interscript 0.1.2 → 0.1.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (120) hide show
  1. checksums.yaml +4 -4
  2. data/README.adoc +246 -14
  3. data/bin/interscript +38 -17
  4. data/bin/setup +8 -0
  5. data/lib/g2pwrapper.py +34 -0
  6. data/lib/interscript.rb +140 -16
  7. data/lib/interscript/command.rb +27 -0
  8. data/lib/interscript/mapping.rb +125 -0
  9. data/lib/interscript/version.rb +1 -1
  10. data/lib/model-7 +0 -0
  11. data/lib/tha-pt-b-7 +0 -0
  12. data/maps/acadsin-zho-Hani-Latn-2002.yaml +38912 -0
  13. data/maps/alalc-bel-cyrl-latn-1997.yaml +125 -0
  14. data/maps/alalc-ben-Beng-Latn-2017.yaml +130 -0
  15. data/maps/alalc-bul-Cyrl-Latn-1997.yaml +94 -0
  16. data/maps/alalc-ell-Grek-Latn-1997.yaml +625 -0
  17. data/maps/alalc-ell-Grek-Latn-2010.yaml +628 -0
  18. data/maps/alalc-kat-Geok-Latn-1997.yaml +112 -0
  19. data/maps/alalc-kat-Geor-Latn-1997.yaml +146 -0
  20. data/maps/alalc-kor-Hang-Latn-1997.yaml +94 -0
  21. data/maps/alalc-mkd-Cyrl-Latn-2013.yaml +103 -0
  22. data/maps/alalc-mkd-cyrl-latn-1997.yaml +114 -0
  23. data/maps/alalc-srp-Cyrl-Latn-1997.yaml +114 -0
  24. data/maps/alalc-srp-cyrl-latn-2013.yaml +135 -0
  25. data/maps/alalc-ukr-Cyrl-Latn-1997.yaml +141 -0
  26. data/maps/alalc-ukr-Cyrl-Latn-2011.yaml +16 -0
  27. data/maps/apcbg-bul-Cyrl-Latn-1995.yaml +283 -0
  28. data/maps/{bas-rus-Cyrl-Latn-bss.yaml → bas-rus-Cyrl-Latn-2017-bss.yaml} +57 -31
  29. data/maps/{bas-rus-Cyrl-Latn-oss.yaml → bas-rus-Cyrl-Latn-2017-oss.yaml} +54 -34
  30. data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +294 -0
  31. data/maps/bgn-kor-Hang-Latn-1943.yaml +31 -0
  32. data/maps/bgn-kor-Kore-Latn-1943.yaml +31 -0
  33. data/maps/bgna-bul-Cyrl-Latn-2006.yaml +208 -0
  34. data/maps/bgna-bul-Cyrl-Latn-2009.yaml +208 -0
  35. data/maps/bgnpcgn-arm-Armn-Latn-1981.yaml +1 -2
  36. data/maps/bgnpcgn-aze-Cyrl-Latn-1993.yaml +104 -0
  37. data/maps/bgnpcgn-bel-cyrl-latn-1979.yaml +285 -0
  38. data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml +115 -0
  39. data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml +10 -64
  40. data/maps/bgnpcgn-chn-Hans-Latn-1979.yaml +7456 -0
  41. data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +702 -0
  42. data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +20 -0
  43. data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml +257 -0
  44. data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml +127 -0
  45. data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +43 -0
  46. data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +253 -0
  47. data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +48 -0
  48. data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +48 -0
  49. data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml +159 -0
  50. data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +190 -0
  51. data/maps/bgnpcgn-rus-Cyrl-Latn-1947.yaml +145 -64
  52. data/maps/bgnpcgn-srp-Cyrl-Latn-2005.yaml +166 -0
  53. data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +75 -2
  54. data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml +208 -0
  55. data/maps/by-bel-Cyrl-Latn-1998.yaml +168 -0
  56. data/maps/by-bel-Cyrl-Latn-2007.yaml +115 -0
  57. data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +685 -0
  58. data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +681 -0
  59. data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +20 -0
  60. data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +32 -0
