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
|
from os import mkdir, makedirs, chdir, getcwd, listdir
from os.path import isfile, isdir, exists, dirname, realpath, getsize, walk
from re import match, escape, search, sub
from shutil import copytree
from HTMLParser import HTMLParser, HTMLParseError, piclose
from BaseHTTPServer import HTTPServer, BaseHTTPRequestHandler
from urllib import unquote
from time import sleep
from mimetypes import guess_type
from chm import chmlib
if exists("arch.conf"):
config = "arch.conf"
else:
config = "/etc/archmage/arch.conf"
def listdir_r(dir):
def f(res, dir, files):
for each in files:
d = '/'.join(dir.split('/')[1:])
if d: d += '/'
res.append(d + each)
res = []
walk(dir, f, res)
return res
class CHMDir(object):
"""docstring should be here"""
def __init__(self, name):
self.sourcename = name
execfile(config, self.__dict__)
self.entries = self.get_entries(name)
self.templates = self.get_templates()
for e in self.entries:
if e.endswith('.hhc'):
self.hhc = e
if e.endswith('.hhk'):
self.hhk = e
hhclines = self.get_entry_by_name(self.hhc)
self.contents, self.deftopic = SitemapFile(hhclines).parse()
def get_entries(self, name):
entries = list()
for fname in listdir_r(name):
name = '/' + fname
if isdir(self.sourcename + name):
name += '/'
entries.append(name)
return entries
def get_entry_by_name(self, name):
if name == '/':
name = '/index.html'
if name in self.templates:
return self.get_template_by_name(name)
if name.lower() in [ '/icons/' + icon.lower()
for icon in listdir(self.templates_dir + '/icons/') ]:
return open(self.templates_dir + name).read()
for e in self.entries:
if e.lower() == name.lower():
return CHMEntry(self, e).get()
else:
raise NameError, "there is no " + name
def sub_mytag(self,re):
"""docstring should be here"""
try:
res = eval("self."+re.group(1))
except:
res = eval(re.group(1))
return res
def get_templates(self):
"""docstring should be here"""
return [ '/'+file for file in listdir(self.templates_dir)
if isfile(self.templates_dir + file) ]
def get_template_by_name(self,name):
"""docstring should be here"""
s = open(self.templates_dir + name).read()
return sub('\<%(.+?)%\>', self.sub_mytag, s)
def process_templ(self):
"""docstring should be here"""
for template in self.templates:
open(template[1:],'w').write(self.get_template_by_name(template))
if not exists('icons/'):
copytree(self.templates_dir+'/icons/','icons/')
def raw_extract(self):
"""docstring should be here"""
aux_re='|'.join([ escape(s) for s in self.auxes])
for e in self.entries:
if match(aux_re, e):
continue
fname=e[1:]
fname=fname.lower()
dname=dirname(fname)
if e[-1:]=='/':
makedirs(fname)
else:
if dname and not exists(dname):
makedirs(dname)
if self.fs_encoding:
fname=fname.decode('utf-8').encode(self.fs_encoding)
(open(fname,'w')).writelines(CHMEntry(self,e).get())
def extract(self,dir):
"""docstring should be here"""
mkdir(dir)
chdir(dir)
self.raw_extract()
self.process_templ()
class CHMFile(CHMDir):
"""docstring should be here"""
def get_entries(self, name):
entries = []
self._handler = chmlib.chm_open(name)
for name in self.get_names(self._handler):
if (name == '/'):
continue
entries.append(name)
return entries
def get_names(self, chmfile):
def _get_name(chmfile, ui, context):
context.append(ui.path)
return chmlib.CHM_ENUMERATOR_CONTINUE
chmdir = []
if (chmlib.chm_enumerate(chmfile, chmlib.CHM_ENUMERATE_ALL, _get_name, chmdir)) == 0:
print(" *** ERROR ***")
return chmdir
def __del__(self):
chmlib.chm_close(self._handler)
class CHMEntry(object):
"""docstring should be here"""
def __init__(self, parent ,name):
self.name = name
self.parent = parent
def read(self):
"""docstring should be here"""
if isinstance(self.parent, CHMFile):
result, ui = chmlib.chm_resolve_object(self.parent._handler, self.name)
if (result != chmlib.CHM_RESOLVE_SUCCESS):
return None
size, text = chmlib.chm_retrieve_object(self.parent._handler, ui, 0L, ui.length)
if (size == 0):
return None
return text
else:
return open(self.parent.sourcename + self.name).read()
def lower_links(self, text):
