interscript 0.1.0 → 0.1.5

data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml

@@ -0,0 +1,41 @@
+---
+authority_id: iso
+id: 1997
+language: ell
+source_script: Grek
+destination_script: Latn
+name: ISO 843:1997
+url: 
+creation_date: 1997
+description: |
+  ISO Transcription table for Greek
+
+note:
+  - Transliteration of Greek into Latin: Type 2, Clause 3 Table 2
+  - Introduced casing to digamma, yot, and lunate sigma. (Casing was late introduction to character sets for those characters)
+
+tests:
+
+  - source: |
+        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.
+
+        Γιάννης Μακρυγιάννης.
+
+    expected: |
+        Éna práma mónon me parakínise ki eména na grápso óti toútin tin patrída tin échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai ftochoí kai politikoí kai stratiotikoí kai oi pléon mikróteroi ánthropoi; ósoi agonistíkamen, analógos o katheís, échomen na zísomen edó. To loipón doulépsamen óloi mazí, na tin fylámen ki óloi mazí kai na min légei oúte o dynatós «egó» oúte o adýnatos. Xérete póte na légei o katheís «egó»? Ótan agonisteí mónos tou kai fkiásei í chalásei, na légei «egó»; ótan ómos agonízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egó». Kai eis to exís na máthomen gnósi, an thélomen na fkiásomen chorión, na zísomen óloi mazí.
+
+        Giánnis Makrygiánnis.
+
+map:
+  character_separator: ""
+  word_separator: " "
+  inherit: "elot-ell-Grek-Latn-743-1982-ts"
+
+  characters:
+    "\u03DC": "W"   # Ϝ
+    "\u03DD": "w"   # ϝ
+    "\u03F2": "s"   # ϲ
+    "\u03F9": "S"   # Ϲ
+    "\u03F3": "j"
+    "\u037F": "j"
+

data/maps/iso-jpn-Hrkt-Latn-3602-1989.yaml

@@ -0,0 +1,62 @@
+---
+authority_id: iso
+id: 3602-1989
+language: jpn
+source_script: Hrkt
+destination_script: Latn
+name: ISO 3602 Romanization of Japanese (Kana Script)
+url:
+creation_date:
+adoption_date:
+description:
+
+notes:
+
+tests:
+  - source: かんおう
+    expected: kan’ô
+  - source: かのう
+    expected: kanô
+  - source: きんゆう
+    expected: kin’yû
+  - source: とうきょう
+    expected: tôkyô
+  - source: がっ•こう
+    expected: gakkô
+  - source: かごっま
+    expected: kagomma
+  - source: ぽっぽっや
+    expected: poppoyya
+  - source: てっら
+    expected: terra
+  - source: にゃっほー
+    expected: nyahhô
+  - source: ゴッホ
+    expected: gohho
+  - source: おも•う
+    expected: omou
+  - source: こうし
+    expected: kôsi
+  - source: こう•し #格子
+    expected: kôsi
+  - source: こ•うし #子牛
+    expected: kousi
+  - source: ぎゃあ
+    expected: gyâ
+
+map:
+  inherit: mext-jpn-Hrkt-Latn-1954
+
+  rules:
+    # Remove morpheme boundary marker after sokuon っ/ッ
+    - pattern: "([っッ])•"
+      result: "\\1"
+
+  postrules:
+    # Remove morpheme boundary marker
+    - pattern: "•"
+      result: ""
+
+    # Use ’ instead of '
+    - pattern: "'"
+      result: "’"

data/maps/iso-rus-Cyrl-Latn-9-1995.yaml

@@ -0,0 +1,272 @@
+---
+authority_id: iso
+id: 9-1995
+language: rus
+source_script: Cyrl
+destination_script: Latn
+name: ISO 9
+url: https://www.iso.org/standard/3589.html
+creation_date: 1995
+description: |
+  Establishes a system for the transliteration into Latin characters of
+  Cyrillic characters constituting the alphabets of Slavic and non-Slavic
+  languages. Table 3 includes in a single sequence, listed in the
+  Cyrillic alphabetic order, the 118 single or diacritic-carrying
+  characters that appear in one or another of the considered alphabets.
