1
by
This commit was manufactured by cvs2svn to create branch |
1 |
#! @PYTHON@
|
2 |
#
|
|
3 |
# transcheck - (c) 2002 by Simone Piunno <pioppo@ferrara.linux.it>
|
|
1030
by Mark Sapiro
bin/transcheck - copyright date. |
4 |
# Copyright (C) 2002-2007 by the Free Software Foundation, Inc.
|
1
by
This commit was manufactured by cvs2svn to create branch |
5 |
#
|
6 |
# This program is free software; you can redistribute it and/or modify it
|
|
7 |
# under the terms of the version 2.0 of the GNU General Public License as
|
|
8 |
# published by the Free Software Foundation.
|
|
9 |
#
|
|
10 |
# This program is distributed in the hope that it will be useful, but
|
|
11 |
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
|
|
12 |
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
13 |
# for more details.
|
|
14 |
#
|
|
15 |
# You should have received a copy of the GNU General Public License along
|
|
16 |
# with this program; if not, write to the Free Software Foundation, Inc.,
|
|
749
by tkikuchi
FSF office has moved to 51 Franklin Street. |
17 |
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
1
by
This commit was manufactured by cvs2svn to create branch |
18 |
|
19 |
"""
|
|
20 |
Check a given Mailman translation, making sure that variables and
|
|
21 |
tags referenced in translation are the same variables and tags in
|
|
22 |
the original templates and catalog.
|
|
23 |
||
24 |
Usage:
|
|
25 |
||
26 |
cd $MAILMAN_DIR
|
|
27 |
%(program)s [-q] <lang>
|
|
28 |
||
29 |
Where <lang> is your country code (e.g. 'it' for Italy) and -q is
|
|
30 |
to ask for a brief summary.
|
|
31 |
"""
|
|
32 |
||
33 |
import sys |
|
34 |
import re |
|
35 |
import os |
|
36 |
import getopt |
|
37 |
||
38 |
import paths |
|
39 |
from Mailman.i18n import _ |
|
40 |
||
41 |
program = sys.argv[0] |
|
42 |
||
43 |
||
44 |
||
45 |
def usage(code, msg=''): |
|
46 |
if code: |
|
47 |
fd = sys.stderr |
|
48 |
else: |
|
49 |
fd = sys.stdout |
|
50 |
print >> fd, _(__doc__) |
|
51 |
if msg: |
|
52 |
print >> fd, msg |
|
53 |
sys.exit(code) |
|
54 |
||
55 |
||
56 |
||
57 |
class TransChecker: |
|
58 |
"check a translation comparing with the original string"
|
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
59 |
def __init__(self, regexp, escaped=None): |
1
by
This commit was manufactured by cvs2svn to create branch |
60 |
self.dict = {} |
61 |
self.errs = [] |
|
62 |
self.regexp = re.compile(regexp) |
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
63 |
self.escaped = None |
64 |
if escaped: |
|
65 |
self.escaped = re.compile(escaped) |
|
1
by
This commit was manufactured by cvs2svn to create branch |
66 |
|
67 |
def checkin(self, string): |
|
68 |
"scan a string from the original file"
|
|
69 |
for key in self.regexp.findall(string): |
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
70 |
if self.escaped and self.escaped.match(key): |
71 |
continue
|
|
1
by
This commit was manufactured by cvs2svn to create branch |
72 |
if self.dict.has_key(key): |
73 |
self.dict[key] += 1 |
|
74 |
else: |
|
75 |
self.dict[key] = 1 |
|
76 |
||
77 |
def checkout(self, string): |
|
78 |
"scan a translated string"
|
|
79 |
for key in self.regexp.findall(string): |
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
80 |
if self.escaped and self.escaped.match(key): |
81 |
continue
|
|
1
by
This commit was manufactured by cvs2svn to create branch |
82 |
if self.dict.has_key(key): |
83 |
self.dict[key] -= 1 |
|
84 |
else: |
|
85 |
self.errs.append( |
|
86 |
"%(key)s was not found" % |
|
87 |
{ 'key' : key } |
|
88 |
)
|
|
89 |
||
90 |
def computeErrors(self): |
|
91 |
"check for differences between checked in and checked out"
|
|
92 |
for key in self.dict.keys(): |
|
93 |
if self.dict[key] < 0: |
|
94 |
self.errs.append( |
|
95 |
"Too much %(key)s" % |
|
96 |
{ 'key' : key } |
|
97 |
)
|
|
98 |
if self.dict[key] > 0: |
|
99 |
self.errs.append( |
|
100 |
"Too few %(key)s" % |
|
101 |
{ 'key' : key } |
|
102 |
)
|
|
103 |
return self.errs |
|
104 |
||
105 |
def status(self): |
|
106 |
if self.errs: |
|
107 |
return "FAILED" |
|
108 |
else: |
|
109 |
return "OK" |
|
110 |
||
111 |
def errorsAsString(self): |
|
112 |
msg = "" |
|
113 |
for err in self.errs: |
|
114 |
msg += " - %(err)s" % { 'err': err } |
|
115 |
return msg |
|
116 |
||
117 |
def reset(self): |
|
118 |
self.dict = {} |
|
119 |
self.errs = [] |
|
120 |
||
121 |
||
122 |
||
123 |
class POParser: |
|
124 |
"parse a .po file extracting msgids and msgstrs"
|
|
125 |
def __init__(self, filename=""): |
|
126 |
self.status = 0 |
|
127 |
self.files = [] |
|
128 |
self.msgid = "" |
|
129 |
self.msgstr = "" |
|
130 |
self.line = 1 |
|
131 |
self.f = None |
|
132 |
self.esc = { "n": "\n", "r": "\r", "t": "\t" } |
|
133 |
if filename: |
|
134 |
self.f = open(filename) |
|
135 |
||
136 |
def open(self, filename): |
|
137 |
self.f = open(filename) |
|
138 |
||
139 |
def close(self): |
|
140 |
self.f.close() |
|
141 |
||
142 |
def parse(self): |
|
143 |
"""States table for the finite-states-machine parser:
|
|
144 |
0 idle
|
|
145 |
1 filename-or-comment
|
|
146 |
2 msgid
|
|
147 |
3 msgstr
|
|
148 |
4 end
|
|
149 |
"""
