summaryrefslogtreecommitdiff
path: root/l10ntools/scripts/po2lo
blob: 0f81ebc203e3e59267d6ddfe5d5a71b3db9bd144 (plain)
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
#!/usr/bin/env python
# Version: MPL 1.1 / GPLv3+ / LGPLv3+
#
# The contents of this file are subject to the Mozilla Public License Version
# 1.1 (the "License"); you may not use this file except in compliance with
# the License or as specified alternatively below. You may obtain a copy of
# the License at http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS" basis,
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
# for the specific language governing rights and limitations under the
# License.
#
# The Initial Developer of the Original Code is
#       Miklos Vajna <vmiklos@frugalware.org>
# Portions created by the Initial Developer are Copyright (C) 2011 the
# Initial Developer. All Rights Reserved.
#
# Major Contributor(s):
#
# For minor contributions see the git repository.
#
# Alternatively, the contents of this file may be used under the terms of
# either the GNU General Public License Version 3 or later (the "GPLv3+"), or
# the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
# in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
# instead of those above.

import getopt, sys, os, re

class Options:
    """Options of this script."""

    def __init__(self):
        self.input = None
        self.output = None
        self.language = None
        self.template = None

class Entry:
    """Represents a single line in an SDF file."""

    def __init__(self, items):
        self.items = items # list of 15 fields
        path = self.items[1].split('\\')
        self.po = "%s/%s/%s.po" % (options.input.replace('\\', '/'), self.items[0], "/".join(path[:-1]))
        prefix = ""
        if len(self.items[5]):
            prefix += "%s." % self.items[5]
        if len(self.items[3]):
            prefix += "%s." % self.items[3]
        self.keys = []
        # 10..13 are translation types
        for idx in range(10, 14):
            if len(self.items[idx]):
                t = {10:'text', 12:'quickhelptext', 13:'title'}[idx]
                self.keys.append((idx, self.sdf2po("%s#%s.%s%s" % (path[-1], self.items[4], prefix, t))))

    def translate(self, translations):
        """Translates text in the entry based on translations."""

        self.items[9] = options.language
        for idx, key in self.keys:
            try:
                self.items[idx] = translations.data[(self.po, key)]

                self.items[14] = "2002-02-02 02:02:02"
            except KeyError:
                pass
        self.items[14] = self.items[14].strip()

    def sdf2po(self, s):
        """Escapes special chars in po key names."""

        return s.translate(normalizetable)

class Template:
    """Represents a reference template in SDF format."""

    def __init__(self, path):
        sock = open(path)
        self.lines = []
        for line in sock:
            entry = Entry(line.split('\t'))
            if os.path.exists(entry.po):
                self.lines.append(entry)

    def translate(self, translations):
        """Translates entires in the template based on translations."""

        sock = open(options.output, "w")
        for line in self.lines:
            line.translate(translations)
            sock.write("\t".join(line.items)+"\r\n")
        sock.close()

class Translations:
    """Represents a set of .po files, containing translations."""

    def __init__(self):
        key = None
        self.data = {}
        for root, dirs, files in os.walk(options.input):
            for file in files:
                path = "%s/%s" % (root, file)
                sock = open(path)
                buf = []
                multiline = False
                fuzzy = False
                for line in sock:
                    if line.startswith("#: "):
                        key = line.strip()[3:]
                    elif line.startswith("#, fuzzy"):
                        fuzzy = True
                    elif line.startswith("msgstr "):
                        trans = line.strip()[8:-1]
                        if len(trans):
                            if fuzzy:
                                fuzzy = False
                            else:
                                self.setdata(path, key, trans)
                                multiline = False
                        else:
                            buf = []
                            buf.append(trans)
                            multiline = True
                    elif multiline and line.startswith('"'):
                        buf.append(line.strip()[1:-1])
                    elif multiline and not len(line.strip()) and len("".join(buf)):
                        if fuzzy:
                            fuzzy = False
                        else:
                            self.setdata(path, key, "".join(buf))
                        buf = []
                        multiline = False
                if multiline and len("".join(buf)) and not fuzzy:
                    self.setdata(path, key, "".join(buf))

    def setdata(self, path, key, s):
        """Sets the translation for a given path and key, handling (un)escaping
        as well."""
        if key:
            # unescape the po special chars
            s = s.replace('\\"', '"')
            if key.split('#')[0].endswith(".xhp"):
                s = self.escape_help_text(s)
            else:
                s = s.replace('\\\\', '\\')
            self.data[(path.replace('\\', '/'), key)] = s

    def escape_help_text(self, text):
        """Escapes the help text as it would be in an SDF file."""

        for tag in helptagre.findall(text):
            # <, >, " are only escaped in <[[:lower:]]> tags. Some HTML tags make it in in
            # lowercase so those are dealt with. Some LibreOffice help tags are not
            # escaped.
            escapethistag = False
            for escape_tag in ["ahelp", "link", "item", "emph", "defaultinline", "switchinline", "caseinline", "variable", "bookmark_value", "image", "embedvar", "alt"]:
                if tag.startswith("<%s" % escape_tag) or tag == "</%s>" % escape_tag:
                    escapethistag = True
            if tag in ["<br/>", "<help-id-missing/>"]:
                escapethistag = True
            if escapethistag:
                escaped_tag = ("\\<" + tag[1:-1] + "\\>").replace('"', '\\"')
                text = text.replace(tag, escaped_tag)
        return text

def main():
    """Main function of this script."""

    opts, args = getopt.getopt(sys.argv[1:], "si:o:l:t:", ["skipsource", "input=", "output=", "language=", "template="])
    for opt, arg in opts:
        if opt in ("-s", "--skipsource"):
            pass
        elif opt in ("-i", "--input"):
            options.input = arg.strip('/')
        elif opt in ("-o", "--output"):
            options.output = arg
        elif opt in ("-l", "--language"):
            options.language = arg
        elif opt in ("-t", "--template"):
            options.template = arg
    template = Template(options.template)
    translations = Translations()
    template.translate(translations)

# used by ecape_help_text
helptagre = re.compile('''<[/]??[a-z_\-]+?(?:| +[a-z]+?=".*?") *[/]??>''')

options = Options()

# used by sdf2po()
normalfilenamechars = "/#.0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
normalizetable = ""
for i in map(chr, range(256)):
    if i in normalfilenamechars:
        normalizetable += i
    else:
        normalizetable += "_"

if __name__ == "__main__":
    main()

# vim:set filetype=python shiftwidth=4 softtabstop=4 expandtab: