interscript-maps 3.1.0 → 3.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bdc55bef9d08e9a879308411cdce2570ede10ff0fe986df258f6e6744b33778e
-  data.tar.gz: c3c026d26865c3827316ac82af260f57f20c30fb8bdf8d6b09a4e2c63081ceac
+  metadata.gz: 1b0ef91a3c4a9bb3e96e27ac51abfe7ae3190d47c55fd2d9dd869f5062bc8bcb
+  data.tar.gz: 2c920d0eb3509320d2018c92ee8538c4d73d2146013166b699076e1a4e20bac3
 SHA512:
-  metadata.gz: e11e930359276474cec3d169024b77553a9fcb8ea6427f5f68a3d0a1f4a8bb7a08c018406c3ced193c61715c709ef57bc2e48533fc6320489254dbcf8e03aab1
-  data.tar.gz: 673d8e940e3a622c19884cc16c7aad5e843dad05988d308f8b0b8bcda89e8c448b2b54c3b350f0bde278742d0df5e3dccbb4051437de822c88d0811992460b5f
+  metadata.gz: 3262737df76250886faee260292e9d5f8afbd37d198eed799b92272bf37c1d858e9c751cc1563ddc00c104456c506c7dc11969c320f8ba9417d394b68ef964f4
+  data.tar.gz: 55a888bea4db9f612c817e1df49d53da86fb51427789f92387808711be21859e9d934a6e0ddd0ab34a10ae6368d25d6a4415eb08d481519406b5080e9cc04846

data/interscript-maps.gemspec

@@ -1,4 +1,4 @@
-INTERSCRIPT_MAPS_VERSION = "3.1.0"
+INTERSCRIPT_MAPS_VERSION = "3.2.0"
 
 Gem::Specification.new do |spec|
   spec.name          = "interscript-maps"

data/libs/hebr-latn.isc

@@ -0,0 +1,84 @@
+system "hebr-latn" {
+
+# Shared ALA-LC Hebrew-script machinery: rows byte-identical between the
+# Ladino (alalc-lad-Hebr-Latn-2025) and Judeo-Arabic (alalc-jba-Hebr-Latn-2011)
+# romanization tables. The runs are split at every point where either map
+# carries a map-specific row, so each map splices the rulesets at its own
+# document positions; the two tables order he differently (Ladino before
+# bet/gimel/dalet, Judeo-Arabic after), so hebr_common_f is referenced on
+# either side of hebr_common_g.
+
+ruleset hebr_common_a {
+    # ALA-LC pe with geresh reads f in both the Ladino and the
+    # Judeo-Arabic tables
+    sub "פ׳" "f"
+    sub "ף׳" "f"
+}
+
+ruleset hebr_common_b {
+    # bet with dagesh (ligature and composed forms)
+    sub "בּ" "b"
+    sub "בּ" "b"
+}
+
+ruleset hebr_common_c {
+    # kaf with dagesh, including the final forms
+    sub "כּ" "k"
+    sub "כּ" "k"
+    sub "ךּ" "k"
+    sub "ךּ" "k"
+}
+
+ruleset hebr_common_d {
+    # tav with dagesh (ligature and composed forms)
+    sub "תּ" "t"
+    sub "תּ" "t"
+}
+
+ruleset hebr_common_e {
+    # shin with sin dot reads ś in both tables
+    sub "שׂ" "ś"
+    sub "שׂ" "ś"
+}
+
+ruleset hebr_common_f {
+    # pointless he reads h; the Ladino word-final -ah reading is a
+    # map-local row that runs before this
+    sub "ה" "h"
+}
+
+ruleset hebr_common_g {
+    # plain bet, gimel, dalet
+    sub "ב" "b"
+    sub "ג" "g"
+    sub "ד" "d"
+}
+
+ruleset hebr_common_h {
+    # zayin, het, tet
+    sub "ז" "z"
+    sub "ח" "ḥ"
+    sub "ט" "ṭ"
+}
+
+ruleset hebr_common_i {
+    # lamed, mem and nun (with their final forms), samekh
+    sub "ל" "l"
+    sub "מ" "m"
+    sub "ם" "m"
+    sub "נ" "n"
+    sub "ן" "n"
+    sub "ס" "s"
+}
+
+ruleset hebr_common_j {
+    # resh
+    sub "ר" "r"
+}
+
+ruleset hebr_common_k {
+    # tav
+    sub "ת" "t"
+}
+
+}

