2000-09-01 05:10:08 -03:00
|
|
|
|
#! /usr/bin/env python
|
2003-05-09 05:59:17 -03:00
|
|
|
|
# -*- coding: iso-8859-1 -*-
|
2000-09-01 05:10:08 -03:00
|
|
|
|
# Written by Martin v. L<>wis <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:
|
2001-03-02 12:53:54 -04:00
|
|
|
|
-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).
|
|
|
|
|
|
2000-09-01 05:10:08 -03:00
|
|
|
|
-h
|
|
|
|
|
--help
|
|
|
|
|
Print this message and exit.
|
|
|
|
|
|
|
|
|
|
-V
|
|
|
|
|
--version
|
|
|
|
|
Display version information and exit.
|
|
|
|
|
"""
|
|
|
|
|
|
2001-03-02 12:53:54 -04:00
|
|
|
|
import os
|
2012-11-09 06:46:19 -04:00
|
|
|
|
import sys
|
|
|
|
|
import ast
|
2000-09-01 05:10:08 -03:00
|
|
|
|
import getopt
|
|
|
|
|
import struct
|
|
|
|
|
import array
|
|
|
|
|
|
2001-03-02 12:53:54 -04:00
|
|
|
|
__version__ = "1.1"
|
2000-09-01 05:10:08 -03:00
|
|
|
|
|
|
|
|
|
MESSAGES = {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def usage(code, msg=''):
|
|
|
|
|
print >> sys.stderr, __doc__
|
|
|
|
|
if msg:
|
|
|
|
|
print >> sys.stderr, msg
|
|
|
|
|
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
|
|
|
|
|
keys = MESSAGES.keys()
|
|
|
|
|
# the keys are sorted in the .mo file
|
|
|
|
|
keys.sort()
|
|
|
|
|
offsets = []
|
|
|
|
|
ids = strs = ''
|
|
|
|
|
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 + '\0'
|
|
|
|
|
strs += MESSAGES[id] + '\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
|
2003-05-09 05:59:17 -03:00
|
|
|
|
output = struct.pack("Iiiiiii",
|
|
|
|
|
0x950412deL, # Magic
|
2000-09-01 05:10:08 -03:00
|
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2001-03-02 12:53:54 -04:00
|
|
|
|
def make(filename, outfile):
|
2000-09-01 05:10:08 -03:00
|
|
|
|
ID = 1
|
|
|
|
|
STR = 2
|
|
|
|
|
|
2001-03-02 12:53:54 -04:00
|
|
|
|
# Compute .mo name from .po name and arguments
|
2000-09-01 05:10:08 -03:00
|
|
|
|
if filename.endswith('.po'):
|
|
|
|
|
infile = filename
|
|
|
|
|
else:
|
|
|
|
|
infile = filename + '.po'
|
2001-03-02 12:53:54 -04:00
|
|
|
|
if outfile is None:
|
|
|
|
|
outfile = os.path.splitext(infile)[0] + '.mo'
|
|
|
|
|
|
2000-09-01 05:10:08 -03:00
|
|
|
|
try:
|
|
|
|
|
lines = open(infile).readlines()
|
|
|
|
|
except IOError, msg:
|
|
|
|
|
print >> sys.stderr, msg
|
|
|
|
|
sys.exit(1)
|
2004-07-18 03:16:08 -03:00
|
|
|
|
|
2000-09-01 05:10:08 -03:00
|
|
|
|
section = None
|
|
|
|
|
fuzzy = 0
|
|
|
|
|
|
|
|
|
|
# Parse the catalog
|
|
|
|
|
lno = 0
|
|
|
|
|
for l in lines:
|
|
|
|
|
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
|
2006-04-06 03:44:33 -03:00
|
|
|
|
if l[:2] == '#,' and 'fuzzy' in l:
|
2000-09-01 05:10:08 -03:00
|
|
|
|
fuzzy = 1
|
|
|
|
|
# Skip comments
|
|
|
|
|
if l[0] == '#':
|
|
|
|
|
continue
|
|
|
|
|
# Now we are in a msgid section, output previous section
|
2010-06-04 15:04:42 -03:00
|
|
|
|
if l.startswith('msgid') and not l.startswith('msgid_plural'):
|
2000-09-01 05:10:08 -03:00
