interscript-maps 2.0.5

data/maps/odni-kaz-Cyrl-Latn-2015.imp

@@ -0,0 +1,164 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:kaz
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of kazakh personal names in written reports and products
+  source: ICS-630-01 Annex Q
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Kazakh person names
+    that will be applied to all final written reports and products for IC consumers. It is not
+    intended to eliminate variations of a name that can contribute forensic information. Rather, it is
+    to provide an IC standard Romanized (English) transliteration from Kazakh that can then be linked
+    to forensic information in ways that will help identify the referent of the name.
+
+    In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+    Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the
+    first usage. In addition, if the original Cyrillic-script spelling is known, that spelling should
+    also appear in parentheses following the name, if possible, following best practices of the
+    issuing organization and taking into consideration information system capabilities. For example:
+    Bekzat Sattarkhanov (also seen as Bekzat Sattarkanov, Бекзат Саттарханов). This convention is
+    designed to ensure that vital forensic information is not lost.
+
+    For names of persons who are known to not be part of the Kazakh-speaking community, use the
+    relevant IC transliteration standard for names from that language (e.g., Yitzhak). A translator’s
+    note may be used to clarify the known origin of the person. Spell names of individuals from
+    languages that are written in Roman letters as they are spelled in those languages (e.g.,
+    George Clooney, Jorge Garcia, Georges Pompidou).
+
+    In the case of active senior government officials in the on-line CIA World Factbook and the on-
+    line directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings given
+    in these on-line reference works should be used in place of the IC Standard. For any individual
+    who has at one time been listed in the Factbook or Chiefs of State directory but who no longer
+    appears in those resources (i.e. is no longer a government official), the IC Standard spelling
+    should appear first, with the spelling, if known, as it previously appeared in those resources
+    listed within parentheses at the first usage.
+
+    The primary goal is to produce a consistent Romanized transcription of names that is specifically
+    readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+    (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use of
+    diacritics. However, within the context of a report, where additional information about the
+    individual is provided, the referent will be clearly identified. This system will be used in
+    conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+    names of well-known individuals.
+
+  notes:
+    - Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh
+    - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,
+      (e.g. 's' followed by 'h').
+    - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+}
+
+tests {
+  test "Бекзат Саттарханов", "Bekzat Sattarkhanov"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁЖҢХЦЧШЩЮЯ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub capture(any("Ғғ"))+any("Ғғ"), ref(1)
+  sub capture(any("Ёё"))+any("Ёё"), ref(1)
+  sub capture(any("Жж"))+any("Жж"), ref(1)
+  sub capture(any("Ңң"))+any("Ңң"), ref(1)
+  sub capture(any("Хх"))+any("Хх"), ref(1)
+  sub capture(any("Цц"))+any("Цц"), ref(1)
+  sub capture(any("Чч"))+any("Чч"), ref(1)
+  sub capture(any("Шш"))+any("Шш"), ref(1)
+  sub capture(any("Щщ"))+any("Щщ"), ref(1)
+  sub capture(any("Юю"))+any("Юю"), ref(1)
+  sub capture(any("Яя"))+any("Яя"), ref(1)
+  # note[3]
+  sub any("\u044A\u044C"), none
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u04D8", "A" # Ә
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0492", "Gh" # Ғ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u0406", "I" # І
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u049A", "Q" # Қ
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u04A2", "Ng" # Ң
+    sub "\u041E", "O" # О
+    sub "\u04E8", "O" # Ө
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\u04AE", "U" # Ү
+    sub "\u04B0", "U" # Ұ
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u04BA", "H" # Һ
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u0429", "Shch" # Щ
+    sub "\u042B", "Y" # Ы
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u04D9", "a" # ә
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0493", "gh" # ғ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0456", "i" # і
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u049B", "q" # қ
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", "ng" # ң
+    sub "\u043E", "o" # о
+    sub "\u04E9", "o" # ө
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u04AF", "u" # ү
+    sub "\u04B1", "u" # ұ
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u04BB", "h" # һ
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}

data/maps/odni-kir-Cyrl-Latn-2015.imp

@@ -0,0 +1,149 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:kir
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of kyrgyz personal names in written reports and products
+  source: ICS-630-01 Annex R
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Kyrgyz person names
+    that will be applied to all final written reports and products for IC consumers. It is not
+    intended to eliminate variations of a name that can contribute forensic information. Rather, it is
+    to provide an IC standard Romanized (English) transliteration from Kyrgyz that can then be linked
+    to forensic information in ways that will help identify the referent of the name.
