File: xliff_parser.py

package info (click to toggle)
python-odf 1.3.4%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 6,356 kB
  • ctags: 1,902
  • sloc: python: 21,654; makefile: 352; sh: 10; xml: 2
file content (169 lines) | stat: -rw-r--r-- 5,393 bytes parent folder | download | duplicates (2)
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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
# -*- coding: utf-8 -*-
# Copyright (C) 2000-2004  Juan David Ibáñez Palomar <jdavid@itaapy.com>
#               2003  Roberto Quero, Eduardo Corrales
#               2004  Søren Roug
#
# 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, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.

# NOTE:
# This parser doesn't understand the ALT-TRANS element.

from xml.sax.handler import ContentHandler
from xml.sax import *
from cStringIO import StringIO
from types import StringType, UnicodeType

#constants
_FILE_ATTRS = ['original', 'source-language', 'datatype', 'date',
          'target-language', 'product-name', 'product-version', 'build-num']
_PHASE_ATTRS = ['phase-name', 'process-name', 'tool', 'date', 'contact-name',
          'contact-email', 'company-name']


class XLIFFHandler(ContentHandler):
    """ This is used to parse the xliff file
    """

    def __init__(self):
        """constructor """
        self.__currentTag = ''
        self.__filetag = []
        self.__phase_group = []
        self.__source = 0
        self.__body = {}
        self.__data = []
        self.__inside_alttrans = 0
        self.__tuid = ''

    #functions related with <file> tag
    def getFileTag(self):
        return self.__filetag

    def setFileTag(self, dict):
        self.__filetag.extend(dict)

    #functions related with <phase-group> tag
    def getPhaseGroup(self):
        return self.__phase_group

    def setPhaseGroup(self, dict):
        self.__phase_group.append(dict)

    def getBody(self):
        return self.__body

    def setBody(self, key, value):
        self.__body[key] = value

    def startElement(self, name, attrs):
        self.__currentTag = name

        if name == 'alt-trans':
            self.__inside_alttrans = 1
        # Make the attributes available
        # Implicit assumption: There is only one <file> element.
        if name == 'file':
            tmp = attrs.items()
            for i in [elem for elem in attrs.keys() if elem not in _FILE_ATTRS]:
                tmp.remove((i, attrs[i]))
            self.setFileTag(tmp)

        if name == 'phase':
            tmp = attrs.items()
            for i in [elem for elem in attrs.keys() if elem not in _PHASE_ATTRS]:
                tmp.remove((i, attrs[i]))
            self.setPhaseGroup(tmp)

        if name == 'trans-unit':
            self.__tuid = attrs['id']
            self.__source = u''
            self.__target = u''
            self.__note = u''

    def endElement(self, name):
        if name == 'alt-trans':
            self.__inside_alttrans = 0

        if name == 'source' and self.__inside_alttrans == 0:
            content = u''.join(self.__data).strip()
            self.__data = []
            self.__source = content

        if name == 'target' and self.__inside_alttrans == 0:
            content = u''.join(self.__data).strip()
            self.__data = []
            self.__target = content

        if name == 'note' and self.__inside_alttrans == 0:
            content = u''.join(self.__data).strip()
            self.__data = []
            self.__note = content

        if name == 'trans-unit':
            self.setBody(self.__tuid, {'source':self.__source,
                'target':self.__target, 'note':self.__note})

        self.__currentTag = ''

    def characters(self, content):
        currentTag = self.__currentTag
        if currentTag in ( 'source', 'target', 'note'):
            self.__data.append(content)

class HandleXliffParsing:
    """ class for parse xliff files """

    def __init__(self):
        """ """
        pass

    def parseXLIFFSTring(self, xml_string):
        """ """
        chandler = XLIFFHandler()
        parser = make_parser()
        # Tell the parser to use our handler
        parser.setContentHandler(chandler)
        # Don't load the DTD from the Internet
        parser.setFeature(handler.feature_external_ges, 0)
        inpsrc = InputSource()
        inpsrc.setByteStream(StringIO(xml_string))
        try:
            parser.parse(inpsrc)
            return chandler
        except:
            return None

    def parseXLIFFFile(self, file):
        # Create a parser
        parser = make_parser()
        chandler = XLIFFHandler()
        # Tell the parser to use our handler
        parser.setContentHandler(chandler)
        # Don't load the DTD from the Internet
        parser.setFeature(handler.feature_external_ges, 0)
        inputsrc = InputSource()

        try:
            if type(file) is StringType:
                inputsrc.setByteStream(StringIO(file))
            else:
                filecontent = file.read()
                inputsrc.setByteStream(StringIO(filecontent))
            parser.parse(inputsrc)
            return chandler
        except:
            return None