interscript-maps 3.0.0 → 3.1.0

data/maps/alalc-chu-Cyrl-Latn-2022.isc

@@ -0,0 +1,244 @@
+system "ALA-LC:chu-Cyrl:Latn:2022" {
+
+metadata {
+  authority_id alalc
+  id 2022
+  language iso-639-2:chu
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Church Slavic (2022)
+  url https://www.loc.gov/catdir/cpso/romanization/church-slavic.pdf
+  creation_date 2022
+  description {
+    ALA-LC romanization table for Church Slavic, 2022 version
+    (earlier versions 2011 and 1997). Covers the full Church Slavonic
+    alphabet including the yuses, ksi, psi, fita, izhitsa and the two uk
+    forms, with the letters' numeric values annotated. Transcribed from
+    the digitized table (pages 1-2).
+  }
+
+  notes {
+    note "Diacritical signs: accents and aspiration marks are ignored in romanization, including the acute accent, the grave accent, the aspiration mark, and combinations thereof. The letters ї and ѷ are sometimes printed with two dots (or marks): when no other accent appears the dots have no particular significance and are ignored; when the dots (or other diacritical marks) indicate that the letter is a vowel, the letter is romanized ẏ. The symbol indicating a short i (breve) is taken into account in romanization, resulting in ĭ."
+    note "Abbreviations: abbreviated words are transcribed in full, without the use of brackets. The most common symbol for abbreviation is the titlo; omitted letters may be placed above other letters, and the symbol above a letter indicates the omission of ъ or ь."
+    note "Numerals: represented in Church Slavic by letters (as shown in the romanization table) with the addition of the signs ҂, U+20DD, U+0488 and U+0489; an added titlo indicates a basic numeral (в҃ = 2), and higher numerals: ҂в҃ = 2,000, в U+20DD = 20,000, в U+0488 = 200,000, в U+0489 = 2,000,000; the figure 1913 is written ҂аці҃г. This map renders the letters, not the numeral values."
+    note "Dates: Church Slavic books dated by the Mundane Era of Constantinople convert to the Christian Era by subtracting 5508; prior to 1700 the mundane year began on September 1st, so two years are given by subtracting 5509 (September through December) and 5508 (January through August); thus 7203 in the Mundane Era is 1694/95 in the Christian Era."
+    note "The iotated letters ѥ, ю, ꙗ, Ѩ and Ѭ are romanized Ī plus tie plus the vowel (Ī͡e, Ī͡u, Ī͡a, Ī͡ę, Ī͡ǫ), mirroring the table's romanization of і as Ī; the digraph-letter Ѿ (ot) is romanized Ō plus tie plus t (ō͡t); the digraph-letter pairs Ѯ and Ѱ are romanized k͡s and p͡s with the tie."
+    note "The table lists two uk forms, both with numeric value 400: the monograph uk Ꙋ is romanized U and the digraph uk Ѹ is romanized Ū. Both forms are encoded."
+    note "The table's row for ћ (used for the soft g in Serbian-printed Church Slavic) gives ǵ, distinct from the Serbian table's đ."
+    note "Izhitsa ѷ is romanized ẏ (Y with dot above); the table notes the alternative rendering v̇ when the letter is used without diacritical marks. Only the vowel rendering ẏ is encoded, as the alternative cannot be resolved without reading context."
+    note "Source erratum: the lower-case row for и prints the romanization as uppercase I. Encoded as i for case parity; flagged in the pull request."
+    note "Numeric-value column of the source table: А=1, В=2, Г=3, Д=4, Є=5, Ѕ=6, З=7, И=8, І=10, К=20, Л=30, М=40, Н=50, О=70, П=80, Р=100, С=200, Т=300, both uk forms=400, Ф=500, Х=600, Ѯ=60, Ѱ=700, Ѡ and Ѿ=800, Ѧ=900, Ѳ=9, Ѷ=400."
+    note "Transcribed visually from the scanned table pages; the romanization cells for Ѥ, Ѿ, Ц, Ы, Ю, Ꙗ, Ѯ, Ѱ, Ѩ and Ѭ are embedded raster images in the source PDF and were verified at magnification from the extracted image rasters."
