interscript 0.1.6 → 2.1.0a9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (226) 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 +3 -39
  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/exe/interscript +6 -0
  19. data/interscript.gemspec +31 -0
  20. data/lib/interscript.rb +81 -127
  21. data/lib/interscript/command.rb +5 -5
  22. data/lib/interscript/compiler.rb +22 -0
  23. data/lib/interscript/compiler/javascript.rb +292 -0
  24. data/lib/interscript/compiler/ruby.rb +262 -0
  25. data/lib/interscript/dsl.rb +67 -0
  26. data/lib/interscript/dsl/aliases.rb +23 -0
  27. data/lib/interscript/dsl/document.rb +46 -0
  28. data/lib/interscript/dsl/group.rb +45 -0
  29. data/lib/interscript/dsl/group/parallel.rb +6 -0
  30. data/lib/interscript/dsl/items.rb +89 -0
  31. data/lib/interscript/dsl/metadata.rb +26 -0
  32. data/lib/interscript/dsl/stage.rb +6 -0
  33. data/lib/interscript/dsl/symbol_mm.rb +11 -0
  34. data/lib/interscript/dsl/tests.rb +12 -0
  35. data/lib/interscript/interpreter.rb +251 -0
  36. data/lib/interscript/node.rb +25 -0
  37. data/lib/interscript/node/alias_def.rb +15 -0
  38. data/lib/interscript/node/dependency.rb +13 -0
  39. data/lib/interscript/node/document.rb +45 -0
  40. data/lib/interscript/node/group.rb +34 -0
  41. data/lib/interscript/node/group/parallel.rb +9 -0
  42. data/lib/interscript/node/group/sequential.rb +2 -0
  43. data/lib/interscript/node/item.rb +52 -0
  44. data/lib/interscript/node/item/alias.rb +42 -0
  45. data/lib/interscript/node/item/any.rb +61 -0
  46. data/lib/interscript/node/item/capture.rb +50 -0
  47. data/lib/interscript/node/item/group.rb +51 -0
  48. data/lib/interscript/node/item/repeat.rb +40 -0
  49. data/lib/interscript/node/item/stage.rb +23 -0
  50. data/lib/interscript/node/item/string.rb +51 -0
  51. data/lib/interscript/node/metadata.rb +18 -0
  52. data/lib/interscript/node/rule.rb +6 -0
  53. data/lib/interscript/node/rule/funcall.rb +18 -0
  54. data/lib/interscript/node/rule/run.rb +15 -0
  55. data/lib/interscript/node/rule/sub.rb +65 -0
  56. data/lib/interscript/node/stage.rb +19 -0
  57. data/lib/interscript/node/tests.rb +15 -0
  58. data/lib/interscript/stdlib.rb +211 -0
  59. data/lib/interscript/utils/regexp_converter.rb +283 -0
  60. data/lib/interscript/version.rb +1 -1
  61. data/requirements.txt +1 -0
  62. metadata +75 -339
  63. data/README.adoc +0 -298
  64. data/bin/rspec +0 -29
  65. data/lib/__pycache__/g2pwrapper.cpython-38.pyc +0 -0
  66. data/lib/g2pwrapper.py +0 -34
  67. data/lib/interscript-opal.rb +0 -2
  68. data/lib/interscript/fs.rb +0 -71
  69. data/lib/interscript/mapping.rb +0 -142
  70. data/lib/interscript/opal.rb +0 -27
  71. data/lib/interscript/opal/maps.js.erb +0 -10
  72. data/lib/interscript/opal_map_translate.rb +0 -12
  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 -38912
  76. data/maps/alalc-amh-Ethi-Latn-1997.yaml +0 -509
  77. data/maps/alalc-amh-Ethi-Latn-2011.yaml +0 -138
  78. data/maps/alalc-ara-Arab-Latn-1997.yaml +0 -1283
  79. data/maps/alalc-asm-Deva-Latn-1997.yaml +0 -159
  80. data/maps/alalc-aze-Cyrl-Latn-1997.yaml +0 -141
  81. data/maps/alalc-bel-Cyrl-Latn-1997.yaml +0 -125
  82. data/maps/alalc-ben-Beng-Latn-2017.yaml +0 -130
  83. data/maps/alalc-bul-Cyrl-Latn-1997.yaml +0 -94
  84. data/maps/alalc-ell-Grek-Latn-1997.yaml +0 -624
  85. data/maps/alalc-ell-Grek-Latn-2010.yaml +0 -627
  86. data/maps/alalc-hin-Deva-Latn-2020.yaml +0 -159
  87. data/maps/alalc-kat-Geok-Latn-1997.yaml +0 -111
  88. data/maps/alalc-kat-Geor-Latn-1997.yaml +0 -146
  89. data/maps/alalc-kor-Hang-Latn-1997.yaml +0 -94
  90. data/maps/alalc-mar-Deva-Latn-1997.yaml +0 -170
  91. data/maps/alalc-mkd-Cyrl-Latn-1997.yaml +0 -114
  92. data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +0 -103
  93. data/maps/alalc-pan-Deva-Latn-1997.yaml +0 -237
  94. data/maps/alalc-rus-Cyrl-Latn-1997.yaml +0 -221
  95. data/maps/alalc-rus-Cyrl-Latn-2012.yaml +0 -162
  96. data/maps/alalc-srp-Cyrl-Latn-1997.yaml +0 -114
  97. data/maps/alalc-srp-Cyrl-Latn-2013.yaml +0 -135
  98. data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +0 -141