  61. data/maps/ggg-kat-Geor-Latn-2002.yaml +89 -0
  62. data/maps/gki-bel-cyrl-latn-1992.yaml +33 -0
  63. data/maps/gki-bel-cyrl-latn-2000.yaml +201 -0
  64. data/maps/gost-rus-cyrl-latn-16876-71-1983.yaml +186 -0
  65. data/maps/hk-yue-Hani-Latn-1888.yaml +38497 -0
  66. data/maps/icao-bel-Cyrl-Latn-9303.yaml +108 -92
  67. data/maps/icao-bul-Cyrl-Latn-9303.yaml +1 -2
  68. data/maps/icao-heb-Hebr-Latn-9303.yaml +118 -124
  69. data/maps/icao-mkd-Cyrl-Latn-9303.yaml +1 -2
  70. data/maps/icao-per-Arab-Latn-9303.yaml +5 -6
  71. data/maps/icao-rus-Cyrl-Latn-9303.yaml +1 -2
  72. data/maps/icao-srp-Cyrl-Latn-9303.yaml +1 -2
  73. data/maps/icao-ukr-Cyrl-Latn-9303.yaml +1 -2
  74. data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +610 -0
  75. data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +41 -0
  76. data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml +62 -0
  77. data/maps/{iso-rus-Cyrl-Latn-iso9.yaml → iso-rus-Cyrl-Latn-9-1995.yaml} +2 -3
  78. data/maps/iso-tha-Thai-Latn-11940-1998.yaml +109 -0
  79. data/maps/kp-kor-Hang-Latn-2002.yaml +901 -0
  80. data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +44820 -0
  81. data/maps/mext-jpn-Hrkt-Latn-1954.yaml +411 -0
  82. data/maps/moct-kor-Hang-Latn-2000.yaml +803 -0
  83. data/maps/mofa-jpn-Hrkt-Latn-1989.yaml +541 -0
  84. data/maps/nil-kor-Hang-Hang-jamo.yaml +11193 -0
  85. data/maps/odni-kat-Geor-Latn-2015.yaml +88 -0
  86. data/maps/odni-ukr-Cyrl-Latn-2015.yaml +157 -0
  87. data/maps/royin-tha-Thai-Latn-1939-generic.yaml +90 -0
  88. data/maps/royin-tha-Thai-Latn-1968.yaml +179 -0
  89. data/maps/royin-tha-Thai-Latn-1999-chained.yaml +180 -0
  90. data/maps/royin-tha-Thai-Latn-1999.yaml +76 -0
  91. data/maps/{cn-chn-Hans-Latn-pinyin.yaml → sac-zho-Hans-Latn-1979.yaml} +6 -7
  92. data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml +222 -0
  93. data/maps/ua-ukr-Cyrl-Latn-1996.yaml +193 -0
  94. data/maps/un-bel-Cyrl-Latn-2007.yaml +114 -0
  95. data/maps/un-ben-Beng-Latn-2016.yaml +534 -0
  96. data/maps/un-ell-Grek-Latn-1987-tl.yaml +32 -0
  97. data/maps/un-ell-Grek-Latn-1987-ts.yaml +20 -0
  98. data/maps/un-ell-Grek-Latn-phonetic-1987.yaml +780 -0
  99. data/maps/un-mon-Mong-Latn-2013.yaml +19 -6
  100. data/maps/un-rus-Cyrl-Latn-1987.yaml +166 -0
  101. data/maps/un-ukr-cyrl-latn-1998.yaml +30 -0
  102. data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml +406 -0
  103. data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml +386 -0
  104. data/maps/var-kor-Hang-Latn-mr-1939.yaml +1054 -0
  105. data/maps/var-kor-Kore-Hang-2013.yaml +59754 -0
  106. data/maps/var-kor-Kore-Latn-mr-1939.yaml +37 -0
  107. data/maps/var-tha-Thai-Thai-phonemic.yaml +59 -0
  108. data/maps/var-tha-Thai-Zsym-ipa.yaml +301 -0
  109. data/maps/var-zho-Hani-Latn-1979.yaml +38908 -0
  110. data/spec/interscript/mapping_spec.rb +42 -0
  111. data/spec/interscript_spec.rb +20 -5
  112. data/spec/spec_helper.rb +3 -1
  113. metadata +149 -24
  114. data/maps/bgnpcgn-chn-Hans-Latn-pinyin.yaml +0 -7503
  115. data/maps/historic-jpn-Hrkt-Latn-hepburn.yaml +0 -336
  116. data/maps/icao-gre-Grek-Latn-9303.yaml +0 -101
  117. data/maps/mext-jpn-Hrkt-Latn-hepburn.yaml +0 -330
  118. data/maps/mext-jpn-Hrkt-Latn-kunrei.yaml +0 -308
  119. data/maps/un-jpn-Hrkt-Latn-hepburn.yaml +0 -313
  120. data/maps/un-jpn-Hrkt-Latn-kunrei.yaml +0 -354
@@ -21,8 +21,7 @@ description: |
21
21
  This document defines the transliteration mappings used to produce
22
22
  this transcription or transliteration.
