UrduRomanization.cfg 10.0 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480
  1. # version 1.1
  2. # Original table by William Kopycki
  3. # revised by Phong Tran
  4. # Last updated 19 August 2013
  5. [General]
  6. Name=Urdu
  7. Truncation=%
  8. [RomanToScript]
  9. FieldsIncluded=100 110 111 130 240 245 246 250 260 264 440 490 505 600 610 611 630 651 700 710 711 730 740 800 830
  10. SubfieldsAlwaysExcluded=uvxy0123456789
  11. OtherSubfieldsExcludedByTag=100/e 110/e 111/j 246/i 260/c 264/c 650/a 700/e 700/i 710/e 710/i 711/i 711/j 730/i
  12. Subfield6Code=(3
  13. IncludeFormattingCharactersLcPattern=True
  14. # RDA boilerplate phrases not transliterated:
  15. Place of publication not identified=Place of publication not identified
  16. publisher not identified=publisher not identified
  17. # Punctuation marks:
  18. # %=U+066A ; cannot transliterate the truncation character
  19. *=U+066D
  20. ,=U+060C
  21. ;=U+061B
  22. ?=U+061F
  23. # Exceptions for specific words
  24. # Allah
  25. AllaU+0304h=U+0627U+0644U+0644U+0647
  26. allaU+0304h=U+0627U+0644U+0644U+0647
  27. # Qur'an
  28. QurU+02BCaU+0304n=U+0642U+0631U+0622U+0646
  29. qurU+02BCaU+0304n=U+0642U+0631U+0622U+0646
  30. # aur (with spaces)
  31. aur = U+0627U+0648U+0631
  32. Aur =U+0627U+0648U+0631
  33. ####
  34. # Abdurrahman
  35. U+02BBAbdurrahU+0323maU+0301n=U+0639U+0628U+062FU+0627U+0644U+0631U+062DU+0645U+0670U+0646
  36. U+02BBAbdurrahU+0323maU+0304n=U+0639U+0628U+062FU+0627U+0644U+0631U+062DU+0645U+0670U+0646
  37. # Abd names
  38. U+02BBAbdulU+02BB=U+0639U+0628U+062FU+0627U+0644U+0639
  39. U+02BBAbdula=U+0639U+0628U+062FU+0627U+0644
  40. U+02BBAbdulb=U+0639U+0628U+062FU+0627U+0644U+0628
  41. U+02BBAbdulf=U+0639U+0628U+062FU+0627U+0644U+0641
  42. U+02BBAbdulgU+0332hu+0332=U+0639U+0628U+062FU+0627U+0644U+063A
  43. U+02BBAbdulhU+0323=U+0639U+0628U+062FU+0627U+0644U+062D
  44. U+02BBAbdulh=U+0639U+0628U+062FU+0627U+0644U+0647
  45. U+02BBAbdulj=U+0639U+0628U+062FU+0627U+0644U+062C
  46. U+02BBAbdulkU+0332hU+0332=U+0639U+0628U+062FU+0627U+0644U+062E
  47. U+02BBAbdulk=U+0639U+0628U+062FU+0627U+0644U+0643
  48. U+02BBAbdulm=U+0639U+0628U+062FU+0627U+0644U+0645
  49. U+02BBAbdulq=U+0639U+0628U+062FU+0627U+0644U+0642
  50. U+02BBAbdulv=U+0639U+0628U+062FU+0627U+0644U+0648
  51. U+02BBAbdunn=U+0639U+0628U+062FU+0627U+0644U+646
  52. U+02BBAbdurr=U+0639U+0628U+062FU+0627U+0644U+0631
  53. U+02BBAbdusU+0323sU+0323=U+0639U+0628U+062FU+0627U+0644U+0325
  54. U+02BBAbduss=U+0639U+0628U+062FU+0627U+0644U+0633