data/libs/jawi-latn.isc

@@ -0,0 +1,110 @@
+system "jawi-latn" {
+
+ruleset malay_jawi_common_a {
+    # Marked vowels (Vowels and Diphthongs rows)
+    sub "وُ" "u"
+    sub "وَ" "o"
+    sub "يِ" "i"
+    sub "يَ" "e"
+    # Rule 8 - hamzah
+    sub "ٴ" ""
+    # the high-hamza separator mark (rule 8b) is not represented
+    sub "أ" ""
+    # alef-hamza separator (rule 8b)
+    sub "ئ" ""
+    # yeh-hamza (rule 8b/8c; the elided vowel value is lexical)
+    sub "ؤ" "u"
+    # waw-hamza
+    sub {
+        from "ء"
+        to "k"
+        after boundary
+      }
+    # rule 8e word-final glottal stop
+    sub "ء" "ʼ"
+    # rule 8a Arabic reading
+    # Rule 5 - alif gantung: the superscript alif marks the final a of the
+    # word, which romanizes before the nasal it sits over (tiang); swap the
+    # mark order before the letters convert
+    sub "ڠٰ" "aڠ"
+    sub "ٰ" "a"
+    # Marks not represented (rule 11) and leftover vowel signs
+    sub "ْ" ""
+    sub "ّ" ""
+    sub "َ" ""
+    sub "ُ" ""
+    sub "ِ" ""
+    sub "ـ" ""
+    # Final-form yad (alef maksura codepoint) joins the yad rules
+    sub "ى" "ي"
+    # Letters of the alphabet (Malay values)
+    sub "ب" "b"
+    sub "ت" "t"
+    sub "ث" "s"
+    sub "ج" "j"
+    sub "چ" "c"
+    sub "ح" "h"
+    sub "خ" "kh"
+    sub "د" "d"
+    sub "ذ" "z"
+    sub "ر" "r"
+    sub "ز" "z"
+    sub "س" "s"
+    sub "ش" "sy"
+    sub "ص" "s"
+    sub "ض" "d"
+    sub "ط" "t"
+    sub "ظ" "z"
+    sub "ع" ""
+    sub "غ" "gh"
+    sub "ڠ" "ng"
+    sub "ف" "p"
+    sub "ق" "k"
+    sub "ڤ" "p"
+    sub "ك̇" "g"
+    sub "ک̇" "g"
+    sub "ك" "k"
+    sub "ک" "k"
+    sub "ل" "l"
+    sub "م" "m"
+    sub "ن" "n"
+    sub "ڽ" "ny"
+}
+
+ruleset malay_jawi_common_b {
+    sub "ه" "h"
+    sub "ة" "h"
+    # Rule 4 - bare alif as the vowel a
+    sub "ا" "a"
+    # Rule 7 - yad: word-initial and inter-vocalic y, else the vowel i
+    sub {
+        from boundary + "ي"
+        to "y"
+      }
+    sub {
+        from "ي"
+        to "y"
+        before any(["a", "e", "i", "o", "u"])
+        after any(["a", "e", "i", "o", "u"])
+      }
+    sub "ي" "i"
+    # Rule 6 - wau: word-initial and post-vocalic w, word-final and
+    # post-consonantal u
+    sub {
+        from boundary + "و"
+        to "w"
+      }
+    sub {
+        from "و"
+        to "u"
+        after boundary
+      }
+    sub {
+        from "و"
+        to "w"
+        before any(["a", "e", "i", "o", "u"])
+      }
+    sub "و" "u"
+}
+
+}