+tests:
+
+
+map:
+  characters:
+    "\u0410": "A"                              # А => A
+    "\u04d2": "\u00c4"                         # Ӓ => Ä (a diaeresis)
+    "\u04d2\u0304": "\u1ea0\u0308"             # Ӓ̄ => Ạ̈ (a diaeresis and dot below)
+    "\u04d0": "\u0102"                         # Ӑ => Ă (a breve)
+    "\u0410\u0304": "\u0100"                   # А̄ => Ā (a macron)
+    "\u04d4": "\u00c6"                         # Ӕ => Æ (ae ligature)
+    "\u0410\u0301": "\u00c1"                   # А́ => Á (a acute)
+    "\u0410\u030a": "\u00c5"                   # А̊ => Å (a ring)
+    "\u0411": "B"                              # Б => B
+    "\u0412": "V"                              # В => V
+    "\u0413": "G"                              # Г => G
+    "\u0403": "\u01f4"                         # Ѓ => Ǵ (g acute)
+    "\u0492": "\u0120"                         # Ғ => Ġ (g dot)
+    "\u0494": "\u011e"                         # Ҕ => Ğ (g breve)
+    "\u04ba": "\u1e24"                         # Һ => Ḥ (h dot)
+    "\u0414": "D"                              # Д => D
+    "\u0402": "\u0110"                         # Ђ => Đ (d macron)
+    "\u0415": "E"                              # Е => E
+    "\u04d6": "\u0114"                         # Ӗ => Ĕ (e breve)
+    "\u0401": "\u00cb"                         # Ё => Ë (e diaeresis)
+    "\u0404": "\u00ca"                         # Є => Ê (e circumflex)
+    "\u0416": "\u017d"                         # Ж => Ž (z caron)
+    "\u0496": "\u017d\u0327"                   # Җ => Ž̧ (z caron and cedilla[4])
+    "\u04dc": "\u005a\u0304"                   # Ӝ => Z̄ (z macron)
+    "\u04c1": "\u005a\u0306"                   # Ӂ => Z̆ (z breve)
+    "\u0417": "\u005a"                         # З => Z
+    "\u04de": "\u005a\u0308"                   # Ӟ => Z̈ (z diaeresis)
+    "\u04e0": "\u0179"                         # Ӡ => Ź (z acute)
+    "\u0405": "\u1e90"                         # Ѕ => Ẑ (z circumflex)
+    "\u0418": "I"                              # И => I
+    "\u04e2": "\u012a"                         # Ӣ => Ī (i macron)
+    "\u0418\u0301": "\u00cd"                   # И́ => Í (i acute)
+    "\u04e4": "\u00ce"                         # Ӥ => Î (i circumflex)
+    "\u0419": "\u004a"                         # Й => J
+    "\u0406": "\u00cc"                         # І => Ì (i grave)
+    "\u0407": "\u00cf"                         # Ї => Ï (i diaeresis)
+    "\u0406\u0304": "\u01cf"                   # І̄ => Ǐ (i caron (or breve))
+    "\u0408": "\u004a\u030c"                   # Ј => J̌ (j caron)
+    "\u0408\u0335": "\u004a\u0301"             # Ј̵ => J́ (j acute)
+    "\u041a": "K"                              # К => K
+    "\u040c": "\u1e30"                         # Ќ => Ḱ (k acute)
+    "\u04c3": "\u1e32"                         # Ӄ => Ḳ (k dot below)
+    "\u049c": "\u004b\u0302"                   # Ҝ => K̂ (k circumflex)
