interscript-maps 2.0.5

data/maps/mvd-rus-Cyrl-Latn-2010.imp

@@ -0,0 +1,40 @@
+metadata {
+  authority_id: mvd
+  id: 2010
+  language: iso-639-2:bel
+  source_script: Cyrl
+  destination_script: Latn
+  name: |
+    8/22721 On approval of the Instructions on the organization of work of units of citizenship
+    and migration of internal affairs bodies on the issuance, registration, exchange,
+    invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+  url: https://pravo.by/document/?guid=3871&p0=W21022721
+  creation_date: 2010
+
+  description: |
+    RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
+    June 28, 2010 No. 200
+    On approval of the Instructions on the organization of work of units of citizenship
+    and migration of internal affairs bodies on the issuance, registration, exchange,
+    invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+
+  notes:
+    - check notes from mvd-rus-Cyrl-Latn-2008
+}
+
+tests {
+  test "Ева", "Eva"
+  test "Васiльева", "Vasileva"
+  test "Адъютантов", "Adjutantov"
+}
+
+dependency "mvd-rus-Cyrl-Latn-2008", as: cyrllatn
+
+stage {
+  run map.cyrllatn.stage.translit
+
+  # POSTRULES
+  sub "\u0301", "" # remove diacritics
+
+  compose
+}

data/maps/odni-ara-Arab-Latn-2004.imp

@@ -0,0 +1,106 @@
+metadata {
+  authority_id: odni
+  id: 2004
+  language: ics-630-01:ara
+  source_script: Arab
+  destination_script: Latn
+  name: Arabic Personal Names Office of the Director Of National Intelligence 2004 System
+  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Arabic_IC_Standard.doc
+  creation_date: 2004
+  confirmation_date: 2004-06
+  description:
+  notes:
+    - Long/Short Vowels Long and short vowels are not
+      distinguished in this system Samir (could be Saamir or
+      Samiir in Arabic).
+
+    - Double consonants Double consonants represented by the
+      Arabic shaddah are shown in most cases (e.g., Hassan,
+      Muhammad). Exceptions ’ayn and consonants represented by
+      digraphs are not doubled (e.g., al-Qadhafi [not
+      alQadhdhafi], Mubashir [not Mubashshir]).
+
+    - Hamzah (glottal stop) The hamzah is represented by an
+      apostrophe (’). Note that this is the same symbol used to
+      represent another consonant, the ’ayn.
+
+    - Ta’ marbutah (feminine ending marker) On the construct
+      form or when pronounced “t”, it is represented with a roman
+      t. In all other cases, it is represented with an h.
+
+    - Digraphs No distinction is made between digraphs such as
+      sh and single contiguous letters (e.g., s followed by h).
+
+    - Definite article “al” (‘the’) Follows Arabic spelling
+      rather than pronunciation. That is, sun letter assimilation
+      is not shown in the Romanized form (e.g., ’Abd-alRahman,
+      not ’Abd-ar-Rahman).
+
+    - Diphthongs the second element of the diphthong is
+      represented by a y or a w (rather than an i or a u)
+      Haytham, Faysal, Tawfiq, Rawdah.
+
+    - Hyphens Hyphens (-) are used to connect name elements
+      within a name ’Abd- al Rahman, Abu-al-Bashar, Bin-Ladin.
+      Exceptions Names that incorporate “Allah” as part of the
+      name (e.g., ’Abdallah, Nasrallah), names marked by the
+      lineage/family marker “Al” (e.g., Al Thani) are not
+      hyphenated.
+
+    - The definite article, “al”, within name phrases, is
+      Romanized as al and not as ul Nur-al-Din (not Nur-ul-Din).
+      It is not capitalized when name-initial.
+
+    - Names that incorporate Allah as part of the name retain the
+      a of Allah rather than a grammatical marker u ’Abdallah (
+      not ’Abdullah).
+
+    - Foreign names borrowed or appearing in Arabic are spelled
+      according to the standard Western tradition Georges,
+      Michel. However, names of non-Arabic origin no longer
+      considered foreign by Arabic speakers follow the IC
+      conventions Butrus (not Peter).
+
+    - Prefix ‫بن‬ (bin ‘son of’) is Romanized Bin unless written
+      with an alif, in which case it is Romanized as Ibn. The
+      colloquial form Bu (‘father’) should not be standardized as
+      Abu. These prefixes are capitalized.
+
+    - In general, Romanization follows the Modern Standard
+      Arabic (MSA) form rather than local pronunciation
+      standards. For example, the letter ‫ج‬ (jim) is represented
+      as a j even when pronounced as a “g” (e.g., Egyptian Gamal
+      is Romanized as Jamal).
+}
+
+tests {
+  test "مِصر", "Miṣr"
+  test "قَطَر", "Qaṭar"
+  test "المَغرِب", "Al Maghrib"
+  test "الجُمهُورِيَّة العِراقِيَّة", "Al Jumhuriyah al ’Iraqiyah"
+  test "جُمهُورِيَّة العِراق", "Jumhuriyat al ’Iraq"
+  test "جُمهُورِيَّة مِصر العَرَبِيَّة", "Jumhuriyat Miṣr al ’Arabiyah"
+  test "بَغداد", "Baghdad"
+  test "تُونِس", "Tunis"
+  test "حَسّان", "Hassan"
+  test "مُحَمَّد", "Muhammad"
+  test "القَذَّافِي", "Al Qadhafi"
+  test "مُبَشِّر", "Mubashir"
+  test "الجَزائِر", "Al Jaza’ir"
+  test "عَبدالرَحمَن", "’Abd al Rahman"
+  test "هَيْثَم", "Haytham"
+  test "فَيْصَل", "Fayṣal"
+  test "تَوْفِيق", "Tawfiq"
+  test "رَوْضَة", "Rawḍah"
+  test "نُورُالدِين", "Nur al Din"
+  test "عَبدُاللَّه", "’Abdallah"
+}
+
+dependency "odni-ara-Arab-Latn-2015", as: arablatn
+
+stage {
+
+  run map.arablatn.stage.main
+
+}
+

