interscript 0.1.6 → 2.1.0a9

Sign up to get free protection for your applications and to get access to all the features.
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
@@ -1,575 +0,0 @@
1
- ---
2
- authority_id: ungegn
3
- id: 2016
4
- language: amh
5
- source_script: Ethi
6
- destination_script: Latn
7
- name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
8
- url: http://www.eki.ee/wgrs/rom1_am.pdf
9
- creation_date: 1967
10
- confirmation date: 2016-03
11
- description: |
12
- The United Nations recommended romanization system was approved in 1967 (resolution I/17), based on the Amharic to English Transliteration System (2nd revised edition, August 1962) by the Imperial Ethiopian Mapping and Geography Institute. The table has been published in volume II of the conference report (see Ref. in Notes section).
13
-
14
- The UN-approved system is not being used in Ethiopia, instead a simple version without diacritical marks is used. In international cartographic products mostly the BGN/PCGN 1967 system is used which differs from the former mainly by using diacritical marks differently. Often the same spellings are used without any diacritical marks.
15
-
16
- Amharic uses the Ethiopic syllabic script whereby each syllable denotes a combination of a consonant and a vowel. It has 34 basic characters, each character having several different forms, usually called orders, according to the vowel with which the basic character is combined. The system is mainly reversible with the exception of some syllables of the 1st order which are pronounced in the same manner as the syllables of the 4th order, and some consonants.
17
-
18
- notes:
19
- - (A) The vowel of the sixth order (i̠) is eliminated in spelling except when the actual pronunciation requires it (e.g. not Me̠ni̠gi̠si̠ti̠ but Me̠ngi̠st).
20
-
21
- - (B) Sounds identical to fourth-order form.
22
-
23
- - (C) Row 34 and most combinations with W and Y are not present in the original table. These Amharic syllable characters have been taken from the BGN/PCGN 1967 table, preserving however the indication of vowels as it is done elsewhere in the table.
24
-
25
- - |
26
- Other systems of romanization.
27
- The BGN/PCGN 1967 System is practically very close to the system above, except for the diacritical marks used with vowels:
28
-
29
- UN BGN/PCGN
30
- 1st order e̠ e
31
- 1st order a ā (ሀ hā, ሐ hā, ኀ hā, አ ā, ’ā, ዐ ‘ā)
32
- 3rd order i ī
33
- 5th order e ē
34
- 6th order i̠ i
35
-
36
- Other differences:
37
-
38
- 1. The vowel characters in row 16 should be romanized in the BGN/PCGN System ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o in all other positions.
39
-
40
- 2. The characters in row 20 should be romanized in the BGN/PCGN System ‘ā, ‘u, ‘ī, ‘a, ‘ē, ‘ or ‘i, and ‘o.
41
-
42
- 3. The syllables gwe̠, hwe̠, kwe̠, k’we̠ of the UN system are treated as variations of the syllables go, ho, ko, k’o in the BGN/PCGN system.
43
-
44
- 4. For documentation purposes the following consonants may be romanized with diacritical marks in the BGN/PCGN system: ḥ (row 3), š (row 5), ḫ (row 13), ẖ (row 18), t͟s’ (row 31).
45
-
46
-
47
- - (Ref.) Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp. 165–168 (Table 2).
