interscript-maps 2.5.1 → 3.0.0

data/maps/din-gag-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,78 @@
+system "DIN:gag-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-17
+  language iso-639-3:gag
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 17: Gagausisch (Turkic)"
+  url https://www.beuth.de/de/norm/din-1460-2/134564104
+  creation_date 2011
+  adoption_date
+  description {
+    DIN 1460-2:2011-10, Romanization of Cyrillic alphabets of
+    non-Slavic languages, Tabelle 1, language row 17
+    (Gagausisch). The table assigns each Cyrillic letter of the
+    language's alphabet a Latin letter or letter group; the column
+    order follows DIN 1460:1982 (Slavic). Extracted mechanically from
+    the standard's text layer; the mapping rows below are the table's
+    own cells.
+  }
+
+  notes {
+    note "Extraction provenance: the PDF's text layer carries the full
+    grid; columns were anchored on the per-page position-number row and
+    each cell matched by x-coordinate to its Cyrillic header letter.
+    Position 13's header glyph is PUA (U+E519) in the text layer and
+    was visually identified at 10x as h with comma below (U+0068 + U+0322), the plain-h counterpart of position 12's hooktop-h symbol."
+  }
+}
+
+tests {
+   "a" ->  "a"
+   "ä" ->  "ä"
+   "б" ->  "b"
+   "в" ->  "v"
+}
+
+stage main {
+  parallel {
+    sub "a" "a"
+    sub "ä" "ä"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "ӂ" "ǧ"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "ӧ" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ӱ" "ü"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "щ" "šč"
+    sub "ъ" "\""
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

data/maps/din-gld-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,74 @@
+system "DIN:gld-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-40
+  language iso-639-3:gld
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 40: Nanaisch ((Tg))"
+  url https://www.beuth.de/de/norm/din-1460-2/134564104
+  creation_date 2011
+  adoption_date
+  description {
+    DIN 1460-2:2011-10, Romanization of Cyrillic alphabets of
+    non-Slavic languages, Tabelle 1, language row 40
+    (Nanaisch). The table assigns each Cyrillic letter of the
+    language's alphabet a Latin letter or letter group; the column
+    order follows DIN 1460:1982 (Slavic). Extracted mechanically from
+    the standard's text layer; the mapping rows below are the table's
+    own cells.
+  }
+
+  notes {
+    note "Extraction provenance: the PDF's text layer carries the full
+    grid; columns were anchored on the per-page position-number row and
+    each cell matched by x-coordinate to its Cyrillic header letter.
+    Position 13's header glyph is PUA (U+E519) in the text layer and
+    was visually identified at 10x as h with comma below (U+0068 + U+0322), the plain-h counterpart of position 12's hooktop-h symbol."
+  }
+}
+
+tests {
+   "a" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "g"
+}
+
+stage main {
+  parallel {
+    sub "a" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    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" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "щ" "šč"
+    sub "ъ" "\""
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

data/maps/din-heb-Hebr-Latn-31636-2018.isc

@@ -0,0 +1,355 @@
+system "DIN:heb-Hebr:Latn:31636-2018" {
+
+metadata {
+  authority_id din
+  id 31636-2018
+  language iso-639-2:heb
+  source_script Hebr
+  destination_script Latn
+  name "DIN 31636:2018-10 Information und Dokumentation - Umschrift des hebraeischen Alphabets"
+  url https://www.din.de
+  creation_date 2018
+  confirmation_date 2018-10
+  description {    Information and documentation -- Romanization of the Hebrew alphabet.
+    2018-10 edition, replacing DIN 31636:2011-01. The norm fixes the rendering of the
+    letters of the Hebrew alphabet (including Ivrit) in letters of the Latin alphabet.
+    This map implements the Hebrew (including Ivrit) column over vocalized input;
+    the Yiddish column of the same norm is a separate map.
