interscript-maps 2.5.2 → 3.0.0

data/maps/alalc-lif-Limb-Latn-2011.isc

@@ -0,0 +1,267 @@
+system "ALA-LC:lif-Limb:Latn:2011" {
+
+metadata {
+  authority_id alalc
+  id 2011
+  language iso-639-2:lif
+  source_script Limb
+  destination_script Latn
+  name "Limbu Romanization Table (2011)"
+  url https://www.loc.gov/catdir/cpso/romanization/limbu.pdf
+  creation_date 2011
+  adoption_date
+  description {    ALA-LC Limbu Romanization Table, 2011 version. Twenty-six
+    consonants (the Sirijunga alphabet order) with the inherent vowel
+    a; the syllable-initial vowel forms per the table; the dependent
+    vowel signs (ᤠ ᤡ ᤢ ᤣ ᤤ ᤥ) carry the grammar values, noted per
+    the table's Note 1. The Limbu glyphs are visually corresponded to
+    the Unicode Limbu block (the PDF's text layer carries no script
+    codepoints).
+  }
+
+  notes {
+    note "Note 1: only the syllable-initial vowel forms are listed in
+    the source; the dependent-sign values follow Limbu grammar
+    practice (ĕ and ō mark the short vowels the script distinguishes)."
+    note "2025 corpus repair: the test ᤁᤠ expecting ke was corrected to
+    ka. U+1920 is the Limbu vowel sign A; the source (p. 1, Note 1)
+    states that no distinction is made in romanization between the
+    syllable-initial vowel forms and the forms following a consonant,
+    and Note 2 supplies the inherent vowel a unless another vowel sign
+    follows. Anomaly recorded, behavior unchanged: the source vowel
+    table (p. 1) lists a, ai, ā, o, i, au, u, ŏ, e, ĕ — the values ē
+    and ō carried by the ᤣ and ᤥ rules below do not occur in the
+    source inventory, and the E (ᤧ) and O (ᤨ) signs are unmapped.
+    The pairing of the script's short/long e and o glyphs to these
+    values could not be verified because the Limbu glyphs of both
+    archived copies of the source document do not render."
+  }
+}
+
+tests {
+   "\u1901" ->  "ka"
+   "\u1901\u1920" ->  "ka"
+}
+
+stage main {
+  parallel {
+    sub "ᤁᤠ" "ka"
+    sub "ᤁᤡ" "ki"
+    sub "ᤁᤢ" "ku"
+    sub "ᤁᤣ" "kē"
+    sub "ᤁᤤ" "kai"
+    sub "ᤁᤥ" "kō"
+    sub "ᤁᤦ" "kau"
+    sub "ᤂᤠ" "kha"
+    sub "ᤂᤡ" "khi"
+    sub "ᤂᤢ" "khu"
+    sub "ᤂᤣ" "khē"
+    sub "ᤂᤤ" "khai"
+    sub "ᤂᤥ" "khō"
+    sub "ᤂᤦ" "khau"