48
-
49
- tests:
50
- - source: የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ
51
- expected: Ye̠zegi̠ne̠ti̠ Ki̠bi̠ri̠ Be̠ Iti̠yop’i̠yachi̠ni̠ Ts’e̠ni̠to
52
- - source: ታየ ሕዝባዊነት ዳር እስከዳር በርቶ
53
- expected: Taye̠ Hi̠zi̠bawine̠ti̠ Dari̠ I̠si̠ke̠dari̠ Be̠ri̠to
54
- - source: ለሰላም ለፍትህ ለሕዝቦች ነጻነት
55
- expected: Le̠se̠lami̠ Le̠fi̠ti̠hi̠ Le̠hi̠zi̠bochi̠ Ne̠ts’ane̠ti̠
56
- - source: በእኩልነት በፍቅር ቆመናል ባንድነት
57
- expected: Be̠i̠kuli̠ne̠ti̠ Be̠fi̠k’i̠ri̠ K’ome̠nali̠ Bani̠di̠ne̠ti̠
58
- - source: መሠረተ ፅኑ ሰብዕናን ያልሻርን
59
- expected: Me̠se̠re̠te̠ Ts’i̠nu Se̠bi̠i̠nani̠ Yali̠shari̠ni̠
60
- - source: ሕዝቦች ነን ለሥራ በሥራ የኖርን
61
- expected: Hi̠zi̠bochi̠ Ne̠ni̠ Le̠si̠ra Be̠si̠ra Ye̠nori̠ni̠
62
- - source: ድንቅ የባህል መድረክ ያኩሪ ቅርስ ባለቤት
63
- expected: Di̠ni̠k’i̠ Ye̠bahi̠li̠ Me̠di̠re̠ki̠ Yakuri K’i̠ri̠si̠ Bale̠beti̠
64
- - source: የተፈጥሮ ጸጋ የጀግና ሕዝብ እናት
65
- expected: Ye̠te̠fe̠t’i̠ro Ts’e̠ga Ye̠je̠gi̠na Hi̠zi̠bi̠ I̠nati̠
66
- - source: እንጠብቅሻለን አለብን አደራ
67
- expected: I̠ni̠t’e̠bi̠k’i̠shale̠ni̠ Ale̠bi̠ni̠ Ade̠ra
68
- - source: ኢትዮጵያችን ኑሪ እኛም ባንቺ እንኩራ
69
- expected: Iti̠yop’i̠yachi̠ni̠ Nuri I̠nyami̠ Bani̠chi I̠ni̠kura
70
- - source: ቋንቋ የድምጽ፣ የምልክት ወይም የምስል ቅንብር ሆኖ
71
- expected: K’wani̠k’wa Ye̠di̠mi̠ts’i̠፣ Ye̠mi̠li̠ki̠ti̠ We̠yi̠mi̠ Ye̠mi̠si̠li̠ K’i̠ni̠bi̠ri̠ Hono
72
- - source: ለማሰብ ወይም የታሰበን ሃሳብ ለሌላ ለማስተላለፍ የሚረዳ መሳሪያ ነው
73
- expected: Le̠mase̠bi̠ We̠yi̠mi̠ Ye̠tase̠be̠ni̠ Hasabi̠ Le̠lela Le̠masi̠te̠lale̠fi̠ Ye̠mire̠da Me̠sariya Ne̠wi̠
74
- - source: በአጭሩ ቋንቋ የምልክቶች ስርዓትና እኒህን ምልክቶች ለማቀናበር
75
- expected: Be̠ach’i̠ru K’wani̠k’wa Ye̠mi̠li̠ki̠tochi̠ Si̠ri̠ati̠na I̠nihi̠ni̠ Mi̠li̠ki̠tochi̠ Le̠mak’e̠nabe̠ri̠
76
- - source: የሚያስፈልጉ ህጎች ጥንቅር ነው። ቋንቋወችን ለመፈረጅ እንዲሁም
77
- expected: Ye̠miyasi̠fe̠li̠gu Hi̠gochi̠ T’i̠ni̠k’i̠ri̠ Ne̠wi̠። K’wani̠k’wawe̠chi̠ni̠ Le̠me̠fe̠re̠ji̠ I̠ni̠dihumi̠
78
- - source: ለምክፈል የሚያስችሉ መስፈርቶችን ለማስቀመጥ ባለው ችግር
79
- expected: Le̠mi̠ki̠fe̠li̠ Ye̠miyasi̠chi̠lu Me̠si̠fe̠ri̠tochi̠ni̠ Le̠masi̠k’e̠me̠t’i̠ Bale̠wi̠ Chi̠gi̠ri̠
80
- - source: ምክንያት በአሁኑ ሰዓት በርግጠኝነት ስንት ቋንቋ በዓለም ላይ
81
- expected: Mi̠ki̠ni̠yati̠ Be̠ahunu Se̠ati̠ Be̠ri̠gi̠t’e̠nyi̠ne̠ti̠ Si̠ni̠ti̠ K’wani̠k’wa Be̠ale̠mi̠ Layi̠
