Commit 63e19a76d1c5db059a3a228da410590c93f884ad - i18nspector

+2

-1

Makefile less more

17	17	# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
18	18	# SOFTWARE.
19	19
	20	PYTHON = python3
20	21	PREFIX = /usr/local
21	22	DESTDIR =
22	23

49	50
50	51	.PHONY: test
51	52	test:
52		python3 -c 'import nose; nose.main()' -v
	53	$(PYTHON) -c 'import nose; nose.main()' -v
53	54
54	55	# vim:ts=4 sw=4 noet

+100

-3

data/tags less more

24	24	This normally indicates an error in the plural form expression.
25	25	references =
26	26	http://www.gnu.org/software/gettext/manual/html_node/Plural-forms.html
	27
	28	[boilerplate-in-content-type]
	29	severity = important
	30	certainty = certain
	31	description =
	32	The Content-Type header field contains xgettext boilerplate.
	33	It should be in the form ``text/plain; charset=``\ encoding.
	34	references =
	35	http://www.gnu.org/software/gettext/manual/html_node/Header-Entry.html
27	36
28	37	[boilerplate-in-language-team]
29	38	severity = minor

98	107	references =
99	108	http://www.gnu.org/software/gettext/manual/html_node/Plural-forms.html
100	109
	110	[conflict-marker-in-header-entry]
	111	severity = serious
	112	certainty = certain
	113	description =
	114	The header contains a conflict marker (#-#-#-#-# … #-#-#-#-#).
	115	The conflict will have to be resolved manually.
	116	references =
	117	http://www.gnu.org/software/gettext/manual/html_node/Creating-Compendia.html#Creating-Compendia
	118
	119	[conflict-marker-in-translation]
	120	severity = serious
	121	certainty = possible
	122	description =
	123	One of the translated messages appear to contain a conflict marker (#-#-#-#-# … #-#-#-#-#).
	124	The conflict will have to be resolved manually.
	125	references =
	126	http://www.gnu.org/software/gettext/manual/html_node/Creating-Compendia.html#Creating-Compendia
	127
101	128	[date-from-future]
102	129	severity = normal
103	130	certainty = certain

105	132	The date refers to the future. As such, it's extremely unlikely to be correct.
106	133
107	134	[duplicate-header-field]
108		severity = serious
109		certainty = certain
	135	severity = minor
	136	certainty = wild-guess
110	137	description =
111	138	This file contains multiple header fields of the same name.
	139
	140	[duplicate-header-field-content-transfer-encoding]
	141	severity = pedantic
	142	certainty = certain
	143	description =
	144	This file contains multiple Content-Transfer-Encoding header fields.
	145
	146	[duplicate-header-field-content-type]
	147	severity = serious
	148	certainty = certain
	149	description =
	150	This file contains multiple Content-Type header fields.
	151
	152	[duplicate-header-field-date]
	153	severity = normal
	154	certainty = certain
	155	description =
	156	This file contains multiple date header fields of the same name.
	157
	158	[duplicate-header-field-language]
	159	severity = important
	160	certainty = certain
	161	description =
	162	This file contains multiple Language header fields.
	163
	164	[duplicate-header-field-language-team]
	165	severity = normal
	166	certainty = certain
	167	description =
	168	This file contains multiple Language-Team header fields.
	169
	170	[duplicate-header-field-last-translator]
	171	severity = normal
	172	certainty = certain
	173	description =
	174	This file contains multiple Last-Translator header fields.
	175
	176	[duplicate-header-field-mime-version]
	177	severity = pedantic
	178	certainty = certain
	179	description =
	180	This file contains multiple MIME-Version header fields.
	181
	182	[duplicate-header-field-plural-forms]
	183	severity = serious
	184	certainty = certain
	185	description =
	186	This file contains multiple Plural-Forms header fields.
	187
	188	[duplicate-header-field-project-id-version]
	189	severity = minor
	190	certainty = certain
	191	description =
	192	This file contains multiple Project-Id-Version header fields.
	193
	194	[duplicate-header-field-report-msgid-bugs-to]
	195	severity = normal
	196	certainty = certain
	197	description =
	198	This file contains multiple Report-Msgid-Bugs-To header fields.
112	199
113	200	[duplicate-message-definition]
114	201	severity = serious

130	217	shouldn't be included in this field.
131	218	references =
132	219	http://www.gnu.org/software/gettext/manual/html_node/Header-Entry.html
	220
	221	[fuzzy-header-entry]
	222	severity = pedantic
	223	certainty = certain
	224	description =
	225	The header entry is marked as fuzzy.
	226	To increase operability with very old (<< 0.11) msgfmt\ (1) versions,
	227	which didn't support fuzzy header entries, it shouldn't be marked as such.
	228	references =
	229	http://git.savannah.gnu.org/cgit/gettext.git/tree/NEWS?id=7808a2b730c4#n44
133	230
134	231	[inconsistent-leading-newlines]
135	232	severity = important

272	369	severity = minor
273	370	certainty = possible
274	371	description =
275		Language-Team and Last-Translator header fields contains the same e-mail
	372	Language-Team and Last-Translator header fields contain the same e-mail
276	373	address.
277	374
278	375	[language-variant-does-not-affect-translation]

+5

-1

doc/Makefile less more

	0	export LC_ALL=C
	1
0	2	rst2man = $(or $(shell which rst2man),rst2man.py)
1	3	exe = i18nspector
2	4

8	10	mv $(@).tmp $(@)
9	11
10	12	$(exe).1: $(exe).txt tags.txt
11		$(rst2man) < $(<) > $(@).tmp
	13	$(rst2man) --input-encoding=UTF-8:strict < $(<) > $(@).tmp
	14	sed -i -e 's/^[.]de1/.de/' $(@).tmp # work-around for http://bugs.debian.org/710678
	15	sed -i -e "s/$[a-z]$\\\$aq\([a-z]$/\1'\2/g" $(@).tmp # prefer ' to \(aq when used as an apostrophe
12	16	mv $(@).tmp $(@)
13	17
14	18	.PHONY: clean

+43

-0

doc/changelog less more

	0	i18nspector (0.10) unstable; urgency=low
	1
	2	* Summary of tag changes:
	3	+ Added:
	4	- boilerplate-in-content-type
	5	- conflict-marker-in-header-entry
	6	- conflict-marker-in-translation
	7	- duplicate-header-field-content-transfer-encoding
	8	- duplicate-header-field-content-type
	9	- duplicate-header-field-date
	10	- duplicate-header-field-language
	11	- duplicate-header-field-language-team
	12	- duplicate-header-field-last-translator
	13	- duplicate-header-field-mime-version
	14	- duplicate-header-field-plural-forms
	15	- duplicate-header-field-project-id-version
	16	- duplicate-header-field-report-msgid-bugs-to
	17	- fuzzy-header-entry
	18
	19	* Check for boilerplate (“charset=CHARSET”) in the Content-Type header
	20	field.
	21	* Check header field name syntax.
	22	* Overhaul duplicate header field detection.
	23	+ Emit duplicate-header-field only for non-standard fields. Downgrade
	24	duplicate-header-field to minor/wild-guess.
	25	+ Emit duplicate-header-field-$NAME for standard fields.
	26	+ Don't trust values of standard header fields if duplicates exist.
	27	* Check for conflict markers (“#-#-#-#-# … #-#-#-#-#”).
	28	* Check for fuzzy header entries.
	29	* Fix a typo in the language-team-equal-to-last-translator description.
	30	* Post-process the manual page, so that it can be more easily translated by
	31	po4a.
	32	* If iconv(3) is available in the C standard library, use it to implement
	33	encodings that are not implemented in the Python standard library.
	34	* Don't pass -s to iconv(1); it makes GNU iconv quieten errors, and other
	35	implementations don't have this option at all.
	36	* Improve the test suite:
	37	+ Add new tests.
	38	+ Make exception messages raised when a subprocess fails more readable.
	39	+ Make it possible to use a custom Python interpreter for “make test”.
	40
	41	-- Jakub Wilk <jwilk@jwilk.net> Sat, 15 Jun 2013 17:37:22 +0200
	42
0	43	i18nspector (0.9.2) unstable; urgency=low
1	44
2	45	* When emitting broken-encoding, don't output the whole file, but only the

+205

-32

doc/i18nspector.1 less more

0	0	.\" Man page generated from reStructuredText.
1	1	.
2		.TH I18NSPECTOR 1 "2013-06-08" "i18nspector 0.9.2" ""
	2	.TH I18NSPECTOR 1 "2013-06-15" "i18nspector 0.10" ""
3	3	.SH NAME
4	4	i18nspector \- checking tool for gettext POT, PO and MO files
5	5	.
6	6	.nr rst2man-indent-level 0
7	7	.
8		.de1 rstReportMargin
	8	.de rstReportMargin
9	9	\\$1 \\n[an-margin]
10	10	level \\n[rst2man-indent-level]
11	11	level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]

14	14	\\n[rst2man-indent1]
15	15	\\n[rst2man-indent2]
16	16	..
17		.de1 INDENT
	17	.de INDENT
18	18	.\" .rstReportMargin pre:
19	19	. RS \\$1
20	20	. nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]

76	76	.SS ancient\-date
77	77	.sp
78	78	The date refers to the time before the first GNU gettext release. As such,
79		it\(aqs extremely unlikely to be correct.
	79	it's extremely unlikely to be correct.
80	80	.sp
81	81	References:
82	82	.INDENT 0.0

128	128	important, possible
129	129	.UNINDENT
130	130	.UNINDENT
	131	.SS boilerplate\-in\-content\-type
	132	.sp
	133	The Content\-Type header field contains xgettext boilerplate.
	134	It should be in the form \fBtext/plain; charset=\fP\fIencoding\fP.
	135	.sp
	136	References:
	137	.INDENT 0.0
	138	.INDENT 3.5
	139	\fI\%http://www.gnu.org/software/gettext/manual/html_node/Header\-Entry.html\fP
	140	.UNINDENT
	141	.UNINDENT
	142	.sp
	143	Severity, certainty:
	144	.INDENT 0.0
	145	.INDENT 3.5
	146	important, certain
	147	.UNINDENT
	148	.UNINDENT
131	149	.SS boilerplate\-in\-language\-team
132	150	.sp
133	151	The Language\-Team header field contains xgettext boilerplate.

