interscript-maps 3.0.0 → 3.1.0

data/maps/alalc-vai-Vaii-Latn-2010.isc

@@ -0,0 +1,305 @@
+system "ALA-LC:vai-Vaii:Latn:2010" {
+
+metadata {
+  authority_id alalc
+  id 2010
+  language iso-639-2:vai
+  source_script Vaii
+  destination_script Latn
+  name "Vai Romanization Table (2010)"
+  url https://www.loc.gov/catdir/cpso/romanization/vai.pdf
+  creation_date 2010
+  adoption_date
+  description {    ALA-LC Vai Romanization Table, 2010 version. One-to-one
+    romanization of the Vai syllabary as scoped by the table: 239
+    syllable characters across the e, i, a, o, u, ɔ and ɛ vowel
+    series (including the nasalized syllables and the ŋã, kpã, gbɔ̃,
+    kpɛ̃, gɛ̃, ŋgɛ̃, ŋɔ̃, ŋɛ̃ forms) plus the syllabic nasal ꘋ (ŋ).
+    Nasalized Latin vowels are normalized to the precomposed tilded
+    letters (ẽ ĩ ã õ ũ) where they exist and to the combining tilde
+    for ɔ̃ and ɛ̃. The extended Latin letters ɓ ɗ ɛ ŋ ɲ ɔ follow the
+    table's Note 1 (Unicode standard usage approved by NDMSO, 2007).
+  }
+
+  notes {
+    note "Note 1 (MARC-8): within a strictly MARC-8 environment the
+    double underscore may be applied to a base character following
+    LCRI 1.0E for ɓ ɗ ɛ ŋ ɲ ɔ (b̳ d̳ e̳ n̳ n̳ o̳); the ambiguity of n̳
+    illustrates the advantage of extended Latin, long-standing in the
+    Vai transcription tradition."
+    note "Note 2 of the table excludes four categories of rarely used
+    Vai characters: archaic logograms, Momolu Massaquoi's innovations
+    (c. 1911), digits, and punctuation. In addition, the printed
+    syllable grid does not include the twenty-eight syllable
+    characters of the th, dh, sh and zh series of the Unicode Vai
+    block (U+A50F U+A511 U+A517 U+A519 and the other twenty-four
+    members); this omission is the source table's, and is recorded
+    here so it is not mistaken for a transcription gap."
+    note "The syllabic lengthener ꘌ is described in the table as
+    repeating the preceding vowel; it is an instruction rather than a
+    romanization value, so it carries no character rule."
+    note "The syllables printed che chi cha cho chu chɔ chɛ correspond to
+    the ch romanization of the table; the table uses ch rather than c
+    before i and e."
+  }
+}
+
+tests {
+  "ꔀ" -> "e"
+  "ꔁ" -> "ẽ"
+  "ꕉ" -> "a"
+  "ꕱ" -> "o"
+  "ꖕ" -> "u"
+  "ꖺ" -> "ɔ"
+  "ꗡ" -> "ɛ"
+  "ꖻ" -> "ɔ̃"
+  "ꗢ" -> "ɛ̃"
+  "ꘋ" -> "ŋ"
+  "ꔀꔤꕉꕱꖕꗡ" -> "eiaouɛ"
+}
+
+stage main {
+  parallel {
+    sub "ꔀ" "e"
+    sub "ꔤ" "i"
+    sub "ꕉ" "a"
+    sub "ꕱ" "o"
+    sub "ꔁ" "ẽ"
+    sub "ꔥ" "ĩ"
+    sub "ꕊ" "ã"
+    sub "ꕲ" "õ"
+    sub "ꕋ" "ŋã"
+    sub "ꔂ" "he"
+    sub "ꔦ" "hi"
+    sub "ꕌ" "ha"
+    sub "ꕳ" "ho"
+    sub "ꔧ" "hĩ"
+    sub "ꕍ" "hã"
