\""
or t[0] == t[-1] == "\'"
or (t[0] == "(" and t[-1] == ")") ) ):
self.references[id] = (m.group(3), t[1:-1])
else:
new_text.append(line)
else:
new_text.append(line)
return new_text #+ "\n"
REFERENCE_PREPROCESSOR = ReferencePreprocessor()
"""
======================================================================
========================== INLINE PATTERNS ===========================
======================================================================
Inline patterns such as *emphasis* are handled by means of auxiliary
objects, one per pattern. Pattern objects must be instances of classes
that extend markdown.Pattern. Each pattern object uses a single regular
expression and needs support the following methods:
pattern.getCompiledRegExp() - returns a regular expression
pattern.handleMatch(m, doc) - takes a match object and returns
a NanoDom node (as a part of the provided
doc) or None
All of python markdown's built-in patterns subclass from Patter,
but you can add additional patterns that don't.
Also note that all the regular expressions used by inline must
capture the whole block. For this reason, they all start with
'^(.*)' and end with '(.*)!'. In case with built-in expression
Pattern takes care of adding the "^(.*)" and "(.*)!".
Finally, the order in which regular expressions are applied is very
important - e.g. if we first replace http://.../ links with <a> tags
and _then_ try to replace inline html, we would end up with a mess.
So, we apply the expressions in the following order:
* escape and backticks have to go before everything else, so
that we can preempt any markdown patterns by escaping them.
* then we handle auto-links (must be done before inline html)
* then we handle inline HTML. At this point we will simply
replace all inline HTML strings with a placeholder and add
the actual HTML to a hash.
* then inline images (must be done before links)
* then bracketed links, first regular then reference-style
* finally we apply strong and emphasis
"""
NOBRACKET = r'[^\]\[]*'
BRK = ( r'\[('
+ (NOBRACKET + r'(\[')*6
+ (NOBRACKET+ r'\])*')*6
+ NOBRACKET + r')\]' )
NOIMG = r'(?<!\!)'
BACKTICK_RE = r'\`([^\`]*)\`' # `e= m*c^2`
DOUBLE_BACKTICK_RE = r'\`\`(.*)\`\`' # ``e=f("`")``
ESCAPE_RE = r'\\(.)' # \<
EMPHASIS_RE = r'\*([^\*]*)\*' # *emphasis*
STRONG_RE = r'\*\*(.*)\*\*' # **strong**
STRONG_EM_RE = r'\*\*\*([^_]*)\*\*\*' # ***strong***
if SMART_EMPHASIS:
EMPHASIS_2_RE = r'(?<!\S)_(\S[^_]*)_' # _emphasis_
else:
EMPHASIS_2_RE = r'_([^_]*)_' # _emphasis_
STRONG_2_RE = r'__([^_]*)__' # __strong__
STRONG_EM_2_RE = r'___([^_]*)___' # ___strong___
LINK_RE = NOIMG + BRK + r'\s*\(([^\)]*)\)' # [text](url)
LINK_ANGLED_RE = NOIMG + BRK + r'\s*\(<([^\)]*)>\)' # [text](<url>)
IMAGE_LINK_RE = r'\!' + BRK + r'\s*\(([^\)]*)\)' # ![alttxt](http://x.com/)
REFERENCE_RE = NOIMG + BRK+ r'\s*\[([^\]]*)\]' # [Google][3]
IMAGE_REFERENCE_RE = r'\!' + BRK + '\s*\[([^\]]*)\]' # ![alt text][2]
NOT_STRONG_RE = r'( \* )' # stand-alone * or _
AUTOLINK_RE = r'<(http://[^>]*)>' # <http://www.123.com>
AUTOMAIL_RE = r'<([^> \!]*@[^> ]*)>' # <me@example.com>
#HTML_RE = r'(\<[^\>]*\>)' # <...>
HTML_RE = r'(\<[a-zA-Z/][^\>]*\>)' # <...>
ENTITY_RE = r'(&[\#a-zA-Z0-9]*;)' # &
LINE_BREAK_RE = r' \n' # two spaces at end of line
LINE_BREAK_2_RE = r' $' # two spaces at end of text
class Pattern:
def __init__ (self, pattern):
self.pattern = pattern
self.compiled_re = re.compile("^(.*)%s(.*)$" % pattern, re.DOTALL)
def getCompiledRegExp (self):
return self.compiled_re
