interscript-maps 2.5.2 → 3.0.0

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

@@ -0,0 +1,76 @@
+system "DIN:yrk-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-41
+  language iso-639-3:yrk
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 41: Nenzisch ((S))"
+  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 41
+    (Nenzisch). 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 "ң" "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" "śč"
+    sub "ъ" "q"
+    sub "ы" "y"
+    sub "ь" "ĭ"
+    sub "э" "ė"
+    sub "э̇" "é"
+  }
+}
+}

data/maps/icao-bel-Cyrl-Latn-9303.isc

@@ -22,6 +22,15 @@ metadata {
     This document defines the transliteration mappings used to produce
     this transcription or transliteration.
   }
+
+  notes {
+    note "Diffed against ICAO Doc 9303 Part 3 Amd 1 (16/09/16), Section 6.B: the rows for Ќ, Ъ, Ѵ and Ғ were missing and were added with their source values. U+2019 right single quotation mark is now dropped alongside the ASCII apostrophe per Section 4.6 (apostrophes shall be omitted in the MRZ)."
+    note "Divergences corrected against the same source: the lowercase rows for у, ю, ў and ѫ were emptied or truncated (to nothing and to i); the source gives У to U, Ю to IU, Ў to U and Ѫ to U regardless of case, so the lowercase rows now mirror their uppercase rows."
+    note "Belarusian exceptions applied per the source: Ё renders IO and Г renders H."
+    note "The map carries a row for Ѓ (U+0403) to G, which has no row in the Amd 1 Section 6.B table (the table has Ғ, U+0492, to G); kept as a practical extension."
+    note "Soft sign Ь has no row in the Amd 1 Section 6.B table and is left unmapped."
+    note "The Amd 1 table prints row 04BA Һ (Cyrillic shha) as C; the map follows the source as printed, though C rather than H may be a source-side erratum."
+  }
 }
 
 tests {
@@ -33,6 +42,25 @@ tests {
    "Ігар" ->  "Ihar"
    "Палто Алена" ->  "Palto Alena"
    "Мікалай" ->  "Mikalai"
+   "Магілёў" ->  "Mahiliou"
+   "Гродна" ->  "Hrodna"
+   "Ё" ->  "IO"
+   "ё" ->  "io"
+   "Г" ->  "H"
+   "г" ->  "h"
+   "Ў" ->  "U"
+   "ў" ->  "u"
+   "у" ->  "u"
+   "Ю" ->  "IU"
+   "ю" ->  "iu"
+   "Ъ" ->  "IE"
+   "ъ" ->  "ie"
+   "Ѵ" ->  "Y"
+   "ѷ" ->  "y"
+   "Ғ" ->  "G"
+   "ғ" ->  "g"
+   "Ќ" ->  "K"
+   "ќ" ->  "k"
 }
 
 # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
@@ -41,6 +69,7 @@ stage main {
   # CHARACTERS
   parallel {
     sub "'" ""
+    sub "’" ""
     sub "А" "A"
     sub "Б" "B"
     sub "Д" "D"
@@ -52,6 +81,7 @@ stage main {
     sub "И" "I"
     sub "Й" "I"
     sub "К" "K"
+    sub "Ќ" "K"
     sub "Л" "L"
     sub "М" "M"
     sub "Н" "N"
@@ -70,11 +100,14 @@ stage main {
     sub "Х" "KH"
     sub "Ш" "SH"
     sub "Щ" "SHCH"
+    sub "Ъ" "IE"
     sub "Ц" "TS"
     sub "Ж" "ZH"
     sub "Ґ" "G"
+    sub "Ғ" "G"
     sub "Ў" "U"
     sub "Ѫ" "U"
+    sub "Ѵ" "Y"
     sub "Ђ" "D"
     sub "Ѕ" "DZ"
     sub "Ј" "J"
@@ -106,21 +139,24 @@ stage main {
     sub "р" "r"
     sub "с" "s"
     sub "т" "t"
-    sub "у" ""
+    sub "у" "u"
     sub "в" "v"
     sub "ы" "y"
     sub "з" "z"
     sub "ч" "ch"
     sub "я" "ia"
-    sub "ю" "i"
+    sub "ю" "iu"
     sub "х" "kh"
     sub "ш" "sh"
     sub "щ" "shch"
+    sub "ъ" "ie"
     sub "ц" "ts"
     sub "ж" "zh"
     sub "ґ" "g"
-    sub "ў" ""
-    sub "ѫ" ""
+    sub "ғ" "g"
+    sub "ў" "u"
+    sub "ѫ" "u"
+    sub "ѷ" "y"
     sub "ђ" "d"
     sub "ѕ" "dz"
     sub "ј" "j"
@@ -132,6 +168,7 @@ stage main {
     sub "ї" "i"
     sub "ѓ" "g"
     sub "і" "i"
+    sub "ќ" "k"
   }
 
