pdf-print / mpdf / config_lang2fonts.php

config_lang2fonts.php in PDF & Print by BestWebSoft – WordPress Posts and Pages PDF Generator Plugin trunk, at mpdf/config_lang2fonts.php

514 lines 13.0 KB

Raw Download Zip

1	<?php
2
3	/*
4	mPDF recognises IETF language tags as:
5	- a single primary language subtag composed of a two letter language code from ISO 639-1 (2002), or a three letter code from ISO 639-2 (1998), ISO 639-3 (2007) or ISO 639-5 (2008) (usually written in lower case);
6	- an optional script subtag, composed of a four letter script code from ISO 15924 (usually written in title case);
7	- an optional region subtag composed of a two letter country code from ISO 3166-1 alpha-2 (usually written in upper case), or a three digit code from UN M.49 for geographical regions;
8	Subtags are not case sensitive, but the specification recommends using the same case as in the Language Subtag Registry, where region subtags are uppercase, script subtags are titlecase and all other subtags are lowercase.
9
10	Region subtags are often deprecated by the registration of specific primary language subtags from ISO 639-3 which are now "preferred values". For example, "ar-DZ" is deprecated with the preferred value "arq" for Algerian Spoken Arabic;
11
12	Example: Serbian written in the Cyrillic (sr-Cyrl) or Latin (sr-Latn) script
13
14	und (for undetermined or undefined) is used in situations in which a script must be indicated but the language cannot be identified.
15	e.g. und-Cyrl is an undefined language written in Cyrillic script.
16	*/
17
18	function GetLangOpts($llcc, $adobeCJK, &$fontdata)
19	{
20	$tags = preg_split('/-/', $llcc);
21	$lang = strtolower($tags[0]);
22	$country = '';
23	$script = '';
24	if (isset($tags[1]) && $tags[1]) {
25	if (strlen($tags[1]) == 4) {
26	$script = strtolower($tags[1]);
27	} else {
28	$country = strtolower($tags[1]);
29	}
30	}
31	if (isset($tags[2]) && $tags[2]) {
32	$country = strtolower($tags[2]);
33	}
34
35	$unifont = "";
36	$coreSuitable = false;
37
38	switch ($lang) {
39
40	/* European */
41	CASE "en": CASE "eng": // English // LATIN
42	CASE "eu": CASE "eus": // Basque
43	CASE "br": CASE "bre": // Breton
44	CASE "ca": CASE "cat": // Catalan
45	CASE "co": CASE "cos": // Corsican
46	CASE "kw": CASE "cor": // Cornish
47	CASE "cy": CASE "cym": // Welsh
48	CASE "cs": CASE "ces": // Czech
49	CASE "da": CASE "dan": // Danish
50	CASE "nl": CASE "nld": // Dutch
51	CASE "et": CASE "est": // Estonian
52	CASE "fo": CASE "fao": // Faroese
53	CASE "fi": CASE "fin": // Finnish
54	CASE "fr": CASE "fra": // French
55	CASE "gl": CASE "glg": // Galician
56	CASE "de": CASE "deu": // German
57	CASE "ht": CASE "hat": // Haitian; Haitian Creole
58	CASE "hu": CASE "hun": // Hungarian
59	CASE "ga": CASE "gle": // Irish
60	CASE "is": CASE "isl": // Icelandic
61	CASE "it": CASE "ita": // Italian
62	CASE "la": CASE "lat": // Latin
63	CASE "lb": CASE "ltz": // Luxembourgish
64	CASE "li": CASE "lim": // Limburgish
65	CASE "lt": CASE "lit": // Lithuanian
66	CASE "lv": CASE "lav": // Latvian
67	CASE "gv": CASE "glv": // Manx
68	CASE "no": CASE "nor": // Norwegian
69	CASE "nn": CASE "nno": // Norwegian Nynorsk
70	CASE "nb": CASE "nob": // Norwegian Bokmål
71	CASE "pl": CASE "pol": // Polish
72	CASE "pt": CASE "por": // Portuguese
73	CASE "ro": CASE "ron": // Romanian
74	CASE "gd": CASE "gla": // Scottish Gaelic
75	CASE "es": CASE "spa": // Spanish
76	CASE "sv": CASE "swe": // Swedish
77	CASE "sl": CASE "slv": // Slovene
78	CASE "sk": CASE "slk": // Slovak