  99. data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +0 -16
  100. data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +0 -283
  101. data/maps/bas-rus-Cyrl-Latn-2017-bss.yaml +0 -174
  102. data/maps/bas-rus-Cyrl-Latn-2017-oss.yaml +0 -169
  103. data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +0 -292
  104. data/maps/bgn-kor-Hang-Latn-1943.yaml +0 -31
  105. data/maps/bgn-kor-Kore-Latn-1943.yaml +0 -31
  106. data/maps/bgna-bul-Cyrl-Latn-2006.yaml +0 -208
  107. data/maps/bgna-bul-Cyrl-Latn-2009.yaml +0 -208
  108. data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +0 -528
  109. data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +0 -592
  110. data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +0 -108
  111. data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +0 -104
  112. data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +0 -184
  113. data/maps/bgnpcgn-bel-Cyrl-Latn-1979.yaml +0 -285
  114. data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +0 -115
  115. data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +0 -38
  116. data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +0 -701
  117. data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +0 -19
  118. data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +0 -257
  119. data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +0 -127
  120. data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +0 -42
  121. data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +0 -253
  122. data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +0 -48
  123. data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +0 -48
  124. data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +0 -159
  125. data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +0 -190
  126. data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +0 -200
  127. data/maps/bgnpcgn-per-Arab-Latn-1956.yaml +0 -92
  128. data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +0 -314
  129. data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +0 -166
  130. data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +0 -162
  131. data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +0 -208
  132. data/maps/bgnpcgn-zho-Hans-Latn-1979.yaml +0 -7456
  133. data/maps/bis-asm-Beng-Latn-13194-1991.yaml +0 -159
  134. data/maps/bis-ben-Beng-Latn-13194-1991.yaml +0 -156
  135. data/maps/bis-dev-Deva-Latn-13194-1991.yaml +0 -184
  136. data/maps/bis-gjr-Gujr-Latn-13194-1991.yaml +0 -166
  137. data/maps/bis-knd-Knda-Latn-13194-1991.yaml +0 -173
  138. data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +0 -176
  139. data/maps/bis-ori-Orya-Latn-13194-1991.yaml +0 -160
  140. data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +0 -175
  141. data/maps/bis-tel-Telu-Latn-13194-1991.yaml +0 -170
  142. data/maps/bis-tml-Taml-Latn-13194-1991.yaml +0 -155
  143. data/maps/by-bel-Cyrl-Latn-1998.yaml +0 -168
  144. data/maps/by-bel-Cyrl-Latn-2007.yaml +0 -115
  145. data/maps/dos-nep-Deva-Latn-1997.yaml +0 -33
  146. data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +0 -684
  147. data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +0 -680
  148. data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +0 -19
  149. data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +0 -31
  150. data/maps/ggg-kat-Geor-Latn-2002.yaml +0 -88
  151. data/maps/gki-bel-Cyrl-Latn-1992.yaml +0 -33
  152. data/maps/gki-bel-Cyrl-Latn-2000.yaml +0 -201
  153. data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml +0 -186
  154. data/maps/hk-yue-Hani-Latn-1888.yaml +0 -38497
  155. data/maps/icao-bel-Cyrl-Latn-9303.yaml +0 -136
  156. data/maps/icao-bul-Cyrl-Latn-9303.yaml +0 -118
  157. data/maps/icao-heb-Hebr-Latn-9303.yaml +0 -151
  158. data/maps/icao-mkd-Cyrl-Latn-9303.yaml +0 -117
  159. data/maps/icao-per-Arab-Latn-9303.yaml +0 -103
  160. data/maps/icao-rus-Cyrl-Latn-9303.yaml +0 -117
  161. data/maps/icao-srp-Cyrl-Latn-9303.yaml +0 -117
  162. data/maps/icao-ukr-Cyrl-Latn-9303.yaml +0 -119
  163. data/maps/iso-ara-Arab-Latn-233-1984.yaml +0 -323