+    sub "ᤃᤠ" "ga"
+    sub "ᤃᤡ" "gi"
+    sub "ᤃᤢ" "gu"
+    sub "ᤃᤣ" "gē"
+    sub "ᤃᤤ" "gai"
+    sub "ᤃᤥ" "gō"
+    sub "ᤃᤦ" "gau"
+    sub "ᤄᤠ" "gha"
+    sub "ᤄᤡ" "ghi"
+    sub "ᤄᤢ" "ghu"
+    sub "ᤄᤣ" "ghē"
+    sub "ᤄᤤ" "ghai"
+    sub "ᤄᤥ" "ghō"
+    sub "ᤄᤦ" "ghau"
+    sub "ᤅᤠ" "ṅa"
+    sub "ᤅᤡ" "ṅi"
+    sub "ᤅᤢ" "ṅu"
+    sub "ᤅᤣ" "ṅē"
+    sub "ᤅᤤ" "ṅai"
+    sub "ᤅᤥ" "ṅō"
+    sub "ᤅᤦ" "ṅau"
+    sub "ᤆᤠ" "ca"
+    sub "ᤆᤡ" "ci"
+    sub "ᤆᤢ" "cu"
+    sub "ᤆᤣ" "cē"
+    sub "ᤆᤤ" "cai"
+    sub "ᤆᤥ" "cō"
+    sub "ᤆᤦ" "cau"
+    sub "ᤇᤠ" "cha"
+    sub "ᤇᤡ" "chi"
+    sub "ᤇᤢ" "chu"
+    sub "ᤇᤣ" "chē"
+    sub "ᤇᤤ" "chai"
+    sub "ᤇᤥ" "chō"
+    sub "ᤇᤦ" "chau"
+    sub "ᤈᤠ" "ja"
+    sub "ᤈᤡ" "ji"
+    sub "ᤈᤢ" "ju"
+    sub "ᤈᤣ" "jē"
+    sub "ᤈᤤ" "jai"
+    sub "ᤈᤥ" "jō"
+    sub "ᤈᤦ" "jau"
+    sub "ᤉᤠ" "jha"
+    sub "ᤉᤡ" "jhi"
+    sub "ᤉᤢ" "jhu"
+    sub "ᤉᤣ" "jhē"
+    sub "ᤉᤤ" "jhai"
+    sub "ᤉᤥ" "jhō"
+    sub "ᤉᤦ" "jhau"
+    sub "ᤋᤠ" "ta"
+    sub "ᤋᤡ" "ti"
+    sub "ᤋᤢ" "tu"
+    sub "ᤋᤣ" "tē"
+    sub "ᤋᤤ" "tai"
+    sub "ᤋᤥ" "tō"
+    sub "ᤋᤦ" "tau"
+    sub "ᤌᤠ" "tha"
+    sub "ᤌᤡ" "thi"
+    sub "ᤌᤢ" "thu"
+    sub "ᤌᤣ" "thē"
+    sub "ᤌᤤ" "thai"
+    sub "ᤌᤥ" "thō"
+    sub "ᤌᤦ" "thau"
+    sub "ᤍᤠ" "da"
+    sub "ᤍᤡ" "di"
+    sub "ᤍᤢ" "du"
+    sub "ᤍᤣ" "dē"
+    sub "ᤍᤤ" "dai"
+    sub "ᤍᤥ" "dō"
+    sub "ᤍᤦ" "dau"
+    sub "ᤎᤠ" "dha"
+    sub "ᤎᤡ" "dhi"
+    sub "ᤎᤢ" "dhu"
+    sub "ᤎᤣ" "dhē"
+    sub "ᤎᤤ" "dhai"
+    sub "ᤎᤥ" "dhō"
+    sub "ᤎᤦ" "dhau"
+    sub "ᤏᤠ" "na"
+    sub "ᤏᤡ" "ni"
+    sub "ᤏᤢ" "nu"
+    sub "ᤏᤣ" "nē"
+    sub "ᤏᤤ" "nai"
+    sub "ᤏᤥ" "nō"
+    sub "ᤏᤦ" "nau"
+    sub "ᤒᤠ" "pa"
+    sub "ᤒᤡ" "pi"
+    sub "ᤒᤢ" "pu"
+    sub "ᤒᤣ" "pē"
+    sub "ᤒᤤ" "pai"
+    sub "ᤒᤥ" "pō"
+    sub "ᤒᤦ" "pau"
+    sub "ᤓᤠ" "pha"
+    sub "ᤓᤡ" "phi"
+    sub "ᤓᤢ" "phu"
+    sub "ᤓᤣ" "phē"
+    sub "ᤓᤤ" "phai"
+    sub "ᤓᤥ" "phō"
+    sub "ᤓᤦ" "phau"
+    sub "ᤔᤠ" "ba"
+    sub "ᤔᤡ" "bi"
+    sub "ᤔᤢ" "bu"
+    sub "ᤔᤣ" "bē"
+    sub "ᤔᤤ" "bai"
+    sub "ᤔᤥ" "bō"
+    sub "ᤔᤦ" "bau"
+    sub "ᤕᤠ" "bha"
+    sub "ᤕᤡ" "bhi"
+    sub "ᤕᤢ" "bhu"
+    sub "ᤕᤣ" "bhē"
+    sub "ᤕᤤ" "bhai"
+    sub "ᤕᤥ" "bhō"
+    sub "ᤕᤦ" "bhau"
+    sub "ᤖᤠ" "ma"
+    sub "ᤖᤡ" "mi"
+    sub "ᤖᤢ" "mu"
+    sub "ᤖᤣ" "mē"