+    "\u04a0": "\u01e8"                         # Ҡ => Ǩ (k caron)
+    "\u049e": "\u004b\u0304"                   # Ҟ => K̄ (k macron)
+    "\u049a": "\u0136"                         # Қ => Ķ (k cedilla[4])
+    "\u041a\u0328": "\u004b\u0300"             # К̨ => K̀ (k grave)
+    "\u051a": "Q"                              # Ԛ => Q
+    "\u041b": "L"                              # Л => L
+    "\u0409": "\u004c\u0302"                   # Љ => L̂ (l circumflex)
+    "\u0520": "\u013b"                         # Ԡ => Ļ (l cedilla[4])
+    "\u041c": "M"                              # М => M
+    "\u041d": "N"                              # Н => N
+    "\u040a": "\u004e\u0302"                   # Њ => N̂ (n circumflex)
+    "\u04a2": "\u0145"                         # Ң => Ņ (n cedilla[4])
+    "\u04c9": "\u1e46"                         # Ӊ => Ṇ (n dot below)
+    "\u04a4": "\u1e44"                         # Ҥ => Ṅ (n dot)
+    "\u050a": "\u01f8"                         # Ԋ => Ǹ (n grave)
+    "\u0522": "\u0143"                         # Ԣ => Ń (n acute)
+    "\u04c7": "\u0147"                         # Ӈ => Ň (n caron)
+    "\u041d\u0304": "\u004e\u0304"             # Н̄ => N̄ (n macron)
+    "\u041e": "O"                              # О => O
+    "\u04e6": "\u00d6"                         # Ӧ => Ö (o diaeresis)
+    "\u04e8": "\u00d4"                         # Ө => Ô (o circumflex)
+    "\u04ea": "\u0150"                         # Ӫ => Ő (o double acute)
+    "\u04e6\u0304": "\u1ecc\u0308"             # Ӧ̄ => Ọ̈ (o diaeresis and dot below)
+    "\u04a8": "\u00d2"                         # Ҩ => Ò (o grave)
+    "\u041e\u0301": "\u00d3"                   # О́ => Ó (o acute)
+    "\u041e\u0304": "\u014c"                   # О̄ => Ō (o macron)
+    "\u0152": "\u0152"                         # Π=> Π(oe ligature)
+    "\u041f": "P"                              # П => P
+    "\u04a6": "\u1e54"                         # Ҧ => Ṕ (p acute)
+    "\u0524": "\u0050\u0300"                   # Ԥ => P̀ (p grave)
+    "\u0420": "R"                              # Р => R
+    "\u0421": "S"                              # С => S
+    "\u04aa": "\u015e"                         # Ҫ => Ş (s cedilla[4])
+    "\u0421\u0300": "\u0053\u0300"             # С̀ => S̀ (s grave)
+    "\u0422": "T"                              # Т => T
+    "\u040b": "\u0106"                         # Ћ => Ć (c acute)
+    "\u050e": "\u0054\u0300"                   # Ԏ => T̀ (t grave)
+    "\u0422\u030c": "\u0164"                   # Т̌ => Ť (t caron)
+    "\u04ac": "\u0162"                         # Ҭ => Ţ (t cedilla[4])
+    "\u0423": "U"                              # У => U
+    "\u04f0": "\u00dc"                         # Ӱ => Ü (u diaeresis)
+    "\u04ee": "\u016a"                         # Ӯ => Ū (u macron)
+    "\u040e": "\u016c"                         # Ў => Ŭ (u breve)