+  }
+
+  notes {
+    note "Consonants (Table 1): alef is rendered with the right half-ring U+02BE or ignored per the rules; bet with dagesh lene b, bet v; gimel g; dalet d; he always as consonant h; vav v with dot below (U+1E7F), vav with dagesh (shuruk) u; double vav (U+05F0) as consonant v with dot below; zayin z; het h with dot below (U+1E25); tet t with dot below (U+1E6D); yod y as consonant only when a vowel follows, otherwise omitted; kaf with dagesh k, khaf kh, end-khaf kh; lamed l; mem m, end-mem m; nun n, end-nun n; samekh s; ayin left half-ring U+02BF; pe with dagesh p, fe f, end-fe f; tsadi ts, end-tsadi ts; qof k with dot below (k + U+0323); resh r; shin sh, sin s with acute (U+015B); tav t."
+    note "Vowels (Table 3): patach a (with following yod: ai); qamats a or o - this map renders a, the o-reading (qamats qatan) is a reading-side determination; segol e; tsere e; hireq i; holam (U+05B9) or holam male (U+FB4B) o; qubuts (U+05BB) or shuruk (U+FB35) u; sheva e or ignored per the rules; hataf-patach a; hataf-segol e; hataf-qamats o."
+    note "Neo-Hebrew additional letters (Table 2) are marked with the straight apostrophe (geresh, U+02B9): gimel-geresh g-apostrophe, dalet-geresh d-apostrophe, zayin-geresh z-apostrophe, het-geresh h-dot-apostrophe, tet-geresh t-dot-apostrophe, ayin-geresh g with dot above (U+0307), tsadi-geresh ts-apostrophe for English names, or d with dot below for Arabic names (variant; this map renders ts-apostrophe)."
+    note "Special characters (Table 5): right half-ring U+02BE for alef, left half-ring U+02BF for ayin, straight apostrophe U+02B9 for the geresh. Diacritics (Table 6): circumflex U+0302 for the facultative plene marking, acute U+0301 marking the sin, grave U+0300 for the Yiddish tav (Yiddish map), dot below U+0323 for v, h-dot, t-dot, k-dot, dot above U+0307 only for the neo-Hebrew g-dot."
+    note "Rules (section 8): (a) a straight apostrophe separates two letters whose combination would render a different consonant; (b) vowel length is not marked, including the composed forms; (c) alef at the beginning or end of a word and at the end of a syllable is not transliterated; word-internal alef that merely indicates a vowel is likewise ignored, while alef with a vowel sign under it is rendered with U+02BE - this map implements word-initial, word-final, word-internal unvocalized (ignored) and word-internal vocalized (U+02BE) alef; the syllable-end condition is a reading-side determination; (d) bet, kaf and pe follow the modern Hebrew pronunciation with the dagesh lene observed; the distinction between dagesh forte and dagesh lene is not made - residual dagesh signs are deleted; (e) he is always transliterated as a consonant; (f) yod is transliterated as consonant y only when a vowel follows; otherwise it is omitted; (g) the plene spelling of vowels may optionally be shown by a circumflex - this map does not add it; (h) all shevas at the beginning of Hebrew words are rendered e; the sheva word-internally is generally not transliterated - the root-morphology exceptions (doubled third root consonant, yod as second consonant) are reading-side determinations and are not implemented; (i) capitalization follows the rules of the user community; this map outputs lower case and does not apply title case."
+    note "Rules 8(h)(16)-(20) hyphenate preposed particles (ha-arets, mi-bayit, le-David) and 8(j)-(k) govern the punctuation of abbreviations; both require word-segmentation and lexical knowledge and are not implemented in this map."
+    note "The map is deterministic over vocalized input (text carrying niqqud). Unvocalized text is an underspecified skeleton: matres lectionis (vav, yod, he standing for vowels), the qamats qatan reading, the sheva readings and defective spellings are resolved by a vocalization model, after which this map applies (composition, not duplication)."
+  }
+}
+
+tests {
+  # section 8 examples, vocalized
+   "יִשְׂרָאֵל" ->  "yiśraʾel"
+   "קְרִיאָה" ->  "ḳeriʾah"
+   "תְּקוּפָה" ->  "teḳufah"
+   "תְּשׁוּבָה" ->  "teshuvah"
+   "מִשְׁנָה" ->  "mishnah"
+   "רֹאשׁ" ->  "rosh"
+   "אַהֲרֹן" ->  "aharon"
+   "תּוֹרָה" ->  "torah"
+      "שֶׂכֶל" ->  "śekhel"
+      "יִצְחָק" ->  "yitsḥaḳ"
+   "אִגֶּרֶת" ->  "igeret"
+   "חַיֵּי" ->  "ḥaye"
+   "סִפְרֵי" ->  "sifre"
+  # table 1 rows
+   "בּ" ->  "b"
+   "בּ" ->  "b"
+   "ב" ->  "v"
+   "ג" ->  "g"
+   "ד" ->  "d"
+   "ה" ->  "h"
+   "ו" ->  "ṿ"
+   "וּ" ->  "u"
+   "וּ" ->  "u"
+   "װ" ->  "ṿ"
+   "ז" ->  "z"
+   "ח" ->  "ḥ"
+   "ט" ->  "ṭ"
+   "כּ" ->  "k"
+   "כּ" ->  "k"
+   "כ" ->  "kh"
+   "ך" ->  "kh"
+   "ל" ->  "l"
+   "מ" ->  "m"
+   "ם" ->  "m"
+   "נ" ->  "n"
+   "ן" ->  "n"
+   "ס" ->  "s"
+   "ע" ->  "ʿ"
+   "פּ" ->  "p"
+   "פּ" ->  "p"
+   "פ" ->  "f"
+   "ף" ->  "f"
+   "צ" ->  "ts"
+   "ץ" ->  "ts"
+   "ק" ->  "ḳ"
+   "ר" ->  "r"
+   "שׁ" ->  "sh"
+   "שׁ" ->  "sh"
+   "שׂ" ->  "ś"
+   "שׂ" ->  "ś"
+   "ש" ->  "sh"
+   "תּ" ->  "t"
+   "תּ" ->  "t"
+   "ת" ->  "t"
+  # table 2 rows (geresh-marked)
+   "גʹ" ->  "gʹ"
+   "דʹ" ->  "dʹ"
+   "זʹ" ->  "zʹ"
+   "חʹ" ->  "ḥʹ"
+   "טʹ" ->  "ṭʹ"
+   "עʹ" ->  "ġ"
+   "צʹ" ->  "tsʹ"
+  # table 3 rows
+   "בַּ" ->  "ba"
+   "בָּ" ->  "ba"
+   "בֶּ" ->  "be"
+   "בֵּ" ->  "be"
+   "בִּ" ->  "bi"
+   "בֹּ" ->  "bo"
+   "וֹ" ->  "o"
+   "בֻּ" ->  "bu"
+   "בַּי" ->  "ba"
+   "בֲּ" ->  "ba"
+   "בֱּ" ->  "be"
+   "בֳּ" ->  "bo"
+}
+
+stage main {
+
+  # RULES
+  # Unicode mark-order normalization: move dagesh and the shin/sin dots
+  # directly after their base letter when a vowel mark intervenes
+  sub {
+    from "ֲּ"
+    to "ֲּ"
+  }
+  sub {
+    from "ֲׂ"
+    to "ֲׂ"
+  }
+  sub {
+    from "ֲׁ"
+    to "ֲׁ"
+  }
+  sub {
+    from "ֱּ"
+    to "ֱּ"
+  }
+  sub {
+    from "ֱׂ"
+    to "ֱׂ"
+  }
+  sub {
+    from "ֱׁ"
+    to "ֱׁ"
+  }
+  sub {
+    from "ֳּ"
+    to "ֳּ"
+  }
+  sub {
+    from "ֳׂ"
+    to "ֳׂ"
+  }
+  sub {
+    from "ֳׁ"
+    to "ֳׁ"
+  }
+  sub {
+    from "ַּ"
+    to "ַּ"
+  }
+  sub {
+    from "ַׂ"
+    to "ַׂ"
+  }
+  sub {
+    from "ַׁ"
+    to "ַׁ"
+  }
+  sub {
+    from "ָּ"
+    to "ָּ"
+  }
+  sub {
+    from "ָׂ"
+    to "ָׂ"
+  }
+  sub {
+    from "ָׁ"
+    to "ָׁ"
+  }
+  sub {
+    from "ֶּ"
+    to "ֶּ"
+  }
+  sub {
+    from "ֶׂ"
+    to "ֶׂ"
+  }
+  sub {
+    from "ֶׁ"
+    to "ֶׁ"
+  }
+  sub {
+    from "ֵּ"
+    to "ֵּ"
+  }
+  sub {
+    from "ֵׂ"
+    to "ֵׂ"
+  }
+  sub {
+    from "ֵׁ"
+    to "ֵׁ"
+  }
+  sub {
+    from "ִּ"
+    to "ִּ"
+  }
+  sub {
+    from "ִׂ"
+    to "ִׂ"
+  }
+  sub {
+    from "ִׁ"
+    to "ִׁ"
+  }
+  sub {
+    from "ֹּ"
+    to "ֹּ"
+  }
+  sub {
+    from "ֹׂ"
+    to "ֹׂ"
+  }
