interscript 0.1.3 → 0.1.9

data/maps/iso-kor-Hang-Latn-1996-method1.yaml

@@ -0,0 +1,240 @@
+---
+authority_id: iso
+id: 1996-method1
+language: iso-639-2:kor
+source_script: Hang
+destination_script: Latn
+name: "ISO/TR 11941:1996 Information and documentation — Transliteration of Korean script into Latin characters"
+url: https://www.iso.org/standard/20564.html
+creation_date: 1996
+adoption_date:
+description: Establishes a system for the transliteration of the characters of Korean script into Latin characters. Intended to provide a means for international communication of written documents.
+
+notes: ""
+
+tests:
+  # Tests from https://www.eki.ee/wgrs/rom2_ko.pdf
+  - source: "꽃이"
+    expected: "kkoch'i" # Bad OCR
+  - source: "강에"
+    expected: "kang'e"
+  - source: "앉아라"
+    expected: "anc'ara"
+  - source: "아까"
+    expected: "a'kka"
+  - source: "흰떡"
+    expected: "hyin'tteok"
+  - source: "유쾌하다"
+    expected: "yu'khwaehata"
+
+  # Tests from https://github.com/interscript/interscript/files/5249245/ISO-TR-11941-1996.pdf
+  - source: "애기"
+    expected: "aeki"
+  - source: "방"
+    expected: "pang"
+  - source: "아이"
+    expected: "a'i"
+  - source: "고양이"
+    expected: "ko'yang'i"
+  - source: "굽이"
+    expected: "kup'i"
+  - source: "밖에"
+    expected: "pakk'e"
+  - source: "박게"
+    expected: "pakke"
+  - source: "바께"
+    expected: "pa'kke"
+  - source: "간게"
+    expected: "kanke"
+  - source: "안자라"
+    expected: "ancara"
+  - source: "오빠"
+    expected: "o'ppa"
+  - source: "어찌"
+    expected: "eo'cci"
+  - source: "아씨"
+    expected: "a'ssi"
+  - source: "애타다"
+    expected: "ae'thata"
+  - source: "아프다"
+    expected: "a'pheuta"
+  - source: "기차다"
+    expected: "ki'chata"
+  - source: "동녘에"
+    expected: "tongnyeokh'e"
+  - source: "같이"
+    expected: "kath'i"
+  - source: "앞에"
+    expected: "aph'e"
+  - source: "꽃에"
+    expected: "kkoch'e"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: False
+  inherit: var-kor-Hang-Hang-jamo
+
+  rules:
+
+  postrules:
+    # Add space to the two ends of the string for easier word boundary handling
+    - pattern: "^"
+      result: " "
+    - pattern: "$"
+      result: " "
+
+    # Marks A, B, C
+    - pattern: "(?<!\\p{Hangul})ᄋ" # Word initially
+      result: ""
+    - pattern: "ᄋ" # See notes 2, 3 and 4.
+      result: "'"
+    - pattern: "ᆼ" # At the end of a syllable.
+      result: "ng"
+
+    # Note 4: add apostrophe before 5 double consonants at initial position
+    #         unless start of the word
+    - pattern: "(?<=\\p{Hangul})([ᄁᄄᄈᄍᄊ])"
+      result: "'\\1"
+    # Note 4: (only method 1) same but with 4 aspirated
+    - pattern: "(?<=\\p{Hangul})([ᄏᄐᄑᄎ])"
+      result: "'\\1"
+
+    # Consonants differing between method1 and method2
+    - pattern: "[ᄀᆨ]"
+      result: "k"
+    - pattern: "[ᄏᆿ]"
+      result: "kh"
+    - pattern: "[ᄁᆩ]"
+      result: "kk"
+    - pattern: "[ᄃᆮ]"
+      result: "t"
+    - pattern: "[ᄐᇀ]"
+      result: "th"
+    - pattern: "[ᄄퟍ]"
+      result: "tt"
+    - pattern: "[ᄇᆸ]"
+      result: "p"
+    - pattern: "[ᄑᇁ]"
+      result: "ph"
+    - pattern: "[ᄈퟦ]"
+      result: "pp"
+    - pattern: "[ᄌᆽ]"
+      result: "c"
+    - pattern: "[ᄎᆾ]"
+      result: "ch"
+    - pattern: "[ᄍퟹ]"
+      result: "cc"
+    # End
+
+    # Composite differing consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ᆪ]"
+      result: "ks"
+    - pattern: "[ꥤ]" # D. R at the beginning of a syllable
+      result: "rk"
+    - pattern: "[ᆰ]"
+      result: "lk"
+    - pattern: "[ᆴ]"
+      result: "lth"
+    - pattern: "[ꥩ]" # D. R at the beginning of a syllable
+      result: "rp"
+    - pattern: "[ᆲ]"
+      result: "lp"
+    - pattern: "[ᆵ]"
+      result: "lph"
+    - pattern: "[ᅜᆬ]"
+      result: "nc"
+    - pattern: "[ᄡᆹ]"
+      result: "ps"
+    # End
+
+    # Other consonants
+    - pattern: "[ᄉᆺ]"
+      result: "s"
+    - pattern: "[ᄊᆻ]"
+      result: "ss"
+    - pattern: "[ᄒᇂ]"
+      result: "h"
+    - pattern: "[ᄂᆫ]"
+      result: "n"
+    - pattern: "[ᄅ]" # D. R at the beginning of a syllable.
