forked from mattharrison/rst2epub2
/
rst2epub.py
842 lines (733 loc) · 28.4 KB
/
rst2epub.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
#!/usr/bin/env python
"""
Copyright (c) 2011, matthewharrison@gmail.com
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the
distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
TODO:
* re-number footnotes with each chapter
* Dropcap cmd line option
* smartypants option
* Populate metadata from rst
* Cover generation
* see http://blog.threepress.org/2009/11/20/best-practices-in-epub-cover-images/
* Should probably convert pngs to jpegs
* Check xhtml validation
"""
from contextlib import contextmanager
import os
import sys
import tempfile
from genshi.util import striptags
import docutils
from docutils.core import Publisher, default_description, \
default_usage
from docutils import io, nodes
from docutils.parsers.rst import Directive, directives
from docutils.readers import standalone
from docutils.writers import html4css1
try:
import smartypants
except:
smartypants = None
from epublib import epub
@contextmanager
def cwd_cm():
cur_dir = os.getcwd()
found = False
for arg in sys.argv:
if arg.endswith(".rst"):
found = arg
break
if found:
directory = os.path.dirname(arg)
if directory:
os.chdir(directory)
yield
os.chdir(cur_dir)
def cwd_decorator(func):
"""
decorator to change cwd to directory containing rst for this function
"""
def wrapper(*args, **kw):
cur_dir = os.getcwd()
found = False
for arg in sys.argv:
if arg.endswith(".rst"):
found = arg
break
if found:
directory = os.path.dirname(arg)
if directory:
os.chdir(directory)
data = func(*args, **kw)
os.chdir(cur_dir)
return data
return wrapper
class EpubWriter(html4css1.Writer):
def __init__(self):
html4css1.Writer.__init__(self)
self.translator_class = HTMLTranslator
def translate(self):
self.visitor = visitor = self.translator_class(self.document)
self.document.walkabout(visitor)
for attr in self.visitor_attributes:
setattr(self, attr, getattr(visitor, attr))
self.output = self.visitor.get_output()
class HTMLTranslator(html4css1.HTMLTranslator):
def __init__(self, document):
html4css1.HTMLTranslator.__init__(self, document)
self.book = epub.EpubBook()
self.sections = []
self.body_len_before_node = {}
self.section_title = ''
self.authors = []
self.footnotes = [] # keep track of footnotes per chapter
self.cover_image = None
self._ignore_image = False
self.images = {} # absolute path to book path
self.first_page = True
self.field_name = None
self.fields = {}
self.in_node = {}
self.is_title_page = False
self.first_paragraph = True
self.css = ['main.css']
self.js = []
self.font = [] # user embedded font paths
self.toc_parents = []
self.toc_page = False
self.toc_entry = True # page that has entry in TOC and NCX
self.parent_level = 0
self.guide_type=None
self.first_admonition_para = False
def dispatch_visit(self, node):
# mark body length before visiting node
self.body_len_before_node[node.__class__.__name__] = len(self.body)
# keep track of parents
count = self.in_node.setdefault(node.tagname, 0)
self.in_node[node.tagname] += 1
html4css1.HTMLTranslator.dispatch_visit(self, node)
def dispatch_departure(self, node):
try:
self.in_node[node.tagname] -= 1
except KeyError as e:
print node.tagname
html4css1.HTMLTranslator.dispatch_departure(self, node)
def at(self, nodename):
"""
shortcut for at/under this node
"""
return self.in_node.get(nodename, False)
def _dumb(self, node):
pass
visit_comment = _dumb
depart_comment = _dumb
def visit_envvar(self, node):
# !!! hook up to index when motivated
self.visit_literal(node)
def depart_envvar(self, node):
self.depart_literal(node)
def visit_literal(self, node):
if self.at('index'):
return
else:
html4css1.HTMLTranslator.visit_literal(self, node)
def depart_literal(self, node):
if self.at('index'):
return
else:
html4css1.HTMLTranslator.depart_literal(self, node)
def visit_admonition(self, node):
self.first_admonition_para = True
html4css1.HTMLTranslator.visit_admonition(self, node)
def depart_admonition(self, node):
self.first_admonition_para = False
html4css1.HTMLTranslator.depart_admonition(self, node)
def visit_paragraph(self, node):
if self.at('index'):
return
# All text need p's (else breaks epubcheck)
if self.first_paragraph and not self.at('admonition'):
if self.section_level == 1:
self.body.append(self.starttag(node, 'p', '', **{'class':'first-para-chapter'}))
