#! /opt/alt/python312/bin/python3.12
# 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. Currently it
does not handle plural forms but it does handle message contexts.
Usage: msgfmt.py [OPTIONS] filename.po
Specify the output file to write to. If omitted, output will go to a
file named filename.mo (based off the input file name).
Print this message and exit.
Display version information and exit.
from email.parser import HeaderParser
print(__doc__, file=sys.stderr)
print(msg, file=sys.stderr)
def add(ctxt, id, str, fuzzy):
"Add a non-fuzzy translation to the dictionary."
MESSAGES[b"%b\x04%b" % (ctxt, id)] = str
"Return the generated output."
# the keys are sorted in the .mo file
keys = sorted(MESSAGES.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])))
strs += MESSAGES[id] + b'\0'
# The header is 7 32-bit unsigned integers. We don't use hash tables, so
# the keys start right after the index tables.
keystart = 7*4+16*len(keys)
# and the values start after the keys
valuestart = keystart + len(ids)
# 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",
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).tobytes()
def make(filename, outfile):
# Compute .mo name from .po name and arguments
if filename.endswith('.po'):
infile = filename + '.po'
outfile = os.path.splitext(infile)[0] + '.mo'
with open(infile, 'rb') as f:
print(msg, file=sys.stderr)
# Start off assuming Latin-1, so everything decodes without failure,
# until we know the exact encoding
# If we get a comment line after a msgstr, this is a new entry
if l[0] == '#' and section == STR:
add(msgctxt, msgid, msgstr, fuzzy)
if l[:2] == '#,' and 'fuzzy' in l:
# Now we are in a msgid or msgctxt section, output previous section
if l.startswith('msgctxt'):
add(msgctxt, msgid, msgstr, fuzzy)
elif l.startswith('msgid') and not l.startswith('msgid_plural'):
add(msgctxt, msgid, msgstr, fuzzy)
# See whether there is an encoding declaration
charset = p.parsestr(msgstr.decode(encoding)).get_content_charset()
# This is a message with plural forms
elif l.startswith('msgid_plural'):
print('msgid_plural not preceded by msgid on %s:%d' % (infile, lno),
msgid += b'\0' # separator of singular and plural
# Now we are in a msgstr section
elif l.startswith('msgstr'):
if l.startswith('msgstr['):
print('plural without msgid_plural on %s:%d' % (infile, lno),
msgstr += b'\0' # Separator of the various plural forms
print('indexed msgstr required for plural on %s:%d' % (infile, lno),
msgctxt += l.encode(encoding)
msgid += l.encode(encoding)
msgstr += l.encode(encoding)
print('Syntax error on %s:%d' % (infile, lno), \
'before:', file=sys.stderr)
print(l, file=sys.stderr)
add(msgctxt, msgid, msgstr, fuzzy)
with open(outfile,"wb") as f:
print(msg, file=sys.stderr)
opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
['help', 'version', 'output-file='])
except getopt.error as msg:
if opt in ('-h', '--help'):
elif opt in ('-V', '--version'):
print("msgfmt.py", __version__)
elif opt in ('-o', '--output-file'):
print('No input file given', file=sys.stderr)
print("Try `msgfmt --help' for more information.", file=sys.stderr)
if __name__ == '__main__':
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