+
+    In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+    Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the
+    first usage. In addition, if the original Cyrillic-script spelling is known, that spelling should
+    also appear in parentheses following the name, if possible, following best practices of the
+    issuing organization and taking into consideration information system capabilities. For example:
+    Guljigit Kalykov (also seen as Guljigit Kalikov, Гульжигит Калыков). This convention is designed
+    to ensure that vital forensic information is not lost.
+
+    For names of persons who are known to not be part of the Kyrgyz-speaking community, use the
+    relevant IC transliteration standard for names from that language (e.g., Yitzhak). A translator’s
+    note may be used to clarify the known origin of the person. Spell names of individuals from
+    languages that are written in Roman letters as they are spelled in those languages (e.g.,
+    George Clooney, Jorge Garcia, Georges Pompidou).
+
+    In the case of active senior government officials in the on-line CIA World Factbook and the on-
+    line directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings given
+    in these on-line reference works should be used in place of the IC Standard. For any individual
+    who has at one time been listed in the Factbook or Chiefs of State directory but who no longer
+    appears in those resources (i.e. is no longer a government official), the IC Standard spelling
+    should appear first, with the spelling, if known, as it previously appeared in those resources
+    listed within parentheses at the first usage.
+
+    The primary goal is to produce a consistent Romanized transcription of names that is specifically
+    readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+    (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use of
+    diacritics. However, within the context of a report, where additional information about the
+    individual is provided, the referent will be clearly identified. This system will be used in
+    conjunction with on-line tools, name dictionaries, and lists containing conventional spellings
+    of names of well-known individuals.
+
+  notes:
+    - Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh
+    - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,
+      (e.g. 's' followed by 'h').
+    - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+}
+
+tests {
+  test "Гульжигит Калыков", "Guljigit Kalykov"
+}
+
+stage {
+  # RULES
+  # note[1]
+  # generated with: "ЁҢХЦЧШЩЮЯ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub capture(any("Ёё"))+any("Ёё"), ref(1)
+  sub capture(any("Ңң"))+any("Ңң"), ref(1)
+  sub capture(any("Хх"))+any("Хх"), ref(1)
+  sub capture(any("Цц"))+any("Цц"), ref(1)
+  sub capture(any("Чч"))+any("Чч"), ref(1)
+  sub capture(any("Шш"))+any("Шш"), ref(1)
+  sub capture(any("Щщ"))+any("Щщ"), ref(1)
+  sub capture(any("Юю"))+any("Юю"), ref(1)
+  sub capture(any("Яя"))+any("Яя"), ref(1)
+  # note[3]
+  sub any("\u044A\u044C"), none
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "J" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u04A2", "Ng" # Ң
+    sub "\u041E", "O" # О
+    sub "\u04E8", "O" # Ө
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\u04AE", "U" # Ү
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u0429", "Shch" # Щ
+    sub "\u042B", "Y" # Ы
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "j" # ж
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", "ng" # ң
+    sub "\u043E", "o" # о
+    sub "\u04E9", "o" # ө
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u04AF", "u" # ү
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}

data/maps/odni-kor-Hang-Latn-2015.imp

@@ -0,0 +1,307 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:kor
+  source_script: Hang
+  destination_script: Latn
+  name: Office of the Director Of National Intelligence Korean 2015 System, ICS-630-01 Annex W
+  url:
+  creation_date: 2015
+  adoption_date:
+  description:
+
+  notes: |
+    1.  Name order shall be Family Name Given name, with the family name separated
+        from the given name by one space, and the first and second syllable of a two-
+        syllable given name connected by a hyphen. The initial letter of the family name
+        and the initial letter of the first syllable of the given name are capitalized; the
+        second syllable of the given name is in lower case: Kim Yo’ng-su.
+
+    2.  In the case of a full name with only two syllables, the initial letters of both
+        syllables are capitalized and the two names are separated by a space: Ho’ Tam.
+
+        In the case of family names consisting of a combination of two syllables, the
+        syllables are written together (i.e., without a space): So’nu Hak-wo’n.
+
+    3.  The family surname 이 will be rendered "Yi" in the IC Standard spelling, but in
+        accordance with personal preference or official usage in the Factbook and Chiefs
+        of State directory.
+
+    4.  In order to facilitate the use of the IC Standard, a reference guide containing a list
+        of syllables used in Korean personal names along with their IC Standard
+        equivalents follows.
