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
|
# -*- coding: utf-8 -*-
"""
sphinx.builders.epub
~~~~~~~~~~~~~~~~~~~~
Build epub files.
Originally derived from qthelp.py.
:copyright: Copyright 2007-2011 by the Sphinx team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import re
import sys
import time
import codecs
import zipfile
from os import path
try:
from PIL import Image
except ImportError:
try:
import Image
except ImportError:
Image = None
from docutils import nodes
from sphinx import addnodes
from sphinx.builders.html import StandaloneHTMLBuilder
from sphinx.util.osutil import ensuredir, EEXIST
from sphinx.util.smartypants import sphinx_smarty_pants as ssp
from sphinx.util.console import brown
# (Fragment) templates from which the metainfo files content.opf, toc.ncx,
# mimetype, and META-INF/container.xml are created.
# This template section also defines strings that are embedded in the html
# output but that may be customized by (re-)setting module attributes,
# e.g. from conf.py.
_mimetype_template = 'application/epub+zip' # no EOL!
_container_template = u'''\
<?xml version="1.0" encoding="UTF-8"?>
<container version="1.0"
xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles>
<rootfile full-path="content.opf"
media-type="application/oebps-package+xml"/>
</rootfiles>
</container>
'''
_toc_template = u'''\
<?xml version="1.0"?>
<ncx version="2005-1" xmlns="http://www.daisy.org/z3986/2005/ncx/">
<head>
<meta name="dtb:uid" content="%(uid)s"/>
<meta name="dtb:depth" content="%(level)d"/>
<meta name="dtb:totalPageCount" content="0"/>
<meta name="dtb:maxPageNumber" content="0"/>
</head>
<docTitle>
<text>%(title)s</text>
</docTitle>
<navMap>
%(navpoints)s
</navMap>
</ncx>
'''
_navpoint_template = u'''\
%(indent)s <navPoint id="%(navpoint)s" playOrder="%(playorder)d">
%(indent)s <navLabel>
%(indent)s <text>%(text)s</text>
%(indent)s </navLabel>
%(indent)s <content src="%(refuri)s" />
%(indent)s </navPoint>'''
_navpoint_indent = ' '
_navPoint_template = 'navPoint%d'
_content_template = u'''\
<?xml version="1.0" encoding="UTF-8"?>
<package xmlns="http://www.idpf.org/2007/opf" version="2.0"
unique-identifier="%(uid)s">
<metadata xmlns:opf="http://www.idpf.org/2007/opf"
xmlns:dc="http://purl.org/dc/elements/1.1/">
<dc:language>%(lang)s</dc:language>
<dc:title>%(title)s</dc:title>
<dc:creator opf:role="aut">%(author)s</dc:creator>
<dc:publisher>%(publisher)s</dc:publisher>
<dc:rights>%(copyright)s</dc:rights>
<dc:identifier id="%(uid)s" opf:scheme="%(scheme)s">%(id)s</dc:identifier>
<dc:date>%(date)s</dc:date>
</metadata>
<manifest>
<item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml" />
%(files)s
</manifest>
<spine toc="ncx">
%(spine)s
</spine>
<guide>
%(guide)s
</guide>
</package>
'''
_cover_template = u'''\
<meta name="cover" content="%(cover)s"/>
'''
_coverpage_name = u'epub-cover.html'
_file_template = u'''\
<item id="%(id)s"
href="%(href)s"
media-type="%(media_type)s" />'''
_spine_template = u'''\
<itemref idref="%(idref)s" />'''
_guide_template = u'''\
<reference type="%(type)s" title="%(title)s" href="%(uri)s" />'''
_toctree_template = u'toctree-l%d'
_link_target_template = u' [%(uri)s]'
_css_link_target_class = u'link-target'
# XXX These strings should be localized according to epub_language
_guide_titles = {
'toc': u'Table of Contents',
'cover': u'Cover Page'
}
_media_types = {
'.html': 'application/xhtml+xml',
'.css': 'text/css',
'.png': 'image/png',
'.gif': 'image/gif',
'.svg': 'image/svg+xml',
'.jpg': 'image/jpeg',
'.jpeg': 'image/jpeg',
'.otf': 'application/x-font-otf',
'.ttf': 'application/x-font-ttf',
}
# Regular expression to match colons only in local fragment identifiers.
# If the URI contains a colon before the #,
# it is an external link that should not change.
_refuri_re = re.compile("([^#:]*#)(.*)")
# The epub publisher
class EpubBuilder(StandaloneHTMLBuilder):
"""
Builder that outputs epub files.