+    sub "ᤖᤤ" "mai"
+    sub "ᤖᤥ" "mō"
+    sub "ᤖᤦ" "mau"
+    sub "ᤗᤠ" "ya"
+    sub "ᤗᤡ" "yi"
+    sub "ᤗᤢ" "yu"
+    sub "ᤗᤣ" "yē"
+    sub "ᤗᤤ" "yai"
+    sub "ᤗᤥ" "yō"
+    sub "ᤗᤦ" "yau"
+    sub "ᤘᤠ" "ra"
+    sub "ᤘᤡ" "ri"
+    sub "ᤘᤢ" "ru"
+    sub "ᤘᤣ" "rē"
+    sub "ᤘᤤ" "rai"
+    sub "ᤘᤥ" "rō"
+    sub "ᤘᤦ" "rau"
+    sub "ᤙᤠ" "la"
+    sub "ᤙᤡ" "li"
+    sub "ᤙᤢ" "lu"
+    sub "ᤙᤣ" "lē"
+    sub "ᤙᤤ" "lai"
+    sub "ᤙᤥ" "lō"
+    sub "ᤙᤦ" "lau"
+    sub "ᤚᤠ" "va"
+    sub "ᤚᤡ" "vi"
+    sub "ᤚᤢ" "vu"
+    sub "ᤚᤣ" "vē"
+    sub "ᤚᤤ" "vai"
+    sub "ᤚᤥ" "vō"
+    sub "ᤚᤦ" "vau"
+    sub "ᤛᤠ" "śa"
+    sub "ᤛᤡ" "śi"
+    sub "ᤛᤢ" "śu"
+    sub "ᤛᤣ" "śē"
+    sub "ᤛᤤ" "śai"
+    sub "ᤛᤥ" "śō"
+    sub "ᤛᤦ" "śau"
+    sub "ᤜᤠ" "sa"
+    sub "ᤜᤡ" "si"
+    sub "ᤜᤢ" "su"
+    sub "ᤜᤣ" "sē"
+    sub "ᤜᤤ" "sai"
+    sub "ᤜᤥ" "sō"
+    sub "ᤜᤦ" "sau"
+    sub "ᤝᤠ" "ha"
+    sub "ᤝᤡ" "hi"
+    sub "ᤝᤢ" "hu"
+    sub "ᤝᤣ" "hē"
+    sub "ᤝᤤ" "hai"
+    sub "ᤝᤥ" "hō"
+    sub "ᤝᤦ" "hau"
+  }
+
+  parallel {
+    sub "ᤁ" "ka"
+    sub "ᤂ" "kha"
+    sub "ᤃ" "ga"
+    sub "ᤄ" "gha"
+    sub "ᤅ" "ṅa"
+    sub "ᤆ" "ca"
+    sub "ᤇ" "cha"
+    sub "ᤈ" "ja"
+    sub "ᤉ" "jha"
+    sub "ᤋ" "ta"
+    sub "ᤌ" "tha"
+    sub "ᤍ" "da"
+    sub "ᤎ" "dha"
+    sub "ᤏ" "na"
+    sub "ᤒ" "pa"
+    sub "ᤓ" "pha"
+    sub "ᤔ" "ba"
+    sub "ᤕ" "bha"
+    sub "ᤖ" "ma"
+    sub "ᤗ" "ya"
+    sub "ᤘ" "ra"
+    sub "ᤙ" "la"
+    sub "ᤚ" "va"
+    sub "ᤛ" "śa"
+    sub "ᤜ" "sa"
+    sub "ᤝ" "ha"
+  }
+
+  parallel {
+    sub "ᤀ" "a"
+    sub "ᤡ" "i"
+    sub "ᤢ" "u"
+  }
+}
+}

data/maps/alalc-mni-Mtei-Latn-2022.isc

@@ -0,0 +1,289 @@
+system "ALA-LC:mni-Mtei:Latn:2022" {
+
+metadata {
+  authority_id alalc
+  id 2022
+  language iso-639-2:mni
+  source_script Mtei
+  destination_script Latn
+  name "Modern Manipuri (Meitei script) Romanization Table (2022)"
+  url https://www.loc.gov/catdir/cpso/romanization/manipuri.pdf
+  creation_date 2022
+  adoption_date
+  description {    ALA-LC Modern Manipuri (Meitei Mayek) Romanization Table,
+    June 2022. Consonants carry the inherent vowel a; the seven final
+    letters (katap) close syllables without a vowel; dependent vowel
+    signs override; the heavy-tone mark romanizes as a dot below.