23
23
  tests:
24
- - source:
25
- expected:
24
+
26
25
  map:
27
26
  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
28
27
  characters:
@@ -21,8 +21,7 @@ description: |
21
21
  This document defines the transliteration mappings used to produce
22
22
  this transcription or transliteration.
23
23
  tests:
24
- - source:
25
- expected:
24
+
26
25
  map:
27
26
  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
28
27
  characters:
@@ -30,10 +29,10 @@ map:
30
29
  "\u0027": "" # '
31
30
  "\u0621": "XE" # ء
32
31
  "\u0622": "XAA" # آ
33
- "\u0623": 'XAE', # أ
34
- "\u0624": 'U', # ؤ
35
- "\u0625": 'I', # إ
36
- "\u0626": 'XI', # ئ
32
+ "\u0623": 'XAE' # أ
33
+ "\u0624": 'U' # ؤ
34
+ "\u0625": 'I' # إ
35
+ "\u0626": 'XI' # ئ
37
36
  "\u0627": "A" # ا
38
37
  "\u0628": "B" # ب
39
38
  "\u0629": "P" # ة
@@ -21,8 +21,7 @@ description: |
21
21
  This document defines the transliteration mappings used to produce
22
22
  this transcription or transliteration.
23
23
  tests:
24
- - source:
25
- expected:
24
+
26
25
  map:
27
26
  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
28
27
  characters:
@@ -21,8 +21,7 @@ description: |
21
21
  This document defines the transliteration mappings used to produce
22
22
  this transcription or transliteration.
23
23
  tests:
24
- - source:
25
- expected:
24
+
26
25
  map:
27
26
  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
28
27
  characters:
@@ -21,8 +21,7 @@ description: |
21
21
  This document defines the transliteration mappings used to produce
22
22
  this transcription or transliteration.
23
23
  tests:
24
- - source:
25
- expected:
24
+
26
25
 
27
26
  map:
28
27
  # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
@@ -0,0 +1,610 @@
1
+ ---
2
+ authority_id: iso
3
+ id: 1997
4
+ language: ell
5
+ source_script: Grek
6
+ destination_script: Latn
7
+ name: ISO 843:1997
8
+ url:
9
+ creation_date: 1997
10
+ description: |
11
+ ISO Transliteration table for Greek
12
+
13
+ note:
14
+ - Transliteration of Greek into Latin: Type 1, Clause 3 Table 1
15
+ - Equivalent to elot-ell-Grek-Latn-743-2001-ts, the transliteration table of ELOT 743:2001
16
+ - Assuming that ou, au, eu transliterations are only intended for historical diphthongs /u, av, ev/, and that όυ, άυ, έυ are not to be transliterated as ou, au, eu
17
+ - Introduced casing to digamma and lunate sigma. (Casing was late introduction to character sets for those characters)
18
+
19
+ tests:
20
+
21
+ - source: |
22
+ Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.
23
+
24
+ Γιάννης Μακρυγιάννης.
25
+
26
+ expected: |
27
+ Éna práma mónon me parakínīse ki eména na grápsō óti toútīn tīn patrída tīn échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai ftōchoí kai politikoí kai stratiōtikoí kai oi pléon mikróteroi ánthrōpoi; ósoi agōnistī́kamen, analógōs o katheís, échomen na zī́somen edṓ. To loipón doulépsamen óloi mazí, na tīn fylámen ki óloi mazí kai na mīn légei oúte o dynatós «egṓ» oúte o adýnatos. Xérete póte na légei o katheís «egṓ»? Ótan agōnisteí mónos tou kai fkiásei ī́ chalásei, na légei «egṓ»; ótan ómōs agōnízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egṓ». Kai eis to exī́s na máthomen gnṓsī, an thélomen na fkiásomen chōrión, na zī́somen óloi mazí.
28
+
29
+ Giánnīs Makrygiánnīs.
