interscript 0.1.9 → 2.0.5

Sign up to get free protection for your applications and to get access to all the features.
Files changed (352) 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 +53 -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 +80 -135
  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 +67 -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 +26 -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 +61 -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 +65 -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/requirements.txt +1 -0
  63. metadata +73 -458
  64. data/README.adoc +0 -296
  65. data/aliases.json +0 -1
  66. data/lib/g2pwrapper.py +0 -34
  67. data/lib/interscript/fs.rb +0 -96
  68. data/lib/interscript/mapping.rb +0 -144
  69. data/lib/interscript/opal.rb +0 -196
  70. data/lib/interscript/opal/entrypoint.rb +0 -20
  71. data/lib/interscript/opal/exports.rb +0 -11
  72. data/lib/interscript/opal/maps.js.erb +0 -8
  73. data/lib/model-7 +0 -0
  74. data/lib/tha-pt-b-7 +0 -0
  75. data/maps/acadsin-zho-Hani-Latn-2002.yaml +0 -38916
  76. data/maps/alalc-amh-Ethi-Latn-1997.yaml +0 -513
  77. data/maps/alalc-amh-Ethi-Latn-2011.yaml +0 -138
  78. data/maps/alalc-ara-Arab-Latn-1997.yaml +0 -1287
  79. data/maps/alalc-asm-Deva-Latn-1997.yaml +0 -259
  80. data/maps/alalc-asm-Deva-Latn-2012.yaml +0 -55
  81. data/maps/alalc-aze-Arab-Latn-1997.yaml +0 -376
  82. data/maps/alalc-aze-Cyrl-Latn-1997.yaml +0 -145
  83. data/maps/alalc-bel-Cyrl-Latn-1997.yaml +0 -129
  84. data/maps/alalc-ben-Beng-Latn-1997.yaml +0 -291
  85. data/maps/alalc-ben-Beng-Latn-2017.yaml +0 -130
  86. data/maps/alalc-bul-Cyrl-Latn-1997.yaml +0 -98
  87. data/maps/alalc-div-Thaa-Latn-1997.yaml +0 -211
  88. data/maps/alalc-ell-Grek-Latn-1997.yaml +0 -628
  89. data/maps/alalc-ell-Grek-Latn-2010.yaml +0 -626
  90. data/maps/alalc-guj-Gujr-Latn-1997.yaml +0 -266
  91. data/maps/alalc-guj-Gujr-Latn-2011.yaml +0 -64
  92. data/maps/alalc-hin-Deva-Latn-1997.yaml +0 -303
  93. data/maps/alalc-hin-Deva-Latn-2011.yaml +0 -65
  94. data/maps/alalc-kan-Kana-Latn-1997.yaml +0 -274
  95. data/maps/alalc-kan-Kana-Latn-2011.yaml +0 -63
  96. data/maps/alalc-kat-Geok-Latn-1997.yaml +0 -111
  97. data/maps/alalc-kat-Geor-Latn-1997.yaml +0 -150
  98. data/maps/alalc-kor-Hang-Latn-1997.yaml +0 -98
  99. data/maps/alalc-mal-Mlym-Latn-1997.yaml +0 -303
  100. data/maps/alalc-mal-Mlym-Latn-2012.yaml +0 -73
  101. data/maps/alalc-mar-Deva-Latn-1997.yaml +0 -189
  102. data/maps/alalc-mar-Deva-Latn-2011.yaml +0 -45
  103. data/maps/alalc-mkd-Cyrl-Latn-1997.yaml +0 -114
  104. data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +0 -103
  105. data/maps/alalc-mon-Cyrl-Latn-1997.yaml +0 -220
  106. data/maps/alalc-ori-Orya-Latn-1997.yaml +0 -284
  107. data/maps/alalc-ori-Orya-Latn-2011.yaml +0 -67
  108. data/maps/alalc-pan-Guru-Latn-1997.yaml +0 -256
  109. data/maps/alalc-pan-Guru-Latn-2011.yaml +0 -78
  110. data/maps/alalc-per-Arab-Latn-1997.yaml +0 -375
  111. data/maps/alalc-pli-Deva-Latn-2012.yaml +0 -144
  112. data/maps/alalc-pra-Deva-Latn-2012.yaml +0 -47
  113. data/maps/alalc-rus-Cyrl-Latn-1997.yaml +0 -225
  114. data/maps/alalc-rus-Cyrl-Latn-2012.yaml +0 -162
  115. data/maps/alalc-san-Deva-Latn-2012.yaml +0 -241
  116. data/maps/alalc-sin-Sinh-Latn-1997.yaml +0 -292
  117. data/maps/alalc-sin-Sinh-Latn-2011.yaml +0 -71
  118. data/maps/alalc-srp-Cyrl-Latn-1997.yaml +0 -118
  119. data/maps/alalc-srp-Cyrl-Latn-2013.yaml +0 -135
  120. data/maps/alalc-tam-Taml-Latn-1997.yaml +0 -62
  121. data/maps/alalc-tam-Taml-Latn-2011.yaml +0 -58
  122. data/maps/alalc-tel-Telu-Latn-1997.yaml +0 -284
  123. data/maps/alalc-tel-Telu-Latn-2011.yaml +0 -64
  124. data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +0 -145
  125. data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +0 -16
  126. data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +0 -283
  127. data/maps/az-aze-Cyrl-Latn-1939.yaml +0 -105
  128. data/maps/az-aze-Cyrl-Latn-1958.yaml +0 -45
  129. data/maps/bas-rus-Cyrl-Latn-2017-bss.yaml +0 -174
  130. data/maps/bas-rus-Cyrl-Latn-2017-oss.yaml +0 -169
  131. data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +0 -292
  132. data/maps/bgn-kor-Hang-Latn-1943.yaml +0 -35
  133. data/maps/bgn-kor-Kore-Latn-1943.yaml +0 -31
  134. data/maps/bgna-bul-Cyrl-Latn-2006.yaml +0 -208
  135. data/maps/bgna-bul-Cyrl-Latn-2009.yaml +0 -208
  136. data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +0 -532
  137. data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +0 -598
  138. data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +0 -108
  139. data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +0 -111