It creates the metainfo files container.opf, toc.ncx, mimetype, and
META-INF/container.xml. Afterwards, all necessary files are zipped to an
epub file.
"""
name = 'epub'
# don't copy the reST source
copysource = False
supported_image_types = ['image/svg+xml', 'image/png', 'image/gif',
'image/jpeg']
# don't add links
add_permalinks = False
# don't add sidebar etc.
embedded = True
def init(self):
StandaloneHTMLBuilder.init(self)
# the output files for epub must be .html only
self.out_suffix = '.html'
self.playorder = 0
def get_theme_config(self):
return self.config.epub_theme, self.config.epub_theme_options
# generic support functions
def make_id(self, name):
"""Replace all characters not allowed for (X)HTML ids."""
return name.replace('/', '_').replace(' ', '')
def esc(self, name):
"""Replace all characters not allowed in text an attribute values."""
# Like cgi.escape, but also replace apostrophe
name = name.replace('&', '&')
name = name.replace('<', '<')
name = name.replace('>', '>')
name = name.replace('"', '"')
name = name.replace('\'', ''')
return name
def get_refnodes(self, doctree, result):
"""Collect section titles, their depth in the toc and the refuri."""
# XXX: is there a better way than checking the attribute
# toctree-l[1-8] on the parent node?
if isinstance(doctree, nodes.reference) and doctree.has_key('refuri'):
refuri = doctree['refuri']
if refuri.startswith('http://') or refuri.startswith('https://') \
or refuri.startswith('irc:') or refuri.startswith('mailto:'):
return result
classes = doctree.parent.attributes['classes']
for level in range(8, 0, -1): # or range(1, 8)?
if (_toctree_template % level) in classes:
result.append({
'level': level,
'refuri': self.esc(refuri),
'text': ssp(self.esc(doctree.astext()))
})
break
else:
for elem in doctree.children:
result = self.get_refnodes(elem, result)
return result
def get_toc(self):
"""Get the total table of contents, containing the master_doc
and pre and post files not managed by sphinx.
"""
doctree = self.env.get_and_resolve_doctree(self.config.master_doc,
self, prune_toctrees=False, includehidden=True)
self.refnodes = self.get_refnodes(doctree, [])
master_dir = os.path.dirname(self.config.master_doc)
if master_dir:
master_dir += '/' # XXX or os.sep?
for item in self.refnodes:
item['refuri'] = master_dir + item['refuri']
self.refnodes.insert(0, {
'level': 1,
'refuri': self.esc(self.config.master_doc + '.html'),
'text': ssp(self.esc(
self.env.titles[self.config.master_doc].astext()))
})
for file, text in reversed(self.config.epub_pre_files):
self.refnodes.insert(0, {
'level': 1,
'refuri': self.esc(file),
'text': ssp(self.esc(text))
})
for file, text in self.config.epub_post_files:
self.refnodes.append({
'level': 1,
'refuri': self.esc(file),
'text': ssp(self.esc(text))
})
def fix_fragment(self, prefix, fragment):
"""Return a href/id attribute with colons replaced by hyphens."""
return prefix + fragment.replace(':', '-')
def fix_ids(self, tree):
"""Replace colons with hyphens in href and id attributes.
Some readers crash because they interpret the part as a
transport protocol specification.
"""
for node in tree.traverse(nodes.reference):
if 'refuri' in node:
m = _refuri_re.match(node['refuri'])
if m:
node['refuri'] = self.fix_fragment(m.group(1), m.group(2))
if 'refid' in node:
node['refid'] = self.fix_fragment('', node['refid'])
for node in tree.traverse(addnodes.desc_signature):
ids = node.attributes['ids']
newids = []
for id in ids:
newids.append(self.fix_fragment('', id))
node.attributes['ids'] = newids
def add_visible_links(self, tree):
"""Append visible link targets after external links."""
for node in tree.traverse(nodes.reference):
uri = node.get('refuri', '')
if (uri.startswith('http:') or uri.startswith('https:') or
uri.startswith('ftp:')) and uri not in node.astext():
uri = _link_target_template % {'uri': uri}
if uri:
idx = node.parent.index(node) + 1
link = nodes.inline(uri, uri)
link['classes'].append(_css_link_target_class)
node.parent.insert(idx, link)
def write_doc(self, docname, doctree):
"""Write one document file.