else:
self.body.append(self.starttag(node, 'p', '', **{'class':'first-para'}))
self.context.append('</p>\n')
elif self.at('admonition'):
if self.first_admonition_para:
self.body.append(self.starttag(node, 'p', '', **{'class':'note-p-first'}))
self.first_admonition_para = False
else:
self.body.append(self.starttag(node, 'p', '', **{'class':'note-p'}))
self.context.append('</p>\n')
elif self.at('block_quote'):
self.body.append(self.starttag(node, 'p', '', **{}))
self.context.append('</p>\n')
else:
html4css1.HTMLTranslator.visit_paragraph(self, node)
self.first_paragraph = False
def depart_paragraph(self, node):
if self.at('index'):
return
else:
html4css1.HTMLTranslator.depart_paragraph(self, node)
def append_class_on_child(self, node, class_, index=0):
children = [n for n in node if not isinstance(n, nodes.Invisible)]
try:
child = children[index]
except IndexError:
return
# should only be one class
if child['classes']:
child['classes'] = child['classes'][0] + class_
def set_first_last(self, node):
# mobi doesn't like multiple classes per tag
self.append_class_on_child(node, '-first', 0)
def visit_literal_block(self, node):
# mobi needs an extra div here, otherwise headings following <pre> are indented poorly
if self.at('admonition'):
self.body.append(self.starttag(node, 'div', CLASS='div-literal-block-admonition'))
self.body.append(self.starttag(node, 'pre', CLASS='literal-block-admonition'))
else:
self.body.append(self.starttag(node, 'div'))
self.body.append(self.starttag(node, 'pre', CLASS='literal-block'))
def depart_literal_block(self, node):
html4css1.HTMLTranslator.depart_literal_block(self, node)
self.body.append('</div>\n')
def visit_footnote_reference(self, node):
"""
This is the superscript in the text that links to the footnote
<footnote_reference auto="1" ids="id2" refid="id3">1</footnote_reference>"""
refid = node.attributes['refid']
ids = node.attributes['ids'][0]
self.body.append('<sup><a href="#{}" id="{}">'.format(refid, ids))
def depart_footnote_reference(self, node):
self.body.append('</a></sup>')
def visit_footnote(self, node):
"""
AmazonKindlePublishingGuidelines.pdf state that footnotes should look like this
This sample text has a footnote.<sup><a href="footnotes.html#fn1"
id="r1">[1]</a></sup>
<p id="fn1"><a href="chapter01.html#r1">1.</a> This is the footnote text.
A footnote has this structure:
<footnote auto="1" backrefs="id2" ids="id3" names="1"><label>1</label><paragraph>pandas (<reference refuri="http://pandas.pydata.org">http://pandas.pydata.org</reference>) refers to itself in lower-case, so this
book will follow suit.</paragraph></footnote>
"""
# note that footnotes can't have newlines in them!
print node.attributes
self.backref = node.attributes['backrefs'][0]
self.ids = node.attributes['ids'][0]
self.start_footnote_idx = len(self.body)
self.body.append('<p id="{}">'.format(self.ids))
def depart_footnote(self, node):
self.body.append('</p>\n')
footnote = self.body[self.start_footnote_idx:]
self.body = self.body[:self.start_footnote_idx]
self.footnotes.extend(footnote)
def visit_label(self, node):
if self.at('footnote'):
self.body.append('<a href="#{}">'.format(
self.backref))
else:
html4css1.HTMLTranslator.visit_label(self, node)
def depart_label(self, node):
if self.at('footnote'):
self.body.append('</a> - ')
else:
html4css1.HTMLTranslator.depart_label(self, node)
def visit_meta(self, node):
# support gutenberg extensions
# http://www.gutenberg.org/wiki/Gutenberg:The_PG_boilerplate_for_RST
name = node.get('name', '')
if name.startswith('DC'):
self.fields[name[3:]] = node.get('content')
elif name.startswith('coverpage'):
with cwd_cm():
cover_page = node.get('content')
self.cover_image = os.path.abspath(cover_page)
@cwd_decorator
def visit_Text(self, node):
if "Copyright" in str(node):
pass
txt = node.astext()
if self.at('index'):
print "INDEX NODE", node.parent
# no support in epub :(
return
if self.at('field_name'):
self.field_name = node.astext()
elif self.at('field_body'):
pass
elif self.at('generated'):# and 'sectnum' in node.get('classes'):
# avoid <generated classes="sectnum">5.1</generated>
pass
elif self.at('comment'):
if txt == 'titlepage':
self.is_title_page = True
elif txt.startswith('newpage:'):
# don't create table of contents entry
self.create_chapter()
self.toc_entry = False
self.section_level = 1
