11124789710

Committed 01 Oct 2024 11:57AM UTC coverage: 29.567% (-31.4%) from 60.926%

Build # 11124789710

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #2105 from Omikhleia/refactor-collated-sort

Run Details

0 of 10 new or added lines in 1 file covered. (0.0%)

5252 existing lines in 53 files now uncovered.

5048 of 17073 relevant lines covered (29.57%)

1856.13 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 hyphenation mark if the break
3	-- occurs at an apostrophe (kesme işareti). Some older guidance and some publishers
4	-- suggest dropping the apostrophe instead.
UNCOV 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
UNCOV 13	SILE.nodeMakers.tr = pl.class(SILE.nodeMakers.unicode)	×
UNCOV 14	SILE.nodeMakers.tr.wordTypes = { cm = true, qu = true }	×
15
UNCOV 16	SILE.hyphenator.languages["tr"] = {}	×
17
UNCOV 18	SILE.hyphenator.languages["tr"].hyphenateSegments = function (node, segments, j)	×
19	local hyphenChar, replacement
UNCOV 20	local maybeNextApostrophe = #segments > j and luautf8.match(segments[j + 1], "^['’]")	×
UNCOV 21	if maybeNextApostrophe then	×
UNCOV 22	segments[j + 1] = luautf8.gsub(segments[j + 1], "^['’]", "")	×
UNCOV 23	if SILE.settings:get("languages.tr.replaceApostropheAtHyphenation") then	×
UNCOV 24	hyphenChar = SILE.settings:get("font.hyphenchar")	×
25	else
UNCOV 26	hyphenChar = maybeNextApostrophe	×
UNCOV 27	replacement = SILE.shaper:createNnodes(maybeNextApostrophe, node.options)	×
28	end
29	else
UNCOV 30	hyphenChar = SILE.settings:get("font.hyphenchar")	×
31	end
UNCOV 32	local hyphen = SILE.shaper:createNnodes(hyphenChar, node.options)	×
UNCOV 33	return SILE.types.node.discretionary({ replacement = replacement, prebreak = hyphen }), segments	×
34	end
35
36	-- typos: ignore start
UNCOV 37	SILE.hyphenator.languages["tr"].patterns = {	×
38	"2a1",
39	"2â1",
40	"2e1",
41	"2ı1",
42	"2i1",
43	"2î1",
44	"2o1",
45	"2ö1",
46	"2u1",
47	"2ü1",
48	"2û1",
49	-- allow hyphen either side of consonants
50	"1b1",
51	"1c1",
52	"1ç1",
53	"1d1",
54	"1f1",
55	"1g1",
56	"1ğ1",
57	"1h1",
58	"1j1",
59	"1k1",
60	"1l1",
61	"1m1",
62	"1n1",
63	"1p1",
64	"1r1",
65	"1s1",
66	"1ş1",
67	"1t1",
68	"1v1",
69	"1y1",
70	"1z1",
71	-- prevent a-cak/e-cek at end of word
72	"2a2cak.",
73	"2e2cek.",
74	-- prohibit hyphen before pair of consonants
75	-- many pairs generated here are impossible anyway
76	"2bb",
77	"2bc",
78	"2bç",
79	"2bd",
80	"2bf",
81	"2bg",
82	"2bğ",
83	"2bh",
84	"2bj",
85	"2bk",
86	"2bl",
87	"2bm",
88	"2bn",
89	"2bp",
90	"2br",
91	"2bs",
92	"2bş",
93	"2bt",
94	"2bv",
95	"2by",
96	"2bz",
97	"2cb",
98	"2cc",
99	"2cç",
100	"2cd",
101	"2cf",
102	"2cg",
103	"2cğ",
104	"2ch",
105	"2cj",
106	"2ck",
107	"2cl",
108	"2cm",