  140. data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +0 -188
  141. data/maps/bgnpcgn-bal-Arab-Latn-2008.yaml +0 -329
  142. data/maps/bgnpcgn-bel-Cyrl-Latn-1979.yaml +0 -289
  143. data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +0 -119
  144. data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +0 -42
  145. data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml +0 -184
  146. data/maps/bgnpcgn-div-Thaa-Latn-1988.yaml +0 -75
  147. data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +0 -705
  148. data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +0 -23
  149. data/maps/bgnpcgn-far-Latn-Latn-1964.yaml +0 -28
  150. data/maps/bgnpcgn-fas-Arab-Latn-1956.yaml +0 -96
  151. data/maps/bgnpcgn-isl-Latn-Latn-1964.yaml +0 -37
  152. data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +0 -257
  153. data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +0 -131
  154. data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +0 -42
  155. data/maps/bgnpcgn-kaz-Cyrl-Latn-1979.yaml +0 -247
  156. data/maps/bgnpcgn-kir-Cyrl-Latn-1979.yaml +0 -218
  157. data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +0 -253
  158. data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +0 -48
  159. data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +0 -48
  160. data/maps/bgnpcgn-kur-Arab-Latn-2007.yaml +0 -249
  161. data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +0 -163
  162. data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +0 -190
  163. data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml +0 -223
  164. data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +0 -230
  165. data/maps/bgnpcgn-per-Arab-Latn-1958.yaml +0 -338
  166. data/maps/bgnpcgn-prs-Arab-Latn-2007.yaml +0 -673
  167. data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.yaml +0 -459
  168. data/maps/bgnpcgn-pus-Arab-Latn-1968.yaml +0 -377
  169. data/maps/bgnpcgn-rue-Cyrl-Latn-2016.yaml +0 -168
  170. data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +0 -318
  171. data/maps/bgnpcgn-srp-Cyrl-Latn-1962.yaml +0 -73
  172. data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +0 -170
  173. data/maps/bgnpcgn-tat-Cyrl-Latn-2007.yaml +0 -220
  174. data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.yaml +0 -240
  175. data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +0 -166
  176. data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +0 -119
  177. data/maps/bgnpcgn-urd-Arab-Latn-2007.yaml +0 -459
  178. data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.yaml +0 -127
  179. data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.yaml +0 -82
  180. data/maps/bgnpcgn-zho-Hans-Latn-1979.yaml +0 -7456
  181. data/maps/bis-asm-Beng-Latn-13194-1991.yaml +0 -159
  182. data/maps/bis-ben-Beng-Latn-13194-1991.yaml +0 -156
  183. data/maps/bis-dev-Deva-Latn-13194-1991.yaml +0 -184
  184. data/maps/bis-guj-Gujr-Latn-13194-1991.yaml +0 -181
  185. data/maps/bis-kan-Kana-Latn-13194-1991.yaml +0 -173
  186. data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +0 -176
  187. data/maps/bis-ori-Orya-Latn-13194-1991.yaml +0 -175
  188. data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +0 -175
  189. data/maps/bis-tel-Telu-Latn-13194-1991.yaml +0 -170
  190. data/maps/bis-tml-Taml-Latn-13194-1991.yaml +0 -155
  191. data/maps/by-bel-Cyrl-Latn-1998.yaml +0 -172
  192. data/maps/by-bel-Cyrl-Latn-2007.yaml +0 -115
  193. data/maps/din-grc-Grek-Latn-31634-2011-t1.yaml +0 -899
  194. data/maps/din-hin-Deva-Latn-33904-2018.yaml +0 -100
  195. data/maps/din-kat-Geor-Latn-32707-2010.yaml +0 -145
  196. data/maps/din-mar-Deva-Latn-33904-2018.yaml +0 -84
  197. data/maps/din-nep-Deva-Latn-33904-2018.yaml +0 -119
  198. data/maps/din-pli-Deva-Latn-33904-2018.yaml +0 -75
  199. data/maps/din-pra-Deva-Latn-33904-2018.yaml +0 -63
  200. data/maps/din-san-Deva-Latn-33904-2018.yaml +0 -338
  201. data/maps/din-tam-Taml-Latn-33903-2016.yaml +0 -213
  202. data/maps/dos-nep-Deva-Latn-1997.yaml +0 -47
  203. data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +0 -684
  204. data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +0 -680
  205. data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +0 -19
  206. data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +0 -31
  207. data/maps/ggg-kat-Geor-Latn-2002.yaml +0 -92
  208. data/maps/gki-bel-Cyrl-Latn-1992.yaml +0 -33
  209. data/maps/gki-bel-Cyrl-Latn-2000.yaml +0 -201
  210. data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml +0 -190
  211. data/maps/gost-rus-Cyrl-Latn-7.79-2000-2002.yaml +0 -157
  212. data/maps/hk-yue-Hani-Latn-1888.yaml +0 -38497
  213. data/maps/icao-bel-Cyrl-Latn-9303.yaml +0 -136
  214. data/maps/icao-bul-Cyrl-Latn-9303.yaml +0 -118
