interscript-maps 2.5.2 → 3.0.0

data/maps/bgnpcgn-sah-Cyrl-Latn-2012.isc

@@ -0,0 +1,257 @@
+system "BGN-PCGN:sah-Cyrl:Latn:2012" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2012
+  language iso-639-2:sah
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Yakut (2012)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2012
+  confirmation_date 2017-11
+  description {
+    Yakut, or Sakha, is a Turkic language spoken by the Yakut people of the Sakha
+    (Yakutiya) Republic of the Russian Federation. The BGN/PCGN system romanizes names
+    written in the Yakut Cyrillic alphabet.
+  }
+
+  notes {
+    note "The characters в, ж, з, ф, ш, щ, ъ, ь, ю and я occur only in loanwords, and are represented in the same style as in the BGN/PCGN Romanization System for Russian."
+    note "Е and Ё should be romanized ye and yë word-initially and after vowels. In all other instances, they should be romanized e and ë."
+    note "The source document pairs the capital Ѳ (text-layer codepoint U+0472, FITA) with the lowercase ө (U+04E9); the standard Yakut capital is Ө (U+04E8). This map accepts both capitals and romanizes them Ö."
+    note "The source document prints the lowercase form of НЬ as the ligature њ (U+045A); this map maps нь (U+043D+044C), Нь, НЬ and њ to ny."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:"
+    note "All apostrophes appearing in romanization are U+2019"
+    note "Ë (U+00CB)  ë (U+00EB)  Ö (U+00D6)  ö (U+00F6)  Ü (U+00DC)  ü (U+00FC)"
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+  # every table row, upper and lower
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "G"
+   "г" ->  "g"
+   "Ҕ" ->  "Gh"
+   "ҕ" ->  "gh"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "ДЬ" ->  "DJ"
+   "Дь" ->  "Dj"
+   "дь" ->  "dj"
+   "Е" ->  "Ye"
+   "е" ->  "ye"
+   "Ё" ->  "Yë"
+   "ё" ->  "yë"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Й" ->  "Y"
+   "й" ->  "y"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "Ҥ" ->  "Ng"
+   "ҥ" ->  "ng"
+   "НЬ" ->  "NY"
+   "Нь" ->  "Ny"
+   "нь" ->  "ny"
+   "њ" ->  "ny"
+   "О" ->  "O"
+   "о" ->  "o"
+   "Ѳ" ->  "Ö"
+   "Ө" ->  "Ö"
+   "ө" ->  "ö"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Һ" ->  "H"
+   "һ" ->  "h"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "У" ->  "U"
+   "у" ->  "u"
+   "Ү" ->  "Ü"
+   "ү" ->  "ü"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ц" ->  "Ts"
+   "ц" ->  "ts"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Shch"
+   "щ" ->  "shch"
+   "Ъ" ->  "”"
+   "ъ" ->  "”"
+   "Ы" ->  "Y"
+   "ы" ->  "y"
+   "Ь" ->  "’"
+   "ь" ->  "’"
+   "Э" ->  "E"
+   "э" ->  "e"
+   "Ю" ->  "Yu"
+   "ю" ->  "yu"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+  # notes 1-2: ye/yë word-initially and after vowels; e/ë elsewhere
+   "бе" ->  "be"
+   "үе" ->  "üye"
+   "ое" ->  "oye"
+   "кё" ->  "kë"
+   "үё" ->  "üyë"
+}
+
+stage main {
+
+  # RULES
+  # notes 1-2: е and ё word-initially and after vowels
+  sub {
+    from boundary + "Е"
+    to "Ye"
+  }
+  sub {
+    from boundary + "е"
+    to "ye"
+  }
+  sub {
+    from "Е"
+    to "Ye"
+    before any("АаЕеЁёИиОоУуҮүЫыЭэЮюЯя")
+  }
+  sub {
+    from "е"
+    to "ye"
+    before any("АаЕеЁёИиОоУуҮүЫыЭэЮюЯя")
+  }
+  sub {
+    from boundary + "Ё"
+    to "Yë"
+  }
+  sub {
+    from boundary + "ё"
+    to "yë"
+  }
+  sub {
+    from "Ё"
+    to "Yë"
+    before any("АаЕеЁёИиОоУуҮүЫыЭэЮюЯя")
+  }
+  sub {
+    from "ё"
+    to "yë"
+    before any("АаЕеЁёИиОоУуҮүЫыЭэЮюЯя")
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "ДЬ" "DJ"
+    sub "Дь" "Dj"
+    sub "НЬ" "NY"
+    sub "Нь" "Ny"
+    sub "Ҕ" "Gh"
+    sub "Ҥ" "Ng"
+    sub "Ѳ" "Ö"
+    sub "Ө" "Ö"
+    sub "Ү" "Ü"
+    sub "Һ" "H"
+    sub "Щ" "Shch"
+    sub "Ы" "Y"
+    sub "Ъ" "”"
+    sub "Ь" "’"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ё" "Ë"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Й" "Y"