82
- - source: እንዳለ ማወቅ አስቸጋሪ ነው
83
- expected: I̠ni̠dale̠ Mawe̠k’i̠ Asi̠che̠gari Ne̠wi̠
84
- - source: አሰላ
85
- expected: Ase̠la
86
- - source: አሶሳ
87
- expected: Asosa
88
- - source: አንኮበር
89
- expected: Ani̠kobe̠ri̠
90
- - source: አክሱም
91
- expected: Aki̠sumi̠
92
- - source: አዋሳ
93
- expected: Awasa
94
- - source: አዲስ ዘመን (ከተማ)
95
- expected: Adisi̠ Ze̠me̠ni̠ (ke̠te̠ma)
96
- - source: አዲግራት
97
- expected: Adigi̠rati̠
98
- - source: አዳማ
99
- expected: Adama
100
- - source: ደምበጫ
101
- expected: De̠mi̠be̠ch’a
102
- - source: ደርባ
103
- expected: De̠ri̠ba
104
- - source: ደብረ ማርቆስ
105
- expected: De̠bi̠re̠ Mari̠k’osi̠
106
- - source: ደብረ ብርሃን
107
- expected: De̠bi̠re̠ Bi̠ri̠hani̠
108
- - source: ደብረ ታቦር (ከተማ)
109
- expected: De̠bi̠re̠ Tabori̠ (ke̠te̠ma)
110
- - source: ደብረ ዘይት
111
- expected: De̠bi̠re̠ Ze̠yi̠ti̠
112
- - source: ደገሃቡር
113
- expected: De̠ge̠haburi̠
114
- - source: ወልቂጤ
115
- expected: We̠li̠k’it’e
116
- - source: ወልወል
117
- expected: We̠li̠we̠li̠
118
- - source: ወልደያ
119
- expected: We̠li̠de̠ya
120
- - source: ናይሎ ሳህራን
121
- expected: Nayi̠lo Sahi̠rani̠
122
- - source: አኙዋክኛ
123
- expected: Anyuwaki̠nya
124
- - source: ኡዱክኛ
125
- expected: Uduki̠nya
126
- - source: ኦፓኛ
127
- expected: Opanya
128
- - source: ጉምዝኛ
129
- expected: Gumi̠zi̠nya
130
- - source: አፋርኛ
131
- expected: Afari̠nya
132
- - source: አላባኛ
133
- expected: Alabanya
134
- - source: አርቦርኛ
135
- expected: Ari̠bori̠nya
136
- - source: ባይሶኛ
137
- expected: Bayi̠sonya
138
- - source: ቡሳኛ
139
- expected: Busanya
140
- - source: ሁለተኛ ጥፋት ከገበያ ማንቀላፋት
141
- expected: Hule̠te̠nya T’i̠fati̠ Ke̠ge̠be̠ya Mani̠k’e̠lafati̠
142
- - source: ሁሉም ከልኩ አያልፍም
143
- expected: Hulumi̠ Ke̠li̠ku Ayali̠fi̠mi̠
144
- - source: አልሞት ባይ ተጋዳይ
145
- expected: Ali̠moti̠ Bayi̠ Te̠gadayi̠
146
- - source: ውርድ ከራሴ
147
- expected: Wi̠ri̠di̠ Ke̠rase
148
- - source: ፀጉር መሰንጠቅ
149
- expected: Ts’e̠guri̠ Me̠se̠ni̠t’e̠k’i̠
150
- - source: ግንትር ፀሐይ
151
- expected: Gi̠ni̠ti̠ri̠ Ts’e̠hayi̠
152
- - source: በሬ ወለደ
153
- expected: Be̠re We̠le̠de̠
154
- - source: ራስ ሳይጠና ጉተና
155