  215. data/maps/icao-fas-Arab-Latn-9303.yaml +0 -103
  216. data/maps/icao-heb-Hebr-Latn-9303.yaml +0 -151
  217. data/maps/icao-mkd-Cyrl-Latn-9303.yaml +0 -117
  218. data/maps/icao-rus-Cyrl-Latn-9303.yaml +0 -117
  219. data/maps/icao-srp-Cyrl-Latn-9303.yaml +0 -117
  220. data/maps/icao-ukr-Cyrl-Latn-9303.yaml +0 -119
  221. data/maps/iso-ara-Arab-Latn-233-1984.yaml +0 -323
  222. data/maps/iso-asm-Beng-Latn-15919-2001.yaml +0 -75
  223. data/maps/iso-ben-Beng-Latn-15919-2001.yaml +0 -175
  224. data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +0 -613
  225. data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +0 -44
  226. data/maps/iso-guj-Gujr-Latn-15919-2001.yaml +0 -220
  227. data/maps/iso-hin-Deva-Latn-15919-2001.yaml +0 -87
  228. data/maps/iso-inc-Deva-Latn-15919-2001.yaml +0 -61
  229. data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +0 -66
  230. data/maps/iso-kan-Kana-Latn-15919-2001.yaml +0 -220
  231. data/maps/iso-kat-Geor-Latn-9984-1996.yaml +0 -145
  232. data/maps/iso-kor-Hang-Latn-1996-method1.yaml +0 -240
  233. data/maps/iso-kor-Hang-Latn-1996-method2.yaml +0 -226
  234. data/maps/iso-mal-Mlym-Latn-15919-2001.yaml +0 -281
  235. data/maps/iso-mar-Deva-Latn-15919-2001.yaml +0 -75
  236. data/maps/iso-nep-Deva-Latn-15919-2001.yaml +0 -87
  237. data/maps/iso-ori-Orya-Latn-15919-2001.yaml +0 -193
  238. data/maps/iso-pan-Guru-Latn-15919-2001.yaml +0 -222
  239. data/maps/iso-pli-Beng-Latn-15919-2001.yaml +0 -73
  240. data/maps/iso-pli-Deva-Latn-15919-2001.yaml +0 -74
  241. data/maps/iso-pli-Sinh-Latn-15919-2001.yaml +0 -219
  242. data/maps/iso-pli-Thai-Latn-15919-2001.yaml +0 -55
  243. data/maps/iso-pra-Deva-Latn-15919-2001.yaml +0 -59
  244. data/maps/iso-prs-Arab-Latn-233-3-1999.yaml +0 -366
  245. data/maps/iso-rus-Cyrl-Latn-9-1995.yaml +0 -271
  246. data/maps/iso-san-Deva-Latn-15919-2001.yaml +0 -220
  247. data/maps/iso-tam-Taml-Latn-15919-2001.yaml +0 -159
  248. data/maps/iso-tel-Telu-Latn-15919-2001.yaml +0 -220
  249. data/maps/iso-tha-Thai-Latn-11940-1998.yaml +0 -109
  250. data/maps/kp-kor-Hang-Latn-2002.yaml +0 -909
  251. data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +0 -44820
  252. data/maps/masm-mon-Cyrl-Latn-5217-2012.yaml +0 -163
  253. data/maps/masm-mon-Latn-Cyrl-5217-2012.yaml +0 -200
  254. data/maps/mext-jpn-Hrkt-Latn-1954.yaml +0 -411
  255. data/maps/moct-kor-Hang-Latn-2000.yaml +0 -807
  256. data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +0 -541
  257. data/maps/mv-div-Thaa-Latn-1987.yaml +0 -200
  258. data/maps/mvd-bel-Cyrl-Latn-2008.yaml +0 -225
  259. data/maps/mvd-bel-Cyrl-Latn-2010.yaml +0 -63
  260. data/maps/mvd-rus-Cyrl-Latn-2008.yaml +0 -109
  261. data/maps/mvd-rus-Cyrl-Latn-2010.yaml +0 -37
  262. data/maps/odni-ara-Arab-Latn-2004.yaml +0 -137
  263. data/maps/odni-ara-Arab-Latn-2015.yaml +0 -315
  264. data/maps/odni-aze-Cyrl-Latn-2015.yaml +0 -144
  265. data/maps/odni-bel-Cyrl-Latn-2015.yaml +0 -148
  266. data/maps/odni-bul-Cyrl-Latn-2005.yaml +0 -90
  267. data/maps/odni-bul-Cyrl-Latn-2015.yaml +0 -96
  268. data/maps/odni-che-Cyrl-Latn-2015.yaml +0 -169
  269. data/maps/odni-fas-Arab-Latn-2004.yaml +0 -276
  270. data/maps/odni-fas-Arab-Latn-2015.yaml +0 -406
  271. data/maps/odni-hin-Deva-Latn-2004.yaml +0 -182
  272. data/maps/odni-hin-Deva-Latn-2015.yaml +0 -258
  273. data/maps/odni-kat-Geor-Latn-2015.yaml +0 -87
  274. data/maps/odni-kaz-Cyrl-Latn-2015.yaml +0 -148
  275. data/maps/odni-kir-Cyrl-Latn-2015.yaml +0 -136
  276. data/maps/odni-kor-Hang-Latn-2015.yaml +0 -375
  277. data/maps/odni-mkd-Cyrl-Latn-2005.yaml +0 -21
  278. data/maps/odni-mkd-Cyrl-Latn-2015.yaml +0 -122
  279. data/maps/odni-prs-Arab-Latn-2004.yaml +0 -123
  280. data/maps/odni-prs-Arab-Latn-2015.yaml +0 -228
  281. data/maps/odni-rus-Cyrl-Latn-2015.yaml +0 -77
  282. data/maps/odni-srp-Cyrl-Latn-2005.yaml +0 -36
  283. data/maps/odni-srp-Cyrl-Latn-2015.yaml +0 -129
  284. data/maps/odni-tat-Cyrl-Latn-2015.yaml +0 -142
  285. data/maps/odni-tgk-Cyrl-Latn-2015.yaml +0 -148
  286. data/maps/odni-tuk-Cyrl-Latn-2015.yaml +0 -170
  287. data/maps/odni-uig-Cyrl-Latn-2015.yaml +0 -138
  288. data/maps/odni-ukr-Cyrl-Latn-2015.yaml +0 -161
  289. data/maps/odni-urd-Arab-Latn-2015.yaml +0 -221
  290. data/maps/odni-uzb-Cyrl-Latn-2015.yaml +0 -166
  291. data/maps/royin-tha-Thai-Latn-1939-generic.yaml +0 -90
  292. data/maps/royin-tha-Thai-Latn-1968.yaml +0 -183
  293. data/maps/royin-tha-Thai-Latn-1999-chained.yaml +0 -180
  294. data/maps/royin-tha-Thai-Latn-1999.yaml +0 -80
  295. data/maps/sac-zho-Hans-Latn-1979.yaml +0 -24763
  296. data/maps/sasm-mon-Mong-Latn-general-1978.yaml +0 -389
  297. data/maps/sasm-mon-Mong-Latn-phonetic-1978.yaml +0 -354