+    sub "К" "K"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Э" "E"
+
+    sub "дь" "dj"
+    sub "нь" "ny"
+    sub "њ" "ny"
+    sub "ҕ" "gh"
+    sub "ҥ" "ng"
+    sub "ө" "ö"
+    sub "ү" "ü"
+    sub "һ" "h"
+    sub "щ" "shch"
+    sub "ы" "y"
+    sub "ъ" "”"
+    sub "ь" "’"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ë"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "y"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "э" "e"
+  }
+
+}
+
+}

data/maps/bgnpcgn-syc-Syrc-Latn-2011.isc

@@ -0,0 +1,94 @@
+system "BGN-PCGN:syc-Syrc:Latn:2011" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2011
+  language iso-639-2:syc
+  source_script Syrc
+  destination_script Latn
+  name Romanization System for Modern Syriac Script (BGN/PCGN 2011 System)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693736/ROMANIZATION_OF_MODERN_SYRIAC.pdf
+  creation_date 2011
+  confirmation_date 2017-11
+  description {    The modern Syriac script is used today by Assyrian writers of the neo-Aramaic language.
+    This Romanization System may be applied to any toponyms written in this script as may be
+    encountered in parts of northern Iraq, Syria, northern Iran and eastern Turkey. The
+    Neo-Aramaic language has a degree of locally official status within Iraq, and accordingly
+    some bilingual Arabic and modern Syriac signage may be encountered.
+
+    The script is closely aligned to that of both Hebrew and Arabic, and, as these, is written
+    from right to left. In this Romanization System, “strong” consonants have been marked with
+    a sub-dot so as not to give a closer visual relation to either Arabic (which marks such
+    consonants with a cedilla) or Hebrew (which marks these with an underbar). The equivalences
+    where they exist in the Arabic and Hebrew scripts have also been shown only for a guide to
+    the cognate root.
+  }
+
+  notes {
+    note "Letters connect to the following letter (to the left) except those marked with † in the source table (Ālap, Dālat, Hē, Wāw, Zayn, Ṣādē, Rēsh, Taw)."
+    note "Kāp, Mīm and Nūn: the source table shows the form in independent or word-final position. The form initially and medially differs but this is not included in a standalone form in the Unicode Standard; the initial/medial form will however be automatically generated when using the letter’s Unicode encoding initially or medially in a word. To illustrate the different forms, using the Unicode encoding twice gives: ܟܟ (U+071F); ܡܡ (U+0721); and ܢܢ (U+0722)."
+    note "Ālap (ܐ) has a number of functions in modern Syriac script:\n\n• It appears word-initially to denote a vowel, and is sometimes followed by yōd or wāw to denote ‘ī’ or ‘ū’ respectively.\n• It appears word-medially to denote what historically was a glottal stop. It is understood that this does not now function as a “stop” in speech, though the Ālap still appears in the written form. This is romanized ’.\n• It appears word-medially to denote a long vowel ā or ē.\n• It appears word-finally to denote the long vowel ā or ē.\n\nGiven the ambiguity in its function, it is recommended that a reference source be consulted for further guidance as to the appropriate romanization."
+    note "Taw should be romanized ‘t’ when unaspirated, and ‘th’ when aspirated. A reference source should be consulted for further guidance as to the appropriate romanization."
+    note "Numerals in modern Syriac script are represented by letters of the alphabet: Ālap, Bēt, Gāmal = 1, 2, 3 etc.; Yōd = 10, Kāp = 20, Lāmad = 30 etc.; Qōp = 100, Rēsh = 200, Shīn = 300 and finally Taw = 400. Unlike Arabic, composite numerals are written from right-to-left, so for instance 12 is written ܝܒ (10+2). Given the limited number of single-character numerals, other numbers are naturally quite elaborately composed: for instance, 999 may be written as (90×10)+90+9 or as 400+400+100+90+9. Arabic numerals are also used."