elif txt.startswith('newchapter:'):
# don't create table of contents entry
self.create_chapter()
self.section_level = 1
elif txt.startswith('guide:'):
self.guide_type=txt.split(':')[-1]
elif txt.startswith('css:'):
paths = txt.split(':')[-1].split(',')
self.css = self.css + [os.path.abspath(path) for path in paths if path]
elif txt.startswith('js:'):
paths = txt.split(':')[-1].split(',')
self.js = self.js + [os.path.abspath(path) for path in paths if path]
elif txt.startswith('font:'):
paths = txt.split(':')[-1].split(',')
self.font = self.font + [os.path.abspath(path) for path in paths if path]
elif txt == 'nocss':
self.css = None
elif txt.startswith('addimg:'):
uri = txt.split(':')[-1]
self.images[os.path.abspath(uri)] = uri
elif txt.startswith('toc:show'):
# old school hack now overriding .. contents::
# see visit_epubcontent
if self.body:
self.create_chapter()
self.book.add_toc_page(order=self.book.next_order())
elif txt.startswith('toc:parent1'):
self.is_parent = True
self.parent_level = 1
self.toc_parents = []
elif txt.startswith('toc:parent2'):
self.is_parent = True
self.parent_level = 2
elif txt.startswith('toc:clear'):
self.is_parent = False
self.toc_parents = []
else:
html4css1.HTMLTranslator.visit_Text(self, node)
def visit_epubcontent(self, node):
if self.body:
# create an existing chapter
self.create_chapter()
self.toc_page = True
def depart_epubcontent(self, node):
self.section_level = 0
@cwd_decorator
def visit_image(self, node):
self._ignore_image = False
if 'cover' in node.get('classes'):
source = node.get('uri')
self.cover_image = os.path.abspath(source)
self._ignore_image = True
else:
source = node.get('uri')
self.images[os.path.abspath(source)] = source
if not self._ignore_image:
# appease epubcheck
self.body.append('<div>\n')
html4css1.HTMLTranslator.visit_image(self, node)
def depart_image(self, node):
if not self._ignore_image:
# appease epubcheck
self.body.append('</div>\n')
html4css1.HTMLTranslator.depart_image(self, node)
def visit_field_list(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.visit_field_list(self, node)
def depart_field_list(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.depart_field_list(self, node)
def visit_field(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.visit_field(self, node)
def depart_field(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.depart_field(self, node)
def visit_field_body(self, node):
if self.first_page:
#pass
# need to deal with para's that have multiple text children
# such as foo... |copy| foo :(
self.fields[self.field_name] = node.astext()
else:
return html4css1.HTMLTranslator.visit_field_body(self, node)
def depart_field_body(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.depart_field_body(self, node)
def visit_field_name(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.visit_field_name(self, node)
def depart_field_name(self, node):
if self.first_page:
pass
else:
return html4css1.HTMLTranslator.depart_field_name(self, node)
def visit_title(self, node):
html4css1.HTMLTranslator.visit_title(self, node)
def depart_title(self, node):
if self.section_level == 1:
if self.section_title == '':
start = self.body_len_before_node[node.__class__.__name__]
self.section_title = ''.join(self.body[start + 1:])
html4css1.HTMLTranslator.depart_title(self, node)
def depart_author(self, node):
start = self.body_len_before_node[node.__class__.__name__]
self.authors.append(node.children[0])
def visit_transition2(self, node):
# hack to have titleless chapter
self.reset_chapter()
def visit_section(self, node):
# too many divs is bad for mobi...
#print "\tSECTION", section_level, node
if self.section_level == 0:
if self.body:
self.create_chapter()
else:
self.reset_chapter()
self.section_level += 1
self.first_paragraph = True
def depart_section(self, node):
self.first_page = False
if self.section_level >= 1:
self.section_level -= 1
if self.section_level == 0:
self.create_chapter()
def visit_generated(self, node):
pass
#depart_generated = depart_section
def visit_index(self, node):
pass
def depart_index(self, node):
pass
def create_chapter(self):
self.sections.append(self.body)
self.body = []
body = ''.join(self.sections[-1])
if self.footnotes:
# add footnotes to end of chapter
body += '<br/>'
body += ''.join(self.footnotes)
self.footnotes = []
if smartypants:
#body = smartypants.smartyPants(body)
