persian.yml 7.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309
  1. general:
  2. name: Persian
  3. roman_to_script:
  4. map:
  5. # Punctuation marks:
  6. "# %": "\u066A ; cannot transliterate the truncation character"
  7. "*": "\u066D"
  8. ",": "\u060C"
  9. ";": "\u061B"
  10. "?": "\u061F"
  11. # Exceptions for specific words
  12. # Allah
  13. "Alla\u0304h": "\u0627\u0644\u0644\u0647"
  14. # Qur'an
  15. "Qur\u02BCa\u0304n": "\u0642\u0631\u0622\u0646"
  16. # lillah
  17. "lilla\u0304h": "\u0644\u0644\u0647"
  18. # billah
  19. "billa\u0304h": "\u0628\u0644\u0644\u0647"
  20. # Rahman
  21. "Rah\u0323ma\u0304n": "\u0631\u062D\u0645\u0646"
  22. # ta'lif
  23. # Ibn when it appears in the middle of a name sequence
  24. "ibn": "\u0628\u0646"
  25. # Parsing "sh[dot below] as in "Ishaq [name]"
  26. "%sh\u0323%": "\u0633\u062D"
  27. # Edition statements with Latin number
  28. "Cha\u0304p-i 1": "\u0686\u0627\u067E 1"
  29. "Cha\u0304p-i 2": "\u0686\u0627\u067E 2"
  30. "Cha\u0304p-i 3": "\u0686\u0627\u067E 3"
  31. "Cha\u0304p-i 4": "\u0686\u0627\u067E 4"
  32. "Cha\u0304p-i 5": "\u0686\u0627\u067E 5"
  33. "Cha\u0304p-i 6": "\u0686\u0627\u067E 6"
  34. "Cha\u0304p-i 7": "\u0686\u0627\u067E 7"
  35. "Cha\u0304p-i 8": "\u0686\u0627\u067E 8"
  36. "Cha\u0304p-i 9": "\u0686\u0627\u067E 9"
  37. # Numbers (Extended Arabic \u06F0-06F9 for Persian)
  38. # currently *not* valid MARC21 characters
  39. "# 0": "\u06F0"
  40. "# 1": "\u06F1"
  41. "# 2": "\u06F2"
  42. "# 3": "\u06F3"
  43. "# 4": "\u06F4"
  44. "# 5": "\u06F5"
  45. "# 6": "\u06F6"
  46. "# 7": "\u06F7"
  47. "# 8": "\u06F8"
  48. "# 9": "\u06F9"
  49. # Use Basic Arabic \u0660-0669, instead:
  50. "0": "\u0660"
  51. "1": "\u0661"
  52. "2": "\u0662"
  53. "3": "\u0663"
  54. "4": "\u0664"
  55. "5": "\u0665"
  56. "6": "\u0666"
  57. "7": "\u0667"
  58. "8": "\u0668"
  59. "9": "\u0669"
  60. "# prime ": " ZWNJ"
  61. "\u02B9a\u0304": "\u200C\u0622"
  62. "\u02B9a": "\u200C\u0627"
  63. "%\u02B9i\u0304": "\u200C\u0627\u0649"
  64. "\u02B9i\u0304": "\u200C\u0627\u064A"
  65. "i\u0304\u02B9a\u0304": "\u0649\u200C\u0622"
  66. "i\u0304\u02B9a": "\u0649\u200C\u0627"
  67. "i\u0304\u02B9u\u0304": "\u0649\u200C\u0622"
  68. "i\u0304\u02B9u": "\u0649\u200C\u0627"
  69. "i\u0304\u02B9": "\u0649\u200C"
  70. "\u02B9": "\u200C"
  71. # Vowel and vowel/consonant combinations
  72. # and hyphenated suffixes:
  73. # izafah here
  74. "%h-\u02BEi": "\u06C0"
  75. "%h-\u02BCi": "\u06C0 "
  76. "%-\u02BEi": "\u06C0"
  77. "%-\u02BCi": "\u06C0"
  78. "%h-yi": "\u0647\u200C\u0649"
  79. "%-yi": "\u0649"
  80. "%yi": "\u0649"
  81. "%\u02BEi\u0304": "\u0649"
  82. "%\u02BCi\u0304": "\u0649"
  83. "%i\u0304-i": "\u0649"