30
+
31
+
32
+ - source: ΑΘΗΝΑ
33
+ expected: ATHĪNA
34
+ - source: μπαμπάκι
35
+ expected: mpampáki
36
+ - source: νταντά
37
+ expected: ntantá
38
+ - source: γκέγκε
39
+ expected: gkégke
40
+ - source: Γκαμπόν
41
+ expected: Gkampón
42
+ - source: Μάγχη
43
+ expected: Mágchī
44
+ - source: κογξ
45
+ expected: kogx
46
+ - source: υιός
47
+ expected: yiós
48
+ - source: Υιός
49
+ expected: Yiós
50
+ - source: νεράντζι
51
+ expected: nerántzi
52
+ - source: Γοίθιος
53
+ expected: Goíthios
54
+ - source: μπέικον
55
+ expected: mpéikon
56
+ - source: μπέϊκον
57
+ expected: mpéïkon
58
+ - source: βόλεϊ
59
+ expected: vóleï
60
+ - source: αθεΐα
61
+ expected: atheḯa
62
+ - source: Εϊγιαφιάτλαγιοκουτλ
63
+ expected: Eïgiafiátlagiokoutl
64
+ - source: Εΐτζι
65
+ expected: Eḯtzi
66
+ - source: Μυρτώο
67
+ expected: Myrtṓo
68
+ - source: αέρας
69
+ expected: aéras
70
+ - source: γαυ γαυ
71
+ expected: gau gau
72
+ - source: Ταΰγετος
73
+ expected: Taÿ́getos
74
+ - source: σπρέυ
75
+ expected: spréy
76
+
77
+ - source: Αθήνα
78
+ expected: Athī́na
79
+ - source: Άγιον Όρος
80
+ expected: Ágion Óros
81
+ - source: Άγραφα
82
+ expected: Ágrafa
83
+ - source: Αγρίνιο
84
+ expected: Agrínio
85
+ - source: Αίγινα
86
+ expected: Aígina
87
+ - source: Αίγιο
88
+ expected: Aígio
89
+ - source: Αλεξανδρούπολη
90
+ expected: Alexandroúpolī
91
+ - source: Αλεποχώρι
92
+ expected: Alepochṓri
93
+ - source: Αμοργός
94
+ expected: Amorgós
95
+ - source: Άμφισσα
96
+ expected: Ámfissa
97
+ - source: Αράχωβα
98
+ expected: Aráchōva
99
+ - source: Άργος
100
+ expected: Árgos
101
+ - source: Αρκαδία
102
+ expected: Arkadía
103
+ - source: Άρτα
104
+ expected: Árta
105
+ - source: Βελούχι
106
+ expected: Veloúchi
107
+ - source: Βέροια
108
+ expected: Véroia
109
+ - source: Βοιωτία
110
+ expected: Voiōtía
111
+ - source: Βόλος
112
+ expected: Vólos
113
+ - source: Βόνιτσα
114
+ expected: Vónitsa
115
+ - source: Γαλαξίδι
116
+ expected: Galaxídi
117
+ - source: Γαλάτσι
118
+ expected: Galátsi
119
+ - source: Γιαννιτσά
120
+ expected: Giannitsá
121
+ - source: Γλυφάδα
122
+ expected: Glyfáda
123
+ - source: Γρανίτσα
124
+ expected: Granítsa
125
+ - source: Γρεβενά
126
+ expected: Grevená
127
+ - source: Γύθειο
128
+ expected: Gýtheio
129
+ - source: Διόνυσος
130
+ expected: Diónysos
131
+ - source: Δίστομο
132
+ expected: Dístomo
133
+ - source: Δολιανά
134
+ expected: Dolianá
135
+ - source: Δράμα
136
+ expected: Dráma
137
+ - source: Δωδεκάνησα
138
+ expected: Dōdekánīsa
139
+ - source: Έδεσσα
140
+ expected: Édessa
141
+ - source: Ελευσίνα
142
+ expected: Eleusína
143
+ - source: Επίδαυρος
144
+ expected: Epídauros
145
+ - source: Επτάνησα
146
+ expected: Eptánīsa
147
+ - source: Ερμούπολη
148
+ expected: Ermoúpolī
149
+ - source: Εύβοια
150
+ expected: Eúvoia
151
+ - source: Ζάκυνθος
152
+ expected: Zákynthos
153
+ - source: Ήπειρος
154
+ expected: Ī́peiros
155
+ - source: Ηράκλειο
156
+ expected: Īrákleio
157
+ - source: Θάσος
158
+ expected: Thásos
159