|
|
150 |
# each time we can safely re-initialize those vars
|
|
151 |
self.files = [] |
|
152 |
self.msgid = "" |
|
153 |
self.msgstr = "" |
|
154 |
||
155 |
||
156 |
# can't continue if status == 4, this is a dead status
|
|
157 |
if self.status == 4: |
|
158 |
return 0 |
|
159 |
||
160 |
while 1: |
|
161 |
# continue scanning, char-by-char
|
|
162 |
c = self.f.read(1) |
|
163 |
if not c: |
|
164 |
# EOF -> maybe we have a msgstr to save?
|
|
165 |
self.status = 4 |
|
166 |
if self.msgstr: |
|
167 |
return 1 |
|
168 |
else: |
|
169 |
return 0 |
|
170 |
||
171 |
# keep the line count up-to-date
|
|
172 |
if c == "\n": |
|
173 |
self.line += 1 |
|
174 |
||
175 |
# a pound was detected the previous char...
|
|
176 |
if self.status == 1: |
|
177 |
if c == ":": |
|
178 |
# was a line of filenames
|
|
179 |
row = self.f.readline() |
|
180 |
self.files += row.split() |
|
181 |
self.line += 1 |
|
182 |
elif c == "\n": |
|
183 |
# was a single pount on the line
|
|
184 |
pass
|
|
185 |
else: |
|
186 |
# was a comment... discard
|
|
187 |
self.f.readline() |
|
188 |
self.line += 1 |
|
189 |
# in every case, we switch to idle status
|
|
190 |
self.status = 0; |
|
191 |
continue
|
|
192 |
||
193 |
# in idle status we search for a '#' or for a 'm'
|
|
194 |
if self.status == 0: |
|
195 |
if c == "#": |
|
196 |
# this could be a comment or a filename
|
|
197 |
self.status = 1; |
|
198 |
continue
|
|
199 |
elif c == "m": |
|
200 |
# this should be a msgid start...
|
|
201 |
s = self.f.read(4) |
|
202 |
assert s == "sgid" |
|
203 |
# so now we search for a '"'
|
|
204 |
self.status = 2 |
|
205 |
continue
|
|
206 |
# in idle only those other chars are possibile
|
|
207 |
assert c in [ "\n", " ", "\t" ] |
|
208 |
||
209 |
# searching for the msgid string
|
|
210 |
if self.status == 2: |
|
211 |
if c == "\n": |
|
212 |
# a double LF is not possible here
|
|
213 |
c = self.f.read(1) |
|
214 |
assert c != "\n" |
|
215 |
if c == "\"": |
|
216 |
# ok, this is the start of the string,
|
|
217 |
# now search for the end
|
|
218 |
while 1: |
|
219 |
c = self.f.read(1) |
|
220 |
if not c: |
|
221 |
# EOF, bailout
|
|
222 |
self.status = 4 |
|
223 |
return 0 |
|
224 |
if c == "\\": |
|
225 |
# a quoted char...
|
|
226 |
c = self.f.read(1) |
|
227 |
if self.esc.has_key(c): |
|
228 |
self.msgid += self.esc[c] |
|
229 |
else: |
|
230 |
self.msgid += c |
|
231 |
continue
|
|
232 |
if c == "\"": |
|
233 |
# end of string found
|
|
234 |
break
|
|
235 |
# a normal char, add it
|
|
236 |
self.msgid += c |
|
237 |
if c == "m": |
|
238 |
# this should be a msgstr identifier
|
|
239 |
s = self.f.read(5) |
|
240 |
assert s == "sgstr" |
|
241 |
# ok, now search for the msgstr string
|