+    sub "ꔃ" "we"
+    sub "ꔨ" "wi"
+    sub "ꕎ" "wa"
+    sub "ꕴ" "wo"
+    sub "ꔄ" "wẽ"
+    sub "ꔩ" "wĩ"
+    sub "ꕏ" "wã"
+    sub "ꕵ" "wõ"
+    sub "ꔅ" "pe"
+    sub "ꔪ" "pi"
+    sub "ꕐ" "pa"
+    sub "ꕶ" "po"
+    sub "ꔆ" "be"
+    sub "ꔫ" "bi"
+    sub "ꕑ" "ba"
+    sub "ꕷ" "bo"
+    sub "ꔇ" "ɓe"
+    sub "ꔬ" "ɓi"
+    sub "ꕒ" "ɓa"
+    sub "ꕸ" "ɓo"
+    sub "ꔈ" "mɓe"
+    sub "ꔭ" "mɓi"
+    sub "ꕓ" "mɓa"
+    sub "ꕹ" "mɓo"
+    sub "ꔉ" "kpe"
+    sub "ꔮ" "kpi"
+    sub "ꕔ" "kpa"
+    sub "ꕺ" "kpo"
+    sub "ꕕ" "kpã"
+    sub "ꔊ" "mgbe"
+    sub "ꔯ" "mgbi"
+    sub "ꕖ" "mgba"
+    sub "ꕻ" "mgbo"
+    sub "ꔋ" "gbe"
+    sub "ꔰ" "gbi"
+    sub "ꕗ" "gba"
+    sub "ꕼ" "gbo"
+    sub "ꔌ" "fe"
+    sub "ꔱ" "fi"
+    sub "ꕘ" "fa"
+    sub "ꕽ" "fo"
+    sub "ꔍ" "ve"
+    sub "ꔲ" "vi"
+    sub "ꕙ" "va"
+    sub "ꕾ" "vo"
+    sub "ꔎ" "te"
+    sub "ꔳ" "ti"
+    sub "ꕚ" "ta"
+    sub "ꕿ" "to"
+    sub "ꔐ" "de"
+    sub "ꔵ" "di"
+    sub "ꕜ" "da"
+    sub "ꖁ" "do"
+    sub "ꔒ" "le"
+    sub "ꔷ" "li"
+    sub "ꕞ" "la"
+    sub "ꖃ" "lo"
+    sub "ꔓ" "re"
+    sub "ꔸ" "ri"
+    sub "ꕟ" "ra"
+    sub "ꖄ" "ro"
+    sub "ꔔ" "ɗe"
+    sub "ꔹ" "ɗi"
+    sub "ꕠ" "ɗa"
+    sub "ꖅ" "ɗo"
+    sub "ꔕ" "nɗe"
+    sub "ꔺ" "nɗi"
+    sub "ꕡ" "nɗa"
+    sub "ꖆ" "nɗo"
+    sub "ꔖ" "se"
+    sub "ꔻ" "si"
+    sub "ꕢ" "sa"
+    sub "ꖇ" "so"
+    sub "ꔘ" "ze"
+    sub "ꔽ" "zi"
+    sub "ꕤ" "za"
+    sub "ꖉ" "zo"
+    sub "ꔚ" "che"
+    sub "ꔿ" "chi"
+    sub "ꕦ" "cha"
+    sub "ꖋ" "cho"
+    sub "ꔛ" "je"
+    sub "ꕀ" "ji"
+    sub "ꕨ" "ja"
+    sub "ꖌ" "jo"
+    sub "ꔜ" "nje"
+    sub "ꕁ" "nji"
+    sub "ꕧ" "nja"
+    sub "ꖍ" "njo"
+    sub "ꔝ" "ye"
+    sub "ꕂ" "yi"
+    sub "ꕩ" "ya"
+    sub "ꖎ" "yo"
+    sub "ꔞ" "ke"
+    sub "ꕃ" "ki"
+    sub "ꕪ" "ka"
+    sub "ꖏ" "ko"
+    sub "ꕫ" "kã"
+    sub "ꔟ" "ŋge"
+    sub "ꕄ" "ŋgi"
+    sub "ꕬ" "ŋga"
+    sub "ꖐ" "ŋgo"
+    sub "ꔠ" "ge"
+    sub "ꕅ" "gi"
+    sub "ꕭ" "ga"
+    sub "ꖑ" "go"
+    sub "ꔡ" "me"
+    sub "ꕆ" "mi"
+    sub "ꕮ" "ma"
+    sub "ꖒ" "mo"
+    sub "ꔢ" "ne"
+    sub "ꕇ" "ni"
+    sub "ꕯ" "na"
+    sub "ꖓ" "no"
+    sub "ꔣ" "ɲe"
+    sub "ꕈ" "ɲi"
+    sub "ꕰ" "ɲa"
+    sub "ꖔ" "ɲo"
+    sub "ꖕ" "u"
+    sub "ꖺ" "ɔ"
+    sub "ꗡ" "ɛ"
+    sub "ꖖ" "ũ"
+    sub "ꖻ" "ɔ̃"
+    sub "ꗢ" "ɛ̃"
+    sub "ꖼ" "ŋɔ̃"
+    sub "ꗣ" "ŋɛ̃"
+    sub "ꖗ" "hu"
+    sub "ꖽ" "hɔ"
+    sub "ꗤ" "hɛ"
+    sub "ꖘ" "hũ"
+    sub "ꖾ" "hɔ̃"
+    sub "ꗥ" "hɛ̃"
+    sub "ꖙ" "wu"
+    sub "ꖿ" "wɔ"
+    sub "ꗦ" "wɛ"
+    sub "ꖚ" "wũ"
+    sub "ꗀ" "wɔ̃"
+    sub "ꗧ" "wɛ̃"
+    sub "ꖛ" "pu"
+    sub "ꗁ" "pɔ"
+    sub "ꗨ" "pɛ"
+    sub "ꖜ" "bu"
+    sub "ꗂ" "bɔ"
+    sub "ꗩ" "bɛ"
+    sub "ꖝ" "ɓu"
+    sub "ꗃ" "ɓɔ"
+    sub "ꗪ" "ɓɛ"
+    sub "ꖞ" "mɓu"
