interscript 0.1.7 → 2.1.0b1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (314) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +11 -0
  3. data/.rspec +3 -0
  4. data/Gemfile +29 -0
  5. data/LICENSE.adoc +31 -0
  6. data/README.md +3 -0
  7. data/Rakefile +116 -0
  8. data/bin/console +14 -0
  9. data/bin/interscript +5 -0
  10. data/bin/maps_analyze_staging +168 -0
  11. data/bin/maps_debug_compilers +58 -0
  12. data/bin/maps_debug_ordering +88 -0
  13. data/bin/maps_debug_ruby_compile +24 -0
  14. data/bin/maps_debug_step_by_step +44 -0
  15. data/bin/maps_optimize_order +112 -0
  16. data/bin/maps_v1_analyze_regexps +45 -0
  17. data/bin/maps_v1_to_v2 +426 -0
  18. data/bin/setup +8 -0
  19. data/exe/interscript +6 -0
  20. data/interscript.gemspec +31 -0
  21. data/lib/interscript.rb +83 -133
  22. data/lib/interscript/command.rb +5 -5
  23. data/lib/interscript/compiler.rb +22 -0
  24. data/lib/interscript/compiler/javascript.rb +292 -0
  25. data/lib/interscript/compiler/ruby.rb +262 -0
  26. data/lib/interscript/dsl.rb +68 -0
  27. data/lib/interscript/dsl/aliases.rb +23 -0
  28. data/lib/interscript/dsl/document.rb +46 -0
  29. data/lib/interscript/dsl/group.rb +45 -0
  30. data/lib/interscript/dsl/group/parallel.rb +6 -0
  31. data/lib/interscript/dsl/items.rb +89 -0
  32. data/lib/interscript/dsl/metadata.rb +68 -0
  33. data/lib/interscript/dsl/stage.rb +6 -0
  34. data/lib/interscript/dsl/symbol_mm.rb +11 -0
  35. data/lib/interscript/dsl/tests.rb +12 -0
  36. data/lib/interscript/interpreter.rb +251 -0
  37. data/lib/interscript/node.rb +25 -0
  38. data/lib/interscript/node/alias_def.rb +15 -0
  39. data/lib/interscript/node/dependency.rb +13 -0
  40. data/lib/interscript/node/document.rb +45 -0
  41. data/lib/interscript/node/group.rb +34 -0
  42. data/lib/interscript/node/group/parallel.rb +9 -0
  43. data/lib/interscript/node/group/sequential.rb +2 -0
  44. data/lib/interscript/node/item.rb +52 -0
  45. data/lib/interscript/node/item/alias.rb +42 -0
  46. data/lib/interscript/node/item/any.rb +76 -0
  47. data/lib/interscript/node/item/capture.rb +50 -0
  48. data/lib/interscript/node/item/group.rb +51 -0
  49. data/lib/interscript/node/item/repeat.rb +40 -0
  50. data/lib/interscript/node/item/stage.rb +23 -0
  51. data/lib/interscript/node/item/string.rb +51 -0
  52. data/lib/interscript/node/metadata.rb +18 -0
  53. data/lib/interscript/node/rule.rb +6 -0
  54. data/lib/interscript/node/rule/funcall.rb +18 -0
  55. data/lib/interscript/node/rule/run.rb +15 -0
  56. data/lib/interscript/node/rule/sub.rb +68 -0
  57. data/lib/interscript/node/stage.rb +19 -0
  58. data/lib/interscript/node/tests.rb +15 -0
  59. data/lib/interscript/stdlib.rb +211 -0
  60. data/lib/interscript/utils/regexp_converter.rb +283 -0
  61. data/lib/interscript/version.rb +1 -1
  62. data/lib/interscript/visualize.rb +61 -0
  63. data/lib/interscript/visualize/group.html.erb +59 -0
  64. data/lib/interscript/visualize/json.rb +57 -0
  65. data/lib/interscript/visualize/map.html.erb +46 -0
  66. data/lib/interscript/visualize/nodes.rb +89 -0
  67. data/requirements.txt +1 -0
  68. metadata +78 -416
  69. data/README.adoc +0 -298
  70. data/lib/g2pwrapper.py +0 -34
  71. data/lib/interscript/fs.rb +0 -69
  72. data/lib/interscript/mapping.rb +0 -142
  73. data/lib/interscript/opal.rb +0 -57
  74. data/lib/interscript/opal/entrypoint.rb +0 -12
  75. data/lib/interscript/opal/map_translate.rb +0 -7
  76. data/lib/interscript/opal/maps.js.erb +0 -10
  77. data/lib/model-7 +0 -0
  78. data/lib/tha-pt-b-7 +0 -0
  79. data/maps/acadsin-zho-Hani-Latn-2002.yaml +0 -38916
  80. data/maps/alalc-amh-Ethi-Latn-1997.yaml +0 -513
  81. data/maps/alalc-amh-Ethi-Latn-2011.yaml +0 -138
  82. data/maps/alalc-ara-Arab-Latn-1997.yaml +0 -1287
  83. data/maps/alalc-asm-Deva-Latn-1997.yaml +0 -165
  84. data/maps/alalc-asm-Deva-Latn-2012.yaml +0 -40
  85. data/maps/alalc-aze-Cyrl-Latn-1997.yaml +0 -145
  86. data/maps/alalc-bel-Cyrl-Latn-1997.yaml +0 -129
  87. data/maps/alalc-ben-Beng-Latn-2017.yaml +0 -130
  88. data/maps/alalc-bul-Cyrl-Latn-1997.yaml +0 -98
  89. data/maps/alalc-ell-Grek-Latn-1997.yaml +0 -628
  90. data/maps/alalc-ell-Grek-Latn-2010.yaml +0 -626
  91. data/maps/alalc-guj-Gujr-Latn-1997.yaml +0 -266
  92. data/maps/alalc-guj-Gujr-Latn-2011.yaml +0 -64
  93. data/maps/alalc-hin-Deva-Latn-1997.yaml +0 -211
  94. data/maps/alalc-hin-Deva-Latn-2011.yaml +0 -47
  95. data/maps/alalc-kat-Geok-Latn-1997.yaml +0 -111
  96. data/maps/alalc-kat-Geor-Latn-1997.yaml +0 -150
  97. data/maps/alalc-kor-Hang-Latn-1997.yaml +0 -98
  98. data/maps/alalc-mal-Mlym-Latn-1997.yaml +0 -303
  99. data/maps/alalc-mal-Mlym-Latn-2012.yaml +0 -73
  100. data/maps/alalc-mar-Deva-Latn-1997.yaml +0 -189
  101. data/maps/alalc-mar-Deva-Latn-2011.yaml +0 -45
  102. data/maps/alalc-mkd-Cyrl-Latn-1997.yaml +0 -114
  103. data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +0 -103
  104. data/maps/alalc-mon-Cyrl-Latn-1997.yaml +0 -220
  105. data/maps/alalc-pan-Guru-Latn-1997.yaml +0 -256
  106. data/maps/alalc-pan-Guru-Latn-2011.yaml +0 -78
  107. data/maps/alalc-per-Arab-Latn-1997.yaml +0 -375
  108. data/maps/alalc-pli-Deva-Latn-2012.yaml +0 -144
  109. data/maps/alalc-pra-Deva-Latn-2012.yaml +0 -47
  110. data/maps/alalc-rus-Cyrl-Latn-1997.yaml +0 -225
  111. data/maps/alalc-rus-Cyrl-Latn-2012.yaml +0 -162
  112. data/maps/alalc-san-Deva-Latn-2012.yaml +0 -172
  113. data/maps/alalc-sin-Sinh-Latn-1997.yaml +0 -292
  114. data/maps/alalc-sin-Sinh-Latn-2011.yaml +0 -71
  115. data/maps/alalc-srp-Cyrl-Latn-1997.yaml +0 -118
  116. data/maps/alalc-srp-Cyrl-Latn-2013.yaml +0 -135
  117. data/maps/alalc-tam-Taml-Latn-1997.yaml +0 -62
  118. data/maps/alalc-tam-Taml-Latn-2011.yaml +0 -58
  119. data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +0 -145
  120. data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +0 -16
  121. data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +0 -283
  122. data/maps/bas-rus-Cyrl-Latn-2017-bss.yaml +0 -174
  123. data/maps/bas-rus-Cyrl-Latn-2017-oss.yaml +0 -169
  124. data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +0 -292
  125. data/maps/bgn-kor-Hang-Latn-1943.yaml +0 -35
  126. data/maps/bgn-kor-Kore-Latn-1943.yaml +0 -31
  127. data/maps/bgna-bul-Cyrl-Latn-2006.yaml +0 -208
  128. data/maps/bgna-bul-Cyrl-Latn-2009.yaml +0 -208
  129. data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +0 -532
  130. data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +0 -596
  131. data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +0 -108
  132. data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +0 -104
  133. data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +0 -188
  134. data/maps/bgnpcgn-bel-Cyrl-Latn-1979.yaml +0 -289
  135. data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +0 -119
  136. data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +0 -42
  137. data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml +0 -184
  138. data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +0 -705
  139. data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +0 -23
  140. data/maps/bgnpcgn-fas-Arab-Latn-1956.yaml +0 -96
  141. data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +0 -257
  142. data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +0 -131
  143. data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +0 -42
  144. data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +0 -253
  145. data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +0 -48
  146. data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +0 -48
  147. data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +0 -163
  148. data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +0 -190
  149. data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml +0 -223
  150. data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +0 -230
  151. data/maps/bgnpcgn-per-Arab-Latn-1958.yaml +0 -336
  152. data/maps/bgnpcgn-prs-Arab-Latn-2007.yaml +0 -639
  153. data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.yaml +0 -459
  154. data/maps/bgnpcgn-rue-Cyrl-Latn-2016.yaml +0 -168
  155. data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +0 -318
  156. data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +0 -170
  157. data/maps/bgnpcgn-tat-Cyrl-Latn-2007.yaml +0 -220
  158. data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.yaml +0 -240
  159. data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +0 -166
  160. data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +0 -119
  161. data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.yaml +0 -127
  162. data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.yaml +0 -82
  163. data/maps/bgnpcgn-zho-Hans-Latn-1979.yaml +0 -7456
  164. data/maps/bis-asm-Beng-Latn-13194-1991.yaml +0 -159
  165. data/maps/bis-ben-Beng-Latn-13194-1991.yaml +0 -156
  166. data/maps/bis-dev-Deva-Latn-13194-1991.yaml +0 -184
  167. data/maps/bis-guj-Gujr-Latn-13194-1991.yaml +0 -181
  168. data/maps/bis-knd-Knda-Latn-13194-1991.yaml +0 -173
  169. data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +0 -176
  170. data/maps/bis-ori-Orya-Latn-13194-1991.yaml +0 -160
  171. data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +0 -175
  172. data/maps/bis-tel-Telu-Latn-13194-1991.yaml +0 -170
  173. data/maps/bis-tml-Taml-Latn-13194-1991.yaml +0 -155
  174. data/maps/by-bel-Cyrl-Latn-1998.yaml +0 -172
  175. data/maps/by-bel-Cyrl-Latn-2007.yaml +0 -115
  176. data/maps/din-grc-Grek-Latn-31634-2011-t1.yaml +0 -899
  177. data/maps/din-hin-Deva-Latn-33904-2018.yaml +0 -100
  178. data/maps/din-kat-Geor-Latn-32707-2010.yaml +0 -145
  179. data/maps/din-mar-Deva-Latn-33904-2018.yaml +0 -84
  180. data/maps/din-nep-Deva-Latn-33904-2018.yaml +0 -119
  181. data/maps/din-pli-Deva-Latn-33904-2018.yaml +0 -75
  182. data/maps/din-pra-Deva-Latn-33904-2018.yaml +0 -63
  183. data/maps/din-san-Deva-Latn-33904-2018.yaml +0 -338
  184. data/maps/din-tam-Taml-Latn-33903-2016.yaml +0 -213
  185. data/maps/dos-nep-Deva-Latn-1997.yaml +0 -47
  186. data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +0 -684
  187. data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +0 -680
  188. data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +0 -19
  189. data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +0 -31
  190. data/maps/ggg-kat-Geor-Latn-2002.yaml +0 -92
  191. data/maps/gki-bel-Cyrl-Latn-1992.yaml +0 -33
  192. data/maps/gki-bel-Cyrl-Latn-2000.yaml +0 -201
  193. data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml +0 -190
  194. data/maps/gost-rus-Cyrl-Latn-7.79-2000-2002.yaml +0 -157
  195. data/maps/hk-yue-Hani-Latn-1888.yaml +0 -38497
  196. data/maps/icao-bel-Cyrl-Latn-9303.yaml +0 -136
  197. data/maps/icao-bul-Cyrl-Latn-9303.yaml +0 -118
  198. data/maps/icao-fas-Arab-Latn-9303.yaml +0 -103
  199. data/maps/icao-heb-Hebr-Latn-9303.yaml +0 -151
  200. data/maps/icao-mkd-Cyrl-Latn-9303.yaml +0 -117
  201. data/maps/icao-rus-Cyrl-Latn-9303.yaml +0 -117
  202. data/maps/icao-srp-Cyrl-Latn-9303.yaml +0 -117
  203. data/maps/icao-ukr-Cyrl-Latn-9303.yaml +0 -119
  204. data/maps/iso-ara-Arab-Latn-233-1984.yaml +0 -323
  205. data/maps/iso-asm-Beng-Latn-15919-2001.yaml +0 -75
  206. data/maps/iso-ben-Beng-Latn-15919-2001.yaml +0 -175
  207. data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +0 -613
  208. data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +0 -44
  209. data/maps/iso-guj-Gujr-Latn-15919-2001.yaml +0 -220
  210. data/maps/iso-hin-Deva-Latn-15919-2001.yaml +0 -87
  211. data/maps/iso-inc-Deva-Latn-15919-2001.yaml +0 -61
  212. data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +0 -66
  213. data/maps/iso-kan-Knda-Latn-15919-2001.yaml +0 -220
  214. data/maps/iso-kat-Geor-Latn-9984-1996.yaml +0 -145
  215. data/maps/iso-kor-Hang-Latn-1996-method1.yaml +0 -240
  216. data/maps/iso-kor-Hang-Latn-1996-method2.yaml +0 -226
  217. data/maps/iso-mal-Mlym-Latn-15919-2001.yaml +0 -281
  218. data/maps/iso-mar-Deva-Latn-15919-2001.yaml +0 -75
  219. data/maps/iso-nep-Deva-Latn-15919-2001.yaml +0 -87
  220. data/maps/iso-ori-Orya-Latn-15919-2001.yaml +0 -193
  221. data/maps/iso-pan-Guru-Latn-15919-2001.yaml +0 -222
  222. data/maps/iso-pli-Beng-Latn-15919-2001.yaml +0 -73
  223. data/maps/iso-pli-Deva-Latn-15919-2001.yaml +0 -74
  224. data/maps/iso-pli-Sinh-Latn-15919-2001.yaml +0 -219
  225. data/maps/iso-pli-Thai-Latn-15919-2001.yaml +0 -55
  226. data/maps/iso-pra-Deva-Latn-15919-2001.yaml +0 -59
  227. data/maps/iso-prs-Arab-Latn-233-3-1999.yaml +0 -366
  228. data/maps/iso-rus-Cyrl-Latn-9-1995.yaml +0 -271
  229. data/maps/iso-san-Deva-Latn-15919-2001.yaml +0 -220
  230. data/maps/iso-tam-Taml-Latn-15919-2001.yaml +0 -159
  231. data/maps/iso-tel-Telu-Latn-15919-2001.yaml +0 -220
  232. data/maps/iso-tha-Thai-Latn-11940-1998.yaml +0 -109
  233. data/maps/kp-kor-Hang-Latn-2002.yaml +0 -909
  234. data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +0 -44820
  235. data/maps/mext-jpn-Hrkt-Latn-1954.yaml +0 -411
  236. data/maps/mns-mon-Cyrl-Latn-5217-2012.yaml +0 -163
  237. data/maps/mns-mon-Latn-Cyrl-5217-2012.yaml +0 -200
  238. data/maps/moct-kor-Hang-Latn-2000.yaml +0 -807
  239. data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +0 -541
  240. data/maps/mvd-bel-Cyrl-Latn-2008.yaml +0 -225
  241. data/maps/mvd-bel-Cyrl-Latn-2010.yaml +0 -63
  242. data/maps/mvd-rus-Cyrl-Latn-2008.yaml +0 -109
  243. data/maps/mvd-rus-Cyrl-Latn-2010.yaml +0 -37
  244. data/maps/odni-ara-Arab-Latn-2015.yaml +0 -425
  245. data/maps/odni-aze-Cyrl-Latn-2015.yaml +0 -144
  246. data/maps/odni-bel-Cyrl-Latn-2015.yaml +0 -148
  247. data/maps/odni-bul-Cyrl-Latn-2015.yaml +0 -96
  248. data/maps/odni-che-Cyrl-Latn-2015.yaml +0 -169
  249. data/maps/odni-fas-Arab-Latn-2015.yaml +0 -406
  250. data/maps/odni-hin-Deva-Latn-2015.yaml +0 -258
  251. data/maps/odni-kat-Geor-Latn-2015.yaml +0 -87
  252. data/maps/odni-kaz-Cyrl-Latn-2015.yaml +0 -148
  253. data/maps/odni-kir-Cyrl-Latn-2015.yaml +0 -136
  254. data/maps/odni-kor-Hang-Latn-2015.yaml +0 -375
  255. data/maps/odni-mkd-Cyrl-Latn-2015.yaml +0 -122
  256. data/maps/odni-per-Arab-Latn-2015.yaml +0 -228
  257. data/maps/odni-rus-Cyrl-Latn-2015.yaml +0 -77
  258. data/maps/odni-srp-Cyrl-Latn-2015.yaml +0 -129
  259. data/maps/odni-tat-Cyrl-Latn-2015.yaml +0 -142
  260. data/maps/odni-tgk-Cyrl-Latn-2015.yaml +0 -148
  261. data/maps/odni-uig-Cyrl-Latn-2015.yaml +0 -138
  262. data/maps/odni-ukr-Cyrl-Latn-2015.yaml +0 -157
  263. data/maps/odni-urd-Arab-Latn-2015.yaml +0 -221
  264. data/maps/odni-uzb-Cyrl-Latn-2015.yaml +0 -166
  265. data/maps/royin-tha-Thai-Latn-1939-generic.yaml +0 -90
  266. data/maps/royin-tha-Thai-Latn-1968.yaml +0 -183
  267. data/maps/royin-tha-Thai-Latn-1999-chained.yaml +0 -180
  268. data/maps/royin-tha-Thai-Latn-1999.yaml +0 -80
  269. data/maps/sac-zho-Hans-Latn-1979.yaml +0 -24763
  270. data/maps/sasm-mon-Mong-Latn-general-1978.yaml +0 -389
  271. data/maps/sasm-mon-Mong-Latn-phonetic-1978.yaml +0 -354
  272. data/maps/ses-ara-Arab-Latn-1930.yaml +0 -283
  273. data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +0 -222
  274. data/maps/ua-ukr-Cyrl-Latn-1996.yaml +0 -197
  275. data/maps/ua-ukr-Cyrl-Latn-2007.yaml +0 -75
  276. data/maps/ua-ukr-Cyrl-Latn-2010.yaml +0 -192
  277. data/maps/un-amh-Ethi-Latn-2016.yaml +0 -602
  278. data/maps/un-ara-Arab-Latn-1971.yaml +0 -139
  279. data/maps/un-ara-Arab-Latn-1972.yaml +0 -159
  280. data/maps/un-ara-Arab-Latn-2017.yaml +0 -420
  281. data/maps/un-bel-Cyrl-Latn-2007.yaml +0 -114
  282. data/maps/un-ben-Beng-Latn-2016.yaml +0 -534
  283. data/maps/un-ell-Grek-Latn-1987-phonetic.yaml +0 -780
  284. data/maps/un-ell-Grek-Latn-1987-tl.yaml +0 -31
  285. data/maps/un-ell-Grek-Latn-1987-ts.yaml +0 -19
  286. data/maps/un-hin-Deva-Latn-2016.yaml +0 -222
  287. data/maps/un-mar-Deva-Latn-2016.yaml +0 -91
  288. data/maps/un-mon-Mong-Latn-general-2013.yaml +0 -264
  289. data/maps/un-mon-Mong-Latn-phonetic-2013.yaml +0 -264
  290. data/maps/un-nep-Deva-Latn-1972.yaml +0 -350
  291. data/maps/un-nep-Deva-Latn-2013.yaml +0 -74
  292. data/maps/un-rus-Cyrl-Latn-1987.yaml +0 -166
  293. data/maps/un-ukr-Cyrl-Latn-1998.yaml +0 -53
  294. data/maps/un-ukr-Cyrl-Latn-2012.yaml +0 -162
  295. data/maps/var-hin-Deva-Latn-hunterian-1872.yaml +0 -221
  296. data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +0 -406
  297. data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +0 -386
  298. data/maps/var-kor-Hang-Hang-jamo.yaml +0 -11193
  299. data/maps/var-kor-Hang-Latn-mr-1939.yaml +0 -1054
  300. data/maps/var-kor-Kore-Hang-2013.yaml +0 -59754
  301. data/maps/var-kor-Kore-Latn-mr-1939.yaml +0 -36
  302. data/maps/var-mar-Deva-Latn-hunterian-1872.yaml +0 -43
  303. data/maps/var-mon-Mong-Latn-1930.yaml +0 -102
  304. data/maps/var-mon-Mong-Latn-lessing.yaml +0 -272
  305. data/maps/var-mon-Mong-Latn-vpmc.yaml +0 -274
  306. data/maps/var-pra-Deva-Latn-iast-1912.yaml +0 -30
  307. data/maps/var-san-Deva-Latn-iast-1912.yaml +0 -149
  308. data/maps/var-tha-Thai-Thai-phonemic.yaml +0 -59
  309. data/maps/var-tha-Thai-Zsym-ipa.yaml +0 -301
  310. data/maps/var-zho-Hani-Latn-wd-1979.yaml +0 -38912
  311. data/spec/interscript/filenames_spec.rb +0 -384
  312. data/spec/interscript/mapping_spec.rb +0 -42
  313. data/spec/interscript_spec.rb +0 -29
  314. data/spec/spec_helper.rb +0 -3
@@ -1,213 +0,0 @@
1
- ---
2
- authority_id: din
3
- id: 33903-2016
4
- language: iso-639-2:tam
5
- source_script: Taml
6
- destination_script: Latn
7
- name: "DIN 33903:2016-02: Information und Dokumentation - Umschrift Tamil"
8
- url: https://www.beuth.de/de/norm/din-33903/247150527
9
- creation_date: 2018
10
- description: |
11
- This standard specifies the transcription of the letters of the
12
- Tamil alphabet in Latin letters. It is based on international
13
- standards as well as on the preprint of the alphabetical tables,
14
- which were published in 1976 with the introduction of the rules for
15
- alphabetical cataloging. It can be used in all areas, but in
16
- particular the aim is to standardize the library and publication
17
- area.
