interscript 0.1.2 → 0.1.7

data/maps/odni-kat-Geor-Latn-2015.yaml

@@ -0,0 +1,87 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:kat
+source_script: Geor
+destination_script: Latn
+name: Office of the Director Of National Intelligence Georgian Personal Names 2015, ICS 630-01 Annex E
+# url:
+source: ICS 630-01, Annex E
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Georgian 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 Georgian that can then be linked to forensic
+  information in ways that will help identify the referent of the name.
+
+notes:
+
+tests:
+
+  - source: ბაყაყი
+    expected: baqaqi
+
+  - source: ძროხა
+    expected: dzrokha
+
+  - source: ჰაერი
+    expected: haeri
+
+  - source: ჟოლო
+    expected: zholo
+
+  - source: ჯართი
+    expected: jarti
+
+  - source: ღრმაღელე
+    expected: ghrmaghele
+
+  - source: ზვიად გამსახურდია
+    expected: zviad gamsakhurdia
+
+  - source: ედუარდ შევარდნაძე
+    expected: eduard shevardnadze
+
+  - source: მიხეილ სააკაშვილი
+    expected: mikheil saakashvili
+
+  - source: გიორგი მარგველაშვილი
+    expected: giorgi margvelashvili
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+    '\u10d7' : 't' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p' # პ
+    '\u10df' : 'zh' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't' # ტ
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'p' # ფ
+    '\u10e5' : 'k' # ქ
+    '\u10e6' : 'gh' # ღ
+    '\u10e7' : 'q' # ყ
+    '\u10e8' : 'sh' # შ
+    '\u10e9' : 'ch' # ჩ
+    '\u10ea' : 'ts' # ც
+    '\u10eb' : 'dz' # ძ
+    '\u10ec' : 'ts' # წ
+    '\u10ed' : 'ch' # ჭ
+    '\u10ee' : 'kh' # ხ
+    '\u10ef' : 'j' # ჯ
+    '\u10f0' : 'h' # ჰ

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

@@ -0,0 +1,148 @@
+---
+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:
+  - source: Бекзат Саттарханов
+    expected: Bekzat Sattarkhanov
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(?i)(\u0492|\u0401|\u0416|\u04A2|\u0425|\u0426|\u0427|\u0428|\u0429|\u042E|\u042F)\\1(?-i)"
+      result: "\\1"
+    # note[3]
+    - pattern: \u044A|\u044C
+      result: ""
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u04D8': 'A'      # Ә
+    '\u0411': 'B'      # Б
+    '\u0412': 'V'      # В
+    '\u0413': 'G'      # Г
+    '\u0492': 'Gh'     # Ғ
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u0416': 'Zh'     # Ж
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\u0406': 'I'      # І
+    '\u0419': 'Y'      # Й
+    '\u041A': 'K'      # К
+    '\u049A': 'Q'      # Қ
+    '\u041B': 'L'      # Л
+    '\u041C': 'M'      # М
+    '\u041D': 'N'      # Н
+    '\u04A2': 'Ng'     # Ң
+    '\u041E': 'O'      # О
+    '\u04E8': 'O'      # Ө
+    '\u041F': 'P'      # П
+    '\u0420': 'R'      # Р
+    '\u0421': 'S'      # С
+    '\u0422': 'T'      # Т
+    '\u0423': 'U'      # У
+    '\u04AE': 'U'      # Ү
+    '\u04B0': 'U'      # Ұ
+    '\u0424': 'F'      # Ф
+    '\u0425': 'Kh'     # Х
+    '\u04BA': 'H'      # Һ
+    '\u0426': 'Ts'     # Ц
+    '\u0427': 'Ch'     # Ч
+    '\u0428': 'Sh'     # Ш
+    '\u0429': 'Shch'   # Щ
+    '\u042B': 'Y'      # Ы
+    '\u042D': 'E'      # Э
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u04D9': 'a'      # ә
+    '\u0431': 'b'      # б
+    '\u0432': 'v'      # в
+    '\u0433': 'g'      # г
+    '\u0493': 'gh'     # ғ
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # e
+    '\u0451': 'yo'     # ё
+    '\u0436': 'zh'     # ж
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\u0456': 'i'      # і
+    '\u0439': 'y'      # й
+    '\u043A': 'k'      # к
+    '\u049B': 'q'      # қ
+    '\u043B': 'l'      # л
+    '\u043C': 'm'      # м
+    '\u043D': 'n'      # н
+    '\u04A3': 'ng'     # ң
+    '\u043E': 'o'      # о
+    '\u04E9': 'o'      # ө
+    '\u043F': 'p'      # п
+    '\u0440': 'r'      # р
+    '\u0441': 's'      # с
+    '\u0442': 't'      # т
+    '\u0443': 'u'      # у
+    '\u04AF': 'u'      # ү
+    '\u04B1': 'u'      # ұ
+    '\u0444': 'f'      # ф
+    '\u0445': 'kh'     # х
+    '\u04BB': 'h'      # һ
+    '\u0446': 'ts'     # ц
+    '\u0447': 'ch'     # ч
+    '\u0448': 'sh'     # ш
+    '\u0449': 'shch'   # щ
+    '\u044B': 'y'      # ы
+    '\u044D': 'e'      # э
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