  84. "%i\u0304": "\u0649"
  85. "%ayy-i": "\u0649"
  86. "%ay": "\u0649"
  87. "%al-i": "\u0644"
  88. "%-i": ""
  89. # Hyphenated prefixes:
  90. "wa-": "\u0648"
  91. "bi-": "\u0628"
  92. "al-": "\u0627\u0644"
  93. "lil-": "\u0644\u0644"
  94. "li-": "\u0644"
  95. "ka-": "\u0643"
  96. # ayn combo
  97. "%\u02BBa\u0304%": "\u0639\u0627"
  98. # alif combos
  99. # [final position]
  100. "%a\u0304\u02BE": "\u0627\u0621"
  101. "%a\u0304\u02BC": "\u0627\u0621"
  102. "%a\u0304\u02BEi\u0304": "\u0627\u0626\u0649"
  103. "%a\u0304\u02BCi\u0304": "\u0627\u0626\u0649"
  104. # [initial position]
  105. "A\u0304\u02BEi\u0304%": "\u0622\u0626\u064A"
  106. "A\u0304\u02BCi\u0304%": "\u0622\u0626\u064A"
  107. "a\u0304\u02BEi\u0304%": "\u0622\u0626\u064A"
  108. "a\u0304\u02BCi\u0304%": "\u0622\u0626\u064A"
  109. # [medial position]
  110. "a\u0304\u02BEi\u0304": "\u0627\u0626\u064A"
  111. "a\u0304\u02BCi\u0304": "\u0627\u0626\u064A"
  112. "a\u0304\u02BEi": "\u0627\u0626"
  113. "a\u0304\u02BCi": "\u0627\u0626"
  114. "a\u02BEi\u0304": "\u0626\u064A"
  115. "a\u02BCi\u0304": "\u0626\u064A"
  116. "u\u0304\u02BEi\u0304": "\u0648\u0626\u0649"
  117. "u\u0304\u02BCi\u0304": "\u0648\u0626\u0649"
  118. # A
  119. "\u02BBA\u0304": "\u0639\u0627"
  120. "\u02BBa\u0304": "\u0639\u0627"
  121. "\u02BBA%": "\u0639"
  122. "\u02BBa": "\u0639"
  123. "A\u02BB%": "\u0627\u0639"
  124. "a\u02BB%": "\u0627\u0639"
  125. "A\u02BB": "\u0623\u0639"
  126. "a\u02BB": "\u0639"
  127. "a\u02BE": "\u0623"
  128. "a\u02BC": "\u0623"
  129. "\u02BEa": "\u0623"
  130. "\u02BCa": "\u0623"
  131. "a\u0304\u02BE": "\u0621"
  132. "a\u0304\u02BC": "\u0621"
  133. "A\u0304%": "\u0622"
  134. "a\u0304%": "\u0622"
  135. # previously an alif:
  136. "A\u0304": "\u0622"
  137. "a\u0304": "\u0627"
  138. "A\u0301": "\u0649"
  139. "a\u0301": "\u0649"
  140. "ayy": "\u064A"
  141. "A%": "\u0627"
  142. "a%": "\u0627"
  143. "A": "\u0627"
  144. "a": ""
  145. # I
  146. "\u02BBI\u0304": "\u0639\u064A"
  147. "\u02BBi\u0304": "\u0639\u064A"
  148. "I\u02BB%": "\u0627\u0639"
  149. "i\u02BB%": "\u0627\u0639"
  150. "i\u02BB": "\u0639"
  151. "\u02BBI%": "\u0639"
  152. "I\u02BE%": "\u0627\u0626"
  153. "I\u02BC%": "\u0627\u0626"
  154. "i\u02BE": "\u0626"
  155. "i\u02BC": "\u0626"
  156. "\u02BEi\u0304": "\u0626\u0649"
  157. "\u02BCi\u0304": "\u0626\u0649"
  158. "\u02BEi": "\u0626"
  159. "\u02BCi": "\u0626"
  160. "I\u0304%": "\u0627\u064A"
  161. "i\u0304%": "\u0627\u064A"
  162. "i\u0304y": "\u064A"
  163. "I\u0304": "\u0627\u0649"
  164. "i\u0304": "\u064A"
  165. "I%": "\u0627"
  166. "i%": "\u0627"
  167. "I": "\u0627"
  168. "i": ""
  169. # U
  170. "\u02BEu\u0304": "\u0626\u0648"
  171. "\u02BCu\u0304": "\u0626\u0648"