  164. data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +0 -609
  165. data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +0 -40
  166. data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +0 -62
  167. data/maps/iso-rus-Cyrl-Latn-9-1995.yaml +0 -271
  168. data/maps/iso-tha-Thai-Latn-11940-1998.yaml +0 -109
  169. data/maps/kp-kor-Hang-Latn-2002.yaml +0 -901
  170. data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +0 -44820
  171. data/maps/mext-jpn-Hrkt-Latn-1954.yaml +0 -411
  172. data/maps/moct-kor-Hang-Latn-2000.yaml +0 -803
  173. data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +0 -541
  174. data/maps/mvd-bel-Cyrl-Latn-2008.yaml +0 -225
  175. data/maps/mvd-bel-Cyrl-Latn-2010.yaml +0 -63
  176. data/maps/mvd-rus-Cyrl-Latn-2008.yaml +0 -109
  177. data/maps/mvd-rus-Cyrl-Latn-2010.yaml +0 -37
  178. data/maps/nil-kor-Hang-Hang-jamo.yaml +0 -11193
  179. data/maps/odni-aze-Cyrl-Latn-2015.yaml +0 -144
  180. data/maps/odni-bel-Cyrl-Latn-2015.yaml +0 -148
  181. data/maps/odni-bul-Cyrl-Latn-2015.yaml +0 -96
  182. data/maps/odni-hin-Deva-Latn-2015.yaml +0 -258
  183. data/maps/odni-kat-Geor-Latn-2015.yaml +0 -87
  184. data/maps/odni-kaz-Cyrl-Latn-2015.yaml +0 -148
  185. data/maps/odni-kir-Cyrl-Latn-2015.yaml +0 -136
  186. data/maps/odni-mkd-Cyrl-Latn-2015.yaml +0 -122
  187. data/maps/odni-rus-Cyrl-Latn-2015.yaml +0 -77
  188. data/maps/odni-srp-Cyrl-Latn-2015.yaml +0 -129
  189. data/maps/odni-tat-Cyrl-Latn-2015.yaml +0 -142
  190. data/maps/odni-tgk-Cyrl-Latn-2015.yaml +0 -148
  191. data/maps/odni-uig-Cyrl-Latn-2015.yaml +0 -138
  192. data/maps/odni-ukr-Cyrl-Latn-2015.yaml +0 -157
  193. data/maps/odni-urd-Arab-Latn-2015.yaml +0 -221
  194. data/maps/odni-uzb-Cyrl-Latn-2015.yaml +0 -166
  195. data/maps/royin-tha-Thai-Latn-1939-generic.yaml +0 -90
  196. data/maps/royin-tha-Thai-Latn-1968.yaml +0 -179
  197. data/maps/royin-tha-Thai-Latn-1999-chained.yaml +0 -180
  198. data/maps/royin-tha-Thai-Latn-1999.yaml +0 -76
  199. data/maps/sac-zho-Hans-Latn-1979.yaml +0 -24759
  200. data/maps/ses-ara-Arab-Latn-1930.yaml +0 -279
  201. data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +0 -222
  202. data/maps/ua-ukr-Cyrl-Latn-1996.yaml +0 -193
  203. data/maps/un-ara-Arab-Latn-1971.yaml +0 -139
  204. data/maps/un-ara-Arab-Latn-1972.yaml +0 -159
  205. data/maps/un-ara-Arab-Latn-2017.yaml +0 -420
  206. data/maps/un-bel-Cyrl-Latn-2007.yaml +0 -114
  207. data/maps/un-ben-Beng-Latn-2016.yaml +0 -534
  208. data/maps/un-ell-Grek-Latn-1987-tl.yaml +0 -31
  209. data/maps/un-ell-Grek-Latn-1987-ts.yaml +0 -19
  210. data/maps/un-ell-Grek-Latn-phonetic-1987.yaml +0 -780
  211. data/maps/un-mon-Mong-Latn-2013.yaml +0 -99
  212. data/maps/un-nep-Deva-Latn-1972.yaml +0 -163
  213. data/maps/un-rus-Cyrl-Latn-1987.yaml +0 -166
  214. data/maps/un-ukr-Cyrl-Latn-1998.yaml +0 -30
  215. data/maps/ungegn-amh-Ethi-Latn-2016.yaml +0 -575
  216. data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +0 -406
  217. data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +0 -386
  218. data/maps/var-kor-Hang-Latn-mr-1939.yaml +0 -1054
  219. data/maps/var-kor-Kore-Hang-2013.yaml +0 -59754
  220. data/maps/var-kor-Kore-Latn-mr-1939.yaml +0 -36
  221. data/maps/var-tha-Thai-Thai-phonemic.yaml +0 -59
  222. data/maps/var-tha-Thai-Zsym-ipa.yaml +0 -301
  223. data/maps/var-zho-Hani-Latn-1979.yaml +0 -38908
  224. data/spec/interscript/mapping_spec.rb +0 -42
  225. data/spec/interscript_spec.rb +0 -26
  226. data/spec/spec_helper.rb +0 -3
@@ -1,160 +0,0 @@
1
- ---
2
- authority_id: bis
3
- id: 1991
4
- language: ori
5
- source_script: Orya
6
- destination_script: Latn
7
- name: Indian script code for information interchange - ISCII - Oriya Romanization
8
- #url:
9
- creation_date: 1991
10
- description: |
11
- IS 13194 (1991): Indian script code for information
12
- interchange - ISCII [LITD 20: Indian Language Technologies
13
- and Products]
14
-
15
- notes:
16
- - |
17
- Exception: Anusvāra is transliterated by:
18
-
19
- a) ṅ before gutturals,
20
- b) ñ before palatals,
21
- c) ṇ before cerebrals,
22
- d) n before dentals, and
23
- e) m before labials.