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

@@ -0,0 +1,136 @@
+---
+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:
+  - source: Гульжигит Калыков
+    expected: Guljigit Kalykov
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(?i)(\u0401|\u04A2|\u0425|\u0426|\u0427|\u0428|\u0429|\u042E|\u042F)\\1(?-i)"
+      result: "\\1"
+    # note[3]
+    - pattern: \u044A|\u044C
+      result: ""
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u0411': 'B'      # Б
+    '\u0412': 'V'      # В
+    '\u0413': 'G'      # Г
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u0416': 'J'      # Ж
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\u0419': 'Y'      # Й
+    '\u041A': 'K'      # К
+    '\u041B': 'L'      # Л
+    '\u041C': 'M'      # М
+    '\u041D': 'N'      # Н
+    '\u04A2': 'Ng'     # Ң
+    '\u041E': 'O'      # О
+    '\u04E8': 'O'      # Ө
+    '\u041F': 'P'      # П
+    '\u0420': 'R'      # Р
+    '\u0421': 'S'      # С
+    '\u0422': 'T'      # Т
+    '\u0423': 'U'      # У
+    '\u04AE': 'U'      # Ү
+    '\u0424': 'F'      # Ф
+    '\u0425': 'Kh'     # Х
+    '\u0426': 'Ts'     # Ц
+    '\u0427': 'Ch'     # Ч
+    '\u0428': 'Sh'     # Ш
+    '\u0429': 'Shch'   # Щ
+    '\u042B': 'Y'      # Ы
+    '\u042D': 'E'      # Э
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u0431': 'b'      # б
+    '\u0432': 'v'      # в
+    '\u0433': 'g'      # г
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # e
+    '\u0451': 'yo'     # ё
+    '\u0436': 'j'      # ж
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\u0439': 'y'      # й
+    '\u043A': 'k'      # к
+    '\u043B': 'l'      # л
+    '\u043C': 'm'      # м
+    '\u043D': 'n'      # н
+    '\u04A3': 'ng'     # ң
+    '\u043E': 'o'      # о
+    '\u04E9': 'o'      # ө
+    '\u043F': 'p'      # п
+    '\u0440': 'r'      # р
+    '\u0441': 's'      # с
+    '\u0442': 't'      # т
+    '\u0443': 'u'      # у
+    '\u04AF': 'u'      # ү
+    '\u0444': 'f'      # ф
+    '\u0445': 'kh'     # х
+    '\u0446': 'ts'     # ц
+    '\u0447': 'ch'     # ч
+    '\u0448': 'sh'     # ш
+    '\u0449': 'shch'   # щ
+    '\u044B': 'y'      # ы
+    '\u044D': 'e'      # э
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