+  }
+}
+
+tests {
+  # every table row, upper and lower (the document has no example words
+  # beyond the table itself)
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "G"
+   "г" ->  "g"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Є" ->  "E"
+   "є" ->  "e"
+   "Е" ->  "Ē"
+   "е" ->  "ē"
+   "Ѥ" ->  "Ī͡E"
+   "ѥ" ->  "ī͡e"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "Ѕ" ->  "Ż"
+   "ѕ" ->  "ż"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Й" ->  "Ĭ"
+   "й" ->  "ĭ"
+   "І" ->  "Ī"
+   "і" ->  "ī"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "Ꙋ" ->  "U"
+   "ꙋ" ->  "u"
+   "Ѹ" ->  "Ū"
+   "ѹ" ->  "ū"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ѿ" ->  "Ō͡T"
+   "ѿ" ->  "ō͡t"
+   "Ѡ" ->  "Ō"
+   "ѡ" ->  "ō"
+   "Ц" ->  "T͡S"
+   "ц" ->  "t͡s"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Sht"
+   "щ" ->  "sht"
+   "Ъ" ->  "ʺ"
+   "ъ" ->  "ʺ"
+   "Ы" ->  "Ȳ"
+   "ы" ->  "ȳ"
+   "Ꙑ" ->  "Y"
+   "ꙑ" ->  "y"
+   "Ь" ->  "ʹ"
+   "ь" ->  "ʹ"
+   "Ѣ" ->  "Ě"
+   "ѣ" ->  "ě"
+   "Ю" ->  "Ī͡U"
+   "ю" ->  "ī͡u"
+   "Ꙗ" ->  "Ī͡A"
+   "ꙗ" ->  "ī͡a"
+   "Ѧ" ->  "Ę"
+   "ѧ" ->  "ę"
+   "Ѯ" ->  "K͡S"
+   "ѯ" ->  "k͡s"
+   "Ѱ" ->  "P͡S"
+   "ѱ" ->  "p͡s"
+   "Ѳ" ->  "Ḟ"
+   "ѳ" ->  "ḟ"
+   "Ѷ" ->  "Ẏ"
+   "ѷ" ->  "ẏ"
+   "Ѫ" ->  "Ǫ"
+   "ѫ" ->  "ǫ"
+   "Ѩ" ->  "Ī͡Ę"
+   "ѩ" ->  "ī͡ę"
+   "Ѭ" ->  "Ī͡Ǫ"
+   "ѭ" ->  "ī͡ǫ"
+   "Ћ" ->  "Ǵ"
+   "ћ" ->  "ǵ"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "а" "a"
+    sub "Б" "B"
+    sub "б" "b"
+    sub "В" "V"
+    sub "в" "v"
+    sub "Г" "G"
+    sub "г" "g"
+    sub "Д" "D"
+    sub "д" "d"
+    sub "Є" "E"
+    sub "є" "e"
+    sub "Е" "Ē"
+    sub "е" "ē"
+    sub "Ѥ" "Ī͡E"
+    sub "ѥ" "ī͡e"
+    sub "Ж" "Zh"
+    sub "ж" "zh"
+    sub "Ѕ" "Ż"
+    sub "ѕ" "ż"
+    sub "З" "Z"
+    sub "з" "z"
+    sub "И" "I"
+    sub "и" "i"
+    sub "Й" "Ĭ"
+    sub "й" "ĭ"
+    sub "І" "Ī"
+    sub "і" "ī"
+    sub "К" "K"
+    sub "к" "k"
+    sub "Л" "L"
+    sub "л" "l"
+    sub "М" "M"
+    sub "м" "m"
+    sub "Н" "N"
+    sub "н" "n"
+    sub "О" "O"
+    sub "о" "o"
+    sub "П" "P"
+    sub "п" "p"
+    sub "Р" "R"
+    sub "р" "r"
+    sub "С" "S"
+    sub "с" "s"
+    sub "Т" "T"
+    sub "т" "t"
+    sub "Ꙋ" "U"
+    sub "ꙋ" "u"
+    sub "Ѹ" "Ū"
+    sub "ѹ" "ū"
+    sub "Ф" "F"
+    sub "ф" "f"
+    sub "Х" "Kh"
+    sub "х" "kh"
+    sub "Ѿ" "Ō͡T"
+    sub "ѿ" "ō͡t"
+    sub "Ѡ" "Ō"
+    sub "ѡ" "ō"
+    sub "Ц" "T͡S"
+    sub "ц" "t͡s"
+    sub "Ч" "Ch"
+    sub "ч" "ch"
+    sub "Ш" "Sh"
+    sub "ш" "sh"
+    sub "Щ" "Sht"
+    sub "щ" "sht"