|
|
|
|
if section == STR:
|
|
|
|
|
add(msgid, msgstr, fuzzy)
|
|
|
|
|
section = ID
|
|
|
|
|
l = l[5:]
|
|
|
|
|
msgid = msgstr = ''
|
2010-06-04 15:04:42 -03:00
|
|
|
|
is_plural = False
|
|
|
|
|
# This is a message with plural forms
|
|
|
|
|
elif l.startswith('msgid_plural'):
|
|
|
|
|
if section != ID:
|
|
|
|
|
print >> sys.stderr, 'msgid_plural not preceeded by msgid on %s:%d' %\
|
|
|
|
|
(infile, lno)
|
|
|
|
|
sys.exit(1)
|
|
|
|
|
l = l[12:]
|
|
|
|
|
msgid += '\0' # separator of singular and plural
|
|
|
|
|
is_plural = True
|
2000-09-01 05:10:08 -03:00
|
|
|
|
# Now we are in a msgstr section
|
|
|
|
|
elif l.startswith('msgstr'):
|
|
|
|
|
section = STR
|
2010-06-04 15:04:42 -03:00
|
|
|
|
if l.startswith('msgstr['):
|
|
|
|
|
if not is_plural:
|
|
|
|
|
print >> sys.stderr, 'plural without msgid_plural on %s:%d' %\
|
|
|
|
|
(infile, lno)
|
|
|
|
|
sys.exit(1)
|
|
|
|
|
l = l.split(']', 1)[1]
|
|
|
|
|
if msgstr:
|
|
|
|
|
msgstr += '\0' # Separator of the various plural forms
|
|
|
|
|
else:
|
|
|
|
|
if is_plural:
|
|
|
|
|
print >> sys.stderr, 'indexed msgstr required for plural on %s:%d' %\
|
|
|
|
|
(infile, lno)
|
|
|
|
|
sys.exit(1)
|
|
|
|
|
l = l[6:]
|
2000-09-01 05:10:08 -03:00
|
|
|
|
# Skip empty lines
|
|
|
|
|
l = l.strip()
|
|
|
|
|
if not l:
|
|
|
|
|
continue
|
2012-11-09 06:46:19 -04:00
|
|
|
|
l = ast.literal_eval(l)
|
2000-09-01 05:10:08 -03:00
|
|
|
|
if section == ID:
|
|
|
|
|
msgid += l
|
|
|
|
|
elif section == STR:
|
|
|
|
|
msgstr += l
|
|
|
|
|
else:
|
|
|
|
|
print >> sys.stderr, 'Syntax error on %s:%d' % (infile, lno), \
|
|
|
|
|
'before:'
|
|
|
|
|
print >> sys.stderr, l
|
|
|
|
|
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,msg:
|
|
|
|
|
print >> sys.stderr, msg
|
2004-07-18 03:16:08 -03:00
|
|
|
|
|
2000-09-01 05:10:08 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
|
try:
|
2001-03-02 12:53:54 -04:00
|
|
|
|
opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
|
|
|
|
|
['help', 'version', 'output-file='])
|
2000-09-01 05:10:08 -03:00
|
|
|
|
except getopt.error, msg:
|
|
|
|
|
usage(1, msg)
|
|
|
|
|
|
2001-03-02 12:53:54 -04:00
|
|
|
|
outfile = None
|
2000-09-01 05:10:08 -03:00
|
|
|
|
# parse options
|
|
|
|
|
for opt, arg in opts:
|
|
|
|
|
if opt in ('-h', '--help'):
|
|
|
|
|
usage(0)
|
|
|
|
|
elif opt in ('-V', '--version'):
|
|
|
|
|
print >> sys.stderr, "msgfmt.py", __version__
|
|
|
|
|
sys.exit(0)
|
2001-03-02 12:53:54 -04:00
|
|
|
|
elif opt in ('-o', '--output-file'):
|
|
|
|
|
outfile = arg
|
2000-09-01 05:10:08 -03:00
|
|
|
|
# do it
|
|
|
|
|
if not args:
|
|
|
|
|
print >> sys.stderr, 'No input file given'
|
|
|
|
|
print >> sys.stderr, "Try `msgfmt --help' for more information."
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
for filename in args:
|
2001-03-02 12:53:54 -04:00
|
|
|
|
make(filename, outfile)
|
2000-09-01 05:10:08 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
main()
|