+ - source: Θεσσαλονίκη
160
+ expected: Thessaloníkī
161
+ - source: Θεσσαλία
162
+ expected: Thessalía
163
+ - source: Θεσπρωτία
164
+ expected: Thesprōtía
165
+ - source: Θήβα
166
+ expected: Thī́va
167
+ - source: Θράκη
168
+ expected: Thrákī
169
+ - source: Ιθάκη
170
+ expected: Ithákī
171
+ - source: Ίος
172
+ expected: Íos
173
+ - source: Ιωάννινα
174
+ expected: Iōánnina
175
+ - source: Καβάλα
176
+ expected: Kavála
177
+ - source: Καλάβρυτα
178
+ expected: Kalávryta
179
+ - source: Καλαμάτα
180
+ expected: Kalamáta
181
+ - source: Καλαμπάκα
182
+ expected: Kalampáka
183
+ - source: Καλύβια
184
+ expected: Kalývia
185
+ - source: Κάλυμνος
186
+ expected: Kálymnos
187
+ - source: Καρδίτσα
188
+ expected: Kardítsa
189
+ - source: Καρπενήσι
190
+ expected: Karpenī́si
191
+ - source: Κάρυστος
192
+ expected: Kárystos
193
+ - source: Καστελλόριζο
194
+ expected: Kastellórizo
195
+ - source: Καστοριά
196
+ expected: Kastoriá
197
+ - source: Κατερίνη
198
+ expected: Katerínī
199
+ - source: Κάτω Αχαΐα
200
+ expected: Kátō Achaḯa
201
+ - source: Κερατέα
202
+ expected: Keratéa
203
+ - source: Κέρκυρα
204
+ expected: Kérkyra
205
+ - source: Κεφαλλονιά
206
+ expected: Kefalloniá
207
+ - source: Κηφισιά
208
+ expected: Kīfisiá
209
+ - source: Κιλκίς
210
+ expected: Kilkís
211
+ - source: Κοζάνη
212
+ expected: Kozánī
213
+ - source: Κολωνός
214
+ expected: Kolōnós
215
+ - source: Κομοτηνή
216
+ expected: Komotīnī́
217
+ - source: Κόρινθος
218
+ expected: Kórinthos
219
+ - source: Κορώνη
220
+ expected: Korṓnī
221
+ - source: Κρανίδι
222
+ expected: Kranídi
223
+ - source: Κρέστενα
224
+ expected: Kréstena
225
+ - source: Κρήτη
226
+ expected: Krī́tī
227
+ - source: Κύθηρα
228
+ expected: Kýthīra
229
+ - source: Κυκλάδες
230
+ expected: Kykládes
231
+ - source: Κύμη
232
+ expected: Kýmī
233
+ - source: Κυψέλη
234
+ expected: Kypsélī
235
+ - source: Κως
236
+ expected: Kōs
237
+ - source: Λαγκαδάς
238
+ expected: Lagkadás
239
+ - source: Λαμία
240
+ expected: Lamía
241
+ - source: Λάρισα
242
+ expected: Lárisa
243
+ - source: Λαύριο
244
+ expected: Laúrio
245
+ - source: Λέρος
246
+ expected: Léros
247
+ - source: Λέσβος
248
+ expected: Lésvos
249
+ - source: Λευκάδα
250
+ expected: Leukáda
251
+ - source: Λήμνος
252
+ expected: Lī́mnos
253
+ - source: Λιβαδειά
254
+ expected: Livadeiá
255
+ - source: Μακεδονία
256
+ expected: Makedonía
257
+ - source: Μάνη
258
+ expected: Mánī
259
+ - source: Μαραθώνας
260
+ expected: Marathṓnas
261
+ - source: Μαρκόπουλο
262
+ expected: Markópoulo
263
+ - source: Μαρούσι
264
+ expected: Maroúsi
265
+ - source: Μέγαρα
266
+ expected: Mégara
267
+ - source: Μεσολόγγι
268
+ expected: Mesológgi
269
+ - source: Μεταξουργείο
270
+ expected: Metaxourgeío
271
+ - source: Μέτσοβο
272
+ expected: Métsovo
273
+ - source: Μήλος
274
+ expected: Mī́los
275
+ - source: Μύκονος
276
+ expected: Mýkonos
277
+ - source: Μυστράς
278
+ expected: Mystrás
279
+ - source: Μυτιλήνη
280
+ expected: Mytilī́nī
281
+ - source: Νάξος
282
+ expected: Náxos