150	168	.SS boilerplate\-in\-last\-translator
151	169	.sp
152	170	The Last\-Translator header field contains xgettext boilerplate.
153		It should contain the last translator\(aqs name and email address.
	171	It should contain the last translator's name and email address.
154	172	.sp
155	173	References:
156	174	.INDENT 0.0

204	222	.UNINDENT
205	223	.SS broken\-encoding
206	224	.sp
207		Header fields and messages contained by this file couldn\(aqt be decoded to
	225	Header fields and messages contained by this file couldn't be decoded to
208	226	Unicode.
209	227	The usual cause of this is incorrect or missing encoding declaration.
210	228	.sp

265	283	important, possible
266	284	.UNINDENT
267	285	.UNINDENT
	286	.SS conflict\-marker\-in\-header\-entry
	287	.sp
	288	The header contains a conflict marker (\fB#\-#\-#\-#\-#\fP \fI…\fP \fB#\-#\-#\-#\-#\fP).
	289	The conflict will have to be resolved manually.
	290	.sp
	291	References:
	292	.INDENT 0.0
	293	.INDENT 3.5
	294	\fI\%http://www.gnu.org/software/gettext/manual/html_node/Creating\-Compendia.html#Creating\-Compendia\fP
	295	.UNINDENT
	296	.UNINDENT
	297	.sp
	298	Severity, certainty:
	299	.INDENT 0.0
	300	.INDENT 3.5
	301	serious, certain
	302	.UNINDENT
	303	.UNINDENT
	304	.SS conflict\-marker\-in\-translation
	305	.sp
	306	One of the translated messages appear to contain a conflict marker (\fB#\-#\-#\-#\-#\fP \fI…\fP \fB#\-#\-#\-#\-#\fP).
	307	The conflict will have to be resolved manually.
	308	.sp
	309	References:
	310	.INDENT 0.0
	311	.INDENT 3.5
	312	\fI\%http://www.gnu.org/software/gettext/manual/html_node/Creating\-Compendia.html#Creating\-Compendia\fP
	313	.UNINDENT
	314	.UNINDENT
	315	.sp
	316	Severity, certainty:
	317	.INDENT 0.0
	318	.INDENT 3.5
	319	serious, possible
	320	.UNINDENT
	321	.UNINDENT
268	322	.SS date\-from\-future
269	323	.sp
270		The date refers to the future. As such, it\(aqs extremely unlikely to be correct.
	324	The date refers to the future. As such, it's extremely unlikely to be correct.
271	325	.sp
272	326	Severity, certainty:
273	327	.INDENT 0.0

282	336	Severity, certainty:
283	337	.INDENT 0.0
284	338	.INDENT 3.5
	339	minor, wild\-guess
	340	.UNINDENT
	341	.UNINDENT
	342	.SS duplicate\-header\-field\-content\-transfer\-encoding
	343	.sp
	344	This file contains multiple Content\-Transfer\-Encoding header fields.
	345	.sp
	346	Severity, certainty:
	347	.INDENT 0.0
	348	.INDENT 3.5
	349	pedantic, certain
	350	.UNINDENT
	351	.UNINDENT
	352	.SS duplicate\-header\-field\-content\-type
	353	.sp
	354	This file contains multiple Content\-Type header fields.
	355	.sp
	356	Severity, certainty:
	357	.INDENT 0.0
	358	.INDENT 3.5
285	359	serious, certain
286	360	.UNINDENT
287	361	.UNINDENT
	362	.SS duplicate\-header\-field\-date
	363	.sp
	364	This file contains multiple date header fields of the same name.
	365	.sp
	366	Severity, certainty:
	367	.INDENT 0.0
	368	.INDENT 3.5
	369	normal, certain
	370	.UNINDENT
	371	.UNINDENT
	372	.SS duplicate\-header\-field\-language
	373	.sp
	374	This file contains multiple Language header fields.
	375	.sp
	376	Severity, certainty:
	377	.INDENT 0.0
	378	.INDENT 3.5
	379	important, certain
	380	.UNINDENT
	381	.UNINDENT
	382	.SS duplicate\-header\-field\-language\-team
	383	.sp
	384	This file contains multiple Language\-Team header fields.
	385	.sp
	386	Severity, certainty:
	387	.INDENT 0.0
	388	.INDENT 3.5
	389	normal, certain
	390	.UNINDENT
	391	.UNINDENT
	392	.SS duplicate\-header\-field\-last\-translator
	393	.sp
	394	This file contains multiple Last\-Translator header fields.
	395	.sp
	396	Severity, certainty:
	397	.INDENT 0.0
	398	.INDENT 3.5
	399	normal, certain
	400	.UNINDENT
	401	.UNINDENT
	402	.SS duplicate\-header\-field\-mime\-version
	403	.sp
	404	This file contains multiple MIME\-Version header fields.
	405	.sp
	406	Severity, certainty:
	407	.INDENT 0.0
	408	.INDENT 3.5
	409	pedantic, certain
	410	.UNINDENT
	411	.UNINDENT
	412	.SS duplicate\-header\-field\-plural\-forms
	413	.sp
	414	This file contains multiple Plural\-Forms header fields.
	415	.sp
	416	Severity, certainty:
	417	.INDENT 0.0
	418	.INDENT 3.5
	419	serious, certain
	420	.UNINDENT
	421	.UNINDENT
	422	.SS duplicate\-header\-field\-project\-id\-version
	423	.sp
	424	This file contains multiple Project\-Id\-Version header fields.
	425	.sp
	426	Severity, certainty:
	427	.INDENT 0.0
	428	.INDENT 3.5
	429	minor, certain
	430	.UNINDENT
	431	.UNINDENT
	432	.SS duplicate\-header\-field\-report\-msgid\-bugs\-to
	433	.sp
	434	This file contains multiple Report\-Msgid\-Bugs\-To header fields.
	435	.sp
	436	Severity, certainty:
	437	.INDENT 0.0
	438	.INDENT 3.5
	439	normal, certain
	440	.UNINDENT
	441	.UNINDENT
288	442	.SS duplicate\-message\-definition
289	443	.sp
290	444	This file contains multiple definitions of the same message.

297	451	.UNINDENT
298	452	.SS empty\-file
299	453	.sp
300		This file doesn\(aqt contain any messages.
	454	This file doesn't contain any messages.
301	455	.sp
302	456	Severity, certainty:
303	457	.INDENT 0.0

308	462	.SS encoding\-in\-language\-header\-field
309	463	.sp
310	464	The language header field contains encoding declaration. Such information
311		shouldn\(aqt be included in this field.
	465	shouldn't be included in this field.
312	466	.sp
313	467	References:
314	468	.INDENT 0.0

323	477	minor, certain
324	478	.UNINDENT
325	479	.UNINDENT
	480	.SS fuzzy\-header\-entry
	481	.sp
	482	The header entry is marked as fuzzy.
	483	To increase operability with very old (<< 0.11) \fBmsgfmt\fP(1) versions,
	484	which didn't support fuzzy header entries, it shouldn't be marked as such.
	485	.sp
	486	References:
	487	.INDENT 0.0
	488	.INDENT 3.5
	489	\fI\%http://git.savannah.gnu.org/cgit/gettext.git/tree/NEWS?id=7808a2b730c4#n44\fP
	490	.UNINDENT
	491	.UNINDENT
	492	.sp
	493	Severity, certainty:
	494	.INDENT 0.0
	495	.INDENT 3.5
	496	pedantic, certain
	497	.UNINDENT
	498	.UNINDENT
326	499	.SS inconsistent\-leading\-newlines
327	500	.sp
328		Some strings in an entry start with a newline, but some don\(aqt.
	501	Some strings in an entry start with a newline, but some don't.
329	502	Either all of them should start with a newline, or none of them should.
330	503	.sp
331	504	Severity, certainty:

336	509	.UNINDENT
337	510	.SS inconsistent\-number\-of\-plural\-forms
338	511	.sp
339		Number of plural forms in a message definition doesn\(aqt match number of plural
	512	Number of plural forms in a message definition doesn't match number of plural
340	513	forms declared in another message definition.
341	514	.sp
342	515	References:

356	529	.UNINDENT
357	530	.SS inconsistent\-trailing\-newlines
358	531	.sp
359		Some strings in an entry end with a newline, but some don\(aqt.
	532	Some strings in an entry end with a newline, but some don't.
360	533	Either all of them should end with a newline, or none of them should.
361	534	.sp
362	535	Severity, certainty:

367	540	.UNINDENT
368	541	.SS incorrect\-number\-of\-plural\-forms
369	542	.sp
370		Number of plural forms in a message definition doesn\(aqt match number of plural
	543	Number of plural forms in a message definition doesn't match number of plural
371	544	forms declared in the header.
372	545	.sp
373	546	References:

387	560	.UNINDENT
388	561	.SS incorrect\-plural\-forms
389	562	.sp
390		The Plural\-Forms declaration is incorrect, according to i18nspector\(aqs
	563	The Plural\-Forms declaration is incorrect, according to i18nspector's
391	564	linguistic data.
392	565	.sp
393	566	Severity, certainty:

398	571	.UNINDENT
399	572	.SS incorrect\-unused\-plural\-forms
400	573	.sp
401		The Plural\-Forms declaration is incorrect, according to i18nspector\(aqs
	574	The Plural\-Forms declaration is incorrect, according to i18nspector's
402	575	linguistic data.
403	576	(But there are no translated messages which use plural forms.)
404	577	.sp

