mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-26 18:29:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

Port to Python 3.

Browse source
This commit is contained in:
Martin v. Löwis 2010-06-04 18:40:55 +00:00
parent cb081b838f
commit b6b8110c48
1 changed files with 21 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

30
Tools/i18n/msgfmt.py
View file

@ -30,6 +30,7 @@ import os
import getopt import getopt
import struct import struct
import array import array
from email.parser import HeaderParser
__version__ = "1.1" __version__ = "1.1"
@ -59,13 +60,13 @@ def generate():
# the keys are sorted in the .mo file # the keys are sorted in the .mo file
keys = sorted(MESSAGES.keys()) keys = sorted(MESSAGES.keys())
offsets = [] offsets = []
ids = strs = '' ids = strs = b''
for id in keys: for id in keys:
# For each string, we need size and file offset. Each string is NUL # For each string, we need size and file offset. Each string is NUL
# terminated; the NUL does not count into the size. # terminated; the NUL does not count into the size.
offsets.append((len(ids), len(id), len(strs), len(MESSAGES[id]))) offsets.append((len(ids), len(id), len(strs), len(MESSAGES[id])))
ids += id + '\0' ids += id + b'\0'
strs += MESSAGES[id] + '\0' strs += MESSAGES[id] + b'\0'
output = '' output = ''
# The header is 7 32-bit unsigned integers. We don't use hash tables, so # The header is 7 32-bit unsigned integers. We don't use hash tables, so
# the keys start right after the index tables. # the keys start right after the index tables.
@ -108,7 +109,7 @@ def make(filename, outfile):
outfile = os.path.splitext(infile)[0] + '.mo' outfile = os.path.splitext(infile)[0] + '.mo'
try: try:
lines = open(infile).readlines() lines = open(infile, 'rb').readlines()
except IOError as msg: except IOError as msg:
print(msg, file=sys.stderr) print(msg, file=sys.stderr)
sys.exit(1) sys.exit(1)
@ -116,9 +117,14 @@ def make(filename, outfile):
section = None section = None
fuzzy = 0 fuzzy = 0
# Start off assuming Latin-1, so everything decodes without failure,
# until we know the exact encoding
encoding = 'latin-1'
# Parse the catalog # Parse the catalog
lno = 0 lno = 0
for l in lines: for l in lines:
l = l.decode(encoding)
lno += 1 lno += 1
# If we get a comment line after a msgstr, this is a new entry # If we get a comment line after a msgstr, this is a new entry
if l[0] == '#' and section == STR: if l[0] == '#' and section == STR:
@ -135,9 +141,15 @@ def make(filename, outfile):
if l.startswith('msgid') and not l.startswith('msgid_plural'): if l.startswith('msgid') and not l.startswith('msgid_plural'):
if section == STR: if section == STR:
add(msgid, msgstr, fuzzy) 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 section = ID
l = l[5:] l = l[5:]
msgid = msgstr = '' msgid = msgstr = b''
is_plural = False is_plural = False
# This is a message with plural forms # This is a message with plural forms
elif l.startswith('msgid_plural'): elif l.startswith('msgid_plural'):
@ -146,7 +158,7 @@ def make(filename, outfile):
file=sys.stderr) file=sys.stderr)
sys.exit(1) sys.exit(1)
l = l[12:] l = l[12:]
msgid += '\0' # separator of singular and plural msgid += b'\0' # separator of singular and plural
is_plural = True is_plural = True
# Now we are in a msgstr section # Now we are in a msgstr section
elif l.startswith('msgstr'): elif l.startswith('msgstr'):
@ -158,7 +170,7 @@ def make(filename, outfile):
sys.exit(1) sys.exit(1)
l = l.split(']', 1)[1] l = l.split(']', 1)[1]
if msgstr: if msgstr:
msgstr += '\0' # Separator of the various plural forms msgstr += b'\0' # Separator of the various plural forms
else: else:
if is_plural: if is_plural:
print(sys.stderr, 'indexed msgstr required for plural on %s:%d' % (infile, lno), print(sys.stderr, 'indexed msgstr required for plural on %s:%d' % (infile, lno),
@ -172,9 +184,9 @@ def make(filename, outfile):
# XXX: Does this always follow Python escape semantics? # XXX: Does this always follow Python escape semantics?
l = eval(l) l = eval(l)
if section == ID: if section == ID:
msgid += l msgid += l.encode(encoding)
elif section == STR: elif section == STR:
msgstr += l msgstr += l.encode(encoding)
else: else:
print('Syntax error on %s:%d' % (infile, lno), \ print('Syntax error on %s:%d' % (infile, lno), \
'before:', file=sys.stderr) 'before:', file=sys.stderr)