This method is overwritten in order to fix fragment identifiers
and to add visible external links.
"""
self.fix_ids(doctree)
self.add_visible_links(doctree)
return StandaloneHTMLBuilder.write_doc(self, docname, doctree)
def fix_genindex(self, tree):
"""Fix href attributes for genindex pages."""
# XXX: modifies tree inline
# Logic modeled from themes/basic/genindex.html
for key, columns in tree:
for entryname, (links, subitems) in columns:
for (i, (ismain, link)) in enumerate(links):
m = _refuri_re.match(link)
if m:
links[i] = (ismain,
self.fix_fragment(m.group(1), m.group(2)))
for subentryname, subentrylinks in subitems:
for (i, (ismain, link)) in enumerate(subentrylinks):
m = _refuri_re.match(link)
if m:
subentrylinks[i] = (ismain,
self.fix_fragment(m.group(1), m.group(2)))
def copy_image_files_pil(self):
"""Copy images using the PIL.
The method tries to read and write the files with the PIL,
converting the format and resizing the image if necessary/possible.
"""
ensuredir(path.join(self.outdir, '_images'))
for src in self.status_iterator(self.images, 'copying images... ',
brown, len(self.images)):
dest = self.images[src]
try:
img = Image.open(path.join(self.srcdir, src))
except IOError:
self.warn('cannot read image file %r: copying it instead' %
(path.join(self.srcdir, src), ))
try:
copyfile(path.join(self.srcdir, src),
path.join(self.outdir, '_images', dest))
except Exception, err:
self.warn('cannot copy image file %r: %s' %
(path.join(self.srcdir, src), err))
continue
if self.config.epub_fix_images:
if img.mode in ('P',):
# See PIL documentation for Image.convert()
img = img.convert()
if self.config.epub_max_image_width > 0:
(width, height) = img.size
nw = self.config.epub_max_image_width
if width > nw:
nh = (height * nw) / width
img = img.resize((nw, nh), Image.BICUBIC)
try:
img.save(path.join(self.outdir, '_images', dest))
except IOError, err:
self.warn('cannot write image file %r: %s' %
(path.join(self.srcdir, src), err))
def copy_image_files(self):
"""Copy image files to destination directory.
This overwritten method can use the PIL to convert image files.
"""
if self.images:
if self.config.epub_fix_images or self.config.epub_max_image_width:
if not Image:
self.warn('PIL not found - copying image files')
super(EpubBuilder, self).copy_image_files()
else:
self.copy_image_files_pil()
else:
super(EpubBuilder, self).copy_image_files()
def handle_page(self, pagename, addctx, templatename='page.html',
outfilename=None, event_arg=None):
"""Create a rendered page.
This method is overwritten for genindex pages in order to fix href link
attributes.
"""
if pagename.startswith('genindex'):
self.fix_genindex(addctx['genindexentries'])
StandaloneHTMLBuilder.handle_page(self, pagename, addctx, templatename,
outfilename, event_arg)
# Finish by building the epub file
def handle_finish(self):
"""Create the metainfo files and finally the epub."""
self.get_toc()
self.build_mimetype(self.outdir, 'mimetype')
self.build_container(self.outdir, 'META-INF/container.xml')
self.build_content(self.outdir, 'content.opf')
self.build_toc(self.outdir, 'toc.ncx')
self.build_epub(self.outdir, self.config.epub_basename + '.epub')
def build_mimetype(self, outdir, outname):
"""Write the metainfo file mimetype."""
self.info('writing %s file...' % outname)
f = codecs.open(path.join(outdir, outname), 'w', 'utf-8')
try:
f.write(_mimetype_template)
finally:
f.close()
def build_container(self, outdir, outname):
"""Write the metainfo file META-INF/cointainer.xml."""
self.info('writing %s file...' % outname)
fn = path.join(outdir, outname)
try:
os.mkdir(path.dirname(fn))
except OSError, err:
if err.errno != EEXIST:
raise
f = codecs.open(path.join(outdir, outname), 'w', 'utf-8')
try:
f.write(_container_template)
finally:
f.close()
def content_metadata(self, files, spine, guide):
"""Create a dictionary with all metadata for the content.opf
file properly escaped.
