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
|
"""
Makes the necesary files to convert from plain html of
Python 1.5 and 1.5.x Documentation to
Microsoft HTML Help format version 1.1
Doesn't change the html's docs.
by hernan.foffani@iname.com
no copyright and no responsabilities.
modified by Dale Nagata for Python 1.5.2
Renamed from make_chm.py to prechm.py, and checked into the Python
project, 19-Apr-2002 by Tim Peters. Assorted modifications by Tim
and Fred Drake. Obtained from Robin Dunn's .chm packaging of the
Python 2.2 docs, at <http://alldunn.com/python/>.
"""
import sys
import os
import formatter
import htmllib
import string
import getopt
usage_mode = '''
Usage: make_chm.py [-c] [-k] [-p] [-v 1.5[.x]] filename
-c: does not build filename.hhc (Table of Contents)
-k: does not build filename.hhk (Index)
-p: does not build filename.hhp (Project File)
-v 1.5[.x]: makes help for the python 1.5[.x] docs
(default is python 1.5.2 docs)
'''
# Project file (*.hhp) template. 'arch' is the file basename (like
# the pythlp in pythlp.hhp); 'version' is the doc version number (like
# the 2.2 in Python 2.2).
# The magical numbers in the long line under [WINDOWS] set most of the
# user-visible features (visible buttons, tabs, etc).
project_template = '''
[OPTIONS]
Compiled file=%(arch)s.chm
Contents file=%(arch)s.hhc
Default Window=%(arch)s
Default topic=index.html
Display compile progress=No
Full text search stop list file=%(arch)s.stp
Full-text search=Yes
Index file=%(arch)s.hhk
Language=0x409
Title=Python %(version)s Documentation
[WINDOWS]
%(arch)s="Python %(version)s Documentation","%(arch)s.hhc","%(arch)s.hhk",\
"index.html","index.html",,,,,0x63520,220,0x384e,[271,372,740,718],,,,,,,0
[FILES]
'''
contents_header = '''
<OBJECT type="text/site properties">
<param name="Window Styles" value="0x801227">
<param name="ImageType" value="Folder">
</OBJECT>
<UL>
<LI> <OBJECT type="text/sitemap">
<param name="Name" value="Python %s Docs">
<param name="Local" value="./index.html">
</OBJECT>
<UL>
'''
contents_footer = '''
</UL></UL>
'''
object_sitemap = '''
<LI> <OBJECT type="text/sitemap">
<param name="Local" value="%s">
<param name="Name" value="%s">
</OBJECT>
'''
