interscript 0.1.1 → 0.1.6

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

@@ -0,0 +1,138 @@
+---
+authority_id: odni
+id: 2015
+language: uig
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of uyghur personal names in written reports and products
+source: ICS-630-01 Annex U
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Uyghur 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 Uyghur 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 or 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.
+  For example: Zordun Sabir (also seen as Zordun Sabeer, Зордун Сабир ,زوردون سابیر). 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 Uyghur-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: Зордун Сабир
+    expected: Zordun Sabir
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(?i)(\u0492|\u0401|\u0496|\u04A2|\u0427|\u0428|\u042E|\u042F)\\1(?-i)"
+      result: "\\1"
+    # note[3]
+    - pattern: \u044A|\u044C
+      result: ""
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u04D8': 'E'      # Ә
+    '\u0411': 'B'      # Б
+    '\u0412': 'W'      # В
+    '\u0413': 'G'      # Г
+    '\u0492': 'Gh'     # Ғ
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u0416': 'J'      # Ж
+    '\u0496': 'Zh'     # Җ
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\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
+    '\u0424': 'F'      # Ф
+    '\u0425': 'X'      # Х
+    '\u04BA': 'H'      # Һ
+    '\u0427': 'Ch'     # Ч
+    '\u0428': 'Sh'     # Ш
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u04D9': 'e'      # ә
+    '\u0431': 'b'      # б
+    '\u0432': 'w'      # в
+    '\u0433': 'g'      # г
+    '\u0493': 'gh'     # ғ
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # e
+    '\u0451': 'yo'     # ё
+    '\u0436': 'j'      # ж
+    '\u0497': 'zh'     # җ
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\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
+    '\u0444': 'f'      # ф
+    '\u0445': 'x'      # х
+    '\u04BB': 'h'      # һ
+    '\u0447': 'ch'     # ч
+    '\u0448': 'sh'     # ш
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

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

@@ -0,0 +1,157 @@
+---
+authority_id: odni
+id: 2015
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Ukrainian Personal Names 2004 System, ICS 630-01 Annex M
+# url:
+source: ICS 630-01, Annex M
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the
+  transliteration of Ukrainian 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 Ukrainian that can then be linked to
+  forensic information in ways that will help identify the referent of
+  the name.
+
+tests:
+  - source: Андрій
+    expected: Andriy
+  - source: Борисенко
+    expected: Borysenko
+  - source: Володимир
+    expected: Volodymyr
+  - source: Богдан
+    expected: Bohdan
+  - source: Згурський
+    expected: Zhurskyy
+  - source: Дмитро
+    expected: Dmytro
+  - source: Олег
+    expected: Oleh
+  - source: Гаєвич
+    expected: Hayevych
+  - source: Жанна
+    expected: Zhanna
+  - source: Казимирчук
+    expected: Kazymyrchuk
+  - source: Михайленко
+    expected: Mykhaylenko
+  - source: Іващенко
+    expected: Ivashchenko
+  - source: Олексій
+    expected: Oleksiy
+  - source: Коваленко
+    expected: Kovalenko
+  - source: Леонід
+    expected: Leonid
+  - source: Маринич
+    expected: Marynych
+  - source: Наталія
+    expected: Nataliya
+  - source: Онищенко
+    expected: Onyshchenko
+  - source: Петро
+    expected: Petro
+  - source: Рибчинський
+    expected: Rybchynskyy
+  - source: Соломія
+    expected: Solomiya
+  - source: Троць
+    expected: Trots
+  - source: Уляна
+    expected: Ulyana
+  - source: Філіпчук
+    expected: Filipchuk
+  - source: Христина
+    expected: Khrystyna
+  - source: Стеценко
+    expected: Stetsenko
+  - source: Шевченко
+    expected: Shevchenko
+  - source: Гаращенко
+    expected: Harashchenko