109	"2cn",
110	"2cp",
111	"2cr",
112	"2cs",
113	"2cş",
114	"2ct",
115	"2cv",
116	"2cy",
117	"2cz",
118	"2çb",
119	"2çc",
120	"2çç",
121	"2çd",
122	"2çf",
123	"2çg",
124	"2çğ",
125	"2çh",
126	"2çj",
127	"2çk",
128	"2çl",
129	"2çm",
130	"2çn",
131	"2çp",
132	"2çr",
133	"2çs",
134	"2çş",
135	"2çt",
136	"2çv",
137	"2çy",
138	"2çz",
139	"2db",
140	"2dc",
141	"2dç",
142	"2dd",
143	"2df",
144	"2dg",
145	"2dğ",
146	"2dh",
147	"2dj",
148	"2dk",
149	"2dl",
150	"2dm",
151	"2dn",
152	"2dp",
153	"2dr",
154	"2ds",
155	"2dş",
156	"2dt",
157	"2dv",
158	"2dy",
159	"2dz",
160	"2fb",
161	"2fc",
162	"2fç",
163	"2fd",
164	"2ff",
165	"2fg",
166	"2fğ",
167	"2fh",
168	"2fj",
169	"2fk",
170	"2fl",
171	"2fm",
172	"2fn",
173	"2fp",
174	"2fr",
175	"2fs",
176	"2fş",
177	"2ft",
178	"2fv",
179	"2fy",
180	"2fz",
181	"2gb",
182	"2gc",
183	"2gç",
184	"2gd",
185	"2gf",
186	"2gg",
187	"2gğ",
188	"2gh",
189	"2gj",
190	"2gk",
191	"2gl",
192	"2gm",
193	"2gn",
194	"2gp",
195	"2gr",
196	"2gs",
197	"2gş",
198	"2gt",
199	"2gv",
200	"2gy",
201	"2gz",
202	"2ğb",
203	"2ğc",
204	"2ğç",
205	"2ğd",
206	"2ğf",
207	"2ğg",
208	"2ğğ",
209	"2ğh",
210	"2ğj",
211	"2ğk",
212	"2ğl",
213	"2ğm",
214	"2ğn",
215	"2ğp",
216	"2ğr",
217	"2ğs",
218	"2ğş",
219	"2ğt",
220	"2ğv",
221	"2ğy",
222	"2ğz",
223	"2hb",
224	"2hc",
225	"2hç",
226	"2hd",
227	"2hf",
228	"2hg",
229	"2hğ",
230	"2hh",
231	"2hj",
232	"2hk",
233	"2hl",
234	"2hm",
235	"2hn",
236	"2hp",
237	"2hr",
238	"2hs",
239	"2hş",
240	"2ht",
241	"2hv",
242	"2hy",
243	"2hz",
244	"2jb",
245	"2jc",
246	"2jç",
247	"2jd",
248	"2jf",
249	"2jg",
250	"2jğ",
251	"2jh",
252	"2jj",
253	"2jk",
254	"2jl",
255	"2jm",
256	"2jn",
257	"2jp",
258	"2jr",
259	"2js",
260	"2jş",
261	"2jt",
262	"2jv",
263	"2jy",
264	"2jz",
265	"2kb",
266	"2kc",
267	"2kç",
268	"2kd",
269	"2kf",
270	"2kg",
271	"2kğ",
272	"2kh",
273	"2kj",
274	"2kk",
275	"2kl",
276	"2km",
277	"2kn",
278	"2kp",
279	"2kr",
280	"2ks",
281	"2kş",
282	"2kt",
283	"2kv",
284	"2ky",
285	"2kz",
286	"2lb",
287	"2lc",
288	"2lç",
289	"2ld",
290	"2lf",
291	"2lg",
292	"2lğ",
293	"2lh",
294	"2lj",
295	"2lk",
296	"2ll",
297	"2lm",
298	"2ln",
299	"2lp",
300	"2lr",
301	"2ls",
302	"2lş",
303	"2lt",
304	"2lv",
305	"2ly",
306	"2lz",
307	"2mb",
308	"2mc",
309	"2mç",
310	"2md",
311	"2mf",
312	"2mg",
313	"2mğ",
314	"2mh",
315	"2mj",
316	"2mk",
317	"2ml",
318	"2mm",
319	"2mn",
320	"2mp",
321	"2mr",
322	"2ms",
323	"2mş",
324	"2mt",
325	"2mv",
326	"2my",
327	"2mz",
328	"2nb",
329	"2nc",
330	"2nç",
331	"2nd",
332	"2nf",
333	"2ng",
334	"2nğ",
335	"2nh",
336	"2nj",
337	"2nk",
338	"2nl",
339	"2nm",
340	"2nn",
341	"2np",
342	"2nr",
343	"2ns",
344	"2nş",
345	"2nt",
346	"2nv",
347	"2ny",
348	"2nz",
349	"2pb",
350	"2pc",
351	"2pç",
352	"2pd",
353	"2pf",