  298. data/maps/ses-ara-Arab-Latn-1930.yaml +0 -283
  299. data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +0 -222
  300. data/maps/ua-ukr-Cyrl-Latn-1996.yaml +0 -197
  301. data/maps/ua-ukr-Cyrl-Latn-2007.yaml +0 -75
  302. data/maps/ua-ukr-Cyrl-Latn-2010.yaml +0 -192
  303. data/maps/un-amh-Ethi-Latn-2016.yaml +0 -602
  304. data/maps/un-ara-Arab-Latn-1971.yaml +0 -139
  305. data/maps/un-ara-Arab-Latn-1972.yaml +0 -159
  306. data/maps/un-ara-Arab-Latn-2017.yaml +0 -420
  307. data/maps/un-asm-Beng-Latn-1972.yaml +0 -223
  308. data/maps/un-bel-Cyrl-Latn-2007.yaml +0 -114
  309. data/maps/un-ben-Beng-Latn-2016.yaml +0 -534
  310. data/maps/un-ell-Grek-Latn-1987-phonetic.yaml +0 -780
  311. data/maps/un-ell-Grek-Latn-1987-tl.yaml +0 -31
  312. data/maps/un-ell-Grek-Latn-1987-ts.yaml +0 -19
  313. data/maps/un-guj-Gujr-Latn-1972.yaml +0 -229
  314. data/maps/un-hin-Deva-Latn-2016.yaml +0 -316
  315. data/maps/un-kan-Kana-Latn-2016.yaml +0 -254
  316. data/maps/un-mal-Mlym-Latn-1972.yaml +0 -251
  317. data/maps/un-mar-Deva-Latn-2016.yaml +0 -102
  318. data/maps/un-mon-Mong-Latn-general-2013.yaml +0 -264
  319. data/maps/un-mon-Mong-Latn-phonetic-2013.yaml +0 -264
  320. data/maps/un-nep-Deva-Latn-1972.yaml +0 -269
  321. data/maps/un-nep-Deva-Latn-2013.yaml +0 -74
  322. data/maps/un-ori-Orya-Latn-1972.yaml +0 -247
  323. data/maps/un-pan-Guru-Latn-1972.yaml +0 -402
  324. data/maps/un-prs-Arab-Latn-1967.yaml +0 -236
  325. data/maps/un-rus-Cyrl-Latn-1987.yaml +0 -166
  326. data/maps/un-tam-Taml-Latn-1972.yaml +0 -194
  327. data/maps/un-tel-Telu-Latn-1972.yaml +0 -270
  328. data/maps/un-ukr-Cyrl-Latn-1998.yaml +0 -53
  329. data/maps/un-ukr-Cyrl-Latn-2012.yaml +0 -162
  330. data/maps/un-urd-Arab-Latn-1972.yaml +0 -405
  331. data/maps/var-amh-Ethi-Latn-eae-2003.yaml +0 -466
  332. data/maps/var-gez-Ethi-Latn-eae-2003.yaml +0 -76
  333. data/maps/var-hin-Deva-Latn-hunterian-1872.yaml +0 -221
  334. data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +0 -406
  335. data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +0 -386
  336. data/maps/var-kor-Hang-Hang-jamo.yaml +0 -11193
  337. data/maps/var-kor-Hang-Latn-mr-1939.yaml +0 -1054
  338. data/maps/var-kor-Kore-Hang-2013.yaml +0 -59754
  339. data/maps/var-kor-Kore-Latn-mr-1939.yaml +0 -36
  340. data/maps/var-mar-Deva-Latn-hunterian-1872.yaml +0 -43
  341. data/maps/var-mon-Mong-Latn-1930.yaml +0 -102
  342. data/maps/var-mon-Mong-Latn-lessing.yaml +0 -272
  343. data/maps/var-mon-Mong-Latn-vpmc.yaml +0 -274
  344. data/maps/var-pra-Deva-Latn-iast-1912.yaml +0 -30
  345. data/maps/var-san-Deva-Latn-iast-1912.yaml +0 -149
  346. data/maps/var-tha-Thai-Thai-phonemic.yaml +0 -59
  347. data/maps/var-tha-Thai-Zsym-ipa.yaml +0 -301
  348. data/maps/var-zho-Hani-Latn-wd-1979.yaml +0 -38912
  349. data/spec/interscript/filenames_spec.rb +0 -21
  350. data/spec/interscript/mapping_spec.rb +0 -42
  351. data/spec/interscript_spec.rb +0 -37
  352. data/spec/spec_helper.rb +0 -3
data/bin/setup ADDED
@@ -0,0 +1,8 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+ set -vx
5
+
6
+ bundle install
7
+
8
+ # Do any other automated setup that you need to do here
data/exe/interscript ADDED
@@ -0,0 +1,6 @@
1
+ require 'interscript/command'
2
+
3
+ if ARGV.any? && !Interscript::Command.all_tasks.key?(ARGV.first)
4
+ ARGV.unshift :translit
5
+ end
6
+ Interscript::Command.start ARGV
@@ -0,0 +1,31 @@
1
+ require_relative 'lib/interscript/version'
2
+
3
+ Gem::Specification.new do |spec|
4
+ spec.name = "interscript"
5
+ spec.version = Interscript::VERSION
6
+ spec.summary = %q{Interoperable script conversion systems}
7
+ spec.description = %q{Interoperable script conversion systems}
8
+ spec.authors = ["Ribose Inc."]
9
+ spec.email = ["open.source@ribose.com"]
10
+
11
+ spec.date = %q{2019-11-17}
12
+ spec.homepage = "https://www.interscript.com"
13
+ spec.license = "BSD-2-Clause"
14
+
15
+ spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
16
+
17
+ spec.metadata["homepage_uri"] = spec.homepage
18
+ spec.metadata["source_code_uri"] = "https://github.com/interscript/interscript"
19
+
20
+ # Specify which files should be added to the gem when it is released.
21
+ # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
22
+ spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
23
+ `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
24
+ end
25
+ spec.bindir = "exe"
26
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
27
+ spec.require_paths = ["lib"]
28
+
29
+ spec.add_dependency "thor"
30
+ spec.add_dependency "interscript-maps"
31
+ end
data/lib/interscript.rb CHANGED
@@ -1,166 +1,111 @@
1
- # frozen_string_literal: true
1
+ require "interscript/version"
2
+ require "yaml"
2
3
 