 }

data/maps/icao-bul-Cyrl-Latn-9303.isc

@@ -22,9 +22,30 @@ metadata {
     This document defines the transliteration mappings used to produce
     this transcription or transliteration.
   }
+
+  notes {
+    note "Diffed against ICAO Doc 9303 Part 3 Amd 1 (16/09/16), Section 6.B: the rows for І, Ќ, Ъ, Ѵ and Ғ were missing and were added with their source values. U+2019 right single quotation mark is now dropped alongside the ASCII apostrophe per Section 4.6 (apostrophes shall be omitted in the MRZ)."
+    note "Divergences corrected against the same source: the lowercase rows for у, ю, ў and ѫ were emptied or truncated (to nothing and to i); the source gives У to U, Ю to IU, Ў to U and Ѫ to U regardless of case, so the lowercase rows now mirror their uppercase rows. A duplicated apostrophe row was removed."
+    note "Bulgarian exception applied per the source: Щ renders SHT. Note that Ъ renders IE per the source table even though it is a vowel in Bulgarian."
+    note "The map carries a row for Ѓ (U+0403) to G, which has no row in the Amd 1 Section 6.B table (the table has Ғ, U+0492, to G); kept as a practical extension."
+    note "Soft sign Ь has no row in the Amd 1 Section 6.B table and is left unmapped."
+    note "The Amd 1 table prints row 04BA Һ (Cyrillic shha) as C; the map follows the source as printed, though C rather than H may be a source-side erratum."
+  }
 }
 
 tests {
+   "Щ" ->  "SHT"
+   "щ" ->  "sht"
+   "Ъ" ->  "IE"
+   "ъ" ->  "ie"
+   "у" ->  "u"
+   "Ю" ->  "IU"
+   "ю" ->  "iu"
+   "Ѵ" ->  "Y"
+   "ѷ" ->  "y"
+   "Ғ" ->  "G"
+   "ғ" ->  "g"
+   "България" ->  "Bielgariia"
 }
 
 # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
@@ -33,6 +54,7 @@ stage main {
   # CHARACTERS
   parallel {
     sub "'" ""
+    sub "’" ""
     sub "А" "A"
     sub "Б" "B"
     sub "Д" "D"
@@ -44,6 +66,7 @@ stage main {
     sub "И" "I"
     sub "Й" "I"
     sub "К" "K"
+    sub "Ќ" "K"
     sub "Л" "L"
     sub "М" "M"
     sub "Н" "N"
@@ -62,11 +85,14 @@ stage main {
     sub "Х" "KH"
     sub "Ш" "SH"
     sub "Щ" "SHT"
+    sub "Ъ" "IE"
     sub "Ц" "TS"
     sub "Ж" "ZH"
     sub "Ґ" "G"
+    sub "Ғ" "G"
     sub "Ў" "U"
     sub "Ѫ" "U"
+    sub "Ѵ" "Y"
     sub "Ђ" "D"
     sub "Ѕ" "DZ"
     sub "Ј" "J"
@@ -76,8 +102,8 @@ stage main {
     sub "Џ" "DZ"
     sub "Є" "IE"
     sub "Ї" "I"
+    sub "І" "I"
     sub "Ѓ" "G"
-    sub "'" ""
 
     sub "а" "a"
     sub "б" "b"
@@ -90,6 +116,7 @@ stage main {
     sub "и" "i"
     sub "й" "i"
     sub "к" "k"
+    sub "ќ" "k"
     sub "л" "l"
     sub "м" "m"
     sub "н" "n"
@@ -98,21 +125,24 @@ stage main {
     sub "р" "r"
     sub "с" "s"
     sub "т" "t"
-    sub "у" ""
+    sub "у" "u"
     sub "в" "v"
     sub "ы" "y"
     sub "з" "z"
     sub "ч" "ch"
     sub "я" "ia"
-    sub "ю" "i"
+    sub "ю" "iu"
     sub "х" "kh"
     sub "ш" "sh"
     sub "щ" "sht"
+    sub "ъ" "ie"
     sub "ц" "ts"
     sub "ж" "zh"
     sub "ґ" "g"
-    sub "ў" ""
-    sub "ѫ" ""
+    sub "ғ" "g"
+    sub "ў" "u"
+    sub "ѫ" "u"
+    sub "ѷ" "y"
     sub "ђ" "d"
     sub "ѕ" "dz"
     sub "ј" "j"
@@ -122,6 +152,7 @@ stage main {
     sub "џ" "dz"
     sub "є" "ie"
     sub "ї" "i"
+    sub "і" "i"
     sub "ѓ" "g"
   }
 

