~charith-h/caffeine/gnome3

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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
    Generate POT
    ~~~~~~~~~~~~

    Generate a pot file with all translations for PyGTK applications
    based on the organization idea I shared in my article about i18n
    in PyGTK applications.

    :copyright: 2006-2007 by Armin Ronacher.
    :license: GNU GPL, see LICENSE for more details.
"""
import os
import sys
from xml.dom import minidom
from compiler import parse, ast
from datetime import datetime

PO_HEADER = """#
# %(name)s Language File
#
msgid ""
msgstr ""
"Project-Id-Version: %(name)s %(version)s\\n"
"POT-Creation-Date: %(time)s\\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\\n"
"Language-Team: LANGUAGE <LL@li.org>\\n"
"MIME-Version: 1.0\\n"
"Content-Type: text/plain; charset=utf-8\\n"
"Content-Transfer-Encoding: utf-8\\n"
"Generated-By: %(filename)s\\n"\
"""

EMPTY_STRING = ''
EMPTY_LINE = ['""\n']
LINE_SHIFT = ['\\n"\n"']


class StringCollection(object):
    """Class for collecting strings."""

    def __init__(self, basename):
        self.db = {}
        self.order = []
        self.offset = len(basename)

    def feed(self, file, line, string):
        name = file[self.offset:].lstrip('/')
        if string not in self.db:
            self.db[string] = [(name, line)]
            self.order.append(string)
        else:
            self.db[string].append((name, line))

    def __iter__(self):
        for string in self.order:
            yield string, self.db[string]


def quote(s):
    """Quotes a given string so that it is useable in a .po file."""
    result = ['"']
    firstmatch = True
    for char in s:
        if char == '\n':
            if firstmatch:
                result = EMPTY_LINE + result
                firstmatch = False
            result += LINE_SHIFT
            continue
        if char in '\t"':
            result.append('\\')
        result.append(char)
    result.append('"')
    return EMPTY_STRING.join(result)


def scan_python_file(filename, calls):
    """Scan a python file for gettext calls."""
    def scan(nodelist):
        for node in nodelist:
            if isinstance(node, ast.CallFunc):
                handle = False
                for pos, n in enumerate(node):
                    if pos == 0:
                        if isinstance(n, ast.Name) and n.name in calls:
                            handle = True
                    elif pos == 1:
                        if handle:
                            if n.__class__ is ast.Const and \
                               isinstance(n.value, basestring):
                                yield n.lineno, n.value
                            break
                        else:
                            for line in scan([n]):
                                yield line
            elif hasattr(node, '__iter__'):
                for n in scan(node):
                    yield n

    fp = file(filename)
    try:
        try:
            return scan(parse(fp.read()))
        except:
            print >> sys.stderr, 'Syntax Error in file %r' % filename
    finally:
        fp.close()


def scan_glade_file(filename):
    """Scan a glade file for translatable strings."""
    try:
        doc = minidom.parse(filename)
    except:
        print >> sys.stderr, 'Syntax Error in file %r' % filename
    for element in doc.getElementsByTagName('property'):
        if element.getAttribute('translatable') == 'yes':
            data = element.firstChild.nodeValue
            if data and not data.startswith('gtk-'):
                yield data


def scan_tree(pathname, calls=['_']):
    """Scans a tree for translatable strings."""
    out = StringCollection(pathname)
    for folder, _, files in os.walk(pathname):
        for filename in files:
            filename = os.path.join(folder, filename)
            if filename.endswith('.py'):
                result = scan_python_file(filename, calls)
                if result is not None:
                    for lineno, string in result:
                        out.feed(filename, lineno, string)
            elif filename.endswith('.glade'):
                result = scan_glade_file(filename)
                if result is not None:
                    for string in result:
                        out.feed(filename, None, string)
    for line in out:
        yield line


def main():
    if len(sys.argv) != 5:
        print 'usage: %s <basefolder> <name> <version> <outputfile>' % sys.argv[0]
        sys.exit()
    output = sys.argv[4]
    output = open(output,'w')

    print >> output, PO_HEADER % {
        'time':     datetime.now(),
        'filename': sys.argv[0],
        'name':     sys.argv[2],
        'version':  sys.argv[3]
    }

    basepath = sys.argv[1]
    for string, occurrences in scan_tree(basepath):
        try:
            print >> output, 'msgid %s' % quote(string.encode("utf_8"))
        except Exception,data:
            print data
            #print >> output, 'msgid %s' % quote(string)

        else:
            for path, lineno in occurrences:
                print >> output,'#. file %r, line %s' % (path, lineno or '?')
            print >> output, 'msgstr ""'

    output.close()

if __name__ == '__main__':
    main()