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

@@ -0,0 +1,375 @@
+---
+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:
+  - source: "김영수"
+    expected: "Kim Yo’ng-su"
+  - source: "허담"
+    expected: "Ho’ Tam"
+  - source: "선우학원"
+    expected: "So’nu Hak-wo’n"
+  - source: "이담"
+    expected: "Yi Tam"
+
+  # examples testing space handling
+  - source: "동방국"
+    expected: "Tongpang Kuk"
+  - source: "동 방국"
+    expected: "Tong Pang-kuk"
+  - source: "동방 국"
+    expected: "Tongpang Kuk"
+  - source: "화방국"
+    expected: "Hwa Pang-kuk"
+  - source: "황목국"
+    expected: "Hwangmok Kuk"
+
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: var-kor-Hang-Hang-jamo
+
+  rules:
+    - pattern: "^ | $"
+      result: ""
+
+    - pattern: " +"
+      result: " "
+
+    # 2 character inputs will have a space between them
+    - pattern: "^(\\p{Hangul})(\\p{Hangul})$"
+      result: "\\1 \\2"
+
+    # 4 character inputs will have a space as in XXXX -> XX XX
+    - pattern: "^(\\p{Hangul}{2})(\\p{Hangul}{2})$"
+      result: "\\1 \\2"
+
+    # 3 character inputs are more complicated. We enumerate all possible 2
+    # letter surnames according to: https://en.wikipedia.org/wiki/List_of_Korean_surnames
+    - pattern: "^(독고|동방|등정|망절|무본|부여|사공|서문|선우|어금|제갈|황목|황보)(\\p{Hangul})$"
+      result: "\\1 \\2"
+
+    # Otherwise the first character is probably a surname
+    - pattern: "^(\\p{Hangul})(\\p{Hangul}{2})$"
+      result: "\\1 \\2"
+
+    # In case of uncertainity, user needs to add a space himself.
+
+    - pattern: " +"
+      result: " "
+
+    - pattern: "^ | $"
+      result: ""
+
+  postrules:
+
+    # HANGUL JONGSEONG SSANGKIYEOK
+    - pattern: "ᆩ"
+      result: "kk"
+
+    # HANGUL JONGSEONG SSANGKIYEOK
+    - pattern: "ᆪ"
+      result: "ks"
+
+    # HANGUL JONGSEONG NIEUN-CIEUC
+    - pattern: "ᆬ"
+      result: "nch"
+
+    # HANGUL JONGSEONG NIEUN-CIEUC
+    - pattern: "ᆭ"
+      result: "nh"
+
+    # HANGUL JONGSEONG TIEUT
+    - pattern: "ᆮ"
+      result: "t"
+
+    # HANGUL JONGSEONG RIEUL-SIOS
+    - pattern: "ᆳ"
+      result: "l"
+
+    # HANGUL JONGSEONG RIEUL-THIEUTH
+    - pattern: "ᆴ"
+      result: "lt’"
+
+    # HANGUL JONGSEONG RIEUL-PHIEUPH
+    - pattern: "ᆵ"
+      result: "lp’"
+
+    # HANGUL JONGSEONG RIEUL-HIEUH
+    - pattern: "ᆶ"
+      result: "lh"
+
+    # HANGUL JONGSEONG PIEUP-SIOS
+    - pattern: "ᆹ"
+      result: "ps"
+
+    # HANGUL JONGSEONG SSANG-SIOS
+    - pattern: "ᆻ"
+      result: "ss"
+
+    # HANGUL JONGSEONG CIEUC
+    - pattern: "ᆽ"
+      result: "ch"
+
+    # HANGUL JONGSEONG CHIEUCH
+    - pattern: "ᆾ"
+      result: "ch’"
+
+    # HANGUL JONGSEONG KHIEUKH
+    - pattern: "ᆿ"
+      result: "k’"
+
+    # HANGUL JONGSEONG THIEUTH
+    - pattern: "ᇀ"
+      result: "t’"
+
+    # HANGUL JONGSEONG PHIEUPH
+    - pattern: "ᇁ"
+      result: "p’"
+
+    # HANGUL JONGSEONG HIEUH
+    - pattern: "ᇂ"
+      result: "h"
+
+    # HANGUL JONGSEONG KIYEOK
+    - pattern: "ᆨ"
+      result: "k"
+
+    # HANGUL JONGSEONG NIEUN
+    - pattern: "ᆫ"
+      result: "n"
+
+    # HANGUL JONGSEONG RIEUL
+    - pattern: "ᆯ"
+      result: "l"
+
+    # HANGUL JONGSEONG MIEUM
+    - pattern: "ᆷ"
+      result: "m"
+
+    # HANGUL JONGSEONG PIEUP
+    - pattern: "ᆸ"
+      result: "p"
+
+    # HANGUL JONGSEONG SIOS
+    - pattern: "ᆺ"
+      result: "s"
+
+    # HANGUL JONGSEONG IEUNG
+    - pattern: "ᆼ"
+      result: "ng"
+
+    # HANGUL JONGSEONG RIEUL-KIYEOK
+    - pattern: "ᆰ"
+      result: "lk"
+
+    # HANGUL JONGSEONG RIEUL-PIEUP
+    - pattern: "ᆲ"