+    sub "ꗄ" "mɓɔ"
+    sub "ꗫ" "mɓɛ"
+    sub "ꖟ" "kpu"
+    sub "ꗅ" "kpɔ"
+    sub "ꗬ" "kpɛ"
+    sub "ꗭ" "kpɛ̃"
+    sub "ꖠ" "mgbu"
+    sub "ꗆ" "mgbɔ"
+    sub "ꗮ" "mgbɛ"
+    sub "ꖡ" "gbu"
+    sub "ꗇ" "gbɔ"
+    sub "ꗯ" "gbɛ"
+    sub "ꗈ" "gbɔ̃"
+    sub "ꗰ" "gbɛ̃"
+    sub "ꖢ" "fu"
+    sub "ꗉ" "fɔ"
+    sub "ꗱ" "fɛ"
+    sub "ꖣ" "vu"
+    sub "ꗊ" "vɔ"
+    sub "ꗲ" "vɛ"
+    sub "ꖤ" "tu"
+    sub "ꗋ" "tɔ"
+    sub "ꗳ" "tɛ"
+    sub "ꖦ" "du"
+    sub "ꗍ" "dɔ"
+    sub "ꗵ" "dɛ"
+    sub "ꖨ" "lu"
+    sub "ꗏ" "lɔ"
+    sub "ꗷ" "lɛ"
+    sub "ꖩ" "ru"
+    sub "ꗐ" "rɔ"
+    sub "ꗸ" "rɛ"
+    sub "ꖪ" "ɗu"
+    sub "ꗑ" "ɗɔ"
+    sub "ꗹ" "ɗɛ"
+    sub "ꖫ" "nɗu"
+    sub "ꗒ" "nɗɔ"
+    sub "ꗺ" "nɗɛ"
+    sub "ꖬ" "su"
+    sub "ꗓ" "sɔ"
+    sub "ꗻ" "sɛ"
+    sub "ꖮ" "zu"
+    sub "ꗕ" "zɔ"
+    sub "ꗽ" "zɛ"
+    sub "ꖰ" "chu"
+    sub "ꗗ" "chɔ"
+    sub "ꗿ" "chɛ"
+    sub "ꖱ" "ju"
+    sub "ꗘ" "jɔ"
+    sub "ꘀ" "jɛ"
+    sub "ꖲ" "nju"
+    sub "ꗙ" "njɔ"
+    sub "ꘁ" "njɛ"
+    sub "ꖳ" "yu"
+    sub "ꗚ" "yɔ"
+    sub "ꘂ" "yɛ"
+    sub "ꖴ" "ku"
+    sub "ꗛ" "kɔ"
+    sub "ꘃ" "kɛ"
+    sub "ꖵ" "ŋgu"
+    sub "ꗜ" "ŋgɔ"
+    sub "ꘄ" "ŋgɛ"
+    sub "ꘅ" "ŋgɛ̃"
+    sub "ꖶ" "gu"
+    sub "ꗝ" "gɔ"
+    sub "ꘆ" "gɛ"
+    sub "ꘇ" "gɛ̃"
+    sub "ꖷ" "mu"
+    sub "ꗞ" "mɔ"
+    sub "ꘈ" "mɛ"
+    sub "ꖸ" "nu"
+    sub "ꗟ" "nɔ"
+    sub "ꘉ" "nɛ"
+    sub "ꖹ" "ɲu"
+    sub "ꗠ" "ɲɔ"
+    sub "ꘊ" "ɲɛ"
+    sub "ꘋ" "ŋ"
+  }
+}
+}

data/maps/alalc-zgh-Tfng-Latn-2012.isc

@@ -0,0 +1,114 @@
+system "ALA-LC:zgh-Tfng:Latn:2012" {
+
+metadata {
+  authority_id alalc
+  id 2012
+  language iso-639-2:zgh
+  source_script Tfng
+  destination_script Latn
+  name "Moroccan Tamazight Romanization Table (2012)"
+  url https://www.loc.gov/catdir/cpso/romanization/tamazight.pdf
+  creation_date 2012
+  adoption_date
+  description {    ALA-LC Moroccan Tamazight Romanization Table, approved by
+    CC:AAM 2012-01-22 (no version year printed on the document; the
+    approval date is from the PDF metadata). The table follows, with
+    minimal exceptions, the romanization method used by the Institut
+    Royal de la Culture Amazighe (IRCAM) for texts published in the
+    Central Atlas Tamazight and Standard Tamazight languages of
+    Morocco, using neo-Tifinagh script. Characters needed to support
+    the Tachelhit and Tarifit languages have also been included, so
+    the scope covers all living Moroccan Tamazight languages in
+    neo-Tifinagh. Forty-two letter rules plus the labialized digraphs
+    and the labialization mark (tamatart). The spirant letters romanize
+    with a macron below (ḇ ḡ ḏ ṯ, U+0331); the emphatic letters with a
+    dot below (ḍ ḥ ṛ ṣ ṭ ẓ); the Tachelhit emphatic d with both marks.