18
-
19
- notes:
20
- - |
21
- Since the Tamil script is a syllabic script, the consonant -a inherent in the transliteration is always written, even in the final.
22
-
23
- - |
24
- A point above the consonant, the so-called "pulli", means in Tamil that the inherent -a is omitted:
25
- கார்த்திகேயன் kārttikēyaṉ
26
- - |
27
- Tamil has no anusvara; in contrast to other South Asian scripts, the class nasal is always written.
28
- - |
29
- Tamil also has no ligatures.
30
-
31
- tests:
32
- - source: "கார்த்திகேயன்"
33
- expected: "kārttikēyaṉ"
34
- - source: "௲"
35
- expected: "1000"
36
- - source: "இளைஞர்களின் உறுதியான மனநிலையை பிரதிபலிக்கிறது: நீட் தேர்வில் ௮௫-௯௦ சதவீத மாணவர்கள் பங்கேற்பு - ரமேஷ் பொக்ரியால்"
37
- expected: "iḷaiñarkaḷiṉ uṟutiyāṉa maṉanilaiyai piratipalikkiṟatu: nīṭ tērvil 85-90 catavīta māṇavarkaḷ paṅkēṟpu - ramēṣ pokriyāl"
38
- - source: "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்"
39
- expected: "nāṭāḷumaṉṟattil 4 macōtākkaḷai etirkka kāṅkiras muṭivu - jeyarām ramēṣ"
40
- - source: "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி"
41
- expected: "karnāṭakāvil mēlum 9,894 pērukku korōṉā toṟṟu uṟuti"
42
- - source: "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?"
43
- expected: "aitarāpāttukku kaikoṭukkumā atiraṭi?"
44
- - source: "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்"
45
- expected: "amerikka ōpaṉ ṭeṉṉis: iṟutippōṭṭiyil ṭomiṉik-sverēv"
46
- - source: "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்"
47
- expected: "ai.pi.el. kirikkeṭṭil kaḷam iṟaṅkum amerikka vīrar"
48
- - source: "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்"
49
- expected: "amerikka ōpaṉ ṭeṉṉis; navōmi ocākā cāmpiyaṉ paṭṭam veṉṟār"
50
- - source: "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்"
51
- expected: "putiya kalvikkoḷkaikku etirppu: muṉṉāḷ tuṇaivēntarkaḷ 20 pēr piratamarukku kaṭitam"
52
- - source: "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு"
53
- expected: "inta āṇṭu ai.pi.el. kōppaiyai enta aṇi vellum? - keviṉ pīṭṭarcaṉ kaṇippu"
54
- - source: "இந்திய எண்ணெய் கப்பலில் தீ: விபத்து குறித்த எச்சரிக்கையை கப்பல் அதிகாரிகள் புறக்கணித்தனர் - இலங்கை கோர்ட்டு தகவல்"
55
- expected: "intiya eṇṇey kappalil tī: vipattu kuṟitta eccarikkaiyai kappal atikārikaḷ puṟakkaṇittaṉar - ilaṅkai kōrṭṭu takaval"
56
-
57
- map:
58
-
59
- rules:
60
- - pattern: ([க]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
61
- result: 'k'
62
- - pattern: ([ங]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
63
- result: 'ṅ'
64
- - pattern: ([ச]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
65
- result: 'c'
66
- - pattern: ([ஞ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
67
- result: 'ñ'
68
- - pattern: ([ட]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
69
- result: 'ṭ'
70
- - pattern: ([ண]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
71
- result: 'ṇ'
72
- - pattern: ([த]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
73
- result: 't'
74
- - pattern: ([ந]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
75
- result: 'n'
76
- - pattern: ([ப]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
77
- result: 'p'
78
- - pattern: ([ம]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
79
- result: 'm'
80
- - pattern: ([ய]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
81
- result: 'y'
82
- - pattern: ([ர]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
83
- result: 'r'
84
- - pattern: ([ல]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
85
- result: 'l'
86
- - pattern: ([ள]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
87
- result: 'ḷ'
88
- - pattern: ([ழ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
89
- result: 'ḻ'
90
- - pattern: ([வ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
91
- result: 'v'
92
- - pattern: ([ற]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
93
- result: 'ṟ'
94
- - pattern: ([ன]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
95
- result: 'ṉ'
96
- - pattern: ([ஜ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
97
- result: 'j'
98
- - pattern: ([ஶ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
99
- result: 'ś'
100
- - pattern: ([ஷ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
101
- result: 'ṣ'
102
- - pattern: ([ஸ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
103
- result: 's'
104
- - pattern: ([ஹ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
105
- result: 'h'
106
-
107
- characters:
108
- 'அ': 'a'
109
- 'ஆ': 'ā'
110
- 'ா': 'ā'
111
-
112
- 'இ': 'i'
113
- 'ி': 'i'
114
-
115
- 'ஈ': 'ī'
116
- 'ீ': 'ī'
117
-
118
- 'உ': 'u'
119
- 'ு': 'u'
120
-
121
- 'ஊ': 'ū'
122
- 'ூ': 'ū'
123
-
124
- 'ெ': "e"
125
- 'எ': 'e'
126
-
127
- 'ே': "ē"
128
- 'ஏ': 'ē'
129
-
130
- 'ஐ': 'ai'
131
- 'ை': "ai"
132
-
133
- 'ஒ': 'o'
134
- 'ொ': 'o'
135
-
136
- 'ோ': 'ō'
137
- 'ஓ': 'ō'
138
-
139
- 'ஔ': 'au'
140
- 'ௌ': 'au'
141
-
142
- 'க்': 'k'
143
- 'ங்': 'ṅ'
144
- 'ச்': 'c'
145
- 'ஞ்': 'ñ'
146
- 'ட்': 'ṭ'
147
- 'ண்': 'ṇ'
148
- 'த்': 't'
149
- 'ந்': 'n'
150
- 'ப்': 'p'
151
- 'ம்': 'm'
152
- 'ய்': 'y'
153
- 'ர்': 'r'
154
- 'ல்': 'l'
155
- 'ள்': 'ḷ'
156
- 'ழ்': 'ḻ'
157
- 'வ்': 'v'
158
- 'ற்': 'ṟ'
159
- 'ன்': 'ṉ'
160
- 'ஜ்': 'j'
161
-
162
- 'ஶ்': 'ś'
163
- 'ஷ்': 'ṣ'
164
- 'ஸ்': 's'
165
- 'ஹ்': 'h'
166
-
167
-
168
- 'க': 'ka'
169
- 'ங': 'ṅa'
170
- 'ஃ': 'ḵ'
171
- 'ச': 'ca'
172
- 'ஞ': 'ña'
173
- 'ட': 'ṭa'
174
- 'ண': 'ṇa'
175
- 'த': 'ta'
176
- 'ந': 'na'
177
- 'ப': 'pa'
178
- 'ம': 'ma'
179
- 'ய': 'ya'
180
- 'ர': 'ra'
181
- 'ல': 'la'
182
- 'ள': 'ḷa'
183
- 'ழ': 'ḻa'
184
- 'வ': 'va'
185
- 'ற': 'ṟa'
186
- 'ன': 'ṉa'
187
- 'ஜ': 'ja'
188
- 'ஶ': 'śa'
189
- 'ஷ': 'ṣa'
190
- 'ஸ': 'sa'
191
- 'ஹ': 'ha'
192
-
193
- # Digits
194
- '௧': '1'
195
- '௨': '2'
196
- '௩': '3'
197
- '௪': '4'
198
- '௫': '5'
199
- '௬': '6'
200
- '௭': '7'
201
- '௮': '8'
202
- '௯': '9'
203
- '௦': '0'
204
- '௰': '10'
205
- '௱': '100'
206
- '௲': '1000'
207
-
208
-
209
-
210
-
211
- "‍": '' # no need for zero with joiner
212
- "‌": '' # no need for zero with non joiner
213
-
@@ -1,47 +0,0 @@
1
- ---
2
- authority_id: bgnpcgn
3
- id: 1997
4
- language: iso-639-2:nep
5
- source_script: Deva
6
- destination_script: Latn
7
- name: Nepali Romanization, 1997
8
- url: http://nationalgeoportal.gov.np/old/pdf/translation2.pdf
9
- creation_date: 1997
10
- description: |
11
- Survey Department, Ministry of Land Management, Cooperatives and Poverty Alleviation, Government of Nepal.