  55. U+02BBAbdushsh=U+0639U+0628U+062FU+0627U+0644U+634
  56. U+02BBAbdutt=U+0639U+0628U+062FU+0627U+0644U+062A
  57. U+02BBAbduzU+0323zU+0323=U+0639U+0628U+062FU+0627U+0644U+0636
  58. U+02BBAbduzU+0324zU+0324=U+0639U+0628U+062FU+0627U+0644U+0638
  59. # Abu names
  60. AbuU+0304 =U+0627U+0628U+0648U+0020
  61. AbuU+0304=U+0627U+0628U+0648U+200CU+0627U+0644
  62. ####
  63. #lillah
  64. lillaU+0304h=U+0644U+0644U+0647
  65. #billah
  66. billaU+0304h=U+0628U+0644U+0644U+0647
  67. # Rahman
  68. RahU+0323maU+0304n=U+0631U+062DU+0645U+0646
  69. # Nuzhat
  70. Nuzhat=U+0646U+0632U+0647U+062A
  71. # Uddin names
  72. %iU+0304uddiU+0304n=U+0649U+200CU+0627U+0644U+062FU+0651U+064AU+0646
  73. %uddiU+0304n=U+200CU+0627U+0644U+062FU+0651U+064AU+0646
  74. # ta'lif
  75. # Ibn when it appears in the middle of a name sequence
  76. ibn=U+0628U+0646
  77. # Abbreviated name elements
  78. # Ae=U+0627U+06D2
  79. # Parsing "sh[dot below] as in "Ishaq [name]"
  80. %shU+0323%=U+0633U+062D
  81. # Numbers (U+06F0-06F9 for Persian/Urdu)
  82. # currently *not* valid MARC21 characters
  83. # 0=U+06F0
  84. # 1=U+06F1
  85. # 2=U+06F2
  86. # 3=U+06F3
  87. # 4=U+06F4
  88. # 5=U+06F5
  89. # 6=U+06F6
  90. # 7=U+06F7
  91. # 8=U+06F8
  92. # 9=U+06F9
  93. # Postpositions
  94. # Aspirates [06BE] vs. heh [062D] combinations
  95. bhU+0323=U+0628U+062D
  96. Bh=U+0628U+06BE
  97. bh=U+0628U+06BE
  98. phU+0323=U+067EU+062D
  99. Ph=U+067EU+06BE
  100. ph=U+067EU+06BE
  101. thU+0323=U+062AU+062D
  102. Th=U+062AU+06BE
  103. th=U+062AU+06BE
  104. tU+0323hU+0323=U+0679U+062D
  105. TU+0323h=U+0679U+06BE
  106. tU+0323h=U+0679U+06BE
  107. jhU+0323=U+062CU+062D
  108. Jh=U+062CU+06BE
  109. jh=U+062CU+06BE
  110. chU+0323=U+0686U+062D
  111. Ch=U+0686U+06BE
  112. ch=U+0686U+06BE
  113. dhU+0323=U+062FU+062D
  114. Dh=U+062FU+06BE
  115. dh=U+062FU+06BE
  116. dU+0323hU+0323=U+0688U+062D
  117. DU+0323h=U+0688U+06BE
  118. dU+0323h=U+0688U+06BE
  119. rU+0323hU+0323=U+0691U+062D
  120. RU+0323h=U+0691U+06BE
  121. rU+0323h=U+0691U+06BE
  122. khU+0323=U+06A9U+062D
  123. Kh=U+06A9U+06BE
  124. kh=U+06A9U+06BE
  125. ghU+0323=U+06AFU+062D
  126. Gh=U+06AFU+06BE
  127. gh=U+06AFU+06BE
  128. # prime = ZWNJ
  129. U+02B9AU+0304=U+200CU+0622
  130. U+02B9aU+0304=U+200CU+0622
  131. aU+0304U+02BCU+02B9=U+0627U+0621U+200C
  132. iU+0304U+02B9=U+0649U+200C
  133. U+02B9=U+200C
  134. # Izafah here
  135. %aU+0304-yi=U+0627U+0626U+06D2
  136. %uU+0304-yi=U+0648U+0626U+06D2