data/maps/odni-ara-Arab-Latn-2015.imp

@@ -0,0 +1,281 @@
+metadata {
+  authority_id: odni
+  id: 2017
+  language: ics-630-01:ara
+  source_script: Arab
+  destination_script: Latn
+  name: Office of the Director Of National Intelligence Arabic Personal Names 2015 System
+  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20A%20-%20Arabic_Personal_Names_FLTS%20(U).pdf
+  creation_date: 2017
+  confirmation_date: 2018-06
+  description: |
+    This system, adapted from the Board on Geographic Names, is
+    the Intelligence Community (IC) standard for the
+    transliteration of Arabic 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
+    modern standard Arabic that can then be linked to forensic
+    information in ways that will help identify the referent of
+    the name. Ambiguities can result from the Romanization of
+    Arabic names because the Arabic source generally omits
+    short vowel markings, double consonant marks, and other
+    diacritics that would clearly distinguish the name.
+    Linguists use their experience with the language and aids
+    such as on-line tools and name dictionaries to determine
+    the exact Arabic and the appropriate transliteration into
+    the Roman alphabet. 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 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 Arabic-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 online 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 plus the apostrophe. 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: |
+    - Long/Short Vowels: Long and short vowels are not
+    distinguished in this system Samir (could be Saamir or
+    Samiir in Arabic).
+
+    - Double consonants: Double consonants represented by the
+    Arabic shaddah are shown in most cases (e.g., Hassan,
+    Muhammad). Exceptions: ’ayn and consonants represented by
+    digraphs are not doubled (e.g., al-Qadhafi [not
+    alQadhdhafi], Mubashir [not Mubashshir]).
+
+    - Hamzah (glottal stop): The hamzah is represented by an
+    apostrophe (’). Note that this is the same symbol used to
+    represent another consonant, the ’ayn.
+
+    - Ta’ marbutah (feminine ending marker): On the construct
+    form or when pronounced “t”, it is represented with a roman
+    t. In all other cases, it is represented with an h.
+
+    - Digraphs: No distinction is made between digraphs such as
+    sh and single contiguous letters (e.g., s followed by h).
+
+    - Definite article “al” (‘the’): Follows Arabic spelling
+    rather than pronunciation. That is, sun letter assimilation
+    is not shown in the Romanized form (e.g., ’Abd-alRahman,
+    not ’Abd-ar-Rahman).
+
+    - Diphthongs: the second element of the diphthong is
+      represented by a y or a w (rather than an i or a u):
+      Haytham, Faysal, Tawfiq, Rawdah.
+
+    - Hyphens: Hyphens (-) are used to connect name elements
+      within a name: ’Abd- al Rahman, Abu-al-Bashar, Bin-Ladin.
+      Exceptions: Names that incorporate “Allah” as part of the
+      name (e.g., ’Abdallah, Nasrallah), names marked by the
+      lineage/family marker “Al” (e.g., Al Thani) are not
+      hyphenated.
+
+    - The definite article, “al”, within name phrases, is
+      Romanized as al and not as ul: Nur-al-Din (not Nur-ul-Din).
+      It is not capitalized when name-initial.
+
+    - Names that incorporate Allah as part of the name retain the
+      a of Allah rather than a grammatical marker u: ’Abdallah (
+      not ’Abdullah).
+
+    - Foreign names borrowed or appearing in Arabic are spelled
+      according to the standard Western tradition: Georges,
+      Michel. However, names of non-Arabic origin no longer
+      considered foreign by Arabic speakers follow the IC
+      conventions: Butrus (not Peter).
+
+    - Prefix ‫بن‬ (bin ‘son of’) is Romanized Bin unless written
+      with an alif, in which case it is Romanized as Ibn. The
+      colloquial form Bu (‘father’) should not be standardized as
+      Abu. These prefixes are capitalized.
+
+    - In general, Romanization follows the Modern Standard
+      Arabic (MSA) form rather than local pronunciation