|
242 |
self.status = 3 |
|
243 |
||
244 |
# searching for the msgstr string
|
|
245 |
if self.status == 3: |
|
246 |
if c == "\n": |
|
247 |
# a double LF is the end of the msgstr!
|
|
248 |
c = self.f.read(1) |
|
249 |
if c == "\n": |
|
250 |
# ok, time to go idle and return
|
|
251 |
self.status = 0 |
|
252 |
self.line += 1 |
|
253 |
return 1 |
|
254 |
if c == "\"": |
|
255 |
# start of string found
|
|
256 |
while 1: |
|
257 |
c = self.f.read(1) |
|
258 |
if not c: |
|
259 |
# EOF, bail out
|
|
260 |
self.status = 4 |
|
261 |
return 1 |
|
262 |
if c == "\\": |
|
263 |
# a quoted char...
|
|
264 |
c = self.f.read(1) |
|
265 |
if self.esc.has_key(c): |
|
1029
by Mark Sapiro
Corrected a long standing, mostly inconsequential error in bin/transcheck. |
266 |
self.msgstr += self.esc[c] |
1
by
This commit was manufactured by cvs2svn to create branch |
267 |
else: |
1029
by Mark Sapiro
Corrected a long standing, mostly inconsequential error in bin/transcheck. |
268 |
self.msgstr += c |
1
by
This commit was manufactured by cvs2svn to create branch |
269 |
continue
|
270 |
if c == "\"": |
|
271 |
# end of string
|
|
272 |
break
|
|
273 |
# a normal char, add it
|
|
274 |
self.msgstr += c |
|
275 |
||
276 |
||
277 |
||
278 |
||
279 |
def check_file(translatedFile, originalFile, html=0, quiet=0): |
|
280 |
"""check a translated template against the original one
|
|
281 |
search also <MM-*> tags if html is not zero"""
|
|
282 |
||
283 |
if html: |
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
284 |
c = TransChecker("(%%|%\([^)]+\)[0-9]*[sd]|</?MM-[^>]+>)", "^%%$") |
1
by
This commit was manufactured by cvs2svn to create branch |
285 |
else: |
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
286 |
c = TransChecker("(%%|%\([^)]+\)[0-9]*[sd])", "^%%$") |
1
by
This commit was manufactured by cvs2svn to create branch |
287 |
|
288 |
try: |
|
289 |
f = open(originalFile) |
|
290 |
except IOError: |
|
291 |
if not quiet: |
|
292 |
print " - Can'open original file " + originalFile |
|
293 |
return 1 |
|
294 |
||
295 |
while 1: |
|
296 |
line = f.readline() |
|
297 |
if not line: break |
|
298 |
c.checkin(line) |
|
299 |
||
300 |
f.close() |
|
301 |
||
302 |
try: |
|
303 |
f = open(translatedFile) |
|
304 |
except IOError: |
|
305 |
if not quiet: |
|
306 |
print " - Can'open translated file " + translatedFile |
|
307 |
return 1 |
|
308 |
||
309 |
while 1: |
|
310 |
line = f.readline() |
|
311 |
if not line: break |
|
312 |
c.checkout(line) |
|
313 |
||
314 |
f.close() |
|
315 |
||
316 |
n = 0 |
|
317 |
msg = "" |
|
318 |
for desc in c.computeErrors(): |
|
319 |
n +=1 |
|
320 |
if not quiet: |
|
321 |
print " - %(desc)s" % { 'desc': desc } |
|