468	641	.UNINDENT
469	642	.SS invalid\-language
470	643	.sp
471		The Language header field couldn\(aqt be parsed, or it contains an unknown
	644	The Language header field couldn't be parsed, or it contains an unknown
472	645	language.
473	646	.sp
474	647	References:

541	714	.UNINDENT
542	715	.SS invalid\-mo\-file
543	716	.sp
544		This file couldn\(aqt be parsed a MO file.
	717	This file couldn't be parsed a MO file.
545	718	.sp
546	719	Severity, certainty:
547	720	.INDENT 0.0

572	745	.SS language\-disparity
573	746	.sp
574	747	Language of this file has been declared in multiple places, but the
575		declarations don\(aqt match.
	748	declarations don't match.
576	749	.sp
577	750	Severity, certainty:
578	751	.INDENT 0.0

582	755	.UNINDENT
583	756	.SS language\-team\-equal\-to\-last\-translator
584	757	.sp
585		Language\-Team and Last\-Translator header fields contains the same e\-mail
	758	Language\-Team and Last\-Translator header fields contain the same e\-mail
586	759	address.
587	760	.sp
588	761	Severity, certainty:

611	784	.UNINDENT
612	785	.SS no\-content\-transfer\-encoding\-header\-field
613	786	.sp
614		The Content\-Transfer\-Encoding header field doesn\(aqt exist. It should be set to
	787	The Content\-Transfer\-Encoding header field doesn't exist. It should be set to
615	788	\fB8bit\fP.
616	789	.sp
617	790	References:

631	804	.UNINDENT
632	805	.SS no\-content\-type\-header\-field
633	806	.sp
634		The Content\-Type header field doesn\(aqt exist. It should be set to
	807	The Content\-Type header field doesn't exist. It should be set to
635	808	\fBtext/plain; charset=\fP\fIencoding\fP.
636	809	.sp
637	810	Note that in the absence of encoding declaration, i18nspector assumes ASCII

654	827	.UNINDENT
655	828	.SS no\-date\-header\-field
656	829	.sp
657		The date header field doesn\(aqt exist.
	830	The date header field doesn't exist.
658	831	.sp
659	832	References:
660	833	.INDENT 0.0

671	844	.UNINDENT
672	845	.SS no\-language\-header\-field
673	846	.sp
674		The Language header field doesn\(aqt exist.
	847	The Language header field doesn't exist.
675	848	.sp
676	849	References:
677	850	.INDENT 0.0

707	880	.UNINDENT
708	881	.SS no\-last\-translator\-header\-field
709	882	.sp
710		The Last\-Translator header field doesn\(aqt exist.
711		It should contain the last translator\(aqs name and email address.
	883	The Last\-Translator header field doesn't exist.
	884	It should contain the last translator's name and email address.
712	885	.sp
713	886	References:
714	887	.INDENT 0.0

725	898	.UNINDENT
726	899	.SS no\-mime\-version\-header\-field
727	900	.sp
728		The MIME\-Version header field does\(aqt exist. It should be to set to \fB1.0\fP.
	901	The MIME\-Version header field does't exist. It should be to set to \fB1.0\fP.
729	902	.sp
730	903	References:
731	904	.INDENT 0.0

742	915	.UNINDENT
743	916	.SS no\-package\-name\-in\-project\-id\-version
744	917	.sp
745		The Project\-Id\-Version header field doesn\(aqt appear to contain any name.
	918	The Project\-Id\-Version header field doesn't appear to contain any name.
746	919	It should contain both the name and the version of the package.
747	920	.sp
748	921	References:

833	1006	.UNINDENT
834	1007	.SS no\-version\-in\-project\-id\-version
835	1008	.sp
836		The Project\-Id\-Version header field doesn\(aqt appear to contain any version.
	1009	The Project\-Id\-Version header field doesn't appear to contain any version.
837	1010	It should contain both the name and the version of the package.
838	1011	.sp
839	1012	References:

925	1098	.UNINDENT
926	1099	.SS syntax\-error\-in\-po\-file
927	1100	.sp
928		This file couldn\(aqt be parsed a PO file.
	1101	This file couldn't be parsed a PO file.
929	1102	In some rare cases this is due to incorrect or missing encoding declaration.
930	1103	.sp
931	1104	References:

975	1148	.UNINDENT
976	1149	.SS unknown\-encoding
977	1150	.sp
978		This file declares an encoding that couldn\(aqt be recognized by i18nspector.
	1151	This file declares an encoding that couldn't be recognized by i18nspector.
979	1152	It might be a typo.
980	1153	Absence of encoding information will prevent i18nspector from performing
981	1154	further checks.

988	1161	.UNINDENT
989	1162	.SS unknown\-file\-type
990	1163	.sp
991		File format of this file couldn\(aqt be recognized.
	1164	File format of this file couldn't be recognized.
992	1165	It might be a bug in i18nspector.
993	1166	.sp
994	1167	Severity, certainty:

1018	1191	.UNINDENT
1019	1192	.SS unknown\-poedit\-language
1020	1193	.sp
1021		Language declared in X\-Poedit\-Language couldn\(aqt be recognized.
	1194	Language declared in X\-Poedit\-Language couldn't be recognized.
1022	1195	It might be a bug in i18nspector.
1023	1196	.sp
1024	1197	Severity, certainty:

+1

-1

doc/i18nspector.txt less more

6	6	----------------------------------------------
7	7
8	8	:manual section: 1
9		:version: i18nspector 0.9.2
	9	:version: i18nspector 0.10
10	10	:date: \|date\|
11	11
12	12	Synopsis

+135

-2

doc/tags.txt less more

39	39	Severity, certainty:
40	40
41	41	important, possible
	42
	43	boilerplate-in-content-type
	44	~~~~~~~~~~~~~~~~~~~~~~~~~~~
	45	The Content-Type header field contains xgettext boilerplate.
	46	It should be in the form ``text/plain; charset=``\ encoding.
	47
	48	References:
	49
	50	http://www.gnu.org/software/gettext/manual/html_node/Header-Entry.html
	51
	52	Severity, certainty:
	53
	54	important, certain
42	55
43	56	boilerplate-in-language-team
44	57	~~~~~~~~~~~~~~~~~~~~~~~~~~~~

142	155
143	156	important, possible
144	157
	158	conflict-marker-in-header-entry
	159	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	160	The header contains a conflict marker (#-#-#-#-# … #-#-#-#-#).
	161	The conflict will have to be resolved manually.
	162
	163	References:
	164
	165	http://www.gnu.org/software/gettext/manual/html_node/Creating-Compendia.html#Creating-Compendia
	166
	167	Severity, certainty:
	168
	169	serious, certain
	170
	171	conflict-marker-in-translation
	172	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	173	One of the translated messages appear to contain a conflict marker (#-#-#-#-# … #-#-#-#-#).
	174	The conflict will have to be resolved manually.
	175
	176	References:
	177
	178	http://www.gnu.org/software/gettext/manual/html_node/Creating-Compendia.html#Creating-Compendia
	179
	180	Severity, certainty:
	181
	182	serious, possible
	183
145	184	date-from-future
146	185	~~~~~~~~~~~~~~~~
147	186	The date refers to the future. As such, it's extremely unlikely to be correct.

156	195
157	196	Severity, certainty:
158	197
159		serious, certain
	198	minor, wild-guess
	199
	200	duplicate-header-field-content-transfer-encoding
	201	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	202	This file contains multiple Content-Transfer-Encoding header fields.
	203
	204	Severity, certainty:
	205
	206	pedantic, certain
	207
	208	duplicate-header-field-content-type
	209	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	210	This file contains multiple Content-Type header fields.
	211
	212	Severity, certainty:
	213
	214	serious, certain
	215
	216	duplicate-header-field-date
	217	~~~~~~~~~~~~~~~~~~~~~~~~~~~
	218	This file contains multiple date header fields of the same name.
	219
	220	Severity, certainty:
	221
	222	normal, certain
	223
	224	duplicate-header-field-language
	225	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	226	This file contains multiple Language header fields.
	227
	228	Severity, certainty:
	229
	230	important, certain
	231
	232	duplicate-header-field-language-team
	233	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	234	This file contains multiple Language-Team header fields.
	235
	236	Severity, certainty:
	237
	238	normal, certain
	239
	240	duplicate-header-field-last-translator
	241	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	242	This file contains multiple Last-Translator header fields.
	243
	244	Severity, certainty:
	245
	246	normal, certain
	247
	248	duplicate-header-field-mime-version
	249	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	250	This file contains multiple MIME-Version header fields.
	251
	252	Severity, certainty:
	253
	254	pedantic, certain
	255
	256	duplicate-header-field-plural-forms
	257	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	258	This file contains multiple Plural-Forms header fields.
	259
	260	Severity, certainty:
	261
	262	serious, certain
	263
	264	duplicate-header-field-project-id-version
	265	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	266	This file contains multiple Project-Id-Version header fields.
	267
	268	Severity, certainty:
	269
	270	minor, certain
	271
	272	duplicate-header-field-report-msgid-bugs-to
	273	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	274	This file contains multiple Report-Msgid-Bugs-To header fields.
	275
	276	Severity, certainty:
	277
	278	normal, certain
160	279
161	280	duplicate-message-definition
162	281	~~~~~~~~~~~~~~~~~~~~~~~~~~~~

186	305	Severity, certainty:
187	306
188	307	minor, certain
	308
	309	fuzzy-header-entry
	310	~~~~~~~~~~~~~~~~~~
	311	The header entry is marked as fuzzy.
	312	To increase operability with very old (<< 0.11) msgfmt\ (1) versions,
	313	which didn't support fuzzy header entries, it shouldn't be marked as such.
	314
	315	References:
	316
	317	http://git.savannah.gnu.org/cgit/gettext.git/tree/NEWS?id=7808a2b730c4#n44
	318
	319	Severity, certainty:
	320
	321	pedantic, certain
189	322
190	323	inconsistent-leading-newlines
191	324	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

384	517
385	518	language-team-equal-to-last-translator
386	519	~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
387		Language-Team and Last-Translator header fields contains the same e-mail
	520	Language-Team and Last-Translator header fields contain the same e-mail
388	521	address.
389	522
390	523	Severity, certainty:

+9

-0

doc/todo.txt less more

47	47	Make duplicate-header-field work for .mo files, too.
48	48	* https://bitbucket.org/izi/polib/issue/36
49	49
	50	Check for initial stray lines in headers. (They are currently ignored due to
	51	deficiencies in the polib parser.)
	52
50	53	Add support for configuration files. Once it's implemented:
51	54	* Disable --debian by default.
52	55	* Disable --pedantic by default.