+    "\u04f2": "\u0170"                         # Ӳ => Ű (u double acute)
+    "\u0423\u0301": "\u00da"                   # У́ => Ú (u acute)
+    "\u04f0\u0304": "\u1ee4\u0308"             # Ӱ̄ => Ụ̈ (u diaeresis and dot below)
+    "\u04ae": "\u00d9"                         # Ү => Ù (u grave)
+    "\u04b0": "\u0055\u0307"                   # Ұ => U̇ (u dot)
+    "\u051c": "W"                              # Ԝ => W
+    "\u0424": "F"                              # Ф => F
+    "\u0425": "H"                              # Х => H
+    "\u04b2": "\u1e28"                         # Ҳ => Ḩ (h cedilla[4])
+    "\u0426": "C"                              # Ц => C
+    "\u04b4": "\u0043\u0304"                   # Ҵ => C̄ (c macron)
+    "\u040f": "\u0044\u0302"                   # Џ => D̂ (d circumflex)
+    "\u0427": "\u010c"                         # Ч => Č (c caron)
+    "\u04b6": "\u00c7"                         # Ҷ => Ç (c cedilla[4])
+    "\u04cb": "\u0043\u0323"                   # Ӌ => C̣ (c dot below)
+    "\u04f4": "\u0043\u0308"                   # Ӵ => C̈ (c diaeresis)
+    "\u04b8": "\u0108"                         # Ҹ => Ĉ (c circumflex)
+    "\u0427\u0300": "\u0043\u0300"             # Ч̀ => C̀ (c grave)
+    "\u04bc": "\u0043\u0306"                   # Ҽ => C̆ (c breve)
+    "\u04be": "\u0043\u0328\u0306"             # Ҿ => C̨̆ (c ogonek[4] and breve)
+    "\u0428": "\u0160"                         # Ш => Š (s caron)
+    "\u0429": "\u015c"                         # Щ => Ŝ (s circumflex)
+    "\u042a": "\u02ba"                         # Ъ => ʺ (modifier letter double prime[5])
+    "\u042b": "Y"                              # Ы => Y
+    "\u04f8": "\u0178"                         # Ӹ => Ÿ (y diaeresis)
+    "\u042b\u0304": "\u0232"                   # Ы̄ => Ȳ (y macron)
+    "\u042c": "\u02b9"                         # Ь => ʹ (modifier letter prime[5])
+    "\u042d": "\u00c8"                         # Э => È (e grave)
+    "\u04d8": "\u0041\u030b"                   # Ә => A̋ (a double acute)
+    "\u04da": "\u00c0"                         # Ӛ => À (a grave)
+    "\u042e": "\u00db"                         # Ю => Û (u circumflex)
+    "\u042e\u0304": "\u00db\u0304"             # Ю̄ => Û̄ (u circumflex with macron)
+    "\u042f": "\u00c2"                         # Я => Â (a circumflex)
+    "\u0490": "\u0047\u0300"                   # Ґ => G̀ (g grave)
+    "\u0462": "\u011a"                         # Ѣ => Ě (e caron)
+    "\u046a": "\u01cd"                         # Ѫ => Ǎ (a caron)
+    "\u0472": "\u0046\u0300"                   # Ѳ => F̀ (f grave)
+    "\u0474": "\u1ef2"                         # Ѵ => Ỳ (y grave)
+    "\u0430": "a"                              # а => a
+    "\u04d3": "\u00e4"                         # ӓ => ä
+    "\u04d3\u0304": "\u1ea1\u0308"             # ӓ̄ => ạ̈
+    "\u04d1": "\u0103"                         # ӑ => ă