+    Transcribed from the loc.gov document's complete text layer.
+  }
+
+  notes {
+    note "The heavy tone symbol (꯬) is a recent innovation; its
+    romanization is the combining dot below per the table."
+    note "2025 corpus repair: the source (p. 2) romanizes the numerals
+    ꯰-꯹ as 0-9; the digit rules were added and the numeral test
+    corrected (꯳ = 3, not saṣ). The vowel test was corrected to the
+    source's own row ꯁꯦ = se (p. 1, Vowels: Dependent vowel sign with
+    ꯁ); the katap test to ꯛ = k (p. 1, Final-consonants); the heavy
+    tone test to the source's own example ꯀꯥ꯬ = kā + combining dot
+    below (p. 2, Heavy tone: ꯀꯥ꯬ = kạ̄). Recorded gaps, behavior
+    unchanged: the punctuation row (꫱ question mark, ꫰ comma, ꯫ full
+    stop, p. 2) and the apun iyek/halanta killer ꯭ (p. 2 — its
+    inherent-vowel omission applies to the preceding consonant and
+    needs context-sensitive handling) are not yet encoded."
+  }
+}
+
+tests {
+   "\uabc1\uabe6" ->  "se"
+   "\uabf3" ->  "3"
+   "\uabdb" ->  "k"
+   "\uabc0\uabe5\uabec" ->  "k\u0101\u0323"
+}
+stage main {
+  parallel {
+    sub "ꯀꯥ" "kā"
+    sub "ꯂꯥ" "lā"
+    sub "ꯃꯥ" "mā"
+    sub "ꯄꯥ" "pā"
+    sub "ꯅꯥ" "nā"
+    sub "ꯆꯥ" "cā"
+    sub "ꯇꯥ" "tā"
+    sub "ꯈꯥ" "khā"
+    sub "ꯉꯥ" "ṅā"
+    sub "ꯊꯥ" "thā"
+    sub "ꯋꯥ" "vā"
+    sub "ꯌꯥ" "yā"
+    sub "ꯍꯥ" "hā"
+    sub "ꯐꯥ" "phā"
+    sub "ꯒꯥ" "gā"
+    sub "ꯓꯥ" "jhā"
+    sub "ꯔꯥ" "rā"
+    sub "ꯕꯥ" "bā"
+    sub "ꯖꯥ" "jā"
+    sub "ꯗꯥ" "dā"
+    sub "ꯘꯥ" "ghā"
+    sub "ꯙꯥ" "dhā"
+    sub "ꯚꯥ" "bhā"
+    sub "ꯁꯥ" "sā"
+    sub "ꯀꯤ" "ki"
+    sub "ꯂꯤ" "li"
+    sub "ꯃꯤ" "mi"
+    sub "ꯄꯤ" "pi"
+    sub "ꯅꯤ" "ni"
+    sub "ꯆꯤ" "ci"
+    sub "ꯇꯤ" "ti"
+    sub "ꯈꯤ" "khi"
+    sub "ꯉꯤ" "ṅi"
+    sub "ꯊꯤ" "thi"
+    sub "ꯋꯤ" "vi"
+    sub "ꯌꯤ" "yi"
+    sub "ꯍꯤ" "hi"
+    sub "ꯐꯤ" "phi"