  172. "U\u02BE%": "\u0627\u0624"
  173. "U\u02BC%": "\u0627\u0624"
  174. "u\u02BE": "\u0624"
  175. "u\u02BC": "\u0624"
  176. "U\u0304w%": "\u0627\u0628"
  177. "u\u0304w": "\u0628"
  178. "U\u0304": "\u0627\u0648"
  179. "u\u0304": "\u0648"
  180. "U%": "\u0627"
  181. "u%": "\u0627"
  182. "U": "\u0627"
  183. "u": ""
  184. # Consonants:
  185. "B": "\u0628"
  186. "bb": "\u0628"
  187. "b": "\u0628"
  188. "P": "\u067E"
  189. "pp": "\u067E"
  190. "p": "\u067E"
  191. "T\u0323": "\u0637"
  192. "t\u0323t\u0323": "\u0637"
  193. "t\u0323": "\u0637"
  194. "T": "\u062A"
  195. "tt": "\u062A"
  196. "t": "\u062A"
  197. "Sh": "\u0634"
  198. "shsh": "\u0634"
  199. "sh": "\u0634"
  200. "S\u0323": "\u0635"
  201. "s\u0323s\u0323": "\u0635"
  202. "s\u0323": "\u0635"
  203. "S\u0332": "\u062B"
  204. "ss\u0332": "\u062B"
  205. "s\u0332": "\u062B"
  206. "S": "\u0633"
  207. "ss": "\u0633"
  208. "s": "\u0633"
  209. "J": "\u062C"
  210. "jj": "\u062C"
  211. "j": "\u062C"
  212. "Ch": "\u0686"
  213. "chch": "\u0686"
  214. "ch": "\u0686"
  215. "H\u0323": "\u062D"
  216. "h\u0323h\u0323": "\u062D"
  217. "h\u0323": "\u062D"
  218. "H": "\u0647"
  219. "hh": "\u0647"
  220. "h": "\u0647"
  221. "Kh": "\u062E"
  222. "khkh": "\u062E"
  223. "kh": "\u062E"
  224. "K": "\u06A9"
  225. "kk": "\u06A9"
  226. "k": "\u06A9"
  227. # Arabic d with dot below:
  228. "D\u0323": "\u0636"
  229. "d\u0323d\u0323": "\u0636"
  230. "d\u0323": "\u0636"
  231. "D": "\u062F"
  232. "dd": "\u062F"
  233. "d": "\u062F"
  234. "Zh": "\u0698"
  235. "zhzh": "\u0698"
  236. "zh": "\u0698"
  237. "Z\u0323": "\u0638"
  238. "z\u0323z\u0323": "\u0638"
  239. "z\u0323": "\u0638"
  240. "Z\u0324": "\u0636"
  241. "z\u0324z\u0324": "\u0636"
  242. "z\u0324": "\u0636"
  243. "Z\u0332": "\u0630"
  244. "zz\u0332": "\u0630"
  245. "z\u0332": "\u0630"
  246. "Z": "\u0632"
  247. "zz": "\u0632"
  248. "z": "\u0632"
  249. "R": "\u0631"
  250. "rr": "\u0631"
  251. "r": "\u0631"
  252. "Gh": "\u063A"
  253. "ghgh": "\u063A"
  254. "gh": "\u063A"
  255. "G": "\u06AF"
  256. "g": "\u06AF"
  257. "F": "\u0641"
  258. "ff": "\u0641"
  259. "f": "\u0641"
  260. "Q": "\u0642"
  261. "qq": "\u0642"
  262. "q": "\u0642"
  263. "L": "\u0644"
  264. "ll": "\u0644"
  265. "l": "\u0644"
  266. "M": "\u0645"
  267. "mm": "\u0645"
  268. "m": "\u0645"
  269. "N": "\u0646"
  270. "nn": "\u0646"
  271. "n": "\u0646"
  272. "V": "\u0648"
  273. "vv": "\u0648"
  274. "v": "\u0648"
  275. "W": "\u0648"
  276. "ww": "\u0648"
  277. "w": "\u0648"
  278. "Y": "\u064A"
  279. "y": "\u064A"
  280. # non-Arabic consonants:
  281. # ain (alone)
  282. "\u02BB": "\u0639"
  283. # hamza (alone in final position)
  284. "%\u02BE": "\u0621"
  285. "%\u02BC": "\u0621"