- expected: Rasi̠ Sayi̠t’e̠na Gute̠na
156
- - source: ለሆዴ ጠግቤ በልብሴ አንግቤ
157
- expected: Le̠hode T’e̠gi̠be Be̠li̠bi̠se Ani̠gi̠be
158
- - source: ለልጅ ከሳቁለት ለውሻ ከሮጡለት
159
- expected: Le̠li̠ji̠ Ke̠sak’ule̠ti̠ Le̠wi̠sha Ke̠rot’ule̠ti̠
160
- - source: መልካም ባል መጥፎ ሴት ይገራል
161
- expected: Me̠li̠kami̠ Bali̠ Me̠t’i̠fo Seti̠ Yi̠ge̠rali̠
162
- - source: ሆድና ግንባር አይሸሸግም
163
- expected: Hodi̠na Gi̠ni̠bari̠ Ayi̠she̠she̠gi̠mi̠
164
- - source: ቀሊል አማት ሲሶ በትር አላት
165
- expected: K’e̠lili̠ Amati̠ Siso Be̠ti̠ri̠ Alati̠
166
- - source: ጨው ለራስህ ብለህ ጣፍጥ አለበለዚያ ድንጋይ ነው ብለው ይወረውሩሀል
167
- expected: Ch’e̠wi̠ Le̠rasi̠hi̠ Bi̠le̠hi̠ T’afi̠t’i̠ Ale̠be̠le̠ziya Di̠ni̠gayi̠ Ne̠wi̠ Bi̠le̠wi̠ Yi̠we̠re̠wi̠ruhali̠
168
- - source: ጀምሮ ይጨርሳል አልሞ ይተኩሳል
169
- expected: Je̠mi̠ro Yi̠ch’e̠ri̠sali̠ Ali̠mo Yi̠te̠kusali̠
170
-
171
- map:
172
- word_separator: " "
173
- title_case: true
174
- characters:
175
- '\u1200' : 'ha' # ሀ (see note B)
176
- '\u1201' : 'hu' # ሁ
177
- '\u1202' : 'hi' # ሂ
178
- '\u1203' : 'ha' # ሃ
179
- '\u1204' : 'he' # ሄ
180
- '\u1205' : # ህ
181
- - 'hi̠'
182
- - 'h'
183
- '\u1206' : 'ho' # ሆ
184
- # Combinations with W and Y (see note C):
185
- '\u1207' : 'hwa' # ሇ
186
-
187
- '\u1208' : 'le̠' # ለ
188
- '\u1209' : 'lu' # ሉ
189
- '\u120A' : 'li' # ሊ
190
- '\u120B' : 'la' # ላ
191
- '\u120C' : 'le' # ሌ
192
- '\u120D' : # ል
193
- - 'li̠'
194
- - 'l'
195
- '\u120E' : 'lo' # ሎ
196
- # Combinations with W and Y (see note C):
197
- '\u120F' : 'lwa' # ሏ
198
-
199
- '\u1210' : 'ha' # ሐ (see note B)
200
- '\u1211' : 'hu' # ሑ
201
- '\u1212' : 'hi' # ሒ
202
- '\u1213' : 'ha' # ሓ
203
- '\u1214' : 'he' # ሔ
204
- '\u1215' : # ሕ
205
- - 'hi̠'
206
- - 'h'
207
- '\u1216' : 'ho' # ሖ
208
-
209
- '\u1218' : 'me̠' # መ
210
- '\u1219' : 'mu' # ሙ
211
- '\u121A' : 'mi' # ሚ
212
- '\u121B' : 'ma' # ማ
213
- '\u121C' : 'me' # ሜ
214
- '\u121D' : # ም
215
- - 'mi̠'
216
- - 'm'
217
- '\u121E' : 'mo' # ሞ
218
- # Combinations with W and Y (see note C):
219
- '\u121F' : 'mwa' # ሟ
220
- '\u1359' : 'mya' # ፙ
221
-
222
- '\u1220' : 'se̠' # ሠ
223
- '\u1221' : 'su' # ሡ
224
- '\u1222' : 'si' # ሢ
225
- '\u1223' : 'sa' # ሣ