  137. %o-yi=U+0648U+0626U+06D2
  138. %e-yi=U+06D2
  139. %iU+0304-yi=U+0649
  140. %h-yi=U+06C0
  141. %-yi=U+06C0
  142. %al-i=U+0644
  143. %ul-i=U+0644
  144. %-i=
  145. # Hyphenated prefixes:
  146. bi-=U+0628
  147. al-aU+0304%=U+0627U+0644U+0627
  148. ul-aU+0304%=U+0627U+0644U+0627
  149. al-=U+0627U+0644
  150. ul-=U+0627U+0644
  151. lil-i=U+0644U+0644
  152. lil-=U+0644U+0644
  153. # al-/ul- plus sun letters
  154. ar-r=U+0627U+0644U+0631
  155. ur-r=U+0627U+0644U+0631
  156. ar-R=U+0627U+0644U+0631
  157. ur-R=U+0627U+0644U+0631
  158. azU+0332-zU+0332=U+0627U+0644U+0630
  159. uzU+0332-zU+0332=U+0627U+0644U+0630
  160. azU+0332-ZU+0332=U+0627U+0644U+0630
  161. uzU+0332-ZU+0332=U+0627U+0644U+0630
  162. ad-d=U+0627U+0644U+0627
  163. ud-d=U+0627U+0644U+0627
  164. ad-D=U+0627U+0644U+0627
  165. ud-D=U+0627U+0644U+0627
  166. asU+0332-sU+0332=U+0627U+0644U+062B
  167. usU+0332-sU+0332=U+0627U+0644U+062B
  168. asU+0332-SU+0332=U+0627U+0644U+062B
  169. usU+0332-SU+0332=U+0627U+0644U+062B
  170. at-t=U+0627U+0644U+062A
  171. ut-t=U+0627U+0644U+062A
  172. at-T=U+0627U+0644U+062A
  173. ut-T=U+0627U+0644U+062A
  174. an-n=U+0627U+0644U+0646
  175. un-n=U+0627U+0644U+0646
  176. an-N=U+0627U+0644U+0646
  177. un-N=U+0627U+0644U+0646
  178. al-l=U+0627U+0644U+0644
  179. ul-l=U+0627U+0644U+0644
  180. al-L=U+0627U+0644U+0644
  181. ul-L=U+0627U+0644U+0644
  182. azU+0324-zU+0324=U+0627U+0644U+0638
  183. uzU+0324-zU+0324=U+0627U+0644U+0638
  184. azU+0324-ZU+0324=U+0627U+0644U+0638
  185. uzU+0324-ZU+0324=U+0627U+0644U+0638
  186. atU+0324-tU+0324=U+0627U+0644U+0637
  187. utU+0324-tU+0324=U+0627U+0644U+0637
  188. atU+0324-TU+0324=U+0627U+0644U+0637
  189. utU+0324-TU+0324=U+0627U+0644U+0637
  190. azU+0323-zU+0323=U+0627U+0644U+0636
  191. uzU+0323-zU+0323=U+0627U+0644U+0636
  192. azU+0323-ZU+0323=U+0627U+0644U+0636
  193. uzU+0323-ZU+0323=U+0627U+0644U+0636
  194. asU+0323-sU+0323=U+0627U+0644U+0635
  195. usU+0323-sU+0323=U+0627U+0644U+0635
  196. asU+0323-SU+0323=U+0627U+0644U+0635
  197. usU+0323-SU+0323=U+0627U+0644U+0635
  198. ash-sh=U+0627U+0644U+0634
  199. ush-sh=U+0627U+0644U+0634
  200. ash-Sh=U+0627U+0644U+0634
  201. ush-Sh=U+0627U+0644U+0634
  202. as-s=U+0627U+0644U+0633
  203. us-s=U+0627U+0644U+0633
  204. as-S=U+0627U+0644U+0633
  205. us-S=U+0627U+0644U+0633
  206. az-z=U+0627U+0644U+0632
  207. uz-z=U+0627U+0644U+0632
  208. az-Z=U+0627U+0644U+0632
  209. uz-Z=U+0627U+0644U+0632
  210. # Diphthongs here
  211. Ae=U+0627U+06D2
  212. %ai=U+06D2