data/maps/alalc-jav-Arab-Latn-2012.isc

@@ -138,116 +138,18 @@ tests {
    "راماي" ->  "ramai"
 }
 
+dependency "jawi-latn" as jawi
+
 stage main {
+  use jawi.malay_jawi_common_a
+
   sequence {
-    # Marked vowels (Vowels and Diphthongs rows)
-    sub "وُ" "u"
-    sub "وَ" "o"
-    sub "يِ" "i"
-    sub "يَ" "e"
-
-    # Rule 8 - hamzah
-    sub "ٴ" ""  # the high-hamza separator mark (rule 8b) is not represented
-    sub "أ" ""  # alef-hamza separator (rule 8b)
-    sub "ئ" ""  # yeh-hamza (rule 8b/8c; the elided vowel value is lexical)
-    sub "ؤ" "u"  # waw-hamza
-    sub {
-    from "ء"
-    to "k"
-    after boundary
-  }  # rule 8e word-final glottal stop
-    sub "ء" "ʼ"  # rule 8a Arabic reading
-
-    # Rule 5 - alif gantung: the superscript alif marks the final a of the
-    # word, which romanizes before the nasal it sits over (tiang); swap the
-    # mark order before the letters convert
-    sub "ڠٰ" "aڠ"
-    sub "ٰ" "a"
-
-    # Marks not represented (rule 11) and leftover vowel signs
-    sub "ْ" ""
-    sub "ّ" ""
-    sub "َ" ""
-    sub "ُ" ""
-    sub "ِ" ""
-    sub "ـ" ""
-
-    # Final-form yad (alef maksura codepoint) joins the yad rules
-    sub "ى" "ي"
-
-    # Letters of the alphabet (Malay values)
-    sub "ب" "b"
-    sub "ت" "t"
-    sub "ث" "s"
-    sub "ج" "j"
-    sub "چ" "c"
-    sub "ح" "h"
-    sub "خ" "kh"
-    sub "د" "d"
-    sub "ذ" "z"
-    sub "ر" "r"
-    sub "ز" "z"
-    sub "س" "s"
-    sub "ش" "sy"
-    sub "ص" "s"
-    sub "ض" "d"
-    sub "ط" "t"
-    sub "ظ" "z"
-    sub "ع" ""
-    sub "غ" "gh"
-    sub "ڠ" "ng"
-    sub "ف" "p"
-    sub "ق" "k"
-    sub "ڤ" "p"
-    sub "ك̇" "g"
-    sub "ک̇" "g"
-    sub "ك" "k"
-    sub "ک" "k"
-    sub "ل" "l"
-    sub "م" "m"
-    sub "ن" "n"
-    sub "ڽ" "ny"
     sub "ڎ" "dh"
     sub "ڟ" "th"
     sub "ۏ" "v"
-    sub "ه" "h"
-    sub "ة" "h"
-
-    # Rule 4 - bare alif as the vowel a
-    sub "ا" "a"
-
-    # Rule 7 - yad: word-initial and inter-vocalic y, else the vowel i
-    sub {
-    from boundary + "ي"
-    to "y"
-  }
-    sub {
-    from "ي"
-    to "y"
-    before any(["a", "e", "i", "o", "u"])
-    after any(["a", "e", "i", "o", "u"])
-  }
-    sub "ي" "i"
-
-    # Rule 6 - wau: word-initial and post-vocalic w, word-final and
-    # post-consonantal u
-    sub {
-    from boundary + "و"
-    to "w"
-  }
-    sub {
-    from "و"
-    to "u"
-    after boundary
-  }
-    sub {
-    from "و"
-    to "w"
-    before any(["a", "e", "i", "o", "u"])
-  }
-    sub "و" "u"
   }
 
