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
|
#! /usr/bin/python3
from html.parser import HTMLParser
from xml.sax.saxutils import escape
import os, sys, re
class PyHTMLParser(HTMLParser):
pages_to_include = set(('whatsnew/index.html', 'tutorial/index.html', 'using/index.html',
'reference/index.html', 'library/index.html', 'howto/index.html',
'extending/index.html', 'c-api/index.html', 'install/index.html',
'distutils/index.html'))
def __init__(self, basedir, fn, indent, parents=set()):
HTMLParser.__init__(self, convert_charrefs=True)
self.basedir = basedir
self.dir, self.fn = os.path.split(fn)
self.data = ''
self.parents = parents
self.link = {}
self.indent = indent
self.last_indent = indent - 1
self.sub_indent = 0
self.sub_count = 0
self.next_link = False
def escape(self, text):
return escape(text, {'"': '"'})
def process_link(self):
new_href = self.escape(os.path.join(self.dir, self.link['href']))
text = self.escape(self.link['text'])
indent = self.indent + self.sub_indent
if self.last_indent == indent:
print('%s</sub>' % (' ' * self.last_indent))
self.sub_count -= 1
print('%s<sub link="%s" name="%s">' % (' ' * indent, new_href, text))
self.sub_count += 1
self.last_indent = self.indent + self.sub_indent
def handle_starttag(self, tag, attrs):
if tag == 'a':
self.start_a(attrs)
elif tag == 'li':
self.start_li(attrs)
def handle_endtag(self, tag):
if tag == 'a':
self.end_a()
elif tag == 'li':
self.end_li()
def start_li(self, attrs):
self.sub_indent += 1
self.next_link = True
def end_li(self):
indent = self.indent + self.sub_indent
if self.sub_count > 0:
print('%s</sub>' % (' ' * self.last_indent))
self.sub_count -= 1
self.last_indent -= 1
self.sub_indent -= 1
def start_a(self, attrs):
self.link = {}
for attr in attrs:
self.link[attr[0]] = attr[1]
self.data = ''
def end_a(self):
process = False
text = self.escape(self.data.replace('\t', '').replace('\n', ' '))
self.link['text'] = text
# handle a tag without href attribute
try:
href = self.link['href']
except KeyError:
return
abs_href = os.path.join(self.basedir, href)
if abs_href in self.parents:
return
if href.startswith('..') or href.startswith('http:') \
or href.startswith('mailto:') or href.startswith('news:'):
return
if href in ('', 'about.html', 'modindex.html', 'genindex.html', 'glossary.html',
'search.html', 'contents.html', 'download.html', 'bugs.html',
'license.html', 'copyright.html'):
return
if 'class' in self.link:
if self.link['class'] in ('biglink'):
process = True
if self.link['class'] in ('reference external'):
if self.next_link:
process = True
next_link = False
if process == True:
self.process_link()
if href in self.pages_to_include:
self.parse_file(os.path.join(self.dir, href))
def finish(self):
if self.sub_count > 0:
print('%s</sub>' % (' ' * self.last_indent))
def handle_data(self, data):
self.data += data
def parse_file(self, href):
# TODO basedir bestimmen
parent = os.path.join(self.basedir, self.fn)
self.parents.add(parent)
parser = PyHTMLParser(self.basedir, href, self.indent + 1,
self.parents)
text = open(self.basedir + '/' + href, encoding='latin_1').read()
parser.feed(text)
parser.finish()
parser.close()
if parent in self.parents:
self.parents.remove(parent)
class PyIdxHTMLParser(HTMLParser):
def __init__(self, basedir, fn, indent):
HTMLParser.__init__(self, convert_charrefs=True)
self.basedir = basedir
self.dir, self.fn = os.path.split(fn)
self.data = ''
self.link = {}
self.indent = indent
self.active = False
self.indented = False
self.nolink = False
self.header = ''
self.last_letter = 'Z'
self.last_text = ''
def escape(self, text):
return escape(text, {'"': '"'})
def process_link(self):
new_href = self.escape(os.path.join(self.dir, self.link['href']))
text = self.escape(self.link['text'])
if not self.active:
return
if text.startswith('['):
return
if self.link.get('rel', None) in ('prev', 'parent', 'next', 'contents', 'index'):
return
if self.indented:
text = self.last_text + ' ' + text
else:
# Save it in case we need it again
self.last_text = re.sub(' \([\w\-\.\s]+\)', '', text)
indent = self.indent
print('%s<function link="%s" name="%s"/>' % (' ' * indent, new_href, text))
def handle_starttag(self, tag, attrs):
if tag == 'a':
self.start_a(attrs)
elif tag == 'dl':
self.start_dl(attrs)
elif tag == 'dt':
self.start_dt(attrs)
elif tag == 'h2':
self.start_h2(attrs)
elif tag == 'td':
self.start_td(attrs)
elif tag == 'table':
self.start_table(attrs)
def handle_endtag(self, tag):
if tag == 'a':
self.end_a()
elif tag == 'dl':
self.end_dl()
elif tag == 'dt':
self.end_dt()
elif tag == 'h2':
self.end_h2()
elif tag == 'td':
self.end_td()
elif tag == 'table':
self.end_table()
def start_dl(self, attrs):
if self.last_text:
# Looks like we found the second part to a command
self.indented = True
def end_dl(self):
self.indented = False
def start_dt(self, attrs):
self.data = ''
self.nolink = True
def end_dt(self):
if not self.active:
return
if self.nolink == True:
# Looks like we found the first part to a command
self.last_text = re.sub(' \([\w\-\.\s]+\)', '', self.data)
self.nolink = False
def start_h2(self, attrs):
for k, v in attrs:
if k == 'id':
self.header = v
if v == '_':
self.active = True
def end_h2(self):
pass
def start_td(self, attrs):
self.indented = False
self.last_text = ''
def end_td(self):
pass
def start_table(self, attrs):
pass
def end_table(self):
if self.header == self.last_letter:
self.active = False
def start_a(self, attrs):
self.nolink = False
self.link = {}
for attr in attrs:
self.link[attr[0]] = attr[1]
self.data = ''
def end_a(self):
text = self.data.replace('\t', '').replace('\n', ' ')
text = text.replace("Whats ", "What's ")
self.link['text'] = text
# handle a tag without href attribute
try:
href = self.link['href']
except KeyError:
return
self.process_link()
def handle_data(self, data):
self.data += data
def handle_entityref(self, name):
# not meant to be called while convert_charrefs is true
raise AssertionError('entityrefs should not be handled any more')
def main():
base = sys.argv[1]
fn = sys.argv[2]
version = escape(sys.argv[3])
parser = PyHTMLParser(base, fn, indent=0)
print('<?xml version="1.0" encoding="iso-8859-1"?>')
print('<book title="Python %s Documentation" name="Python %s" version="%s" link="index.html">' % (version, version, version))
print('<chapters>')
parser.parse_file(fn)
print('</chapters>')
print('<functions>')
fn = 'genindex-all.html'
parser = PyIdxHTMLParser(base, fn, indent=1)
text = open(base + '/' + fn, encoding='latin_1').read()
parser.feed(text)
parser.close()
print('</functions>')
print('</book>')
main()
|