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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
from __future__ import unicode_literals, division, absolute_import, print_function
import os
from .unipath import pathof
from .compatibility_utils import unescapeit
import re
# note: re requites the pattern to be the exact same type as the data to be searched in python3
# but u"" is not allowed for the pattern itself only b""
from xml.sax.saxutils import escape as xmlescape
from .mobi_utils import toBase32
from .mobi_index import MobiIndex
DEBUG_NCX = False
class ncxExtract:
def __init__(self, mh, files):
self.mh = mh
self.sect = self.mh.sect
self.files = files
self.isNCX = False
self.mi = MobiIndex(self.sect)
self.ncxidx = self.mh.ncxidx
self.indx_data = None
def parseNCX(self):
indx_data = []
tag_fieldname_map = {
1: ['pos',0],
2: ['len',0],
3: ['noffs',0],
4: ['hlvl',0],
5: ['koffs',0],
6: ['pos_fid',0],
21: ['parent',0],
22: ['child1',0],
23: ['childn',0]
}
if self.ncxidx != 0xffffffff:
outtbl, ctoc_text = self.mi.getIndexData(self.ncxidx, "NCX")
if DEBUG_NCX:
print(ctoc_text)
print(outtbl)
num = 0
for [text, tagMap] in outtbl:
tmp = {
'name': text.decode('utf-8'),
'pos': -1,
'len': 0,
'noffs': -1,
'text' : "Unknown Text",
'hlvl' : -1,
'kind' : "Unknown Kind",
'pos_fid' : None,
'parent' : -1,
'child1' : -1,
'childn' : -1,
'num' : num
}
for tag in tag_fieldname_map:
[fieldname, i] = tag_fieldname_map[tag]
if tag in tagMap:
fieldvalue = tagMap[tag][i]
if tag == 6:
pos_fid = toBase32(fieldvalue,4).decode('utf-8')
fieldvalue2 = tagMap[tag][i+1]
pos_off = toBase32(fieldvalue2,10).decode('utf-8')
fieldvalue = 'kindle:pos:fid:%s:off:%s' % (pos_fid, pos_off)
tmp[fieldname] = fieldvalue
if tag == 3:
toctext = ctoc_text.get(fieldvalue, 'Unknown Text')
toctext = toctext.decode(self.mh.codec)
tmp['text'] = toctext
if tag == 5:
kindtext = ctoc_text.get(fieldvalue, 'Unknown Kind')
kindtext = kindtext.decode(self.mh.codec)
tmp['kind'] = kindtext
indx_data.append(tmp)
if DEBUG_NCX:
print("record number: ", num)
print("name: ", tmp['name'],)
print("position", tmp['pos']," length: ", tmp['len'])
print("text: ", tmp['text'])
print("kind: ", tmp['kind'])
print("heading level: ", tmp['hlvl'])
print("parent:", tmp['parent'])
print("first child: ",tmp['child1']," last child: ", tmp['childn'])
print("pos_fid is ", tmp['pos_fid'])
print("\n\n")
num += 1
self.indx_data = indx_data
return indx_data
def buildNCX(self, htmlfile, title, ident, lang):
indx_data = self.indx_data
ncx_header = \
'''<?xml version='1.0' encoding='utf-8'?>
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="%s">
<head>
<meta content="%s" name="dtb:uid"/>
<meta content="%d" name="dtb:depth"/>
<meta content="mobiunpack.py" name="dtb:generator"/>
<meta content="0" name="dtb:totalPageCount"/>
<meta content="0" name="dtb:maxPageNumber"/>
</head>
<docTitle>
<text>%s</text>
</docTitle>
<navMap>
'''
ncx_footer = \
''' </navMap>
</ncx>
'''
ncx_entry = \
'''<navPoint id="%s" playOrder="%d">
<navLabel>
<text>%s</text>
</navLabel>
<content src="%s"/>'''
# recursive part
def recursINDX(max_lvl=0, num=0, lvl=0, start=-1, end=-1):
if start>len(indx_data) or end>len(indx_data):
print("Warning: missing INDX child entries", start, end, len(indx_data))
return ''
if DEBUG_NCX:
print("recursINDX lvl %d from %d to %d" % (lvl, start, end))
xml = ''
if start <= 0:
start = 0
if end <= 0:
end = len(indx_data)
if lvl > max_lvl:
max_lvl = lvl
indent = ' ' * (2 + lvl)