  213. Ai=U+0627U+064A
  214. ai%=U+0627U+064A
  215. ai=U+064A
  216. U+02BBAu=U+0639U+0648
  217. U+02BBau=U+0639U+0648
  218. Au=U+0627U+0648
  219. au=U+0648
  220. # ayn-alif combo
  221. %U+02BBaU+0304U+02BE=U+0639U+0627U+0621
  222. %U+02BBaU+0304U+02BC=U+0639U+0627U+0621
  223. %U+02BBaU+0304%=U+0639U+0627
  224. # hamza and vowel combo
  225. # [in final position]
  226. %uU+0304U+02BEiU+304=U+0648U+0626U+0649
  227. %uU+0304U+02BCiU+304=U+0648U+0626U+0649
  228. %U+02BEiU+0304=U+0626U+0649
  229. %U+02BCiU+0304=U+0626U+0649
  230. %U+02BEe=U+0626U+06D2
  231. %U+02BCe=U+0626U+06D2
  232. %U+02BEuU+0304=U+0624
  233. %U+02BCuU+0304=U+0624
  234. %U+02BEo=U+0624
  235. %U+02BCo=U+0624
  236. # [in medial position]
  237. aU+02BEa=U+0623
  238. aU+02BCa=U+0623
  239. aU+0304U+02BEa=U+0627U+0621
  240. aU+0304U+02BCa=U+0627U+0621
  241. aU+02BEaU+0304=U+0622
  242. aU+02BCaU+0304=U+0622
  243. oU+02BEiU+0304=U+0648U+0626U+064A
  244. oU+02BCiU+0304=U+0648U+0626U+064A
  245. oU+02BEi=U+0648U+0626
  246. oU+02BCi=U+0648U+0626
  247. U+02BEiU+0304=U+0626U+064A
  248. U+02BCiU+0304=U+0626U+064A
  249. U+02BEi=U+0626
  250. U+02BCi=U+0626
  251. U+02BEe=U+0626U+064A
  252. U+02BCe=U+0626U+064A
  253. U+02BEuU+0304=U+0624
  254. U+02BCuU+0304=U+0624
  255. uU+0304U+02BE=U+0624
  256. uU+0304U+02BC=U+0624
  257. U+02BEo=U+0624
  258. U+02BCo=U+0624
  259. oU+02BE=U+0624
  260. oU+02BC=U+0624
  261. auU+02BE=U+0624
  262. auU+02BC=U+0624
  263. U+02BEa=U+0626
  264. U+02BCa=U+0626
  265. %iU+0304=U+0649
  266. %aU+0301=U+0649U+0670
  267. # A
  268. U+02BBAU+0304=U+0639U+0627
  269. U+02BBaU+0304=U+0639U+0627
  270. U+02BBA%=U+0639
  271. U+02BBa=U+0639
  272. AU+02BB=U+0627U+0639
  273. aU+02BB%=U+0627U+0639
  274. aU+02BB=U+0639
  275. AU+0304%=U+0622
  276. aU+0304%=U+0622
  277. aU+0304=U+0627
  278. aU+0301=U+0649
  279. ayy=U+064AU+0651
  280. A%=U+0627
  281. a%=U+0627
  282. A=
  283. a=
  284. # E
  285. %e=U+06D2
  286. E%=U+0627U+064A
  287. e%=U+0627U+064A
  288. e=U+064A
  289. # I
  290. U+02BBIU+0304=U+0639U+064A
  291. U+02BBiU+0304=U+0639U+064A
  292. IU+02BB=U+0627U+0639
  293. iU+02BB=U+0639
  294. U+02BBI=U+0639
  295. IU+0304%=U+0627U+064A
  296. iU+0304%=U+0627U+064A
  297. iU+0304y=U+064A
  298. iU+0304=U+064A
  299. iyy=U+064AU+0651
  300. I%=U+0627
  301. i%=U+0627
  302. I=U+0627
  303. i=
  304. # O
  305. O%=U+0627U+0648
  306. o=U+0648
  307. # U
  308. U+02BBuU+0304=U+0639U+0648
  309. U+02BBU=U+0639
  310. U+02BBu=U+0639
  311. UU+0304%=U+0627U+0648