+  - source: Юрій
+    expected: Yuriy
+  - source: Ярошенко
+    expected: Yaroshenko
+  - source: Костянтин
+    expected: Kostyantyn
+
+map:
+  rules:
+    - pattern: \b\u2019\b # remove ’
+      result: ""
+
+  characters:
+    "\u0410": "A"        # А
+    "\u0411": "B"        # Б
+    "\u0412": "V"        # В
+    "\u0413": "H"        # Г
+    "\u0490": "G"        # Ґ
+    "\u0414": "D"        # Д
+    "\u0415": "E"        # Е
+    "\u0404": "Ye"       # Є
+    "\u0416": "Zh"       # Ж
+    "\u0417": "Z"        # З
+    "\u0418": "Y"        # И
+    "\u0406": "I"        # І
+    "\u0407": "Yi"       # Ї
+    "\u0419": "Y"        # Й
+    "\u041a": "K"        # К
+    "\u041b": "L"        # Л
+    "\u041c": "M"        # М
+    "\u041d": "N"        # Н
+    "\u041e": "O"        # О
+    "\u041f": "P"        # П
+    "\u0420": "R"        # Р
+    "\u0421": "S"        # С
+    "\u0422": "T"        # Т
+    "\u0423": "U"        # У
+    "\u0424": "F"        # Ф
+    "\u0425": "Kh"       # Х
+    "\u0426": "Ts"       # Ц
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042e": "Yu"       # Ю
+    "\u042f": "Ya"       # Я
+    "\u042c": ""         # Ь
+    "\u0430": "a"        # а
+    "\u0431": "b"        # б
+    "\u0432": "v"        # в
+    "\u0433": "h"        # г
+    "\u0491": "g"        # ґ
+    "\u0434": "d"        # д
+    "\u0435": "e"        # е
+    "\u0454": "ye"       # є
+    "\u0436": "zh"       # ж
+    "\u0437": "z"        # з
+    "\u0438": "y"        # и
+    "\u0456": "i"        # і
+    "\u0457": "yi"       # ї
+    "\u0439": "y"        # й
+    "\u043a": "k"        # к
+    "\u043b": "l"        # л
+    "\u043c": "m"        # м
+    "\u043d": "n"        # н
+    "\u043e": "o"        # о
+    "\u043f": "p"        # п
+    "\u0440": "r"        # р
+    "\u0441": "s"        # с
+    "\u0442": "t"        # т
+    "\u0443": "u"        # у
+    "\u0444": "f"        # ф
+    "\u0445": "kh"       # х
+    "\u0446": "ts"       # ц
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044e": "yu"       # ю
+    "\u044f": "ya"       # я
+    "\u044c": ""         # Ь

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

@@ -0,0 +1,221 @@
+---
+authority_id: odni
+id: 2015
+language: urd
+source_script: Arab
+destination_script: Latn
+name: Office of the Director Of National Intelligence Hindi Urdu Personal Names 2015 System, ICS-630-01 Annex F
+#url:
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of names
+  from Hindi and Urdu 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 standard Hindi and Urdu that can then be linked to forensic
+  information in ways that will help identify the referent of the name.
+
+  There are typically a number of ways that names can be Romanized from either
+  Devanagari (Hindi) or modified Arabic (Urdu) scripts. Ambiguities can result from the
+  Romanization of Hindi and Urdu names for several reasons, including the fact that some
+  sounds in South Asian languages (e.g., retroflex consonants, voiced aspirates) have no
+  equivalent in English or other European languages. In the case of Urdu, as in the original
+  Arabic source of many Islamic names, short vowel markings, double consonant marks
+  and other diacritics that would clearly distinguish the name are almost always omitted
+  from standard written texts. And many Islamic names of Arabic or Persian origin reflect
+  spelling distinctions from those languages that are lost in modern Urdu pronunciation
+  (e.g., three distinct Arabic letters all represent the identical sound [s] for Urdu speakers);
+  transliterations might either maintain those spelling distinctions or ignore them entirely.
+  And, as in the Arabic source, names containing the Arabic definite article ‘al’ (‘ul’) show
+  anticipatory assimilation in pronunciation (e.g., Shams al Din > Shamsuddin);
+  transliterations may either reflect spelling or pronunciation in such cases.