+}
+
+tests {
+  test "김영수", "Kim Yo’ng-su"
+  test "허담", "Ho’ Tam"
+  test "선우학원", "So’nu Hak-wo’n"
+  test "이담", "Yi Tam"
+  # examples testing space handling
+  test "동방국", "Tongpang Kuk"
+  test "동 방국", "Tong Pang-kuk"
+  test "동방 국", "Tongpang Kuk"
+  test "화방국", "Hwa Pang-kuk"
+  test "황목국", "Hwangmok Kuk"
+}
+
+dependency "unicode", import: true
+dependency "var-kor-Hang-Hang-jamo", as: hanghang
+
+aliases{
+
+  def_alias alpha_plus, any("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ’")
+}
+
+stage {
+
+
+  # RULES
+  sub any([line_start + " ", " " + line_end]), ""
+
+  #sub some(" "), " "
+
+  # 2 character inputs will have a space between them
+  sub line_start + capture(unicode_hangul) + capture(unicode_hangul) + line_end, ref( 1 ) + " " + ref( 2 )
+
+  # 4 character inputs will have a space as in XXXX -> XX XX
+  sub line_start + capture(unicode_hangul + unicode_hangul) + capture(unicode_hangul + unicode_hangul) + line_end, ref( 1 ) + " " + ref( 2 )
+
+  # 3 character inputs are more complicated. We enumerate all possible 2
+  # letter surnames according to: https://en.wikipedia.org/wiki/List_of_Korean_surnames
+  sub line_start + capture(any(["독고", "동방", "등정", "망절", "무본", "부여", "사공", "서문", "선우", "어금", "제갈", "황목", "황보"])) + capture(unicode_hangul) + line_end, ref( 1 ) + " " + ref( 2 )
+
+  # Otherwise the first character is probably a surname
+  sub line_start + capture(unicode_hangul) + capture(unicode_hangul + unicode_hangul) + line_end, ref( 1 ) + " " + ref( 2 )
+
+  # In case of uncertainity, user needs to add a space himself.
+
+  #sub some(" "), " "
+
+  sub any([line_start + " ", " " + line_end]), ""
+
+
+
+  run map.hanghang.stage.main
+
+
+  # CHARACTERS
+  parallel {
+    # This is based on Jamo
+
+  }
+
+  # DICTIONARY
+  parallel {
+    #
+  }
+
+
+
+
+  # POSTRULES
+
+  # HANGUL JONGSEONG SSANGKIYEOK
+  sub "ᆩ", "kk"
+
+  # HANGUL JONGSEONG SSANGKIYEOK
+  sub "ᆪ", "ks"
+
+  # HANGUL JONGSEONG NIEUN-CIEUC
+  sub "ᆬ", "nch"
+
+  # HANGUL JONGSEONG NIEUN-CIEUC
+  sub "ᆭ", "nh"
+
+  # HANGUL JONGSEONG TIEUT
+  sub "ᆮ", "t"
+
+  # HANGUL JONGSEONG RIEUL-SIOS
+  sub "ᆳ", "l"
+
+  # HANGUL JONGSEONG RIEUL-THIEUTH
+  sub "ᆴ", "lt’"
+
+  # HANGUL JONGSEONG RIEUL-PHIEUPH
+  sub "ᆵ", "lp’"
+
+  # HANGUL JONGSEONG RIEUL-HIEUH
+  sub "ᆶ", "lh"
+
+  # HANGUL JONGSEONG PIEUP-SIOS
+  sub "ᆹ", "ps"
+
+  # HANGUL JONGSEONG SSANG-SIOS
+  sub "ᆻ", "ss"
+
+  # HANGUL JONGSEONG CIEUC
+  sub "ᆽ", "ch"
+
+  # HANGUL JONGSEONG CHIEUCH
+  sub "ᆾ", "ch’"
+
+  # HANGUL JONGSEONG KHIEUKH
+  sub "ᆿ", "k’"
+
+  # HANGUL JONGSEONG THIEUTH
+  sub "ᇀ", "t’"
+
+  # HANGUL JONGSEONG PHIEUPH
+  sub "ᇁ", "p’"
+
+  # HANGUL JONGSEONG HIEUH
+  sub "ᇂ", "h"
+
+  # HANGUL JONGSEONG KIYEOK
+  sub "ᆨ", "k"
+
+  # HANGUL JONGSEONG NIEUN