+    note "Vowels are represented either by the “matres lectionis” (“mothers of reading”) ālap (ܐ), yōd (ܝ) and wāw (ܘ), that function both as consonants and vowels, or by pointing marks appearing above or below other letters. The pointing marks are, however, frequently omitted."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n\n’ (U+2019) , ‘ (U+2018)\nĀ (U+0100) , ā (U+0101)\nĒ (U+0112) , ē (U+0113)\nŪ (U+016A) , ū (U+016B)\nḤ (U+0048+0323) , ḥ (U+0068+0323)\nṬ (U+0054+0323) , ṭ (U+0074+0323)\nĪ (U+012A) , ī (U+012B)\nṢ (U+0053+0323) , ṣ (U+0073+0323)"
+    note "The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "ܒܝܬ" ->  "byt"
+   "ܫܡܫܐ" ->  "shmsh"
+   "ܡܠܟܐ" ->  "mlk"
+   "ܐܪܒܝܠ" ->  "rbyl"
+   "ܥܡܐ" ->  "‘m"
+   "ܚܡܪܐ" ->  "ḥmr"
+   "ܛܠܐ" ->  "ṭl"
+   "ܢܨܝܒܝܢ" ->  "nṣybyn"
+   "ܐܘܪܡܝܐ" ->  "wrmy"
+   "ܣܦܪܐ" ->  "spr"
+   "ܟܬܵܒܵܐ" ->  "ktābā"
+   "ܡܸܢ" ->  "min"
+   "ܬܫܵܐ" ->  "tshā"
+   "ܓܼ" ->  "gī"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "ܐ" ""                 # Ālap. See note 1 (’/ā/ē per function)
+    sub "ܒ" "b"                # Bēt
+    sub "ܓ" "g"                # Gāmal
+    sub "ܕ" "d"                # Dālat
+    sub "ܗ" "h"                # Hē
+    sub "ܘ" any(["w", "ū"])    # Wāw
+    sub "ܙ" "z"                # Zayn
+    sub "ܚ" "ḥ"     # Ḥēt
+    sub "ܛ" "ṭ"     # Ṭēt
+    sub "ܝ" any(["y", "ī"])    # Yōd
+    sub "ܟ" "k"                # Kāp
+    sub "ܠ" "l"                # Lāmad
+    sub "ܡ" "m"                # Mīm
+    sub "ܢ" "n"                # Nūn
+    sub "ܣ" "s"                # Semkat
+    sub "ܤ" "s"                # Semkat (final form)
+    sub "ܥ" "‘"                # ‘Ē
+    sub "ܦ" "p"                # Pē
+    sub "ܨ" "ṣ"     # Ṣādē
+    sub "ܩ" "q"                # Qōp
+    sub "ܪ" "r"                # Rēsh
+    sub "ܫ" "sh"               # Shīn
+    sub "ܬ" any(["t", "th"])   # Taw. See note 2
+
+    # VOWEL POINTING MARKS (Table 2)
+    sub "ܲ" "a"
+    sub "ܳ" "o"
+    sub "ܴ" "u"
+    sub "ܵ" "ā"
+    sub "ܸ" "i"
+    sub "ܹ" "ē"
+    sub "ܼ" "ī"
+  }
+}
+}

data/maps/bgnpcgn-syr-Syrc-Latn-2011.isc

@@ -0,0 +1,118 @@
+system "BGN-PCGN:syr-Syrc:Latn:2011" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2011
+  language iso-639-2:syr
+  source_script Syrc
+  destination_script Latn
+  name Romanization of modern Syriac script (2011)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693736/ROMANIZATION_OF_MODERN_SYRIAC.pdf
+  creation_date 2011
+  confirmation_date 2017-11
+  description {
+    The modern Syriac script is used today by Assyrian writers of the neo-Aramaic
+    language. This Romanization System may be applied to any toponyms written in
+    this script as may be encountered in parts of northern Iraq, Syria, northern
+    Iran and eastern Turkey. The Neo-Aramaic language has a degree of locally
+    official status within Iraq, and accordingly some bilingual Arabic and modern
+    Syriac signage may be encountered.
+
+    The script is closely aligned to that of both Hebrew and Arabic, and, as these,
+    is written from right to left. In this Romanization System, 'strong' consonants
+    have been marked with a sub-dot so as not to give a closer visual relation to
+    either Arabic (which marks such consonants with a cedilla) or Hebrew (which
+    marks these with an underbar). The equivalences where they exist in the Arabic
+    and Hebrew scripts have also been shown only for a guide to the cognate root.
+  }
+
+  notes {
+    note "Letters connect to the following letter (to the left) except those referenced to this note."
+    note "This is the form in independent or word-final position. The form initially and medially differs but this is not included in a standalone form in the Unicode Standard. The initial/medial form will however be automatically generated in using the letter's Unicode encoding initially or medially in a word. To illustrate the different forms, using the Unicode encoding twice gives: U+071F; U+0721; and U+0722."