+    sub "ꯒꯤ" "gi"
+    sub "ꯓꯤ" "jhi"
+    sub "ꯔꯤ" "ri"
+    sub "ꯕꯤ" "bi"
+    sub "ꯖꯤ" "ji"
+    sub "ꯗꯤ" "di"
+    sub "ꯘꯤ" "ghi"
+    sub "ꯙꯤ" "dhi"
+    sub "ꯚꯤ" "bhi"
+    sub "ꯁꯤ" "si"
+    sub "ꯀꯨ" "ku"
+    sub "ꯂꯨ" "lu"
+    sub "ꯃꯨ" "mu"
+    sub "ꯄꯨ" "pu"
+    sub "ꯅꯨ" "nu"
+    sub "ꯆꯨ" "cu"
+    sub "ꯇꯨ" "tu"
+    sub "ꯈꯨ" "khu"
+    sub "ꯉꯨ" "ṅu"
+    sub "ꯊꯨ" "thu"
+    sub "ꯋꯨ" "vu"
+    sub "ꯌꯨ" "yu"
+    sub "ꯍꯨ" "hu"
+    sub "ꯐꯨ" "phu"
+    sub "ꯒꯨ" "gu"
+    sub "ꯓꯨ" "jhu"
+    sub "ꯔꯨ" "ru"
+    sub "ꯕꯨ" "bu"
+    sub "ꯖꯨ" "ju"
+    sub "ꯗꯨ" "du"
+    sub "ꯘꯨ" "ghu"
+    sub "ꯙꯨ" "dhu"
+    sub "ꯚꯨ" "bhu"
+    sub "ꯁꯨ" "su"
+    sub "ꯀꯦ" "ke"
+    sub "ꯂꯦ" "le"
+    sub "ꯃꯦ" "me"
+    sub "ꯄꯦ" "pe"
+    sub "ꯅꯦ" "ne"
+    sub "ꯆꯦ" "ce"
+    sub "ꯇꯦ" "te"
+    sub "ꯈꯦ" "khe"
+    sub "ꯉꯦ" "ṅe"
+    sub "ꯊꯦ" "the"
+    sub "ꯋꯦ" "ve"
+    sub "ꯌꯦ" "ye"
+    sub "ꯍꯦ" "he"
+    sub "ꯐꯦ" "phe"
+    sub "ꯒꯦ" "ge"
+    sub "ꯓꯦ" "jhe"
+    sub "ꯔꯦ" "re"
+    sub "ꯕꯦ" "be"
+    sub "ꯖꯦ" "je"
+    sub "ꯗꯦ" "de"
+    sub "ꯘꯦ" "ghe"
+    sub "ꯙꯦ" "dhe"
+    sub "ꯚꯦ" "bhe"
+    sub "ꯁꯦ" "se"
+    sub "ꯀꯩ" "kai"
+    sub "ꯂꯩ" "lai"
+    sub "ꯃꯩ" "mai"
+    sub "ꯄꯩ" "pai"
+    sub "ꯅꯩ" "nai"
+    sub "ꯆꯩ" "cai"
+    sub "ꯇꯩ" "tai"
+    sub "ꯈꯩ" "khai"
+    sub "ꯉꯩ" "ṅai"
+    sub "ꯊꯩ" "thai"
+    sub "ꯋꯩ" "vai"
+    sub "ꯌꯩ" "yai"
+    sub "ꯍꯩ" "hai"
+    sub "ꯐꯩ" "phai"
+    sub "ꯒꯩ" "gai"
+    sub "ꯓꯩ" "jhai"
+    sub "ꯔꯩ" "rai"
+    sub "ꯕꯩ" "bai"
+    sub "ꯖꯩ" "jai"
+    sub "ꯗꯩ" "dai"
+    sub "ꯘꯩ" "ghai"
+    sub "ꯙꯩ" "dhai"
+    sub "ꯚꯩ" "bhai"
+    sub "ꯁꯩ" "sai"
+    sub "ꯀꯣ" "ko"
+    sub "ꯂꯣ" "lo"
+    sub "ꯃꯣ" "mo"
+    sub "ꯄꯣ" "po"
+    sub "ꯅꯣ" "no"
+    sub "ꯆꯣ" "co"
+    sub "ꯇꯣ" "to"
+    sub "ꯈꯣ" "kho"
+    sub "ꯉꯣ" "ṅo"
+    sub "ꯊꯣ" "tho"
+    sub "ꯋꯣ" "vo"
+    sub "ꯌꯣ" "yo"
+    sub "ꯍꯣ" "ho"