+  sub {
+    from "ֹׁ"
+    to "ֹׁ"
+  }
+  sub {
+    from "ֻּ"
+    to "ֻּ"
+  }
+  sub {
+    from "ֻׂ"
+    to "ֻׂ"
+  }
+  sub {
+    from "ֻׁ"
+    to "ֻׁ"
+  }
+  # 8(c): alef word-initially and word-finally is not transliterated
+  sub {
+    from boundary + "א"
+    to ""
+  }
+  sub {
+    from "א"
+    to ""
+    after boundary
+  }
+  # 8(c): word-internal alef with a vowel sign under it is rendered U+02BE
+  sub {
+    from "א"
+    to "ʾ"
+    after any("ְֱֲֳִֵֶַָֹֻ")
+  }
+  # remaining word-internal alefs merely indicate a vowel and are ignored
+  sub {
+    from "א"
+    to ""
+  }
+
+  # 8(h): sheva word-initially (under the word-initial consonant) is e,
+  # word-internally it is not transliterated
+  sub {
+    from "ְ"
+    to "e"
+    before boundary + any("אבגדהוזחטיכלמנסעפצקרשת")
+  }
+  sub {
+    from "ְ"
+    to ""
+  }
+
+  # sin and shin dots (the sheva between them is removed first)
+  sub {
+    from "שׂ"
+    to "ś"
+  }
+  sub {
+    from "שׁ"
+    to "sh"
+  }
+
+  # 8(f): yod as consonant y only when a vowel follows; otherwise omitted
+  sub {
+    from "י"
+    to "y"
+    after any("ִֵֶַָֹֻּ")
+  }
+  sub {
+    from "י"
+    to ""
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "גʹ" "gʹ"
+    sub "דʹ" "dʹ"
+    sub "זʹ" "zʹ"
+    sub "חʹ" "ḥʹ"
+    sub "טʹ" "ṭʹ"
+    sub "עʹ" "ġ"
+    sub "צʹ" "tsʹ"
+    sub "שׂ" "ś"
+    sub "שׁ" "sh"
+    sub "בּ" "b"
+    sub "כּ" "k"
+    sub "פּ" "p"
+    sub "וּ" "u"
+    sub "וֹ" "o"
+    sub "בּ" "b"
+    sub "כּ" "k"
+    sub "פּ" "p"
+    sub "וּ" "u"
+    sub "וֹ" "o"
+    sub "שׁ" "sh"
+    sub "שׂ" "ś"
+    sub "תּ" "t"
+    sub "װ" "ṿ"
+    sub "ך" "kh"
+    sub "כ" "kh"
+    sub "ם" "m"
+    sub "מ" "m"
+    sub "ן" "n"
+    sub "נ" "n"
+    sub "ף" "f"
+    sub "פ" "f"
+    sub "ץ" "ts"
+    sub "צ" "ts"
+    sub "ב" "v"
+    sub "ג" "g"
+    sub "ד" "d"
+    sub "ה" "h"
+    sub "ו" "ṿ"
+    sub "ז" "z"
+    sub "ח" "ḥ"
+    sub "ט" "ṭ"
+    sub "ל" "l"
+    sub "ס" "s"
+    sub "ע" "ʿ"
+    sub "ק" "ḳ"
+    sub "ר" "r"
+    sub "ש" "sh"
+    sub "ת" "t"
+    sub "ַ" "a"
+    sub "ָ" "a"
+    sub "ֶ" "e"
+    sub "ֵ" "e"
+    sub "ִ" "i"
+    sub "ֹ" "o"
+    sub "ֻ" "u"
+    sub "ֲ" "a"
+    sub "ֱ" "e"
+    sub "ֳ" "o"
+    sub "ּ" ""
+  }
+
+}
+
+}

data/maps/din-hye-Armn-Latn-32706-2010.isc

@@ -0,0 +1,197 @@
+system "DIN:arm-Armn:Latn:32706-2010" {
+
+metadata {
+  authority_id din
+  id 32706-2010
+  language iso-639-2:hye
+  source_script Armn
+  destination_script Latn
+  name "DIN 32706:2010-01 Information und Dokumentation - Umschrift des armenischen Alphabets"
+  url https://www.din.de
+  creation_date 2010
+  confirmation_date 2010
+  description {    Information and documentation -- Romanization of the Armenian alphabet.