12
-
13
- notes:
14
- - |
15
- ं (anusvara) is rendered by
16
- ṅ before क, ख, ग, and घ
17
- ñ before च, छ, ज, and झ
18
- ṇ before ट, ठ, ड, and ढ
19
- n before त, थ, द, and ध
20
- ṁ before य, र, ल, व, श, ष, स
21
-
22
- tests:
23
- - source: "दुःख"
24
- expected: "duhkh"
25
- - source: "पूरा भइसकेका विषयलाई माग बनाएर दबाब नदिनुस्"
26
- expected: "pūrā bhiskekā viṣylāī māg bnāer dbāb ndinusa"
27
- - source: "जाँदै छ कता नेपाली संगीत"
28
- expected: "jā~dai chh ktā nepālī sṅgīt"
29
- - source: "३५ मिनेटको यो डकुमेन्ट्री फिल्मले प्रथम पुरस्कारस्वरूप ग्रान्ड पिक्स अवार्ड पाएको हो"
30
- expected: "35 mineṭko yo ḍkumenaṭarī philamle parthm pursakārsavrūp garānaḍ pikas avāraḍ pāeko ho"
31
- - source: "विक्षनरी"
32
- expected: "vikṣnrī"
33
- - source: "रुसमा उत्कृष्ट"
34
- expected: "rusmā utakṛiṣaṭ"
35
- - source: "वाणिज्य"
36
- expected: "vāṇijay"
37
- - source: "अंक विद्या"
38
- expected: "aṅk vidayā"
39
-
40
- map:
41
-
42
- inherit: "bgnpcgn-nep-Deva-Latn-2011"
43
-
44
- characters:
45
-
46
- # Bisarga
47
- 'ः': 'h'
@@ -1,684 +0,0 @@
1
- ---
2
- authority_id: elot
3
- id: 1982-tl
4
- language: iso-639-2:ell
5
- source_script: Grek
6
- destination_script: Latn
7
- name: ELOT 743:1982 (transliteration)
8
- url:
9
- creation_date: 1982
10
- description: |
11
- ELOT 743:1982 transliteration table for Greek
12
-
13
- note:
14
- - This was the intended system in ELOT 743:1982 for transliteration, as is apparent from un-ell-Grek-Latn-1987-tl and iso-ell-Grek-Latn-843-1997-t2, and ELOT 743:2001, Annex B; but the reversible character diacritics are missing from the currently available document, and the document does not indicate what there was supposed to be.
15
- - "\"Transliteration\" as used in this specification and its inheritors refers to reversible transliteration, as distinct from \"transcription\", which is a simpler transliteration and which is intended for default use."
16
-
17
- tests:
18
- - source: |
19
- Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.
20
-
21
- Γιάννης Μακρυγιάννης.
22
-
23
- expected: |
24
- Éna práma mónon me parakíni̱se ki eména na grápso̱ óti toúti̱n ti̱n patrída ti̱n échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai fto̱choí kai politikoí kai stratio̱tikoí kai oi pléon mikróteroi ánthro̱poi; ósoi ago̱nistí̱kamen, analógo̱s o katheís, échomen na zí̱somen edó̱. To loipón doulépsamen óloi mazí, na ti̱n fylámen ki óloi mazí kai na mi̱n légei oúte o dynatós «egó̱» oúte o adýnatos. Xérete póte na légei o katheís «egó̱»? Ótan ago̱nisteí mónos tou kai fkiásei í̱ chalásei, na légei «egó̱»; ótan ómo̱s ago̱nízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egó̱». Kai eis to exí̱s na máthomen gnó̱si̱, an thélomen na fkiásomen cho̱rión, na zí̱somen óloi mazí.
25
-
26
- Giánni̱s Makrygiánni̱s.