+  sub "ᆫ", "n"
+
+  # HANGUL JONGSEONG RIEUL
+  sub "ᆯ", "l"
+
+  # HANGUL JONGSEONG MIEUM
+  sub "ᆷ", "m"
+
+  # HANGUL JONGSEONG PIEUP
+  sub "ᆸ", "p"
+
+  # HANGUL JONGSEONG SIOS
+  sub "ᆺ", "s"
+
+  # HANGUL JONGSEONG IEUNG
+  sub "ᆼ", "ng"
+
+  # HANGUL JONGSEONG RIEUL-KIYEOK
+  sub "ᆰ", "lk"
+
+  # HANGUL JONGSEONG RIEUL-PIEUP
+  sub "ᆲ", "lp"
+
+  # HANGUL CHOSEONG KIYEOK
+  sub "ᄀ", "-k"
+
+  # HANGUL CHOSEONG NIEUN
+  sub "ᄂ", "-n"
+
+  # HANGUL CHOSEONG TIEUT
+  sub "ᄃ", "-t"
+
+  # HANGUL CHOSEONG RIEUL
+  sub "ᄅ", "-r"
+
+  # HANGUL CHOSEONG MIEUM
+  sub "ᄆ", "-m"
+
+  # HANGUL CHOSEONG PIEUP
+  sub "ᄇ", "-p"
+
+  # HANGUL CHOSEONG SIOS
+  sub "ᄉ", "-s"
+
+  # HANGUL CHOSEONG IEUNG
+  sub "ᄋ", "-"
+
+  # HANGUL CHOSEONG CIEUC
+  sub "ᄌ", "-ch"
+
+  # HANGUL CHOSEONG CHIEUCH
+  sub "ᄎ", "-ch’"
+
+  # HANGUL CHOSEONG KHIEUKH
+  sub "ᄏ", "-k’"
+
+  # HANGUL CHOSEONG THIEUTH
+  sub "ᄐ", "-t’"
+
+  # HANGUL CHOSEONG PHIEUPH
+  sub "ᄑ", "-p’"
+
+  # HANGUL CHOSEONG HIEUH
+  sub "ᄒ", "-h"
+
+  # HANGUL CHOSEONG SSANGKIYEOK
+  sub "ᄁ", "-kk"
+
+  # HANGUL CHOSEONG SIOS-KIYEOK
+  sub "ᄭ", "-sk"
+
+  # HANGUL CHOSEONG SSANGTIEUT
+  sub "ᄄ", "-tt"
+
+  # HANGUL CHOSEONG SIOS-TIEUT
+  sub "ᄯ", "-st"
+
+  # HANGUL CHOSEONG SSANGPIEUP
+  sub "ᄈ", "-pp"
+
+  # HANGUL CHOSEONG SIOS-PIEUP
+  sub "ᄲ", "-sp"
+
+  # HANGUL CHOSEONG SSANGSIOS
+  sub "ᄊ", "-ss"
+
+  # HANGUL CHOSEONG SSANGCIEUC
+  sub "ᄍ", "-chch"
+
+  # HANGUL CHOSEONG SIOS-CIEUC
+  sub "ᄶ", "-sch"
+
+  ## End of Choseong Jamos
+
+  # HANGUL JUNGSEONG A
+  sub "ᅡ", "a"
+  # HANGUL JUNGSEONG YA
+  sub "ᅣ", "ya"
+  # HANGUL JUNGSEONG EO
+  sub "ᅥ", "o’"
+  # HANGUL JUNGSEONG YEO
+  sub "ᅧ", "yo’"
+  # HANGUL JUNGSEONG O
+  sub "ᅩ", "o"
+  # HANGUL JUNGSEONG YO
+  sub "ᅭ", "yo"
+  # HANGUL JUNGSEONG U
+  sub "ᅮ", "u"
+  # HANGUL JUNGSEONG YU
+  sub "ᅲ", "yu"
+  # HANGUL JUNGSEONG EU
+  sub "ᅳ", "u’"
+  # HANGUL JUNGSEONG I
+  sub "ᅵ", "i"
+  # HANGUL JUNGSEONG AE
+  sub "ᅢ", "ae"
+  # HANGUL JUNGSEONG YAE
+  sub "ᅤ", "yae"
+  # HANGUL JUNGSEONG E
+  sub "ᅦ", "e"
+  # HANGUL JUNGSEONG YE  # Not found in specification
+  sub "ᅨ", "ye" # actually found in Reference Guide
+  # HANGUL JUNGSEONG WA
+  sub "ᅪ", "wa"
+  # HANGUL JUNGSEONG WAE
+  sub "ᅫ", "wae"
+  # HANGUL JUNGSEONG OE
+  sub "ᅬ", "oe"
+  # HANGUL JUNGSEONG WE
+  sub "ᅰ", "we"
+  # HANGUL JUNGSEONG WEO
+  sub "ᅯ", "wo’"
+  # HANGUL JUNGSEONG WI
+  sub "ᅱ", "wi"
+  # HANGUL JUNGSEONG YI
+  sub "ᅴ", "ui"
+
+  # Remove before the first syllable dash
+  sub "-", "", before: any([line_start, " "])
+
+  # Remove dash in surname
+  sub line_start + capture(some(alpha_plus)) + "-" + capture(some(alpha_plus)), ref( 1 ) + ref( 2 )
+
+  # Change the surname I to Yi
+  sub line_start + "i", "yi"
+
+
+  title_case
+}