9441244789

Committed 10 Jun 2024 01:45AM UTC coverage: 49.048% (-11.6%) from 60.675%

Build # 9441244789

Build Type

push

github

Committed by

web-flow

Commit Message

Merge 8a4989eae into 519864108

Run Details

8320 of 16963 relevant lines covered (49.05%)

1813.12 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/languages/tr.lua

1	-- Different years of TDK and various publisher style guides differ on this point.
2	-- Current official guidance suggests dropping the hypenation mark if the break
3	-- occurs at an apostrophe (kesme işareti). Some older guidance and some publishers
4	-- suggest dropping the apostrophe instead.
5	SILE.settings:declare({	×
6	parameter = "languages.tr.replaceApostropheAtHyphenation",
7	type = "boolean",
8	default = false,
9	help = "If enabled, substitute the apostophe for a hyphen at break points, otherwise keep the apostrophe and hide the hyphen.",
10	})
11
12	-- Quotes may be part of a word in Turkish
13	SILE.nodeMakers.tr = pl.class(SILE.nodeMakers.unicode)	×
14	SILE.nodeMakers.tr.wordTypes = { cm = true, qu = true }	×
15
16	SILE.hyphenator.languages["tr"] = {}	×
17
18	SILE.hyphenator.languages["tr"].hyphenateSegments = function (node, segments, j)	×
19	local hyphenChar, replacement
20	local maybeNextApostrophe = #segments > j and luautf8.match(segments[j + 1], "^['’]")	×
21	if maybeNextApostrophe then	×
22	segments[j + 1] = luautf8.gsub(segments[j + 1], "^['’]", "")	×
23	if SILE.settings:get("languages.tr.replaceApostropheAtHyphenation") then	×
24	hyphenChar = SILE.settings:get("font.hyphenchar")	×
25	else
26	hyphenChar = maybeNextApostrophe	×
27	replacement = SILE.shaper:createNnodes(maybeNextApostrophe, node.options)	×
28	end
29	else
30	hyphenChar = SILE.settings:get("font.hyphenchar")	×
31	end
32	local hyphen = SILE.shaper:createNnodes(hyphenChar, node.options)	×
33	return SILE.types.node.discretionary({ replacement = replacement, prebreak = hyphen }), segments	×
34	end
35
36	SILE.hyphenator.languages["tr"].patterns = {	×
37	"2a1",
38	"2â1",
39	"2e1",
40	"2ı1",
41	"2i1",
42	"2î1",
43	"2o1",
44	"2ö1",
45	"2u1",
46	"2ü1",
47	"2û1",
48	-- allow hyphen either side of consonants
49	"1b1",
50	"1c1",
51	"1ç1",
52	"1d1",
53	"1f1",
54	"1g1",
55	"1ğ1",
56	"1h1",
57	"1j1",
58	"1k1",
59	"1l1",
60	"1m1",
61	"1n1",
62	"1p1",
63	"1r1",
64	"1s1",
65	"1ş1",
66	"1t1",
67	"1v1",
68	"1y1",
69	"1z1",
70	-- prevent a-cak/e-cek at end of word
71	"2a2cak.",
72	"2e2cek.",
73	-- prohibit hyphen before pair of consonants
74	-- many pairs generated here are impossible anyway
75	"2bb",
76	"2bc",
77	"2bç",
78	"2bd",
79	"2bf",
80	"2bg",
81	"2bğ",
82	"2bh",
83	"2bj",
84	"2bk",
85	"2bl",
86	"2bm",
87	"2bn",
88	"2bp",
89	"2br",
90	"2bs",
91	"2bş",
92	"2bt",
93	"2bv",