27
-
28
-
29
- - source: ΑΘΗΝΑ
30
- expected: ATHI̱NA
31
- - source: μπαμπάκι
32
- expected: bampáki
33
- - source: νταντά
34
- expected: ntantá
35
- - source: γκέγκε
36
- expected: gkégke
37
- - source: Γκαμπόν
38
- expected: Gkampón
39
- - source: Μάγχη
40
- expected: Máṉchi̱
41
- - source: κογξ
42
- expected: koṉx
43
- - source: υιός
44
- expected: yiós
45
- - source: Υιός
46
- expected: Yiós
47
- - source: νεράντζι
48
- expected: nerántzi
49
- - source: Γοίθιος
50
- expected: Goíthios
51
- - source: μπέικον
52
- expected: béïkon
53
- - source: μπέϊκον
54
- expected: béïkon
55
- - source: βόλεϊ
56
- expected: vóleï
57
- - source: αθεΐα
58
- expected: atheḯa
59
- - source: Εϊγιαφιάτλαγιοκουτλ
60
- expected: Eïgiafiátlagiokoutl
61
- - source: Εΐτζι
62
- expected: Eḯtzi
63
- - source: Μυρτώο
64
- expected: Myrtó̱o
65
- - source: αέρας
66
- expected: aéras
67
- - source: γαυ γαυ
68
- expected: gaf̱ gaf̱
69
- - source: Ταΰγετος
70
- expected: Taÿ́getos
71
- - source: σπρέυ
72
- expected: spréy
73
-
74
- - source: Αθήνα
75
- expected: Athí̱na
76
- - source: Άγιον Όρος
77
- expected: Ágion Óros
78
- - source: Άγραφα
79
- expected: Ágrafa
80
- - source: Αγρίνιο
81
- expected: Agrínio
82
- - source: Αίγινα
83
- expected: Aígina
84
- - source: Αίγιο
85
- expected: Aígio
86
- - source: Αλεξανδρούπολη
87
- expected: Alexandroúpoli̱
88
- - source: Αλεποχώρι
89
- expected: Alepochó̱ri
90
- - source: Αμοργός
91
- expected: Amorgós
92
- - source: Άμφισσα
93
- expected: Ámfissa
94
- - source: Αράχωβα
95
- expected: Arácho̱va
96
- - source: Άργος
97
- expected: Árgos
98
- - source: Αρκαδία
99
- expected: Arkadía
100
- - source: Άρτα
101
- expected: Árta
102
- - source: Βελούχι
103
- expected: Veloúchi
104
- - source: Βέροια
105
- expected: Véroia
106
- - source: Βοιωτία
107
- expected: Voio̱tía
108
- - source: Βόλος
109
- expected: Vólos
110
- - source: Βόνιτσα
111
- expected: Vónitsa
112
- - source: Γαλαξίδι
113
- expected: Galaxídi
114
- - source: Γαλάτσι
115
- expected: Galátsi
116
- - source: Γιαννιτσά
117
- expected: Giannitsá
118
- - source: Γλυφάδα
119
- expected: Glyfáda
120
- - source: Γρανίτσα
121
- expected: Granítsa
122
- - source: Γρεβενά
123
- expected: Grevená
124
- - source: Γύθειο
125
- expected: Gýtheio
126
- - source: Διόνυσος
127
- expected: Diónysos
128
- - source: Δίστομο
129
- expected: Dístomo
130
- - source: Δολιανά
131
- expected: Dolianá
132
- - source: Δράμα
133
- expected: Dráma
134
- - source: Δωδεκάνησα
135
- expected: Do̱dekáni̱sa
136
- - source: Έδεσσα
137
- expected: Édessa
138
- - source: Ελευσίνα
139
- expected: Elef̱sína
140
- - source: Επίδαυρος
141
- expected: Epídav̱ros
142
- - source: Επτάνησα
143
- expected: Eptáni̱sa
144
- - source: Ερμούπολη
145
- expected: Ermoúpoli̱
146
- - source: Εύβοια
147
- expected: Év̱voia
148
- - source: Ζάκυνθος
149
- expected: Zákynthos
150
- - source: Ήπειρος
151
- expected: Í̱peiros
152
- - source: Ηράκλειο
153
- expected: I̱rákleio
154
- - source: Θάσος
155
- expected: Thásos
156
- - source: Θεσσαλονίκη
157
- expected: Thessaloníki̱
158
- - source: Θεσσαλία
159
- expected: Thessalía
160
- - source: Θεσπρωτία
161
- expected: Thespro̱tía
162
- - source: Θήβα
163
- expected: Thí̱va
164
- - source: Θράκη
165
- expected: Thráki̱
166
- - source: Ιθάκη
167
- expected: Itháki̱
168
- - source: Ίος
169
- expected: Íos
170
- - source: Ιωάννινα
171
- expected: Io̱ánnina
172
- - source: Καβάλα
173
- expected: Kavála
174
- - source: Καλάβρυτα
175
- expected: Kalávryta
176
- - source: Καλαμάτα
177
- expected: Kalamáta
178
- - source: Καλαμπάκα
179
- expected: Kalampáka
180
- - source: Καλύβια
181
- expected: Kalývia
182
- - source: Κάλυμνος
183
- expected: Kálymnos
184
- - source: Καρδίτσα
185
- expected: Kardítsa
186
- - source: Καρπενήσι
187
- expected: Karpení̱si
188
- - source: Κάρυστος
189
- expected: Kárystos
190
- - source: Καστελλόριζο
191
- expected: Kastellórizo
192
- - source: Καστοριά
193
- expected: Kastoriá
194
- - source: Κατερίνη
195
- expected: Kateríni̱
196
- - source: Κάτω Αχαΐα
197
- expected: Káto̱ Achaḯa
198
- - source: Κερατέα
199
- expected: Keratéa
200
- - source: Κέρκυρα
201
- expected: Kérkyra
202
- - source: Κεφαλλονιά
203
- expected: Kefalloniá
204
- - source: Κηφισιά
205
- expected: Ki̱fisiá
206
- - source: Κιλκίς
207
- expected: Kilkís
208
- - source: Κοζάνη
209
- expected: Kozáni̱
210
- - source: Κολωνός
211
- expected: Kolo̱nós
212
- - source: Κομοτηνή
213
- expected: Komoti̱ní̱
214
- - source: Κόρινθος
215
- expected: Kórinthos
216
- - source: Κορώνη
217
- expected: Koró̱ni̱
218
- - source: Κρανίδι
219
- expected: Kranídi
220
- - source: Κρέστενα
221
- expected: Kréstena
222
- - source: Κρήτη
223
- expected: Krí̱ti̱
224
- - source: Κύθηρα
225
- expected: Kýthi̱ra
226
- - source: Κυκλάδες
227
- expected: Kykládes
228
- - source: Κύμη
229
- expected: Kými̱
230
- - source: Κυψέλη
231
- expected: Kypséli̱
232
- - source: Κως
233
- expected: Ko̱s
234
- - source: Λαγκαδάς
235
- expected: Lagkadás
236
- - source: Λαμία
237
- expected: Lamía
238
- - source: Λάρισα
239
- expected: Lárisa
240
- - source: Λαύριο
241
- expected: Láv̱rio
242
- - source: Λέρος
243
- expected: Léros
244
- - source: Λέσβος
245
- expected: Lésvos
246
- - source: Λευκάδα
247
- expected: Lef̱káda
248
- - source: Λήμνος
249
- expected: Lí̱mnos
250
- - source: Λιβαδειά
251
- expected: Livadeiá
252
- - source: Μακεδονία
253
- expected: Makedonía
254
- - source: Μάνη
255
- expected: Máni̱
256
- - source: Μαραθώνας
257
- expected: Marathó̱nas
258
- - source: Μαρκόπουλο
259
- expected: Markópoulo
260
- - source: Μαρούσι
261
- expected: Maroúsi
262
- - source: Μέγαρα
263
- expected: Mégara
264
- - source: Μεσολόγγι
265
- expected: Mesolóṉgi
266
- - source: Μεταξουργείο
267
- expected: Metaxourgeío
