interscript-maps 3.0.0 → 3.1.0

data/maps/alalc-uig-Arab-Latn-2015.isc

@@ -0,0 +1,147 @@
+system "ALA-LC:uig-Arab:Latn:2015" {
+
+metadata {
+  authority_id alalc
+  id 2015
+  language iso-639-2:uig
+  source_script Arab
+  destination_script Latn
+  name "Romanization Table -- Uighur (2015)"
+  url http://catdir.loc.gov/catdir/cpso/romanization/uighur.pdf
+  creation_date 2015
+  confirmation_date 2015
+  description {    ALA-LC Romanization table for Uighur, 2015 version (earlier versions: 2011, 1997)
+  }
+
+  notes {
+    note "Letters of the Alphabet: alif ا, word-initial ئا a; he ه, word-initial ئه ă; ب b; پ p; ت t; ج j; چ ch; خ kh; د d; ر r; ز z; ژ zh; س s; ش sh; غ gh; ف f; ق q; ك k; گ g; ڭ ng; ل l; م m; ن n; teh marbuta ة h; و, word-initial ئو o; ۇ, word-initial ئۇ u; ۆ, word-initial ئۆ ö; ۈ, word-initial ئۈ ü; ۋ v; ې, word-initial ئې e; ی ى, word-initial ئ i; ي y. Each vowel letter is unambiguous; the dotted yad ي is the consonant y and the undotted ی/ى are the vowel i."
+
+    note "Rule 1. Use the single prime (ʹ) to separate two letters representing two distinct consonantal sounds when the combination might be read as a digraph: uzʹhal ئۇزهال. The prime placement is syntactic and is not implemented."
+
+    note "Rule 2. Romanize foreign words that occur in a Uighur context and are written in Uighur letters according to these rules for romanizing Uighur: Vena (not Vienna) ۋېنا, jughrapi (not geography) جۇغراپى, stăyn (not stein) ستهین."
+
+    note "Rule 3. When hamzah is initial it is not represented in romanization; when medial it is romanized ʼ (alif): ayroport ئايروپورت [initial], qarghaʼi قارغائی [medial]. This map renders word-initial ئ as empty and other ئ as ʼ; the hamzah-carrier readings of the word-initial vowel spellings (ئا ئه ئو ئۇ ئۆ ئۈ ئې ئ) fall out of the initial rule."
+
+    note "Rule 4. Follow the rules for the capitalization of English. This map leaves case untouched; the proper-noun capital of the Vena example is lexical."
+
+    note "NOTE: The following examples from the old Uighur romanization table are romanized differently in the new table: ay ئاي, bilishinggă بىلىشىڭگه, jănggă جەڭگه, shojanggă شوجاڭگه, bayiliq بايىلىق, băytulla بهيتۇللا, păyishănbă پەيىشەنبه, dăyfu دهیفو. The values shown are the new-table readings and are encoded."
+
+    note "The he ه is listed both in the ă row and (with teh marbuta ة) in the h row. This map defaults ه to ă (the schwa reading exercised by the note examples) and ة to h; the h reading of ه (as in uzʹhal) is lexical, like the vowel points of the Kazakh he."
+
+    note "The source document's text layer renders the letters in Unicode presentation forms (joining shapes); these carry no letter-identity information in Uighur and are normalized to base codepoints before this map applies."
+  }
+}
+
+tests {
+  # Letters of the Alphabet
+   "ا" ->  "a"
+   "ئا" ->  "a"
+   "ه" ->  "ă"
+   "ئه" ->  "ă"
+   "ب" ->  "b"
+   "پ" ->  "p"
+   "ت" ->  "t"
+   "ج" ->  "j"
+   "چ" ->  "ch"
+   "خ" ->  "kh"
+   "د" ->  "d"
+   "ر" ->  "r"
+   "ز" ->  "z"
+   "ژ" ->  "zh"
+   "س" ->  "s"
+   "ش" ->  "sh"
+   "غ" ->  "gh"
+   "ف" ->  "f"
+   "ق" ->  "q"
+   "ك" ->  "k"
+   "گ" ->  "g"
+   "ڭ" ->  "ng"
+   "ل" ->  "l"
+   "م" ->  "m"
+   "ن" ->  "n"
+   "ة" ->  "h"