# pass need to ignore pre contents...
pass
css = ''
if self.css:
css = ''.join(['<link rel="stylesheet" href="{0}" type="text/css" media="all" />'.format(os.path.basename(item)) for item in self.css])
for item in self.css:
if os.path.exists(item):
self.book.add_css(item, os.path.basename(item))
else:
self.book.add_css(os.path.join(os.path.dirname(epub.__file__),
'templates',
'main.css'),'main.css')
if self.font:
for item in self.font:
if os.path.exists(item):
self.book.add_font(item, os.path.basename(item))
else:
raise KeyError(item)
js = ''
if self.js:
js = ''.join(['<script src="{0}" type="text/javascript"></script>'.format(os.path.basename(item)) for item in self.js])
for item in self.js:
if os.path.exists(item):
self.book.add_js(item, os.path.basename(item))
else:
raise KeyError(item)
title = ''
if 'title' in self.fields and self.is_title_page:
title = self.fields['title']
elif self.section_title:
title=striptags(self.section_title)
header = css+js
html = XHTML_WRAPPER.format(body=body,
title=title,
header=header)
if self.is_title_page:
self.book.add_title_page(html)
# clear out toc_map_node
self.book.last_node_at_depth = {0:self.book.toc_map_root}
self.is_title_page = False
elif self.toc_page:
self.book.add_toc_page(order=self.book.next_order())
self.toc_page = False
else:
dst = '{0}.html'.format(len(self.sections))
item = self.book.add_html('', dst, html)
if self.guide_type:
self.book.add_guide_item(dst, self.section_title, self.guide_type)
self.book.add_spine_item(item)
parent = self.toc_parents[-1] if self.toc_parents else None
if self.toc_entry:
node = self.book.add_toc_map_node(item.dest_path, striptags(self.section_title), parent=parent) #''.join(self.html_subtitle))
if self.parent_level == 1:
self.toc_parents = [node]
elif self.parent_level == 2:
self.toc_parents = self.toc_parents[:1] + [node]
self.reset_chapter()
def reset_chapter(self):
self.section_title = ''
self.first_paragraph = True
self.css = ['main.css']
self.font = []
self.js = []
self.parent_level = 0
self.section_level = 0
self.guide_type = None
self.toc_entry = True # page that has entry in TOC and NCX
def visit_tgroup(self, node):
# don't want colgroup
node.stubs = []
pass
def visit_tbody(self, node):
# don't want tbody
pass
def depart_tbody(self, node):
pass
visit_thead=visit_tbody
depart_thead=depart_tbody
def get_output(self):
root_dir = os.path.join(tempfile.gettempdir(), 'epub')
for k,v in self.fields.items():
if k == 'creator':
self.book.add_creator(v)
elif k.lower() == 'title':
self.book.set_title(v)
else:
self.book.add_meta(k, v)
self.book.add_creator(', '.join(self.authors))
if self.cover_image:
self.book.add_cover(self.cover_image, title=''.join(self.title))
for i, img_paths in enumerate(self.images.items()):
abs_path, dst_path = img_paths
self.book.add_image(abs_path, dst_path, id='image_{0}'.format(i))
self.book.create_book(root_dir)
self.book.create_archive(root_dir, root_dir + '.epub')
return open(root_dir + '.epub').read()
XHTML_WRAPPER = u'''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
<head>
<title>{title}</title>
<meta http-equiv="Content-type" content="application/xhtml+xml;charset=utf8" />
{header}
</head>
<body>
{body}
</body>
</html>'''
class EpubFileOutput(io.FileOutput):
"""
A version of docutils.io.FileOutput which writes to a binary file.
"""
def open(self):
try:
self.destination = open(self.destination_path, 'wb')
except IOError, error:
if not self.handle_io_errors:
raise
# raise
print >>sys.stderr, '%s: %s' % (error.__class__.__name__,
error)
print >>sys.stderr, ('Unable to open destination file for writing '
'(%r). Exiting.' % self.destination_path)
sys.exit(1)
self.opened = 1
class epubcontent(nodes.Element):
# change normal TOC to epubcontent
tagname = 'epubcontent'
class Index(Directive):
"""
Directive to add entries to the index.