3
- require "interscript/mapping"
4
-
5
- # Transliteration
6
4
  module Interscript
7
-
8
- class InvalidSystemError < StandardError; end
9
- class ExternalProcessNotRecognizedError < StandardError; end
10
- class ExternalProcessUnavailableError < StandardError; end
11
-
12
- if RUBY_ENGINE == 'opal'
13
- require "interscript/opal"
14
- extend Opal
15
- else
16
- require "interscript/fs"
17
- extend Fs
18
- end
5
+ class MapNotFoundError < StandardError; end
19
6
 
20
7
  class << self
8
+ def load_path
9
+ @load_path ||= ['.', *Interscript.map_locations]
10
+ end
21
11
 
22
- def transliterate(system_code, string, maps={})
23
- system_code = map_resolve(system_code)
24
-
25
- unless maps.has_key? system_code
26
- maps[system_code] = Interscript::Mapping.for(system_code)
27
- end
28
- # mapping = Interscript::Mapping.for(system_code)
29
- mapping = maps[system_code]
12
+ def locate map_name
13
+ map_name = map_aliases[map_name] if map_aliases.include? map_name
30
14
 
31
- # First, apply chained transliteration as specified in the list `chain`
32
- chain = mapping.chain.dup
33
- while chain.length > 0
34
- string = transliterate(chain.shift, string, maps)
15
+ load_path.each do |i|
16
+ # iml is an extension for a library, imp for a map
17
+ ["iml", "imp"].each do |ext|
18
+ f = File.expand_path("#{map_name}.#{ext}", i)
19
+ return f if File.exist?(f)
20
+ end
35
21
  end
22
+ raise MapNotFoundError, "Couldn't locate #{map_name}"
23
+ end
36
24
 
37
- # Then, apply the rest of the map
38
- separator = mapping.character_separator || ""
39
- word_separator = mapping.word_separator || ""
40
- title_case = mapping.title_case
41
- downcase = mapping.downcase
42
-
43
- charmap = mapping.characters_hash
44
- dictmap = mapping.dictionary_hash
45
- trie = mapping.dictionary_trie
46
-
47
- string = external_processing(mapping, string)
25
+ def parse(map_name)
26
+ Interscript::DSL.parse(map_name)
27
+ end
48
28
 
49
- pos = 0
50
- while pos < string.to_s.size
51
- m = 0
52
- wordmatch = ""
29
+ def load(system_code, maps={}, compiler: Interscript::Interpreter)
30
+ maps[[system_code, compiler.name]] ||= compiler.(system_code)
31
+ end
53
32
 
54
- # Using Trie, find the longest matching substring
55
- while (pos + m < string.to_s.size) && (trie.partial_word?string[pos..pos+m])
56
- wordmatch = string[pos..pos+m] if trie.word?string[pos..pos+m]
57
- m += 1
58
- end
33
+ # Transliterates the string.
34
+ def transliterate(system_code, string, maps={}, compiler: Interscript::Interpreter)
35
+ # The current best implementation is Interpreter
36
+ load(system_code, maps, compiler: compiler).(string)
37
+ end
59
38
 
60
- m = wordmatch.length
61
- if m > 0
62
- repl = dictmap[string[pos..pos+m-1]]
63
- string = sub_replace(string, pos, m, repl)
64
- pos += repl.length
65
- else
66
- pos += 1
67
- end
68
- end
39
+ # Gives each possible value of the transliteration.
40
+ def transliterate_each(system_code, string, maps={}, &block)
41
+ load(system_code, maps).(string, each: true, &block)
42
+ end
69
43
 
70
- output = string.clone
71
- offsets = Array.new string.to_s.size, 1
72
-
73
- # mapping.rules.each do |r|
74
- # string.to_s.scan(/#{r['pattern']}/) do |matches|
75
- # match = Regexp.last_match
76
- # pos = match.offset(0).first
77
- # result = r['result'].clone
78
- # matches.each.with_index { |v, i| result.sub!(/\\#{i + 1}/, v) } if matches.is_a? Array
79
- # result.upcase! if up_case_around?(string, pos)
80
- # output[offsets[0...pos].sum, match[0].size] = result
81
- # offsets[pos] += result.size - match[0].size
82
- # end
83
- # end
84
-
85
- mapping.rules.each do |r|
86
- next unless output
87
- re = mkregexp(r["pattern"])
88
- output = output.gsub(re, r["result"])
89
- end
44
+ def transliterate_file(system_code, input_file, output_file, maps={})
45
+ input = File.read(input_file)
46
+ output = transliterate(system_code, input, maps)
90
47
 
91
- charmap.each do |k, v|
92
- re = mkregexp(k)
93
- while (match = output&.match(re))
94
- pos = match.offset(0).first
95
- result = !downcase && up_case_around?(output, pos) ? v.upcase : v
96
-
97
- # if more than one, choose the first one
98
- result = result[0] if result.is_a?(Array)
99
-
100
- output = sub_replace(
101
- output,
102
- pos,
103
- match[0].size,
104
- add_separator(separator, pos, result)
105
- )
106
- end
48
+ File.open(output_file, 'w') do |f|
49
+ f.puts(output)
107
50
  end
108
51
 
109
- mapping.postrules.each do |r|
110
- next unless output
111
- re = mkregexp(r["pattern"])
112
- output = if r["result"] == "upcase"
113
- output.gsub(re, &:upcase)
114
- else
115
- output.gsub(re, r["result"])
116
- end
117
- end
52
+ puts "Output written to: #{output_file}"
53
+ output_file
54
+ end
118
55
 
119
- return unless output
56
+ def map_gems
57
+ @map_gems ||= Gem.find_latest_files('interscript-maps.yaml').map do |i|
58
+ [i, YAML.load_file(i)]
59
+ end.to_h
60
+ end
120
61
 