+
+  Because Hindi and Urdu overlap so extensively, it is desirable to correlate Hindi and
+  Urdu transliterations as much as possible. In the area of names, this can become
+  problematic when the Urdu spelling accurately reflects original Arabic spelling while the
+  Hindi spelling was phonetically-based, in essence, already a transliteration. This would
+  argue for ignoring Arabic/Urdu spelling distinctions not reflected in pronunciation in
+  either Urdu or Hindi (e.g., letter sin versus letter sad) while maintaining Arabic/Urdu
+  spelling distinctions like Hindi also maintains (e.g., qaf as in Qutubbin versus kaf)).
+  However, this is not always possible (see Hindi va versus Urdu wau).
+
+  In cases where an individual’s name has already been transliterated, that is to be indicated
+  – as found – in parentheses immediately following its rendition in the transliteration
+  standard (e.g., Muhammad Khulud (Mohamed Khulood)). In addition, if the original
+  Devanagari or 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.
+
+  For names of persons who are known to not be part of the Hindi- or Urdu-speaking
+  community, use the relevant IC transliteration standard for names from that language
+  (e.g., Mikhail, 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 of this system is to produce a consistent Romanized transcription of the
+  name that is readable to the 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.
+  Additionally, 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:
+
+  - |
+    Long/Short Vowels: Long and short vowels are not distinguished in the system:
+    The borrowed Arabic name Samir could represent two distinct names, one with a
+    long /a/ (Saamir) and one with a long /i/ (Samiir). One solution would be to use
+    /ee/ to stand for the long /i/, as is often done (Sameer). The IC Standard will not
+    distinguish between these.
+
+  - |
+    No distinction is made between: retroflex and non-retroflex consonants; and
+    nasalized vowels and vowels followed by /n/.
+  - |
+    No distinction is made between the several Arabic letters with the same phonetic
+    value in Urdu: e.g., letters sin/svad, zal/ze/zoe.
+  - |
+    A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,
+    Hindi qa and ka).
+  - |
+    A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants
+    (e.g., /dh/), with the exception of ch/chh, both represented by /ch/.
+  - |
+    Double consonants: Double consonants represented by the tashdid (shaddah) are
+    shown in most cases (e.g., Hassan, Muhammad). Exceptions: consonants
+    represented by digraphs are not doubled (e.g., Mubashir [not Mubashshir]).
+  - |
+    Hamzah (glottal stop) and ayn: Unlike in the Arabic IC Standard, these are not
+    represented in the IC standard.
+  - |
+    Digraphs: No distinction is made between digraphs such as /sh/ and single
+    contiguous letters such as /s/ followed by /h/.
+  - |
+    Arabic definite article “al” (‘the’): Shows sun letter assimilation in the
+    Romanized form (e.g., Abdur Rahman rather than Abdal Rahman, rather than
+    Arabic IC standard 'Abd al-Rahman).
+  - |
+    Special Rules
+    - |
+      Hyphens: Hyphens (-) are NOT used to connect name elements within a name:
+      Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in
+      noun-link-modifier construction of Persian origin), which does show a hyphen
+      before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e
+      xx” (‘Army of xx’ construction).
+    - |
+      Names incorporating “din” are written as one unit: Azermuddin, Badruddin,
+    Faizuddin, Salahuddin.
+    - |
+      Names that incorporate Allah as part of the name show the Arabic grammatical
+      marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).
+    - |
+      Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final
+      consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not
+      Rama Lala).
+    - |
+      As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.
+      Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is
+      transcribed as /w/: Wasim, Walid.