# List of words the full text search facility shouldn't index. This
# becomes file ARCH.stp. Note that this list must be pretty small!
# Different versions of the MS docs claim the file has a maximum size of
# 256 or 512 bytes (including \r\n at the end of each line).
# Note that "and", "or", "not" and "near" are operators in the search
# language, so not point indexing them even if wanted to.
stop_list = '''
a an and
is
near
not
of
or
the
'''
# Library Doc list of tuples:
# each 'book' : (Dir, Title, First page, Content page, Index page)
#
supported_libraries = {
'2.2': ### Beta!!! fix for actual release
[
('.', 'Global Module Index', 'modindex.html', None, None),
('whatsnew', "What's New", 'index.html', 'contents.html', None),
('tut','Tutorial','tut.html','node2.html',None),
('lib','Library Reference','lib.html','contents.html','genindex.html'),
('ref','Language Reference','ref.html','contents.html','genindex.html'),
('mac','Macintosh Reference','mac.html','contents.html','genindex.html'),
('ext','Extending and Embedding','ext.html','contents.html',None),
('api','Python/C API','api.html','contents.html','genindex.html'),
('doc','Documenting Python','doc.html','contents.html',None),
('inst','Installing Python Modules', 'inst.html', 'index.html', None),
('dist','Distributing Python Modules', 'dist.html', 'index.html', None),
],
'2.1.1':
[
('.', 'Global Module Index', 'modindex.html', None, None),
('tut','Tutorial','tut.html','node2.html',None),
('lib','Library Reference','lib.html','contents.html','genindex.html'),
('ref','Language Reference','ref.html','contents.html','genindex.html'),
('mac','Macintosh Reference','mac.html','contents.html','genindex.html'),
('ext','Extending and Embedding','ext.html','contents.html',None),
('api','Python/C API','api.html','contents.html','genindex.html'),
('doc','Documenting Python','doc.html','contents.html',None),
('inst','Installing Python Modules', 'inst.html', 'index.html', None),
('dist','Distributing Python Modules', 'dist.html', 'index.html', None),
],
'2.0.0':
[
('.', 'Global Module Index', 'modindex.html', None, None),
('tut','Tutorial','tut.html','node2.html',None),
('lib','Library Reference','lib.html','contents.html','genindex.html'),
('ref','Language Reference','ref.html','contents.html','genindex.html'),
('mac','Macintosh Reference','mac.html','contents.html','genindex.html'),
('ext','Extending and Embedding','ext.html','contents.html',None),
('api','Python/C API','api.html','contents.html','genindex.html'),
('doc','Documenting Python','doc.html','contents.html',None),
('inst','Installing Python Modules', 'inst.html', 'contents.html', None),
('dist','Distributing Python Modules', 'dist.html', 'contents.html', None),
],
# <dnagata@creo.com> Apr 17/99: library for 1.5.2 version:
# <hernan.foffani@iname.com> May 01/99: library for 1.5.2 (04/30/99):
'1.5.2':
[
('tut','Tutorial','tut.html','node2.html',None),
('lib','Library Reference','lib.html','contents.html','genindex.html'),
('ref','Language Reference','ref.html','contents.html','genindex.html'),
('mac','Macintosh Reference','mac.html','contents.html','genindex.html'),
('ext','Extending and Embedding','ext.html','contents.html',None),
('api','Python/C API','api.html','contents.html','genindex.html'),
('doc','Documenting Python','doc.html','contents.html',None)
],
# library for 1.5.1 version:
'1.5.1':
[
('tut','Tutorial','tut.html','contents.html',None),
('lib','Library Reference','lib.html','contents.html','genindex.html'),
('ref','Language Reference','ref-1.html','ref-2.html','ref-11.html'),
('ext','Extending and Embedding','ext.html','contents.html',None),
('api','Python/C API','api.html','contents.html','genindex.html')
],
# library for 1.5 version:
'1.5':
[
('tut','Tutorial','tut.html','node1.html',None),
('lib','Library Reference','lib.html','node1.html','node268.html'),
('ref','Language Reference','ref-1.html','ref-2.html','ref-11.html'),
('ext','Extending and Embedding','ext.html','node1.html',None),
('api','Python/C API','api.html','node1.html','node48.html')
]
}
class AlmostNullWriter(formatter.NullWriter):
savedliteral = ''
def send_flowing_data(self, data):
# need the text tag for later
datastriped = string.strip(data)
if self.savedliteral == '':
self.savedliteral = datastriped
else:
self.savedliteral = string.strip(self.savedliteral +
' ' + datastriped)
class HelpHtmlParser(htmllib.HTMLParser):
indent = 0 # number of tabs for pritty printing of files
ft = None # output file
path = None # relative path
proc = 0 # if true I process, if false I skip
# (some headers, footers, etc.)
def begin_group(self):
if not self.proc:
# first level, start processing
self.proc = 1
self.indent = self.indent + 1
def finnish_group(self):
self.indent = self.indent - 1
if self.proc and self.indent == 0:
# if processing and back to root, then stop
self.proc = 0
def anchor_bgn(self, href, name, type):
if self.proc:
self.formatter.writer.savedliteral = ''
self.ft.write('<OBJECT type="text/sitemap">\n')
self.ft.write('\t' * self.indent + \
'\t<param name="Local" value="' + self.path + \
'/' + href + '">\n')
def anchor_end(self):
if self.proc:
self.ft.write('\t' * self.indent + \
'\t<param name="Name" value="' + \
self.formatter.writer.savedliteral + '">\n')
self.ft.write('\t' * self.indent + '\t</OBJECT>\n')
def start_dl(self, atr_val):
self.begin_group()
def end_dl(self):
self.finnish_group()
def do_dt(self, atr_val):