+      result: "lp"
+
+    # HANGUL CHOSEONG KIYEOK
+    - pattern: "ᄀ"
+      result: "-k"
+
+    # HANGUL CHOSEONG NIEUN
+    - pattern: "ᄂ"
+      result: "-n"
+
+    # HANGUL CHOSEONG TIEUT
+    - pattern: "ᄃ"
+      result: "-t"
+
+    # HANGUL CHOSEONG RIEUL
+    - pattern: "ᄅ"
+      result: "-r"
+
+    # HANGUL CHOSEONG MIEUM
+    - pattern: "ᄆ"
+      result: "-m"
+
+    # HANGUL CHOSEONG PIEUP
+    - pattern: "ᄇ"
+      result: "-p"
+
+    # HANGUL CHOSEONG SIOS
+    - pattern: "ᄉ"
+      result: "-s"
+
+    # HANGUL CHOSEONG IEUNG
+    - pattern: "ᄋ"
+      result: "-"
+
+    # HANGUL CHOSEONG CIEUC
+    - pattern: "ᄌ"
+      result: "-ch"
+
+    # HANGUL CHOSEONG CHIEUCH
+    - pattern: "ᄎ"
+      result: "-ch’"
+
+    # HANGUL CHOSEONG KHIEUKH
+    - pattern: "ᄏ"
+      result: "-k’"
+
+    # HANGUL CHOSEONG THIEUTH
+    - pattern: "ᄐ"
+      result: "-t’"
+
+    # HANGUL CHOSEONG PHIEUPH
+    - pattern: "ᄑ"
+      result: "-p’"
+
+    # HANGUL CHOSEONG HIEUH
+    - pattern: "ᄒ"
+      result: "-h"
+
+    # HANGUL CHOSEONG SSANGKIYEOK
+    - pattern: "ᄁ"
+      result: "-kk"
+
+    # HANGUL CHOSEONG SIOS-KIYEOK
+    - pattern: "ᄭ"
+      result: "-sk"
+
+    # HANGUL CHOSEONG SSANGTIEUT
+    - pattern: "ᄄ"
+      result: "-tt"
+
+    # HANGUL CHOSEONG SIOS-TIEUT
+    - pattern: "ᄯ"
+      result: "-st"
+
+    # HANGUL CHOSEONG SSANGPIEUP
+    - pattern: "ᄈ"
+      result: "-pp"
+
+    # HANGUL CHOSEONG SIOS-PIEUP
+    - pattern: "ᄲ"
+      result: "-sp"
+
+    # HANGUL CHOSEONG SSANGSIOS
+    - pattern: "ᄊ"
+      result: "-ss"
+
+    # HANGUL CHOSEONG SSANGCIEUC
+    - pattern: "ᄍ"
+      result: "-chch"
+
+    # HANGUL CHOSEONG SIOS-CIEUC
+    - pattern: "ᄶ"
+      result: "-sch"
+
+    ## End of Choseong Jamos
+
+    # HANGUL JUNGSEONG A
+    - pattern: "ᅡ"
+      result: "a"
+    # HANGUL JUNGSEONG YA
+    - pattern: "ᅣ"
+      result: "ya"
+    # HANGUL JUNGSEONG EO
+    - pattern: "ᅥ"
+      result: "o’"
+    # HANGUL JUNGSEONG YEO
+    - pattern: "ᅧ"
+      result: "yo’"
+    # HANGUL JUNGSEONG O
+    - pattern: "ᅩ"
+      result: "o"
+    # HANGUL JUNGSEONG YO
+    - pattern: "ᅭ"
+      result: "yo"
+    # HANGUL JUNGSEONG U
+    - pattern: "ᅮ"
+      result: "u"
+    # HANGUL JUNGSEONG YU
+    - pattern: "ᅲ"
+      result: "yu"
+    # HANGUL JUNGSEONG EU
+    - pattern: "ᅳ"
+      result: "u’"
+    # HANGUL JUNGSEONG I
+    - pattern: "ᅵ"
+      result: "i"
+    # HANGUL JUNGSEONG AE
+    - pattern: "ᅢ"
+      result: "ae"
+    # HANGUL JUNGSEONG YAE
+    - pattern: "ᅤ"
+      result: "yae"
+    # HANGUL JUNGSEONG E
+    - pattern: "ᅦ"
+      result: "e"
+    # HANGUL JUNGSEONG YE  # Not found in specification
+    - pattern: "ᅨ"        # actually found in Reference Guide
+      result: "ye"
+    # HANGUL JUNGSEONG WA
+    - pattern: "ᅪ"
+      result: "wa"
+    # HANGUL JUNGSEONG WAE
+    - pattern: "ᅫ"
+      result: "wae"
+    # HANGUL JUNGSEONG OE
+    - pattern: "ᅬ"
+      result: "oe"
+    # HANGUL JUNGSEONG WE
+    - pattern: "ᅰ"
+      result: "we"
+    # HANGUL JUNGSEONG WEO
+    - pattern: "ᅯ"
+      result: "wo’"
+    # HANGUL JUNGSEONG WI
+    - pattern: "ᅱ"
+      result: "wi"
+    # HANGUL JUNGSEONG YI
+    - pattern: "ᅴ"
+      result: "ui"
+
+    # Remove before the first syllable dash
+    - pattern: "(?<=^| )-"
+      result: ""
+
+    # Remove dash in surname
+    - pattern: "(^[^ ]*)-"
+      result: "\\1"
+
+    # Change the surname I to Yi
+    - pattern: "^i"
+      result: "yi"
+
+  characters:
+  # This is based on Jamo
+
+  dictionary:
+  #