data/maps/icao-fas-Arab-Latn-9303.isc

@@ -22,9 +22,28 @@ metadata {
     This document defines the transliteration mappings used to produce
     this transcription or transliteration.
   }
+
+  notes {
+    note "Diffed against ICAO Doc 9303 Part 3 Amd 1 (16/09/16), Section 6.C (Transliteration of Arabic Script)."
+    note "Divergence corrected against the source: teh marbuta was rendered P, which is the value of peh; the source's row 0629 renders teh marbuta XTA. The other divergences corrected: the vowel-sign rows fathatan, dammatan, kasratan, fatha, damma, kasra and sukun were rendered F, N, K, A, U, I and O, but the source marks all of them (and tatwheel and superscript alef) as Not encoded; they now drop from the output instead of injecting Latin letters."
+    note "NOT ENCODED -- teh marbuta word-final variant. Source footnote 1: XTA is used generally except if teh marbuta occurs at the end of the name component, in which case XAH is used. This positional rule needs an after-boundary constraint, which the current Ruby ISC runtime drops (Interscript::Isc::NodeAdapter reads constraint :value while the DocumentBuilder emits :item), so it would silently never fire; once fixed, encode it as sub { from \"ة\" to \"XAH\" after boundary } before the parallel block."
+    note "NOT ENCODED -- shadda (U+0651). Source footnote 2: shadda denotes doubling, the Latin character or sequence is repeated (e.g. abbas with shadda becomes EBBAS). Doubling the previous output is not expressible as a parallel substitution, so shadda is left unmapped rather than guessed."
+    note "The four further Not encoded rows of the source table (069C, 06A2, 06A7, 06A8) are likewise left unmapped."
+  }
 }
 
 tests {
+   "ة" ->  "XTA"
+   "پ" ->  "P"
+   "چ" ->  "XC"
+   "ژ" ->  "XJ"
+   "گ" ->  "XGG"
+   "ک" ->  "XKK"
+   "ی" ->  "XYA"
+   "َ" ->  ""
+   "ْ" ->  ""
+   "ـ" ->  ""
+   "پاکستان" ->  "PAXKKSTAN"
 }
 
 # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
@@ -42,7 +61,7 @@ stage main {
     sub "ئ" "XI"
     sub "ا" "A"
     sub "ب" "B"
-    sub "ة" "P"
+    sub "ة" "XTA"
     sub "ت" "T"
     sub "ث" "XTH"
     sub "ج" "J"
@@ -60,6 +79,7 @@ stage main {
     sub "ظ" "XZZ"
     sub "ع" "E"
     sub "غ" "G"
+    sub "ـ" ""
     sub "ف" "F"
     sub "ق" "Q"
     sub "ك" "K"
@@ -70,13 +90,13 @@ stage main {
     sub "و" "W"
     sub "ى" "XAY"
     sub "ي" "Y"
-    sub "ً" "F"
-    sub "ٌ" "N"
-    sub "ٍ" "K"
-    sub "َ" "A"
-    sub "ُ" "U"
-    sub "ِ" "I"
-    sub "ْ" "O"
+    sub "ً" ""
+    sub "ٌ" ""
+    sub "ٍ" ""
+    sub "َ" ""
+    sub "ُ" ""
+    sub "ِ" ""
+    sub "ْ" ""
     sub "ٰ" ""
     sub "ٱ" "XXA"
     sub "ٹ" "XXT"

data/maps/icao-heb-Hebr-Latn-9303.isc

@@ -22,6 +22,11 @@ metadata {
     This document defines the transliteration mappings used to produce
     this transcription or transliteration.
   }
+
+  notes {
+    note "NOT DIFFABLE against ICAO Doc 9303 Part 3 Amd 1 (16/09/16): its Section 6 (Transliterations Recommended for Use by States) provides tables only for the Latin, Cyrillic and Arabic families of languages; there is no Hebrew table in that source, and no Appendix covering Hebrew."
+    note "The mapping in this file follows the Wikipedia Romanization of Hebrew (see the comment above the stage), not any ICAO Doc 9303 table in hand; its attribution to Doc 9303 is unverified. No values were changed in the WO09 diff because no ICAO Hebrew source was available to diff against."
+  }
 }
 