24
-
25
- tests:
26
- - source: "ସାମ୍ପ୍ରତିକ ବିଶ୍ବ ସ୍ଥିତାବସ୍ଥାକୁ ଚାଲେଞ୍ଜ୍‌ କରୁଥିବା ଦୁଇ ମୁଖ୍ୟ ପ୍ରତିଦ୍ବନ୍ଦ୍ବୀ ହେଉଛନ୍ତି ଚୀନ୍‌ ଓ ରୁଷ୍: ଇଂଲଣ୍ଡ୍‌ ଗୁଇନ୍ଦା ଅଧିକାରୀ"
27
- expected: "sāmprtik biśb sthitābsthāku cālēñj kruthibā dui mukhẏ prtidbndbī hēuchnti cīn ŏ ruṣ: iṃlṇḍ guindā adhikārī"
28
- - source: "ଏଣିକି ଏହି ଗାଡ଼ି ଚଳାଇଲେ ପୁଲିସ କାଟି ପାରିବ ନାହିଁ ଫାଇନ୍"
29
- expected: "ēṇiki ēhi gād̂i cḷāilē pulis kāṭi pārib nāhim phāin"
30
- - source: "ପିସି କାରବାର ଘଟଣା, ନିଲମ୍ବନ ହେଲେ ପଞ୍ଚାୟତ ଅଧିକାରୀ"
31
- expected: "pisi kārbār ghṭṇā, nilmbn hēlē pñcāẏt adhikārī"
32
- - source: "ବରିଷ୍ଠ ଓଡ଼ିଆ ଚଳଚ୍ଚିତ୍ର ଅଭିନେତା ଅଜିତ ଦାସଙ୍କ"
33
- expected: "briṣṭh ŏḍiā cḷccitr abhinētā ajit dāsṅk"
34
- - source: "ସଞ୍ଚୟ କରିବାରେ କେଉଁ ରାଶି ଅଧିକ ସତର୍କ ?"
35
- expected: "sñcẏ kribārē kēum rāśi adhik strk ?"
36
- - source: "କର୍କଟ ରାଶିର ଅଧିକାରୀ ନିଜ ଜ୍ଞାତିପରିଜନଙ୍କ ପାଇଁ ଟଙ୍କା ଖର୍ଚ୍ଚ କରିବାକୁ ପସନ୍ଦ କରିଥାନ୍ତି।"
37
- expected: "krkṭ rāśir adhikārī nij jñātiprijnṅk pāim ṭṅkā khrcc kribāku psnd krithānti."
38
- - source: "ବୃଷ ରାଶିର ବ୍ୟକ୍ତିମାନେ ସ୍ବଭାବରେ କଞ୍ଜୁସ୍ କିମ୍ବା କୃପଣ ନୁହନ୍ତି"
39
- expected: "bṛṣ rāśir bẏktimānē sbbhābrē kñjus kimbā kṛpṇ nuhnti"
40
- - source: "ନବନିଯୁକ୍ତ ଓଡିଶା କଂଗ୍ରେସ ପ୍ରଭାରୀ ଏ.ଚେଲ୍ଲା କୁମାରଙ୍କୁ କରୋନା"
41
- expected: "nbniyukt ŏḍiśā kṅgrēs prbhārī ē.cēllā kumārṅku krŏnā"
42
- - source: "ଦିଲ୍ଲୀ: ଦିନ ଦ୍ବିପହରରେ ଗାଡ଼ି ଉପରକୁ ଦୁର୍ବୃତ୍ତ ଚଳାଇଲେ ୮ ରାଉଣ୍ଡ ଗୁଳି: ଚାଳକଙ୍କ ମୃତ୍ୟୁ"
43
- expected: "dillī: din dbiphrrē gād̂i uprku durbṛtt cḷāilē ୮ rāuṇḍ guḷi: cāḷkṅk mṛtẏu"
44
- - source: "ବୟସରେ ଆର ପାରିକୁ ଚାଲିଗଲେ କଣ୍ଠଶିଳ୍ପୀ ଅନୁରାଧା ପୋଡୱାଲଙ୍କ ପୁଅ ଆଦିତ୍ୟ"
45
- expected: "bẏsrē ār pāriku cāliglē kṇṭhśiḷpī anurādhā pēāḍୱālṅk pua āditẏ"
46
-
47
- map:
48
-
49
- rules:
50
- # note
51
- - pattern: \u0B02(?=[କଖଗଘଙ])
52
- result: ṅ
53
- - pattern: \u0B02(?=[ଚଛଜଝଞ])
54
- result: ñ
55
- - pattern: \u0B02(?=[ଟଠଡଡ଼ଢଣଢ଼])
56
- result: ṇ
57
- - pattern: \u0B02(?=[ତଥଦଧନ])
58
- result: n
59
- - pattern: \u0B02(?=[ପଫବଭମ])
60
- result: m
61
-
62
-
63
- characters:
64
- 'ଅ': 'a'
65
- 'ଆ': 'ā'
66
- 'ଇ': 'i'
67
- 'ଈ': 'ī'
68
- 'ଉ': 'u'
69
- 'ଊ': 'ū'
70
- 'ଋ': 'ṛ'
71
- 'ଌ': 'ḻ'
72
- 'ଏ': 'ē'
73
- 'ଐ': 'ai'
74
- 'ଓ': 'ŏ'
75
- 'ଔ': 'au'
76
-
77
- # II. Consonants (see Note 2)
78
- # Gutturals
79
- 'କ': 'k'
80
- 'ଖ': 'kh'
81
- 'ଗ': 'g'
82
- 'ଘ': 'gh'
83
- 'ଙ': 'ṅ'
84
-
85
- # Palatals
86
- 'ଚ': 'c'
87
- 'ଛ': 'ch'
88
- 'ଜ': 'j'
89
- 'ଝ': 'jh'
90
- 'ଞ': 'ñ'
91
-
92
- # Cerebrals
93
- 'ଟ': 'ṭ'
94
- 'ଠ': 'ṭh'
95
- 'ଡ': 'ḍ'
96
- 'ଡ଼': 'd̂'
97
- 'ଢ': 'ḍh'
98
- 'ଢ଼': 'd̂h'
99
- 'ଣ': 'ṇ'
100
-
101
- # Dentals
102
- 'ତ': 't'
103
- 'ଥ': 'th'
104