+      result: "r"
+    - pattern: "[ᆯ]"
+      result: "l"
+    - pattern: "[ᄆᆷ]"
+      result: "m"
+    # End
+
+    # Other composite consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ꥬ]" # D. R at the beginning of a syllable
+      result: "rs"
+    - pattern: "[ᆳ]"
+      result: "ls"
+    - pattern: "[ꥨ]" # D. R at the beginning of a syllable
+      result: "rm"
+    - pattern: "[ᆱ]"
+      result: "lm"
+    - pattern: "[ᄚ]" # D. R at the beginning of a syllable
+      result: "rh"
+    - pattern: "[ᆶ]"
+      result: "lh"
+    - pattern: "[ᅝᆭ]"
+      result: "nh"
+    # End
+
+    # Vowels
+    - pattern: "ᅡ"
+      result: "a"
+    - pattern: "ᅥ"
+      result: "eo"
+    - pattern: "ᅩ"
+      result: "o"
+    - pattern: "ᅮ"
+      result: "u"
+    - pattern: "ᅳ"
+      result: "eu"
+    - pattern: "ᅵ"
+      result: "i"
+    - pattern: "ᅢ"
+      result: "ae"
+    - pattern: "ᅦ"
+      result: "e"
+    - pattern: "ᅬ"
+      result: "oe"
+    - pattern: "ᅣ"
+      result: "ya"
+    - pattern: "ᅧ"
+      result: "yeo"
+    - pattern: "ᅭ"
+      result: "yo"
+    - pattern: "ᅲ"
+      result: "yu"
+    - pattern: "ᅤ"
+      result: "yae"
+    - pattern: "ᅨ"
+      result: "ye"
+    - pattern: "ᅪ"
+      result: "wa"
+    - pattern: "ᅯ"
+      result: "weo"
+    - pattern: "ᅱ"
+      result: "wi"
+    - pattern: "ᅫ"
+      result: "wae"
+    - pattern: "ᅰ"
+      result: "we"
+    - pattern: "ᅴ"
+      result: "yi"
+    # End
+
+    # Remove space added
+    - pattern: "^ "
+      result: ""
+    - pattern: " $"
+      result: ""
+
+  characters:
+  # This is based on Jamo
+
+  dictionary:
+  #

data/maps/iso-kor-Hang-Latn-1996-method2.yaml

@@ -0,0 +1,226 @@
+---
+authority_id: iso
+id: 1996-method2
+language: iso-639-2:kor
+source_script: Hang
+destination_script: Latn
+name: "ISO/TR 11941:1996 Information and documentation — Transliteration of Korean script into Latin characters"
+url: https://www.iso.org/standard/20564.html
+creation_date: 1996
+adoption_date:
+description: Establishes a system for the transliteration of the characters of Korean script into Latin characters. Intended to provide a means for international communication of written documents.
+
+notes: ""
+
+tests:
+  # Tests from https://www.eki.ee/wgrs/rom2_ko.pdf
+  - source: "꽃이"
+    expected: "ggoc'i" # Bad OCR
+  - source: "강에"
+    expected: "gang'e"
+  - source: "앉아라"
+    expected: "anj'ara"
+  - source: "아까"
+    expected: "a'gga"
+  - source: "흰떡"
+    expected: "hyin'ddeog"
+  #- source: "유쾌하다" not present in method2
+  #  expected: "yu'khwaehata"
+
+  # Tests from https://github.com/interscript/interscript/files/5249245/ISO-TR-11941-1996.pdf
+  - source: "애기"
+    expected: "aegi"
+  - source: "방"
+    expected: "bang"
+  - source: "아이"
+    expected: "a'i"
+  - source: "고양이"
+    expected: "go'yang'i"
+  - source: "굽이"
+    expected: "gub'i"
+  - source: "밖에"
+    expected: "bagg'e"
+  - source: "박게"
+    expected: "bagge"
+  - source: "바께"
+    expected: "ba'gge"
+  - source: "간게"
+    expected: "gange"
+  - source: "안자라"
+    expected: "anjara"
+  - source: "오빠"
+    expected: "o'bba"
+  - source: "어찌"
+    expected: "eo'jji"
+  - source: "아씨"
+    expected: "a'ssi"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: False
+  inherit: var-kor-Hang-Hang-jamo
+
+  rules:
+
+  postrules:
+    # Add space to the two ends of the string for easier word boundary handling
+    - pattern: "^"
+      result: " "
+    - pattern: "$"
+      result: " "
+
+    # Marks A, B, C
+    - pattern: "(?<!\\p{Hangul})ᄋ" # Word initially
+      result: ""
+    - pattern: "ᄋ" # See notes 2, 3 and 4.