64	67
65	68	Run ``msgfmt --check-format`` on PO files.
66	69
	70	Reimplement 8-bit codecs without iconv(1)/iconv(3).
	71
	72	Check for hardcoded Language in POT files.
	73
	74	Add option for printing tags descriptions.
	75
67	76	.. vim:ft=rst

+120

-37

lib/checker.py less more

42	42	pass
43	43
44	44	find_unusual_characters = re.compile(
45		r'[\x00-\x08\x0b-\x1a\x1c-\x1f]' # C0 except TAB, LF, ESC
46		r'\|\x1b(?!\[)' # ESC, except when followed by [
47		r'\|\x7f' # DEL
48		r'\|[\x80-\x9f]' # C1
49		'\|\ufffd' # REPLACEMENT CHARACTER
50		'\|[\ufffe\uffff]' # non-characters
51		r'\|(?<=\w)\xbf' # INVERTED QUESTION MARK but only directly after a letter
	45	r'[\x00-\x08\x0b-\x1a\x1c-\x1f]' # C0 except TAB, LF, ESC
	46	r'\|\x1b(?!\[)' # ESC, except when followed by [
	47	r'\|\x7f' # DEL
	48	r'\|[\x80-\x9f]' # C1
	49	'\|\ufffd' # REPLACEMENT CHARACTER
	50	'\|[\ufffe\uffff]' # non-characters
	51	r'\|(?<=\w)\xbf' # INVERTED QUESTION MARK but only directly after a letter
52	52	).findall
53	53
54	54	class Checker(object):

162	162	broken_encoding = True
163	163	# check_headers() modifies the file metadata,
164	164	# so it has to be the first check:
165		self.check_headers(file)
	165	self.check_headers(file, is_template=is_template)
166	166	language = self.check_language(file, is_template=is_template)
167	167	self.check_plurals(file, is_template=is_template, language=language)
168	168	encoding = self.check_mime(file, is_template=is_template, language=language)

175	175
176	176	def check_language(self, file, *, is_template):
177	177	if is_template:
178		if not 'Language' in file.metadata:
	178	if 'Language' in file.metadata.duplicates:
	179	self.tag('duplicate-header-field-language')
	180	elif not 'Language' in file.metadata:
179	181	self.tag('no-language-header-field')
180	182	return
181	183	language = self.options.language

216	218	language = None
217	219	else:
218	220	language_source = 'pathname'
219		meta_language = orig_meta_language = file.metadata.get('Language')
	221	if 'Language' in file.metadata.duplicates:
	222	self.tag('duplicate-header-field-language')
	223	duplicate_meta_language = True
	224	meta_language = None
	225	else:
	226	duplicate_meta_language = False
	227	meta_language = file.metadata.get('Language')
	228	orig_meta_language = meta_language
220	229	if meta_language:
221	230	try:
222	231	meta_language = linginfo.parse_language(meta_language)

269	278	poedit_language, tags.safestr('(X-Poedit-Language header field)')
270	279	)
271	280	if language is None:
272		if not orig_meta_language:
	281	if not orig_meta_language and not duplicate_meta_language:
273	282	self.tag('no-language-header-field')
274	283	self.tag('unable-to-determine-language')
275	284	return
276		if not orig_meta_language:
	285	if not orig_meta_language and not duplicate_meta_language:
277	286	self.tag('no-language-header-field', tags.safestr('Language:'), language)
278	287	return language
279	288
280	289	def check_plurals(self, file, *, is_template, language):
	290	if 'Plural-Forms' in file.metadata.duplicates:
	291	self.tag('duplicate-header-field-plural-forms')
	292	return
281	293	correct_plural_forms = None
282	294	if language is not None:
283	295	correct_plural_forms = language.get_plural_forms()
284	296	plural_forms = file.metadata.get('Plural-Forms')
285		has_plurals = False # messages with plural forms (translated or not)?
286		expected_nplurals = {} # number of plurals in _translated_ messages
	297	has_plurals = False # messages with plural forms (translated or not)?
	298	expected_nplurals = {} # number of plurals in _translated_ messages
287	299	for message in file:
288	300	if message.obsolete:
289	301	continue

395	407	self.tag('codomain-error-in-unused-plural-forms', message)
396	408
397	409	def check_mime(self, file, *, is_template, language):
	410	# MIME-Version:
398	411	mime_version = file.metadata.get('MIME-Version')
399		if mime_version is not None:
	412	if 'MIME-Version' in file.metadata.duplicates:
	413	self.tag('duplicate-header-field-mime-version')
	414	elif mime_version is not None:
400	415	if mime_version != '1.0':
401	416	self.tag('invalid-mime-version', mime_version, '=>', '1.0')
402	417	else:
403	418	self.tag('no-mime-version-header-field', tags.safestr('MIME-Version: 1.0'))
	419	# Content-Transfer-Encoding:
404	420	cte = file.metadata.get('Content-Transfer-Encoding')
405		if cte is not None:
	421	if 'Content-Transfer-Encoding' in file.metadata.duplicates:
	422	self.tag('duplicate-header-field-content-transfer-encoding')
	423	elif cte is not None:
406	424	if cte != '8bit':
407	425	self.tag('invalid-content-transfer-encoding', cte, '=>', '8bit')
408	426	else:
409	427	self.tag('no-content-transfer-encoding-header-field', tags.safestr('Content-Transfer-Encoding: 8bit'))
410		ct = file.metadata.get('Content-Type')
	428	# Content-Type:
	429	if 'Content-Type' in file.metadata.duplicates:
	430	duplicate_ct = True
	431	ct = None
	432	else:
	433	duplicate_ct = False
	434	ct = file.metadata.get('Content-Type')
411	435	encoding = None
412	436	content_type_hint = 'text/plain; charset=<encoding>'
413	437	if ct is not None:

418	442	try:
419	443	is_ascii_compatible = encinfo.is_ascii_compatible_encoding(encoding)
420	444	except LookupError:
421		if is_template and (encoding == 'CHARSET'):
422		pass
	445	if encoding == 'CHARSET':
	446	if not is_template:
	447	self.tag('boilerplate-in-content-type', ct)
423	448	else:
424	449	self.tag('unknown-encoding', encoding)
425	450	encoding = None

447	472	self.tag('invalid-content-type', ct, '=>', content_type_hint)
448	473	else:
449	474	self.tag('invalid-content-type', ct, '=>', content_type_hint)
	475	elif duplicate_ct:
	476	self.tag('duplicate-header-field-content-type')
450	477	else:
451	478	self.tag('no-content-type-header-field', tags.safestr('Content-Type: ' + content_type_hint))
452	479	return encoding
453	480
454	481	def check_dates(self, file, *, is_template):
455	482	for field in 'POT-Creation-Date', 'PO-Revision-Date':
	483	if field in file.metadata.duplicates:
	484	self.tag('duplicate-header-field-date', field)
	485	continue
456	486	date = file.metadata.get(field)
457	487	if date is None:
458	488	self.tag('no-date-header-field', field)

472	502	self.tag('ancient-date', tags.safestr(field + ':'), date)
473	503
474	504	def check_project(self, file):
	505	# Project-Id-Version:
475	506	project_id_version = file.metadata.get('Project-Id-Version')
	507	if 'Project-Id-Version' in file.metadata.duplicates:
	508	self.tag('duplicate-header-field-project-id-version')
476	509	if project_id_version is None:
477	510	self.tag('no-project-id-version-header-field')
478	511	elif project_id_version in {'PACKAGE VERSION', 'PROJECT VERSION'}:

482	515	self.tag('no-package-name-in-project-id-version', project_id_version)
483	516	if not re.search(r'[0-9]', project_id_version):
484	517	self.tag('no-version-in-project-id-version', project_id_version)
	518	# Report-Msgid-Bugs-To:
485	519	report_msgid_bugs_to = file.metadata.get('Report-Msgid-Bugs-To')
486		if not report_msgid_bugs_to:
	520	if 'Report-Msgid-Bugs-To' in file.metadata.duplicates:
	521	self.tag('duplicate-header-field-report-msgid-bugs-to')
	522	elif not report_msgid_bugs_to:
487	523	self.tag('no-report-msgid-bugs-to-header-field')
488		else:
489		real_name, email_address = email.utils.parseaddr(report_msgid_bugs_to)
	524	elif report_msgid_bugs_to:
	525	real_name, email_address = email.utils.parseaddr(report_msgid_bugs_to)
490	526	if '@' not in email_address:
491	527	uri = urllib.parse.urlparse(report_msgid_bugs_to)
492	528	if uri.scheme == '':

497	533	self.tag('boilerplate-in-report-msgid-bugs-to', report_msgid_bugs_to)
498	534
499	535	def check_translator(self, file, *, is_template):
	536	# Last-Translator:
500	537	translator = file.metadata.get('Last-Translator')
501		if translator is None:
	538	if 'Last-Translator' in file.metadata.duplicates:
	539	self.tag('duplicate-header-field-last-translator')
	540	elif translator is None:
502	541	self.tag('no-last-translator-header-field')
503	542	else:
504	543	translator_name, translator_email = email.utils.parseaddr(translator)