121
- re = mkregexp('^(.)')
122
- output = output.gsub(re, &:upcase) if title_case
123
- if word_separator != ''
124
- re = mkregexp("#{word_separator}#{separator}")
125
- output = output.gsub(re, word_separator)
62
+ def map_locations
63
+ @map_locations ||= map_gems.map do |i,v|
64
+ paths = v["paths"].dup
65
+ paths += v["staging"] if ENV["INTERSCRIPT_STAGING"] && v["staging"]
126
66
 
127
- if title_case
128
- re = mkregexp("#{word_separator}(.)")
129
- output = output.gsub(re, &:upcase)
67
+ paths.map do |j|
68
+ File.expand_path(j, File.dirname(i))
130
69
  end
131
- end
132
-
133
- output.unicode_normalize
70
+ end.flatten
134
71
  end
135
72
 
136
- def map_resolve(map)
137
- map = aliases[map] if aliases.key? map
138
- raise ArgumentError, "Map #{map} doesn't exist" unless map_exist? map
139
- map
73
+ def secryst_index_locations
74
+ @secryst_index_locations ||= map_gems.map do |i,v|
75
+ v["secryst-models"]
76
+ end.compact.flatten
140
77
  end
141
78
 
142
- private
79
+ def map_aliases
80
+ return @map_aliases if @map_aliases
143
81
 
144
- def add_separator(separator, pos, result)
145
- pos == 0 ? result : separator + result
82
+ @map_aliases = {}
83
+ map_gems.each do |i,v|
84
+ (v["aliases"] || {}).each do |code, value|
85
+ value.each do |al, map|
86
+ @map_aliases[al] = map["alias_to"]
87
+ end
88
+ end
89
+ end
90
+ @map_aliases
146
91
  end
147
92
 
148
- def up_case_around?(string, pos)
149
- return false if string[pos] == string[pos].downcase
150
-
151
- i = pos - 1
152
- i -= 1 while i.positive? && string[i] !~ mkregexp('[[:alpha:]]')
153
- before = i >= 0 && i < pos ? string[i].to_s.strip : ''
93
+ # List all possible maps to use
94
+ def maps(basename: true, load_path: false, select: "*", libraries: false)
95
+ paths = load_path ? Interscript.load_path : Interscript.map_locations
96
+ ext = libraries ? "iml" : "imp"
154
97
 
155
- i = pos + 1
156
- i += 1 while i < string.size - 1 && string[i] !~ mkregexp('[[:alpha:]]')
157
- after = i > pos ? string[i].to_s.strip : ''
98
+ imps = paths.map { |i| Dir["#{i}/#{select}.#{ext}"] }.flatten
158
99
 
159
- before_uc = !before.empty? && before == before.upcase
160
- after_uc = !after.empty? && after == after.upcase
161
- # before_uc && (after.empty? || after_uc) || after_uc && (before.empty? || before_uc)
162
- before_uc || after_uc
100
+ basename ? imps.map { |j| File.basename(j, ".#{ext}") } : imps
163
101
  end
164
-
165
102
  end
166
103
  end
104
+
105
+ require 'interscript/stdlib'
106
+
107
+ require "interscript/compiler"
108
+ require "interscript/interpreter"
109
+
110
+ require 'interscript/dsl'
111
+ require 'interscript/node'
@@ -7,11 +7,12 @@ module Interscript
7
7
  desc '<file>', 'Transliterate text'
8
8
  option :system, aliases: '-s', required: true, desc: 'Transliteration system'
9
9
  option :output, aliases: '-o', required: false, desc: 'Output file'
10
- option :map, aliases: '-m', required: false, default: "{}", desc: 'Transliteration mapping json'
10
+ # Was this option really well thought out? The last parameter is a cache, isn't it?
11
+ #option :map, aliases: '-m', required: false, default: "{}", desc: 'Transliteration mapping json'
11
12
 
12
13
  def translit(input)
13
14
  if options[:output]
14
- Interscript.transliterate_file(options[:system], input, options[:output], JSON.parse(options[:map]))
15
+ Interscript.transliterate_file(options[:system], input, options[:output]) #, JSON.parse(options[:map]))
15
16
  else
16
17
  puts Interscript.transliterate(options[:system], IO.read(input))
17
18
  end
@@ -19,9 +20,8 @@ module Interscript
19
20
 