+    sub "Ъ" "ʺ"
+    sub "ъ" "ʺ"
+    sub "Ы" "Ȳ"
+    sub "ы" "ȳ"
+    sub "Ꙑ" "Y"
+    sub "ꙑ" "y"
+    sub "Ь" "ʹ"
+    sub "ь" "ʹ"
+    sub "Ѣ" "Ě"
+    sub "ѣ" "ě"
+    sub "Ю" "Ī͡U"
+    sub "ю" "ī͡u"
+    sub "Ꙗ" "Ī͡A"
+    sub "ꙗ" "ī͡a"
+    sub "Ѧ" "Ę"
+    sub "ѧ" "ę"
+    sub "Ѯ" "K͡S"
+    sub "ѯ" "k͡s"
+    sub "Ѱ" "P͡S"
+    sub "ѱ" "p͡s"
+    sub "Ѳ" "Ḟ"
+    sub "ѳ" "ḟ"
+    sub "Ѷ" "Ẏ"
+    sub "ѷ" "ẏ"
+    sub "Ѫ" "Ǫ"
+    sub "ѫ" "ǫ"
+    sub "Ѩ" "Ī͡Ę"
+    sub "ѩ" "ī͡ę"
+    sub "Ѭ" "Ī͡Ǫ"
+    sub "ѭ" "ī͡ǫ"
+    sub "Ћ" "Ǵ"
+    sub "ћ" "ǵ"
+  }
+
+}
+
+}

data/maps/alalc-cop-Copt-Latn-2014.isc

@@ -0,0 +1,231 @@
+system "ALA-LC:cop-Copt:Latn:2014" {
+
+metadata {
+  authority_id alalc
+  id 2014
+  language iso-639-2:cop
+  source_script Copt
+  destination_script Latn
+  name "Coptic Romanization Table (2014)"
+  url https://www.loc.gov/catdir/cpso/romanization/coptic.pdf
+  creation_date 2014
+  adoption_date
+  description {    ALA-LC Coptic Romanization Table, 2014 version (no earlier
+    versions). Covers the Coptic alphabet (Greek-derived and Demotic
+    letters), the Old Coptic letters with their diacritic romanizations
+    (diaeresis forms Ï Ü Ẍ, the K-diaeresis-below and dialect-p ni and
+    crossed shei letters, the dialect-p alef to a modifier-letter
+    apostrophe), the Old Nubian letters (ŋ ɲ w), the letter-numeral
+    table (macron above for units, overline for thousands), and the
+    note rules: the single prime inserted between two letters that
+    could be misread as a digraph, and the ignoring of diacritics per
+    the practice of the Journal of Coptic Studies except the iaude (ⲓ)
+    and ua (ⲩ) diaereses.
+  }
+
+  notes {
+    note "The upper-case romanization cells for Ⲻ (dialect-p ni) and
+    Ⳃ (crossed shei) are blank in the source document; the lower-case
+    cells carry n̈ and ç̈. The map supplies the upper-case forms N̈ and
+    Ç̈ as the mechanical case counterparts (flagged for review)."
+    note "Note 1 (MARC-8): within a strictly MARC-8 environment the
+    double underscore may be applied to a base character n following
+    LC-PCC PS 1.4 for ŋ and ɲ; the resulting ambiguity of n̳ illustrates
+    the advantage of extended Latin."
+    note "Note 2: a single prime (ʹ, U+02B9) is inserted between two
+    letters representing two distinct consonantal sounds when the
+    combination might otherwise be read as a digraph. The document's
+    examples give ⲙⲛ̅ⲧϩⲗ̅ⲗⲟ = mntʹhllo (prime in ⲧϩ, since th is a
+    digraph) versus ⲙⲛ̅ⲑⲗ̅ⲗⲟ = mnthllo (ⲑ is itself the th digraph).