+    sub "ꯐꯣ" "pho"
+    sub "ꯒꯣ" "go"
+    sub "ꯓꯣ" "jho"
+    sub "ꯔꯣ" "ro"
+    sub "ꯕꯣ" "bo"
+    sub "ꯖꯣ" "jo"
+    sub "ꯗꯣ" "do"
+    sub "ꯘꯣ" "gho"
+    sub "ꯙꯣ" "dho"
+    sub "ꯚꯣ" "bho"
+    sub "ꯁꯣ" "so"
+    sub "ꯀꯧ" "kau"
+    sub "ꯂꯧ" "lau"
+    sub "ꯃꯧ" "mau"
+    sub "ꯄꯧ" "pau"
+    sub "ꯅꯧ" "nau"
+    sub "ꯆꯧ" "cau"
+    sub "ꯇꯧ" "tau"
+    sub "ꯈꯧ" "khau"
+    sub "ꯉꯧ" "ṅau"
+    sub "ꯊꯧ" "thau"
+    sub "ꯋꯧ" "vau"
+    sub "ꯌꯧ" "yau"
+    sub "ꯍꯧ" "hau"
+    sub "ꯐꯧ" "phau"
+    sub "ꯒꯧ" "gau"
+    sub "ꯓꯧ" "jhau"
+    sub "ꯔꯧ" "rau"
+    sub "ꯕꯧ" "bau"
+    sub "ꯖꯧ" "jau"
+    sub "ꯗꯧ" "dau"
+    sub "ꯘꯧ" "ghau"
+    sub "ꯙꯧ" "dhau"
+    sub "ꯚꯧ" "bhau"
+    sub "ꯁꯧ" "sau"
+  }
+
+  parallel {
+    sub "ꯀ" "ka"
+    sub "ꯂ" "la"
+    sub "ꯃ" "ma"
+    sub "ꯄ" "pa"
+    sub "ꯅ" "na"
+    sub "ꯆ" "ca"
+    sub "ꯇ" "ta"
+    sub "ꯈ" "kha"
+    sub "ꯉ" "ṅa"
+    sub "ꯊ" "tha"
+    sub "ꯋ" "va"
+    sub "ꯌ" "ya"
+    sub "ꯍ" "ha"
+    sub "ꯐ" "pha"
+    sub "ꯒ" "ga"
+    sub "ꯓ" "jha"
+    sub "ꯔ" "ra"
+    sub "ꯕ" "ba"
+    sub "ꯖ" "ja"
+    sub "ꯗ" "da"
+    sub "ꯘ" "gha"
+    sub "ꯙ" "dha"
+    sub "ꯚ" "bha"
+    sub "ꯁ" "sa"
+  }
+
+  parallel {
+    sub "ꯛ" "k"
+    sub "ꯜ" "l"
+    sub "ꯝ" "m"
+    sub "ꯞ" "p"
+    sub "ꯟ" "n"
+    sub "ꯠ" "t"
+    sub "ꯡ" "ṅ"
+  }
+
+  parallel {
+    sub "꯰" "0"
+    sub "꯱" "1"
+    sub "꯲" "2"
+    sub "꯳" "3"
+    sub "꯴" "4"
+    sub "꯵" "5"
+    sub "꯶" "6"
+    sub "꯷" "7"
+    sub "꯸" "8"
+    sub "꯹" "9"
+  }
+
+  parallel {
+    sub "ꯑ" "a"
+    sub "ꯑꯥ" "ā"
+    sub "ꯏ" "i"
+    sub "ꯎ" "u"
+    sub "ꯑꯦ" "e"
+    sub "ꯑꯩ" "ai"
+    sub "ꯑꯣ" "o"
+    sub "ꯑꯧ" "au"
+  }
+
+  parallel {
+    sub "ꫵ" "ḥ"
+    sub "ꯪ" "ṃ"
+    sub "꯬" "̣"
+    sub "ꯥ" "ā"
+    sub "ꯤ" "i"
+    sub "ꯨ" "u"
+    sub "ꯦ" "e"
+    sub "ꯩ" "ai"
+    sub "ꯣ" "o"
+    sub "ꯧ" "au"
+  }
+}
+}