+    The norm fixes the rendering of the letters of the Armenian alphabet in letters of the
+    Latin alphabet and is suitable for all fields of application. It follows the principle
+    of transliteration and is based on library practice and on ISO 9985:1996.
+  }
+
+  notes {
+    note "Table 1 renders each letter with its majuscule, minuscule, numeric value (the letters of the Armenian alphabet formerly also served as numerals) and Romanization: a=1, b=2, g=3, d=4, e=5, z=6, ê=7, ẹ=8, t̕=9, ž=10, i=20, l=30, x=40, c=50, k=60, h=70, j=80, ġ=90, č=100, m=200, y=300, n=400, š=500, o=600, č̕=700, p=800, ǰ=900, ṙ=1000, s=2000, v=3000, t=4000, r=5000, c̕=6000, w=7000, p̕=8000, k̕=9000, ô=10000, f=20000."
+    note "The ejective consonants are romanized with the combining comma above right (U+0315): t̕ (0074+0315), č̕ (010D+0315), c̕ (0063+0315), p̕ (0070+0315), k̕ (006B+0315)."
+    note "The letter ǰ is the precomposed U+01F0; its capital cannot currently be represented as a single Unicode character and is post-combined as 004A+030C (footnote a of the source)."
+    note "The ligature և (U+0587) is romanized ew with the combining double inverted breve (0065+0077+0361). The source notes the alternative representation 0065+FE20+0077+FE21 and that the ligature bow may likewise be set for the Armenian ligatures at U+FB13 to U+FB17; this map does not assign those ligatures Romanizations, as the table does not specify any."
+    note "The source document's Unicode annotation column prints the minuscule of letter 18 as 0571; the glyph shown and encoded is ղ U+0572 (0571 is the minuscule of letter 17, ձ)."
+    note "Normative references: DIN 1460; ISO 9985:1996; ISO/IEC 10646:2003."
+  }
+}
+
+tests {
+  # every table row, majuscule and minuscule
+   "Ա" ->  "A"
+   "ա" ->  "a"
+   "Բ" ->  "B"
+   "բ" ->  "b"
+   "Գ" ->  "G"
+   "գ" ->  "g"
+   "Դ" ->  "D"
+   "դ" ->  "d"
+   "Ե" ->  "E"
+   "ե" ->  "e"
+   "Զ" ->  "Z"
+   "զ" ->  "z"
+   "Է" ->  "Ê"
+   "է" ->  "ê"
+   "Ը" ->  "Ẹ"
+   "ը" ->  "ẹ"
+   "Թ" ->  "T̕"
+   "թ" ->  "t̕"
+   "Ժ" ->  "Ž"
+   "ժ" ->  "ž"
+   "Ի" ->  "I"
+   "ի" ->  "i"
+   "Լ" ->  "L"
+   "լ" ->  "l"
+   "Խ" ->  "X"
+   "խ" ->  "x"
+   "Ծ" ->  "C"