94	"2by",
95	"2bz",
96	"2cb",
97	"2cc",
98	"2cç",
99	"2cd",
100	"2cf",
101	"2cg",
102	"2cğ",
103	"2ch",
104	"2cj",
105	"2ck",
106	"2cl",
107	"2cm",
108	"2cn",
109	"2cp",
110	"2cr",
111	"2cs",
112	"2cş",
113	"2ct",
114	"2cv",
115	"2cy",
116	"2cz",
117	"2çb",
118	"2çc",
119	"2çç",
120	"2çd",
121	"2çf",
122	"2çg",
123	"2çğ",
124	"2çh",
125	"2çj",
126	"2çk",
127	"2çl",
128	"2çm",
129	"2çn",
130	"2çp",
131	"2çr",
132	"2çs",
133	"2çş",
134	"2çt",
135	"2çv",
136	"2çy",
137	"2çz",
138	"2db",
139	"2dc",
140	"2dç",
141	"2dd",
142	"2df",
143	"2dg",
144	"2dğ",
145	"2dh",
146	"2dj",
147	"2dk",
148	"2dl",
149	"2dm",
150	"2dn",
151	"2dp",
152	"2dr",
153	"2ds",
154	"2dş",
155	"2dt",
156	"2dv",
157	"2dy",
158	"2dz",
159	"2fb",
160	"2fc",
161	"2fç",
162	"2fd",
163	"2ff",
164	"2fg",
165	"2fğ",
166	"2fh",
167	"2fj",
168	"2fk",
169	"2fl",
170	"2fm",
171	"2fn",
172	"2fp",
173	"2fr",
174	"2fs",
175	"2fş",
176	"2ft",
177	"2fv",
178	"2fy",
179	"2fz",
180	"2gb",
181	"2gc",
182	"2gç",
183	"2gd",
184	"2gf",
185	"2gg",
186	"2gğ",
187	"2gh",
188	"2gj",
189	"2gk",
190	"2gl",
191	"2gm",
192	"2gn",
193	"2gp",
194	"2gr",
195	"2gs",
196	"2gş",
197	"2gt",
198	"2gv",
199	"2gy",
200	"2gz",
201	"2ğb",
202	"2ğc",
203	"2ğç",
204	"2ğd",
205	"2ğf",
206	"2ğg",
207	"2ğğ",
208	"2ğh",
209	"2ğj",
210	"2ğk",
211	"2ğl",
212	"2ğm",
213	"2ğn",
214	"2ğp",
215	"2ğr",
216	"2ğs",
217	"2ğş",
218	"2ğt",
219	"2ğv",
220	"2ğy",
221	"2ğz",
222	"2hb",
223	"2hc",
224	"2hç",
225	"2hd",
226	"2hf",
227	"2hg",
228	"2hğ",
229	"2hh",
230	"2hj",
231	"2hk",
232	"2hl",
233	"2hm",
234	"2hn",
235	"2hp",
236	"2hr",
237	"2hs",
238	"2hş",
239	"2ht",
240	"2hv",
241	"2hy",
242	"2hz",
243	"2jb",
244	"2jc",
245	"2jç",
246	"2jd",
247	"2jf",
248	"2jg",
249	"2jğ",
250	"2jh",
251	"2jj",
252	"2jk",
253	"2jl",
254	"2jm",
255	"2jn",
256	"2jp",
257	"2jr",
258	"2js",
259	"2jş",
260	"2jt",
261	"2jv",
262	"2jy",
263	"2jz",
264	"2kb",
265	"2kc",
266	"2kç",
267	"2kd",
268	"2kf",
269	"2kg",
270	"2kğ",
271	"2kh",
272	"2kj",
273	"2kk",
274	"2kl",
275	"2km",
276	"2kn",
277	"2kp",
278	"2kr",
279	"2ks",
280	"2kş",
281	"2kt",
282	"2kv",
283	"2ky",
284	"2kz",
285	"2lb",
286	"2lc",
287	"2lç",
288	"2ld",
289	"2lf",
290	"2lg",
291	"2lğ",
292	"2lh",
293	"2lj",
294	"2lk",
295	"2ll",
296	"2lm",
297	"2ln",
298	"2lp",
299	"2lr",
300	"2ls",
301	"2lş",
302	"2lt",
303	"2lv",
304	"2ly",
305	"2lz",
306	"2mb",
307	"2mc",
308	"2mç",
309	"2md",
310	"2mf",
311	"2mg",
312	"2mğ",
313	"2mh",
314	"2mj",
315	"2mk",
316	"2ml",
317	"2mm",
318	"2mn",
319	"2mp",
320	"2mr",
321	"2ms",
322	"2mş",
323	"2mt",
324	"2mv",
325	"2my",
326	"2mz",
327	"2nb",
328	"2nc",
329	"2nç",
330	"2nd",
331	"2nf",
332	"2ng",
333	"2nğ",
334	"2nh",
335	"2nj",
336	"2nk",
337	"2nl",
338	"2nm",
339	"2nn",
340	"2np",
341	"2nr",