354	"2pg",
355	"2pğ",
356	"2ph",
357	"2pj",
358	"2pk",
359	"2pl",
360	"2pm",
361	"2pn",
362	"2pp",
363	"2pr",
364	"2ps",
365	"2pş",
366	"2pt",
367	"2pv",
368	"2py",
369	"2pz",
370	"2rb",
371	"2rc",
372	"2rç",
373	"2rd",
374	"2rf",
375	"2rg",
376	"2rğ",
377	"2rh",
378	"2rj",
379	"2rk",
380	"2rl",
381	"2rm",
382	"2rn",
383	"2rp",
384	"2rr",
385	"2rs",
386	"2rş",
387	"2rt",
388	"2rv",
389	"2ry",
390	"2rz",
391	"2sb",
392	"2sc",
393	"2sç",
394	"2sd",
395	"2sf",
396	"2sg",
397	"2sğ",
398	"2sh",
399	"2sj",
400	"2sk",
401	"2sl",
402	"2sm",
403	"2sn",
404	"2sp",
405	"2sr",
406	"2ss",
407	"2sş",
408	"2st",
409	"2sv",
410	"2sy",
411	"2sz",
412	"2şb",
413	"2şc",
414	"2şç",
415	"2şd",
416	"2şf",
417	"2şg",
418	"2şğ",
419	"2şh",
420	"2şj",
421	"2şk",
422	"2şl",
423	"2şm",
424	"2şn",
425	"2şp",
426	"2şr",
427	"2şs",
428	"2şş",
429	"2şt",
430	"2şv",
431	"2şy",
432	"2şz",
433	"2tb",
434	"2tc",
435	"2tç",
436	"2td",
437	"2tf",
438	"2tg",
439	"2tğ",
440	"2th",
441	"2tj",
442	"2tk",
443	"2tl",
444	"2tm",
445	"2tn",
446	"2tp",
447	"2tr",
448	"2ts",
449	"2tş",
450	"2tt",
451	"2tv",
452	"2ty",
453	"2tz",
454	"2vb",
455	"2vc",
456	"2vç",
457	"2vd",
458	"2vf",
459	"2vg",
460	"2vğ",
461	"2vh",
462	"2vj",
463	"2vk",
464	"2vl",
465	"2vm",
466	"2vn",
467	"2vp",
468	"2vr",
469	"2vs",
470	"2vş",
471	"2vt",
472	"2vv",
473	"2vy",
474	"2vz",
475	"2yb",
476	"2yc",
477	"2yç",
478	"2yd",
479	"2yf",
480	"2yg",
481	"2yğ",
482	"2yh",
483	"2yj",
484	"2yk",
485	"2yl",
486	"2ym",
487	"2yn",
488	"2yp",
489	"2yr",
490	"2ys",
491	"2yş",
492	"2yt",
493	"2yv",
494	"2yy",
495	"2yz",
496	"2zb",
497	"2zc",
498	"2zç",
499	"2zd",
500	"2zf",
501	"2zg",
502	"2zğ",
503	"2zh",
504	"2zj",
505	"2zk",
506	"2zl",
507	"2zm",
508	"2zn",
509	"2zp",
510	"2zr",
511	"2zs",
512	"2zş",
513	"2zt",
514	"2zv",
515	"2zy",
516	"2zz",
517	-- allow hyphen between vowels, but not after second vowel of pair
518	-- several phonetically impossible pairs here
519	"a3a2",
520	"a3â2",
521	"a3e2",
522	"a3ı2",
523	"a3i2",
524	"a3î2",
525	"a3o2",
526	"a3ö2",
527	"a3u2",
528	"a3ü2",
529	"a3û2",
530	"â3a2",
531	"â3â2",
532	"â3e2",
533	"â3ı2",
534	"â3i2",
535	"â3î2",
536	"â3o2",
537	"â3ö2",
538	"â3u2",
539	"â3ü2",
540	"â3û2",
541	"e3a2",
542	"e3â2",
543	"e3e2",
544	"e3ı2",
545	"e3i2",
546	"e3î2",
547	"e3o2",
548	"e3ö2",
549	"e3u2",
550	"e3ü2",
551	"e3û2",
552	"ı3a2",
553	"ı3â2",
554	"ı3e2",
555	"ı3ı2",
556	"ı3i2",
557	"ı3î2",
558	"ı3o2",
559	"ı3ö2",
560	"ı3u2",
561	"ı3ü2",
562	"ı3û2",
563	"i3a2",
564	"i3â2",
565	"i3e2",
566	"i3ı2",
567	"i3i2",
568	"i3î2",
569	"i3o2",
570	"i3ö2",
571	"i3u2",
572	"i3ü2",
573	"i3û2",
574	"î3a2",
575	"î3â2",
576	"î3e2",
577	"î3ı2",
578	"î3i2",
579	"î3î2",
580	"î3o2",
581	"î3ö2",
582	"î3u2",
583	"î3ü2",