  312. uU+0304%=U+0627U+0648
  313. uU+0304=U+0648
  314. U%=U+0627
  315. u%=U+0627
  316. U=
  317. u=
  318. # Consonants:
  319. B=U+0628
  320. bb=U+0628U+0651
  321. b=U+0628
  322. P=U+067E
  323. pp=U+067EU+0651
  324. p=U+067E
  325. TU+0323=U+0679
  326. tU+0323tU+0323=U+0679U+0651
  327. tU+0323=U+0679
  328. TU+0324=U+0637
  329. tU+0324tU+0324=U+0637U+0651
  330. tU+0324=U+0637
  331. T=U+062A
  332. tt=U+062AU+0651
  333. t=U+062A
  334. Sh=U+0634
  335. shsh=U+0634U+0651
  336. sh=U+0634
  337. SU+0323=U+0635
  338. sU+0323sU+0323=U+0635U+0651
  339. sU+0323=U+0635
  340. SU+0332=U+062B
  341. sU+0332sU+0332=U+062BU+0651
  342. sU+0332=U+062B
  343. S=U+0633
  344. ss=U+0633U+0651
  345. s=U+0633
  346. J=U+062C
  347. jj=U+062CU+0651
  348. j=U+062C
  349. C=U+0686
  350. cc=U+0686U+0651
  351. c=U+0686
  352. HU+0323=U+062D
  353. hU+0323hU+0323=U+062DU+0651
  354. hU+0323=U+062D
  355. H=U+0647
  356. hh=U+0647U+0651
  357. h=U+0647
  358. KU+0332hU+0332=U+062E
  359. kU+0332hU+0332kU+0332hU+0332=U+062EU+0651
  360. kU+0332hU+0332=U+062E
  361. K=U+06A9
  362. kk=U+06A9U+0651
  363. k=U+06A9
  364. DU+0323=U+0688
  365. dU+0323dU+0323=U+0688U+0651
  366. dU+0323=U+0688
  367. D=U+062F
  368. dd=U+062FU+0651
  369. d=U+062F
  370. ZU+0324=U+0638
  371. zU+0324zU+0324=U+0638U+0651
  372. zU+0324=U+0638
  373. ZU+0323=U+0636
  374. zU+0323zU+0323=U+0636U+0651
  375. zU+0323=U+0636
  376. ZU+0332=U+0630
  377. zU+0332zU+0332=U+0630U+0651
  378. zU+0332=U+0630
  379. zz=U+0632U+0651
  380. Zh=U+0698
  381. zhzh=U+0698U+0651
  382. zh=U+0698
  383. Z=U+0632
  384. z=U+0632
  385. RU+0323=U+0691
  386. rU+0323rU+0323=U+0691U+0651
  387. rU+0323=U+0691
  388. R=U+0631
  389. rr=U+0631U+0651
  390. r=U+0631
  391. GU+0332hU+0332=U+063A
  392. gU+0332hU+0332gU+0332hU+0332=U+063AU+0651
  393. gU+0332hU+0332=U+063A
  394. G=U+06AF
  395. gg=U+06AFU+0651
  396. g=U+06AF
  397. F=U+0641
  398. ff=U+0641U+0651
  399. f=U+0641
  400. Q=U+0642
  401. qq=U+0642U+0651
  402. q=U+0642
  403. L=U+0644
  404. ll=U+0644U+0651
  405. l=U+0644
  406. M=U+0645
  407. mm=U+0645U+0651
  408. m=U+0645
  409. NU+0332=U+06BA
  410. nU+0332nU+0332=U+06BAU+0651
  411. nU+0332=U+06BA
  412. N=U+0646
  413. nn=U+0646U+0651
  414. n=U+0646
  415. V=U+0648
  416. vv=U+0648U+0651
  417. v=U+0648
  418. Y=U+064A
  419. yy=U+064AU+0651
  420. y=U+064A
  421. # ain (alone)
  422. U+02BB=U+0639
  423. # hamza (alone in final position)
  424. %U+02BE=U+0621
  425. %U+02BC=U+0621
  426. [ScriptToRoman]