268
- - source: Μέτσοβο
269
- expected: Métsovo
270
- - source: Μήλος
271
- expected: Mí̱los
272
- - source: Μύκονος
273
- expected: Mýkonos
274
- - source: Μυστράς
275
- expected: Mystrás
276
- - source: Μυτιλήνη
277
- expected: Mytilí̱ni̱
278
- - source: Νάξος
279
- expected: Náxos
280
- - source: Νάουσα
281
- expected: Náousa
282
- - source: Ναύπακτος
283
- expected: Náf̱paktos
284
- - source: Ναύπλιο
285
- expected: Náf̱plio
286
- - source: Νέα Σμύρνη
287
- expected: Néa Smýrni̱
288
- - source: Νίσυρος
289
- expected: Nísyros
290
- - source: Ξάνθη
291
- expected: Xánthi̱
292
- - source: Όλυμπος
293
- expected: Ólympos
294
- - source: Παγκράτι
295
- expected: Pagkráti
296
- - source: Παπάγου
297
- expected: Papágou
298
- - source: Πάρος
299
- expected: Páros
300
- - source: Πασαλιμάνι
301
- expected: Pasalimáni
302
- - source: Πατήσια
303
- expected: Patí̱sia
304
- - source: Πάτμος
305
- expected: Pátmos
306
- - source: Πάτρα
307
- expected: Pátra
308
- - source: Πειραιάς
309
- expected: Peiraiás
310
- - source: Πελοπόννησος
311
- expected: Pelopónni̱sos
312
- - source: Περιστέρι
313
- expected: Peristéri
314
- - source: Πεύκη
315
- expected: Péf̱ki̱
316
- - source: Πήλιο
317
- expected: Pí̱lio
318
- - source: Πολύγυρος
319
- expected: Polýgyros
320
- - source: Πόρος
321
- expected: Póros
322
- - source: Πρέβεζα
323
- expected: Préveza
324
- - source: Πτολεμαΐδα
325
- expected: Ptolemaḯda
326
- - source: Πύλος
327
- expected: Pýlos
328
- - source: Πύργος
329
- expected: Pýrgos
330
- - source: Ρέθυμνο
331
- expected: Réthymno
332
- - source: Ρόδος
333
- expected: Ródos
334
- - source: Ρούμελη
335
- expected: Roúmeli̱
336
- - source: Σαλαμίνα
337
- expected: Salamína
338
- - source: Σαμοθράκη
339
- expected: Samothráki̱
340
- - source: Σάμος
341
- expected: Sámos
342
- - source: Σαντορίνη
343
- expected: Santoríni̱
344
- - source: Σέρρες
345
- expected: Sérres
346
- - source: Σίκινος
347
- expected: Síkinos
348
- - source: Σίφνος
349
- expected: Sífnos
350
- - source: Σκιάθος
351
- expected: Skiáthos
352
- - source: Σκόπελος
353
- expected: Skópelos
354
- - source: Σούλι
355
- expected: Soúli
356
- - source: Σπάρτη
357
- expected: Spárti̱
358
- - source: Στερεά Ελλάδα
359
- expected: Stereá Elláda
360
- - source: Στύρα
361
- expected: Stýra
362
- - source: Σύμη
363
- expected: Sými̱
364
- - source: Σύρος
365
- expected: Sýros
366
- - source: Σφακιά
367
- expected: Sfakiá
368
- - source: Τήλος
369
- expected: Tí̱los
370
- - source: Τήνος
371
- expected: Tí̱nos
372
- - source: Τρίκαλα
373
- expected: Tríkala
374
- - source: Τρίπολη
375
- expected: Trípoli̱
376
- - source: Τσακωνιά
377
- expected: Tsako̱niá
378
- - source: Ύδρα
379
- expected: Ýdra
380
- - source: Φάληρο
381
- expected: Fáli̱ro
382
- - source: Φλώρινα
383
- expected: Fló̱rina
384
- - source: Φολέγανδρος
385
- expected: Folégandros
386
- - source: Χάλκη
387
- expected: Chálki̱
388
- - source: Χαλκίδα
389
- expected: Chalkída
390
- - source: Χαλάνδρι
391
- expected: Chalándri
392
- - source: Χαλκιδική
393
- expected: Chalkidikí̱
394
- - source: Χανιά
395
- expected: Chaniá
396
- - source: Χίος
397
- expected: Chíos
398
- - source: Ψαρά
399
- expected: Psará
400
- - source: Αβάνα
401
- expected: Avána
402
- - source: Αγγλία
403
- expected: Aṉglía
404
- - source: Αϊβαλί
405
- expected: Aïvalí
406
- - source: Αλεξάνδρεια
407
- expected: Alexándreia
408
- - source: Άμστερνταμ
409
- expected: Ámsterntam
410
- - source: Βαυαρία
411
- expected: Vav̱aría
412
- - source: Βενετία
413
- expected: Venetía
414
- - source: Βερολίνο
415
- expected: Verolíno
416
- - source: Βερόνα
417
- expected: Veróna
418
- - source: Βιέννη
419
- expected: Viénni̱
420
- - source: Γένοβα
421
- expected: Génova
422
- - source: Δουβλίνο
423
- expected: Douvlíno
424
- - source: Καλαβρία
425
- expected: Kalavría
426
- - source: Καλιφόρνια
427
- expected: Kalifórnia
428
- - source: Καύκασος
429
- expected: Káf̱kasos
430
- - source: Κονγκό
431
- expected: Kongkó
432
- - source: Κορσική
433
- expected: Korsikí̱
434
- - source: Κουρδιστάν
435
- expected: Kourdistán
436
- - source: Κωνσταντινούπολη
437
- expected: Ko̱nstantinoúpoli̱
438
- - source: Κατεχόμενη Κύπρος
439
- expected: Katechómeni̱ Kýpros
440
- - source: Λαπωνία
441
- expected: Lapo̱nía
442
- - source: Λευκωσία
443
- expected: Lef̱ko̱sía
444
- - source: Λιβόρνο
445
- expected: Livórno
446
- - source: Λονδίνο
447
- expected: Londíno
448
- - source: Λυών
449
- expected: Lyó̱n
450
- - source: Μάλαγα
451
- expected: Málaga
452
- - source: Μασσαλία
453
- expected: Massalía
454
- - source: Μικρονησία
455
- expected: Mikroni̱sía
456
- - source: Μιλάνο
457
- expected: Miláno
458
- - source: Μόσχα
459
- expected: Móscha
460
- - source: Μπολόνια
461
- expected: Bolónia
462
- - source: Νάπολη
463
- expected: Nápoli̱
464
- - source: Νταγκεστάν
465
- expected: Ntagkestán
466
- - source: Νέα Υόρκη
467
- expected: Néa Yórki̱
468
- - source: Οξφόρδη
469
- expected: Oxfórdi̱
470
- - source: Ουαλία
471
- expected: Oualía
472
- - source: Παρίσι
473
- expected: Parísi
474
- - source: Πάφος
475
- expected: Páfos
476
- - source: Πολυνησία
477
- expected: Polyni̱sía
478
- - source: Ρώμη
479
- expected: Ró̱mi̱
480
- - source: Σαμάρεια
481
- expected: Samáreia
482
- - source: Σικελία
483
- expected: Sikelía
484
- - source: Σκανδιναβία
485
- expected: Skandinavía
486
- - source: Σκόπια
487
- expected: Skópia
488
- - source: Σκωτία
489
- expected: Sko̱tía
490
- - source: Σμύρνη
491
- expected: Smýrni̱
492
- - source: Ταϊτή
493
- expected: Taïtí̱
494
- - source: Ταταρστάν
495
- expected: Tatarstán
496
- - source: Τζαμάικα
497
- expected: Tzamáika
498
- - source: Τηλλυρία
499
- expected: Ti̱llyría
500
- - source: Τιρόλο
501
- expected: Tirólo
502