226
- '\u1224' : 'se' # ሤ
227
- '\u1225' : # ሥ
228
- - 'si̠'
229
- - 's'
230
- '\u1226' : 'so' # ሦ
231
-
232
- '\u1228' : 're̠' # ረ
233
- '\u1229' : 'ru' # ሩ
234
- '\u122A' : 'ri' # ሪ
235
- '\u122B' : 'ra' # ራ
236
- '\u122C' : 're' # ሬ
237
- '\u122D' : # ር
238
- - 'ri̠'
239
- - 'r'
240
- '\u122E' : 'ro' # ሮ
241
- # Combinations with W and Y (see note C):
242
- '\u122F' : 'rwa' # ሯ
243
- '\u1358' : 'rya' # ፘ
244
-
245
- '\u1230' : 'se̠' # ሰ
246
- '\u1231' : 'su' # ሱ
247
- '\u1232' : 'si' # ሲ
248
- '\u1233' : 'sa' # ሳ
249
- '\u1234' : 'se' # ሴ
250
- '\u1235' : # ስ
251
- - 'si̠'
252
- - 's'
253
- '\u1236' : 'so' # ሶ
254
- # Combinations with W and Y (see note C):
255
- '\u1237' : 'swa' # ሷ
256
-
257
- '\u1238' : 'she̠' # ሸ
258
- '\u1239' : 'shu' # ሹ
259
- '\u123A' : 'shi' # ሺ
260
- '\u123B' : 'sha' # ሻ
261
- '\u123C' : 'she' # ሼ
262
- '\u123D' : # ሽ
263
- - 'shi̠'
264
- - 'sh'
265
- '\u123E' : 'sho' # ሾ
266
- # Combinations with W and Y (see note C):
267
- '\u123F' : 'shwa' # ሿ
268
-
269
- '\u1240' : 'k’e̠' # ቀ
270
- '\u1241' : 'k’u' # ቁ
271
- '\u1242' : 'k’i' # ቂ
272
- '\u1243' : 'k’a' # ቃ
273
- '\u1244' : 'k’e' # ቄ
274
- '\u1245' : # ቅ
275
- - 'k’i̠'
276
- - 'k’'
277
- '\u1246' : 'k’o' # ቆ
278
- # Combinations with W and Y (see note C):
279
- '\u1248' : 'k’we̠' # ቈ
280
- '\u124A' : 'k’wi' # ቊ
281
- '\u124B' : 'k’wa' # ቋ
282
- '\u124C' : 'k’we' # ቌ
283
- '\u124D' : 'k’wi̠' # ቍ
284
-
285
- '\u1260' : 'be̠' # በ
286
- '\u1261' : 'bu' # ቡ
287
- '\u1262' : 'bi' # ቢ
288
- '\u1263' : 'ba' # ባ
289
- '\u1264' : 'be' # ቤ
290
- '\u1265' : # ብ
291
- - 'bi̠'
292
- - 'b'
293
- '\u1266' : 'bo' # ቦ
294
- # Combinations with W and Y (see note C):
295
- '\u1267' : 'bwa' # ቧ
296
-
297
- '\u1270' : 'te̠' # ተ
298
- '\u1271' : 'tu' # ቱ
299
- '\u1272' : 'ti' # ቲ
300
- '\u1273' : 'ta' # ታ
301
- '\u1274' : 'te' # ቴ
302
- '\u1275' : # ት
303
- - 'ti̠'
304
- - 't'
305
- '\u1276' : 'to' # ቶ
306
- # Combinations with W and Y (see note C):
307
- '\u1277' : 'twa' # ቷ
308
-
309
- '\u1278' : 'che̠' # ቸ
310
- '\u1279' : 'chu' # ቹ
311
- '\u127A' : 'chi' # ቺ
312