509	548	elif translator_email == 'EMAIL@ADDRESS':
510	549	if not is_template:
511	550	self.tag('boilerplate-in-last-translator', translator)
	551	# Language-Team:
512	552	team = file.metadata.get('Language-Team')
513		if team is None:
	553	if 'Language-Team' in file.metadata.duplicates:
	554	self.tag('duplicate-header-field-language-team')
	555	elif team is None:
514	556	self.tag('no-language-team-header-field')
515	557	else:
516	558	team_name, team_email = email.utils.parseaddr(team)

532	574	if team_is_translator:
533	575	self.tag('language-team-equal-to-last-translator', team, translator)
534	576
535		def check_headers(self, file):
	577	def check_headers(self, file, *, is_template):
536	578	header_fields = frozenset(self.options.gettextinfo.header_fields)
537	579	header_fields_lc = {str.lower(s): s for s in header_fields}
538		new_metadata = {}
	580	class userdict(dict): pass
	581	new_metadata = userdict()
	582	seen_conflict_marker = False
539	583	for key, value in sorted(file.metadata.items()):
	584	if not gettext.is_valid_field_name(key):
	585	line = key + (':' if value else '')
	586	self.tag('stray-header-line', line)
	587	key = None
540	588	value, *strays = value.split('\n')
541	589	for stray in strays:
542		self.tag('stray-header-line', stray)
	590	if gettext.search_for_conflict_marker(stray):
	591	if not seen_conflict_marker:
	592	self.tag('conflict-marker-in-header-entry', stray)
	593	seen_conflict_marker = True
	594	else:
	595	self.tag('stray-header-line', stray)
	596	if key is None:
	597	continue
543	598	new_metadata[key] = value
544	599	if key.startswith('X-'):
545	600	continue

558	613	try:
559	614	duplicates = file.metadata.duplicates
560	615	except AttributeError:
561		pass
	616	duplicates = {}
562	617	else:
563	618	for key, values in sorted(duplicates.items()):
564		self.tag('duplicate-header-field', key)
	619	if not gettext.is_valid_field_name(key):
	620	line = key + (':' if any(values) else '')
	621	self.tag('stray-header-line', key + ':')
	622	elif key in {
	623	'Content-Transfer-Encoding',
	624	'Content-Type',
	625	'Language',
	626	'Language-Team',
	627	'Last-Translator',
	628	'MIME-Version',
	629	'PO-Revision-Date',
	630	'POT-Creation-Date',
	631	'Plural-Forms',
	632	'Project-Id-Version',
	633	'Report-Msgid-Bugs-To'
	634	}:
	635	# These will be handled elsewhere.
	636	pass
	637	else:
	638	self.tag('duplicate-header-field', key)
565	639	for value in values:
566	640	value, *strays = value.split('\n')
567	641	for stray in strays:
568	642	self.tag('stray-header-line', stray)
	643	new_metadata.duplicates = frozenset(duplicates)
569	644	file.metadata = new_metadata
	645	if file.metadata_is_fuzzy and not is_template:
	646	self.tag('fuzzy-header-entry')
570	647
571	648	def check_messages(self, file, *, encoding):
572	649	if encoding is None:

600	677	set(find_unusual_characters(message.msgid_plural))
601	678	)
602	679	strings = [message.msgstr] + sorted(message.msgstr_plural.values())
	680
	681	conflict_marker = None
603	682	for msgstr in strings:
604	683	msgstr_uc = set(find_unusual_characters(msgstr))
605	684	uc = msgstr_uc - msgid_uc - found_unusual_characters
606		if not uc:
607		continue
608		names = ', '.join(
609		'U+{:04X} {}'.format(ord(ch), encinfo.get_character_name(ch))
610		for ch in sorted(uc)
611		)
612		self.tag('unusual-character-in-translation', tags.safestr(names + ':'), msgstr)
613		found_unusual_characters \|= uc
	685	if uc:
	686	names = ', '.join(
	687	'U+{:04X} {}'.format(ord(ch), encinfo.get_character_name(ch))
	688	for ch in sorted(uc)
	689	)
	690	self.tag('unusual-character-in-translation', tags.safestr(names + ':'), msgstr)
	691	found_unusual_characters \|= uc
	692	if conflict_marker is None:
	693	conflict_marker = gettext.search_for_conflict_marker(msgstr)
	694	if conflict_marker is not None:
	695	conflict_marker = conflict_marker.group(0)
	696	self.tag('conflict-marker-in-translation', message_repr(message), conflict_marker)
614	697	msgid_counter[message.msgid, message.msgctxt] += 1
615	698	if msgid_counter[message.msgid, message.msgctxt] == 2:
616	699	self.tag('duplicate-message-definition', message_repr(message))

+8

-3

lib/cli.py less more

33	33	from . import tags
34	34	from . import terminal
35	35
36		__version__ = '0.9.2'
	36	__version__ = '0.10'
37	37
38	38	def initialize_terminal():
39	39	if sys.stdout.isatty():

50	50	def tag(self, tagname, *extra):
51	51	if tagname in self.options.ignore_tags:
52	52	return
53		tag = self.options.taginfo[tagname]
	53	try:
	54	tag = self.options.taginfo[tagname]
	55	except KeyError:
	56	raise misc.DataIntegrityError(
	57	'attempted to emit an unknown tag: {tag!r}'.format(tag=tagname)
	58	)
54	59	s = tag.format(self.fake_path, *extra, color=True)
55	60	print(s)
56	61

85	90	with open(os.devnull) as bitbucket:
86	91	ipc.check_call(
87	92	['dpkg-source', '--no-copy', '--no-check', '-x', filename, real_root],
88		stdout=bitbucket # dpkg-source would be noisy without this...
	93	stdout=bitbucket # dpkg-source would be noisy without this...
89	94	)
90	95	options = copy_options(options,
91	96	ignore_tags=ignore_tags,

+15

-43

lib/encodings.py less more

27	27	import contextlib
28	28	import itertools
29	29	import os
30		import subprocess as ipc
31	30	import unicodedata
32	31
	32	from lib import iconv
33	33	from lib import misc
34	34
35	35	def iconv_encoding(encoding, *, parent):
36
37		# FIXME: This implementation is SLOW.
38
39		def popen(*args):
40		def set_lc_all_c():
41		os.environ['LC_ALL'] = 'C' # <no-coverage>
42		return ipc.Popen(args,
43		stdin=ipc.PIPE, stdout=ipc.PIPE, stderr=ipc.PIPE,
44		preexec_fn=set_lc_all_c,
45		)
46	36
47	37	def encode(input, errors='strict'):
48	38	if not (parent._extra_encodings_installed > 0):
49	39	# There doesn't seem to be a way to de-register a codec.
50	40	# As a poor man's substitute, raise LookupError at encoding time.
51	41	raise LookupError('unknown encoding: ' + encoding)
52		if len(input) == 0:
53		return b'', 0
54		if errors != 'strict':
55		raise NotImplementedError
56		child = popen('iconv', '-s', '-f', 'UTF-8', '-t', encoding)
57		(stdout, stderr) = child.communicate(input.encode('UTF-8'))
58		if stderr != b'':
59		stderr = stderr.decode('ASCII', 'replace')
60		raise UnicodeEncodeError(encoding, input, 0, len(input), stderr)
61		return stdout, len(input)
	42	output = iconv.encode(input, encoding=encoding, errors=errors)
	43	return output, len(input)
62	44
63	45	def decode(input, errors='strict'):
64	46	if not (parent._extra_encodings_installed > 0):
65	47	# There doesn't seem to be a way to de-register a codec.
66	48	# As a poor man's substitute, raise LookupError at decoding time.
67	49	raise LookupError('unknown encoding: ' + encoding)
68		if len(input) == 0:
69		# This actually never happens. Python optimizes out empty-string
70		# decoding.
71		return '', 0 # <no-coverage>
72		if errors != 'strict':
73		raise NotImplementedError
74		child = popen('iconv', '-s', '-f', encoding, '-t', 'UTF-8')
75		(stdout, stderr) = child.communicate(input)
76		if stderr != b'':
77		stderr = stderr.decode('ASCII', 'replace')
78		raise UnicodeDecodeError(encoding, input, 0, len(input), stderr)
79		return stdout.decode('UTF-8'), len(input)
	50	output = iconv.decode(bytes(input), encoding=encoding, errors=errors)
	51	return output, len(input)
80	52
81	53	def not_implemented(args, *kwargs):
82	54	raise NotImplementedError

94	66	class EncodingInfo(object):
95	67
96	68	_interesting_ascii_bytes = bytes(itertools.chain([
97		0, # NUL
98		4, # EOT
99		7, # BEL
100		8, # BS
101		9, # HT
102		10, # LF
103		11, # VT
104		12, # FF
105		13, # CR
106		27, # ESC
	69	0, # NUL
	70	4, # EOT
	71	7, # BEL
	72	8, # BS
	73	9, # HT
	74	10, # LF
	75	11, # VT
	76	12, # FF
	77	13, # CR
	78	27, # ESC
107	79	], range(32, 127)))
108	80	_interesting_ascii_str = _interesting_ascii_bytes.decode()
109	81

+14

-7

lib/gettext.py less more

44	44	misc.check_sorted(fields)
45	45	self.header_fields = frozenset(fields)
46	46
	47	is_valid_field_name = re.compile(r'^[\x21-\x39\x3b-\x7e]+$').match
	48	# http://tools.ietf.org/html/rfc5322#section-3.6.8
	49
	50	search_for_conflict_marker = re.compile(r'^#-#-#-#-# .+ #-#-#-#-#$', re.MULTILINE).search
	51	# gettext-tools/src/msgl-cat.c
	52	# http://www.gnu.org/software/gettext/manual/html_node/Creating-Compendia.html#Creating-Compendia
	53
47	54	# ================
48	55	# Plurals handling
49	56	# ================