+   "و" ->  "o"
+   "ئو" ->  "o"
+   "ۇ" ->  "u"
+   "ئۇ" ->  "u"
+   "ۆ" ->  "ö"
+   "ئۆ" ->  "ö"
+   "ۈ" ->  "ü"
+   "ئۈ" ->  "ü"
+   "ۋ" ->  "v"
+   "ې" ->  "e"
+   "ئې" ->  "e"
+   "ی" ->  "i"
+   "ى" ->  "i"
+   "ئ" ->  ""  # rule 3: initial hamzah not represented
+   "ي" ->  "y"
+  # Rule 1 (the prime is syntactic; the h reading of he is lexical)
+  # - source: ئۇزهال, expected: uzʹhal (mechanical: uzăal)
+  # Rule 2 examples
+   "جۇغراپى" ->  "jughrapi"
+   "ستهين" ->  "stăyn"
+  # - source: ۋېنا, expected: Vena (proper-noun capital)
+  # Rule 3 examples
+   "ئايروپورت" ->  "ayroport"
+   "قارغائی" ->  "qarghaʼi"
+  # NOTE examples (old-table words, new-table readings)
+   "ئاي" ->  "ay"
+   "بىلىشىڭگه" ->  "bilishinggă"
+   "جهڭگه" ->  "jănggă"
+   "شوجاڭگه" ->  "shojanggă"
+   "بايىلىق" ->  "bayiliq"
+   "بهيتۇللا" ->  "băytulla"
+   "پهيىشهنبه" ->  "păyishănbă"
+  # - source: دهيفو (text-layer final glyph و), expected: dăyfu (the romanization
+  #   requires final ۇ; the source glyph is ambiguous و/ۇ)
+}
+
+stage main {
+  parallel {
+    # Rule 3 - hamzah: word-initial carrier not represented, medial ʼ
+    sub {
+    from boundary + "ئ"
+    to ""
+  }
+    sub "ئ" "ʼ"
+
+    # Letters of the Alphabet
+    sub "ه" "ă"
+    sub "ة" "h"
+    sub "ا" "a"
+    sub "ب" "b"
+    sub "پ" "p"
+    sub "ت" "t"
+    sub "ج" "j"
+    sub "چ" "ch"
+    sub "خ" "kh"
+    sub "د" "d"
+    sub "ر" "r"
+    sub "ز" "z"
+    sub "ژ" "zh"
+    sub "س" "s"
+    sub "ش" "sh"
+    sub "غ" "gh"
+    sub "ف" "f"
+    sub "ق" "q"
+    sub "ك" "k"
+    sub "گ" "g"
+    sub "ڭ" "ng"
+    sub "ل" "l"
+    sub "م" "m"
+    sub "ن" "n"
+    sub "و" "o"
+    sub "ۇ" "u"
+    sub "ۆ" "ö"
+    sub "ۈ" "ü"
+    sub "ۋ" "v"
+    sub "ې" "e"
+    sub "ی" "i"
+    sub "ى" "i"
+    sub "ي" "y"
+    sub "ـ" ""
+  }
+
+}
+
+}

data/maps/alalc-und-Dsrt-Latn-2016.isc

@@ -0,0 +1,203 @@
+system "ALA-LC:und-Dsrt:Latn:2016" {
+
+metadata {
+  authority_id alalc
+  id 2016
+  language iso-639-2:und
+  source_script Dsrt
+  destination_script Latn
+  name "Deseret Romanization Table (2016)"
+  url https://www.loc.gov/catdir/cpso/romanization/deseret.pdf
+  creation_date 2016
+  adoption_date
+  description {    ALA-LC Deseret Romanization Table, 2016 version (no earlier
+    versions). The table is scoped to the Deseret script (the Deseret
+    alphabet), not to any one language, so the language field carries
+    the undetermined code; the alphabet was devised in the 1850s for
+    English. Forty letters (six vowels and thirty-four consonants and
+    vowel-length and diphthong forms), each mapping one-to-one; the
+    letter values follow the printed table. The source document's
+    text layer doubles every letter glyph in the vernacular column; a
+    visual check of the rendered pages confirms a single letter per
+    row, and the codepoints below are the Unicode Deseret block values
+    corresponding to the table's letter order.
+  }
+
+  notes {
+    note "Vowel-length letters: Ē (𐐀/𐐨), Ī (𐐌/𐐴), Ō (𐐄/𐐬), Ū (𐐅/𐐭),
+    Ā (𐐁/𐐩) are the long-vowel letters; Ä (𐐂/𐐪), Ô (𐐉/𐐱), Ü (𐐋/𐐳)
+    the broad-vowel letters. The digraph values Dh Zh Th Sh Ch and the
+    diphthong values Aw Oy and the letter Yū (𐐧/𐑏) are single letters
+    in the script."