342	"2ns",
343	"2nş",
344	"2nt",
345	"2nv",
346	"2ny",
347	"2nz",
348	"2pb",
349	"2pc",
350	"2pç",
351	"2pd",
352	"2pf",
353	"2pg",
354	"2pğ",
355	"2ph",
356	"2pj",
357	"2pk",
358	"2pl",
359	"2pm",
360	"2pn",
361	"2pp",
362	"2pr",
363	"2ps",
364	"2pş",
365	"2pt",
366	"2pv",
367	"2py",
368	"2pz",
369	"2rb",
370	"2rc",
371	"2rç",
372	"2rd",
373	"2rf",
374	"2rg",
375	"2rğ",
376	"2rh",
377	"2rj",
378	"2rk",
379	"2rl",
380	"2rm",
381	"2rn",
382	"2rp",
383	"2rr",
384	"2rs",
385	"2rş",
386	"2rt",
387	"2rv",
388	"2ry",
389	"2rz",
390	"2sb",
391	"2sc",
392	"2sç",
393	"2sd",
394	"2sf",
395	"2sg",
396	"2sğ",
397	"2sh",
398	"2sj",
399	"2sk",
400	"2sl",
401	"2sm",
402	"2sn",
403	"2sp",
404	"2sr",
405	"2ss",
406	"2sş",
407	"2st",
408	"2sv",
409	"2sy",
410	"2sz",
411	"2şb",
412	"2şc",
413	"2şç",
414	"2şd",
415	"2şf",
416	"2şg",
417	"2şğ",
418	"2şh",
419	"2şj",
420	"2şk",
421	"2şl",
422	"2şm",
423	"2şn",
424	"2şp",
425	"2şr",
426	"2şs",
427	"2şş",
428	"2şt",
429	"2şv",
430	"2şy",
431	"2şz",
432	"2tb",
433	"2tc",
434	"2tç",
435	"2td",
436	"2tf",
437	"2tg",
438	"2tğ",
439	"2th",
440	"2tj",
441	"2tk",
442	"2tl",
443	"2tm",
444	"2tn",
445	"2tp",
446	"2tr",
447	"2ts",
448	"2tş",
449	"2tt",
450	"2tv",
451	"2ty",
452	"2tz",
453	"2vb",
454	"2vc",
455	"2vç",
456	"2vd",
457	"2vf",
458	"2vg",
459	"2vğ",
460	"2vh",
461	"2vj",
462	"2vk",
463	"2vl",
464	"2vm",
465	"2vn",
466	"2vp",
467	"2vr",
468	"2vs",
469	"2vş",
470	"2vt",
471	"2vv",
472	"2vy",
473	"2vz",
474	"2yb",
475	"2yc",
476	"2yç",
477	"2yd",
478	"2yf",
479	"2yg",
480	"2yğ",
481	"2yh",
482	"2yj",
483	"2yk",
484	"2yl",
485	"2ym",
486	"2yn",
487	"2yp",
488	"2yr",
489	"2ys",
490	"2yş",
491	"2yt",
492	"2yv",
493	"2yy",
494	"2yz",
495	"2zb",
496	"2zc",
497	"2zç",
498	"2zd",
499	"2zf",
500	"2zg",
501	"2zğ",
502	"2zh",
503	"2zj",
504	"2zk",
505	"2zl",
506	"2zm",
507	"2zn",
508	"2zp",
509	"2zr",
510	"2zs",
511	"2zş",
512	"2zt",
513	"2zv",
514	"2zy",
515	"2zz",
516	-- allow hyphen between vowels, but not after second vowel of pair
517	-- several phonetically impossible pairs here
518	"a3a2",
519	"a3â2",
520	"a3e2",
521	"a3ı2",
522	"a3i2",
523	"a3î2",
524	"a3o2",
525	"a3ö2",
526	"a3u2",
527	"a3ü2",
528	"a3û2",
529	"â3a2",
530	"â3â2",
531	"â3e2",
532	"â3ı2",
533	"â3i2",
534	"â3î2",
535	"â3o2",
536	"â3ö2",
537	"â3u2",
538	"â3ü2",
539	"â3û2",
540	"e3a2",
541	"e3â2",
542	"e3e2",
543	"e3ı2",
544	"e3i2",
545	"e3î2",
546	"e3o2",
547	"e3ö2",
548	"e3u2",
549	"e3ü2",
550	"e3û2",
551	"ı3a2",
552	"ı3â2",
553	"ı3e2",
554	"ı3ı2",
555	"ı3i2",
556	"ı3î2",
557	"ı3o2",
558	"ı3ö2",
559	"ı3u2",
560	"ı3ü2",
561	"ı3û2",
562	"i3a2",
563	"i3â2",
564	"i3e2",
565	"i3ı2",
566	"i3i2",
567	"i3î2",
568	"i3o2",
569	"i3ö2",
570	"i3u2",
571	"i3ü2",
572	"i3û2",
573	"î3a2",
574	"î3â2",