- 'ଦ': 'd'
105
- 'ଧ': 'dh'
106
- 'ନ': 'n'
107
-
108
- # Labials
109
- 'ପ': 'p'
110
- 'ଫ': 'ph'
111
- 'ବ': 'b'
112
- 'ଭ': 'bh'
113
- 'ମ': 'm'
114
-
115
- # Semivowels
116
- 'ଯ': 'y'
117
- 'ୟ': 'ẏ'
118
- 'ର': 'r'
119
- 'ଲ': 'l'
120
- 'ଳ': 'ḷ'
121
- 'ଵ': 'v'
122
-
123
- # Sibilants
124
- 'ଶ': 'ś'
125
- 'ଷ': 'ṣ'
126
- 'ସ': 's'
127
-
128
-
129
- # Aspirate
130
- 'ହ': 'h'
131
-
132
- # Chandrabindu
133
- 'ଁ': 'm'
134
-
135
- # Bisarga
136
- 'ଃ': 'ḥ'
137
-
138
- # Anusvāra
139
- 'ଂ': 'ṃ'
140
-
141
- # Medials # Needed for connecting constants
142
-
143
- 'ା': 'ā'
144
- 'ି': 'i'
145
- 'ୀ': 'ī'
146
- 'ୁ': 'u'
147
- 'ୂ': 'ū'
148
- 'ୃ': 'ṛ'
149
- 'େ': 'ē'
150
- 'ୈ': 'ai'
151
- 'ୋ': 'ŏ'
152
- 'ୌ': 'au'
153
-
154
- '्': ''
155
- '୍': ''
156
- '़': ''
157
- '଼': ''
158
- '।': '.'
159
- "‍": ''# Used for joining
160
- "‌": ''# Used for non joining
@@ -1,175 +0,0 @@
1
- ---
2
- authority_id: bis
3
- id: 1991
4
- language: pnj
5
- source_script: Guru
6
- destination_script: Latn
7
- name: Indian script code for information interchange - ISCII - Panjabi(Gurmukhi) Romanization
8
- #url:
9
- creation_date: 1991
10
- description: |
11
- IS 13194 (1991): Indian script code for information
12
- interchange - ISCII [LITD 20: Indian Language Technologies
13
- and Products]
14
-
15
- notes:
16
- - |
17
- Exception: Anusvāra is transliterated by:
18
-
19
- a) ṅ before gutturals,
20
- b) ñ before palatals,
21
- c) ṇ before cerebrals,
22
- d) n before dentals, and
23
- e) m before labials.
24
-
25
- tests:
26
- - source: "ਸਦਾ ਜਵਾਨ ਰਹੋ"
27
- expected: "sdā jvāṉ rhō"
28
- - source: "ਸਵਾਮੀ ਅਗਨੀਵੇਸ਼ ਦੀ ਮੌਤ"
29
- expected: "svāmī agṉīvēs dī maut"
30
- - source: "ਇਸ ਲਈ ਖੱਟੀ ਤਲੀ ਚੀਜ਼ , ਫਾਸਟ ਫੁੂਟ, ਤੇਜ਼ ਮਿਰਚ ਮਸਾਲਿਆਂ ਨੂੰ ਛੱਡਕੇ ਚੰਗੇ ਤੇ ਮੌਸਮੀ ਫਲ, ਹਰੀਆਂ ਸ਼ਬਜ਼ੀਆਂ, ਘਰ ਦੀ ਲੱਸੀ ਤੇ ਦਹੀਂ ਤੇ ਔਰਗੈਨਿਕ ਚੀਜ਼ਾਂ ਹੀ ਅਪਣਾਉ"
31
- expected: "is lī khṭī tlī cīz , phāsṭ phuūṭ, tēz mirc msāliān ṉūṃ chḍkē cṅgē tē mausmī phl, hrīān śbzīān, ghr dī lsī tē dhīn tē aurgaiṉik cīzān hī apṇāu"
32
- - source: "ਤੁਹਾਡਾ ਚਿਹਰਾ ਸਦਾ ਚੜ੍ਹਦੀ ਕਲਾ ‘ਚ ਰਹਿਣਾ ਤੇ ਹਮੇਸ਼ਾ ਖਿੜੀਆਂ ਰਹਿਣਾ ਤੇ ਠਾਠਾਂ ਮਾਰਦਾ ਸਰੀਰ ਹੀ ਤੁਹਾਡੇ ਜਵਾਨ ਰਹਿਣ ਦੀ ਨਿਸ਼ਾਨੀ ਹੈ"
33
- expected: "tuhāḍā cihrā sdā cṛahdī klā ‘c rhiṇā tē hmēśā khiṛaīān rhiṇā tē ṭhāṭhān mārdā srīr hī tuhāḍē jvāṉ rhiṇ dī ṉiśāṉī hai"
34
- - source: "ਧੌਲੇ ਆਉਣਾ ਜਾਂ ਕਹਿ ਲਵੋ, ਵਾਲ ਚਿੱਟੇ ਹੋਣਾ ਬੁੱਢਾਪਾ ਨਹੀਂ ਹੈ।ਪਰ ਉਮਰ ਤਂੋ ਪਹਿਲਾਂ ਮੂੰਹ ਤੋਂ ਨੂਰ ਉੜ ਜਾਣਾ,ਹਮੇਸ਼ਾਂ ਥੱਕਿਆ-2 ਰਹਿਣਾ ,ਬਿਮਾਰ ਰਹਿਣਾ ਅਸਲ ਬੁਢਾਪਾ ਹੈ"
35
- expected: "dhaulē āuṇā jān khi lvō, vāl ciṭē hōṇā buḍhāpā ṉhīn hai.pr umr tnō philān mūṃh tōn ṉūr uṛa jāṇā,hmēśān thkiā-2 rhiṇā ,bimār rhiṇā asl buḍhāpā hai"
36
- - source: "ਇਸ ਲਈ ਇਹ ਆਪਾਂ ਨੂੰ ਦੇਖਣਾ ਪਵੇਗਾ ਕਿ ਆਪਾਂ ਕਿਵੇਂ ਤੰਦਰੁਸਤ ਰਹਿਣਾ ਹੈ ਤੇ ਨਿਰੋਗ ਰਹਿਣਾ ਹੈ"
37
- expected: "is lī ih āpān ṉūṃ dēkhṇā pvēgā ki āpān kivēn tndrust rhiṇā hai tē ṉirōg rhiṇā hai"
38
- - source: "ਸਮਾਜਿਕ ਕਾਰਕੁੰਨ ਸਵਾਮੀ ਅਗਨੀਵੇਸ ਦਾ ਅੱਜ ਸ਼ਾਮੀਂ ਦਿਹਾਂਤ ਹੋ ਗਿਆ"
39
- expected: "smājik kārkunṉ svāmī agṉīvēs dā aj sāmīn dihānt hō giā"
40
- - source: "ਹਰ ਇਨਸਾਨ ਸਦਾ ਸਵਸਥ ਤੇ ਜਵਾਨ ਰਹਿਣਾ ਚਾਹੁੰਦਾ ਹੈ"
41
- expected: "hr iṉsāṉ sdā svsth tē jvāṉ rhiṇā cāhundā hai"
42
- - source: "ਜਨਮ ਲੈਣਾ ਤੇ ਮੌਤ ਇੱਕ ਅਟਲ ਸੱਚਾਈ ਹੈ"
43
- expected: "jṉm laiṇā tē maut ik aṭl scāī hai"
44
- - source: "ਇਸਦੇ ਉਲਟ ਤੁਹਾਡੀ ਗਲਤ ਜੀਵਨ ਸ਼ੈਲੀ, ਗਲਤ ਖਾਣਾ ਤੇ ਹਮੇਸ਼ਾ ਕੀਮਤੀ ਸਰੀਰ ਪ੍ਰਤੀ ਲਾਪਰਵਾਹੀ ਕਦੇ ਵੀ ਤੁਹਾਨੁੂੰ ਜਵਾਨ ਤੇ ਨਿਰੋਗੀ ਨਹੀਂ ਰੱਖ ਸਕਦੀ"
45
- expected: "isdē ulṭ tuhāḍī glt jīvṉ śailī, glt khāṇā tē hmēśā kīmtī srīr prtī lāprvāhī kdē vī tuhāṉuūṃ jvāṉ tē ṉirōgī ṉhīn rkh skdī"
46
-
47
- map:
48
-
49
- rules:
50
- # note
51
- - pattern: \u0A70(?=[ਕਖਖ਼ਗਗ਼ਘਙ]) # ੰ before gutturals
52
- result: ṅ
53
- - pattern: \u0A70(?=[ਚਛਜਜ਼ਝਞ]) # ੰ before palatals
54
- result: ñ
55
- - pattern: \u0A70(?=[ਟਠਡਢਣ]) # ੰ before cerebrals
56
- result: ṇ
57
- - pattern: \u0A70(?=[ਤਥਦਧਨ]) # ੰ before dentals
58
- result: n
59
- - pattern: \u0A70(?=[ਪਫਬਭਮ])
60
- result: m
61
-
62
-
63
- characters:
64
- 'ਅ': 'a'
65
- 'ਆ': 'ā'
66
- 'ਇ': 'i'
67
- 'ਈ': 'ī'
68
- 'ਉ': 'u'
69
- 'ਊ': 'ū'
70
- 'ੲ': 'ṛ'
71
- 'ੳ': 'ṝ'
72
- 'ਏ': 'ē'
73
- 'ਐ': 'ai'
74
-
75
- 'ਓ': 'ŏ'
76
- 'ਔ': 'au'
77
-
78
- # II. Consonants (see Note 2)
79
- # Gutturals
80
- 'ਕ': 'k'
81
- 'ਖ': 'kh'
82
- 'ਗ': 'g'
83
- 'ਘ': 'gh'
84
- 'ਙ': 'ṅ'
85
-
86
- # Palatals
87
- 'ਚ': 'c'
88
- 'ਛ': 'ch'
89
- 'ਜ': 'j'
90
- 'ਝ': 'jh'
91
- 'ਞ': 'ñ'
92
-
93
- # Cerebrals
94
- 'ਟ': 'ṭ'
95
- 'ਠ': 'ṭh'
96
- 'ਡ': 'ḍ'
97
- 'ਢ': 'ḍh'
98
- 'ਣ': 'ṇ'
99
-
100
- # Dentals
101
- 'ਤ': 't'
102
- 'ਥ': 'th'
103
- 'ਦ': 'd'
104
- 'ੜ': 'ṛa'
105
- 'ਧ': 'dh'
106
- 'ਨ': 'ṉ'
107
-
108
- # Labials
109
- 'ਪ': 'p'
110
- 'ਫ': 'ph'
111
- 'ਬ': 'b'
112
- 'ਭ': 'bh'
113
- 'ਮ': 'm'
114
-
115
- # Semivowels
116
- 'ਯ': 'y'
117
- #'य़': 'ẏ'
118
- 'ਰ': 'r'
119
- #'ऱ': 'ṟ'
120
- 'ਲ': 'l'
121
- 'ਲ਼': 'ḷ'
122
- #'ऴ': 'ẕ'
123
-
124
-
125
- 'ਵ': 'v'
126
-
127
- # Sibilants
128
- 'ਸ਼': 'ś'
129
- #'ष': 'ṣ'
130
- 'ਸ': 's'
131
-
132
-
133
- # Aspirate
134
- 'ਹ': 'h'
135
-
136
-
137
- #Nukta Constants
138
-
139
- 'क़': 'q'
140
- 'ਖ਼': 'ḵẖ'
141
- 'ਗ਼': 'gẖ'
142
- 'ਜ਼': 'z'
143
- 'ਫ਼': 'f'
144
-
145
- # Chandrabindu
146
- 'ँ': 'm'
147
-
148
- # Bisarga
149
- 'ः ': 'ḥ'
150
- 'ਂ': 'n'
151
-
152
- # Anusvāra
153
- 'ੰ': 'ṃ'
154
-
155
- # Medials # Needed for connecting constants
156
- 'ਾ': "ā"
157
- 'ਿ': "i"
158
- 'ੀ': "ī"
159
- 'ੁ': "u"
160
- 'ੂ': "ū"
161
- 'ृ': "ṛ"
162
-
163
-
164
- 'ੇ': "ē"
165
- 'ੈ': "ai"
166
-
167
-
168
- 'ੋ': 'ō'
169
- 'ੌ': 'au'
170
-
171
- '੍': ''
172
- '਼': ''
173
- 'ੱ': ''
174
- '।': '.'
175
- "‍": '' # no need for zero with joiner
@@ -1,170 +0,0 @@
1
- ---
2
- authority_id: bis
3
- id: 1991
4
- language: tel
5
- source_script: Telu
6
- destination_script: Latn
7
- name: Indian script code for information interchange - ISCII - Telegu Romanization
8
- #url:
9
- creation_date: 1991
10
- description: |
11
- IS 13194 (1991): Indian script code for information
12
- interchange - ISCII [LITD 20: Indian Language Technologies
13
- and Products]
14
-
15
- notes:
16
- - |
17
- Exception: Anusvāra is transliterated by:
18
-
19
- a) ṅ before gutturals,
20
- b) ñ before palatals,
21
- c) ṇ before cerebrals,
22
- d) n before dentals, and
23
- e) m before labials.
24
-
25
- tests:
26
- - source: "ఇప్పుడు ఇదే కోవలో టాలీవుడ్‌లో మరో మల్టీస్టారర్‌ రూపొందనుందని సినీ వర్గాల్లో వార్తలు వినిపిస్తున్నాయి"
27
- expected: "ippuḍu idē kŏvlŏ ṭālīvuḍlŏ mrŏ mlṭīsṭārr rūpondnundni sinī vrgāllŏ vārtlu vinipistunnāyi"
28
- - source: "అంటే ఉంటాయి, అయితే అవి చాలా పెద్దవై ఉండాల్సిన అవసరం లేదు అంటున్నారు మమ్ముట్టి"
29
- expected: "aṇṭē uṇṭāyi, ayitē avi cālā peddvai uṇḍālsin avsrṃ lēdu aṇṭunnāru mmmuṭṭi"
30
- - source: "ఆ సంతోషాన్ని అభిమానులతో పంచుకున్నారు"
31
- expected: "ā sntŏṣānni abhimānultŏ pñcukunnāru"
32
- - source: "కెమెరాను అన్‌బాక్స్‌ చేసే వీడియోను సోషల్‌ మీడియాలో అభిమానులతో పంచుకున్నారు"
33
- expected: "kemerānu anbāks cēsē vīḍiyŏnu sŏṣl mīḍiyālŏ abhimānultŏ pñcukunnāru"
34
- - source: "ఇన్నాళ్లకు నిజమయింది. ఇక ఇప్పటి నుంచి దీంతో ఫొటోలు క్లిక్‌ మనిపిస్తా’’ అని ఆ వీడియోలో పేర్కొన్నారు"
35
- expected: "innāḷlku nijmyindi. ik ippṭi nuñci dīntŏ phoṭŏlu klik mnipistā’’ ani ā vīḍiyŏlŏ pērkonnāru"
36
- - source: "గవర్నర్‌తో కంగనా భేటీ"
37
- expected: "gvrnrtŏ kṅgnā bhēṭī"
38
- - source: "శ్రియ సినిమా సెట్‌లో అడుగుపెట్టి ఆరు నెలలు కావొస్తోంది"
39
- expected: "śriy sinimā seṭlŏ aḍugupeṭṭi āru nellu kāvostŏndi"
40
- - source: "ఇప్పుడు తను కోరుకున్న కెమెరా చేతికి రావడంతో త్వరలో మమ్ముట్టి నుంచి స్టన్నింగ్‌ ఫొటోస్‌ రావడం ఖాయం అంటున్నారు ఆయన అభిమానులు"
41
- expected: "ippuḍu tnu kŏrukunn kemerā cētiki rāvḍntŏ tvrlŏ mmmuṭṭi nuñci sṭnniṅg phoṭŏs rāvḍṃ khāyṃ aṇṭunnāru āyn abhimānulu"
42
- - source: "ఇప్పుడు ఆ వీడియో వైరల్‌ అయింది. ‘ఆ కెమెరాను కొనాలనేది చాలాకాలంగా నా కల."
43
- expected: "ippuḍu ā vīḍiyŏ vairl ayindi. ‘ā kemerānu konālnēdi cālākālṅgā nā kl."
44
- - source: "మరో వైపు ఎన్టీఆర్‌, రామ్‌చరణ్‌ కలిసి ట్రిపుల్‌ ఆర్‌ సినిమాలో నటిస్తున్నారు"
45
- expected: "mrŏ vaipu enṭīār, rāmcrṇ klisi ṭripul ār sinimālŏ nṭistunnāru"
46
- map:
47
-
48
- rules:
49
- # note
50
- - pattern: \u0C02(?=[కఖగఘఙ])
51
- result: ṅ
52
- - pattern: \u0C02(?=[చఛజఝఞ])
53
- result: ñ
54
- - pattern: \u0C02(?=[టఠడఢణ])
55
- result: ṇ
56
- - pattern: \u0C02(?=[తథదధన])
57
- result: n
58
- - pattern: \u0C02(?=[పఫబభమ])
59
- result: m
60
-
61
-
62
- characters:
63
- 'అ': 'a'
64
- 'ఆ': 'ā'
65
- 'ఇ': 'i'
66
- 'ఈ': 'ī'
67
- 'ఉ': 'u'
68
- 'ఊ': 'ū'
69
- 'ఋ': 'ṛ'
70
- 'ఌ': 'ḻ'
71
- 'ౡ': 'ḻ'
72
- 'ఎ': 'e'
73
- 'ఏ': 'ē'
74
- 'ఐ': 'ai'
75
- 'ఒ': 'o'
76
- 'ఓ': 'ŏ'
77
- 'ఔ': 'au'
78
-
79
- # II. Consonants (see Note 2)
80
- # Gutturals క ఖ గ ఘ ఙ
81
- 'క': 'k'
82
- 'ఖ': 'kh'
83
- 'గ': 'g'
84
- 'ఘ': 'gh'
85
- 'ఙ': 'ṅ'
86
-
87
- # Palatals చ ఛ జ ఝ ఞ
88
- 'చ': 'c'
89
- 'ఛ': 'ch'
90
- 'జ': 'j'
91
- 'ఝ': 'jh'
92
- 'ఞ': 'ñ'
93
-
94
- # Cerebrals ట ఠ డ ఢ ణ
95
- 'ట': 'ṭ'
96
- 'ఠ': 'ṭh'
97
- 'డ': 'ḍ'
98
- 'ఢ': 'ḍh'
99
- 'ణ': 'ṇ'
100
-
101
- # Dentals త థ ద ధ న
102
- 'త': 't'
103
- #'ৎ': 't'
104
- 'థ': 'th'
105
- 'ద': 'd'
106
- 'ధ': 'dh'
107
- 'న': 'n'
108
-
109
- # Labials ప ఫ బ భ మ
110
- 'ప': 'p'
111
- 'ఫ': 'ph'
112
- 'బ': 'b'
113
- 'భ': 'bh'
114
- 'మ': 'm'
115
-
116
- # Semivowels య ర ల వ
117
- 'య': 'y'
118
- 'ర': 'r'
119
- 'ఱ': 'ṛ'
120
- 'ల': 'l'
121
- 'ళ': 'ḷ'
122
- 'వ': 'v'
123
-
124
- # Sibilants శ ష స హ
125
- 'శ': 'ś'
126
- 'ష': 'ṣ'
127
- 'స': 's'
128
-
129
-
130
-
131
- # Aspirate
132
- 'హ': 'h'
133
-
134
-
135
- 'క్ష': 'kṣa'
136
-
137
-
138
- # Chandrabindu
139
- 'ঁ': 'm'
140
-
141
- # Bisarga
142
- 'ః': 'ḥ'
143
-
144
- # Anusvāra
145
- 'ం': 'ṃ'
146
-
147
- # Medials # Needed for connecting constants
148
-
149
- 'ా': 'ā'
150
- 'ి': 'i'
151
- 'ీ': 'ī'
152
- 'ు': 'u'
153
- 'ూ': 'ū'
154
- 'ృ': 'ṛ'
155
- 'ె': 'e'
156
- 'ే': 'ē'
157
- 'ై': 'ai'
158
- 'ొ': 'o'
159
- 'ో': 'ŏ'
160
- 'ౌ': 'au'
161
- '\u09CD': '' # Used for joining
162
-
163
-
164
- '\u0c4d': '' #verma sign for halanta
165
- 'ౕ ': ''
166
- 'ౖ ': ''
167
- '्': ''
168
- '़': ''
169
- "‍": ''# Used for joining
170
- "‌": ''# Used for non joining