+  }
+
+  notes {
+    note "The document example romanizes ⴰⵖⵍⵢⴰⵙ as Aɣlyas, or as
+    Aglyas if applying LCRI 1.0E / LCPS 1.4 (Note 1: extended Latin
+    characters are used in the standard orthography; apply LCRI 1.0E /
+    LCPS 1.4 as needed). The initial capital in the example is proper-
+    noun capitalization, not a script property; the map yields the
+    mechanical aɣlyas."
+    note "Note 2: the Tifinagh modifier letter labialization mark
+    (tamatart, ⵯ) romanizes as the superscript degree sign (°); the
+    labialized digraphs ⴳⵯ and ⴽⵯ carry it as g° and k°."
+    note "ⴺ (YADDH) romanizes as d with dot below and macron below
+    (ḏ with underdot), per the printed table; the mark order in the
+    encoded output is dot below (U+0323) then macron below (U+0331)."
+  }
+}
+
+tests {
+  "ⴰⵖⵍⵢⴰⵙ" -> "aɣlyas"
+  "ⴲ" -> "ḇ"
+  "ⴴ" -> "g̱"
+  "ⴸ" -> "ḏ"
+  "ⴹ" -> "ḍ"
+  "ⴺ" -> "ḍ̱"
+  "ⵃ" -> "ḥ"
+  "ⵕ" -> "ṛ"
+  "ⵚ" -> "ṣ"
+  "ⵝ" -> "ṯ"
+  "ⵟ" -> "ṭ"
+  "ⵥ" -> "ẓ"
+  "ⴳⵯ" -> "g°"
+  "ⵯ" -> "°"
+}
+
+stage main {
+  parallel {
+    sub "ⴳⵯ" "g°"
+    sub "ⴽⵯ" "k°"
+  }
+
+  parallel {
+    sub "ⴰ" "a"
+    sub "ⴱ" "b"
+    sub "ⴲ" "ḇ"
+    sub "ⴳ" "g"
+    sub "ⴴ" "g̱"
+    sub "ⴵ" "ğ"
+    sub "ⴷ" "d"
+    sub "ⴸ" "ḏ"
+    sub "ⴹ" "ḍ"
+    sub "ⴺ" "ḍ̱"
+    sub "ⴻ" "e"
+    sub "ⴼ" "f"
+    sub "ⴽ" "k"
+    sub "ⴿ" "k"
+    sub "ⵀ" "h"
+    sub "ⵃ" "ḥ"
+    sub "ⵄ" "ɛ"
+    sub "ⵅ" "x"
+    sub "ⵇ" "q"
+    sub "ⵉ" "i"
+    sub "ⵊ" "j"
+    sub "ⵍ" "l"
+    sub "ⵎ" "m"
+    sub "ⵏ" "n"
+    sub "ⵓ" "u"
+    sub "ⵔ" "r"
+    sub "ⵕ" "ṛ"
+    sub "ⵖ" "ɣ"
+    sub "ⵙ" "s"
+    sub "ⵚ" "ṣ"
+    sub "ⵛ" "c"
+    sub "ⵜ" "t"
+    sub "ⵝ" "ṯ"
+    sub "ⵞ" "č"
+    sub "ⵟ" "ṭ"
+    sub "ⵠ" "v"
+    sub "ⵡ" "w"
+    sub "ⵢ" "y"
+    sub "ⵣ" "z"
+    sub "ⵥ" "ẓ"
+  }
+
+  parallel {
+    sub "ⵯ" "°"
+  }
+}
+}