+  }
+}
+
+tests {
+  "𐐀" -> "Ē"
+  "𐐨" -> "ē"
+  "𐐄" -> "Ō"
+  "𐐬" -> "ō"
+  "𐐈" -> "A"
+  "𐐰" -> "a"
+  "𐐌" -> "Ī"
+  "𐐴" -> "ī"
+  "𐐐" -> "H"
+  "𐐸" -> "h"
+  "𐐔" -> "D"
+  "𐐼" -> "d"
+  "𐐘" -> "G"
+  "𐑀" -> "g"
+  "𐐜" -> "Dh"
+  "𐑄" -> "dh"
+  "𐐠" -> "Zh"
+  "𐑈" -> "zh"
+  "𐐤" -> "N"
+  "𐑌" -> "n"
+  "𐐁" -> "Ā"
+  "𐐩" -> "ā"
+  "𐐅" -> "Ū"
+  "𐐭" -> "ū"
+  "𐐉" -> "Ô"
+  "𐐱" -> "ô"
+  "𐐍" -> "Aw"
+  "𐐵" -> "aw"
+  "𐐑" -> "P"
+  "𐐹" -> "p"
+  "𐐕" -> "Ch"
+  "𐐽" -> "ch"
+  "𐐙" -> "F"
+  "𐑁" -> "f"
+  "𐐝" -> "S"
+  "𐑅" -> "s"
+  "𐐡" -> "R"
+  "𐑉" -> "r"
+  "𐐥" -> "Ng"
+  "𐑍" -> "ng"
+  "𐐂" -> "Ä"
+  "𐐪" -> "ä"
+  "𐐆" -> "I"
+  "𐐮" -> "i"
+  "𐐊" -> "U"
+  "𐐲" -> "u"
+  "𐐎" -> "W"
+  "𐐶" -> "w"
+  "𐐒" -> "B"
+  "𐐺" -> "b"
+  "𐐖" -> "J"
+  "𐐾" -> "j"
+  "𐐚" -> "V"
+  "𐑂" -> "v"
+  "𐐞" -> "Z"
+  "𐑆" -> "z"
+  "𐐢" -> "L"
+  "𐑊" -> "l"
+  "𐐦" -> "Oy"
+  "𐑎" -> "oy"
+  "𐐃" -> "O"
+  "𐐫" -> "o"
+  "𐐇" -> "E"
+  "𐐯" -> "e"
+  "𐐋" -> "Ü"
+  "𐐳" -> "ü"
+  "𐐏" -> "Y"
+  "𐐷" -> "y"
+  "𐐓" -> "T"
+  "𐐻" -> "t"
+  "𐐗" -> "K"
+  "𐐿" -> "k"
+  "𐐛" -> "Th"
+  "𐑃" -> "th"
+  "𐐟" -> "Sh"
+  "𐑇" -> "sh"
+  "𐐣" -> "M"
+  "𐑋" -> "m"
+  "𐐧" -> "Yū"
+  "𐑏" -> "yū"
+  "𐐒𐐮𐐺" -> "Bib"
+}
+
+stage main {
+  parallel {
+    sub "𐐀" "Ē"
+    sub "𐐨" "ē"
+    sub "𐐄" "Ō"
+    sub "𐐬" "ō"
+    sub "𐐈" "A"
+    sub "𐐰" "a"
+    sub "𐐌" "Ī"
+    sub "𐐴" "ī"
+    sub "𐐐" "H"
+    sub "𐐸" "h"
+    sub "𐐔" "D"
+    sub "𐐼" "d"
+    sub "𐐘" "G"
+    sub "𐑀" "g"
+    sub "𐐜" "Dh"
+    sub "𐑄" "dh"
+    sub "𐐠" "Zh"
+    sub "𐑈" "zh"
+    sub "𐐤" "N"
+    sub "𐑌" "n"
+    sub "𐐁" "Ā"
+    sub "𐐩" "ā"
+    sub "𐐅" "Ū"
+    sub "𐐭" "ū"
+    sub "𐐉" "Ô"
+    sub "𐐱" "ô"
+    sub "𐐍" "Aw"
+    sub "𐐵" "aw"
+    sub "𐐑" "P"
+    sub "𐐹" "p"
+    sub "𐐕" "Ch"
+    sub "𐐽" "ch"
+    sub "𐐙" "F"
+    sub "𐑁" "f"
+    sub "𐐝" "S"
+    sub "𐑅" "s"
+    sub "𐐡" "R"
+    sub "𐑉" "r"
+    sub "𐐥" "Ng"
+    sub "𐑍" "ng"
+    sub "𐐂" "Ä"
+    sub "𐐪" "ä"
+    sub "𐐆" "I"
+    sub "𐐮" "i"
+    sub "𐐊" "U"
+    sub "𐐲" "u"
+    sub "𐐎" "W"
+    sub "𐐶" "w"
+    sub "𐐒" "B"
+    sub "𐐺" "b"
+    sub "𐐖" "J"
+    sub "𐐾" "j"
+    sub "𐐚" "V"
+    sub "𐑂" "v"
+    sub "𐐞" "Z"
+    sub "𐑆" "z"
+    sub "𐐢" "L"
+    sub "𐑊" "l"
+    sub "𐐦" "Oy"
+    sub "𐑎" "oy"
+    sub "𐐃" "O"
+    sub "𐐫" "o"
+    sub "𐐇" "E"
+    sub "𐐯" "e"
+    sub "𐐋" "Ü"
+    sub "𐐳" "ü"
+    sub "𐐏" "Y"
+    sub "𐐷" "y"
+    sub "𐐓" "T"
+    sub "𐐻" "t"
+    sub "𐐗" "K"
+    sub "𐐿" "k"
+    sub "𐐛" "Th"
+    sub "𐑃" "th"
+    sub "𐐟" "Sh"
+    sub "𐑇" "sh"
+    sub "𐐣" "M"
+    sub "𐑋" "m"
+    sub "𐐧" "Yū"
+    sub "𐑏" "yū"
+  }
+}
+}