+    "\u0430\u0304": "\u0101"                   # а̄ => ā
+    "\u04d5": "\u00e6"                         # ӕ => æ
+    "\u0430\u0301": "\u00e1"                   # а́ => á
+    "\u0430\u030a": "\u00e5"                   # а̊ => å
+    "\u0431": "b"                              # б => b
+    "\u0432": "v"                              # в => v
+    "\u0433": "g"                              # г => g
+    "\u0453": "\u01f5"                         # ѓ => ǵ
+    "\u0493": "\u0121"                         # ғ => ġ
+    "\u0495": "\u011f"                         # ҕ => ğ
+    "\u04bb": "\u1e25"                         # һ => ḥ
+    "\u0434": "d"                              # д => d
+    "\u0452": "\u0111"                         # ђ => đ
+    "\u0435": "e"                              # е => e
+    "\u04d7": "\u0115"                         # ӗ => ĕ
+    "\u0451": "\u00eb"                         # ё => ë
+    "\u0454": "\u00ea"                         # є => ê
+    "\u0436": "\u017e"                         # ж => ž
+    "\u0497": "\u017e\u0327"                   # җ => ž̧
+    "\u04dd": "\u007a\u0304"                   # ӝ => z̄
+    "\u04c2": "\u007a\u0306"                   # ӂ => z̆
+    "\u0437": "z"                              # з => z
+    "\u04df": "\u007a\u0308"                   # ӟ => z̈
+    "\u04e1": "\u017a"                         # ӡ => ź
+    "\u0455": "\u1e91"                         # ѕ => ẑ
+    "\u0438": "i"                              # и => i
+    "\u04e3": "\u012b"                         # ӣ => ī
+    "\u0438\u0301": "\u00ed"                   # и́ => í
+    "\u04e5": "\u00ee"                         # ӥ => î
+    "\u0439": "j"                              # й => j
+    "\u0456": "\u00ec"                         # і => ì
+    "\u0457": "\u00ef"                         # ї => ï
+    "\u0456\u0304": "\u01d0"                   # і̄ => ǐ
+    "\u0458": "\u01f0"                         # ј => ǰ
+    "\u0458\u0335": "\u006a\u0301"             # ј̵ => j́
+    "\u043a": "k"                              # к => k
+    "\u045c": "\u1e31"                         # ќ => ḱ
+    "\u04c4": "\u1e33"                         # ӄ => ḳ
+    "\u049d": "\u006b\u0302"                   # ҝ => k̂
+    "\u04a1": "\u01e9"                         # ҡ => ǩ
+    "\u049f": "\u006b\u0304"                   # ҟ => k̄
+    "\u049b": "\u0137"                         # қ => ķ
+    "\u043a\u0328": "\u006b\u0300"             # к̨ => k̀
+    "\u051b": "q"                              # ԛ => q
+    "\u043b": "l"                              # л => l
+    "\u0459": "\u006c\u0302"                   # љ => l̂
+    "\u0521": "\u013c"                         # ԡ => ļ
+    "\u043c": "m"                              # м => m
+    "\u043d": "n"                              # н => n
+    "\u045a": "\u006e\u0302"                   # њ => n̂