283
+ - source: Νάουσα
284
+ expected: Náousa
285
+ - source: Ναύπακτος
286
+ expected: Naúpaktos
287
+ - source: Ναύπλιο
288
+ expected: Naúplio
289
+ - source: Νέα Σμύρνη
290
+ expected: Néa Smýrnī
291
+ - source: Νίσυρος
292
+ expected: Nísyros
293
+ - source: Ξάνθη
294
+ expected: Xánthī
295
+ - source: Όλυμπος
296
+ expected: Ólympos
297
+ - source: Παγκράτι
298
+ expected: Pagkráti
299
+ - source: Παπάγου
300
+ expected: Papágou
301
+ - source: Πάρος
302
+ expected: Páros
303
+ - source: Πασαλιμάνι
304
+ expected: Pasalimáni
305
+ - source: Πατήσια
306
+ expected: Patī́sia
307
+ - source: Πάτμος
308
+ expected: Pátmos
309
+ - source: Πάτρα
310
+ expected: Pátra
311
+ - source: Πειραιάς
312
+ expected: Peiraiás
313
+ - source: Πελοπόννησος
314
+ expected: Pelopónnīsos
315
+ - source: Περιστέρι
316
+ expected: Peristéri
317
+ - source: Πεύκη
318
+ expected: Peúkī
319
+ - source: Πήλιο
320
+ expected: Pī́lio
321
+ - source: Πολύγυρος
322
+ expected: Polýgyros
323
+ - source: Πόρος
324
+ expected: Póros
325
+ - source: Πρέβεζα
326
+ expected: Préveza
327
+ - source: Πτολεμαΐδα
328
+ expected: Ptolemaḯda
329
+ - source: Πύλος
330
+ expected: Pýlos
331
+ - source: Πύργος
332
+ expected: Pýrgos
333
+ - source: Ρέθυμνο
334
+ expected: Réthymno
335
+ - source: Ρόδος
336
+ expected: Ródos
337
+ - source: Ρούμελη
338
+ expected: Roúmelī
339
+ - source: Σαλαμίνα
340
+ expected: Salamína
341
+ - source: Σαμοθράκη
342
+ expected: Samothrákī
343
+ - source: Σάμος
344
+ expected: Sámos
345
+ - source: Σαντορίνη
346
+ expected: Santorínī
347
+ - source: Σέρρες
348
+ expected: Sérres
349
+ - source: Σίκινος
350
+ expected: Síkinos
351
+ - source: Σίφνος
352
+ expected: Sífnos
353
+ - source: Σκιάθος
354
+ expected: Skiáthos
355
+ - source: Σκόπελος
356
+ expected: Skópelos
357
+ - source: Σούλι
358
+ expected: Soúli
359
+ - source: Σπάρτη
360
+ expected: Spártī
361
+ - source: Στερεά Ελλάδα
362
+ expected: Stereá Elláda
363
+ - source: Στύρα
364
+ expected: Stýra
365
+ - source: Σύμη
366
+ expected: Sýmī
367
+ - source: Σύρος
368
+ expected: Sýros
369
+ - source: Σφακιά
370
+ expected: Sfakiá
371
+ - source: Τήλος
372
+ expected: Tī́los
373
+ - source: Τήνος
374
+ expected: Tī́nos
375
+ - source: Τρίκαλα
376
+ expected: Tríkala
377
+ - source: Τρίπολη
378
+ expected: Trípolī
379
+ - source: Τσακωνιά
380
+ expected: Tsakōniá
381
+ - source: Ύδρα
382
+ expected: Ýdra
383
+ - source: Φάληρο
384
+ expected: Fálīro
385
+ - source: Φλώρινα
386
+ expected: Flṓrina
387
+ - source: Φολέγανδρος
388
+ expected: Folégandros
389
+ - source: Χάλκη
390
+ expected: Chálkī
391
+ - source: Χαλκίδα
392
+ expected: Chalkída
393
+ - source: Χαλάνδρι
394
+ expected: Chalándri
395
+ - source: Χαλκιδική
396
+ expected: Chalkidikī́
397
+ - source: Χανιά
398
+ expected: Chaniá
399
+ - source: Χίος
400
+ expected: Chíos
401
+ - source: Ψαρά
402
+ expected: Psará
403
+ - source: Αβάνα
404
+ expected: Avána
405
+ - source: Αγγλία
406
+ expected: Agglía
407
+ - source: Αϊβαλί