"""
metadata = {}
metadata['title'] = self.esc(self.config.epub_title)
metadata['author'] = self.esc(self.config.epub_author)
metadata['uid'] = self.esc(self.config.epub_uid)
metadata['lang'] = self.esc(self.config.epub_language)
metadata['publisher'] = self.esc(self.config.epub_publisher)
metadata['copyright'] = self.esc(self.config.epub_copyright)
metadata['scheme'] = self.esc(self.config.epub_scheme)
metadata['id'] = self.esc(self.config.epub_identifier)
metadata['date'] = self.esc(time.strftime('%Y-%m-%d'))
metadata['files'] = files
metadata['spine'] = spine
metadata['guide'] = guide
return metadata
def build_content(self, outdir, outname):
"""Write the metainfo file content.opf It contains bibliographic data,
a file list and the spine (the reading order).
"""
self.info('writing %s file...' % outname)
# files
if not outdir.endswith(os.sep):
outdir += os.sep
olen = len(outdir)
projectfiles = []
self.files = []
self.ignored_files = ['.buildinfo',
'mimetype', 'content.opf', 'toc.ncx', 'META-INF/container.xml',
self.config.epub_basename + '.epub'] + \
self.config.epub_exclude_files
for root, dirs, files in os.walk(outdir):
for fn in files:
filename = path.join(root, fn)[olen:]
if filename in self.ignored_files:
continue
ext = path.splitext(filename)[-1]
if ext not in _media_types:
self.warn('unknown mimetype for %s, ignoring' % filename)
continue
projectfiles.append(_file_template % {
'href': self.esc(filename),
'id': self.esc(self.make_id(filename)),
'media_type': self.esc(_media_types[ext])
})
self.files.append(filename)
# spine
spine = []
for item in self.refnodes:
if '#' in item['refuri']:
continue
if item['refuri'] in self.ignored_files:
continue
spine.append(_spine_template % {
'idref': self.esc(self.make_id(item['refuri']))
})
for info in self.domain_indices:
spine.append(_spine_template % {
'idref': self.esc(self.make_id(info[0] + self.out_suffix))
})
if self.config.html_use_index:
spine.append(_spine_template % {
'idref': self.esc(self.make_id('genindex' + self.out_suffix))
})
# add the optional cover
content_tmpl = _content_template
html_tmpl = None
if self.config.epub_cover:
image, html_tmpl = self.config.epub_cover
mpos = content_tmpl.rfind('</metadata>')
cpos = content_tmpl.rfind('\n', 0 , mpos) + 1
content_tmpl = content_tmpl[:cpos] + \
_cover_template % {'cover': self.esc(self.make_id(image))} + \
content_tmpl[cpos:]
if html_tmpl:
spine.insert(0, _spine_template % {
'idref': self.esc(self.make_id(_coverpage_name))})
if _coverpage_name not in self.files:
ext = path.splitext(_coverpage_name)[-1]
self.files.append(_coverpage_name)
projectfiles.append(_file_template % {
'href': self.esc(_coverpage_name),
'id': self.esc(self.make_id(_coverpage_name)),
'media_type': self.esc(_media_types[ext])
})
ctx = {'image': self.esc(image), 'title': self.config.project}
self.handle_page(
os.path.splitext(_coverpage_name)[0], ctx, html_tmpl)
guide = []
auto_add_cover = True
auto_add_toc = True
if self.config.epub_guide:
for type, uri, title in self.config.epub_guide:
file = uri.split('#')[0]
if file not in self.files:
self.files.append(file)
if type == 'cover':
auto_add_cover = False
if type == 'toc':
auto_add_toc = False
guide.append(_guide_template % {
'type': self.esc(type),
'title': self.esc(title),
'uri': self.esc(uri)
})
if auto_add_cover and html_tmpl:
guide.append(_guide_template % {
'type': 'cover',
'title': _guide_titles['cover'],
'uri': self.esc(_coverpage_name)
})
if auto_add_toc and self.refnodes:
guide.append(_guide_template % {
'type': 'toc',
'title': _guide_titles['toc'],
'uri': self.esc(self.refnodes[0]['refuri'])
})
projectfiles = '\n'.join(projectfiles)
spine = '\n'.join(spine)
guide = '\n'.join(guide)
# write the project file
f = codecs.open(path.join(outdir, outname), 'w', 'utf-8')
try:
f.write(content_tmpl % \
self.content_metadata(projectfiles, spine, guide))
finally:
f.close()
def new_navpoint(self, node, level, incr=True):
"""Create a new entry in the toc from the node at given level."""