+    "\u04a3": "\u0146"                         # ң => ņ
+    "\u04ca": "\u1e47"                         # ӊ => ṇ
+    "\u04a5": "\u1e45"                         # ҥ => ṅ
+    "\u050b": "\u01f9"                         # ԋ => ǹ
+    "\u0523": "\u0144"                         # ԣ => ń
+    "\u04c8": "\u0148"                         # ӈ => ň
+    "\u043d\u0304": "\u006e\u0304"             # н̄ => n̄
+    "\u043e": "o"                              # о => o
+    "\u04e7": "\u00f6"                         # ӧ => ö
+    "\u04e9": "\u00f4"                         # ө => ô
+    "\u04eb": "\u0151"                         # ӫ => ő
+    "\u043e\u0304\u0308": "\u1ecd\u0308"       # о̄̈ => ọ̈
+    "\u04a9": "\u00f2"                         # ҩ => ò
+    "\u043e\u0301": "\u00f3"                   # о́ => ó
+    "\u043e\u0304": "\u014d"                   # о̄ => ō
+    "\u0153": "\u0153"                         # œ => œ
+    "\u043f": "p"                              # п => p
+    "\u04a7": "\u1e55"                         # ҧ => ṕ
+    "\u0525": "\u0070\u0300"                   # ԥ => p̀
+    "\u0440": "r"                              # р => r
+    "\u0441": "s"                              # с => s
+    "\u04ab": "\u015f"                         # ҫ => ş
+    "\u0441\u0300": "\u0073\u0300"             # с̀ => s̀
+    "\u0442": "t"                              # т => t
+    "\u045b": "\u0107"                         # ћ => ć
+    "\u050f": "\u0074\u0300"                   # ԏ => t̀
+    "\u0442\u030c": "\u0165"                   # т̌ => ť
+    "\u04ad": "\u0163"                         # ҭ => ţ
+    "\u0443": "u"                              # у => u
+    "\u04f1": "\u00fc"                         # ӱ => ü
+    "\u04ef": "\u016b"                         # ӯ => ū
+    "\u045e": "\u016d"                         # ў => ŭ
+    "\u04f3": "\u0171"                         # ӳ => ű
+    "\u0443\u0301": "\u00fa"                   # у́ => ú
+    "\u04f1\u0304": "\u1ee5\u0308"             # ӱ̄ => ụ̈
+    "\u04af": "\u00f9"                         # ү => ù
+    "\u04b1": "\u0075\u0307"                   # ұ => u̇
+    "\u051d": "w"                              # ԝ => w
+    "\u0444": "f"                              # ф => f
+    "\u0445": "h"                              # х => h
+    "\u04b3": "\u1e29"                         # ҳ => ḩ
+    "\u0446": "c"                              # ц => c
+    "\u04b5": "\u0063\u0304"                   # ҵ => c̄
+    "\u045f": "\u0064\u0302"                   # џ => d̂
+    "\u0447": "\u010d"                         # ч => č
+    "\u04b7": "\u00e7"                         # ҷ => ç
+    "\u04cc": "\u0063\u0323"                   # ӌ => c̣
+    "\u04f5": "\u0063\u0308"                   # ӵ => c̈
+    "\u04b9": "\u0109"                         # ҹ => ĉ
+    "\u0447\u0300": "\u0063\u0300"             # ч̀ => c̀