20
21
  desc 'list', 'Prints allowed transliteration systems'
21
22
  def list
22
- dir = File.expand_path '../../maps/*.yaml', __dir__
23
- Dir[dir].each do |path|
24
- puts File.basename path, '.yaml'
23
+ Interscript.maps(load_path: true).each do |path|
24
+ puts path
25
25
  end
26
26
  end
27
27
  end
@@ -0,0 +1,22 @@
1
+ # An Interscript compiler interface
2
+ class Interscript::Compiler
3
+ attr_accessor :code
4
+
5
+ def self.call(map, **kwargs)
6
+ if String === map
7
+ map = Interscript::DSL.parse(map)
8
+ end
9
+ compiler = new
10
+ compiler.compile(map, **kwargs)
11
+ compiler
12
+ end
13
+
14
+ def compile(map)
15
+ raise NotImplementedError, "Compile method on #{self.class} is not implemented"
16
+ end
17
+
18
+ # Execute a map
19
+ def call
20
+ raise NotImplementedError, "Call class on #{self.class} is not implemented"
21
+ end
22
+ end
@@ -0,0 +1,292 @@
1
+ begin
2
+ require 'mini_racer'
3
+ rescue LoadError
4
+ # Ignore loading error
5
+ end
6
+ require 'json'
7
+
8
+ class Interscript::Compiler::Javascript < Interscript::Compiler
9
+ def compile(map, debug: false)
10
+ @map = map
11
+ @parallel_trees = {}
12
+ @parallel_regexps = {}
13
+ @debug = debug
14
+ c = "var map = function(Interscript) {"
15
+ c << "Interscript.define_map(#{map.name.inspect}, function(Interscript, map) {\n";
16
+ c << "map.dependencies = #{map.dependencies.map(&:full_name).to_json};\n"
17
+ c
18
+
19
+ map.aliases.each do |name, value|
20
+ val = compile_item(value.data, map, :str)
21
+ c << "map.aliases.#{name} = #{val};\n"
22
+ val = '"'+compile_item(value.data, map, :re)+'"'
23
+ c << "map.aliases_re.#{name} = #{val};\n"
24
+ end
25
+
26
+ map.stages.each do |_, stage|
27
+ c << compile_rule(stage, @map, true)
28
+ end
29
+ @parallel_trees.each do |k,v|
30
+ c << "map.cache.PTREE_#{k} = #{v.to_json};\n"
31
+ end
32
+ @parallel_regexps.each do |k,v|
33
+ v = "[\"#{v[0]}\", #{v[1].to_json}]"
34
+ c << "map.cache.PRE_#{k} = #{v};\n"
35
+ end
36
+
37
+ c << "});"
38
+ c << "};"
39
+ c << "if (typeof module !== 'undefined') { module.exports = map; }"
40
+ c << "else if (typeof Interscript !== 'undefined') { map(Interscript); }"
41
+ c << 'else { throw "We couldn\'t dispatch Interscript from a map!"; }'
42
+ @code = c
43
+ end
44
+
45
+ def parallel_regexp_compile(subs_hash)
46
+ # puts subs_hash.inspect
47
+ regexp = subs_hash.each_with_index.map do |p,i|
48
+ "(?<_%d>%s)" % [i,p[0]]
49
+ end.join("|")
50
+ subs_regexp = regexp
51
+ # puts subs_regexp.inspect
52
+ end
53
+
54
+ def compile_rule(r, map = @map, wrapper = false)
55
+ c = ""
56
+ case r
57
+ when Interscript::Node::Stage
58
+ c += "map.stages.#{r.name} = function(s) {\n"
59
+ c += "globalThis.map_debug = globalThis.map_debug || [];\n" if @debug
60
+ r.children.each do |t|
61
+ comp = compile_rule(t, map)
62
+ c += comp
63
+ c += %{globalThis.map_debug.push([s, #{@map.name.to_s.to_json}, #{r.name.to_s.to_json}, #{t.inspect.to_json}, #{comp.to_json}]);\n} if @debug
64
+ end
65
+ c += "return s;\n"
66
+ c += "};\n"
67
+ when Interscript::Node::Group::Parallel
68
+ begin
69
+ # Try to build a tree
70
+ a = []
71
+ r.children.each do |i|
72
+ raise ArgumentError, "Can't parallelize #{i.class}" unless Interscript::Node::Rule::Sub === i
73
+ raise ArgumentError, "Can't parallelize rules with :before" if i.before
74
+ raise ArgumentError, "Can't parallelize rules with :after" if i.after
75
+ raise ArgumentError, "Can't parallelize rules with :not_before" if i.not_before
76
+ raise ArgumentError, "Can't parallelize rules with :not_after" if i.not_after
77
+
78
+ a << [compile_item(i.from, map, :par), compile_item(i.to, map, :parstr)]
79
+ end
80
+ ah = a.hash.abs
81
+ unless @parallel_trees.include? ah
82
+ tree = Interscript::Stdlib.parallel_replace_compile_tree(a)
83
+ @parallel_trees[ah] = tree
84
+ end
85
+ c += "s = Interscript.parallel_replace_tree(s, map.cache.PTREE_#{ah});\n"
86
+ rescue
87
+ # Otherwise let's build a megaregexp
88
+ a = []
89
+ Interscript::Stdlib.deterministic_sort_by_max_length(r.children).each do |i|
90
+ raise ArgumentError, "Can't parallelize #{i.class}" unless Interscript::Node::Rule::Sub === i
91
+
92
+ a << [build_regexp(i, map), compile_item(i.to, map, :parstr)]
93
+ end
94
+ ah = a.hash.abs
95
+ unless @parallel_regexps.include? ah
96
+ re = parallel_regexp_compile(a)
97
+ @parallel_regexps[ah] = [re, a.map(&:last)]
98
+ end
99
+ c += "s = Interscript.parallel_regexp_gsub(s, map.cache.PRE_#{ah});\n"
100
+ end
101
+ when Interscript::Node::Rule::Sub
102
+ from = %{"#{build_regexp(r, map).gsub("/", "\\\\/")}"}
103
+ if r.to == :upcase
104
+ to = 'function(a){return a.toUpperCase();}'
105
+ else
106
+ to = compile_item(r.to, map, :str)
107
+ end
108
+ c += "s = Interscript.gsub(s, #{from}, #{to});\n"
109
+ when Interscript::Node::Rule::Funcall
110
+ c += "s = Interscript.functions.#{r.name}(s, #{r.kwargs.to_json});\n"
111
+ when Interscript::Node::Rule::Run
112
+ if r.stage.map
113
+ doc = map.dep_aliases[r.stage.map].document
114
+ stage = doc.imported_stages[r.stage.name]
115
+ else
116
+ stage = map.imported_stages[r.stage.name]
117
+ end
118
+ c += "s = Interscript.transliterate(#{stage.doc_name.to_json}, s, #{stage.name.to_json});\n"
119
+ else
120
+ raise ArgumentError, "Can't compile unhandled #{r.class}"
121
+ end
122
+ c
123
+ end
124
+
125
+ def build_regexp(r, map=@map)
126
+ from = compile_item(r.from, map, :re)
127
+ before = compile_item(r.before, map, :re) if r.before
