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
|
#! /usr/bin/env python3
# Written by Martin v. Löwis <loewis@informatik.hu-berlin.de>
"""Generate binary message catalog from textual translation description.
This program converts a textual Uniforum-style message catalog (.po file) into
a binary GNU catalog (.mo file). This is essentially the same function as the
GNU msgfmt program, however, it is a simpler implementation.
Usage: msgfmt.py [OPTIONS] filename.po
Options:
-o file
--output-file=file
Specify the output file to write to. If omitted, output will go to a
file named filename.mo (based off the input file name).
-h
--help
Print this message and exit.
-V
--version
Display version information and exit.
"""
import os
import sys
import ast
import getopt
import struct
import array
from email.parser import HeaderParser
__version__ = "1.1"
MESSAGES = {}
def usage(code, msg=''):
print(__doc__, file=sys.stderr)
if msg:
print(msg, file=sys.stderr)
sys.exit(code)
def add(id, str, fuzzy):
"Add a non-fuzzy translation to the dictionary."
global MESSAGES
if not fuzzy and str:
MESSAGES[id] = str
def generate():
"Return the generated output."
global MESSAGES
# the keys are sorted in the .mo file
keys = sorted(MESSAGES.keys())
offsets = []
ids = strs = b''
for id in keys:
# For each string, we need size and file offset. Each string is NUL
# terminated; the NUL does not count into the size.
offsets.append((len(ids), len(id), len(strs), len(MESSAGES[id])))
ids += id + b'\0'
strs += MESSAGES[id] + b'\0'
output = ''
# The header is 7 32-bit unsigned integers. We don't use hash tables, so
# the keys start right after the index tables.
# translated string.
keystart = 7*4+16*len(keys)
# and the values start after the keys
valuestart = keystart + len(ids)
koffsets = []
voffsets = []
# The string table first has the list of keys, then the list of values.
# Each entry has first the size of the string, then the file offset.
for o1, l1, o2, l2 in offsets:
koffsets += [l1, o1+keystart]
voffsets += [l2, o2+valuestart]
offsets = koffsets + voffsets
output = struct.pack("Iiiiiii",
0x950412de, # Magic
0, # Version
len(keys), # # of entries
7*4, # start of key index
7*4+len(keys)*8, # start of value index
0, 0) # size and offset of hash table
output += array.array("i", offsets).tostring()
output += ids
output += strs
return output
def make(filename, outfile):
ID = 1
STR = 2
# Compute .mo name from .po name and arguments
if filename.endswith('.po'):
infile = filename
else:
infile = filename + '.po'
if outfile is None:
outfile = os.path.splitext(infile)[0] + '.mo'
try:
lines = open(infile, 'rb').readlines()
except IOError as msg:
print(msg, file=sys.stderr)
sys.exit(1)
section = None
fuzzy = 0
# Start off assuming Latin-1, so everything decodes without failure,
# until we know the exact encoding
encoding = 'latin-1'
# Parse the catalog
lno = 0
for l in lines:
l = l.decode(encoding)
lno += 1
# If we get a comment line after a msgstr, this is a new entry
if l[0] == '#' and section == STR:
add(msgid, msgstr, fuzzy)
section = None
fuzzy = 0
# Record a fuzzy mark
if l[:2] == '#,' and 'fuzzy' in l:
fuzzy = 1
# Skip comments
if l[0] == '#':
continue
# Now we are in a msgid section, output previous section
if l.startswith('msgid') and not l.startswith('msgid_plural'):
if section == STR:
add(msgid, msgstr, fuzzy)
if not msgid:
# See whether there is an encoding declaration
p = HeaderParser()
charset = p.parsestr(msgstr.decode(encoding)).get_content_charset()
if charset:
encoding = charset
section = ID
l = l[5:]
msgid = msgstr = b''
is_plural = False
# This is a message with plural forms
elif l.startswith('msgid_plural'):
if section != ID:
print('msgid_plural not preceded by msgid on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l[12:]
msgid += b'\0' # separator of singular and plural
is_plural = True
# Now we are in a msgstr section
elif l.startswith('msgstr'):
section = STR
if l.startswith('msgstr['):
if not is_plural:
print('plural without msgid_plural on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l.split(']', 1)[1]
if msgstr:
msgstr += b'\0' # Separator of the various plural forms
else:
if is_plural:
print('indexed msgstr required for plural on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l[6:]
# Skip empty lines
l = l.strip()
if not l:
continue
l = ast.literal_eval(l)
if section == ID:
msgid += l.encode(encoding)
elif section == STR:
msgstr += l.encode(encoding)
else:
print('Syntax error on %s:%d' % (infile, lno), \
'before:', file=sys.stderr)
print(l, file=sys.stderr)
sys.exit(1)
# Add last entry
if section == STR:
add(msgid, msgstr, fuzzy)
# Compute output
output = generate()
try:
open(outfile,"wb").write(output)
except IOError as msg:
print(msg, file=sys.stderr)
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
['help', 'version', 'output-file='])
except getopt.error as msg:
usage(1, msg)
outfile = None
# parse options
for opt, arg in opts:
if opt in ('-h', '--help'):
usage(0)
elif opt in ('-V', '--version'):
print("msgfmt.py", __version__)
sys.exit(0)
elif opt in ('-o', '--output-file'):
outfile = arg
# do it
if not args:
print('No input file given', file=sys.stderr)
print("Try `msgfmt --help' for more information.", file=sys.stderr)
return
for filename in args:
make(filename, outfile)
if __name__ == '__main__':
main()
|
