2014-09-19 18:10:09 +00:00
|
|
|
#!/usr/bin/env python
|
|
|
|
# Written by Martin v. Lwis <loewis@informatik.hu-berlin.de>
|
|
|
|
# Plural forms support added by alexander smishlajev <alex@tycobka.lv>
|
|
|
|
"""
|
|
|
|
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.
|
|
|
|
"""
|
2024-09-08 11:36:41 +00:00
|
|
|
|
2014-09-22 21:15:33 +00:00
|
|
|
import array
|
2015-10-23 23:58:14 +00:00
|
|
|
import ast
|
2014-09-19 18:10:09 +00:00
|
|
|
import getopt
|
2014-09-22 21:15:33 +00:00
|
|
|
import os
|
2014-09-19 18:10:09 +00:00
|
|
|
import struct
|
2014-09-22 21:15:33 +00:00
|
|
|
import sys
|
2014-09-19 18:10:09 +00:00
|
|
|
|
2017-02-12 11:26:31 +00:00
|
|
|
__version__ = '1.2'
|
2014-09-19 18:10:09 +00:00
|
|
|
|
|
|
|
MESSAGES = {}
|
|
|
|
|
|
|
|
|
|
|
|
def usage(ecode, msg=''):
|
|
|
|
"""
|
|
|
|
Print usage and msg and exit with given code.
|
|
|
|
"""
|
2016-10-18 05:32:43 +00:00
|
|
|
print(__doc__, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
if msg:
|
2016-10-18 05:32:43 +00:00
|
|
|
print(msg, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
sys.exit(ecode)
|
|
|
|
|
|
|
|
|
|
|
|
def add(msgid, transtr, fuzzy):
|
|
|
|
"""
|
|
|
|
Add a non-fuzzy translation to the dictionary.
|
|
|
|
"""
|
2017-03-17 01:04:11 +00:00
|
|
|
if not fuzzy and transtr and not transtr.startswith('\x00'):
|
2014-09-19 18:10:09 +00:00
|
|
|
MESSAGES[msgid] = transtr
|
|
|
|
|
|
|
|
|
|
|
|
def generate():
|
|
|
|
"""
|
|
|
|
Return the generated output.
|
|
|
|
"""
|
|
|
|
# the keys are sorted in the .mo file
|
2017-03-16 21:39:57 +00:00
|
|
|
keys = sorted(MESSAGES)
|
2014-09-19 18:10:09 +00:00
|
|
|
offsets = []
|
|
|
|
ids = strs = ''
|
|
|
|
for _id in keys:
|
2017-03-17 01:04:11 +00:00
|
|
|
# For each string, we need size and file offset when encoded. Each string is NUL
|
2014-09-19 18:10:09 +00:00
|
|
|
# terminated; the NUL does not count into the size.
|
2018-10-02 14:39:51 +00:00
|
|
|
offsets.append(
|
|
|
|
(
|
|
|
|
len(ids.encode('utf8')),
|
|
|
|
len(_id.encode('utf8')),
|
|
|
|
len(strs.encode('utf8')),
|
|
|
|
len(MESSAGES[_id].encode('utf8')),
|
|
|
|
)
|
|
|
|
)
|
2017-03-17 01:04:11 +00:00
|
|
|
ids += _id + '\x00'
|
|
|
|
strs += MESSAGES[_id] + '\x00'
|
2017-02-12 11:26:31 +00:00
|
|
|
|
2014-09-19 18:10:09 +00:00
|
|
|
# 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
|
2018-10-02 14:39:51 +00:00
|
|
|
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
|
2021-12-25 12:34:49 +00:00
|
|
|
output += array.array('i', offsets).tobytes()
|
2017-03-17 01:04:11 +00:00
|
|
|
output += ids.encode('utf8')
|
|
|
|
output += strs.encode('utf8')
|
2014-09-19 18:10:09 +00:00
|
|
|
return output
|
|
|
|
|
|
|
|
|
|
|
|
def make(filename, outfile):
|
|
|
|
section_id = 1
|
|
|
|
section_str = 2
|
|
|
|
global MESSAGES
|
|
|
|
MESSAGES = {}
|
|
|
|
|
|
|
|
# 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:
|
2021-12-28 20:20:57 +00:00
|
|
|
with open(infile, encoding='utf8') as _file:
|
2016-10-11 10:26:52 +00:00
|
|
|
lines = _file.readlines()
|
2021-12-28 20:20:57 +00:00
|
|
|
except OSError as msg:
|
2016-10-18 05:32:43 +00:00
|
|
|
print(msg, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
sys.exit(1)
|
|
|
|
|
|
|
|
section = None
|
|
|
|
fuzzy = 0
|
|
|
|
|
|
|
|
# Parse the catalog
|
|
|
|
msgid = msgstr = ''
|
|
|
|
lno = 0
|
2017-10-29 11:39:52 +00:00
|
|
|
for line in lines:
|
2014-09-19 18:10:09 +00:00
|
|
|
lno += 1
|
|
|
|
# If we get a comment line after a msgstr, this is a new entry
|
2017-10-29 11:39:52 +00:00
|
|
|
if line[0] == '#' and section == section_str:
|
2014-09-19 18:10:09 +00:00
|
|
|
add(msgid, msgstr, fuzzy)
|
|
|
|
section = None
|
|
|
|
fuzzy = 0
|
|
|
|
# Record a fuzzy mark
|
2017-10-29 11:39:52 +00:00
|
|
|
