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
|
#!/usr/bin/env python
#
# This file is part of the LibreOffice project.
#
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.
#
import sys
import os
import xml.parsers.expat
alltitles=[]
def is_present(title):
for i in alltitles:
try:
if i.strip() == title.strip():
return True
except:
return False
return False
def make_unique(title):
n=0
t = title
while is_present(t):
n=n+1
t = title+"_%d"%(n)
return t
replace_text_list = [
["$[officename]","LibreOffice"],
["%PRODUCTNAME","LibreOffice"],
["$PRODUCTNAME","LibreOffice"],
['"+"',"Plus"],
['"*"',"Star"],
['"-"',"Minus"],
['"/"',"Slash"],
['"^"',"Cap"],
['#',"No"],
[')','_'],
['(','_'],
[']','_'],
['[','_'],
['\\','_'],
['/','_'],
['&',"and"],
[';','_']
]
replace_readable_list = [
["$[officename]","{{ProductName}}"],
["%PRODUCTNAME","{{ProductName}}"],
["$PRODUCTNAME","{{ProductName}}"]
]
modules_list = [
["sbasic","Basic"],
["scalc","Calc"],
["schart","Chart"],
["sdraw","Draw"],
["simpress","Impress"],
["smath","Math"],
["swriter","Writer"],
["shared","Common"]
]
def get_module(text):
for i in modules_list:
if text.find('/' + i[0] + '/') >=0:
return i[1]
return ""
def replace_text(text, replace_list):
for i in replace_list:
if text.find(i[0]) >= 0:
text = text.replace(i[0],i[1])
return text
def wiki_text(text):
t = replace_text(text, replace_text_list)
if t == '':
t = 'LibreOffice' # hardcoded fallback
return t.strip()
def readable_text(text):
return replace_text(text, replace_readable_list)
class TitleParser:
title = ''
is_title = False
def start_element(self, name, attrs):
if name == 'title':
self.is_title = True
def end_element(self, name):
if name == 'title':
self.is_title = False
def char_data(self, data):
if self.is_title:
self.title = self.title + data
def get_title(self):
return self.title.strip()
def parsexhp(filename):
module = get_module(filename)
if module == '':
return
parsing = True
file=open(filename,"r")
p = xml.parsers.expat.ParserCreate()
tp = TitleParser()
p.StartElementHandler = tp.start_element
p.EndElementHandler = tp.end_element
p.CharacterDataHandler = tp.char_data
buf = file.read()
try:
p.Parse(buf)
except:
sys.stderr.write('Cannot parse %s, skipping it\n'% filename)
file.close()
return
file.close()
title = tp.get_title()
if len(title) > 0:
readable_title = readable_text(title)
title = module + '/' + wiki_text(title)
title = title.replace(' ', '_')
title = title.replace('___', '_')
title = title.replace('__', '_')
title = title.strip('_')
title = make_unique(title)
alltitles.append(title)
return((filename, title, readable_title))
# Main Function
def gettitles(path):
pattern = "xhp"
alltitles = []
for root, dirs, files in os.walk(path):
for i in files:
if i.find(pattern) >= 0:
t = parsexhp(root+"/"+i)
if t is not None:
alltitles.append(t)
return alltitles
# vim:set shiftwidth=4 softtabstop=4 expandtab:
|