79	$unifont = "dejavusanscondensed";
80	// Edit this value to define how mPDF behaves when using new mPDF('-x')
81	// If set to TRUE, mPDF will use Adobe core fonts only when it recognises the languages above
82	$coreSuitable = true;
83	break;
84
85	CASE "ru": CASE "rus": // Russian // CYRILLIC
86	CASE "ab": CASE "abk": // Abkhaz
87	CASE "av": CASE "ava": // Avaric
88	CASE "ba": CASE "bak": // Bashkir
89	CASE "be": CASE "bel": // Belarusian
90	CASE "bg": CASE "bul": // Bulgarian
91	CASE "ce": CASE "che": // Chechen
92	CASE "cv": CASE "chv": // Chuvash
93	CASE "kk": CASE "kaz": // Kazakh
94	CASE "kv": CASE "kom": // Komi
95	CASE "ky": CASE "kir": // Kyrgyz
96	CASE "mk": CASE "mkd": // Macedonian
97	CASE "cu": CASE "chu": // Old Church Slavonic
98	CASE "os": CASE "oss": // Ossetian
99	CASE "sr": CASE "srp": // Serbian
100	CASE "tg": CASE "tgk": // Tajik
101	CASE "tt": CASE "tat": // Tatar
102	CASE "tk": CASE "tuk": // Turkmen
103	CASE "uk": CASE "ukr": // Ukrainian
104	$unifont = "dejavusanscondensed"; /* freeserif best coverage for supplements etc. */
105	break;
106
107	CASE "hy": CASE "hye": // ARMENIAN
108	$unifont = "dejavusans";
109	break;
110	CASE "ka": CASE "kat": // GEORGIAN
111	$unifont = "dejavusans";
112	break;
113
114	CASE "el": CASE "ell": // GREEK
115	$unifont = "dejavusanscondensed";
116	break;
117	CASE "cop": // COPTIC
118	$unifont = "quivira";
119	break;
120
121	CASE "got": // GOTHIC
122	$unifont = "freeserif";
123	break;
124
125	/* African */
126	CASE "nqo": // NKO
127	$unifont = "dejavusans";
128	break;
129	//CASE "bax": // BAMUM
130	//CASE "ha": CASE "hau": // Hausa
131	CASE "vai": // VAI
132	$unifont = "freesans";
133	break;
134	CASE "am": CASE "amh": // Amharic ETHIOPIC
135	CASE "ti": CASE "tir": // Tigrinya ETHIOPIC
136	$unifont = "abyssinicasil";
137	break;
138
139
140
141	/* Middle Eastern */
142	CASE "ar": CASE "ara": // Arabic NB Arabic text identified by Autofont will be marked as und-Arab
143	$unifont = "xbriyaz";
144	break;
145	CASE "fa": CASE "fas": // Persian (Farsi)
146	$unifont = "xbriyaz";
147	break;
148	CASE "ps": CASE "pus": // Pashto
149	$unifont = "xbriyaz";
150	break;
151	CASE "ku": CASE "kur": // Kurdish
152	$unifont = "xbriyaz";
153	break;
154	CASE "ur": CASE "urd": // Urdu
155	$unifont = "xbriyaz";
156	break;
157	CASE "he": CASE "heb": // HEBREW
158	CASE "yi": CASE "yid": // Yiddish
159	$unifont = "taameydavidclm"; // dejavusans,dejavusanscondensed,freeserif are fine if you do not need cantillation marks
160	break;
161
162
163	CASE "syr": // SYRIAC
164	$unifont = "estrangeloedessa";
165	break;
166
167
168	//CASE "arc": // IMPERIAL_ARAMAIC
169	//CASE ""ae: // AVESTAN
170	CASE "xcr": // CARIAN
171	$unifont = "aegean";
172	break;
173	CASE "xlc": // LYCIAN
174	$unifont = "aegean";
175	break;
176	CASE "xld": // LYDIAN
177	$unifont = "aegean";
178	break;
179	//CASE "mid": // MANDAIC
180	//CASE "peo": // OLD_PERSIAN
181	CASE "phn": // PHOENICIAN
182	$unifont = "aegean";
183	break;
184	//CASE "smp": // SAMARITAN
185	CASE "uga": // UGARITIC
186	$unifont = "aegean";
187	break;
188
189
190	/* Central Asian */
191	CASE "bo": CASE "bod": // TIBETAN
192	CASE "dz": CASE "dzo": // Dzongkha
193	$unifont = "jomolhari";
194	break;
195	//CASE "mn": CASE "mon": // MONGOLIAN (Vertical script)
196	//CASE "ug": CASE "uig": // Uyghur
197	//CASE "uz": CASE "uzb": // Uzbek
198	//CASE "az": CASE "azb": // South Azerbaijani
199
200
201	/* South Asian */
202	CASE "as": CASE "asm": // Assamese
203	$unifont = "freeserif";
204	break;