+   "ծ" ->  "c"
+   "Կ" ->  "K"
+   "կ" ->  "k"
+   "Հ" ->  "H"
+   "հ" ->  "h"
+   "Ձ" ->  "J"
+   "ձ" ->  "j"
+   "Ղ" ->  "Ġ"
+   "ղ" ->  "ġ"
+   "Ճ" ->  "Č"
+   "ճ" ->  "č"
+   "Մ" ->  "M"
+   "մ" ->  "m"
+   "Յ" ->  "Y"
+   "յ" ->  "y"
+   "Ն" ->  "N"
+   "ն" ->  "n"
+   "Շ" ->  "Š"
+   "շ" ->  "š"
+   "Ո" ->  "O"
+   "ո" ->  "o"
+   "Չ" ->  "Č̕"
+   "չ" ->  "č̕"
+   "Պ" ->  "P"
+   "պ" ->  "p"
+   "Ջ" ->  "J̌"
+   "ջ" ->  "ǰ"
+   "Ռ" ->  "Ṙ"
+   "ռ" ->  "ṙ"
+   "Ս" ->  "S"
+   "ս" ->  "s"
+   "Վ" ->  "V"
+   "վ" ->  "v"
+   "Տ" ->  "T"
+   "տ" ->  "t"
+   "Ր" ->  "R"
+   "ր" ->  "r"
+   "Ց" ->  "C̕"
+   "ց" ->  "c̕"
+   "Ւ" ->  "W"
+   "ւ" ->  "w"
+   "Փ" ->  "P̕"
+   "փ" ->  "p̕"
+   "Ք" ->  "K̕"
+   "ք" ->  "k̕"
+   "և" ->  "ew͡"
+   "Օ" ->  "Ô"
+   "օ" ->  "ô"
+   "Ֆ" ->  "F"
+   "ֆ" ->  "f"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "Թ" "T̕"
+    sub "Չ" "Č̕"
+    sub "Ց" "C̕"
+    sub "Փ" "P̕"
+    sub "Ք" "K̕"
+    sub "և" "ew͡"
+    sub "Է" "Ê"
+    sub "Ը" "Ẹ"
+    sub "Ժ" "Ž"
+    sub "Ղ" "Ġ"
+    sub "Ճ" "Č"
+    sub "Շ" "Š"
+    sub "Ջ" "J̌"
+    sub "Ռ" "Ṙ"
+    sub "Օ" "Ô"
+    sub "Ա" "A"
+    sub "Բ" "B"
+    sub "Գ" "G"
+    sub "Դ" "D"
+    sub "Ե" "E"
+    sub "Զ" "Z"
+    sub "Ի" "I"
+    sub "Լ" "L"
+    sub "Խ" "X"
+    sub "Ծ" "C"
+    sub "Կ" "K"
+    sub "Հ" "H"
+    sub "Ձ" "J"
+    sub "Մ" "M"
+    sub "Յ" "Y"
+    sub "Ն" "N"
+    sub "Ո" "O"
+    sub "Պ" "P"
+    sub "Ս" "S"
+    sub "Վ" "V"
+    sub "Տ" "T"
+    sub "Ր" "R"
+    sub "Ւ" "W"
+    sub "Ֆ" "F"
+
+    sub "թ" "t̕"
+    sub "չ" "č̕"
+    sub "ց" "c̕"
+    sub "փ" "p̕"
+    sub "ք" "k̕"
+    sub "և" "ew͡"
+    sub "է" "ê"
+    sub "ը" "ẹ"
+    sub "ժ" "ž"
+    sub "ղ" "ġ"
+    sub "ճ" "č"
+    sub "շ" "š"
+    sub "ջ" "ǰ"
+    sub "ռ" "ṙ"
+    sub "օ" "ô"
+    sub "ա" "a"
+    sub "բ" "b"
+    sub "գ" "g"
+    sub "դ" "d"
+    sub "ե" "e"
+    sub "զ" "z"
+    sub "ի" "i"
+    sub "լ" "l"
+    sub "խ" "x"
+    sub "ծ" "c"
+    sub "կ" "k"
+    sub "հ" "h"
+    sub "ձ" "j"
+    sub "մ" "m"
+    sub "յ" "y"
+    sub "ն" "n"
+    sub "ո" "o"
+    sub "պ" "p"
+    sub "ս" "s"
+    sub "վ" "v"
+    sub "տ" "t"
+    sub "ր" "r"
+    sub "ւ" "w"
+    sub "ֆ" "f"
+  }
+
+}
+
+}