- '\u127B' : 'cha' # ቻ
313
- '\u127C' : 'che' # ቼ
314
- '\u127D' : # ች
315
- - 'chi̠'
316
- - 'ch'
317
- '\u127E' : 'cho' # ቾ
318
- # Combinations with W and Y (see note C):
319
- '\u127F' : 'chwa' # ቿ
320
-
321
- '\u1280' : 'ha' # ኀ (note B)
322
- '\u1281' : 'hu' # ኁ
323
- '\u1282' : 'hi' # ኂ
324
- '\u1283' : 'ha' # ኃ
325
- '\u1284' : 'he' # ኄ
326
- '\u1285' : # ኅ
327
- - 'hi̠'
328
- - 'h'
329
- '\u1286' : 'ho' # ኆ
330
- # Combinations with W and Y (see note C):
331
- '\u1288' : 'hwe̠' # ኈ
332
- '\u128A' : 'hwi' # ኊ
333
- '\u128B' : 'hwa' # ኋ
334
- '\u128C' : 'hwe' # ኌ
335
- '\u128D' : 'hwi̠' # ኍ
336
-
337
- '\u1290' : 'ne̠' # ነ
338
- '\u1291' : 'nu' # ኑ
339
- '\u1292' : 'ni' # ኒ
340
- '\u1293' : 'na' # ና
341
- '\u1294' : 'ne' # ኔ
342
- '\u1295' : # ን
343
- - 'ni̠'
344
- - 'n'
345
- '\u1296' : 'no' # ኖ
346
- # Combinations with W and Y (see note C):
347
- '\u1297' : 'nwa' # ኗ
348
-
349
- '\u1298' : 'nye̠' # ኘ
350
- '\u1299' : 'nyu' # ኙ
351
- '\u129A' : 'nyi' # ኚ
352
- '\u129B' : 'nya' # ኛ
353
- '\u129C' : 'nye' # ኜ
354
- '\u129D' : # ኝ
355
- - 'nyi̠'
356
- - 'ny'
357
- '\u129E' : 'nyo' # ኞ
358
- # Combinations with W and Y (see note C):
359
- '\u129F' : 'nywa' # ኟ
360
-
361
- '\u12A0' : 'a' # አ (note B)
362
- '\u12A1' : 'u' # ኡ
363
- '\u12A2' : 'i' # ኢ
364
- '\u12A3' : 'a' # ኣ
365
- '\u12A4' : 'e' # ኤ
366
- '\u12A5' : 'i̠' # እ
367
- '\u12A6' : 'o' # ኦ
368
-
369
- '\u12A8' : 'ke̠' # ከ
370
- '\u12A9' : 'ku' # ኩ
371
- '\u12AA' : 'ki' # ኪ
372
- '\u12AB' : 'ka' # ካ
373
- '\u12AC' : 'ke' # ኬ
374
- '\u12AD' : # ክ
375
- - 'ki̠'
376
- - 'k'
377
- '\u12AE' : 'ko' # ኮ
378
- # Combinations with W and Y (see note C):
379
- '\u12B0' : 'kwe̠' # ኰ
380
- '\u12B2' : 'kwi' # ኲ
381
- '\u12B3' : 'kwa' # ኳ
382
- '\u12B4' : 'kwe' # ኴ
383
- '\u12B5' : 'kwi̠' # ኵ
384
-
385
- '\u12B8' : 'he̠' # ኸ
386
- '\u12B9' : 'hu' # ኹ
387
- '\u12BA' : 'hi' # ኺ
388
- '\u12BB' : 'ha' # ኻ
389
- '\u12BC' : 'he' # ኼ
390
- '\u12BD' : # ኽ
391
- - 'hi̠'
392
- - 'h'
393
- '\u12BE' : 'ho' # ኾ
394
-
395
- '\u12C8' : 'we̠' # ወ
396
- '\u12C9' : 'wu' # ዉ
397
- '\u12CA' : 'wi' # ዊ
398
- '\u12CB' : 'wa' # ዋ