67	74	(r'[?:]', None),
68	75	(r'[()]', None),
69	76	(r'[ \t]', None),
70		(r'.', '_'), # junk
	77	(r'.', '_'), # junk
71	78	]
72	79
73	80	_plural_exp_token_re = '\|'.join(

82	89	if ctoken is not None:
83	90	break
84	91	if ctoken is not None:
85		if pytoken == '_': # junk
	92	if pytoken == '_': # junk
86	93	raise PluralExpressionSyntaxError(match.group(0))
87	94	yield ' {} '.format(pytoken)
88	95	else:

140	147
141	148	_parse_date = re.compile('''
142	149	^ \s*
143		( [0-9]{4}-[0-9]{2}-[0-9]{2} ) # YYYY-MM-DD
	150	( [0-9]{4}-[0-9]{2}-[0-9]{2} ) # YYYY-MM-DD
144	151	( \s+ )
145		( [0-9]{2}:[0-9]{2} ) # hh:mm
146		(?: : [0-9]{2} )? # ss
	152	( [0-9]{2}:[0-9]{2} ) # hh:mm
	153	(?: : [0-9]{2} )? # ss
147	154	\s*
148		( [+-] [0-9]{2} ) # ZZ
	155	( [+-] [0-9]{2} ) # ZZ
149	156	:?
150		( [0-9]{2} ) # zz
	157	( [0-9]{2} ) # zz
151	158	\s* $
152	159	''', re.VERBOSE).match
153	160

+227

-0

lib/iconv.py less more

	0	#!/usr/bin/python3
	1
	2	# Copyright © 2012, 2013 Jakub Wilk <jwilk@jwilk.net>
	3	#
	4	# Permission is hereby granted, free of charge, to any person obtaining a copy
	5	# of this software and associated documentation files (the “Software”), to deal
	6	# in the Software without restriction, including without limitation the rights
	7	# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
	8	# copies of the Software, and to permit persons to whom the Software is
	9	# furnished to do so, subject to the following conditions:
	10	#
	11	# The above copyright notice and this permission notice shall be included in
	12	# all copies or substantial portions of the Software.
	13	#
	14	# THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
	15	# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
	16	# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
	17	# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
	18	# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
	19	# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
	20	# SOFTWARE.
	21
	22	'''
	23	string encoding and decoding using iconv(3), with a fallback to iconv(1)
	24	'''
	25
	26	import ctypes
	27	import errno
	28	import os
	29	import subprocess as ipc
	30	import re
	31	import sys
	32
	33	default_encoding = sys.getdefaultencoding()
	34
	35	_boring_iconv_stderr = re.compile('\nTry .+ for more information[.]$')
	36
	37	_libc = ctypes.CDLL(None, use_errno=True)
	38	try:
	39	_iconv_open = _libc.iconv_open
	40	_iconv_close = _libc.iconv_close
	41	_iconv = _libc.iconv
	42	except AttributeError:
	43	_iconv = _iconv_open = _iconv_close = None
	44	else:
	45	_iconv_open.argtypes = [ctypes.c_char_p, ctypes.c_char_p]
	46	_iconv_open.restype = ctypes.c_void_p
	47	_iconv_close.argtypes = [ctypes.c_void_p]
	48	_iconv_close.restype = ctypes.c_int
	49	_iconv.argtypes = (
	50	[ctypes.c_void_p] +
	51	[ctypes.POINTER(ctypes.POINTER(ctypes.c_char)), ctypes.POINTER(ctypes.c_size_t)] * 2
	52	)
	53	_iconv.restype = ctypes.c_size_t
	54
	55	def _popen(*args):
	56	def set_lc_all_c():
	57	os.environ['LC_ALL'] = 'C' # <no-coverage>
	58	return ipc.Popen(args,
	59	stdin=ipc.PIPE, stdout=ipc.PIPE, stderr=ipc.PIPE,
	60	preexec_fn=set_lc_all_c,
	61	)
	62
	63	def encode(input: str, encoding=default_encoding, errors='strict'):
	64	if not isinstance(input, str):
	65	raise TypeError('input must be str, not {tp}'.format(tp=type(input).__name__))
	66	if not isinstance(encoding, str):
	67	raise TypeError('encoding must be str, not {tp}'.format(tp=type(encoding).__name__))
	68	if not isinstance(errors, str):
	69	raise TypeError('errors must be str, not {tp}'.format(tp=type(errors).__name__))
	70	if len(input) == 0:
	71	return b''
	72	if errors != 'strict':
	73	raise NotImplementedError('error handler {e!r} is not implemented'.format(e=errors))
	74	return _encode(input, encoding=encoding)
	75
	76	def _encode_dl(input: str, *, encoding):
	77	if sys.maxunicode < (1 << 16):
	78	uencoding = 'UTF-16LE'
	79	uwidth = 2
	80	else:
	81	uencoding = 'UTF-32LE'
	82	uwidth = 4
	83	binput = bytes(input, encoding=uencoding)
	84	assert len(binput) == len(input) * uwidth
	85	cd = _iconv_open(bytes(encoding, 'ASCII'), bytes(uencoding, 'ASCII'))
	86	assert isinstance(cd, int)
	87	if cd == ctypes.c_void_p(-1).value:
	88	rc = ctypes.get_errno()
	89	raise OSError(rc, os.strerror(rc))
	90	try:
	91	c_input = ctypes.c_char_p(binput)
	92	output_len = len(input)
	93	while True:
	94	inbuf = ctypes.cast(c_input, ctypes.POINTER(ctypes.c_char))
	95	inbytesleft = ctypes.c_size_t(len(binput))
	96	assert inbytesleft.value == len(binput) # no overflow
	97	outbuf = ctypes.create_string_buffer(output_len)
	98	outbytesleft = ctypes.c_size_t(output_len)
	99	assert outbytesleft.value == output_len # no overflow
	100	rc = _iconv(cd, *map(ctypes.byref, [
	101	ctypes.cast(inbuf, ctypes.POINTER(ctypes.c_char)), inbytesleft,
	102	ctypes.cast(outbuf, ctypes.POINTER(ctypes.c_char)), outbytesleft,
	103	]))
	104	if rc == ctypes.c_size_t(-1).value:
	105	rc = ctypes.get_errno()
	106	if rc == errno.E2BIG:
	107	output_len *= 2
	108	continue
	109	elif rc in {errno.EILSEQ, errno.EINVAL}:
	110	begin = len(input) - inbytesleft.value // uwidth
	111	raise UnicodeEncodeError(
	112	encoding,
	113	input,
	114	begin, begin + 1,
	115	os.strerror(errno.EILSEQ),
	116	)
	117	raise OSError(rc, os.strerror(rc))
	118	assert inbytesleft.value == 0, '{n} bytes left'.format(n=inbytesleft.value)
	119	output_len -= outbytesleft.value
	120	return outbuf[:output_len]
	121	finally:
	122	rc = _iconv_close(cd)
	123	if rc != 0:
	124	rc = ctypes.get_errno()
	125	raise OSError(rc, os.strerror(rc))
	126
	127	def _encode_cli(input, *, encoding):
	128	child = _popen('iconv', '-f', 'UTF-8', '-t', encoding)
	129	(stdout, stderr) = child.communicate(input.encode('UTF-8'))
	130	if stderr != b'':
	131	stderr = stderr.decode('ASCII', 'replace')
	132	stderr = _boring_iconv_stderr.sub('', stderr)
	133	raise UnicodeEncodeError(encoding,
	134	input, # .object
	135	0, # .begin
	136	len(input), # .end
	137	stderr.strip() # .reason
	138	)
	139	return stdout
	140
	141	_encode = _encode_dl if _iconv is not None else _encode_cli
	142
	143	def decode(input: bytes, encoding=default_encoding, errors='strict'):
	144	if not isinstance(input, bytes):
	145	raise TypeError('input must be bytes, not {tp}'.format(tp=type(input).__name__))
	146	if not isinstance(encoding, str):
	147	raise TypeError('encoding must be str, not {tp}'.format(tp=type(encoding).__name__))
	148	if not isinstance(errors, str):
	149	raise TypeError('errors must be str, not {tp}'.format(tp=type(errors).__name__))
	150	if len(input) == 0:
	151	return ''
	152	if errors != 'strict':
	153	raise NotImplementedError('error handler {e!r} is not implemented'.format(e=errors))
	154	return _decode(input, encoding=encoding)
	155
	156	def _decode_dl(input: bytes, *, encoding):
	157	cd = _iconv_open(b'WCHAR_T', bytes(encoding, 'ASCII'))
	158	assert isinstance(cd, int)
	159	if cd == ctypes.c_void_p(-1).value:
	160	rc = ctypes.get_errno()
	161	raise OSError(rc, os.strerror(rc))
	162	try:
	163	c_input = ctypes.c_char_p(input)
	164	output_len = len(input)
	165	while True:
	166	inbuf = ctypes.cast(c_input, ctypes.POINTER(ctypes.c_char))
	167	inbytesleft = ctypes.c_size_t(len(input))
	168	assert inbytesleft.value == len(input) # no overflow
	169	outbuf = ctypes.create_unicode_buffer(output_len)
	170	outbytesleft = ctypes.c_size_t(output_len) # no overflow
	171	assert outbytesleft.value == output_len
	172	rc = _iconv(cd, *map(ctypes.byref, [
	173	ctypes.cast(inbuf, ctypes.POINTER(ctypes.c_char)), inbytesleft,
	174	ctypes.cast(outbuf, ctypes.POINTER(ctypes.c_char)), outbytesleft,
	175	]))
	176	if rc == ctypes.c_size_t(-1).value:
	177	rc = ctypes.get_errno()
	178	if rc == errno.E2BIG:
	179	output_len *= 2
	180	continue
	181	elif rc in {errno.EILSEQ, errno.EINVAL}:
	182	begin = len(input) - inbytesleft.value
	183	for end in range(begin + 1, len(input)):
	184	# Assume that the encoding can be synchronized on ASCII characters.
	185	# That's not necessarily true for _every_ encoding, but oh well.
	186	if input[end] < 0x80:
	187	break
	188	else:
	189	end = len(input)
	190	raise UnicodeDecodeError(
	191	encoding,
	192	input,
	193	begin, end,
	194	os.strerror(errno.EILSEQ),
	195	)
	196	raise OSError(rc, os.strerror(rc))
	197	assert inbytesleft.value == 0, '{n} bytes left'.format(n=inbytesleft.value)
	198	output_len -= outbytesleft.value
	199	assert output_len % ctypes.sizeof(ctypes.c_wchar) == 0
	200	unicode_output_len = output_len // ctypes.sizeof(ctypes.c_wchar)
	201	return outbuf[:unicode_output_len]
	202	finally:
	203	rc = _iconv_close(cd)
	204	if rc != 0:
	205	rc = ctypes.get_errno()
	206	raise OSError(rc, os.strerror(rc))
	207
	208	def _decode_cli(input, *, encoding):
	209	child = _popen('iconv', '-f', encoding, '-t', 'UTF-8')
	210	(stdout, stderr) = child.communicate(input)
	211	if stderr != b'':
	212	stderr = stderr.decode('ASCII', 'replace')
	213	stderr = _boring_iconv_stderr.sub('', stderr)
	214	raise UnicodeDecodeError(encoding,
	215	input, # .object
	216	0, # .begin
	217	len(input), # .end
	218	stderr.strip() # .reason
	219	)
	220	return stdout.decode('UTF-8')
	221
	222	_decode = _decode_dl if _iconv is not None else _decode_cli
	223
	224	__all__ = ['encode', 'decode']
	225
	226	# vim:ts=4 sw=4 et