128
+ after = compile_item(r.after, map, :re) if r.after
129
+ not_before = compile_item(r.not_before, map, :re) if r.not_before
130
+ not_after = compile_item(r.not_after, map, :re) if r.not_after
131
+
132
+ re = ""
133
+ re += "(?<=#{before})" if before
134
+ re += "(?<!#{not_before})" if not_before
135
+ re += from
136
+ re += "(?!#{not_after})" if not_after
137
+ re += "(?=#{after})" if after
138
+
139
+ re
140
+ end
141
+
142
+ def compile_item i, doc=@map, target=nil
143
+ i = i.first_string if %i[str parstr].include? target
144
+ i = Interscript::Node::Item.try_convert(i)
145
+ if target == :parstr
146
+ parstr = true
147
+ target = :par
148
+ end
149
+
150
+ out = case i
151
+ when Interscript::Node::Item::Alias
152
+ astr = if i.map
153
+ d = doc.dep_aliases[i.map].document
154
+ a = d.imported_aliases[i.name]
155
+ raise ArgumentError, "Alias #{i.name} of #{i.stage.map} not found" unless a
156
+ "Interscript.get_alias_ALIASTYPE(#{a.doc_name.to_json}, #{a.name.to_json})"
157
+ elsif Interscript::Stdlib::ALIASES.include?(i.name)
158
+ if target != :re && Interscript::Stdlib.re_only_alias?(i.name)
159
+ raise ArgumentError, "Can't use #{i.name} in a #{target} context"
160
+ end
161
+ stdlib_alias = true
162
+ "Interscript.aliases.#{i.name}"
163
+ else
164
+ a = doc.imported_aliases[i.name]
165
+ raise ArgumentError, "Alias #{i.name} not found" unless a
166
+
167
+ "Interscript.get_alias_ALIASTYPE(#{a.doc_name.to_json}, #{a.name.to_json})"
168
+ end
169
+
170
+ if target == :str
171
+ astr = astr.sub("_ALIASTYPE(", "(")
172
+ elsif target == :re
173
+ astr = %{"+#{astr.sub("_ALIASTYPE(", "_re(")}+"}
174
+ elsif parstr && stdlib_alias
175
+ astr = Interscript::Stdlib::ALIASES[i.name]
176
+ elsif target == :par
177
+ # raise NotImplementedError, "Can't use aliases in parallel mode yet"
178
+ astr = Interscript::Stdlib::ALIASES[i.name]
179
+ end
180
+ when Interscript::Node::Item::String
181
+ if target == :str
182
+ # Replace $1 with \$1, this is weird, but it works!
183
+ i.data.gsub("$", "\\\\$").to_json
184
+ elsif target == :par
185
+ i.data
186
+ elsif target == :re
187
+ Regexp.escape(i.data)
188
+ end
189
+ when Interscript::Node::Item::Group
190
+ if target == :par
191
+ i.children.map do |j|
192
+ compile_item(j, doc, target)
193
+ end.reduce([""]) do |j,k|
194
+ Array(j).product(Array(k)).map(&:join)
195
+ end
196
+ elsif target == :str
197
+ i.children.map { |j| compile_item(j, doc, target) }.join("+")
198
+ elsif target == :re
199
+ i.children.map { |j| compile_item(j, doc, target) }.join
200
+ end
201
+ when Interscript::Node::Item::CaptureGroup
202
+ if target != :re
203
+ raise ArgumentError, "Can't use a CaptureGroup in a #{target} context"
204
+ end
205
+ "(" + compile_item(i.data, doc, target) + ")"
206
+ when Interscript::Node::Item::Maybe,
207
+ Interscript::Node::Item::MaybeSome,
208
+ Interscript::Node::Item::Some
209
+
210
+ resuffix = { Interscript::Node::Item::Maybe => "?" ,
211
+ Interscript::Node::Item::Some => "+" ,
212
+ Interscript::Node::Item::MaybeSome => "*" }[i.class]
213
+
214
+ if target == :par
215
+ raise ArgumentError, "Can't use a MaybeSome in a #{target} context"
216
+ end
217
+ if Interscript::Node::Item::String === i.data && i.data.data.length != 1
218
+ "(?:" + compile_item(i.data, doc, target) + ")" + resuffix
219
+ else
220
+ compile_item(i.data, doc, target) + resuffix
221
+ end
222
+ when Interscript::Node::Item::CaptureRef
223
+ if target == :par
224
+ raise ArgumentError, "Can't use CaptureRef in parallel mode"
225
+ elsif target == :re
226
+ "\\\\#{i.id}"
227
+ elsif target == :str
228
+ "\"$#{i.id}\""
229
+ end
230
+ when Interscript::Node::Item::Any
231
+ if target == :str
232
+ raise ArgumentError, "Can't use Any in a string context" # A linter could find this!
233
+ elsif target == :par
234
+ i.data.map(&:data)
235
+ elsif target == :re
236
+ case i.value
237
+ when Array
238
+ data = i.data.map { |j| compile_item(j, doc, target) }
239
+ "(?:"+data.join("|")+")"
240
+ when String
241
+ "[#{Regexp.escape(i.value)}]"
242
+ when Range
243
+ "[#{Regexp.escape(i.value.first)}-#{Regexp.escape(i.value.last)}]"
244
+ end
245
+ end
246
+ end
247
+ end
248
+
249
+ @maps_loaded = {}
250
+ @ctx = nil
251
+ class << self
252
+ attr_accessor :maps_loaded
253
+ attr_accessor :ctx
254
+ end
255
+
256
+ def load
257
+ if !self.class.maps_loaded[@map.name]
258
+ @map.dependencies.each do |dep|
259
+ dep = dep.full_name
260
+ if !self.class.maps_loaded[dep]
261
+ Interscript.load(dep, compiler: self.class).load
262
+ end
263
+ end
264
+
265
+ ctx = self.class.ctx
266
+ unless ctx
267
+ ctx = MiniRacer::Context.new
268
+ ctx.eval File.read(__dir__+"/../../../../js/test-compiler/xregexp.js")
269
+ # Compatibility with Safari: will come later
270
+ #ctx.eval File.read(__dir__+"/../../../js/xregexp-oniguruma.js")
271
+ ctx.eval File.read(__dir__+"/../../../../js/src/stdlib.js")
272
+ self.class.ctx = ctx
273
+ end
274
+ #puts @code
275
+ ctx.eval @code
276
+ self.class.maps_loaded[@map.name] = true
277
+ end
278
+ end
279
+
280
+ def call(str, stage=:main)
281
+ load
282
+ self.class.ctx.eval "Interscript.transliterate(#{@map.name.to_json}, #{str.to_json}, #{stage.to_json})"
283
+ end
284
+
285
+ def self.read_debug_data
286
+ self.ctx.eval "globalThis.map_debug || []"
287
+ end
288
+
289
+ def self.reset_debug_data
290
+ self.ctx.eval "globalThis.map_debug = []"
291
+ end
292
+ end