205	CASE "bn": CASE "ben": // BENGALI; Bangla
206	$unifont = "freeserif";
207	break;
208	CASE "ks": CASE "kas": // Kashmiri
209	$unifont = "freeserif";
210	break;
211	CASE "hi": CASE "hin": // Hindi DEVANAGARI
212	CASE "bh": CASE "bih": // Bihari (Bhojpuri, Magahi, and Maithili)
213	CASE "sa": CASE "san": // Sanskrit
214	$unifont = "freeserif";
215	break;
216	CASE "gu": CASE "guj": // Gujarati
217	$unifont = "freeserif";
218	break;
219	CASE "pa": CASE "pan": // Panjabi, Punjabi GURMUKHI
220	$unifont = "freeserif";
221	break;
222	CASE "kn": CASE "kan": // Kannada
223	$unifont = "lohitkannada";
224	break;
225	CASE "mr": CASE "mar": // Marathi
226	$unifont = "freeserif";
227	break;
228	CASE "ml": CASE "mal": // MALAYALAM
229	$unifont = "freeserif";
230	break;
231	CASE "ne": CASE "nep": // Nepali
232	$unifont = "freeserif";
233	break;
234	CASE "or": CASE "ori": // ORIYA
235	$unifont = "freeserif";
236	break;
237	CASE "si": CASE "sin": // SINHALA
238	$unifont = "kaputaunicode";
239	break;
240	CASE "ta": CASE "tam": // TAMIL
241	$unifont = "freeserif";
242	break;
243	CASE "te": CASE "tel": // TELUGU
244	$unifont = "pothana2000";
245	break;
246
247
248	// Sindhi (Arabic or Devanagari)
249	CASE "sd": CASE "snd": // Sindhi
250	if ($country == "IN") {
251	$unifont = "freeserif";
252	} else if ($country == "PK") {
253	$unifont = "lateef";
254	} else {
255	$unifont = "lateef";
256	}
257	break;
258
259
260	//CASE "ccp": // CHAKMA
261	//CASE "lep": // LEPCHA
262	CASE "lif": // LIMBU
263	$unifont = "sun-exta";
264	break;
265	//CASE "sat": // OL_CHIKI
266	//CASE "saz": // SAURASHTRA
267	CASE "syl": // SYLOTI_NAGRI
268	$unifont = "mph2bdamase";
269	break;
270	//CASE "dgo": // TAKRI
271	CASE "dv": CASE "div": // Divehi; Maldivian THAANA
272	$unifont = "freeserif";
273	break;
274
275
276
277	/* South East Asian */
278	CASE "km": CASE "khm": // KHMER
279	$unifont = "khmeros";
280	break;
281	CASE "lo": CASE "lao": // LAO
282	$unifont = "dhyana";
283	break;
284	CASE "my": CASE "mya": // MYANMAR Burmese
285	$unifont = "tharlon"; // zawgyi-one is non-unicode compliant but in wide usage
286	// ayar is also not strictly compliant
287	// padaukbook is unicode compliant
288	break;
289	CASE "th": CASE "tha": // THAI
290	$unifont = "garuda";
291	break;
292
293
294
295	// VIETNAMESE
296	CASE "vi": CASE "vie": // Vietnamese
297	$unifont = "dejavusanscondensed";
298	break;
299
300
301	//CASE "ms": CASE "msa": // Malay
302	//CASE "ban": // BALINESE
303	//CASE "bya": // BATAK
304	CASE "bug": // BUGINESE
305	$unifont = "freeserif";
306	break;
307	//CASE "cjm": // CHAM
308	//CASE "jv": // JAVANESE
309	CASE "su": // SUNDANESE
310	$unifont = "sundaneseunicode";
311	break;
312	CASE "tdd": // TAI_LE
313	$unifont = "tharlon";
314	break;
315	CASE "blt": // TAI_VIET
316	$unifont = "taiheritagepro";
317	break;
318
319
320	/* Phillipine */
321	CASE "bku": // BUHID
322	$unifont = "quivira";
323	break;
324	CASE "hnn": // HANUNOO
325	$unifont = "quivira";
326	break;
327	CASE "tl": // TAGALOG
328	$unifont = "quivira";
329	break;
330	CASE "tbw": // TAGBANWA
331	$unifont = "quivira";
332	break;
333
334
335	/* East Asian */
336	CASE "zh": CASE "zho": // Chinese
337	if ($country == "HK" \|\| $country == "TW") {
338	if ($adobeCJK) {
339	$unifont = "big5";
340	} else {
341	$unifont = "sun-exta";
342	}
343	} else if ($country == "CN") {
344	if ($adobeCJK) {
345	$unifont = "gb";
346	} else {
347	$unifont = "sun-exta";
348	}
349	} else {
350	if ($adobeCJK) {
351	$unifont = "gb";
352	} else {
353	$unifont = "sun-exta";