+      standards. For example, the letter ‫ج‬ (jim) is represented
+      as a j even when pronounced as a “g” (e.g., Egyptian Gamal
+      is Romanized as Jamal).
+}
+
+tests {
+  test "مِصر", "Miṣr"
+  test "قَطَر", "Qaṭar"
+  test "المَغرِب", "Al Maghrib"
+  test "الجُمهُورِيَّة العِراقِيَّة", "Al Jumhuriyah al ’Iraqiyah"
+  test "جُمهُورِيَّة العِراق", "Jumhuriyat al ’Iraq"
+  test "جُمهُورِيَّة مِصر العَرَبِيَّة", "Jumhuriyat Miṣr al ’Arabiyah"
+  test "بَغداد", "Baghdad"
+  test "تُونِس", "Tunis"
+  test "حَسّان", "Hassan"
+  test "مُحَمَّد", "Muhammad"
+  test "القَذَّافِي", "Al Qadhafi"
+  test "مُبَشِّر", "Mubashir"
+  test "الجَزائِر", "Al Jaza’ir"
+  test "عَبدالرَحمَن", "’Abd al Rahman"
+  test "هَيْثَم", "Haytham"
+  test "فَيْصَل", "Fayṣal"
+  test "تَوْفِيق", "Tawfiq"
+  test "رَوْضَة", "Rawḍah"
+  test "نُورُالدِين", "Nur al Din"
+  test "عَبدُاللَّه", "’Abdallah"
+}
+
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # Tool used for Unicode finding:
+    # https://www.branah.com/unicode-converter
+
+    # pointing
+    sub "\u064e", "a" # َ fatha
+    sub "\u064e", "", after: "\u0629" # َ fatha followed by ta' marboota
+    sub "\u064e", "", after: "a" + any("ht") # َ fatha followed by ta' marboota, handling different order of conversion
+    sub "\u0650", "i" # ِ kasra
+    sub "\u064f", "u" # ُ damma
+    sub "\u0652", "" # ْ sokoon, see note A below
+
+
+    sub "\u0650\u064a", "i" # ـِي kasra followed by ي
+    sub "\u0650\u064a\u0651\u064e", "iy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any(["\u064e", "u064f"]) # ـِي kasra followed by ي
+    sub "\u064f\u0648", "u" # ـُو damma followed by و
+    sub "\u064e\u0627", "a" # ـَا fatha followed by ا
+    sub "\u064e\u0649", "á" # ـَى fatha followed by ى which is ا not ي
+    sub "\u064e\u0648\u0652", "aw" # ـَوْ
+    sub "\u064e\u064a\u0652", "ay" # ـَيْ
+    sub "\u0622", "a" # آ
+
+    # ta' marboota
+    sub "\u0629", "at" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "ah"
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+    # shadda
+
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u062a\u0651", "tt" # ت
+    sub "\u062b\u0651", "th" # ث
+    sub "\u062c\u0651", "jj" # ج
+    sub "\u062d\u0651", "hh" # ح
+    sub "\u062e\u0651", "kh" # خ
+    sub "\u062f\u0651", "dd" # د
+    sub "\u0630\u0651", "dh" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "sh" # ش
+    sub "\u0635\u0651", "ṣṣ" # ص
+    sub "\u0636\u0651", "ḍḍ" # ض
+    sub "\u0637\u0651", "ṭṭ" # ط
+    sub "\u0638\u0651", "ẓẓ" # ظ
+    sub "\u063a\u0651", "gh" # غ
+    sub "\u0641\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u0648\u0651", "ww" # و
+    sub "\u064a\u0651", "yy" # ي
+
+    sub "\u0626", "’" # ئ
+
+    sub boundary + "\u0627\u0644\u0644\u0651\u064e\u0647", "Allah"
+
+    sub non_word_boundary + maybe("\u064f") + "\u0627\u0644\u0644\u0651\u064e\u0647", "allah"
+
+    sub "\u0621", any(["’", ""]) # ء
+
+    sub boundary + "\u0627\u0644", "al " # ال
+    sub non_word_boundary + maybe("\u064f") + "\u0627\u0644", " al " # ال in middle of composite name
+
+    # '\uFE8E' : ''  # ﺎ
+
+
+    sub "\u0623", "" # أ
+    sub boundary + "\u0627", "" # ا
+    sub "\u0627", "a" # ا
+    sub "\u0628", "b" # ب
+    sub "\u062a", "t" # ت
+    sub "\u062b", "th" # ث
+    sub "\u062c", "j" # ج
+    sub "\u062d", "h" # ح
+    sub "\u062e", "kh" # خ
+    sub "\u062f", "d" # د
+    sub "\u0630", "dh" # ذ
+    sub "\u0631", "r" # ر
+    sub "\u0632", "z" # ز
+    sub "\u0633", "s" # س
+    sub "\u0634", "sh" # ش
+    sub "\u0635", "ṣ" # ص
+    sub "\u0636", "ḍ" # ض
+    sub "\u0637", "ṭ" # ط
+    sub "\u0638", "ẓ" # ظ
+    sub "\u0639", "’" # ع
+    sub "\u063a", "gh" # غ
+    sub "\u0641", "f" # ف
+    sub "\u0642", "q" # ق
+    sub "\u0643", "k" # ك
+    sub "\u0644", "l" # ل
+    sub "\u0645", "m" # م
+    sub "\u0646", "n" # ن
+    sub "\u0647", "h" # ه
+    sub "\u0648", "w" # و
+    sub "\u064a", "y" # ي
+  }
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'")
+  sub " Al ", " al " # ال
+
+  # don't capitalize defined article in the middle of a sentence
+
+
+}