408
+ expected: Aïvalí
409
+ - source: Αλεξάνδρεια
410
+ expected: Alexándreia
411
+ - source: Άμστερνταμ
412
+ expected: Ámsterntam
413
+ - source: Βαυαρία
414
+ expected: Vauaría
415
+ - source: Βενετία
416
+ expected: Venetía
417
+ - source: Βερολίνο
418
+ expected: Verolíno
419
+ - source: Βερόνα
420
+ expected: Veróna
421
+ - source: Βιέννη
422
+ expected: Viénnī
423
+ - source: Γένοβα
424
+ expected: Génova
425
+ - source: Δουβλίνο
426
+ expected: Douvlíno
427
+ - source: Καλαβρία
428
+ expected: Kalavría
429
+ - source: Καλιφόρνια
430
+ expected: Kalifórnia
431
+ - source: Καύκασος
432
+ expected: Kaúkasos
433
+ - source: Κονγκό
434
+ expected: Kongkó
435
+ - source: Κορσική
436
+ expected: Korsikī́
437
+ - source: Κουρδιστάν
438
+ expected: Kourdistán
439
+ - source: Κωνσταντινούπολη
440
+ expected: Kōnstantinoúpolī
441
+ - source: Κατεχόμενη Κύπρος
442
+ expected: Katechómenī Kýpros
443
+ - source: Λαπωνία
444
+ expected: Lapōnía
445
+ - source: Λευκωσία
446
+ expected: Leukōsía
447
+ - source: Λιβόρνο
448
+ expected: Livórno
449
+ - source: Λονδίνο
450
+ expected: Londíno
451
+ - source: Λυών
452
+ expected: Lyṓn
453
+ - source: Μάλαγα
454
+ expected: Málaga
455
+ - source: Μασσαλία
456
+ expected: Massalía
457
+ - source: Μικρονησία
458
+ expected: Mikronīsía
459
+ - source: Μιλάνο
460
+ expected: Miláno
461
+ - source: Μόσχα
462
+ expected: Móscha
463
+ - source: Μπολόνια
464
+ expected: Mpolónia
465
+ - source: Νάπολη
466
+ expected: Nápolī
467
+ - source: Νταγκεστάν
468
+ expected: Ntagkestán
469
+ - source: Νέα Υόρκη
470
+ expected: Néa Yórkī
471
+ - source: Οξφόρδη
472
+ expected: Oxfórdī
473
+ - source: Ουαλία
474
+ expected: Oualía
475
+ - source: Παρίσι
476
+ expected: Parísi
477
+ - source: Πάφος
478
+ expected: Páfos
479
+ - source: Πολυνησία
480
+ expected: Polynīsía
481
+ - source: Ρώμη
482
+ expected: Rṓmī
483
+ - source: Σαμάρεια
484
+ expected: Samáreia
485
+ - source: Σικελία
486
+ expected: Sikelía
487
+ - source: Σκανδιναβία
488
+ expected: Skandinavía
489
+ - source: Σκόπια
490
+ expected: Skópia
491
+ - source: Σκωτία
492
+ expected: Skōtía
493
+ - source: Σμύρνη
494
+ expected: Smýrnī
495
+ - source: Ταϊτή
496
+ expected: Taïtī́
497
+ - source: Ταταρστάν
498
+ expected: Tatarstán
499
+ - source: Τζαμάικα
500
+ expected: Tzamáika
501
+ - source: Τηλλυρία
502
+ expected: Tīllyría
503
+ - source: Τιρόλο
504
+ expected: Tirólo
505
+ - source: Τορίνο
506
+ expected: Toríno
507
+ - source: Φανάρι
508
+ expected: Fanári
509
+ - source: Φλωρεντία
510
+ expected: Flōrentía
511
+ - source: Χαβάη
512
+ expected: Chaváī
513
+ - source: Χονγκ Κονγκ
514
+ expected: Chongk Kongk
515
+
516
+ map:
517
+ # https://en.wikipedia.org/wiki/Romanization_of_Greek
518
+ rules:
519
+ - pattern: (?<=[ΑαΕεΟο])\u03A5 # Υ (after Α, Ε, Η)
520
+ result: U
521
+ - pattern: (?<=[ΑαΕεΟο])\u03C5 # υ (after Α, Ε, Η)
522
+ result: u
523
+ - pattern: (?<=[ΑαΕεΟο])\u03CD # ύ (after Ο)
524
+ result: ú
525
+ - pattern: \u037E # ;
526
+ result: "?"