if line[:2] == '#,' and (line.find('fuzzy') >= 0):
|
2014-09-19 18:10:09 +00:00
|
|
|
fuzzy = 1
|
|
|
|
# Skip comments
|
2017-10-29 11:39:52 +00:00
|
|
|
if line[0] == '#':
|
2014-09-19 18:10:09 +00:00
|
|
|
continue
|
|
|
|
# Start of msgid_plural section, separate from singular form with \0
|
2017-10-29 11:39:52 +00:00
|
|
|
if line.startswith('msgid_plural'):
|
2017-03-17 01:04:11 +00:00
|
|
|
msgid += '\x00'
|
2017-10-29 11:39:52 +00:00
|
|
|
line = line[12:]
|
2014-09-19 18:10:09 +00:00
|
|
|
# Now we are in a msgid section, output previous section
|
2017-10-29 11:39:52 +00:00
|
|
|
elif line.startswith('msgid'):
|
2014-09-19 18:10:09 +00:00
|
|
|
if section == section_str:
|
|
|
|
add(msgid, msgstr, fuzzy)
|
|
|
|
section = section_id
|
2017-10-29 11:39:52 +00:00
|
|
|
line = line[5:]
|
2014-09-19 18:10:09 +00:00
|
|
|
msgid = msgstr = ''
|
|
|
|
# Now we are in a msgstr section
|
2017-10-29 11:39:52 +00:00
|
|
|
elif line.startswith('msgstr'):
|
2014-09-19 18:10:09 +00:00
|
|
|
section = section_str
|
2017-10-29 11:39:52 +00:00
|
|
|
line = line[6:]
|
2014-09-19 18:10:09 +00:00
|
|
|
# Check for plural forms
|
2017-10-29 11:39:52 +00:00
|
|
|
if line.startswith('['):
|
2014-09-19 18:10:09 +00:00
|
|
|
# Separate plural forms with \0
|
2017-10-29 11:39:52 +00:00
|
|
|
if not line.startswith('[0]'):
|
2017-03-17 01:04:11 +00:00
|
|
|
msgstr += '\x00'
|
2014-09-19 18:10:09 +00:00
|
|
|
# Ignore the index - must come in sequence
|
2018-10-02 14:39:51 +00:00
|
|
|
line = line[line.index(']') + 1 :]
|
2014-09-19 18:10:09 +00:00
|
|
|
# Skip empty lines
|
2017-10-29 11:39:52 +00:00
|
|
|
line = line.strip()
|
|
|
|
if not line:
|
2014-09-19 18:10:09 +00:00
|
|
|
continue
|
2017-10-29 11:39:52 +00:00
|
|
|
line = ast.literal_eval(line)
|
2014-09-19 18:10:09 +00:00
|
|
|
if section == section_id:
|
2017-10-29 11:39:52 +00:00
|
|
|
msgid += line
|
2014-09-19 18:10:09 +00:00
|
|
|
elif section == section_str:
|
2017-10-29 11:39:52 +00:00
|
|
|
msgstr += line
|
2014-09-19 18:10:09 +00:00
|
|
|
else:
|
2016-10-18 05:32:43 +00:00
|
|
|
print('Syntax error on %s:%d' % (infile, lno), 'before:', file=sys.stderr)
|
2017-10-29 11:39:52 +00:00
|
|
|
print(line, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
sys.exit(1)
|
|
|
|
# Add last entry
|
|
|
|
if section == section_str:
|
|
|
|
add(msgid, msgstr, fuzzy)
|
|
|
|
|
|
|
|
# Compute output
|
|
|
|
output = generate()
|
|
|
|
|
|
|
|
try:
|
2016-11-03 21:26:46 +00:00
|
|
|
with open(outfile, 'wb') as _file:
|
2016-10-11 10:26:52 +00:00
|
|
|
_file.write(output)
|
2021-12-28 20:20:57 +00:00
|
|
|
except OSError as msg:
|
2016-10-18 05:32:43 +00:00
|
|
|
print(msg, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
try:
|
2018-10-02 14:39:51 +00:00
|
|
|
opts, args = getopt.getopt(
|
|
|
|
sys.argv[1:], 'hVo:', ['help', 'version', 'output-file=']
|
|
|
|
)
|
2016-10-18 05:32:43 +00:00
|
|
|
except getopt.error as msg:
|
2014-09-19 18:10:09 +00:00
|
|
|
usage(1, msg)
|
|
|
|
|
|
|
|
outfile = None
|
|
|
|
# parse options
|
|
|
|
for opt, arg in opts:
|
|
|
|
if opt in ('-h', '--help'):
|
|
|
|
usage(0)
|
|
|
|
elif opt in ('-V', '--version'):
|
2016-11-03 21:26:46 +00:00
|
|
|
print('msgfmt.py', __version__, file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
sys.exit(0)
|
|
|
|
elif opt in ('-o', '--output-file'):
|
|
|
|
outfile = arg
|
|
|
|
# do it
|
|
|
|
if not args:
|
2016-10-18 05:32:43 +00:00
|
|
|
print('No input file given', file=sys.stderr)
|
2016-11-13 15:09:30 +00:00
|
|
|
print('Try `msgfmt --help` for more information.', file=sys.stderr)
|
2014-09-19 18:10:09 +00:00
|
|
|
return
|
|
|
|
|
|
|
|
for filename in args:
|
|
|
|
make(filename, outfile)
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
2007-09-16 01:24:08 +00:00
|
|
|
main()
|