+    The ⲧϩ combination is encoded in both cases."
+    note "Note 3: diacritics are ignored when romanizing Coptic,
+    following the practice of the Journal of Coptic Studies, with the
+    exception of the iaude (ⲓ) and ua (ⲩ) diaereses, which carry Ï/ï
+    and Ü/ü. The strip rules at the end of the stage delete the
+    remaining combining marks (macron, overline, diaeresis on other
+    letters, accents, breathing marks, dot marks)."
+    note "Numerals: units and tens and hundreds are letter + combining
+    macron (U+0304): ⲁ̄ 1, ⲃ̄ 2, ⲅ̄ 3, ⲇ̄ 4, ⲉ̄ 5, ⲋ̄ 6, ⲍ̄ 7, ⲏ̄ 8,
+    ⲑ̄ 9, ⲓ̄ 10, ⲕ̄ 20, ⲗ̄ 30, ⲙ̄ 40, ⲛ̄ 50, ⲝ̄ 60, ⲟ̄ 70, ⲡ̄ 80,
+    ϥ̄ 90, ⲣ̄ 100, ⲥ̄ 200, ⲧ̄ 300, ⲩ̄ 400, ⲫ̄ 500, ⲭ̄ 600, ⲯ̄ 700,
+    ⲱ̄ 800, ⳁ 900 (the sampi numeral is bare, without macron, as
+    printed). Thousands are letter + combining overline (U+0305):
+    ⲁ̅ 1000 through ⲑ̅ 9000. The source shows the 6 and 6000 forms
+    with an alternate glyph (rendered through a substitute font and
+    absent from the text layer) identified visually as the Greek
+    stigma; the stigma forms are encoded as alternates alongside ⲋ."
+    note "The superlinear stroke (overline, U+0305) also marks
+    abbreviation/nominal strokes over letters inside words; on the
+    nine thousands letters the numeral value wins per the table, so
+    e.g. word-internal ⲁ̅ romanizes as 1000."
+  }
+}
+
+tests {
+  "ⲙⲛ̅ⲧϩⲗ̅ⲗⲟ" -> "mntʹhllo"
+  "ⲙⲛ̅ⲑⲗ̅ⲗⲟ" -> "mnthllo"
+  "ⲁ̄" -> "1"
+  "ⲁ̅" -> "1000"
+  "ⲓ̈" -> "ï"
+  "ⲩ̈" -> "ü"
+  "ϩⲏ" -> "hē"
+  "Ϣ" -> "Š"
+  "ϧ" -> "ḥ"
+  "ⳟ" -> "ŋ"
+  "ⳣ" -> "w"
+  "Ⲳ" -> "ʼ"
+  "ⲁ̈" -> "a"
+  "ⳁ" -> "900"
+  "ⲋ̄" -> "6"
+  "ϛ̄" -> "6"
+}
+
+stage main {
+  parallel {
+    sub "ⲁ̄" "1"
+    sub "ⲃ̄" "2"
+    sub "ⲅ̄" "3"
+    sub "ⲇ̄" "4"
+    sub "ⲉ̄" "5"
+    sub "ⲋ̄" "6"
+    sub "ϛ̄" "6"
+    sub "ⲍ̄" "7"
+    sub "ⲏ̄" "8"
+    sub "ⲑ̄" "9"
+    sub "ⲓ̄" "10"
+    sub "ⲕ̄" "20"
+    sub "ⲗ̄" "30"
+    sub "ⲙ̄" "40"
+    sub "ⲛ̄" "50"
+    sub "ⲝ̄" "60"
+    sub "ⲟ̄" "70"
+    sub "ⲡ̄" "80"
+    sub "ϥ̄" "90"
+    sub "ⲣ̄" "100"