584	"î3û2",
585	"o3a2",
586	"o3â2",
587	"o3e2",
588	"o3ı2",
589	"o3i2",
590	"o3î2",
591	"o3o2",
592	"o3ö2",
593	"o3u2",
594	"o3ü2",
595	"o3û2",
596	"ö3a2",
597	"ö3â2",
598	"ö3e2",
599	"ö3ı2",
600	"ö3i2",
601	"ö3î2",
602	"ö3o2",
603	"ö3ö2",
604	"ö3u2",
605	"ö3ü2",
606	"ö3û2",
607	"u3a2",
608	"u3â2",
609	"u3e2",
610	"u3ı2",
611	"u3i2",
612	"u3î2",
613	"u3o2",
614	"u3ö2",
615	"u3u2",
616	"u3ü2",
617	"u3û2",
618	"ü3a2",
619	"ü3â2",
620	"ü3e2",
621	"ü3ı2",
622	"ü3i2",
623	"ü3î2",
624	"ü3o2",
625	"ü3ö2",
626	"ü3u2",
627	"ü3ü2",
628	"ü3û2",
629	"û3a2",
630	"û3â2",
631	"û3e2",
632	"û3ı2",
633	"û3i2",
634	"û3î2",
635	"û3o2",
636	"û3ö2",
637	"û3u2",
638	"û3ü2",
639	"û3û2",
640	-- a couple of consonant-clusters
641	"tu4r4k",
642	"m1t4rak",
643	-- See https://github.com/sile-typesetter/sile/issues/355
644	-- Allow hyphenation to apply before apostrophes (before per pattern rules but
645	-- will be substututed later, allowing after breaks minright), but work around
646	-- minleft not being applied mid-word by excluding all possible single letter
647	-- candidates before apostrophes.
648	"1'2",
649	"1’2",
650	"4a1'",
651	"4a1’",
652	"4â1'",
653	"4â1’",
654	"4b1'",
655	"4b1’",
656	"4c1'",
657	"4c1’",
658	"4ç1'",
659	"4ç1’",
660	"4d1'",
661	"4d1’",
662	"4e1'",
663	"4e1’",
664	"4f1'",
665	"4f1’",
666	"4g1'",
667	"4g1’",
668	"4ğ1'",
669	"4ğ1’",
670	"4h1'",
671	"4h1’",
672	"4j1'",
673	"4j1’",
674	"4k1'",
675	"4k1’",
676	"4ı1'",
677	"4ı1’",
678	"4i1'",
679	"4i1’",
680	"4î1'",
681	"4î1’",
682	"4l1'",
683	"4l1’",
684	"4m1'",
685	"4m1’",
686	"4n1'",
687	"4n1’",
688	"4o1'",
689	"4o1’",
690	"4ö1'",
691	"4ö1’",
692	"4p1'",
693	"4p1’",
694	"4r1'",
695	"4r1’",
696	"4s1'",
697	"4s1’",
698	"4ş1'",
699	"4ş1’",
700	"4t1'",
701	"4t1’",
702	"4u1'",
703	"4u1’",
704	"4ü1'",
705	"4ü1’",
706	"4û1'",
707	"4û1’",
708	"4v1'",
709	"4v1’",
710	"4y1'",
711	"4y1’",
712	"4z1'",
713	"4z1’",
714	}
715	-- typos: ignore end
716
717	-- Internationalization stuff
718
719	-- local sum_tens = function (val, loc, digits)
720	-- local ten = string.sub(digits, loc+1, loc+1)
721	-- if ten:len() == 1 then val = val + tonumber(ten) * 10 end
722	-- return val
723	-- end
724
725	local sum_hundreds = function (val, loc, digits)
726	local ten = string.sub(digits, loc + 1, loc + 1)	×
727	local hundred = string.sub(digits, loc + 2, loc + 2)	×
728	if ten:len() == 1 then	×
729	val = val + tonumber(ten) * 10	×
730	end
731	if hundred:len() == 1 then	×
732	val = val + tonumber(hundred) * 100	×
733	end
734	return val	×
735	end
736
737	local tr_nums = function (num, ordinal)
738	local abs = math.abs(num)	×
739	if abs >= 1e+36 then	×
740	SU.error("Numbers past decillions not supported in Turkish")	×
741	end