for i in range(start, end):
e = indx_data[i]
if not e['hlvl'] == lvl:
continue
# open entry
num += 1
link = '%s#filepos%d' % (htmlfile, e['pos'])
tagid = 'np_%d' % num
entry = ncx_entry % (tagid, num, xmlescape(unescapeit(e['text'])), link)
entry = re.sub(re.compile('^', re.M), indent, entry, 0)
xml += entry + '\n'
# recurs
if e['child1']>=0:
xmlrec, max_lvl, num = recursINDX(max_lvl, num, lvl + 1,
e['child1'], e['childn'] + 1)
xml += xmlrec
# close entry
xml += indent + '</navPoint>\n'
return xml, max_lvl, num
body, max_lvl, num = recursINDX()
header = ncx_header % (lang, ident, max_lvl + 1, title)
ncx = header + body + ncx_footer
if not len(indx_data) == num:
print("Warning: different number of entries in NCX", len(indx_data), num)
return ncx
def writeNCX(self, metadata):
# build the xml
self.isNCX = True
print("Write ncx")
# htmlname = os.path.basename(self.files.outbase)
# htmlname += '.html'
htmlname = 'book.html'
xml = self.buildNCX(htmlname, metadata['Title'][0], metadata['UniqueID'][0], metadata.get('Language')[0])
# write the ncx file
# ncxname = os.path.join(self.files.mobi7dir, self.files.getInputFileBasename() + '.ncx')
ncxname = os.path.join(self.files.mobi7dir, 'toc.ncx')
with open(pathof(ncxname), 'wb') as f:
f.write(xml.encode('utf-8'))
def buildK8NCX(self, indx_data, title, ident, lang):
ncx_header = \
'''<?xml version='1.0' encoding='utf-8'?>
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="%s">
<head>
<meta content="%s" name="dtb:uid"/>
<meta content="%d" name="dtb:depth"/>
<meta content="mobiunpack.py" name="dtb:generator"/>
<meta content="0" name="dtb:totalPageCount"/>
<meta content="0" name="dtb:maxPageNumber"/>
</head>
<docTitle>
<text>%s</text>
</docTitle>
<navMap>
'''
ncx_footer = \
''' </navMap>
</ncx>
'''
ncx_entry = \
'''<navPoint id="%s" playOrder="%d">
<navLabel>
<text>%s</text>
</navLabel>
<content src="%s"/>'''
# recursive part
def recursINDX(max_lvl=0, num=0, lvl=0, start=-1, end=-1):
if start>len(indx_data) or end>len(indx_data):
print("Warning: missing INDX child entries", start, end, len(indx_data))
return ''
if DEBUG_NCX:
print("recursINDX lvl %d from %d to %d" % (lvl, start, end))
xml = ''
if start <= 0:
start = 0
if end <= 0:
end = len(indx_data)
if lvl > max_lvl:
max_lvl = lvl
indent = ' ' * (2 + lvl)
for i in range(start, end):
e = indx_data[i]
htmlfile = e['filename']
desttag = e['idtag']
if not e['hlvl'] == lvl:
continue
# open entry
num += 1
if desttag == '':
link = 'Text/%s' % htmlfile
else:
link = 'Text/%s#%s' % (htmlfile, desttag)
tagid = 'np_%d' % num
entry = ncx_entry % (tagid, num, xmlescape(unescapeit(e['text'])), link)
entry = re.sub(re.compile('^', re.M), indent, entry, 0)
xml += entry + '\n'
# recurs
if e['child1']>=0:
xmlrec, max_lvl, num = recursINDX(max_lvl, num, lvl + 1,
e['child1'], e['childn'] + 1)
xml += xmlrec
# close entry
xml += indent + '</navPoint>\n'
return xml, max_lvl, num
body, max_lvl, num = recursINDX()
header = ncx_header % (lang, ident, max_lvl + 1, title)
ncx = header + body + ncx_footer
if not len(indx_data) == num:
print("Warning: different number of entries in NCX", len(indx_data), num)
return ncx
def writeK8NCX(self, ncx_data, metadata):
# build the xml
self.isNCX = True
print("Write K8 ncx")
xml = self.buildK8NCX(ncx_data, metadata['Title'][0], metadata['UniqueID'][0], metadata.get('Language')[0])
bname = 'toc.ncx'
ncxname = os.path.join(self.files.k8oebps,bname)
with open(pathof(ncxname), 'wb') as f:
f.write(xml.encode('utf-8'))
|