322 |
return n |
|
323 |
||
324 |
||
325 |
||
326 |
def check_po(file, quiet=0): |
|
327 |
"scan the po file comparing msgids with msgstrs"
|
|
328 |
n = 0 |
|
329 |
p = POParser(file) |
|
26
by bwarsaw
Backporting various fixes and improvements from the trunk. |
330 |
c = TransChecker("(%%|%\([^)]+\)[0-9]*[sdu]|%[0-9]*[sdu])", "^%%$") |
1
by
This commit was manufactured by cvs2svn to create branch |
331 |
while p.parse(): |
332 |
if p.msgstr: |
|
333 |
c.reset() |
|
334 |
c.checkin(p.msgid) |
|
335 |
c.checkout(p.msgstr) |
|
336 |
for desc in c.computeErrors(): |
|
337 |
n += 1 |
|
338 |
if not quiet: |
|
339 |
print " - near line %(line)d %(file)s: %(desc)s" % { |
|
340 |
'line': p.line, |
|
341 |
'file': p.files, |
|
342 |
'desc': desc |
|
343 |
}
|
|
344 |
p.close() |
|
345 |
return n |
|
346 |
||
347 |
||
348 |
def main(): |
|
349 |
try: |
|
350 |
opts, args = getopt.getopt(sys.argv[1:], 'qh', ['quiet', 'help']) |
|
351 |
except getopt.error, msg: |
|
352 |
usage(1, msg) |
|
353 |
||
354 |
quiet = 0 |
|
355 |
for opt, arg in opts: |
|
356 |
if opt in ('-h', '--help'): |
|
357 |
usage(0) |
|
358 |
elif opt in ('-q', '--quiet'): |
|
359 |
quiet = 1 |
|
360 |
||
361 |
if len(args) <> 1: |
|
362 |
usage(1) |
|
363 |
||
364 |
lang = args[0] |
|
365 |
||
366 |
isHtml = re.compile("\.html$"); |
|
367 |
isTxt = re.compile("\.txt$"); |
|
368 |
||
369 |
numerrors = 0 |
|
370 |
numfiles = 0 |
|
371 |
try: |
|
372 |
files = os.listdir("templates/" + lang + "/") |
|
373 |
except: |
|
374 |
print "can't open templates/%s/" % lang |
|
375 |
for file in files: |
|
376 |
fileEN = "templates/en/" + file |
|
377 |
fileIT = "templates/" + lang + "/" + file |
|
378 |
errlist = [] |
|
379 |
if isHtml.search(file): |
|
380 |
if not quiet: |
|
381 |
print "HTML checking " + fileIT + "... " |
|
382 |
n = check_file(fileIT, fileEN, html=1, quiet=quiet) |
|
383 |
if n: |
|
384 |
numerrors += n |
|
385 |
numfiles += 1 |
|
386 |
elif isTxt.search(file): |
|
387 |
if not quiet: |
|
388 |
print "TXT checking " + fileIT + "... " |
|
389 |
n = check_file(fileIT, fileEN, html=0, quiet=quiet) |
|
390 |
if n: |
|
391 |
numerrors += n |
|
392 |
numfiles += 1 |
|
393 |
||
394 |
else: |
|
395 |
continue
|
|
396 |
||
397 |
file = "messages/" + lang + "/LC_MESSAGES/mailman.po" |
|
398 |
if not quiet: |
|
399 |
print "PO checking " + file + "... " |
|
400 |
n = check_po(file, quiet=quiet) |
|
401 |
if n: |
|
402 |
numerrors += n |
|
403 |
numfiles += 1 |
|
404 |
||
405 |
if quiet: |
|
406 |
print "%(errs)u warnings in %(files)u files" % { |
|
407 |
'errs': numerrors, |
|
408 |
'files': numfiles |
|
409 |
}
|
|
410 |
||
411 |
||
412 |
if __name__ == '__main__': |
|
413 |
main() |