# no trailing newline on pourpose!
self.ft.write("\t" * self.indent + "<LI>")
class IdxHlpHtmlParser(HelpHtmlParser):
# nothing special here, seems enough with parent class
pass
class TocHlpHtmlParser(HelpHtmlParser):
def start_dl(self, atr_val):
self.begin_group()
self.ft.write('\t' * self.indent + '<UL>\n')
def end_dl(self):
self.finnish_group()
self.ft.write('</UL>\n')
def start_ul(self, atr_val):
self.begin_group()
self.ft.write('\t' * self.indent + '<UL>\n')
def end_ul(self):
self.finnish_group()
self.ft.write('</UL>\n')
def do_li(self, atr_val):
# no trailing newline on pourpose!
self.ft.write("\t" * self.indent + "<LI>")
def index(path, archivo, output):
f = formatter.AbstractFormatter(AlmostNullWriter())
parser = IdxHlpHtmlParser(f)
parser.path = path
parser.ft = output
fil = path + '/' + archivo
parser.feed(open(fil).read())
parser.close()
def content(path, archivo, output):
f = formatter.AbstractFormatter(AlmostNullWriter())
parser = TocHlpHtmlParser(f)
parser.path = path
parser.ft = output
fil = path + '/' + archivo
parser.feed(open(fil).read())
parser.close()
def do_index(library, output):
output.write('<UL>\n')
for book in library:
print '\t', book[2]
if book[4]:
index(book[0], book[4], output)
output.write('</UL>\n')
def do_content(library, version, output):
output.write(contents_header % version)
for book in library:
print '\t', book[2]
output.write(object_sitemap % (book[0]+"/"+book[2], book[1]))
if book[3]:
content(book[0], book[3], output)
output.write(contents_footer)
# Fill in the [FILES] section of the project (.hhp) file.
# 'library' is the list of directory description tuples from
# supported_libraries for the version of the docs getting generated.
def do_project(library, output, arch, version):
output.write(project_template % locals())
for book in library:
directory = book[0]
path = directory + '\\%s\n'
for page in os.listdir(directory):
if page.endswith('.html') or page.endswith('.css'):
output.write(path % page)
def openfile(file):
try:
p = open(file, "w")
except IOError, msg:
print file, ":", msg
sys.exit(1)
return p
def usage():
print usage_mode
sys.exit(0)
def do_it(args = None):
if not args:
args = sys.argv[1:]
if not args:
usage()
try:
optlist, args = getopt.getopt(args, 'ckpv:')
except getopt.error, msg:
print msg
usage()
if not args or len(args) > 1:
usage()
arch = args[0]
version = None
for opt in optlist:
if opt[0] == '-v':
version = opt[1]
break
if not version:
usage()
library = supported_libraries[ version ]
if not (('-p','') in optlist):
fname = arch + '.stp'
f = openfile(fname)
print "Building stoplist", fname, "..."
words = stop_list.split()
words.sort()
for word in words:
print >> f, word
f.close()
f = openfile(arch + '.hhp')
print "Building Project..."
do_project(library, f, arch, version)
if version == '2.0.0':
for image in os.listdir('icons'):
f.write('icons'+ '\\' + image + '\n')
f.close()
if not (('-c','') in optlist):
f = openfile(arch + '.hhc')
print "Building Table of Content..."
do_content(library, version, f)
f.close()
if not (('-k','') in optlist):
f = openfile(arch + '.hhk')
print "Building Index..."
do_index(library, f)
f.close()
if __name__ == '__main__':
do_it()
|