+
+tests:
+  - source: "وشال ٹھاکر"
+    expected: "ishal tsakr"
+  - source: "حسن محمود"
+    expected: "hasn mhamid"
+  - source: "یوسف خان"
+    expected: "iisf khan"
+  - source: "معین خان"
+    expected: "mein khan"
+  - source: "سعید اجمل"
+    expected: "seid ajml"
+  - source: "انضمام الحق"
+    expected: "anzmam alhaq"
+  - source: "فرہاد رضا"
+    expected: "frahad rza"
+  - source: "وسیم اکرام"
+    expected: "isim akram"
+  - source: "شکیب الحسن"
+    expected: "shkib alhasn"
+  - source: "حسن عبد اللہ"
+    expected: "hasn ebd allah"
+
+map:
+
+  characters:
+
+
+    '\u0622': 'a' # ARABIC ALEF W/MADDA ABOVE
+    '\u0627': 'a' # or u ARABIC ALEF
+    '\u06cc': 'i' # or ai or u ARABIC LETTER WAW
+    '\u0648': 'i' # or o,au ARABIC LETTER FARSI YEH
+    '\u06d2': 'e' # ARABIC LETTER YEH BARREE
+    '\u0650': 'e' # ARABIC ARABIC KASRA
+    '\u0639': 'e' # ARABIC LETTER AIN
+    '\u06c1': 'ah' # ARABIC LETTER HEH GOAL
+    '\u062d': 'ha' # ARABIC LETTER HAH
+    '\u0648\u0670': 'a' # ARABIC LETTER FARSI YEH + ARABIC LETTER SUPERSCRIPT ALEF
+    '\u0670': 'a' # ARABIC LETTER SUPERSCRIPT ALEF
+    '\u0627\u0650': 'i' # ARABIC ALEF + ARABIC KASRA
+    '\u0639\u0650': 'i' # ARABIC LETTER AIN + ARABIC KASRA
+    '\u064f': 'i' # ARABIC DAMMA
+    '\u06d3': 'i' #  ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
+    '\u06c2': '-e' #  ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
+    '\u06c1\u0650': 'o' #  ARABIC LETTER YEH  WITH HAMZA ABOVE
+    '\u0624': 'au' #  ARABIC LETTER WAW WITH HAMZA ABOVE
+
+
+
+    '\u06a9': 'k' #   ARABIC LETTER KEHEH
+    '\u0642': 'q' #   ARABIC LETTER QAF
+    '\u062e': 'kh' #   ARABIC LETTER KHAH
+    '\u06af': 'g' #   ARABIC LETTER GAF
+    '\u063a': 'gh' #   ARABIC LETTER GHAIN
+    '\u0686': 'ch' #   ARABIC LETTER TCHEH
+    '\u062c': 'j' #   Arabic Letter Jeem
+
+    '\u0632': 'z' #   Arabic Letter ZAIN
+    '\u0630': 'z' #   Arabic Letter THAL
+    '\u0636': 'z' #   Arabic Letter DAD
+    '\u0638': 'z' #   Arabic Letter ZAH
+    '\u0698': 'zh' #   Arabic Letter JEH
+
+
+    '\u0679': 't' #   ARABIC LETTER TTEH
+    '\u0688': 'd' #   Arabic Letter DDAL
+    '\u062f': 'd' #   Arabic Letter DAL
+    '\u0691': 'r' #   Arabic Letter RREH
+    '\u062a': 't' #   Arabic Letter TEH
+    '\u0637': 't' #   Arabic Letter TAH
+    '\u0646': 'n' #   Arabic Letter NOON
+    '\u06ba': 'n' #   Arabic Letter NOON GHUNNA
+
+
+    '\u067e': 'p' #   Arabic Letter PE
+    '\u0641': 'f' #   Arabic Letter FEH
+    '\u0628': 'b' #   Arabic Letter BEH
+    '\u0645': 'm' #   Arabic Letter MEEM
+    '\u0631': 'r' #   Arabic Letter REH
+    '\u0644': 'l' #   Arabic Letter LAM
+    '\u0634': 'sh' #   Arabic Letter SHEEN
+    '\u0633': 's' #   Arabic Letter SHEEN
+    '\u062b': 's' #   Arabic Letter THEH
+    '\u0635': 's' #   Arabic Letter SAD
+    '\u0621': '' #   Arabic Letter HAMZA
+    '\u06be': 's' #   Arabic Letter HEH DOACHASHMEE
+    '\u064b': 'n' #   Arabic Letter FATHATAN
+    '\u064e': 'n' #   Arabic sign FATHATAN
+    '\u0652': '' #   Arabic Letter SUKUN
+    '\u0651': '' #   Arabic Letter SHADDA