BasePattern = Pattern # for backward compatibility
class SimpleTextPattern (Pattern):
def handleMatch(self, m, doc):
return doc.createTextNode(m.group(2))
class SimpleTagPattern (Pattern):
def __init__ (self, pattern, tag):
Pattern.__init__(self, pattern)
self.tag = tag
def handleMatch(self, m, doc):
el = doc.createElement(self.tag)
el.appendChild(doc.createTextNode(m.group(2)))
return el
class SubstituteTagPattern (SimpleTagPattern):
def handleMatch (self, m, doc):
return doc.createElement(self.tag)
class BacktickPattern (Pattern):
def __init__ (self, pattern):
Pattern.__init__(self, pattern)
self.tag = "code"
def handleMatch(self, m, doc):
el = doc.createElement(self.tag)
text = m.group(2).strip()
#text = text.replace("&", "&")
el.appendChild(doc.createTextNode(text))
return el
class DoubleTagPattern (SimpleTagPattern):
def handleMatch(self, m, doc):
tag1, tag2 = self.tag.split(",")
el1 = doc.createElement(tag1)
el2 = doc.createElement(tag2)
el1.appendChild(el2)
el2.appendChild(doc.createTextNode(m.group(2)))
return el1
class HtmlPattern (Pattern):
def handleMatch (self, m, doc):
rawhtml = m.group(2)
inline = True
place_holder = self.stash.store(rawhtml)
return doc.createTextNode(place_holder)
class LinkPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
el.appendChild(doc.createTextNode(m.group(2)))
parts = m.group(9).split('"')
# We should now have [], [href], or [href, title]
if parts:
el.setAttribute('href', parts[0].strip())
else:
el.setAttribute('href', "")
if len(parts) > 1:
# we also got a title
title = '"' + '"'.join(parts[1:]).strip()
title = dequote(title) #.replace('"', """)
el.setAttribute('title', title)
return el
class ImagePattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('img')
src_parts = m.group(9).split()
if src_parts:
el.setAttribute('src', src_parts[0])
else:
el.setAttribute('src', "")
if len(src_parts) > 1:
el.setAttribute('title', dequote(" ".join(src_parts[1:])))
if ENABLE_ATTRIBUTES:
text = doc.createTextNode(m.group(2))
el.appendChild(text)
text.handleAttributes()
truealt = text.value
el.childNodes.remove(text)
else:
truealt = m.group(2)
el.setAttribute('alt', truealt)
return el
class ReferencePattern (Pattern):
def handleMatch(self, m, doc):
if m.group(9):
id = m.group(9).lower()
else:
# if we got something like "[Google][]"
# we'll use "google" as the id
id = m.group(2).lower()
if not self.references.has_key(id): # ignore undefined refs
return None
href, title = self.references[id]
text = m.group(2)
return self.makeTag(href, title, text, doc)
def makeTag(self, href, title, text, doc):
el = doc.createElement('a')
el.setAttribute('href', href)
if title:
el.setAttribute('title', title)
el.appendChild(doc.createTextNode(text))
return el
class ImageReferencePattern (ReferencePattern):
def makeTag(self, href, title, text, doc):
el = doc.createElement('img')
el.setAttribute('src', href)
if title:
el.setAttribute('title', title)
el.setAttribute('alt', text)
return el
class AutolinkPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
el.setAttribute('href', m.group(2))
el.appendChild(doc.createTextNode(m.group(2)))
return el
class AutomailPattern (Pattern):
def handleMatch(self, m, doc):
el = doc.createElement('a')
email = m.group(2)
if email.startswith("mailto:"):
email = email[len("mailto:"):]
for letter in email:
entity = doc.createEntityReference("#%d" % ord(letter))
el.appendChild(entity)
mailto = "mailto:" + email
mailto = "".join(['&#%d;' % ord(letter) for letter in mailto])
el.setAttribute('href', mailto)