527
+ - pattern: \u003B # ;
528
+ result: "?"
529
+
530
+ characters:
531
+ "\u0027": ""
532
+ "\u0386": "Á" # Ά
533
+ "\u0391": "A" # Α
534
+ "\u0392": "V" # Β
535
+ "\u0393": "G" # Γ
536
+ "\u0394": "D" # Δ
537
+ "\u0395": "E" # Ε
538
+ "\u0396": "Z" # Ζ
539
+ "\u0397": "Ī" # Η
540
+ "\u0398": "Th" # Θ
541
+ "\u0399": "I" # Ι
542
+ "\u039A": "K" # Κ
543
+ "\u039B": "L" # Λ
544
+ "\u039C": "M" # Μ
545
+ "\u039D": "N" # Ν
546
+ "\u039E": "X" # Ξ
547
+ "\u039F": "O" # Ο
548
+ "\u03A0": "P" # Π
549
+ "\u03A1": "R" # Ρ
550
+ "\u03A3": "S" # Σ
551
+ "\u03A4": "T" # Τ
552
+ "\u03A5": "Y" # Υ
553
+ "\u03A6": "F" # Φ
554
+ "\u03A7": "Ch" # Χ
555
+ "\u03A8": "Ps" # Ψ
556
+ "\u03A9": "Ō" # Ω
557
+ "\u0388": "É" # Έ
558
+ "\u0389": "Ī́" # Ή
559
+ "\u038A": "Í" # Ί
560
+ "\u038C": "Ó" # Ό
561
+ "\u038E": "Ý" # Ύ
562
+ "\u038F": "Ṓ" # Ώ
563
+ "\u03AA": "Ï" # Ϊ
564
+ "\u03AB": "Ÿ" # Ϋ
565
+
566
+ "\u03AC": "á" # ά
567
+ "\u03B1": "a" # α
568
+ "\u03B2": "v" # β
569
+ "\u03B3": "g" # γ
570
+ "\u03B4": "d" # δ
571
+ "\u03B5": "e" # ε
572
+ "\u03B6": "z" # ζ
573
+ "\u03B7": "ī" # η
574
+ "\u03B8": "th" # θ
575
+ "\u03B9": "i" # ι
576
+ "\u03BA": "k" # κ
577
+ "\u03BB": "l" # λ
578
+ "\u03BC": "m" # μ
579
+ "\u03BD": "n" # ν
580
+ "\u03BE": "x" # ξ
581
+ "\u03BF": "o" # ο
582
+ "\u03C0": "p" # π
583
+ "\u03C1": "r" # ρ
584
+ "\u03C3": "s" # σ
585
+ "\u03C2": "s" # ς
586
+ "\u03C4": "t" # τ
587
+ "\u03C5": "y" # υ
588
+ "\u03C6": "f" # φ
589
+ "\u03C7": "ch" # χ
590
+ "\u03C8": "ps" # ψ
591
+ "\u03C9": "ō" # ω
592
+ "\u03AD": "é" # έ
593
+ "\u03AE": "ī́" # ή
594
+ "\u03AF": "í" # ί
595
+ "\u03CC": "ó" # ό
596
+ "\u03CD": "ý" # ύ
597
+ "\u03CE": "ṓ" # ώ
598
+ "\u03CA": "ï" # ϊ
599
+ "\u03CB": "ÿ" # ϋ
600
+ "\u0390": "ḯ" # ΐ
601
+ "\u03B0": "ÿ́" # ΰ
602
+
603
+ "\u03DC": "W" # Ϝ
604
+ "\u03DD": "w" # ϝ
605
+ "\u03F2": "s" # ϲ
606
+ "\u03F9": "S" # Ϲ
607
+
608
+ "\u0387": ";" # ·
609
+ "\u00B7": ";" # ·
610
+