399
- '\u12CC' : 'we' # ዌ
400
- '\u12CD' : # ው
401
- - 'wi̠'
402
- - 'w'
403
- '\u12CE' : 'wo' # ዎ
404
-
405
- '\u12D0' : 'a' # ዐ (note B)
406
- '\u12D1' : 'u' # ዑ
407
- '\u12D2' : 'i' # ዒ
408
- '\u12D3' : 'a' # ዓ
409
- '\u12D4' : 'e' # ዔ
410
- '\u12D5' : 'i̠' # ዕ
411
- '\u12D6' : 'o' # ዖ
412
-
413
- '\u12D8' : 'ze̠' # ዘ
414
- '\u12D9' : 'zu' # ዙ
415
- '\u12DA' : 'zi' # ዚ
416
- '\u12DB' : 'za' # ዛ
417
- '\u12DC' : 'ze' # ዜ
418
- '\u12DD' : # ዝ
419
- - 'zi̠'
420
- - 'z'
421
- '\u12DE' : 'zo' # ዞ
422
- # Combinations with W and Y (see note C):
423
- '\u12DF' : 'zwa' # ዟ
424
-
425
- '\u12E0' : 'zhe̠' # ዠ
426
- '\u12E1' : 'zhu' # ዡ
427
- '\u12E2' : 'zhi' # ዢ
428
- '\u12E3' : 'zha' # ዣ
429
- '\u12E4' : 'zhe' # ዤ
430
- '\u12E5' : # ዥ
431
- - 'zhi̠'
432
- - 'zh'
433
- '\u12E6' : 'zho' # ዦ
434
- # Combinations with W and Y (see note C):
435
- '\u12E7' : 'zhwa' # ዧ
436
-
437
- '\u12E8' : 'ye̠' # የ
438
- '\u12E9' : 'yu' # ዩ
439
- '\u12EA' : 'yi' # ዪ
440
- '\u12EB' : 'ya' # ያ
441
- '\u12EC' : 'ye' # ዬ
442
- '\u12ED' : # ይ
443
- - 'yi̠'
444
- - 'y'
445
- '\u12EE' : 'yo' # ዮ
446
- '\u12EF' : 'ywa' # ዯ
447
-
448
- '\u12F0' : 'de̠' # ደ
449
- '\u12F1' : 'du' # ዱ
450
- '\u12F2' : 'di' # ዲ
451
- '\u12F3' : 'da' # ዳ
452
- '\u12F4' : 'de' # ዴ
453
- '\u12F5' : # ድ
454
- - 'di̠'
455
- - 'd'
456
- '\u12F6' : 'do' # ዶ
457
- # Combinations with W and Y (see note C):
458
- '\u12F7' : 'dwa' # ዷ
459
-
460
- '\u1300' : 'je̠' # ጀ
461
- '\u1301' : 'ju' # ጁ
462
- '\u1302' : 'ji' # ጂ
463
- '\u1303' : 'ja' # ጃ
464
- '\u1304' : 'je' # ጄ
465
- '\u1305' : # ጅ
466
- - 'ji̠'
467
- - 'j'
468
- '\u1306' : 'jo' # ጆ
469
- # Combinations with W and Y (see note C):
470
- '\u1307' : 'jwa' # ጇ
471
-
472
- '\u1308' : 'ge̠' # ገ
473
- '\u1309' : 'gu' # ጉ
474
- '\u130A' : 'gi' # ጊ
475
- '\u130B' : 'ga' # ጋ
476
- '\u130C' : 'ge' # ጌ
477
- '\u130D' : # ግ
478
- - 'gi̠'
479
- - 'g'
480
- '\u130E' : 'go' # ጎ
481
- # Combinations with W and Y (see note C):
482
- '\u1310' : 'gwe̠' # ጐ
483
- '\u1312' : 'gwi' # ጒ
484
- '\u1313' : 'gwa' # ጓ
485
- '\u1314' : 'gwe' # ጔ
486
- '\u1315' : 'gwi̠' # ጕ