return el
ESCAPE_PATTERN = SimpleTextPattern(ESCAPE_RE)
NOT_STRONG_PATTERN = SimpleTextPattern(NOT_STRONG_RE)
BACKTICK_PATTERN = BacktickPattern(BACKTICK_RE)
DOUBLE_BACKTICK_PATTERN = BacktickPattern(DOUBLE_BACKTICK_RE)
STRONG_PATTERN = SimpleTagPattern(STRONG_RE, 'strong')
STRONG_PATTERN_2 = SimpleTagPattern(STRONG_2_RE, 'strong')
EMPHASIS_PATTERN = SimpleTagPattern(EMPHASIS_RE, 'em')
EMPHASIS_PATTERN_2 = SimpleTagPattern(EMPHASIS_2_RE, 'em')
STRONG_EM_PATTERN = DoubleTagPattern(STRONG_EM_RE, 'strong,em')
STRONG_EM_PATTERN_2 = DoubleTagPattern(STRONG_EM_2_RE, 'strong,em')
LINE_BREAK_PATTERN = SubstituteTagPattern(LINE_BREAK_RE, 'br ')
LINE_BREAK_PATTERN_2 = SubstituteTagPattern(LINE_BREAK_2_RE, 'br ')
LINK_PATTERN = LinkPattern(LINK_RE)
LINK_ANGLED_PATTERN = LinkPattern(LINK_ANGLED_RE)
IMAGE_LINK_PATTERN = ImagePattern(IMAGE_LINK_RE)
IMAGE_REFERENCE_PATTERN = ImageReferencePattern(IMAGE_REFERENCE_RE)
REFERENCE_PATTERN = ReferencePattern(REFERENCE_RE)
HTML_PATTERN = HtmlPattern(HTML_RE)
ENTITY_PATTERN = HtmlPattern(ENTITY_RE)
AUTOLINK_PATTERN = AutolinkPattern(AUTOLINK_RE)
AUTOMAIL_PATTERN = AutomailPattern(AUTOMAIL_RE)
"""
======================================================================
========================== POST-PROCESSORS ===========================
======================================================================
Markdown also allows post-processors, which are similar to
preprocessors in that they need to implement a "run" method. However,
they are run after core processing.
There are two types of post-processors: Postprocessor and TextPostprocessor
"""
class Postprocessor:
'''
Postprocessors are run before the dom it converted back into text.
Each Postprocessor implements a "run" method that takes a pointer to a
NanoDom document, modifies it as necessary and returns a NanoDom
document.
Postprocessors must extend markdown.Postprocessor.
There are currently no standard post-processors, but the footnote
extension uses one.
'''
def run(self, dom):
pass
class TextPostprocessor:
'''
TextPostprocessors are run after the dom it converted back into text.
Each TextPostprocessor implements a "run" method that takes a pointer to a
text string, modifies it as necessary and returns a text string.
TextPostprocessors must extend markdown.TextPostprocessor.
'''
def run(self, text):
pass
class RawHtmlTextPostprocessor(TextPostprocessor):
def __init__(self):
pass
def run(self, text):
for i in range(self.stash.html_counter):
html, safe = self.stash.rawHtmlBlocks[i]
if self.safeMode and not safe:
if str(self.safeMode).lower() == 'escape':
html = self.escape(html)
elif str(self.safeMode).lower() == 'remove':
html = ''
else:
html = HTML_REMOVED_TEXT
text = text.replace("<p>%s\n</p>" % (HTML_PLACEHOLDER % i),
html + "\n")
text = text.replace(HTML_PLACEHOLDER % i, html)
return text
def escape(self, html):
''' Basic html escaping '''
html = html.replace('&', '&')
html = html.replace('<', '<')
html = html.replace('>', '>')
return html.replace('"', '"')
RAWHTMLTEXTPOSTPROCESSOR = RawHtmlTextPostprocessor()
"""
======================================================================
========================== MISC AUXILIARY CLASSES ====================
======================================================================
"""
class HtmlStash:
"""This class is used for stashing HTML objects that we extract
in the beginning and replace with place-holders."""
def __init__ (self):
self.html_counter = 0 # for counting inline html segments