interscript 0.1.6 → 0.1.7

data/maps/odni-hin-Deva-Latn-2015.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: hin
+language: iso-639-2:hin
 source_script: Deva
 destination_script: Latn
 name: Office of the Director Of National Intelligence Hindi Urdu Personal Names 2015 System, ICS-630-01 Annex F

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: kat
+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

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: kaz
+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

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: kir
+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

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:
+  #

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: Standards for the transliteration of macedonian personal names in written reports and products

data/maps/odni-per-Arab-Latn-2015.yaml

@@ -0,0 +1,228 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-3:prs
+source_script: Arab
+destination_script: Latn
+name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
+url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+creation_date: 2015
+confirmation_date: 2015-11
+description: |
+  This system is the Intelligence Community (IC) standard for
+  the transliteration of Persian (Farsi)
+  and Dari names that is 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 Persian (Farsi) and Dari 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 Perso-Arabic
+  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. This convention is
+  designed to ensure that vital forensic information is not
+  lost while maintaining consistency.
+
+  For names of individuals who are not part of the Persian-(
+  Farsi) or Dari-speaking community,
+  but whose names are encountered in Farsi or Dari, use the
+  relevant IC transliteration standard for
+  names from that language (e.g., Mikhail, Yitzhak, Abu-
+  Murtada). 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
+  online CIA World Factbook and the
+  online directory of Chiefs of State and Cabinet Members of
+  Foreign Governments, the spellings
+  given in these online reference works should be used in
+  place of the IC Standard, with the IC
+  Standard included as a variant in parentheses at the first
+  usage. 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 (e.g., former president Mahmud
+  Ahmadinezhad (Ahmadi-Nejad).
+
+  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 plus the apostrophe and hyphen.
+  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 online tools,
+  name dictionaries, and lists containing
+  conventional spellings of names of well-known individuals.
+
+notes:
+  - |
+    This standard is intended only for those Afghan names that
+    have a common bond or similarity with Iranian names. It
+    should not, for example, be used for names of Pashtuns, for
+    which the Pashto IC Standard should be used.
+
+  - |
+    Alef maqsura (final yeh pronounced as “a”): should be written “a” as in
+    “Musa”.
+
+  - |
+    Digraphs: No distinction is drawn between digraphs
+    such as sh and single contiguous letters (e.g., s followed
+    by h).
+
+  - |
+    Long/short vowels: There is no distinction made in
+    Roman between long and short a: E.g., Farhad (first a is
+    short, second is long).
+
+  - |
+    Diphthongs: Diphthongs are written ei and ow respectively:
+    Hosein; Khosrow.
+
+  - |
+    Double consonants: Double consonants represented by the
+    tashdid are shown by doubling the
+    Roman letter: Mo'azzami, Tavakkoli, Sajjad. Exceptions: Ein
+    and consonants represented by
+    Roman digraphs (e.g., sh, ch) are not doubled (Mobasher,
+    not Mobashsher). Double letters
+    are only used for tashdid (Hosein, not Hossein) or to
+    reflect “sun-letter” assimilation (see
+    below). Special care should be taken when possible to
+    discriminate between doubled and
+    non-doubled letters in names that are otherwise
+    indistinguishable in their transliterated forms:
+    Hasan (حسن (vs. Hassan (حسان(
+
+  - |
+    Compound first names will be written as distinct words:
+    Ali Reza (not Alireza or Ali-Reza);
+    Mohammad Hosein (not Mohammadhosein or Mohammad-Hosein),
+    with the exception of cases identified below.
+
+  - |
+    Arabic-origin names that incorporate the word “Allah” are
+    transliterated as one word, with the letter ‘o’ replacing the
+    alef in Allah (Azizollah, Rahimollah).
+
+  - |
+    Name-internal Arabic definite article "al" (‫)ال‬: Common
+    in many names borrowed
+    from Arabic, the transliteration should follow the Arabic
+    rules for “sun letter” assimilation in spoken form and
+    reflect the nominative case. That is: Abdorrahman, not Abd-
+    al-Rahman. (The Arabic sun letters are: ‫ت‬،‫ث‬،‫د‬،‫ذ‬،
+    ‫ر‬، ‫ز‬،‫س‬،‫ش‬،‫ص‬،‫ض‬،‫ط‬،‫ظ‬،‫ل‬،‫ن‬ . These correspond with
+    d, l, n, r, s, sh, t, and z.) Note that the moon letters (
+    i.e., all other Arabic letters) are not assimilated (e.g.,
+    Abdolhasan, Abolfazl). Note also that the “Abdollah” and
+    “Abdol + attribute of Allah” names are written as a single
+    word, as are other names that contain the definite article:
+    Shamsoddin (not Shams-al-Din), Nezamoddin, etc.
+
+  - |
+    Name-initial Arabic definite article "al" (‫)ال‬: For
+    Arabic-origin names starting with the definite article “al” (‫)
+    ال‬, follow the Arabic standard of al-Sisi (‫)الصیصی‬ (not
+    Alsisi or Assisi) and forego sun-letter assimilation.
+
+  - |
+    Arabic "family marker" of Al (‫)آل‬: For Arabic-origin
+    names starting with the "family marker" of Al (‫)آل‬,
+    follow the Arabic standard of Al Davud (‫داود‬ ‫)آل‬ (not
+    Aldavud or Aledavud).
+
+  - |
+    Kunyas: In the rather rare case where
+    a Persian uses a kunya (a name for an adult normally
+    derived from his or her eldest child, and sometimes
+    employed as a nom de guerre), this name will be rendered
+    with a space separating the two elements (Abu Hosein, Abu
+    Ghasem). Note that this does not apply when the person's
+    given or family name was derived from a predecessor's
+    kunya. In these cases, the leading element should be
+    treated as a prefix as indicated below (Abuhosein[i],
+    Abughasem[i]).
+
+tests:
+  - source: مُوسَى
+    expected: musa
+
+  - source: مُؤمِن
+    expected: momen
+
+  - source: رِضايي
+    expected: rezai
+
+  - source: مُبَشِّر
+    expected: mobasher
+
+  - source: حَسَّان
+    expected: hassan
+
+  - source: حَسَن
+    expected: hasan
+
+  - source: صَفَّار
+    expected: saffar
+
+  - source: صَفَر
+    expected: safar
+
+map:
+  inherit: odni-fas-Arab-Latn-2015
+  characters:
+
+    # ta' marboota
+    '\u0629' : 'ah'
+
+    '\u0626' : '' # ئ
+    '\u0624' : '' # ؤ
+
+    # Farsi Vowel (Pointing)
+
+    # '\u064e\u0648' : 'ow'  # ـَو
+    # '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+
+    # additional symbols
+
+    # shadda
+
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0648\u0651' : 'ww'  # و
+
+    '\u0621': '' # ء
+
+    # FROM NOTES
+
+    '\u064a\u064a' : 'i' # NOTE 4 (2)
+    '\u06cc\u06cc' : 'i'
+
+    '\u0627\u064a\b' : 'i' # NOTE 4 (3)
+    '\u0627\u06cc\b' : 'i'
+
+    # Farsi consonant characters
+
+    '\u0639' : ''  # ع # new
+    '\u0642' : 'q'  # ق
+    '\u0648' : 'w'  # و