+    "\u04bd": "\u0063\u0306"                   # ҽ => c̆
+    "\u04bf": "\u0063\u0328\u0306"             # ҿ => c̨̆
+    "\u0448": "\u0161"                         # ш => š
+    "\u0449": "\u015d"                         # щ => ŝ
+    "\u044a": "\u02ba"                         # ъ => ʺ
+    "\u044b": "y"                              # ы => y
+    "\u04f9": "\u00ff"                         # ӹ => ÿ
+    "\u044b\u0304": "\u0233"                   # ы̄ => ȳ
+    "\u044c": "\u02b9"                         # ь => ʹ
+    "\u044d": "\u00e8"                         # э => è
+    "\u04d9": "\u0061\u030b"                   # ә => a̋
+    "\u04db": "\u00e0"                         # ӛ => à
+    "\u044e": "\u00fb"                         # ю => û
+    "\u044e\u0304": "\u00fb\u0304"             # ю̄ => û̄
+    "\u044f": "\u00e2"                         # я => â
+    "\u0491": "\u0067\u0300"                   # ґ => g̀
+    "\u0463": "\u011b"                         # ѣ => ě
+    "\u046b": "\u01ce"                         # ѫ => ǎ
+    "\u0473": "\u0066\u0300"                   # ѳ => f̀
+    "\u0475": "\u1ef3"                         # ѵ => ỳ
+    "\u04c0": "\u2021"                         # Ӏ	=> ‡
+    "\u02bc": "\u0060"                         # ʼ	=> `
+    "\u02ee": "\u00a8"                         # ˮ => ¨
+

data/maps/iso-tha-Thai-Latn-11940-1998.yaml

@@ -0,0 +1,109 @@
+---
+authority_id: iso
+id: 11940-1998
+language: tha
+source_script: Thai
+destination_script: Latn
+name: ISO 11940:1998 Information and documentation -- Transliteration of Thai
+url: https://www.iso.org/standard/20574.html
+creation_date: 1998
+adoption_date: 
+description:
+
+notes:
+
+tests:
+  - source: 'ภาษาไทย'
+    expected: 'p̣hās̛̄āịthy'
+  - source: 'เชียงใหม่'
+    expected: 'echīyngıh̄m̀'
+
+map:
+
+  characters:
+    '\u0e01': 'k' # ก THAI CHARACTER KO KAI
+    '\u0e02': 'k̄h' # ข THAI CHARACTER KHO KHAI
+    '\u0e03': 'ḳ̄h' # ฃ THAI CHARACTER KHO KHUAT
+    '\u0e04': 'kh' # ค THAI CHARACTER KHO KHWAI
+    '\u0e05': 'k̛h' # ฅ THAI CHARACTER KHO KHON
+    '\u0e06': 'ḳh' # ฆ THAI CHARACTER KHO RAKHANG
+    '\u0e07': 'ng' # ง THAI CHARACTER NGO NGU
+    '\u0e08': 'c' # จ THAI CHARACTER CHO CHAN
+    '\u0e09': 'c̄h' # ฉ THAI CHARACTER CHO CHING
+    '\u0e0a': 'ch' # ช THAI CHARACTER CHO CHANG
+    '\u0e0b': 's' # ซ THAI CHARACTER SO SO
+    '\u0e0c': 'c̣h' # ฌ THAI CHARACTER CHO CHOE
+    '\u0e0d': 'ỵ' # ญ THAI CHARACTER YO YING
+    '\u0e0e': 'ḍ' # ฎ THAI CHARACTER DO CHADA
+    '\u0e0f': 'ṭ' # ฏ THAI CHARACTER TO PATAK
+    '\u0e10': 'ṭ̄h' # ฐ THAI CHARACTER THO THAN
+    '\u0e11': 'ṯh' # ฑ THAI CHARACTER THO NANGMONTHO
+    '\u0e12': 't̛h' # ฒ THAI CHARACTER THO PHUTHAO
+    '\u0e13': 'ṇ' # ณ THAI CHARACTER NO NEN
+    '\u0e14': 'd' # ด THAI CHARACTER DO DEK
+    '\u0e15': 't' # ต THAI CHARACTER TO TAO
+    '\u0e16': 't̄h' # ถ THAI CHARACTER THO THUNG
+    '\u0e17': 'th' # ท THAI CHARACTER THO THAHAN