+1

-1

lib/intexpr.py less more

265	265
266	266	def _visit_div(self, node, x, y):
267	267	if y == (0, 0):
268		0 # division by zero
	268	# division by zero
269	269	return
270	270	assert y[1] > 0
271	271	return (

+7

-7

lib/ling.py less more

108	108	raise FixingLanguageCodesFailed()
109	109	elif cc != self.territory_code:
110	110	# This shouldn't really happen, but better safe than sorry.
111		raise ValueError # <no-coverage>
	111	raise ValueError # <no-coverage>
112	112	# TODO: ll_CC could be still incorrect, even when both ll and CC are
113	113	# correct.
114	114	self.language_code = ll

130	130	return True
131	131
132	132	def remove_encoding(self):
133		if self.encoding == None:
	133	if self.encoding is None:
134	134	return
135	135	self.encoding = None
136	136	return True

163	163	return
164	164	result = []
165	165	try:
166		# iconv-based encodings have huge overhead per encode() call. To
167		# reduce number of such calls, optimize the common case of all
168		# characters being representable.
	166	# If iconv(1) is used to implement an encoding, there's a huge
	167	# overhead per encode() call. To reduce number of such calls,
	168	# optimize the common case of all characters being representable.
169	169	''.join(characters).encode(encoding)
170	170	except UnicodeError:
171	171	pass

177	177	except UnicodeError as exc:
178	178	result += [character]
179	179	if exc.reason.startswith('iconv:'):
180		# Avoid further calls to iconv:
	180	# Avoid further calls to iconv(1):
181	181	break
182	182	return result
183	183

237	237	if ll:
238	238	try:
239	239	self._primary_languages[ll]
240		except LookupError: # <no-coverage>
	240	except LookupError: # <no-coverage>
241	241	raise misc.DataIntegrityError
242	242
243	243	def _lookup_language_code(self, language):

+1

-1

private/build-source-tarball less more

9	9	pwd="$PWD"
10	10	version="$1"
11	11	sourceroot=$(mktemp -d -t "$name-source-XXXXXX")
12		export TAR_OPTIONS="--owner root --group root --mode a+rX"
	12	export TAR_OPTIONS="--owner root --group root --mode a+rX --format ustar"
13	13	export GZIP="-9 -n"
14	14	mkdir -p "$sourceroot/$name-$version"
15	15	if [ -d .hg ]

+2

-0

private/tags-as-rst less more

19	19	# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
20	20	# SOFTWARE.
21	21
	22	import io
22	23	import os
23	24	import sys
24	25

51	52	print()
52	53
53	54	def main():
	55	sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='UTF-8')
54	56	datadir = os.path.join(basedir, 'data')
55	57	taginfo = tags.TagInfo(datadir)
56	58	output_tags_rst(taginfo)

+5

-0

private/update-coverage less more

49	49	print('[{check}] {tag}'.format(check=check, tag=tag.name))
50	50	sys.stdout.close()
51	51	os.rename(path + '.tmp', path)
	52	rc = 0
	53	for tag in sorted(set(coverage) - set(t.name for t in taginfo)):
	54	print('update-coverage: error: uknown tag {tag}'.format(tag=tag), file=sys.stderr)
	55	rc = 1
	56	sys.exit(rc)
52	57
53	58	if __name__ == '__main__':
54	59	main()

+6

-0

tests/__init__.py less more

	0	import sys
	1
	2	if sys.version_info < (3, 0):
	3	raise ImportError('Python >= 3 is required')
	4
	5	# vim:ts=4 sw=4 et

+51

-2

tests/blackbox_tests/__init__.py less more

22	22	import os
23	23	import re
24	24	import shlex
	25	import signal
25	26	import subprocess as ipc
26	27	import sys
27	28

101	102
102	103	# ----------------------------------------
103	104
	105	def _get_signal_names():
	106	data = dict(
	107	(name, getattr(signal, name))
	108	for name in dir(signal)
	109	if re.compile('^SIG[A-Z0-9]*$').match(name)
	110	)
	111	try:
	112	if data['SIGABRT'] == data['SIGIOT']:
	113	del data['SIGIOT']
	114	except KeyError:
	115	pass
	116	try:
	117	if data['SIGCHLD'] == data['SIGCLD']:
	118	del data['SIGCLD']
	119	except KeyError:
	120	pass
	121	for name, n in data.items():
	122	yield n, name
	123
	124	_signal_names = dict(_get_signal_names())
	125
	126	def get_signal_name(n):
	127	try:
	128	return _signal_names[n]
	129	except KeyError:
	130	return str(n)
	131
104	132	def assert_emit_tags(path, etags, *, options=()):
105	133	etags = list(etags)
106	134	commandline = os.environ.get('I18NSPECTOR_COMMANDLINE')

112	140	commandline += options
113	141	commandline += [path]
114	142	fixed_env = dict(os.environ, LC_ALL='C')
115		stdout = ipc.check_output(commandline, env=fixed_env)
116		stdout = stdout.decode('ASCII').splitlines()
	143	child = ipc.Popen(commandline, stdout=ipc.PIPE, stderr=ipc.PIPE, env=fixed_env)
	144	stdout, stderr = (
	145	s.decode().splitlines()
	146	for s in child.communicate()
	147	)
	148	rc = child.poll()
	149	if rc != 0:
	150	if rc < 0:
	151	message = ['command was interrupted by signal {sig}'.format(sig=get_signal_name(-rc))]
	152	else:
	153	message = ['command exited with status {rc}'.format(rc=rc)]
	154	message += ['']
	155	if stdout:
	156	message += ['stdout:']
	157	message += ['\| ' + s for s in stdout] + ['']
	158	else:
	159	message += ['stdout: (empty)']
	160	if stderr:
	161	message += ['stderr:']
	162	message += ['\| ' + s for s in stderr]
	163	else:
	164	message += ['stderr: (empty)']
	165	raise AssertionError('\n'.join(message))
117	166	if stdout != etags:
118	167	str_etags = [str(x) for x in etags]
119	168	message = ['Tags differ:', '']

+17

-0

tests/blackbox_tests/boilerplate-in-content-type.po less more

	0	# W: boilerplate-in-content-type 'text/plain; charset=CHARSET'
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=CHARSET\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14
	15	msgid "A quick brown fox jumps over the lazy dog."
	16	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/conflict-marker-in-header-entry.po less more

	0	# E: conflict-marker-in-header-entry '#-#-#-#-# la.po (Gizmo Enhancer 1.0) #-#-#-#-#'
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14	"#-#-#-#-# la.po (Gizmo Enhancer 1.0) #-#-#-#-#\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+21

-0

tests/blackbox_tests/conflict-marker-in-translation.po less more

	0	# E: conflict-marker-in-translation msgid 'A quick brown fox jumps over the lazy dog.' '#-#-#-#-# la.po (Gizmo Enhancer 1.0) #-#-#-#-#'
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14
	15	msgid "A quick brown fox jumps over the lazy dog."
	16	msgstr ""
	17	"#-#-#-#-# la.po (Gizmo Enhancer 1.0) #-#-#-#-#\n"
	18	"Sic fugiens, dux, zelotypos, quam Karus haberis.\n"
	19	"#-#-#-#-# pl.po (Gizmo Enhancer 1.0) #-#-#-#-#\n"
	20	"Mężny bądź, chroń pułk twój i sześć flag."