+    sub "ⲥ̄" "200"
+    sub "ⲧ̄" "300"
+    sub "ⲩ̄" "400"
+    sub "ⲫ̄" "500"
+    sub "ⲭ̄" "600"
+    sub "ⲯ̄" "700"
+    sub "ⲱ̄" "800"
+    sub "ⳁ" "900"
+    sub "ⲁ̅" "1000"
+    sub "ⲃ̅" "2000"
+    sub "ⲅ̅" "3000"
+    sub "ⲇ̅" "4000"
+    sub "ⲉ̅" "5000"
+    sub "ⲋ̅" "6000"
+    sub "ϛ̅" "6000"
+    sub "ⲍ̅" "7000"
+    sub "ⲏ̅" "8000"
+    sub "ⲑ̅" "9000"
+  }
+
+  parallel {
+    sub "Ⲧϩ" "Tʹh"
+    sub "ⲧϩ" "tʹh"
+  }
+
+  parallel {
+    sub "Ⲓ̈" "Ï"
+    sub "ⲓ̈" "ï"
+    sub "Ⲩ̈" "Ü"
+    sub "ⲩ̈" "ü"
+    sub "Ⳉ" "Ẍ"
+    sub "ⳉ" "ẍ"
+    sub "Ϧ" "Ḥ"
+    sub "ϧ" "ḥ"
+    sub "Ⲹ" "K̤"
+    sub "ⲹ" "k̤"
+    sub "Ⲻ" "N̈"
+    sub "ⲻ" "n̈"
+    sub "Ⳃ" "Ç̈"
+    sub "ⳃ" "ç̈"
+    sub "Ⲳ" "ʼ"
+    sub "ⳳ" "ʼ"
+    sub "Ⳟ" "Ŋ"
+    sub "ⳟ" "ŋ"
+    sub "Ⳡ" "Ɲ"
+    sub "ⳡ" "ɲ"
+    sub "Ⳣ" "W"
+    sub "ⳣ" "w"
+  }
+
+  parallel {
+    sub "Ⲁ" "A"
+    sub "ⲁ" "a"
+    sub "Ⲃ" "B"
+    sub "ⲃ" "b"
+    sub "Ⲅ" "G"
+    sub "ⲅ" "g"
+    sub "Ⲇ" "D"
+    sub "ⲇ" "d"
+    sub "Ⲉ" "E"
+    sub "ⲉ" "e"
+    sub "Ⲍ" "Z"
+    sub "ⲍ" "z"
+    sub "Ⲏ" "Ē"
+    sub "ⲏ" "ē"
+    sub "Ⲑ" "Th"
+    sub "ⲑ" "th"
+    sub "Ⲓ" "I"
+    sub "ⲓ" "i"
+    sub "Ⲕ" "K"
+    sub "ⲕ" "k"
+    sub "Ⲗ" "L"
+    sub "ⲗ" "l"
+    sub "Ⲙ" "M"
+    sub "ⲙ" "m"
+    sub "Ⲛ" "N"
+    sub "ⲛ" "n"
+    sub "Ⲝ" "X"
+    sub "ⲝ" "x"
+    sub "Ⲟ" "O"
+    sub "ⲟ" "o"
+    sub "Ⲡ" "P"
+    sub "ⲡ" "p"
+    sub "Ⲣ" "R"
+    sub "ⲣ" "r"
+    sub "Ⲥ" "S"
+    sub "ⲥ" "s"
+    sub "Ⲧ" "T"
+    sub "ⲧ" "t"
+    sub "Ⲩ" "U"
+    sub "ⲩ" "u"
+    sub "Ⲫ" "Ph"
+    sub "ⲫ" "ph"
+    sub "Ⲭ" "Ch"
+    sub "ⲭ" "ch"
+    sub "Ⲯ" "Ps"
+    sub "ⲯ" "ps"
+    sub "Ⲱ" "Ō"
+    sub "ⲱ" "ō"
+    sub "Ϣ" "Š"
+    sub "ϣ" "š"
+    sub "Ϥ" "F"
+    sub "ϥ" "f"
+    sub "Ϩ" "H"
+    sub "ϩ" "h"
+    sub "Ϫ" "Č"
+    sub "ϫ" "č"
+    sub "Ϭ" "Ky"
+    sub "ϭ" "ky"
+    sub "Ϯ" "Ti"
+    sub "ϯ" "ti"
+  }
+
+  parallel {
+    sub "̄" ""
+    sub "̅" ""
+    sub "̈" ""
+    sub "̀" ""
+    sub "́" ""
+    sub "ͅ" ""
+    sub "̓" ""
+    sub "̔" ""
+    sub "̣" ""
+    sub "̤" ""
+  }
+}
+}