return sub('(?i)(href|src)\s*=\s*([^\s|>]+)', lambda m:m.group(0).lower(), text)
def add_restoreframing_js(self, name, text):
name = sub('/+', '/', name)
depth = name.count('/')
js = """<body><script language="javascript">
if ((window.name != "content") && (navigator.userAgent.indexOf("Opera") <= -1) )
document.write("<center><a href='%sindex.html?page=%s'>show framing</a></center>")
</script>""" % ( '../'*depth, name )
return sub('(?i)<\s*body\s*>', js, text)
def get(self):
lines = self.read()
if search('(?i)\.html?$', self.name):
if self.parent.filename_case:
lines = self.lower_links(lines)
if self.parent.restore_framing:
lines = self.add_restoreframing_js(self.name[1:], lines)
return lines
class SitemapFile(object):
def __init__(self, lines):
self.lines = lines
def parse(self):
p = SitemapParser()
p.feed(self.lines)
return (p.parsed + "\n]", p.deftopic)
class TagStack(list):
""" from book of David Mertz "Text Processing in Python" """
def append(self, tag):
# Remove every paragraph-level tag if this is one
if tag.lower() in ('p','blockquote'):
self = TagStack([t for t in super
if t not in ('p','blockquote')])
super(TagStack,self).append(tag)
def pop(self, tag):
# "Pop" by tag from nearest pos, not only last item
self.reverse()
try:
pos = self.index(tag)
except ValueError:
raise HTMLParser.HTMLParseError, "Tag not on stack"
self[:]=self[pos+1:]
self.reverse()
class SitemapParser(HTMLParser):
""" Class for parsing files in SiteMap format, such as .hhc """
def __init__(self):
self.tagstack = TagStack()
self.params = {}
self.parsed = ""
self.deftopic = ""
HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
# first ul, start processing from here
if tag == 'ul' and not self.tagstack:
self.tagstack.append(tag)
self.parsed+="\n["
# if inside ul
elif self.tagstack:
if tag == 'li':
if self.tagstack[-1] != 'ul':
self.parsed += "]"
self.tagstack.pop('li')
indent = " "*len(self.tagstack)
if self.parsed != "\n[":
self.parsed += ','
self.parsed+="\n" + indent + "["
if tag == 'param':
self.params[dict(attrs)['name']]=dict(attrs)['value']
self.tagstack.append(tag)
def handle_endtag(self, tag):
# if inside ul
if self.tagstack:
if tag == 'ul':
self.parsed += "]"
if tag == 'object':
if not self.params.has_key('ImageNumber'):
self.params['ImageNumber'] = 1
if not self.params.has_key('Local'):
self.params['Local'] = ''
if not self.params.has_key('Name'):
self.params['Name'] = ''
if not self.deftopic:
self.deftopic = self.params['Local'].lower()
self.params['Name'] = self.params['Name'].replace("\r\n", "\\n").replace("\n", "\\n")
if '"' in self.params['Local']:
lstr = "'%s'"
self.params['Local']=self.params['Local'].replace("'",'\\\'')
else:
lstr = '"%s"'
self.params['Local']=self.params['Local'].replace('"',"\\\"")
if '"' in self.params['Name']:
nstr = "'%s'"
self.params['Name']=self.params['Name'].replace("'",'\\\'')
else:
nstr = '"%s"'
self.params['Name']=self.params['Name'].replace('"',"\\\"")
fstr=nstr+","+lstr+","+'"%s"'
self.parsed += fstr % (
self.params['Name'],
self.params['Local'].lower(),
self.params['ImageNumber'])
self.params={}
self.tagstack.pop(tag)
def parse_starttag(self,i):
try:
return HTMLParser.parse_starttag(self,i)
except HTMLParseError:
try:
return piclose.search(self.rawdata,i).end()
except AttributeError:
return -1
def parse_endtag(self,i):
try:
return HTMLParser.parse_endtag(self,i)
except HTMLParseError:
try:
return piclose.search(self.rawdata,i).end()
except:
return -1
class CHMServer(HTTPServer):
def __init__(self, CHM, name='', port=8000):
self.address = (name, port)
self.httpd = HTTPServer(self.address, CHMRequestHandler)
self.httpd.CHM = CHM
self.address = (name, port)
def run(self):
self.httpd.serve_forever()
class CHMRequestHandler(BaseHTTPRequestHandler):
def do_GET(self):
pagename = unquote(self.path.split('?')[0])
if pagename == '/':
mimetype = 'text/html'
else:
mimetype = guess_type(pagename)[0]
self.send_response(200)
self.send_header("Content-type", mimetype)
self.end_headers()
self.wfile.write(self.server.CHM.get_entry_by_name(pagename))
|