- - source: Τορίνο
503
- expected: Toríno
504
- - source: Φανάρι
505
- expected: Fanári
506
- - source: Φλωρεντία
507
- expected: Flo̱rentía
508
- - source: Χαβάη
509
- expected: Chavái̱
510
- - source: Χονγκ Κονγκ
511
- expected: Chongk Kongk
512
-
513
- map:
514
- # https://en.wikipedia.org/wiki/Romanization_of_Greek
515
- rules:
516
- - pattern: (?<=[ΑαΕεΗη])\u03A5(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Υ (after Α, Ε, Η)
517
- result: F̱
518
- - pattern: (?<=[ΑαΕεΗη])\u03A5(?=\b) # Υ (after Α, Ε, Η)
519
- result: F̱
520
- - pattern: (?<=[ΑαΕεΗη])\u03C5(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # υ (after Α, Ε, Η)
521
- result: f̱
522
- - pattern: (?<=[ΑαΕεΗη])\u03C5(?=\b) # υ (after Α, Ε, Η)
523
- result: f̱
524
- - pattern: (?<=[ΑαΕεΗη])\u03A5(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Υ (after Α, Ε, Η)
525
- result: V̱
526
- - pattern: (?<=[ΑαΕεΗη])\u03C5(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # υ (after Α, Ε, Η)
527
- result: v̱
528
- - pattern: \u0391\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Αύ
529
- result: Áf̱
530
- - pattern: \u0391\u03CD(?=\b) # Αύ
531
- result: Áf̱
532
- - pattern: \u0391\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Αύ
533
- result: Áv̱
534
- - pattern: \u03B1\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Αύ
535
- result: áf̱
536
- - pattern: \u03B1\u03CD(?=\b) # Αύ
537
- result: áf̱
538
- - pattern: \u03B1\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Αύ
539
- result: áv̱
540
- - pattern: \u0395\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Εύ
541
- result: Éf̱
542
- - pattern: \u0395\u03CD(?=\b) # Εύ
543
- result: Éf̱
544
- - pattern: \u0395\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Εύ
545
- result: Év̱
546
- - pattern: \u03B5\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Εύ
547
- result: éf̱
548
- - pattern: \u03B5\u03CD(?=\b) # Εύ
549
- result: éf̱
550
- - pattern: \u03B5\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Εύ
551
- result: év̱
552
- - pattern: \u0397\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Εύ
553
- result: Í̱f̱
554
- - pattern: \u0397\u03CD(?=\b) # Εύ
555
- result: Í̱f̱
556
- - pattern: \u0397\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Εύ
557
- result: Í̱v̱
558
- - pattern: \u03B7\u03CD(?=[θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]) # Εύ
559
- result: í̱f̱
560
- - pattern: \u03B7\u03CD(?=\b) # Εύ
561
- result: í̱f̱
562
- - pattern: \u03B7\u03CD(?![θΘκΚξΞπΠσΣςτΤφΦχΧψΨ]|\b) # Εύ
563
- result: í̱v̱
564
- - pattern: (?<=[Οο])\u03A5 # Υ (after Ο)
565
- result: U
566
- - pattern: (?<=[Οο])\u03C5 # υ (after Ο)
567
- result: u
568
- - pattern: (?<=[Οο])\u03CD # ύ (after Ο)
569
- result: ú
570
- - pattern: (?<=[ΆάΈέΉήΌό])\u03A5 # Άυ, Έυ, Ήυ, Όυ
571
- result: Υ
572
- - pattern: (?<=[ΆάΈέΉήΌό])\u03C5 # Άυ, Έυ, Ήυ, Όυ
573
- result: y
574
- - pattern: \u0393(?=[ξΞχΧ]) # Γ (before Γ, Ξ, Χ)
575
- result: Ṉ
576
- - pattern: \u03B3(?=[ξΞχΧ]) # γ (before Γ, Ξ, Χ)
577
- result: ṉ
578
- - pattern: \u0393[Γγ] # Γ (before Γ)
579
- result: Ṉg
580
- - pattern: \u03B3\u03B3 # γ (before Γ)
581
- result: ṉg
582
- - pattern: \u0393[Κκ] # Γ (before Κ)
583
- result: Gk
584
- - pattern: \u03B3[Κκ] # γ (before Κ)
585
- result: gk
586
- - pattern: (?<=\b)\u039C[πΠ] # ΜΠ (initially)
587
- result: B
588
- - pattern: (?<=\b)\u03BC[πΠ] # μπ (initially)
589
- result: b
590
- - pattern: \u039C[πΠ](?=\b) # ΜΠ (finally)
591
- result: B
592
- - pattern: \u03BC[πΠ](?=\b) # μπ (finally)
593
- result: b
594
- - pattern: (?<!\b)\u039C[πΠ] # ΜΠ (medially)
595
- result: Mp
596
- - pattern: (?<!\b)\u03BC[πΠ] # μπ (medially)
597
- result: mp
598
- - pattern: \u037E # ;
599
- result: "?"
600
- - pattern: \u003B # ;
601
- result: "?"
602
-
603
- characters:
604
- "\u0027": ""
605
- "\u0386": "Á" # Ά
606
- "\u0391": "A" # Α
607
- "\u0392": "V" # Β
608
- "\u0393": "G" # Γ
609
- "\u0394": "D" # Δ
610
- "\u0395": "E" # Ε
611
- "\u0395\u03AA": "Εï" # ΕΪ
612
- "\u0395\u03CA": "Εï" # Εϊ
613
- "\u0388\u03CA": "Éï" # Έϊ
614
- "\u0388\u03CA": "Éï" # Έι
615
- "\u0396": "Z" # Ζ
616
- "\u0397": "I̱" # Η
617
- "\u0398": "Th" # Θ
618
- "\u0399": "I" # Ι
619
- "\u039A": "K" # Κ
620
- "\u039B": "L" # Λ
621
- "\u039C": "M" # Μ
622
- "\u039D": "N" # Ν
623
- "\u039E": "X" # Ξ
624
- "\u039F": "O" # Ο
625
- "\u03A0": "P" # Π
626
- "\u03A1": "R" # Ρ
627
- "\u03A3": "S" # Σ
628
- "\u03A4": "T" # Τ
629
- "\u03A5": "Y" # Υ
630
- "\u03A6": "F" # Φ
631
- "\u03A7": "Ch" # Χ
632
- "\u03A8": "Ps" # Ψ
633
- "\u03A9": "O̱" # Ω
634
- "\u0388": "É" # Έ
635
- "\u0389": "Í̱" # Ή
636
- "\u038A": "Í" # Ί
637
- "\u038C": "Ó" # Ό
638
- "\u038E": "Ý" # Ύ
639
- "\u038F": "Ó̱" # Ώ
640
- "\u03AA": "Ï" # Ϊ
641
- "\u03AB": "Ÿ" # Ϋ
642
-
643
- "\u03AC": "á" # ά
644
- "\u03B1": "a" # α
645
- "\u03B2": "v" # β
646
- "\u03B3": "g" # γ
647
- "\u03B4": "d" # δ
648
- "\u03B5": "e" # ε
649
- "\u03B5\u03CA": "eï" # εϊ
650
- "\u03AD\u03CA": "éï" # έϊ
651
- "\u03AD\u03B9": "éï" # έι
652
- "\u03B6": "z" # ζ
653
- "\u03B7": "i̱" # η
654
- "\u03B8": "th" # θ
655
- "\u03B9": "i" # ι
656
- "\u03BA": "k" # κ
657
- "\u03BB": "l" # λ
658
- "\u03BC": "m" # μ
659
- "\u03BD": "n" # ν
660
- "\u03BE": "x" # ξ
661
- "\u03BF": "o" # ο
662
- "\u03C0": "p" # π
663
- "\u03C1": "r" # ρ
664
- "\u03C3": "s" # σ
665
- "\u03C2": "s" # ς
666
- "\u03C4": "t" # τ
667
- "\u03C5": "y" # υ
668
- "\u03C6": "f" # φ
669
- "\u03C7": "ch" # χ
670
- "\u03C8": "ps" # ψ
671
- "\u03C9": "o̱" # ω
672
- "\u03AD": "é" # έ
673
- "\u03AE": "í̱" # ή
674
- "\u03AF": "í" # ί
675
- "\u03CC": "ó" # ό
676
- "\u03CD": "ý" # ύ
677
- "\u03CE": "ó̱" # ώ
678
- "\u03CA": "ï" # ϊ
679
- "\u03CB": "ÿ" # ϋ
680
- "\u0390": "ḯ" # ΐ
681
- "\u03B0": "ÿ́" # ΰ
682
-
683
- "\u0387": ";" # ·
684
- "\u00B7": ";" # ·