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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
#!/usr/bin/python3
# vim:se tw=0 sts=4 ts=4 et ai:
"""
Copyright © 2024 Osamu Aoki
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
"""
import sys
import argparse
import collections
import xml.etree.ElementTree as ET
# You must install python3-polib package
import polib
#######################################################################
# PO data XML analyzer class
#######################################################################
class XMLPOEntry:
def __init__(self, **kwargs):
self.linenum = kwargs.get("linenum", 0)
self.tcomment = kwargs.get("tcomment", "")
self.msgid = kwargs.get("msgid", "")
self.msgstr = kwargs.get("msgstr", "")
self.skip_fuzzy = kwargs.get("skip_fuzzy", True)
self.skip_obsolete = kwargs.get("skip_obsolete", True)
self.mask_entity = kwargs.get("mask_entity", True)
self.mask_namespace = kwargs.get("mask_namespace", True)
self.check_skip_tag_match = kwargs.get("check_skip_tag_match", True)
self.xmsgid = self.msgid
self.xmsgstr = self.msgstr
if self.mask_entity:
self.xmsgid = self.xmsgid.replace("&", "_")
self.xmsgstr = self.xmsgstr.replace("&", "_")
if self.mask_namespace:
self.xmsgid = self.xmsgid.replace("xl:href=", "xl_href=")
self.xmsgstr = self.xmsgstr.replace("xl:href=", "xl_href=")
# msgid xml analyze
self.xml_msgid_err = None
xml_msgid = ET.fromstring("<msg></msg>")
try:
xml_msgid = ET.fromstring("<msg>" + self.xmsgid + "</msg>")
except ET.ParseError as err:
# look for error position
col = max(err.position[1] - len("<msg>"), 0)
self.xml_msgid_err = polib.escape(self.msgid[:col]) + '"<<< ERROR'
except Exception as err:
self.xml_msgid_err = "{} error: {}".format(type(err), err)
self.xml_msgid_tags = collections.Counter(
[element.tag for element in xml_msgid.iter()]
)
del self.xml_msgid_tags["msg"]
# msgstr xml analyz
self.xml_msgstr_err = None
xml_msgstr = ET.fromstring("<msg></msg>")
try:
xml_msgstr = ET.fromstring("<msg>" + self.xmsgstr + "</msg>")
except ET.ParseError as err:
# look for error position
col = max(err.position[1] - len("<msg>"), 0)
self.xml_msgstr_err = polib.escape(self.msgstr[:col]) + '"<<< ERROR'
except Exception as err:
self.xml_msgstr_err = "{} error: {}".format(type(err), err)
self.xml_msgstr_tags = collections.Counter(
[element.tag for element in xml_msgstr.iter()]
)
del self.xml_msgstr_tags["msg"]
return
def is_unmatched_xml(self):
if self.msgstr == "":
# ignore not-yet-translated data
return False
elif self.xml_msgid_err is not None:
# ignore non-valid XML in msgid
return False
elif self.xml_msgstr_err is not None:
# ignore non-valid XML in msgstr
return False
elif "skip-tag-match" in self.tcomment and self.check_skip_tag_match:
# ignore data with "skip-tag-match" in its translator comment
return False
elif self.xml_msgid_tags == self.xml_msgstr_tags:
return False
else:
return True
#
def print_error(self):
if self.xml_msgid_err is not None:
print("E: msgid XML error at {}".format(self.linenum))
print(" {}".format(self.xml_msgid_err))
if self.xml_msgstr_err is not None:
print("E: msgstr XML error at {}".format(self.linenum))
print(" {}".format(self.xml_msgstr_err))
if self.xml_msgid_err is not None or self.xml_msgstr_err is not None:
print(' msgid "{}"'.format(polib.escape(self.msgid)))
print(' msgstr "{}"'.format(polib.escape(self.msgstr)))
print()
def print_unmatched_tags(self):
# unmatchd tags
if self.is_unmatched_xml() is True:
print("W: unmatched XML tag at {}".format(self.linenum))
print(" msgid_tags = {}".format(self.xml_msgid_tags))
print(" msgstr_tags = {}".format(self.xml_msgstr_tags))
print(' msgid "{}"'.format(polib.escape(self.msgid)))
print(' msgstr "{}"'.format(polib.escape(self.msgstr)))
print()
return
#######################################################################
# main: parse command line parser
#######################################################################
def main():
parser = argparse.ArgumentParser(
description="""\
analyzer for po-file
copyright 2024 Osamu Aoki <osamu@debian.org>
license: MIT
"""
)
parser.add_argument(
"-f",
"--include-fuzzy",
action="store_true",
default=False,
help="force to include fuzzy PO entries",
)
parser.add_argument(
"-o",
"--include-obsolete",
action="store_true",
default=False,
help="force to include obsolete PO entries",
)
parser.add_argument(
"-t",
"--ignore-skip-tag-match",
action="store_true",
default=False,
help="force to ignore skip-tag-match in translator comment",
)
parser.add_argument(
"-e",
"--expose-entity",
action="store_true",
default=False,
help="force to disable masking of '&' by '_' (expose entity)",
)
parser.add_argument(
"-n",
"--expose-namespace",
action="store_true",
default=False,
help="force to disable masking of 'xl:href=' by 'xl_href=' (expose namespace)",
)
parser.add_argument("pofile", help="po file to be analyzed")
#######################################################################
# generate argument parser instance
#######################################################################
args = parser.parse_args()
#######################################################################
print("I: Process pofile='{}'".format(args.pofile))
print()
try:
po = polib.pofile(args.pofile)
except Exception as err:
print("{} error: {} for PO file='{}'".format(type(err), err, args.pofile))
sys.exit(1)
error_count = 0
warn_count = 0
for entry in po:
if entry.fuzzy and not args.include_fuzzy:
continue
if entry.obsolete and not args.include_obsolete:
continue
xmlentry = XMLPOEntry(
linenum=entry.linenum,
tcomment=entry.tcomment,
fuzzy=entry.fuzzy,
obsolete=entry.obsolete,
msgid=entry.msgid,
msgstr=entry.msgstr,
mask_entity=not args.expose_entity,
mask_namespace=not args.expose_namespace,
check_skip_tag_match=not args.ignore_skip_tag_match,
)
xmlentry.print_error()
xmlentry.print_unmatched_tags()
if (
xmlentry.xml_msgid_err is not None
or xmlentry.xml_msgstr_err is not None
):
error_count += 1
if xmlentry.is_unmatched_xml() is True:
warn_count += 1
print("E: XML markup error counts = {}".format(error_count))
print("W: XML unmatched tag counts = {}".format(warn_count))
sys.exit(error_count + warn_count)
#######################################################################
# Test code
#######################################################################
if __name__ == "__main__":
main()
# vim:set sw=4 sts=4:
|