+    note "Ālap (U+0710) has a number of functions in modern Syriac script: it appears word-initially to denote a vowel, and is sometimes followed by yod or waw to denote i-macron or u-macron respectively; it appears word-medially to denote what historically was a glottal stop, which is understood not to function as a stop in speech now, though the alap still appears in the written form, and is romanized '.'; it appears word-medially and word-finally to denote the long vowel a-macron or e-macron. Given the ambiguity in its function, it is recommended that a reference source be consulted for further guidance as to the appropriate romanization."
+    note "Taw (U+072C) should be romanized t when unaspirated, and th when aspirated. A reference source should be consulted for further guidance as to the appropriate romanization."
+    note "Numerals in modern Syriac script are represented by letters of the alphabet: alap, bet, gamal = 1, 2, 3 etc.; yod = 10, kap = 20, lamad = 30 etc.; qop = 100, resh = 200, shin = 300 and finally taw = 400. Unlike Arabic, composite numerals are written from right to left, so for instance 12 is written bet then yod. Given the limited number of single-character numerals, other numbers are naturally quite elaborately composed: for instance, 999 may be written as (90x10)+90+9 or as 400+400+100+90+9. Arabic numerals are also used."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:"
+    note "Right single quotation mark U+2019, left single quotation mark U+2018; A with macron U+0100, a with macron U+0101; E with macron U+0112, e with macron U+0113; U with macron U+016A, u with macron U+016B; H with dot below U+0048+0323, h with dot below U+0068+0323; T with dot below U+0054+0323, t with dot below U+0074+0323; I with macron U+012A, i with macron U+012B; S with dot below U+0053+0323, s with dot below U+0073+0323."
+    note "The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+    note "The source table gives waw as w or u-macron, yod as y or i-macron, and taw as t or th. This map renders w, y and t; the alternatives are the vocalization-dependent readings (the pointing marks are frequently omitted), the composition point for a vocalization model."
+  }
+}
+
+tests {
+  # every table row; the vowel pointing marks
+   "ܐ" ->  ""
+   "ܒ" ->  "b"
+   "ܓ" ->  "g"
+   "ܕ" ->  "d"
+   "ܗ" ->  "h"
+   "ܘ" ->  "w"
+   "ܙ" ->  "z"
+   "ܚ" ->  "ḥ"
+   "ܛ" ->  "ṭ"
+   "ܝ" ->  "y"
+   "ܟ" ->  "k"
+   "ܠ" ->  "l"
+   "ܡ" ->  "m"
+   "ܢ" ->  "n"
+   "ܣ" ->  "s"
+   "ܤ" ->  "s"
+   "ܥ" ->  "‘"
+   "ܦ" ->  "p"
+   "ܨ" ->  "ṣ"
+   "ܩ" ->  "q"
+   "ܪ" ->  "r"
+   "ܫ" ->  "sh"
+   "ܬ" ->  "t"
+   "ܒܲ" ->  "ba"
+   "ܒܳ" ->  "bo"
+   "ܒܴ" ->  "bu"
+   "ܒܵ" ->  "bā"
+   "ܒܸ" ->  "bi"
+   "ܒܹ" ->  "bē"
+   "ܒܼ" ->  "bī"
+}
+
+
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "ܐ" ""  # Alap. See note
+    sub "ܒ" "b"  # Bet
+    sub "ܓ" "g"  # Gamal
+    sub "ܕ" "d"  # Dalat. See note
+    sub "ܗ" "h"  # He. See note
+    sub "ܘ" "w"  # Waw. See note
+    sub "ܙ" "z"  # Zayn. See note
+    sub "ܚ" "ḥ"  # Het
+    sub "ܛ" "ṭ"  # Tet
+    sub "ܝ" "y"  # Yod
+    sub "ܟ" "k"  # Kap. See note
+    sub "ܠ" "l"  # Lamad
+    sub "ܡ" "m"  # Mim. See note
+    sub "ܢ" "n"  # Nun. See note
+    sub "ܣ" "s"  # Semkat
+    sub "ܤ" "s"  # Semkat (final form)
+    sub "ܥ" "‘"  # E
+    sub "ܦ" "p"  # Pe
+    sub "ܨ" "ṣ"  # Sade. See note
+    sub "ܩ" "q"  # Qop
+    sub "ܪ" "r"  # Resh
+    sub "ܫ" "sh"  # Shin
+    sub "ܬ" "t"  # Taw. See note
+
+    # Vowel pointing marks
+    sub "ܲ" "a"
+    sub "ܳ" "o"
+    sub "ܴ" "u"
+    sub "ܵ" "ā"
+    sub "ܸ" "i"
+    sub "ܹ" "ē"
+    sub "ܼ" "ī"
+  }
+
+}
+
+}