575	"î3e2",
576	"î3ı2",
577	"î3i2",
578	"î3î2",
579	"î3o2",
580	"î3ö2",
581	"î3u2",
582	"î3ü2",
583	"î3û2",
584	"o3a2",
585	"o3â2",
586	"o3e2",
587	"o3ı2",
588	"o3i2",
589	"o3î2",
590	"o3o2",
591	"o3ö2",
592	"o3u2",
593	"o3ü2",
594	"o3û2",
595	"ö3a2",
596	"ö3â2",
597	"ö3e2",
598	"ö3ı2",
599	"ö3i2",
600	"ö3î2",
601	"ö3o2",
602	"ö3ö2",
603	"ö3u2",
604	"ö3ü2",
605	"ö3û2",
606	"u3a2",
607	"u3â2",
608	"u3e2",
609	"u3ı2",
610	"u3i2",
611	"u3î2",
612	"u3o2",
613	"u3ö2",
614	"u3u2",
615	"u3ü2",
616	"u3û2",
617	"ü3a2",
618	"ü3â2",
619	"ü3e2",
620	"ü3ı2",
621	"ü3i2",
622	"ü3î2",
623	"ü3o2",
624	"ü3ö2",
625	"ü3u2",
626	"ü3ü2",
627	"ü3û2",
628	"û3a2",
629	"û3â2",
630	"û3e2",
631	"û3ı2",
632	"û3i2",
633	"û3î2",
634	"û3o2",
635	"û3ö2",
636	"û3u2",
637	"û3ü2",
638	"û3û2",
639	-- a couple of consonant-clusters
640	"tu4r4k",
641	"m1t4rak",
642	-- See https://github.com/sile-typesetter/sile/issues/355
643	-- Allow hyphenation to apply before apostrophes (before per pattern rules but
644	-- will be substututed later, allowing after breaks minright), but work around
645	-- minleft not being applied mid-word by excluding all possible single letter
646	-- candidates before apostrophes.
647	"1'2",
648	"1’2",
649	"4a1'",
650	"4a1’",
651	"4â1'",
652	"4â1’",
653	"4b1'",
654	"4b1’",
655	"4c1'",
656	"4c1’",
657	"4ç1'",
658	"4ç1’",
659	"4d1'",
660	"4d1’",
661	"4e1'",
662	"4e1’",
663	"4f1'",
664	"4f1’",
665	"4g1'",
666	"4g1’",
667	"4ğ1'",
668	"4ğ1’",
669	"4h1'",
670	"4h1’",
671	"4j1'",
672	"4j1’",
673	"4k1'",
674	"4k1’",
675	"4ı1'",
676	"4ı1’",
677	"4i1'",
678	"4i1’",
679	"4î1'",
680	"4î1’",
681	"4l1'",
682	"4l1’",
683	"4m1'",
684	"4m1’",
685	"4n1'",
686	"4n1’",
687	"4o1'",
688	"4o1’",
689	"4ö1'",
690	"4ö1’",
691	"4p1'",
692	"4p1’",
693	"4r1'",
694	"4r1’",
695	"4s1'",
696	"4s1’",
697	"4ş1'",
698	"4ş1’",
699	"4t1'",
700	"4t1’",
701	"4u1'",
702	"4u1’",
703	"4ü1'",
704	"4ü1’",
705	"4û1'",
706	"4û1’",
707	"4v1'",
708	"4v1’",
709	"4y1'",
710	"4y1’",
711	"4z1'",
712	"4z1’",
713	}
714
715	-- Internationalisation stuff
716
717	-- local sum_tens = function (val, loc, digits)
718	-- local ten = string.sub(digits, loc+1, loc+1)
719	-- if ten:len() == 1 then val = val + tonumber(ten) * 10 end
720	-- return val
721	-- end
722
723	local sum_hundreds = function (val, loc, digits)
724	local ten = string.sub(digits, loc + 1, loc + 1)	×
725	local hundred = string.sub(digits, loc + 2, loc + 2)	×
726	if ten:len() == 1 then	×
727	val = val + tonumber(ten) * 10	×
728	end
729	if hundred:len() == 1 then	×
730	val = val + tonumber(hundred) * 100	×
731	end
732	return val	×
733	end
734
735	local tr_nums = function (num, ordinal)
736	local abs = math.abs(num)	×
737	if abs >= 1e+36 then	×
738	SU.error("Numbers past decillions not supported in Turkish")	×