 tests {

data/maps/icao-mkd-Cyrl-Latn-9303.isc

@@ -22,9 +22,41 @@ metadata {
     This document defines the transliteration mappings used to produce
     this transcription or transliteration.
   }
+
+  notes {
+    note "Diffed against ICAO Doc 9303 Part 3 Amd 1 (16/09/16), Section 6.B: the rows for І, Ќ, Ъ, Ѵ and Ғ were missing and were added with their source values; for Ғ the source's Macedonian exception GJ applies. U+2019 right single quotation mark is now dropped alongside the ASCII apostrophe per Section 4.6 (apostrophes shall be omitted in the MRZ)."
+    note "Divergences corrected against the same source: К was rendered KJ (and к kj), but the source renders К to K unconditionally and gives KJ only for Ќ (row 040C: K except in the language spoken in the former Yugoslav Republic of Macedonia = KJ); К now renders K and the missing Ќ/ќ rows render KJ/kj. The lowercase rows for у, ю, ў and ѫ were emptied or truncated; the source gives У to U, Ю to IU, Ў to U and Ѫ to U regardless of case."
+    note "Macedonian exceptions applied per the source: Х renders H, Ц renders C, Ќ renders KJ, Џ renders DJ, Ғ renders GJ."
+    note "The map carries a row for Ѓ (U+0403) to GJ, which has no row of its own in the Amd 1 Section 6.B table; it mirrors the source's Macedonian exception for Ғ (U+0492) applied to the Macedonian letter actually in use. Ғ itself is encoded GJ per the source."
+    note "Soft sign Ь has no row in the Amd 1 Section 6.B table and is left unmapped."
+    note "The Amd 1 table prints row 04BA Һ (Cyrillic shha) as C; the map follows the source as printed, though C rather than H may be a source-side erratum."
+  }
 }
 
 tests {
+   "К" ->  "K"
+   "к" ->  "k"
+   "Ќ" ->  "KJ"
+   "ќ" ->  "kj"
+   "Џ" ->  "DJ"
+   "џ" ->  "dj"
+   "Х" ->  "H"
+   "х" ->  "h"
+   "Ц" ->  "C"
+   "ц" ->  "c"
+   "Ѓ" ->  "GJ"
+   "ѓ" ->  "gj"
+   "Ѕ" ->  "DZ"
+   "ѕ" ->  "dz"
+   "Ъ" ->  "IE"
+   "ъ" ->  "ie"
+   "Ѵ" ->  "Y"
+   "ѷ" ->  "y"
+   "Ғ" ->  "GJ"
+   "ғ" ->  "gj"
+   "у" ->  "u"
+   "ю" ->  "iu"
+   "Скопје" ->  "Skopje"
 }
 
 # https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
@@ -33,6 +65,7 @@ stage main {
   # CHARACTERS
   parallel {
     sub "'" ""
+    sub "’" ""
     sub "А" "A"
     sub "Б" "B"
     sub "Д" "D"
@@ -43,7 +76,8 @@ stage main {
     sub "Г" "G"
     sub "И" "I"
     sub "Й" "I"
-    sub "К" "KJ"
+    sub "К" "K"
+    sub "Ќ" "KJ"
     sub "Л" "L"
     sub "М" "M"
     sub "Н" "N"
@@ -62,11 +96,14 @@ stage main {
     sub "Х" "H"
     sub "Ш" "SH"
     sub "Щ" "SHCH"
+    sub "Ъ" "IE"
     sub "Ц" "C"
     sub "Ж" "ZH"
     sub "Ґ" "G"
+    sub "Ғ" "GJ"
     sub "Ў" "U"
     sub "Ѫ" "U"
+    sub "Ѵ" "Y"
     sub "Ђ" "D"
     sub "Ѕ" "DZ"
     sub "Ј" "J"
@@ -76,6 +113,7 @@ stage main {
     sub "Џ" "DJ"
     sub "Є" "IE"
     sub "Ї" "I"
+    sub "І" "I"
     sub "Ѓ" "GJ"
 
     sub "а" "a"
@@ -88,7 +126,8 @@ stage main {
     sub "г" "g"
     sub "и" "i"
     sub "й" "i"
-    sub "к" "kj"
+    sub "к" "k"
+    sub "ќ" "kj"
     sub "л" "l"
     sub "м" "m"
     sub "н" "n"
@@ -97,21 +136,24 @@ stage main {
     sub "р" "r"
     sub "с" "s"
     sub "т" "t"
-    sub "у" ""
+    sub "у" "u"
     sub "в" "v"
     sub "ы" "y"
     sub "з" "z"
     sub "ч" "ch"
     sub "я" "ia"
-    sub "ю" "i"
+    sub "ю" "iu"
     sub "х" "h"
     sub "ш" "sh"
     sub "щ" "shch"
+    sub "ъ" "ie"
     sub "ц" "c"
     sub "ж" "zh"
     sub "ґ" "g"
-    sub "ў" ""
-    sub "ѫ" ""
+    sub "ғ" "gj"
+    sub "ў" "u"
+    sub "ѫ" "u"
+    sub "ѷ" "y"
     sub "ђ" "d"
     sub "ѕ" "dz"
     sub "ј" "j"
@@ -121,6 +163,7 @@ stage main {
     sub "џ" "dj"
     sub "є" "ie"
     sub "ї" "i"
+    sub "і" "i"
     sub "ѓ" "gj"
   }