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

@@ -0,0 +1,158 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  language: iso-639-2:aze
+  source_script: Cyrl
+  destination_script: Latn
+  name: Standards for the transliteration of azeri personal names in written reports and products
+  source: ICS-630-01 Annex P
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Azeri 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 Azeri 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:
+    Rashad Sadykhov (also seen as Rashad Sadigov, Рашад Садыхов). 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 Azeri-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 "Рашад Садыхов", "Rashad Sadykhov"
+}
+
+stage {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁЖХЧШЩЮЯ".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("Хх"))+any("Хх"), 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 "\u049C", "G" # Ҝ
+    sub "\u0492", "Gh" # Ғ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u04D8", "A" # Ә
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u0419", "Y" # Й
+    sub "\u0408", "Y" # Ј
+    sub "\u041A", "K" # К
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    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 "\u04BA", "H" # Һ
+    sub "\u0427", "Ch" # Ч
+    sub "\u04B8", "J" # Ҹ
+    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 "\u049D", "g" # ҝ
+    sub "\u0493", "gh" # ғ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u04D9", "a" # ә
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u0458", "y" # ј
+    sub "\u043A", "k" # к
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    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 "\u04BB", "h" # һ
+    sub "\u0447", "ch" # ч
+    sub "\u04B9", "j" # ҹ
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}