742	ordinal = SU.boolean(ordinal, false)	×
743	local minus = "eksi"	×
744	local zero = "sıfır"	×
745	local ones = { "bir", "iki", "üç", "dört", "beş", "altı", "yedi", "sekiz", "dokuz" }	×
746	local tens = { "on", "yirmi", "otuz", "kırk", "eli", "altmış", "yetmiş", "seksen", "doksan" }	×
747	local places = {	×
748	"yüz",
749	"bin",
750	"milyon",
751	"milyar",
752	"trilyon",
753	"katrilyon",
754	"kentilyon",
755	"sekstilyon",
756	"septilyon",
757	"oktilyon",
758	"nonilyon",
759	"desilyon",
760	}
761	local zeroordinal = "sıfırıncı"	×
762	local onesordinals =
763	{ "birinci", "ikinci", "üçüncü", "dördüncü", "beşinci", "altıncı", "yedinci", "sekizinci", "dokuzuncu" }	×
764	local tensordinals = {	×
765	"onuncu",
766	"yirmiyinci",
767	"otuzuncu",
768	"kırkıncı",
769	"eliyinci",
770	"altmışıncı",
771	"yetmişinci",
772	"sekseninci",
773	"Doksanıncı",
774	}
775	local placesordinals = {	×
776	"yüzüncü",
777	"bininci",
778	"milyonuncu",
779	"milyarıncı",
780	"trilyonuncu",
781	"katrilyonuncu",
782	"kentilyonuncu",
783	"sekstilyonuncu",
784	"septilyonuncu",
785	"oktilyonuncu",
786	"nonilyonuncu",
787	"desilyonuncu",
788	}
789	local digits = string.reverse(string.format("%.f", abs))	×
790	local words = {}	×
791	for i = 1, #digits do	×
792	local val, place, mod = tonumber(string.sub(digits, i, i)), math.floor(i / 3), i % 3	×
793	if #digits == 1 and val == 0 then	×
794	words[#words + 1] = ordinal and zeroordinal or zero	×
795	elseif val >= 1 or i > 1 then	×
796	if i == 1 then	×
797	words[#words + 1] = ordinal and onesordinals[val] or ones[val]	×
798	ordinal = false	×
799	elseif mod == 2 then	×
800	if val >= 1 then	×
801	words[#words + 1] = ordinal and tensordinals[val] or tens[val]	×
802	ordinal = false	×
803	end
804	elseif mod == 1 then	×
805	if sum_hundreds(val, i, digits) >= 1 then	×
806	words[#words + 1] = ordinal and placesordinals[place + 1] or places[place + 1]	×
807	ordinal = false	×
808	if val > 0 and (i >= 7 or sum_hundreds(val, i, digits) >= 2) then	×
809	words[#words + 1] = ones[val]	×
810	end
811	end
812	elseif mod == 0 then	×
813	if val > 0 then	×
814	words[#words + 1] = ordinal and placesordinals[1] or places[1]	×
815	ordinal = false	×
816	end
817	if val >= 2 then	×
818	words[#words + 1] = ones[val]	×
819	end
820	end
821	end
822	end
823	if abs > num then	×
824	words[#words + 1] = minus	×
825	end
826	SU.flip_in_place(words)	×
827	return table.concat(words, " ")	×
828	end
829
UNCOV 830	SU.formatNumber.tr = {	×
831	string = function (num, _)
832	return tr_nums(num, false)	×
833	end,
834	["ordinal-string"] = function (num, _)
835	return tr_nums(num, true)	×
836	end,
837	}

sile-typesetter / sile / 11124789710

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