interscript 0.1.6 → 2.1.0a9

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

@@ -1,87 +0,0 @@
----
-authority_id: odni
-id: 2015
-language: 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

@@ -1,148 +0,0 @@
----
-authority_id: odni
-id: 2015
-language: 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

@@ -1,136 +0,0 @@
----
-authority_id: odni
-id: 2015
-language: 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-mkd-Cyrl-Latn-2015.yaml

@@ -1,122 +0,0 @@
----
-authority_id: odni
-id: 2015
-language: mkd
-source_script: Cyrl
-destination_script: Latn
-name: Standards for the transliteration of macedonian personal names in written reports and products
-source: ICS-630-01 Annex H
-creation_date: 2015
-confirmation_date: 2015
-description: |
-  This system is the Intelligence Community (IC) standard for the transliteration of Macedonian
-  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 Macedonian 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 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 Macedonian-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 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.
-
-tests:
-  - source: Билјана
-    expected: Biljana
-  - source: Душко
-    expected: Dushko
-
-map:
-  rules:
-    - pattern: \u0053 # S => Dz
-      result: Dz
-    - pattern: \u0073 # s => dz
-      result: dz
-
-  characters:
-    '\u0410': 'A'     # А
-    '\u0411': 'B'     # Б
-    '\u0412': 'V'     # В
-    '\u0413': 'G'     # Г
-    '\u0414': 'D'     # Д
-    '\u0403': 'Gj'    # Ѓ
-    '\u0415': 'E'     # Е
-    '\u0416': 'Zh'    # Ж
-    '\u0417': 'Z'     # З
-    '\u0418': 'I'     # И
-    '\u0408': 'J'     # Ј
-    '\u041A': 'K'     # К
-    '\u041B': 'L'     # Л
-    '\u0409': 'Lj'    # Љ
-    '\u041C': 'M'     # М
-    '\u041D': 'N'     # Н
-    '\u040A':  Nj     # Њ
-    '\u041E': 'O'     # О
-    '\u041F': 'P'     # П
-    '\u0420': 'R'     # Р
-    '\u0421': 'S'     # С
-    '\u0422': 'T'     # Т
-    '\u040C': 'Kj'    # Ќ
-    '\u0423': 'U'     # У
-    '\u0424': 'F'     # Ф
-    '\u0425': 'H'     # Х
-    '\u0426': 'Ts'    # Ц
-    '\u0427': 'Ch'    # Ч
-    '\u040F': 'Dzh'   # Џ
-    '\u0428': 'Sh'    # Ш
-    '\u2019': ''      # ’
-
-    '\u0430': 'a'     # а
-    '\u0431': 'b'     # б
-    '\u0432': 'v'     # в
-    '\u0433': 'g'     # г
-    '\u0434': 'd'     # д
-    '\u0453': 'gj'    # ѓ
-    '\u0435': 'e'     # e
-    '\u0436': 'zh'    # ж
-    '\u0437': 'z'     # з
-    '\u0438': 'i'     # и
-    '\u0458': 'j'     # ј
-    '\u043A': 'k'     # к
-    '\u043B': 'l'     # л
-    '\u0459': 'lj'    # љ
-    '\u043C': 'm'     # м
-    '\u043D': 'n'     # н
-    '\u045A': 'nj'    # њ
-    '\u043E': 'o'     # о
-    '\u043F': 'p'     # п
-    '\u0440': 'r'     # р
-    '\u0441': 's'     # с
-    '\u0442': 't'     # т
-    '\u045C': 'kj'    # ќ
-    '\u0443': 'u'     # у
-    '\u0444': 'f'     # ф
-    '\u0445': 'h'     # х
-    '\u0446': 'ts'    # ц
-    '\u0447': 'ch'    # ч
-    '\u045F': 'dzh'   # џ
-    '\u0448': 'sh'    # ш