"""
#has_content = False
has_content = True
required_arguments = 0
optional_arguments = 1
final_argument_whitespace = True
option_spec = {}
count = 0
def run(self):
text = ''.join(self.content)
# Create the admonition node, to be populated by `nested_parse`.
index_node = index(rawsource=text)
# Parse the directive contents.
self.state.nested_parse(self.content, self.content_offset,
index_node)
targetid = 'index-%s' % Index.count
Index.count += 1
target_node = nodes.target('', '', ids=[targetid])
index_node['entries'] = ne = []
index_node['inline'] = False
if self.arguments:
arguments = self.arguments[0].split('\n')
for entry in arguments:
ne.extend(process_index_entry(entry, targetid))
return [index_node, target_node]
indextypes = [
'single', 'pair', 'double', 'triple', 'see', 'seealso',
]
def process_index_entry(entry, targetid):
indexentries = []
entry = entry.strip()
oentry = entry
main = ''
if entry.startswith('!'):
main = 'main'
entry = entry[1:].lstrip()
for type in pairindextypes:
if entry.startswith(type+':'):
value = entry[len(type)+1:].strip()
value = pairindextypes[type] + '; ' + value
indexentries.append(('pair', value, targetid, main))
break
else:
for type in indextypes:
if entry.startswith(type+':'):
value = entry[len(type)+1:].strip()
if type == 'double':
type = 'pair'
indexentries.append((type, value, targetid, main))
break
# shorthand notation for single entries
else:
for value in oentry.split(','):
value = value.strip()
main = ''
if value.startswith('!'):
main = 'main'
value = value[1:].lstrip()
if not value:
continue
indexentries.append(('single', value, targetid, main))
return indexentries
pairindextypes = {
'module': ('module'),
'keyword': ('keyword'),
'operator': ('operator'),
'object': ('object'),
'exception': ('exception'),
'statement': ('statement'),
'builtin': ('built-in function'),
}
class index(nodes.Invisible, nodes.Inline, nodes.TextElement):
"""Node for index entries.
This node is created by the ``index`` directive and has one attribute,
``entries``. Its value is a list of 4-tuples of ``(entrytype, entryname,
target, ignored)``.
*entrytype* is one of "single", "pair", "double", "triple".
"""
class IndexOld(Directive):
"""
Directive to add entries to the index.
"""
has_content = False
required_arguments = 1
optional_arguments = 0
final_argument_whitespace = True
option_spec = {}
count = 0
def run(self):
return [] #None #ignore for now
# see sphinx.directives.other.Index for hints
arguments = self.arguments[0].split('\n')
targetid = 'index-%s' % Index.count
Index.count += 1
targetnode = nodes.target('', '', ids=[targetid])
self.state.document.note_explicit_target(targetnode)
indexnode = addnodes.index()
indexnode['entries'] = ne = []
indexnode['inline'] = False
for entry in arguments:
ne.extend(process_index_entry(entry, targetid))
return [indexnode, targetnode]
class Contents(Directive):
required_arguments = 0
optional_arguments = 1
final_argument_whitespace = True
option_spec = { 'class': directives.class_option,
'local': directives.flag,
'depth': directives.nonnegative_int,
'page-numbers': directives.flag }
def run(self):
return [epubcontent()]
class Parser(docutils.parsers.rst.Parser):
def __init__(self):
directives.register_directive('contents', Contents)
directives.register_directive('index', Index)
docutils.parsers.rst.Parser.__init__(self)
# fix envvar !!!
from docutils import nodes
class envvar(nodes.Inline, nodes.TextElement): pass
def ignore_role(role, rawtext, text, lineno, inliner,
options={}, content=[]):
return [envvar(rawtext, text)],[]
#class envvar(Inline, TextElement):
#class envvar(nodes.Inline, nodes.TextElement): pass
#envvar = nodes.literal
from docutils.parsers.rst import roles
roles.register_local_role('envvar', ignore_role)
#roles.register_local_role('envvar', envvar)
def main(args):
argv = None
reader = standalone.Reader()
reader_name = 'standalone'
writer = EpubWriter()
writer_name = 'epub2'
parser = Parser()
parser_name = 'restructuredtext'
settings = None
settings_spec = None
settings_overrides = None
config_section = None
enable_exit_status = 1
usage = default_usage
publisher = Publisher(reader, parser, writer, settings,
destination_class=EpubFileOutput)
publisher.set_components(reader_name, parser_name, writer_name)
description = ('Generates epub books from reStructuredText sources. ' + default_description)
output = publisher.publish(argv, usage, description,
settings_spec, settings_overrides,
config_section=config_section,
enable_exit_status=enable_exit_status)
if __name__ == '__main__':
if '--doctest' in sys.argv:
_test()
else:
sys.exit(main(sys.argv) or 0)