354	}
355	}
356	break;
357	CASE "ko": CASE "kor": // HANGUL Korean
358	if ($adobeCJK) {
359	$unifont = "uhc";
360	} else {
361	$unifont = "unbatang";
362	}
363	break;
364	CASE "ja": CASE "jpn": // Japanese HIRAGANA KATAKANA
365	if ($adobeCJK) {
366	$unifont = "sjis";
367	} else {
368	$unifont = "sun-exta";
369	}
370	break;
371	CASE "ii": CASE "iii": // Nuosu; Yi
372	if ($adobeCJK) {
373	$unifont = "gb";
374	} else {
375	$unifont = "sun-exta";
376	}
377	CASE "lis": // LISU
378	$unifont = "quivira";
379	break;
380
381
382
383	/* American */
384	CASE "chr": // CHEROKEE
385	CASE "oj": CASE "oji": // Ojibwe; Chippewa
386	CASE "cr": CASE "cre": // Cree CANADIAN_ABORIGINAL
387	CASE "iu": CASE "iku": // Inuktitut
388	$unifont = "aboriginalsans";
389	break;
390
391
392	/* Undetermined language - script used */
393	CASE "und":
394
395	switch ($script) {
396
397	/* European */
398	CASE "latn": // LATIN
399	$unifont = "dejavusanscondensed";
400	break;
401	CASE "cyrl": // CYRILLIC
402	$unifont = "dejavusanscondensed"; /* freeserif best coverage for supplements etc. */
403	break;
404	CASE "cprt": // CYPRIOT
405	$unifont = "aegean";
406	break;
407	CASE "glag": // GLAGOLITIC
408	$unifont = "mph2bdamase";
409	break;
410	CASE "linb": // LINEAR_B
411	$unifont = "aegean";
412	break;
413	CASE "ogam": // OGHAM
414	$unifont = "dejavusans";
415	break;
416	CASE "ital": // OLD_ITALIC
417	$unifont = "aegean";
418	break;
419	CASE "runr": // RUNIC
420	$unifont = "sun-exta";
421	break;
422	CASE "shaw": // SHAVIAN
423	$unifont = "mph2bdamase";
424	break;
425
426	/* African */
427	CASE "egyp": // EGYPTIAN_HIEROGLYPHS
428	$unifont = "aegyptus";
429	break;
430	CASE "ethi": // ETHIOPIC
431	$unifont = "abyssinicasil";
432	break;
433	//CASE "merc": // MEROITIC_CURSIVE
434	//CASE "mero": // MEROITIC_HIEROGLYPHS
435	CASE "osma": // OSMANYA
436	$unifont = "mph2bdamase";
437	break;
438	CASE "tfng": // TIFINAGH
439	$unifont = "dejavusans";
440	break;
441
442	/* Middle Eastern */
443	CASE "arab": // ARABIC
444	$unifont = "xbriyaz";
445	break;
446	CASE "xsux": // CUNEIFORM
447	$unifont = "akkadian";
448	break;
449	//CASE "sarb": // OLD_SOUTH_ARABIAN
450	//CASE "prti": // INSCRIPTIONAL_PARTHIAN
451	//CASE "phli": // INSCRIPTIONAL_PAHLAVI
452
453
454	/* Central Asian */
455	//CASE "orkh": // OLD_TURKIC
456	//CASE "phag": // PHAGS_PA (Vertical script)
457
458	/* South Asian */
459	//CASE "brah": // BRAHMI
460	//CASE "kthi": // KAITHI
461	CASE "khar": // KHAROSHTHI
462	$unifont = "mph2bdamase";
463	break;
464	CASE "mtei": // MEETEI_MAYEK
465	$unifont = "eeyekunicode";
466	break;
467	//CASE "shrd": // SHARADA
468	//CASE "sora": // SORA_SOMPENG
469
470	/* South East Asian */
471	CASE "kali": // KAYAH_LI
472	$unifont = "freemono";
473	break;
474	//CASE "rjng": // REJANG
475	CASE "lana": // TAI_THAM
476	$unifont = "lannaalif";
477	break;
478	CASE "talu": // NEW_TAI_LUE
479	$unifont = "daibannasilbook";
480	break;
481
482	/* East Asian */
483	CASE "hans": // HAN (SIMPLIFIED)
484	if ($adobeCJK) {
485	$unifont = "gb";
486	} else {
487	$unifont = "sun-exta";
488	}
489	break;
490	CASE "bopo": // BOPOMOFO
491	$unifont = "sun-exta";
492	break;
493	//CASE "plrd": // MIAO
494	CASE "yiii": // YI
495	$unifont = "sun-exta";
496	break;
497
498	/* American */
499	CASE "dsrt": // DESERET
500	$unifont = "mph2bdamase";
501	break;
502
503	/* Other */
504	CASE "brai": // BRAILLE
505	$unifont = "dejavusans";
506	break;
507	} // endswitch
508	break;
509	} // endswitch
510
511
512	return array($coreSuitable, $unifont);
513	}
514