/usr/share/pyshared/translate/convert/csv2tbx.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 | #!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright 2006-2007 Zuza Software Foundation
#
# This file is part of translate.
#
# translate 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.
#
# translate 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/>.
"""Convert Comma-Separated Value (.csv) files to a TermBase eXchange (.tbx)
glossary file
See: http://docs.translatehouse.org/projects/translate-toolkit/en/latest/commands/csv2tbx.html
for examples and usage instructions
"""
from translate.storage import tbx
from translate.storage import csvl10n
class csv2tbx:
"""a class that takes translations from a .csv file and puts them in a
.tbx file"""
def __init__(self, charset=None):
"""construct the converter..."""
self.charset = charset
def convertfile(self, csvfile):
"""converts a csvfile to a tbxfile, and returns it. uses templatepo
if given at construction"""
mightbeheader = True
self.tbxfile = tbx.tbxfile()
for csvunit in csvfile.units:
if mightbeheader:
# ignore typical header strings...
mightbeheader = False
if csvunit.match_header():
continue
if (len(csvunit.location.strip()) == 0 and
csvunit.source.find("Content-Type:") != -1):
continue
term = tbx.tbxunit.buildfromunit(csvunit)
# TODO: we might want to get the location or other information
# from CSV
self.tbxfile.addunit(term)
return self.tbxfile
def convertcsv(inputfile, outputfile, templatefile, charset=None,
columnorder=None):
"""reads in inputfile using csvl10n, converts using csv2tbx, writes to
outputfile"""
inputstore = csvl10n.csvfile(inputfile, fieldnames=columnorder)
convertor = csv2tbx(charset=charset)
outputstore = convertor.convertfile(inputstore)
if len(outputstore.units) == 0:
return 0
outputfile.write(str(outputstore))
return 1
def main():
from translate.convert import convert
formats = {
("csv", "tbx"): ("tbx", convertcsv),
("csv", None): ("tbx", convertcsv),
}
parser = convert.ConvertOptionParser(formats, usetemplates=False,
description=__doc__)
parser.add_option("", "--charset", dest="charset", default=None,
help="set charset to decode from csv files", metavar="CHARSET"
)
parser.add_option("", "--columnorder", dest="columnorder", default=None,
help="specify the order and position of columns (comment,source,target)"
)
parser.passthrough.append("charset")
parser.passthrough.append("columnorder")
parser.run()
if __name__ == '__main__':
main()
|