487
-
488
- '\u1320' : 't’e̠' # ጠ
489
- '\u1321' : 't’u' # ጡ
490
- '\u1322' : 't’i' # ጢ
491
- '\u1323' : 't’a' # ጣ
492
- '\u1324' : 't’e' # ጤ
493
- '\u1325' : # ጥ
494
- - 't’i̠'
495
- - 't’'
496
- '\u1326' : 't’o' # ጦ
497
- # Combinations with W and Y (see note C):
498
- '\u1327' : 't’wa' # ጧ
499
-
500
- '\u1328' : 'ch’e̠' # ጨ
501
- '\u1329' : 'ch’u' # ጩ
502
- '\u132A' : 'ch’i' # ጪ
503
- '\u132B' : 'ch’a' # ጫ
504
- '\u132C' : 'ch’e' # ጬ
505
- '\u132D' : # ጭ
506
- - 'ch’i̠'
507
- - 'ch’'
508
- '\u132E' : 'ch’o' # ጮ
509
- # Combinations with W and Y (see note C):
510
- '\u132F' : 'ch’wa' # ጯ
511
-
512
- '\u1330' : 'p’e̠' # ጰ
513
- '\u1331' : 'p’u' # ጱ
514
- '\u1332' : 'p’i' # ጲ
515
- '\u1333' : 'p’a' # ጳ
516
- '\u1334' : 'p’e' # ጴ
517
- '\u1335' : # ጵ
518
- - 'p’i̠'
519
- - 'p’'
520
- '\u1336' : 'p’o' # ጶ
521
-
522
- '\u1338' : 'ts’e̠' # ጸ
523
- '\u1339' : 'ts’u' # ጹ
524
- '\u133A' : 'ts’i' # ጺ
525
- '\u133B' : 'ts’a' # ጻ
526
- '\u133C' : 'ts’e' # ጼ
527
- '\u133D' : # ጽ
528
- - 'ts’i̠'
529
- - 'ts’'
530
- '\u133E' : 'ts’o' # ጾ
531
- # Combinations with W and Y (see note C):
532
- '\u133F' : 'ts’wa' # ጿ
533
-
534
- '\u1340' : 'ts’e̠' # ፀ
535
- '\u1341' : 'ts’u' # ፁ
536
- '\u1342' : 'ts’i' # ፂ
537
- '\u1343' : 'ts’a' # ፃ
538
- '\u1344' : 'ts’e' # ፄ
539
- '\u1345' : # ፅ
540
- - 'ts’i̠'
541
- - 'ts’'
542
- '\u1346' : 'ts’o' # ፆ
543
-
544
- '\u1348' : 'fe̠' # ፈ
545
- '\u1349' : 'fu' # ፉ
546
- '\u134A' : 'fi' # ፊ
547
- '\u134B' : 'fa' # ፋ
548
- '\u134C' : 'fe' # ፌ
549
- '\u134D' : # ፍ
550
- - 'fi̠'
551
- - 'f'
552
- '\u134E' : 'fo' # ፎ
553
- # Combinations with W and Y (see note C):
554
- '\u134F' : 'fwa' # ፏ
555
- '\u135A' : 'fya' # ፚ
556
-
557
- '\u1350' : 'pe̠' # ፐ
558
- '\u1351' : 'pu' # ፑ
559
- '\u1352' : 'pi' # ፒ
560
- '\u1353' : 'pa' # ፓ
561
- '\u1354' : 'pe' # ፔ
562
- '\u1355' : # ፕ
563
- - 'pi̠'
564
- - 'p'
565
- '\u1356' : 'po' # ፖ
566
-
567
- '\u1268' : 've̠' # ቨ
568
- '\u1269' : 'vu' # ቩ
569
- '\u126A' : 'vi' # ቪ
570
- '\u126B' : 'va' # ቫ
571
- '\u126C' : 've' # ቬ
572
- '\u126D' : # ቭ
573
- - 'vi̠'
574
- - 'v'
575
- '\u126E' : 'vo' # ቮ