+      result: "'"
+    - pattern: "ᆼ" # At the end of a syllable.
+      result: "ng"
+
+    # Note 4: add apostrophe before 5 double consonants at initial position
+    #         unless start of the word
+    - pattern: "(?<=\\p{Hangul})([ᄁᄄᄈᄍᄊ])"
+      result: "'\\1"
+    # Note 4: (only method 1) same but with 4 aspirated
+    #- pattern: "(?<=\\p{Hangul})([ᄏᄐᄑᄎ])"
+    #  result: "'\\1"
+
+    # Consonants differing between method1 and method2
+    - pattern: "[ᄀᆨ]"
+      result: "g"
+    - pattern: "[ᄏᆿ]"
+      result: "k"
+    - pattern: "[ᄁᆩ]"
+      result: "gg"
+    - pattern: "[ᄃᆮ]"
+      result: "d"
+    - pattern: "[ᄐᇀ]"
+      result: "t"
+    - pattern: "[ᄄퟍ]"
+      result: "dd"
+    - pattern: "[ᄇᆸ]"
+      result: "b"
+    - pattern: "[ᄑᇁ]"
+      result: "p"
+    - pattern: "[ᄈퟦ]"
+      result: "bb"
+    - pattern: "[ᄌᆽ]"
+      result: "j"
+    - pattern: "[ᄎᆾ]"
+      result: "c"
+    - pattern: "[ᄍퟹ]"
+      result: "jj"
+    # End
+
+    # Composite differing consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ᆪ]"
+      result: "gs"
+    - pattern: "[ꥤ]" # D. R at the beginning of a syllable
+      result: "rg"
+    - pattern: "[ᆰ]"
+      result: "lg"
+    - pattern: "[ᆴ]"
+      result: "lt"
+    - pattern: "[ꥩ]" # D. R at the beginning of a syllable
+      result: "rb"
+    - pattern: "[ᆲ]"
+      result: "lb"
+    - pattern: "[ᆵ]"
+      result: "lp"
+    - pattern: "[ᅜᆬ]"
+      result: "nj"
+    - pattern: "[ᄡᆹ]"
+      result: "bs"
+    # End
+
+    # Other consonants
+    - pattern: "[ᄉᆺ]"
+      result: "s"
+    - pattern: "[ᄊᆻ]"
+      result: "ss"
+    - pattern: "[ᄒᇂ]"
+      result: "h"
+    - pattern: "[ᄂᆫ]"
+      result: "n"
+    - pattern: "[ᄅ]" # D. R at the beginning of a syllable.
+      result: "r"
+    - pattern: "[ᆯ]"
+      result: "l"
+    - pattern: "[ᄆᆷ]"
+      result: "m"
+    # End
+
+    # Other composite consonants (cons. https://en.wikipedia.org/wiki/ISO/TR_11941 )
+    - pattern: "[ꥬ]" # D. R at the beginning of a syllable
+      result: "rs"
+    - pattern: "[ᆳ]"
+      result: "ls"
+    - pattern: "[ꥨ]" # D. R at the beginning of a syllable
+      result: "rm"
+    - pattern: "[ᆱ]"
+      result: "lm"
+    - pattern: "[ᄚ]" # D. R at the beginning of a syllable
+      result: "rh"
+    - pattern: "[ᆶ]"
+      result: "lh"
+    - pattern: "[ᅝᆭ]"
+      result: "nh"
+    # End
+
+    # Vowels
+    - pattern: "ᅡ"
+      result: "a"
+    - pattern: "ᅥ"
+      result: "eo"
+    - pattern: "ᅩ"
+      result: "o"
+    - pattern: "ᅮ"
+      result: "u"
+    - pattern: "ᅳ"
+      result: "eu"
+    - pattern: "ᅵ"
+      result: "i"
+    - pattern: "ᅢ"
+      result: "ae"
+    - pattern: "ᅦ"
+      result: "e"
+    - pattern: "ᅬ"
+      result: "oe"
+    - pattern: "ᅣ"
+      result: "ya"
+    - pattern: "ᅧ"
+      result: "yeo"
+    - pattern: "ᅭ"
+      result: "yo"
+    - pattern: "ᅲ"
+      result: "yu"
+    - pattern: "ᅤ"
+      result: "yae"
+    - pattern: "ᅨ"
+      result: "ye"
+    - pattern: "ᅪ"
+      result: "wa"
+    - pattern: "ᅯ"
+      result: "weo"
+    - pattern: "ᅱ"
+      result: "wi"
+    - pattern: "ᅫ"
+      result: "wae"
+    - pattern: "ᅰ"
+      result: "we"
+    - pattern: "ᅴ"
+      result: "yi"
+    # End
+
+    # Remove space added
+    - pattern: "^ "
+      result: ""
+    - pattern: " $"
+      result: ""
+
+  characters:
+  # This is based on Jamo
+
+  dictionary:
+  #