+14

-0

tests/blackbox_tests/coverage.txt less more

3	3	[X] ancient-date
4	4	[X] arithmetic-error-in-plural-forms
5	5	[X] arithmetic-error-in-unused-plural-forms
	6	[X] boilerplate-in-content-type
6	7	[X] boilerplate-in-language-team
7	8	[X] boilerplate-in-last-translator
8	9	[X] boilerplate-in-project-id-version

10	11	[X] broken-encoding
11	12	[X] codomain-error-in-plural-forms
12	13	[X] codomain-error-in-unused-plural-forms
	14	[X] conflict-marker-in-header-entry
	15	[X] conflict-marker-in-translation
13	16	[X] date-from-future
14	17	[X] duplicate-header-field
	18	[X] duplicate-header-field-content-transfer-encoding
	19	[X] duplicate-header-field-content-type
	20	[X] duplicate-header-field-date
	21	[X] duplicate-header-field-language
	22	[X] duplicate-header-field-language-team
	23	[X] duplicate-header-field-last-translator
	24	[X] duplicate-header-field-mime-version
	25	[X] duplicate-header-field-plural-forms
	26	[X] duplicate-header-field-project-id-version
	27	[X] duplicate-header-field-report-msgid-bugs-to
15	28	[X] duplicate-message-definition
16	29	[X] empty-file
17	30	[X] encoding-in-language-header-field
	31	[X] fuzzy-header-entry
18	32	[X] inconsistent-leading-newlines
19	33	[X] inconsistent-number-of-plural-forms
20	34	[X] inconsistent-trailing-newlines

+0

-18

~~tests/blackbox_tests/duplicate-field.po~~ less more

0		# E: duplicate-header-field Language
1
2		msgid ""
3		msgstr ""
4		"Project-Id-Version: Gizmo Enhancer 1.0\n"
5		"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
6		"POT-Creation-Date: 2012-11-01 14:42+0100\n"
7		"PO-Revision-Date: 2012-11-01 14:42+0100\n"
8		"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
9		"Language-Team: Latin Strike Force <la@li.org>\n"
10		"Language: la\n"
11		"Language: la\n"
12		"MIME-Version: 1.0\n"
13		"Content-Type: text/plain; charset=UTF-8\n"
14		"Content-Transfer-Encoding: 8bit\n"
15
16		msgid "A quick brown fox jumps over the lazy dog."
17		msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-content-transfer-encoding.po less more

	0	# P: duplicate-header-field-content-transfer-encoding
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-content-type.po less more

	0	# E: duplicate-header-field-content-type
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-language-team.po less more

	0	# W: duplicate-header-field-language-team
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+19

-0

tests/blackbox_tests/duplicate-header-field-language.po less more

	0	# W: duplicate-header-field-language
	1	# I: unable-to-determine-language
	2
	3	msgid ""
	4	msgstr ""
	5	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"Language: la\n"
	13	"MIME-Version: 1.0\n"
	14	"Content-Type: text/plain; charset=UTF-8\n"
	15	"Content-Transfer-Encoding: 8bit\n"
	16
	17	msgid "A quick brown fox jumps over the lazy dog."
	18	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-last-translator.po less more

	0	# W: duplicate-header-field-last-translator
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-mime-version.po less more

	0	# P: duplicate-header-field-mime-version
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+22

-0

tests/blackbox_tests/duplicate-header-field-plural-forms.po less more

	0	# E: duplicate-header-field-plural-forms
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Polish <pl@li.org>\n"
	10	"Language: pl\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14	"Plural-Forms: nplurals=3; plural=n==1 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 \|\| n%100>=20) ? 1 : 2;\n"
	15	"Plural-Forms: nplurals=3; plural=n==1 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 \|\| n%100>=20) ? 1 : 2;\n"
	16
	17	msgid "%d quick brown fox jumps over the lazy dog."
	18	msgid_plural "%d quick brown foxes jump over the lazy dog."
	19	msgstr[0] "Mężny bądź, chroń pułk twój i %d flagę."
	20	msgstr[1] "Mężny bądź, chroń pułk twój i %d flagi."
	21	msgstr[2] "Mężny bądź, chroń pułk twój i %d flag."

+18

-0

tests/blackbox_tests/duplicate-header-field-po-revision-date.po less more

	0	# W: duplicate-header-field-date PO-Revision-Date
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-pot-creation-date.po less more

	0	# W: duplicate-header-field-date POT-Creation-Date
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-project-id-version.po less more

	0	# W: duplicate-header-field-project-id-version
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/duplicate-header-field-report-msgid-bugs-to.po less more

	0	# W: duplicate-header-field-report-msgid-bugs-to
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+19

-0

tests/blackbox_tests/duplicate-header-field.po less more

	0	# I: duplicate-header-field Generated-By
	1
	2	msgid ""
	3	msgstr ""
	4	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	5	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	6	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	7	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	8	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	9	"Language-Team: Latin Strike Force <la@li.org>\n"
	10	"Language: la\n"
	11	"MIME-Version: 1.0\n"
	12	"Content-Type: text/plain; charset=UTF-8\n"
	13	"Content-Transfer-Encoding: 8bit\n"
	14	"Generated-By: VIM 7.3\n"
	15	"Generated-By: VIM 7.3\n"
	16
	17	msgid "A quick brown fox jumps over the lazy dog."
	18	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/fuzzy-header-entry.po less more

	0	# P: fuzzy-header-entry
	1
	2	#, fuzzy
	3	msgid ""
	4	msgstr ""
	5	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/stray-header-line-1.po less more

	0	# W: stray-header-line 'MIME-Version 1.0'
	1	# P: no-mime-version-header-field MIME-Version: 1.0
	2
	3	msgid ""
	4	msgstr ""
	5	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date: 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+18

-0

tests/blackbox_tests/stray-header-line-2.po less more

	0	# W: stray-header-line 'POT-Creation-Date 2012-11-01 14:'
	1	# W: no-date-header-field POT-Creation-Date
	2
	3	msgid ""
	4	msgstr ""
	5	"Project-Id-Version: Gizmo Enhancer 1.0\n"
	6	"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
	7	"POT-Creation-Date 2012-11-01 14:42+0100\n"
	8	"PO-Revision-Date: 2012-11-01 14:42+0100\n"
	9	"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
	10	"Language-Team: Latin Strike Force <la@li.org>\n"
	11	"Language: la\n"
	12	"MIME-Version: 1.0\n"
	13	"Content-Type: text/plain; charset=UTF-8\n"
	14	"Content-Transfer-Encoding: 8bit\n"
	15
	16	msgid "A quick brown fox jumps over the lazy dog."
	17	msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+0

-18

~~tests/blackbox_tests/stray-header-line.po~~ less more

0		# W: stray-header-line 'MIME-Version 1.0'
1		# P: no-mime-version-header-field MIME-Version: 1.0
2
3		msgid ""
4		msgstr ""
5		"Project-Id-Version: Gizmo Enhancer 1.0\n"
6		"Report-Msgid-Bugs-To: gizmoenhancer@jwilk.net\n"
7		"POT-Creation-Date: 2012-11-01 14:42+0100\n"
8		"PO-Revision-Date: 2012-11-01 14:42+0100\n"
9		"Last-Translator: Jakub Wilk <jwilk@jwilk.net>\n"
10		"Language-Team: Latin Strike Force <la@li.org>\n"
11		"Language: la\n"
12		"MIME-Version 1.0\n"
13		"Content-Type: text/plain; charset=UTF-8\n"
14		"Content-Transfer-Encoding: 8bit\n"
15
16		msgid "A quick brown fox jumps over the lazy dog."
17		msgstr "Sic fugiens, dux, zelotypos, quam Karus haberis."

+8

-9

tests/test_gettext.py less more

93	93	def test_plural_exp_and(self):
94	94	self._pe('n && 6', 7, 1)
95	95	self._pe('n && 6', 0, 0)
96		self._pe('n && (6 / 0)', 0, 0) # no ZeroDivisionError
	96	self._pe('n && (6 / 0)', 0, 0) # no ZeroDivisionError
97	97	self._pe('n && 0', 7, 0)
98	98	self._pe('n && 0', 0, 0)
99	99
100	100	def test_plural_exp_or(self):
101	101	self._pe('n \|\| 6', 7, 1)
102		self._pe('n \|\| (6 / 0)', 7, 1) # no ZeroDivisionError
	102	self._pe('n \|\| (6 / 0)', 7, 1) # no ZeroDivisionError
103	103	self._pe('n \|\| 6', 0, 1)
104	104	self._pe('n \|\| 0', 7, 1)
105	105	self._pe('n \|\| 0', 0, 0)

135	135	self._pe('n != 37', 42, 1)
136	136
137	137	def test_plural_exp_multi_compare(self):
138		self._pe('1 < n == 3 <= 4', 1, 0) # False in Python
139		self._pe('1 < n == 3 <= 4', 2, 1) # False in Python
140		self._pe('1 < n == 3 <= 4', 3, 1) # True in Python
141		self._pe('1 < n == 3 <= 4', 4, 1) # False in Python
142		self._pe('2 == 2 == n', 2, 0) # True in Python
143		self._pe('2 == 2 == n', 1, 1) # False in Python
	138	self._pe('1 < n == 3 <= 4', 1, 0) # False in Python
	139	self._pe('1 < n == 3 <= 4', 2, 1) # False in Python
	140	self._pe('1 < n == 3 <= 4', 3, 1) # True in Python
	141	self._pe('1 < n == 3 <= 4', 4, 1) # False in Python
	142	self._pe('2 == 2 == n', 2, 0) # True in Python
	143	self._pe('2 == 2 == n', 1, 1) # False in Python
144	144
145	145	def test_plural_exp_neg(self):
146	146	self._pe('! n', 0, 1)

192	192	else:
193	193	assert_equal(new, expected)
194	194
195
196	195	def test_boilerplate(self):
197	196	self._test('YEAR-MO-DA HO:MI+ZONE', None)
198	197

+0

-1

tests/test_ling.py less more

397	397	with E.extra_encodings():
398	398	result = lang.get_unrepresentable_characters(encoding)
399	399	assert_not_equal(result, [])
400		assert_equal(len(result), 1)
401	400
402	401	# vim:ts=4 sw=4 et

+1

-1

tests/test_tags.py less more

25	25
26	26	class test_escape:
27	27
28		_esc = staticmethod(lib.tags._escape) # FIXME: _escape is private
	28	_esc = staticmethod(lib.tags._escape) # FIXME: _escape is private
29	29
30	30	def _test(self, s, expected):
31	31	assert_equal(