739	end
740	ordinal = SU.boolean(ordinal, false)	×
741	local minus = "eksi"	×
742	local zero = "sıfır"	×
743	local ones = { "bir", "iki", "üç", "dört", "beş", "altı", "yedi", "sekiz", "dokuz" }	×
744	local tens = { "on", "yirmi", "otuz", "kırk", "eli", "altmış", "yetmiş", "seksen", "doksan" }	×
745	local places = {	×
746	"yüz",
747	"bin",
748	"milyon",
749	"milyar",
750	"trilyon",
751	"katrilyon",
752	"kentilyon",
753	"sekstilyon",
754	"septilyon",
755	"oktilyon",
756	"nonilyon",
757	"desilyon",
758	}
759	local zeroordinal = "sıfırıncı"	×
760	local onesordinals =
761	{ "birinci", "ikinci", "üçüncü", "dördüncü", "beşinci", "altıncı", "yedinci", "sekizinci", "dokuzuncu" }	×
762	local tensordinals = {	×
763	"onuncu",
764	"yirmiyinci",
765	"otuzuncu",
766	"kırkıncı",
767	"eliyinci",
768	"altmışıncı",
769	"yetmişinci",
770	"sekseninci",
771	"Doksanıncı",
772	}
773	local placesordinals = {	×
774	"yüzüncü",
775	"bininci",
776	"milyonuncu",
777	"milyarıncı",
778	"trilyonuncu",
779	"katrilyonuncu",
780	"kentilyonuncu",
781	"sekstilyonuncu",
782	"septilyonuncu",
783	"oktilyonuncu",
784	"nonilyonuncu",
785	"desilyonuncu",
786	}
787	local digits = string.reverse(string.format("%.f", abs))	×
788	local words = {}	×
789	for i = 1, #digits do	×
790	local val, place, mod = tonumber(string.sub(digits, i, i)), math.floor(i / 3), i % 3	×
791	if #digits == 1 and val == 0 then	×
792	words[#words + 1] = ordinal and zeroordinal or zero	×
793	elseif val >= 1 or i > 1 then	×
794	if i == 1 then	×
795	words[#words + 1] = ordinal and onesordinals[val] or ones[val]	×
796	ordinal = false	×
797	elseif mod == 2 then	×
798	if val >= 1 then	×
799	words[#words + 1] = ordinal and tensordinals[val] or tens[val]	×
800	ordinal = false	×
801	end
802	elseif mod == 1 then	×
803	if sum_hundreds(val, i, digits) >= 1 then	×
804	words[#words + 1] = ordinal and placesordinals[place + 1] or places[place + 1]	×
805	ordinal = false	×
806	if val > 0 and (i >= 7 or sum_hundreds(val, i, digits) >= 2) then	×
807	words[#words + 1] = ones[val]	×
808	end
809	end
810	elseif mod == 0 then	×
811	if val > 0 then	×
812	words[#words + 1] = ordinal and placesordinals[1] or places[1]	×
813	ordinal = false	×
814	end
815	if val >= 2 then	×
816	words[#words + 1] = ones[val]	×
817	end
818	end
819	end
820	end
821	if abs > num then	×
822	words[#words + 1] = minus	×
823	end
824	SU.flip_in_place(words)	×
825	return table.concat(words, " ")	×
826	end
827
828	SU.formatNumber.tr = {	×
829	string = function (num, _)
830	return tr_nums(num, false)	×
831	end,
832	["ordinal-string"] = function (num, _)
833	return tr_nums(num, true)	×
834	end,
835	}

sile-typesetter / sile / 9441244789

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous