interscript 0.1.2 → 0.1.7

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 (261) hide show
  1. checksums.yaml +4 -4
  2. data/README.adoc +250 -17
  3. data/lib/g2pwrapper.py +34 -0
  4. data/lib/interscript.rb +142 -20
  5. data/lib/interscript/command.rb +28 -0
  6. data/lib/interscript/fs.rb +69 -0
  7. data/lib/interscript/mapping.rb +142 -0
  8. data/lib/interscript/opal.rb +57 -0
  9. data/lib/interscript/opal/entrypoint.rb +12 -0
  10. data/lib/interscript/opal/map_translate.rb +7 -0
  11. data/lib/interscript/opal/maps.js.erb +10 -0
  12. data/lib/interscript/version.rb +1 -1
  13. data/lib/model-7 +0 -0
  14. data/lib/tha-pt-b-7 +0 -0
  15. data/maps/acadsin-zho-Hani-Latn-2002.yaml +38916 -0
  16. data/maps/alalc-amh-Ethi-Latn-1997.yaml +513 -0
  17. data/maps/alalc-amh-Ethi-Latn-2011.yaml +138 -0
  18. data/maps/alalc-ara-Arab-Latn-1997.yaml +1287 -0
  19. data/maps/alalc-asm-Deva-Latn-1997.yaml +165 -0
  20. data/maps/alalc-asm-Deva-Latn-2012.yaml +40 -0
  21. data/maps/alalc-aze-Cyrl-Latn-1997.yaml +145 -0
  22. data/maps/alalc-bel-Cyrl-Latn-1997.yaml +129 -0
  23. data/maps/alalc-ben-Beng-Latn-2017.yaml +130 -0
  24. data/maps/alalc-bul-Cyrl-Latn-1997.yaml +98 -0
  25. data/maps/alalc-ell-Grek-Latn-1997.yaml +628 -0
  26. data/maps/alalc-ell-Grek-Latn-2010.yaml +626 -0
  27. data/maps/alalc-guj-Gujr-Latn-1997.yaml +266 -0
  28. data/maps/alalc-guj-Gujr-Latn-2011.yaml +64 -0
  29. data/maps/alalc-hin-Deva-Latn-1997.yaml +211 -0
  30. data/maps/alalc-hin-Deva-Latn-2011.yaml +47 -0
  31. data/maps/alalc-kat-Geok-Latn-1997.yaml +111 -0
  32. data/maps/alalc-kat-Geor-Latn-1997.yaml +150 -0
  33. data/maps/alalc-kor-Hang-Latn-1997.yaml +98 -0
  34. data/maps/alalc-mal-Mlym-Latn-1997.yaml +303 -0
  35. data/maps/alalc-mal-Mlym-Latn-2012.yaml +73 -0
  36. data/maps/alalc-mar-Deva-Latn-1997.yaml +189 -0
  37. data/maps/alalc-mar-Deva-Latn-2011.yaml +45 -0
  38. data/maps/alalc-mkd-Cyrl-Latn-1997.yaml +114 -0
  39. data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +103 -0
  40. data/maps/alalc-mon-Cyrl-Latn-1997.yaml +220 -0
  41. data/maps/alalc-pan-Guru-Latn-1997.yaml +256 -0
  42. data/maps/alalc-pan-Guru-Latn-2011.yaml +78 -0
  43. data/maps/alalc-per-Arab-Latn-1997.yaml +375 -0
  44. data/maps/alalc-pli-Deva-Latn-2012.yaml +144 -0
  45. data/maps/alalc-pra-Deva-Latn-2012.yaml +47 -0
  46. data/maps/alalc-rus-Cyrl-Latn-1997.yaml +225 -0
  47. data/maps/alalc-rus-Cyrl-Latn-2012.yaml +162 -0
  48. data/maps/alalc-san-Deva-Latn-2012.yaml +172 -0
  49. data/maps/alalc-sin-Sinh-Latn-1997.yaml +292 -0
  50. data/maps/alalc-sin-Sinh-Latn-2011.yaml +71 -0
  51. data/maps/alalc-srp-Cyrl-Latn-1997.yaml +118 -0
  52. data/maps/alalc-srp-Cyrl-Latn-2013.yaml +135 -0
  53. data/maps/alalc-tam-Taml-Latn-1997.yaml +62 -0
  54. data/maps/alalc-tam-Taml-Latn-2011.yaml +58 -0
  55. data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +145 -0
  56. data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +16 -0
  57. data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +283 -0
  58. data/maps/{bas-rus-Cyrl-Latn-bss.yaml → bas-rus-Cyrl-Latn-2017-bss.yaml} +58 -33
  59. data/maps/{bas-rus-Cyrl-Latn-oss.yaml → bas-rus-Cyrl-Latn-2017-oss.yaml} +55 -35
  60. data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +292 -0
  61. data/maps/bgn-kor-Hang-Latn-1943.yaml +35 -0
  62. data/maps/bgn-kor-Kore-Latn-1943.yaml +31 -0
  63. data/maps/bgna-bul-Cyrl-Latn-2006.yaml +208 -0
  64. data/maps/bgna-bul-Cyrl-Latn-2009.yaml +208 -0
  65. data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +532 -0
  66. data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +596 -0
  67. data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +2 -3
  68. data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +104 -0
  69. data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +188 -0
  70. data/maps/bgnpcgn-bel-Cyrl-Latn-1979.yaml +289 -0
  71. data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +119 -0
  72. data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +15 -65
  73. data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml +184 -0
  74. data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +705 -0
  75. data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +23 -0
  76. data/maps/{bgnpcgn-per-Arab-Latn-1956.yaml → bgnpcgn-fas-Arab-Latn-1956.yaml} +5 -2
  77. data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +257 -0
  78. data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +131 -0
  79. data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +42 -0
  80. data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +253 -0
  81. data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +48 -0
  82. data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +48 -0
  83. data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +163 -0
  84. data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +190 -0
  85. data/maps/bgnpcgn-mon-Cyrl-Latn-1964.yaml +223 -0
  86. data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +230 -0
  87. data/maps/bgnpcgn-per-Arab-Latn-1958.yaml +336 -0
  88. data/maps/bgnpcgn-prs-Arab-Latn-2007.yaml +639 -0
  89. data/maps/bgnpcgn-prs-Arab-Latn-yaghoubi.yaml +459 -0
  90. data/maps/bgnpcgn-rue-Cyrl-Latn-2016.yaml +168 -0
  91. data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +150 -65
  92. data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +170 -0
  93. data/maps/bgnpcgn-tat-Cyrl-Latn-2007.yaml +220 -0
  94. data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.yaml +240 -0
  95. data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +80 -4
  96. data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +119 -0
  97. data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.yaml +127 -0
  98. data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.yaml +82 -0
  99. data/maps/bgnpcgn-zho-Hans-Latn-1979.yaml +7456 -0
  100. data/maps/bis-asm-Beng-Latn-13194-1991.yaml +159 -0
  101. data/maps/bis-ben-Beng-Latn-13194-1991.yaml +156 -0
  102. data/maps/bis-dev-Deva-Latn-13194-1991.yaml +184 -0
  103. data/maps/bis-guj-Gujr-Latn-13194-1991.yaml +181 -0
  104. data/maps/bis-knd-Knda-Latn-13194-1991.yaml +173 -0
  105. data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +176 -0
  106. data/maps/bis-ori-Orya-Latn-13194-1991.yaml +160 -0
  107. data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +175 -0
  108. data/maps/bis-tel-Telu-Latn-13194-1991.yaml +170 -0
  109. data/maps/bis-tml-Taml-Latn-13194-1991.yaml +155 -0
  110. data/maps/by-bel-Cyrl-Latn-1998.yaml +172 -0
  111. data/maps/by-bel-Cyrl-Latn-2007.yaml +115 -0
  112. data/maps/din-grc-Grek-Latn-31634-2011-t1.yaml +899 -0
  113. data/maps/din-hin-Deva-Latn-33904-2018.yaml +100 -0
  114. data/maps/din-kat-Geor-Latn-32707-2010.yaml +145 -0
  115. data/maps/din-mar-Deva-Latn-33904-2018.yaml +84 -0
  116. data/maps/din-nep-Deva-Latn-33904-2018.yaml +119 -0
  117. data/maps/din-pli-Deva-Latn-33904-2018.yaml +75 -0
  118. data/maps/din-pra-Deva-Latn-33904-2018.yaml +63 -0
  119. data/maps/din-san-Deva-Latn-33904-2018.yaml +338 -0
  120. data/maps/din-tam-Taml-Latn-33903-2016.yaml +213 -0
  121. data/maps/dos-nep-Deva-Latn-1997.yaml +47 -0
  122. data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +684 -0
  123. data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +680 -0
  124. data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +19 -0
  125. data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +31 -0
  126. data/maps/ggg-kat-Geor-Latn-2002.yaml +92 -0
  127. data/maps/gki-bel-Cyrl-Latn-1992.yaml +33 -0
  128. data/maps/gki-bel-Cyrl-Latn-2000.yaml +201 -0
  129. data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml +190 -0
  130. data/maps/gost-rus-Cyrl-Latn-7.79-2000-2002.yaml +157 -0
  131. data/maps/hk-yue-Hani-Latn-1888.yaml +38497 -0
  132. data/maps/icao-bel-Cyrl-Latn-9303.yaml +109 -98
  133. data/maps/icao-bul-Cyrl-Latn-9303.yaml +2 -7
  134. data/maps/{icao-per-Arab-Latn-9303.yaml → icao-fas-Arab-Latn-9303.yaml} +6 -8
  135. data/maps/icao-heb-Hebr-Latn-9303.yaml +119 -125
  136. data/maps/icao-mkd-Cyrl-Latn-9303.yaml +2 -3
  137. data/maps/icao-rus-Cyrl-Latn-9303.yaml +2 -4
  138. data/maps/icao-srp-Cyrl-Latn-9303.yaml +2 -3
  139. data/maps/icao-ukr-Cyrl-Latn-9303.yaml +2 -4
  140. data/maps/iso-ara-Arab-Latn-233-1984.yaml +323 -0
  141. data/maps/iso-asm-Beng-Latn-15919-2001.yaml +75 -0
  142. data/maps/iso-ben-Beng-Latn-15919-2001.yaml +175 -0
  143. data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +613 -0
  144. data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +44 -0
  145. data/maps/iso-guj-Gujr-Latn-15919-2001.yaml +220 -0
  146. data/maps/iso-hin-Deva-Latn-15919-2001.yaml +87 -0
  147. data/maps/iso-inc-Deva-Latn-15919-2001.yaml +61 -0
  148. data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +66 -0
  149. data/maps/iso-kan-Knda-Latn-15919-2001.yaml +220 -0
  150. data/maps/iso-kat-Geor-Latn-9984-1996.yaml +145 -0
  151. data/maps/iso-kor-Hang-Latn-1996-method1.yaml +240 -0
  152. data/maps/iso-kor-Hang-Latn-1996-method2.yaml +226 -0
  153. data/maps/iso-mal-Mlym-Latn-15919-2001.yaml +281 -0
  154. data/maps/iso-mar-Deva-Latn-15919-2001.yaml +75 -0
  155. data/maps/iso-nep-Deva-Latn-15919-2001.yaml +87 -0
  156. data/maps/iso-ori-Orya-Latn-15919-2001.yaml +193 -0
  157. data/maps/iso-pan-Guru-Latn-15919-2001.yaml +222 -0
  158. data/maps/iso-pli-Beng-Latn-15919-2001.yaml +73 -0
  159. data/maps/iso-pli-Deva-Latn-15919-2001.yaml +74 -0
  160. data/maps/iso-pli-Sinh-Latn-15919-2001.yaml +219 -0
  161. data/maps/iso-pli-Thai-Latn-15919-2001.yaml +55 -0
  162. data/maps/iso-pra-Deva-Latn-15919-2001.yaml +59 -0
  163. data/maps/iso-prs-Arab-Latn-233-3-1999.yaml +366 -0
  164. data/maps/{iso-rus-Cyrl-Latn-iso9.yaml → iso-rus-Cyrl-Latn-9-1995.yaml} +4 -6
  165. data/maps/iso-san-Deva-Latn-15919-2001.yaml +220 -0
  166. data/maps/iso-tam-Taml-Latn-15919-2001.yaml +159 -0
  167. data/maps/iso-tel-Telu-Latn-15919-2001.yaml +220 -0
  168. data/maps/iso-tha-Thai-Latn-11940-1998.yaml +109 -0
  169. data/maps/kp-kor-Hang-Latn-2002.yaml +909 -0
  170. data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +44820 -0
  171. data/maps/mext-jpn-Hrkt-Latn-1954.yaml +411 -0
  172. data/maps/mns-mon-Cyrl-Latn-5217-2012.yaml +163 -0
  173. data/maps/mns-mon-Latn-Cyrl-5217-2012.yaml +200 -0
  174. data/maps/moct-kor-Hang-Latn-2000.yaml +807 -0
  175. data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +541 -0
  176. data/maps/mvd-bel-Cyrl-Latn-2008.yaml +225 -0
  177. data/maps/mvd-bel-Cyrl-Latn-2010.yaml +63 -0
  178. data/maps/mvd-rus-Cyrl-Latn-2008.yaml +109 -0
  179. data/maps/mvd-rus-Cyrl-Latn-2010.yaml +37 -0
  180. data/maps/odni-ara-Arab-Latn-2015.yaml +425 -0
  181. data/maps/odni-aze-Cyrl-Latn-2015.yaml +144 -0
  182. data/maps/odni-bel-Cyrl-Latn-2015.yaml +148 -0
  183. data/maps/odni-bul-Cyrl-Latn-2015.yaml +96 -0
  184. data/maps/odni-che-Cyrl-Latn-2015.yaml +169 -0
  185. data/maps/odni-fas-Arab-Latn-2015.yaml +406 -0
  186. data/maps/odni-hin-Deva-Latn-2015.yaml +258 -0
  187. data/maps/odni-kat-Geor-Latn-2015.yaml +87 -0
  188. data/maps/odni-kaz-Cyrl-Latn-2015.yaml +148 -0
  189. data/maps/odni-kir-Cyrl-Latn-2015.yaml +136 -0
  190. data/maps/odni-kor-Hang-Latn-2015.yaml +375 -0
  191. data/maps/odni-mkd-Cyrl-Latn-2015.yaml +122 -0
  192. data/maps/odni-per-Arab-Latn-2015.yaml +228 -0
  193. data/maps/odni-rus-Cyrl-Latn-2015.yaml +77 -0
  194. data/maps/odni-srp-Cyrl-Latn-2015.yaml +129 -0
  195. data/maps/odni-tat-Cyrl-Latn-2015.yaml +142 -0
  196. data/maps/odni-tgk-Cyrl-Latn-2015.yaml +148 -0
  197. data/maps/odni-uig-Cyrl-Latn-2015.yaml +138 -0
  198. data/maps/odni-ukr-Cyrl-Latn-2015.yaml +157 -0
  199. data/maps/odni-urd-Arab-Latn-2015.yaml +221 -0
  200. data/maps/odni-uzb-Cyrl-Latn-2015.yaml +166 -0
  201. data/maps/royin-tha-Thai-Latn-1939-generic.yaml +90 -0
  202. data/maps/royin-tha-Thai-Latn-1968.yaml +183 -0
  203. data/maps/royin-tha-Thai-Latn-1999-chained.yaml +180 -0
  204. data/maps/royin-tha-Thai-Latn-1999.yaml +80 -0
  205. data/maps/{cn-chn-Hans-Latn-pinyin.yaml → sac-zho-Hans-Latn-1979.yaml} +11 -8
  206. data/maps/sasm-mon-Mong-Latn-general-1978.yaml +389 -0
  207. data/maps/sasm-mon-Mong-Latn-phonetic-1978.yaml +354 -0
  208. data/maps/ses-ara-Arab-Latn-1930.yaml +283 -0
  209. data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +222 -0
  210. data/maps/ua-ukr-Cyrl-Latn-1996.yaml +197 -0
  211. data/maps/ua-ukr-Cyrl-Latn-2007.yaml +75 -0
  212. data/maps/ua-ukr-Cyrl-Latn-2010.yaml +192 -0
  213. data/maps/un-amh-Ethi-Latn-2016.yaml +602 -0
  214. data/maps/un-ara-Arab-Latn-1971.yaml +139 -0
  215. data/maps/un-ara-Arab-Latn-1972.yaml +159 -0
  216. data/maps/un-ara-Arab-Latn-2017.yaml +420 -0
  217. data/maps/un-bel-Cyrl-Latn-2007.yaml +114 -0
  218. data/maps/un-ben-Beng-Latn-2016.yaml +534 -0
  219. data/maps/un-ell-Grek-Latn-1987-phonetic.yaml +780 -0
  220. data/maps/un-ell-Grek-Latn-1987-tl.yaml +31 -0
  221. data/maps/un-ell-Grek-Latn-1987-ts.yaml +19 -0
  222. data/maps/un-hin-Deva-Latn-2016.yaml +222 -0
  223. data/maps/un-mar-Deva-Latn-2016.yaml +91 -0
  224. data/maps/un-mon-Mong-Latn-general-2013.yaml +264 -0
  225. data/maps/un-mon-Mong-Latn-phonetic-2013.yaml +264 -0
  226. data/maps/un-nep-Deva-Latn-1972.yaml +350 -0
  227. data/maps/un-nep-Deva-Latn-2013.yaml +74 -0
  228. data/maps/un-rus-Cyrl-Latn-1987.yaml +166 -0
  229. data/maps/un-ukr-Cyrl-Latn-1998.yaml +53 -0
  230. data/maps/un-ukr-Cyrl-Latn-2012.yaml +162 -0
  231. data/maps/var-hin-Deva-Latn-hunterian-1872.yaml +221 -0
  232. data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +406 -0
  233. data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +386 -0
  234. data/maps/var-kor-Hang-Hang-jamo.yaml +11193 -0
  235. data/maps/var-kor-Hang-Latn-mr-1939.yaml +1054 -0
  236. data/maps/var-kor-Kore-Hang-2013.yaml +59754 -0
  237. data/maps/var-kor-Kore-Latn-mr-1939.yaml +36 -0
  238. data/maps/var-mar-Deva-Latn-hunterian-1872.yaml +43 -0
  239. data/maps/var-mon-Mong-Latn-1930.yaml +102 -0
  240. data/maps/var-mon-Mong-Latn-lessing.yaml +272 -0
  241. data/maps/var-mon-Mong-Latn-vpmc.yaml +274 -0
  242. data/maps/var-pra-Deva-Latn-iast-1912.yaml +30 -0
  243. data/maps/var-san-Deva-Latn-iast-1912.yaml +149 -0
  244. data/maps/var-tha-Thai-Thai-phonemic.yaml +59 -0
  245. data/maps/var-tha-Thai-Zsym-ipa.yaml +301 -0
  246. data/maps/var-zho-Hani-Latn-wd-1979.yaml +38912 -0
  247. data/spec/interscript/filenames_spec.rb +384 -0
  248. data/spec/interscript/mapping_spec.rb +42 -0
  249. data/spec/interscript_spec.rb +23 -5
  250. data/spec/spec_helper.rb +3 -1
  251. metadata +364 -34
  252. data/bin/interscript +0 -20
  253. data/bin/rspec +0 -29
  254. data/maps/bgnpcgn-chn-Hans-Latn-pinyin.yaml +0 -7503
  255. data/maps/historic-jpn-Hrkt-Latn-hepburn.yaml +0 -336
  256. data/maps/icao-gre-Grek-Latn-9303.yaml +0 -101
  257. data/maps/mext-jpn-Hrkt-Latn-hepburn.yaml +0 -330
  258. data/maps/mext-jpn-Hrkt-Latn-kunrei.yaml +0 -308
  259. data/maps/un-jpn-Hrkt-Latn-hepburn.yaml +0 -313
  260. data/maps/un-jpn-Hrkt-Latn-kunrei.yaml +0 -354
  261. data/maps/un-mon-Mong-Latn-2013.yaml +0 -80
@@ -0,0 +1,909 @@
1
+ ---
2
+ authority_id: kp
3
+ id: 2002
4
+ language: iso-639-2:kor
5
+ source_script: Hang
6
+ destination_script: Latn
7
+ name: Korean Democratic People's Republic of Korea Korean System (2002)
8
+ alias:
9
+ ogc11122:
10
+ code: kor_Hang2Latn_GKN_2002
11
+ description: Korean Democratic People's Republic of Korea Korean 2002 System
12
+ url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/8th-uncsgn-docs/inf/8th_UNCSGN_econf.94_INF.72.pdf
13
+ creation_date:
14
+ adoption_date:
15
+ description:
16
+
17
+ notes:
18
+
19
+ - Here is a list of features that are listed in the guideline but
20
+ not unimplemented in this map.
21
+
22
+ - Note 3.2
23
+ The combination n+r is romanized as -ll- only when it is "considered
24
+ to be longstanding". In this implementation, all n+r will be romanized as
25
+ -ll- for the sake of simplicity.
26
+
27
+ - Note 3.3
28
+ Sai-siot (Connective ㅅ) is not written out in DPRK Korean, but it is
29
+ supposed to be romanized. Sai-siot is not predictable.
30
+ This has not been implemented.
31
+
32
+ - Note 4.1
33
+ Hyphen "may be inserted in case of a possible confusion in pronunciation".
34
+ Except for the n-g combination, this has not been implemented.
35
+
36
+ - Note 4.4
37
+ Geographical names "may be transliterated or translated". In this map,
38
+ all names will be transliterated, not translated. Numerals will not be
39
+ transliterated.
40
+
41
+ - Note 4.5
42
+ Spacing rule for personal names has not been implemented.
43
+
44
+ - Note 4.7
45
+ Optional omission of diacritics and optional simplification of
46
+ KK, TT, PP, SS, JJ to single letter have not been implemented.
47
+
48
+ tests:
49
+ # Note1.5
50
+ - source: "우리산"
51
+ expected: "Urisan"
52
+
53
+ # Note2.1
54
+ - source: "교구동"
55
+ expected: "Kyogu-dong"
56
+ - source: "초도"
57
+ expected: "Chodo"
58
+ - source: "고비리"
59
+ expected: "Kobi-ri"
60
+ - source: "강동"
61
+ expected: "Kangdong"
62
+ - source: "금교"
63
+ expected: "Kümgyo"
64
+ - source: "칠보산"
65
+ expected: "Chilbosan"
66
+
67
+ # Note2.2
68
+ - source: "곡산"
69
+ expected: "Koksan"
70
+ - source: "갑산"
71
+ expected: "Kapsan"
72
+ - source: "앞산"
73
+ expected: "Apsan"
74
+ - source: "삿갓봉"
75
+ expected: "Satkatbong"
76
+
77
+ # Note2.3
78
+ - source: "울산"
79
+ expected: "Ulsan"
80
+ # - source: "은률"
81
+ # expected: "Ünryul" # This is an exceptino to note 3.1
82
+
83
+ # Note2.4
84
+ - source: "닭섬"
85
+ expected: "Taksŏm"
86
+ - source: "물곬"
87
+ expected: "Mulkol"
88
+ - source: "붉은바위"
89
+ expected: "Pulgünbawi"
90
+ - source: "앉은바위"
91
+ expected: "Anjünbawi"
92
+
93
+ # Note3.1
94
+ - source: "백마산"
95
+ expected: "Paengmasan"
96
+ - source: "꽃마을"
97
+ expected: "Kkonmaül"
98
+ - source: "압록강"
99
+ expected: "Amrokgang"
100
+
101
+ # Note3.2
102
+ - source: "천리마"
103
+ expected: "Chŏllima"
104
+ # - source: "한나산" # Typo in the original document
105
+ - source: "한라산"
106
+ expected: "Hallasan"
107
+ - source: "전라도"
108
+ expected: "Jŏlla-do"
109
+
110
+ # Note3.3
111
+
112
+ # - source: "기대산" # ROK: 깃대산
113
+ # expected: "Kittaesan"
114
+ # - source: "새별읍" # ROK: 샛별
115
+ # expected: "Saeppyŏl-üp" # hyphen
116
+ # - source: "뒤문" # ROK: 뒷문
117
+ # expected: "Twinmun"
118
+
119
+ # Note4.1 - Separator (OPTIONAL)
120
+
121
+ - source: "앞-언덕"
122
+ expected: "Ap-ŏndŏk"
123
+ - source: "부억-안골"
124
+ expected: "Puŏk-angol"
125
+ - source: "판교"
126
+ expected: "Phan-gyo"
127
+ # - source: "방어동"
128
+ # expected: "Pang-ŏ-dong"
129
+
130
+ # Note4.2
131
+ - source: "평안남도 평성시"
132
+ expected: "Phyŏngannam-do Phyŏngsŏng-si"
133
+
134
+ # Note4.3
135
+ - source: "3.1동"
136
+ expected: "3.1-dong"
137
+
138
+ # Note4.6
139
+ - source: "평양"
140
+ expected: "Pyongyang"
141
+
142
+ # Fix a problem with a trailing comma
143
+ - source: "구현, 글꼴, 문자 배열, 다국어 컴퓨팅."
144
+ expected: "Kuhyŏn, Külkkol, Munja Paeyŏl, Tagugŏ Khŏmphyuthing."
145
+
146
+ map:
147
+ character_separator: ""
148
+ word_separator: " "
149
+ title_case: True
150
+ inherit: "var-kor-Hang-Hang-jamo"
151
+
152
+ rules:
153
+
154
+ # This system does not require transliteration of numerals
155
+ # convert numbers to space + Hangul
156
+ # - pattern: "([^0-9 ])(?=[0-9])"
157
+ # result: "\\1 "
158
+ # - pattern: "1"
159
+ # result: "일"
160
+ # - pattern: "2"
161
+ # result: "이"
162
+ # - pattern: "3"
163
+ # result: "삼"
164
+ # - pattern: "4"
165
+ # result: "사"
166
+ # - pattern: "5"
167
+ # result: "오"
168
+ # - pattern: "6"
169
+ # result: "육"
170
+ # - pattern: "7"
171
+ # result: "칠"
172
+ # - pattern: "8"
173
+ # result: "팔"
174
+ # - pattern: "9"
175
+ # result: "구"
176
+
177
+ # Use voiced onset for geographical features
178
+ # Note 4.3.1
179
+ - pattern: "(?<=..)산( |$)"
180
+ result: "san\\1"
181
+ - pattern: "(?<=..)거리( |$)"
182
+ result: "gŏri\\1"
183
+ - pattern: "(?<=..)고개( |$)"
184
+ result: "gogae\\1"
185
+ - pattern: "(?<=..)대( |$)"
186
+ result: "dae\\1"
187
+ - pattern: "(?<=..)봉( |$)"
188
+ result: "bong\\1"
189
+ - pattern: "(?<=..)교( |$)"
190
+ result: "gyo\\1"
191
+ - pattern: "(?<=..)골( |$)"
192
+ result: "gol\\1"
193
+ - pattern: "(?<=..)각( |$)"
194
+ result: "gak\\1"
195
+ - pattern: "(?<=..)벌( |$)"
196
+ result: "bŏl\\1"
197
+ - pattern: "(?<=..)관( |$)"
198
+ result: "gwan\\1"
199
+ - pattern: "(?<=..)곶( |$)"
200
+ result: "got\\1"
201
+ - pattern: "(?<=..)강( |$)"
202
+ result: "gang\\1"
203
+
204
+ # add hyphen in front of generics
205
+ # Only add hyphen if the name is three syllables or longer
206
+ - pattern: "(?<=..)도( |$)"
207
+ result: "-do\\1"
208
+ - pattern: "(?<=..)시( |$)"
209
+ result: "-si\\1"
210
+ - pattern: "(?<=..)군( |$)"
211
+ result: "-gun\\1"
212
+ - pattern: "(?<=..)면( |$)"
213
+ result: "-myŏn\\1"
214
+ - pattern: "(?<=..)리( |$)"
215
+ result: "-ri\\1"
216
+ - pattern: "(?<=..)동( |$)"
217
+ result: "-dong\\1"
218
+ - pattern: "(?<=..)구( |$)"
219
+ result: "-gu\\1"
220
+ - pattern: "(?<=..)구역( |$)"
221
+ result: "-guyŏk\\1"
222
+
223
+ # The name Pyongyang will be an exception
224
+ # Not Phyŏngyang
225
+
226
+ - pattern: "평양"
227
+ result: "Pyongyang"
228
+
229
+ postrules:
230
+
231
+ # Add space to the two ends of the string for easier word boundary handling
232
+ - pattern: "^"
233
+ result: " "
234
+ - pattern: "$"
235
+ result: " "
236
+
237
+ # HANGUL JONGSEONG SSANGKIYEOK
238
+ - pattern: "ᆩᄋ"
239
+ result: "ᆨᄁ"
240
+ - pattern: "ᆩ"
241
+ result: "ᆨ"
242
+
243
+ # HANGUL JONGSEONG SSANGKIYEOK
244
+ - pattern: "ᆪᄋ"
245
+ result: "ᆨᄉ"
246
+ - pattern: "ᆪ"
247
+ result: "ᆨ"
248
+
249
+ # HANGUL JONGSEONG NIEUN-CIEUC
250
+ - pattern: "ᆬᄋ"
251
+ result: "ᆫᄌ"
252
+ - pattern: "ᆬ"
253
+ result: "ᆫ"
254
+
255
+ # HANGUL JONGSEONG NIEUN-CIEUC
256
+ - pattern: "ᆭᄀ"
257
+ result: "ᆫᄏ"
258
+ - pattern: "ᆭᄃ"
259
+ result: "ᆫᄐ"
260
+ - pattern: "ᆭᄇ"
261
+ result: "ᆫᄑ"
262
+ - pattern: "ᆭᄌ"
263
+ result: "ᆫᄎ"
264
+ - pattern: "ᆭ"
265
+ result: "ᆫ"
266
+
267
+ # HANGUL JONGSEONG TIEUT
268
+ - pattern: "ᆮ(?=[ᄀᄁᄂᄃᄄᄅᄆᄇᄈᄉᄊᄌᄍᄎᄏᄐᄑᄒ])"
269
+ result: "ᆺ"
270
+
271
+ # HANGUL JONGSEONG RIEUL-SIOS
272
+ - pattern: "ᆳᄋ"
273
+ result: "ᆯᄉ"
274
+ - pattern: "ᆳ"
275
+ result: "ᆯ"
276
+
277
+ # HANGUL JONGSEONG RIEUL-THIEUTH
278
+ - pattern: "ᆴᄋ"
279
+ result: "ᆯᄐ"
280
+ - pattern: "ᆴ"
281
+ result: "ᆯ"
282
+
283
+ # HANGUL JONGSEONG RIEUL-PHIEUPH
284
+ - pattern: "ᆵᄋ"
285
+ result: "ᆯᄑ"
286
+ - pattern: "ᆵ(?=[ᄃᄄᄐ])"
287
+ result: "ᆯ"
288
+ - pattern: "ᆵ"
289
+ result: "ᄇ"
290
+
291
+ # HANGUL JONGSEONG RIEUL-HIEUH
292
+ - pattern: "ᆶᄀ"
293
+ result: "ᆯᄏ"
294
+ - pattern: "ᆶᄃ"
295
+ result: "ᆯᄐ"
296
+ - pattern: "ᆶᄇ"
297
+ result: "ᆯᄑ"
298
+ - pattern: "ᆶᄌ"
299
+ result: "ᆯᄎ"
300
+ - pattern: "ᆶ"
301
+ result: "ᆯ"
302
+
303
+ # HANGUL JONGSEONG PIEUP-SIOS
304
+ - pattern: "ᆹᄋ"
305
+ result: "ᄇᄉ"
306
+ - pattern: "ᆹ"
307
+ result: "ᄇ"
308
+
309
+ # HANGUL JONGSEONG SSANG-SIOS
310
+ - pattern: "ᆻᄋ"
311
+ result: "ᆺᄊ"
312
+ - pattern: "ᆻ"
313
+ result: "ᆺ"
314
+
315
+ # HANGUL JONGSEONG CIEUC
316
+ - pattern: "ᆽᄋ"
317
+ result: "ᆺᄌ"
318
+ - pattern: "ᆽ"
319
+ result: "ᆺ"
320
+
321
+ # HANGUL JONGSEONG CHIEUCH
322
+ - pattern: "ᆾᄋ"
323
+ result: "ᆺᄎ"
324
+ - pattern: "ᆾ"
325
+ result: "ᆺ"
326
+
327
+ # HANGUL JONGSEONG KHIEUKH
328
+ - pattern: "ᆿᄋ"
329
+ result: "ᆨᄏ"
330
+ - pattern: "ᆿ"
331
+ result: "ᆨ"
332
+
333
+ # HANGUL JONGSEONG THIEUTH
334
+ - pattern: "ᇀᄋ"
335
+ result: "ᆺᄐ"
336
+ - pattern: "ᇀ"
337
+ result: "ᆺ"
338
+
339
+ # HANGUL JONGSEONG PHIEUPH
340
+ - pattern: "ᇁᄋ"
341
+ result: "ᆸᄑ"
342
+ - pattern: "ᇁ"
343
+ result: "ᆸ"
344
+
345
+ # HANGUL JONGSEONG HIEUH
346
+ - pattern: "ᇂᄀ"
347
+ result: "ᄏ"
348
+ - pattern: "ᇂᄃ"
349
+ result: "ᄐ"
350
+ - pattern: "ᇂᄇ"
351
+ result: "ᄑ"
352
+ - pattern: "ᇂᄌ"
353
+ result: "ᄎ"
354
+ - pattern: "ᇂ"
355
+ result: ""
356
+
357
+ # From Unicode Chart
358
+ # https://github.com/unicode-org/cldr/blob/master/common/transforms/Korean-Latin-BGN.xml
359
+ - pattern: "ᆨᄀ"
360
+ result: "kk" # HANGUL JONGSEONG KIYEOK + CHOSEONG KIYEOK
361
+ - pattern: "ᆨᄂ"
362
+ result: "ngn" # HANGUL JONGSEONG KIYEOK + CHOSEONG NIEUN
363
+ - pattern: "ᆨᄃ"
364
+ result: "kt" # HANGUL JONGSEONG KIYEOK + CHOSEONG TIEUT
365
+ - pattern: "ᆨᄅ"
366
+ result: "ngn" # HANGUL JONGSEONG KIYEOK + CHOSEONG RIEUL
367
+ - pattern: "ᆨᄆ"
368
+ result: "ngm" # HANGUL JONGSEONG KIYEOK + CHOSEONG MIEUM
369
+ - pattern: "ᆨᄇ"
370
+ result: "kp" # HANGUL JONGSEONG KIYEOK + CHOSEONG PIEUP
371
+ - pattern: "ᆨᄉ"
372
+ result: "ks" # HANGUL JONGSEONG KIYEOK + CHOSEONG SIOS
373
+ - pattern: "ᆨᄋ"
374
+ result: "g" # HANGUL JONGSEONG KIYEOK + CHOSEONG IEUNG
375
+ - pattern: "ᆨᄌ"
376
+ result: "kj" # HANGUL JONGSEONG KIYEOK + CHOSEONG CIEUC
377
+ - pattern: "ᆨᄎ"
378
+ result: "kch" # HANGUL JONGSEONG KIYEOK + CHOSEONG CHIEUCH
379
+ - pattern: "ᆨᄏ"
380
+ result: "kkh" # HANGUL JONGSEONG KIYEOK + CHOSEONG KHIEUKH # NOTE: the dash is always skipped
381
+ - pattern: "ᆨᄐ"
382
+ result: "kth" # HANGUL JONGSEONG KIYEOK + CHOSEONG THIEUTH
383
+ - pattern: "ᆨᄑ"
384
+ result: "kp" # HANGUL JONGSEONG KIYEOK + CHOSEONG PHIEUPH
385
+ - pattern: "ᆨᄒ"
386
+ result: "kh" # HANGUL JONGSEONG KIYEOK + CHOSEONG HIEUH
387
+ - pattern: "ᆨᄁ"
388
+ result: "kkk" # HANGUL JONGSEONG KIYEOK + CHOSEONG SSANGKIYEOK
389
+ - pattern: "ᆨᄄ"
390
+ result: "ktt" # HANGUL JONGSEONG KIYEOK + CHOSEONG SSANGTIEUT
391
+ - pattern: "ᆨᄈ"
392
+ result: "kpp" # HANGUL JONGSEONG KIYEOK + CHOSEONG SSANGPIEUP
393
+ - pattern: "ᆨᄊ"
394
+ result: "kss" # HANGUL JONGSEONG KIYEOK + CHOSEONG SSANGSIOS
395
+ - pattern: "ᆨᄍ"
396
+ result: "kjj" # HANGUL JONGSEONG KIYEOK + CHOSEONG SSANGCIEUC
397
+ - pattern: "ᆫᄀ"
398
+ result: "n-g" # HANGUL JONGSEONG NIEUN + CHOSEONG KIEUK
399
+ - pattern: "ᆫᄂ"
400
+ result: "nn" # HANGUL JONGSEONG NIEUN + CHOSEONG NIEUN
401
+ - pattern: "ᆫᄃ"
402
+ result: "nd" # HANGUL JONGSEONG NIEUN + CHOSEONG TIEUT
403
+ - pattern: "ᆫᄅ"
404
+ result: "ll" # HANGUL JONGSEONG NIEUN + CHOSEONG RIEUL
405
+ - pattern: "ᆫᄆ"
406
+ result: "nm" # HANGUL JONGSEONG NIEUN + CHOSEONG MIEUM
407
+ - pattern: "ᆫᄇ"
408
+ result: "nb" # HANGUL JONGSEONG NIEUN + CHOSEONG PIEUP
409
+ - pattern: "ᆫᄉ"
410
+ result: "ns" # HANGUL JONGSEONG NIEUN + CHOSEONG SIOS
411
+ - pattern: "ᆫᄋ"
412
+ result: "n" # HANGUL JONGSEONG NIEUN + CHOSEONG IEUNG
413
+ - pattern: "ᆫᄌ"
414
+ result: "nj" # HANGUL JONGSEONG NIEUN + CHOSEONG CIEUC
415
+ - pattern: "ᆫᄎ"
416
+ result: "nch" # HANGUL JONGSEONG NIEUN + CHOSEONG CHIEUCH
417
+ - pattern: "ᆫᄏ"
418
+ result: "nkh" # HANGUL JONGSEONG NIEUN + CHOSEONG KHIEUKH
419
+ - pattern: "ᆫᄐ"
420
+ result: "nth" # HANGUL JONGSEONG NIEUN + CHOSEONG THIEUTH
421
+ - pattern: "ᆫᄑ"
422
+ result: "nph" # HANGUL JONGSEONG NIEUN + CHOSEONG PHIEUPH
423
+ - pattern: "ᆫᄒ"
424
+ result: "nh" # HANGUL JONGSEONG NIEUN + CHOSEONG HIEUH
425
+ - pattern: "ᆫᄁ"
426
+ result: "nkk" # HANGUL JONGSEONG NIEUN + CHOSEONG SSANGKIYEOK
427
+ - pattern: "ᆫᄄ"
428
+ result: "ntt" # HANGUL JONGSEONG NIEUN + CHOSEONG SSANGTIEUT
429
+ - pattern: "ᆫᄈ"
430
+ result: "npp" # HANGUL JONGSEONG NIEUN + CHOSEONG SSANGPIEUP
431
+ - pattern: "ᆫᄊ"
432
+ result: "nss" # HANGUL JONGSEONG NIEUN + CHOSEONG SSANGSIOS
433
+ - pattern: "ᆫᄍ"
434
+ result: "njj" # HANGUL JONGSEONG NIEUN + CHOSEONG SSANGCIEUC
435
+ - pattern: "ᆯᄀ"
436
+ result: "lk" # HANGUL JONGSEONG RIEUL + CHOSEONG KIYEOK
437
+ - pattern: "ᆯᄂ"
438
+ result: "ll" # HANGUL JONGSEONG RIEUL + CHOSEONG NIEUN
439
+ - pattern: "ᆯᄃ"
440
+ result: "lt" # HANGUL JONGSEONG RIEUL + CHOSEONG TIEUT
441
+ - pattern: "ᆯᄅ"
442
+ result: "ll" # HANGUL JONGSEONG RIEUL + CHOSEONG RIEUL
443
+ - pattern: "ᆯᄆ"
444
+ result: "lm" # HANGUL JONGSEONG RIEUL + CHOSEONG MIEUM
445
+ - pattern: "ᆯᄇ"
446
+ result: "lb" # HANGUL JONGSEONG RIEUL + CHOSEONG PIEUP
447
+ - pattern: "ᆯᄉ"
448
+ result: "ls" # HANGUL JONGSEONG RIEUL + CHOSEONG SIOS
449
+ - pattern: "ᆯᄋ"
450
+ result: "r" # HANGUL JONGSEONG RIEUL + CHOSEONG IEUNG
451
+ - pattern: "ᆯᄌ"
452
+ result: "lj" # HANGUL JONGSEONG RIEUL + CHOSEONG CIEUC
453
+ - pattern: "ᆯᄎ"
454
+ result: "lch" # HANGUL JONGSEONG RIEUL + CHOSEONG CHIEUCH
455
+ - pattern: "ᆯᄏ"
456
+ result: "lkh" # HANGUL JONGSEONG RIEUL + CHOSEONG KHIEUKH
457
+ - pattern: "ᆯᄐ"
458
+ result: "lth" # HANGUL JONGSEONG RIEUL + CHOSEONG THIEUTH
459
+ - pattern: "ᆯᄑ"
460
+ result: "lph" # HANGUL JONGSEONG RIEUL + CHOSEONG PHIEUPH
461
+ - pattern: "ᆯᄒ"
462
+ result: "lh" # HANGUL JONGSEONG RIEUL + CHOSEONG HIEUH
463
+ - pattern: "ᆯᄁ"
464
+ result: "lkk" # HANGUL JONGSEONG RIEUL + CHOSEONG SSANGKIYEOK
465
+ - pattern: "ᆯᄄ"
466
+ result: "ltt" # HANGUL JONGSEONG RIEUL + CHOSEONG SSANGTIEUT
467
+ - pattern: "ᆯᄈ"
468
+ result: "lpp" # HANGUL JONGSEONG RIEUL + CHOSEONG SSANGPIEUP
469
+ - pattern: "ᆯᄊ"
470
+ result: "lss" # HANGUL JONGSEONG RIEUL + CHOSEONG SSANGSIOS
471
+ - pattern: "ᆯᄍ"
472
+ result: "ljj" # HANGUL JONGSEONG RIEUL + CHOSEONG SSANGCIEUC
473
+ - pattern: "ᆷᄀ"
474
+ result: "mg" # HANGUL JONGSEONG MIEUM + CHOSEONG KIYEOK
475
+ - pattern: "ᆷᄂ"
476
+ result: "mn" # HANGUL JONGSEONG MIEUM + CHOSEONG NIEUN
477
+ - pattern: "ᆷᄃ"
478
+ result: "md" # HANGUL JONGSEONG MIEUM + CHOSEONG TIEUT
479
+ - pattern: "ᆷᄅ"
480
+ result: "mr" # HANGUL JONGSEONG MIEUM + CHOSEONG RIEUL # Note 3.1
481
+ - pattern: "ᆷᄆ"
482
+ result: "mm" # HANGUL JONGSEONG MIEUM + CHOSEONG MIEUM
483
+ - pattern: "ᆷᄇ"
484
+ result: "mb" # HANGUL JONGSEONG MIEUM + CHOSEONG PIEUP
485
+ - pattern: "ᆷᄉ"
486
+ result: "ms" # HANGUL JONGSEONG MIEUM + CHOSEONG SIOS
487
+ - pattern: "ᆷᄋ"
488
+ result: "m" # HANGUL JONGSEONG MIEUM + CHOSEONG IEUNG
489
+ - pattern: "ᆷᄌ"
490
+ result: "mj" # HANGUL JONGSEONG MIEUM + CHOSEONG CIEUC
491
+ - pattern: "ᆷᄎ"
492
+ result: "mch" # HANGUL JONGSEONG MIEUM + CHOSEONG CHIEUCH
493
+ - pattern: "ᆷᄏ"
494
+ result: "mkh" # HANGUL JONGSEONG MIEUM + CHOSEONG KHIEUKH
495
+ - pattern: "ᆷᄐ"
496
+ result: "mth" # HANGUL JONGSEONG MIEUM + CHOSEONG THIEUTH
497
+ - pattern: "ᆷᄑ"
498
+ result: "mph" # HANGUL JONGSEONG MIEUM + CHOSEONG PHIEUPH
499
+ - pattern: "ᆷᄒ"
500
+ result: "mh" # HANGUL JONGSEONG MIEUM + CHOSEONG HIEUH
501
+ - pattern: "ᆷᄁ"
502
+ result: "mkk" # HANGUL JONGSEONG MIEUM + CHOSEONG SSANGKIYEOK
503
+ - pattern: "ᆷᄄ"
504
+ result: "mtt" # HANGUL JONGSEONG MIEUM + CHOSEONG SSANGTIEUT
505
+ - pattern: "ᆷᄈ"
506
+ result: "mpp" # HANGUL JONGSEONG MIEUM + CHOSEONG SSANGPIEUP
507
+ - pattern: "ᆷᄊ"
508
+ result: "mss" # HANGUL JONGSEONG MIEUM + CHOSEONG SSANGSIOS
509
+ - pattern: "ᆷᄍ"
510
+ result: "mjj" # HANGUL JONGSEONG MIEUM + CHOSEONG SSANGCIEUC
511
+ - pattern: "ᆸᄀ"
512
+ result: "pk" # HANGUL JONGSEONG PIEUP + CHOSEONG KIYEOK
513
+ - pattern: "ᆸᄂ"
514
+ result: "mn" # HANGUL JONGSEONG PIEUP + CHOSEONG NIEUN
515
+ - pattern: "ᆸᄃ"
516
+ result: "pt" # HANGUL JONGSEONG PIEUP + CHOSEONG TIEUT
517
+ - pattern: "ᆸᄅ"
518
+ result: "mr" # HANGUL JONGSEONG PIEUP + CHOSEONG RIEUL
519
+ - pattern: "ᆸᄆ"
520
+ result: "mm" # HANGUL JONGSEONG PIEUP + CHOSEONG MIEUM
521
+ - pattern: "ᆸᄇ"
522
+ result: "pp" # HANGUL JONGSEONG PIEUP + CHOSEONG PIEUP
523
+ - pattern: "ᆸᄉ"
524
+ result: "ps" # HANGUL JONGSEONG PIEUP + CHOSEONG SIOS
525
+ - pattern: "ᆸᄋ"
526
+ result: "b" # HANGUL JONGSEONG PIEUP + CHOSEONG IEUNG
527
+ - pattern: "ᆸᄌ"
528
+ result: "pj" # HANGUL JONGSEONG PIEUP + CHOSEONG CIEUC
529
+ - pattern: "ᆸᄎ"
530
+ result: "pch" # HANGUL JONGSEONG PIEUP + CHOSEONG CHIEUCH
531
+ - pattern: "ᆸᄏ"
532
+ result: "pkh" # HANGUL JONGSEONG PIEUP + CHOSEONG KHIEUKH
533
+ - pattern: "ᆸᄐ"
534
+ result: "pth" # HANGUL JONGSEONG PIEUP + CHOSEONG THIEUTH
535
+ - pattern: "ᆸᄑ"
536
+ result: "pph" # HANGUL JONGSEONG PIEUP + CHOSEONG PHIEUPH
537
+ - pattern: "ᆸᄒ"
538
+ result: "ph" # HANGUL JONGSEONG PIEUP + CHOSEONG HIEUH
539
+ - pattern: "ᆸᄁ"
540
+ result: "pkk" # HANGUL JONGSEONG PIEUP + CHOSEONG SSANGKIYEOK
541
+ - pattern: "ᆸᄄ"
542
+ result: "ptt" # HANGUL JONGSEONG PIEUP + CHOSEONG SSANGTIEUT
543
+ - pattern: "ᆸᄈ"
544
+ result: "ppp" # HANGUL JONGSEONG PIEUP + CHOSEONG SSANGPIEUP
545
+ - pattern: "ᆸᄊ"
546
+ result: "pss" # HANGUL JONGSEONG PIEUP + CHOSEONG SSANGSIOS
547
+ - pattern: "ᆸᄍ"
548
+ result: "pjj" # HANGUL JONGSEONG PIEUP + CHOSEONG SSANGCIEUC
549
+ - pattern: "ᆺᄀ"
550
+ result: "tk" # HANGUL JONGSEONG SIOS + CHOSEONG KIYEOK
551
+ - pattern: "ᆺᄂ"
552
+ result: "nn" # HANGUL JONGSEONG SIOS + CHOSEONG NIEUN
553
+ - pattern: "ᆺᄃ"
554
+ result: "tt" # HANGUL JONGSEONG SIOS + CHOSEONG TIEUT
555
+ - pattern: "ᆺᄅ"
556
+ result: "nr" # HANGUL JONGSEONG SIOS + CHOSEONG RIEUL # Note 3.1
557
+ - pattern: "ᆺᄆ"
558
+ result: "nm" # HANGUL JONGSEONG SIOS + CHOSEONG MIEUM
559
+ - pattern: "ᆺᄇ"
560
+ result: "tp" # HANGUL JONGSEONG SIOS + CHOSEONG PIEUP
561
+ - pattern: "ᆺᄉ"
562
+ result: "ts" # HANGUL JONGSEONG SIOS + CHOSEONG SIOS
563
+ - pattern: "ᆺᄋ"
564
+ result: "d" # HANGUL JONGSEONG SIOS + CHOSEONG IEUNG
565
+ - pattern: "ᆺᄌ"
566
+ result: "tj" # HANGUL JONGSEONG SIOS + CHOSEONG CIEUC
567
+ - pattern: "ᆺᄎ"
568
+ result: "tch" # HANGUL JONGSEONG SIOS + CHOSEONG CHIEUCH
569
+ - pattern: "ᆺᄏ"
570
+ result: "tkh" # HANGUL JONGSEONG SIOS + CHOSEONG KHIEUKH
571
+ - pattern: "ᆺᄐ"
572
+ result: "tth" # HANGUL JONGSEONG SIOS + CHOSEONG THIEUTH
573
+ - pattern: "ᆺᄑ"
574
+ result: "tph" # HANGUL JONGSEONG SIOS + CHOSEONG PHIEUPH
575
+ - pattern: "ᆺᄒ"
576
+ result: "th" # HANGUL JONGSEONG SIOS + CHOSEONG HIEUH
577
+ - pattern: "ᆺᄁ"
578
+ result: "tkk" # HANGUL JONGSEONG SIOS + CHOSEONG SSANGKIYEOK
579
+ - pattern: "ᆺᄄ"
580
+ result: "ttt" # HANGUL JONGSEONG SIOS + CHOSEONG SSANGTIEUT
581
+ - pattern: "ᆺᄈ"
582
+ result: "tpp" # HANGUL JONGSEONG SIOS + CHOSEONG SSANGPIEUP
583
+ - pattern: "ᆺᄊ"
584
+ result: "tss" # HANGUL JONGSEONG SIOS + CHOSEONG SSANGSIOS
585
+ - pattern: "ᆺᄍ"
586
+ result: "tjj" # HANGUL JONGSEONG SIOS + CHOSEONG SSANGCIEUC
587
+ - pattern: "ᆼᄀ"
588
+ result: "ngg" # HANGUL JONGSEONG IEUNG + CHOSEONG KIYEOK
589
+ - pattern: "ᆼᄂ"
590
+ result: "ngn" # HANGUL JONGSEONG IEUNG + CHOSEONG NIEUN
591
+ - pattern: "ᆼᄃ"
592
+ result: "ngd" # HANGUL JONGSEONG IEUNG + CHOSEONG TIEUT
593
+ - pattern: "ᆼᄅ"
594
+ result: "ngn" # HANGUL JONGSEONG IEUNG + CHOSEONG RIEUL
595
+ - pattern: "ᆼᄆ"
596
+ result: "ngm" # HANGUL JONGSEONG IEUNG + CHOSEONG MIEUM
597
+ - pattern: "ᆼᄇ"
598
+ result: "ngb" # HANGUL JONGSEONG IEUNG + CHOSEONG PIEUP
599
+ - pattern: "ᆼᄉ"
600
+ result: "ngs" # HANGUL JONGSEONG IEUNG + CHOSEONG SIOS
601
+ - pattern: "ᆼᄋ"
602
+ result: "ng" # HANGUL JONGSEONG IEUNG + CHOSEONG IEUNG
603
+ - pattern: "ᆼᄌ"
604
+ result: "ngj" # HANGUL JONGSEONG IEUNG + CHOSEONG CIEUC
605
+ - pattern: "ᆼᄎ"
606
+ result: "ngch" # HANGUL JONGSEONG IEUNG + CHOSEONG CHIEUCH
607
+ - pattern: "ᆼᄏ"
608
+ result: "ngkh" # HANGUL JONGSEONG IEUNG + CHOSEONG KHIEUKH
609
+ - pattern: "ᆼᄐ"
610
+ result: "ngth" # HANGUL JONGSEONG IEUNG + CHOSEONG THIEUTH
611
+ - pattern: "ᆼᄑ"
612
+ result: "ngph" # HANGUL JONGSEONG IEUNG + CHOSEONG PHIEUPH
613
+ - pattern: "ᆼᄒ"
614
+ result: "ngh" # HANGUL JONGSEONG IEUNG + CHOSEONG HIEUH
615
+ - pattern: "ᆼᄁ"
616
+ result: "ngkk" # HANGUL JONGSEONG IEUNG + CHOSEONG SSANGKIYEOK
617
+ - pattern: "ᆼᄄ"
618
+ result: "ngtt" # HANGUL JONGSEONG IEUNG + CHOSEONG SSANGTIEUT
619
+ - pattern: "ᆼᄈ"
620
+ result: "ngpp" # HANGUL JONGSEONG IEUNG + CHOSEONG SSANGPIEUP
621
+ - pattern: "ᆼᄊ"
622
+ result: "ngss" # HANGUL JONGSEONG IEUNG + CHOSEONG SSANGSIOS
623
+ - pattern: "ᆼᄍ"
624
+ result: "ngjj" # HANGUL JONGSEONG IEUNG + CHOSEONG SSANGCIEUC
625
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄀ"
626
+ result: "g" # VOWEL + CHOSEONG KIYEOK # c.f. Note 3.3
627
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄂ"
628
+ result: "n" # VOWEL + CHOSEONG NIEUN # c.f. Note 3.3
629
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄃ"
630
+ result: "d" # VOWEL + CHOSEONG TIEUT # c.f. Note 3.3
631
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄅ"
632
+ result: "r" # VOWEL + CHOSEONG RIEUL
633
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄆ"
634
+ result: "m" # VOWEL + CHOSEONG MIEUM # c.f. Note 3.3
635
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄇ"
636
+ result: "b" # VOWEL + CHOSEONG PIEUP # c.f. Note 3.3
637
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄉ"
638
+ result: "s" # VOWEL + CHOSEONG SIOS
639
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄋ"
640
+ result: "" # VOWEL + CHOSEONG IEUNG
641
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄌ"
642
+ result: "j" # VOWEL + CHOSEONG CIEUC
643
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄎ"
644
+ result: "ch" # VOWEL + CHOSEONG CHIEUCH
645
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄏ"
646
+ result: "kh" # VOWEL + CHOSEONG KHIEUKH
647
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄐ"
648
+ result: "th" # VOWEL + CHOSEONG THIEUTH
649
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄑ"
650
+ result: "ph" # VOWEL + CHOSEONG PHIEUPH
651
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄒ"
652
+ result: "h" # VOWEL + CHOSEONG HIEUH
653
+ - pattern: "(?<=[-A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄁ"
654
+ result: "kk" # VOWEL + CHOSEONG SSANGKIYEOK
655
+ - pattern: "(?<=[A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄄ"
656
+ result: "tt" # VOWEL + CHOSEONG SSANGTIEUT
657
+ - pattern: "(?<=[A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄈ"
658
+ result: "pp" # VOWEL + CHOSEONG SSANGPIEUP
659
+ - pattern: "(?<=[A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄊ"
660
+ result: "ss" # VOWEL + CHOSEONG SSANGSIOS
661
+ - pattern: "(?<=[A-Za-z0-9ᅡᅢᅣᅤᅥᅦᅧᅨᅩᅪᅫᅬᅭᅮᅯᅰᅱᅲᅳᅴᅵ])ᄍ"
662
+ result: "jj" # VOWEL + CHOSEONG SSANGCIEUC
663
+ - pattern: "ᆰᄀ"
664
+ result: "lg" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG KIYEOK
665
+ - pattern: "ᆰᄂ"
666
+ result: "ngn" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG NIEUN
667
+ - pattern: "ᆰᄃ"
668
+ result: "kt" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG TIEUT
669
+ - pattern: "ᆰᄅ"
670
+ result: "ngn" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG RIEUL
671
+ - pattern: "ᆰᄆ"
672
+ result: "ngm" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG MIEUM
673
+ - pattern: "ᆰᄇ"
674
+ result: "kp" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG PIEUP
675
+ - pattern: "ᆰᄉ"
676
+ result: "ks" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SIOS
677
+ - pattern: "ᆰᄋ"
678
+ result: "lg" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG IEUNG
679
+ - pattern: "ᆰᄌ"
680
+ result: "kj" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG CIEUC
681
+ - pattern: "ᆰᄎ"
682
+ result: "kch" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG CHIEUCH
683
+ - pattern: "ᆰᄏ"
684
+ result: "lkh" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG KHIEUKH
685
+ - pattern: "ᆰᄐ"
686
+ result: "kth" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG THIEUTH
687
+ - pattern: "ᆰᄑ"
688
+ result: "kph" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG PHIEUPH
689
+ - pattern: "ᆰᄒ"
690
+ result: "lkh" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG HIEUH
691
+ - pattern: "ᆰᄁ"
692
+ result: "lkk" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SSANGKIYEOK
693
+ - pattern: "ᆰᄄ"
694
+ result: "ktt" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SSANGTIEUT
695
+ - pattern: "ᆰᄈ"
696
+ result: "kpp" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SSANGPIEUP
697
+ - pattern: "ᆰᄊ"
698
+ result: "kss" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SSANGSIOS
699
+ - pattern: "ᆰᄍ"
700
+ result: "kjj" # HANGUL JONGSEONG RIEUL-KIYEOK + CHOSEONG SSANGCIEUC
701
+ - pattern: "ᆱᄀ"
702
+ result: "mg" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG KIYEOK
703
+ - pattern: "ᆱᄂ"
704
+ result: "mn" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG NIEUN
705
+ - pattern: "ᆱᄃ"
706
+ result: "md" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG TIEUT
707
+ - pattern: "ᆱᄅ"
708
+ result: "mr" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG RIEUL
709
+ - pattern: "ᆱᄆ"
710
+ result: "lm" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG MIEUM
711
+ - pattern: "ᆱᄇ"
712
+ result: "mb" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG PIEUP
713
+ - pattern: "ᆱᄉ"
714
+ result: "ms" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SIOS
715
+ - pattern: "ᆱᄋ"
716
+ result: "lm" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG IEUNG
717
+ - pattern: "ᆱᄌ"
718
+ result: "mj" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG CIEUC
719
+ - pattern: "ᆱᄎ"
720
+ result: "mch" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG CHIEUCH
721
+ - pattern: "ᆱᄏ"
722
+ result: "mkh" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG KHIEUKH
723
+ - pattern: "ᆱᄐ"
724
+ result: "mth" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG THIEUTH
725
+ - pattern: "ᆱᄑ"
726
+ result: "mph" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG PHIEUPH
727
+ - pattern: "ᆱᄒ"
728
+ result: "mh" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG HIEUH
729
+ - pattern: "ᆱᄁ"
730
+ result: "mkk" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SSANGKIYEOK
731
+ - pattern: "ᆱᄄ"
732
+ result: "mtt" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SSANGTIEUT
733
+ - pattern: "ᆱᄈ"
734
+ result: "mpp" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SSANGPIEUP
735
+ - pattern: "ᆱᄊ"
736
+ result: "mss" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SSANGSIOS
737
+ - pattern: "ᆱᄍ"
738
+ result: "mjj" # HANGUL JONGSEONG RIEUL-MIEUM + CHOSEONG SSANGCIEUC
739
+ - pattern: "ᆲᄀ"
740
+ result: "pk" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG KIYEOK
741
+ - pattern: "ᆲᄂ"
742
+ result: "mn" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG NIEUN
743
+ - pattern: "ᆲᄃ"
744
+ result: "pt" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG TIEUT
745
+ - pattern: "ᆲᄅ"
746
+ result: "mr" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG RIEUL
747
+ - pattern: "ᆲᄆ"
748
+ result: "mm" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG MIEUM
749
+ - pattern: "ᆲᄇ"
750
+ result: "lb" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG PIEUP
751
+ - pattern: "ᆲᄉ"
752
+ result: "ps" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SIOS
753
+ - pattern: "ᆲᄋ"
754
+ result: "lb" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG IEUNG
755
+ - pattern: "ᆲᄌ"
756
+ result: "pj" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG CIEUC
757
+ - pattern: "ᆲᄎ"
758
+ result: "pch" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG CHIEUCH
759
+ - pattern: "ᆲᄏ"
760
+ result: "pkh" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG KHIEUKH
761
+ - pattern: "ᆲᄐ"
762
+ result: "pth" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG THIEUTH
763
+ - pattern: "ᆲᄑ"
764
+ result: "lph" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG PHIEUPH
765
+ - pattern: "ᆲᄒ"
766
+ result: "lph" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG HIEUH
767
+ - pattern: "ᆲᄁ"
768
+ result: "pkk" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SSANGKIYEOK
769
+ - pattern: "ᆲᄄ"
770
+ result: "ptt" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SSANGTIEUT
771
+ - pattern: "ᆲᄈ"
772
+ result: "lpp" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SSANGPIEUP
773
+ - pattern: "ᆲᄊ"
774
+ result: "pss" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SSANGSIOS
775
+ - pattern: "ᆲᄍ"
776
+ result: "pjj" # HANGUL JONGSEONG RIEUL-PIEUP + CHOSEONG SSANGCIEUC
777
+ - pattern: "(?<= )ᄀ"
778
+ result: "k" # HANGUL CHOSEONG KIYEOK
779
+ - pattern: "(?<= )ᄂ"
780
+ result: "n" # HANGUL CHOSEONG NIEUN
781
+ - pattern: "(?<= )ᄃ"
782
+ result: "t" # HANGUL CHOSEONG TIEUT
783
+
784
+ # DPRK does not follow the R-onset rule
785
+ # - pattern: "(?<= )ᄅ(?=[ᅣᅤᅧᅨᅭᅲ])"
786
+ # result: "" # HANGUL CHOSEONG RIEUL # R-onset rule
787
+ - pattern: "(?<= )ᄅ"
788
+ # result: "n" # HANGUL CHOSEONG RIEUL
789
+ result: "r"
790
+
791
+ - pattern: "(?<= )ᄆ"
792
+ result: "m" # HANGUL CHOSEONG MIEUM
793
+ - pattern: "(?<= )ᄇ"
794
+ result: "p" # HANGUL CHOSEONG PIEUP
795
+ - pattern: "(?<= )ᄉ"
796
+ result: "s" # HANGUL CHOSEONG SIOS
797
+ - pattern: "(?<= )ᄋ"
798
+ result: "" # HANGUL CHOSEONG IEUNG
799
+ - pattern: "(?<= )ᄌ"
800
+ result: "j" # HANGUL CHOSEONG CIEUC
801
+ - pattern: "(?<= )ᄎ"
802
+ result: "ch" # HANGUL CHOSEONG CHIEUCH
803
+ - pattern: "(?<= )ᄏ"
804
+ result: "kh" # HANGUL CHOSEONG KHIEUKH
805
+ - pattern: "(?<= )ᄐ"
806
+ result: "th" # HANGUL CHOSEONG THIEUTH
807
+ - pattern: "(?<= )ᄑ"
808
+ result: "ph" # HANGUL CHOSEONG PHIEUPH
809
+ - pattern: "(?<= )ᄒ"
810
+ result: "h" # HANGUL CHOSEONG HIEUH
811
+ - pattern: "(?<= )ᄁ"
812
+ result: "kk" # HANGUL CHOSEONG SSANGKIYEOK
813
+ - pattern: "(?<= )ᄭ"
814
+ result: "kk" # HANGUL CHOSEONG SIOS-KIYEOK
815
+ - pattern: "(?<= )ᄄ"
816
+ result: "tt" # HANGUL CHOSEONG SSANGTIEUT
817
+ - pattern: "(?<= )ᄯ"
818
+ result: "tt" # HANGUL CHOSEONG SIOS-TIEUT
819
+ - pattern: "(?<= )ᄈ"
820
+ result: "pp" # HANGUL CHOSEONG SSANGPIEUP
821
+ - pattern: "(?<= )ᄲ"
822
+ result: "pp" # HANGUL CHOSEONG SIOS-PIEUP
823
+ - pattern: "(?<= )ᄊ"
824
+ result: "ss" # HANGUL CHOSEONG SSANGSIOS
825
+ - pattern: "(?<= )ᄍ"
826
+ result: "jj" # HANGUL CHOSEONG SSANGCIEUC
827
+ - pattern: "(?<= )ᄶ"
828
+ result: "jj" # HANGUL CHOSEONG SIOS-CIEUC
829
+ - pattern: "ᅡ"
830
+ result: "a" # HANGUL JUNGSEONG A
831
+ - pattern: "ᅣ"
832
+ result: "ya" # HANGUL JUNGSEONG YA
833
+ - pattern: "ᅥ"
834
+ result: "ŏ" # HANGUL JUNGSEONG EO
835
+ - pattern: "ᅧ"
836
+ result: "yŏ" # HANGUL JUNGSEONG YEO
837
+ - pattern: "ᅩ"
838
+ result: "o" # HANGUL JUNGSEONG O
839
+ - pattern: "ᅭ"
840
+ result: "yo" # HANGUL JUNGSEONG YO
841
+ - pattern: "ᅮ"
842
+ result: "u" # HANGUL JUNGSEONG U
843
+ - pattern: "ᅲ"
844
+ result: "yu" # HANGUL JUNGSEONG YU
845
+ - pattern: "ᅳ"
846
+ result: "ü" # HANGUL JUNGSEONG EU
847
+ - pattern: "ᅵ"
848
+ result: "i" # HANGUL JUNGSEONG I
849
+ - pattern: "ᅢ"
850
+ result: "ae" # HANGUL JUNGSEONG AE
851
+ - pattern: "ᅤ"
852
+ result: "yae" # HANGUL JUNGSEONG YAE
853
+ - pattern: "ᅦ"
854
+ result: "e" # HANGUL JUNGSEONG E
855
+ - pattern: "ᅨ"
856
+ result: "ye" # HANGUL JUNGSEONG YE
857
+ - pattern: "ᅬ"
858
+ result: "oe" # HANGUL JUNGSEONG OE
859
+ - pattern: "ᅱ"
860
+ result: "wi" # HANGUL JUNGSEONG WI
861
+ - pattern: "ᅴ"
862
+ result: "üi" # HANGUL JUNGSEONG YI
863
+ - pattern: "ᅪ"
864
+ result: "wa" # HANGUL JUNGSEONG WA
865
+ - pattern: "ᅯ"
866
+ result: "wo" # HANGUL JUNGSEONG WEO
867
+ - pattern: "ᅫ"
868
+ result: "wae" # HANGUL JUNGSEONG WAE
869
+ - pattern: "ᅰ"
870
+ result: "we" # HANGUL JUNGSEONG WE
871
+ - pattern: "ᆨ(?!\\p{Hangul})"
872
+ result: "k" # HANGUL JONGSEONG KIYEOK
873
+ - pattern: "ᆫ(?!\\p{Hangul})"
874
+ result: "n" # HANGUL JONGSEONG NIEUN
875
+ - pattern: "ᆮ(?!\\p{Hangul})"
876
+ result: "t" # HANGUL JONGSEONG TIEUT
877
+ - pattern: "ᆯ(?!\\p{Hangul})"
878
+ result: "l" # HANGUL JONGSEONG RIEUL
879
+ - pattern: "ᆷ(?!\\p{Hangul})"
880
+ result: "m" # HANGUL JONGSEONG MIEUM
881
+ - pattern: "ᆸ(?!\\p{Hangul})"
882
+ result: "p" # HANGUL JONGSEONG PIEUP
883
+ - pattern: "ᆺ(?!\\p{Hangul})"
884
+ result: "t" # HANGUL JONGSEONG SIOS
885
+ - pattern: "ᆼ(?!\\p{Hangul})"
886
+ result: "ng" # HANGUL JONGSEONG IEUNG
887
+ - pattern: "ᆽ(?!\\p{Hangul})"
888
+ result: "t" # HANGUL JONGSEONG CIEUC
889
+ - pattern: "ᆾ(?!\\p{Hangul})"
890
+ result: "t" # HANGUL JONGSEONG CHIEUCH
891
+ - pattern: "ᆿ(?!\\p{Hangul})"
892
+ result: "k" # HANGUL JONGSEONG KHIEUKH
893
+ - pattern: "ᇀ(?!\\p{Hangul})"
894
+ result: "t" # HANGUL JONGSEONG THIEUTH
895
+ - pattern: "ᇁ(?!\\p{Hangul})"
896
+ result: "p" # HANGUL JONGSEONG PHIEUPH
897
+ - pattern: "ᆰ(?!\\p{Hangul})"
898
+ result: "k" # HANGUL JONGSEONG RIEUL-KIYEOK
899
+ - pattern: "ᆲ(?!\\p{Hangul})"
900
+ result: "p" # HANGUL JONGSEONG RIEUL-PIEUP
901
+
902
+ # Remove space added
903
+ - pattern: "^ "
904
+ result: ""
905
+ - pattern: " $"
906
+ result: ""
907
+
908
+ characters:
909
+ # This is based on Jamo