+    '\u0e18': 'ṭh' # ธ THAI CHARACTER THO THONG
+    '\u0e19': 'n' # น THAI CHARACTER NO NU
+    '\u0e1a': 'b' # บ THAI CHARACTER BO BAIMAI
+    '\u0e1b': 'p' # ป THAI CHARACTER PO PLA
+    '\u0e1c': 'p̄h' # ผ THAI CHARACTER PHO PHUNG
+    '\u0e1d': 'f̄' # ฝ THAI CHARACTER FO FA
+    '\u0e1e': 'ph' # พ THAI CHARACTER PHO PHAN
+    '\u0e1f': 'f' # ฟ THAI CHARACTER FO FAN
+    '\u0e20': 'p̣h' # ภ THAI CHARACTER PHO SAMPHAO
+    '\u0e21': 'm' # ม THAI CHARACTER MO MA
+    '\u0e22': 'y' # ย THAI CHARACTER YO YAK
+    '\u0e23': 'r' # ร THAI CHARACTER RO RUA
+    '\u0e24': 'v' # ฤ THAI CHARACTER RU
+    '\u0e25': 'l' # ล THAI CHARACTER LO LING
+    '\u0e26': 'ł' # ฦ THAI CHARACTER LU
+    '\u0e27': 'w' # ว THAI CHARACTER WO WAEN
+    '\u0e28': 'ṣ̄' # ศ THAI CHARACTER SO SALA
+    '\u0e29': 's̛̄' # ษ THAI CHARACTER SO RUSI
+    '\u0e2a': 's̄' # ส THAI CHARACTER SO SUA
+    '\u0e2b': 'h̄' # ห THAI CHARACTER HO HIP
+    '\u0e2c': 'ḷ' # ฬ THAI CHARACTER LO CHULA
+    '\u0e2d': 'x' # อ THAI CHARACTER O ANG
+    '\u0e2e': 'ḥ' # ฮ THAI CHARACTER HO NOKHUK
+    '\u0e2f': 'ǂ' # ฯ THAI CHARACTER PAIYANNOI
+    '\u0e30': 'a' # ะ THAI CHARACTER SARA A
+    '\u0e31': 'ạ' # ั THAI CHARACTER MAI HAN-AKAT
+    '\u0e32': 'ā' # า THAI CHARACTER SARA AA
+    '\u0e33': 'å' # ำ THAI CHARACTER SARA AM
+    '\u0e34': 'i' # ิ THAI CHARACTER SARA I
+    '\u0e35': 'ī' # ี THAI CHARACTER SARA II
+    '\u0e36': 'ụ' # ึ THAI CHARACTER SARA UE
+    '\u0e37': 'ụ̄' # ื THAI CHARACTER SARA UEE
+    '\u0e38': 'u' # ุ THAI CHARACTER SARA U
+    '\u0e39': 'ū' # ู THAI CHARACTER SARA UU
+    '\u0e3a': '–̥' # ฺ THAI CHARACTER PHINTHU
+    '\u0e40': 'e' # เ THAI CHARACTER SARA E
+    '\u0e41': 'æ' # แ THAI CHARACTER SARA AE
+    '\u0e42': 'o' # โ THAI CHARACTER SARA O
+    '\u0e43': 'ı' # ใ THAI CHARACTER SARA AI MAIMUAN
+    '\u0e44': 'ị' # ไ THAI CHARACTER SARA AI MAIMALAI
+    '\u0e45': 'ɨ' # ๅ THAI CHARACTER LAKKHANGYAO
+    '\u0e46': '«' # ๆ THAI CHARACTER MAIYAMOK
+    '\u0e47': '̆' # ็ THAI CHARACTER MAITAIKHU
+    '\u0e48': '̀' # ่ THAI CHARACTER MAI EK
+    '\u0e49': '̂' # ้ THAI CHARACTER MAI THO
+    '\u0e4a': '́' # ๊ THAI CHARACTER MAI TRI
+    '\u0e4b': '̌' # ๋ THAI CHARACTER MAI CHATTAWA
+    '\u0e4c': '̒' # ์ THAI CHARACTER THANTHAKHAT
+    '\u0e4d': '̊' # ํ THAI CHARACTER NIKHAHIT
+    '\u0e4e': '~' # ๎ THAI CHARACTER YAMAKKAN
+    '\u0e4f': '§' # ๏ THAI CHARACTER FONGMAN
+    '\u0e50': '0' # ๐ THAI DIGIT ZERO
+    '\u0e51': '1' # ๑ THAI DIGIT ONE
+    '\u0e52': '2' # ๒ THAI DIGIT TWO
+    '\u0e53': '3' # ๓ THAI DIGIT THREE
+    '\u0e54': '4' # ๔ THAI DIGIT FOUR
+    '\u0e55': '5' # ๕ THAI DIGIT FIVE
+    '\u0e56': '6' # ๖ THAI DIGIT SIX
+    '\u0e57': '7' # ๗ THAI DIGIT SEVEN
+    '\u0e58': '8' # ๘ THAI DIGIT EIGHT
+    '\u0e59': '9' # ๙ THAI DIGIT NINE
+    '\u0e5a': 'ǁ' # ๚ THAI CHARACTER ANGKHANKHU
+    '\u0e5b': '»' # ๛ THAI CHARACTER KHOMUT