# XXX Modifies the node
if incr:
self.playorder += 1
node['indent'] = _navpoint_indent * level
node['navpoint'] = self.esc(_navPoint_template % self.playorder)
node['playorder'] = self.playorder
return _navpoint_template % node
def insert_subnav(self, node, subnav):
"""Insert nested navpoints for given node.
The node and subnav are already rendered to text.
"""
nlist = node.rsplit('\n', 1)
nlist.insert(-1, subnav)
return '\n'.join(nlist)
def build_navpoints(self, nodes):
"""Create the toc navigation structure.
Subelements of a node are nested inside the navpoint. For nested nodes
the parent node is reinserted in the subnav.
"""
navstack = []
navlist = []
level = 1
lastnode = None
for node in nodes:
if not node['text']:
continue
file = node['refuri'].split('#')[0]
if file in self.ignored_files:
continue
if node['level'] > self.config.epub_tocdepth:
continue
if node['level'] == level:
navlist.append(self.new_navpoint(node, level))
elif node['level'] == level + 1:
navstack.append(navlist)
navlist = []
level += 1
if lastnode and self.config.epub_tocdup:
# Insert starting point in subtoc with same playOrder
navlist.append(self.new_navpoint(lastnode, level, False))
navlist.append(self.new_navpoint(node, level))
else:
while node['level'] < level:
subnav = '\n'.join(navlist)
navlist = navstack.pop()
navlist[-1] = self.insert_subnav(navlist[-1], subnav)
level -= 1
navlist.append(self.new_navpoint(node, level))
lastnode = node
while level != 1:
subnav = '\n'.join(navlist)
navlist = navstack.pop()
navlist[-1] = self.insert_subnav(navlist[-1], subnav)
level -= 1
return '\n'.join(navlist)
def toc_metadata(self, level, navpoints):
"""Create a dictionary with all metadata for the toc.ncx file
properly escaped.
"""
metadata = {}
metadata['uid'] = self.config.epub_uid
metadata['title'] = self.config.epub_title
metadata['level'] = level
metadata['navpoints'] = navpoints
return metadata
def build_toc(self, outdir, outname):
"""Write the metainfo file toc.ncx."""
self.info('writing %s file...' % outname)
doctree = self.env.get_and_resolve_doctree(self.config.master_doc,
self, prune_toctrees=False, includehidden=False)
refnodes = self.get_refnodes(doctree, [])
if not refnodes:
refnodes = self.refnodes
navpoints = self.build_navpoints(refnodes)
level = max(item['level'] for item in self.refnodes)
level = min(level, self.config.epub_tocdepth)
f = codecs.open(path.join(outdir, outname), 'w', 'utf-8')
try:
f.write(_toc_template % self.toc_metadata(level, navpoints))
finally:
f.close()
def build_epub(self, outdir, outname):
"""Write the epub file.
It is a zip file with the mimetype file stored uncompressed as the first
entry.
"""
self.info('writing %s file...' % outname)
projectfiles = ['META-INF/container.xml', 'content.opf', 'toc.ncx'] \
+ self.files
epub = zipfile.ZipFile(path.join(outdir, outname), 'w', \
zipfile.ZIP_DEFLATED)
epub.write(path.join(outdir, 'mimetype'), 'mimetype', \
zipfile.ZIP_STORED)
for file in projectfiles:
fp = path.join(outdir, file)
if isinstance(fp, unicode):
fp = fp.encode(sys.getfilesystemencoding())
epub.write(fp, file, zipfile.ZIP_DEFLATED)
epub.close()
|
