/usr/share/pyshared/translate/tools/posegment.py is in translate-toolkit 1.10.0-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright 2008-2009 Zuza Software Foundation
#
# This file is part of the Translate Toolkit.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.
"""Segment Gettext PO, XLIFF and TMX localization files at the sentence level.
See: http://docs.translatehouse.org/projects/translate-toolkit/en/latest/commands/posegment.html
for examples and usage instructions.
"""
from translate.storage import factory
from translate.lang import factory as lang_factory
class segment:
def __init__(self, sourcelang, targetlang, stripspaces=True, onlyaligned=False):
self.sourcelang = sourcelang
self.targetlang = targetlang
self.stripspaces = stripspaces
self.onlyaligned = onlyaligned
def segmentunit(self, unit):
if unit.isheader() or unit.hasplural():
return [unit]
sourcesegments = self.sourcelang.sentences(unit.source, strip=self.stripspaces)
targetsegments = self.targetlang.sentences(unit.target, strip=self.stripspaces)
if unit.istranslated() and (len(sourcesegments) != len(targetsegments)):
if not self.onlyaligned:
return [unit]
else:
return None
# We could do more here to check if the lengths correspond more or less,
# certain quality checks are passed, etc. But for now this is a good
# start.
units = []
for i in range(len(sourcesegments)):
newunit = unit.copy()
newunit.source = sourcesegments[i]
if not unit.istranslated():
newunit.target = ""
else:
newunit.target = targetsegments[i]
units.append(newunit)
return units
def convertstore(self, fromstore):
tostore = type(fromstore)()
for unit in fromstore.units:
newunits = self.segmentunit(unit)
if newunits:
for newunit in newunits:
tostore.addunit(newunit)
return tostore
def segmentfile(inputfile, outputfile, templatefile, sourcelanguage="en", targetlanguage=None, stripspaces=True, onlyaligned=False):
"""reads in inputfile, segments it then, writes to outputfile"""
# note that templatefile is not used, but it is required by the converter...
inputstore = factory.getobject(inputfile)
if inputstore.isempty():
return 0
sourcelang = lang_factory.getlanguage(sourcelanguage)
targetlang = lang_factory.getlanguage(targetlanguage)
convertor = segment(sourcelang, targetlang, stripspaces=stripspaces, onlyaligned=onlyaligned)
outputstore = convertor.convertstore(inputstore)
outputfile.write(str(outputstore))
return 1
def main():
from translate.convert import convert
formats = {"po": ("po", segmentfile), "xlf": ("xlf", segmentfile), "tmx": ("tmx", segmentfile)}
parser = convert.ConvertOptionParser(formats, usepots=True, description=__doc__)
parser.add_option("-l", "--language", dest="targetlanguage", default=None,
help="the target language code", metavar="LANG")
parser.add_option("", "--source-language", dest="sourcelanguage", default=None,
help="the source language code (default 'en')", metavar="LANG")
parser.passthrough.append("sourcelanguage")
parser.passthrough.append("targetlanguage")
parser.add_option("", "--keepspaces", dest="stripspaces", action="store_false",
default=True, help="Disable automatic stripping of whitespace")
parser.passthrough.append("stripspaces")
parser.add_option("", "--only-aligned", dest="onlyaligned", action="store_true",
default=False, help="Removes units where sentence number does not correspond")
parser.passthrough.append("onlyaligned")
parser.run()
if __name__ == '__main__':
main()
|