+  use jawi.malay_jawi_common_b
 }
 
 }

data/maps/alalc-jba-Hebr-Latn-2011.isc

@@ -155,71 +155,55 @@ tests {
   #   mechanical: ʼlṭywr)
 }
 
+dependency "hebr-latn" as hebr
+
 stage main {
-  parallel {
-    # Ligature alef-lamed
-    sub "ﭏ" "ʼl"
-
-    # Geresh-differentiated letters (note 3)
-    sub "ג׳" "ḡ"
-    sub "ד׳" "ḏ"
-    sub "פ׳" "f"
-    sub "ף׳" "f"
-    sub "צ׳" "ṣ̄"
-    sub "ץ׳" "ṣ̄"
-
-    # Dot-differentiated letters (note 3; kaf per note 12)
-    sub "גׄ" "g"
-    sub "ט̇" "ẓ"
-    sub "ה̈" "ḧ"
-    sub "כׄ" "k"
-
-    # Presentation and composed forms
-    sub "בּ" "b"
-    sub "בּ" "b"
-    sub "כּ" "k"
-    sub "כּ" "k"
-    sub "ךּ" "k"
-    sub "ךּ" "k"
-    sub "תּ" "t"
-    sub "תּ" "t"
-    sub "שׁ" "š"
-    sub "שׁ" "š"
-    sub "שׂ" "ś"
-    sub "שׂ" "ś"
-
-    # Doubled vav and yod (one-to-one consonant representation, note 1)
-    sub "וו" "ww"
-    sub "יי" "yy"
-
-    # Letters
-    sub "א" "ʼ"
-    sub "ב" "b"
-    sub "ג" "g"
-    sub "ד" "d"
-    sub "ה" "h"
-    sub "ו" "w"
-    sub "ז" "z"
-    sub "ח" "ḥ"
-    sub "ט" "ṭ"
-    sub "י" "y"
-    sub "כ" "k"
-    sub "ך" "k"
-    sub "ל" "l"
-    sub "מ" "m"
-    sub "ם" "m"
-    sub "נ" "n"
-    sub "ן" "n"
-    sub "ס" "s"
-    sub "ע" "‘"
-    sub "פ" "f"
-    sub "ף" "f"
-    sub "צ" "ṣ"
-    sub "ק" "q"
-    sub "ר" "r"
-    sub "ש" "š"
-    sub "ת" "t"
-  }
+  # Ligature alef-lamed
+  sub "ﭏ" "ʼl"
+
+  # Geresh-differentiated letters (note 3)
+  sub "ג׳" "ḡ"
+  sub "ד׳" "ḏ"
+  use hebr.hebr_common_a
+  sub "צ׳" "ṣ̄"
+  sub "ץ׳" "ṣ̄"
+
+  # Dot-differentiated letters (note 3; kaf per note 12)
+  sub "גׄ" "g"
+  sub "ט̇" "ẓ"
+  sub "ה̈" "ḧ"
+  sub "כׄ" "k"
+
+  # Presentation and composed forms
+  use hebr.hebr_common_b
+  use hebr.hebr_common_c
+  use hebr.hebr_common_d
+  sub "שׁ" "š"
+  sub "שׁ" "š"
+  use hebr.hebr_common_e
+
+  # Doubled vav and yod (one-to-one consonant representation, note 1)
+  sub "וו" "ww"
+  sub "יי" "yy"
+
+  # Letters
+  sub "א" "ʼ"
+  use hebr.hebr_common_g
+  use hebr.hebr_common_f
+  sub "ו" "w"
+  use hebr.hebr_common_h
+  sub "י" "y"
+  sub "כ" "k"
+  sub "ך" "k"
+  use hebr.hebr_common_i
+  sub "ע" "‘"
+  sub "פ" "f"
+  sub "ף" "f"
+  sub "צ" "ṣ"
+  sub "ק" "q"
+  use hebr.hebr_common_j
+  sub "ש" "š"
+  use hebr.hebr_common_k
 
 }
 

data/maps/alalc-lad-Hebr-Latn-2025.isc

@@ -152,141 +152,125 @@ tests {
   # - source: תּורה, expected: Torah (proper-noun capital)
 }
 
+dependency "hebr-latn" as hebr
+
 stage main {
-  sequence {
-    # 1. Clusters of yod and vav carrying point marks (the e/i and ey/yi
-    #    distinctions). Both logical and text-extraction byte orders are
-    #    covered for the marked double-yod clusters.
-    sub "ואִי" "wi"
-    sub "ייִ" "yi"
-    sub "יִי" "yi"
-    sub "ייֵ" "ey"
-    sub "יֵי" "ey"
-    sub "יִ" "i"
+  # 1. Clusters of yod and vav carrying point marks (the e/i and ey/yi
+  #    distinctions). Both logical and text-extraction byte orders are
+  #    covered for the marked double-yod clusters.
+  sub "ואִי" "wi"
+  sub "ייִ" "yi"
+  sub "יִי" "yi"
+  sub "ייֵ" "ey"
+  sub "יֵי" "ey"
+  sub "יִ" "i"
 
-    # 2. Geresh and rafe letter forms (rafé/geresh diacritics)
-    sub "ב׳" "v"
-    sub "בֿ" "v"
-    sub "ג׳" "j"
-    sub "גֿ" "j"
-    sub "ד׳" "dh"
-    sub "דֿ" "dh"
-    sub "ז׳" "zh"
-    sub "זֿ" "zh"
-    sub "פ׳" "f"
-    sub "ף׳" "f"
-    sub "פֿ" "f"
-    sub "ףֿ" "f"
+  # 2. Geresh and rafe letter forms (rafé/geresh diacritics)
+  sub "ב׳" "v"
+  sub "בֿ" "v"
+  sub "ג׳" "j"
+  sub "גֿ" "j"
+  sub "ד׳" "dh"
+  sub "דֿ" "dh"
+  sub "ז׳" "zh"
+  sub "זֿ" "zh"
+  use hebr.hebr_common_a
+  sub "פֿ" "f"
+  sub "ףֿ" "f"
 
-    # 3. Gimel with the superscript dot (ch)
-    sub "גׄ" "ch"
+  # 3. Gimel with the superscript dot (ch)
+  sub "גׄ" "ch"
 
-    # 4. Pointed vav (shuruq, holam) - presentation forms and composed
-    sub "וּ" "u"
-    sub "וּ" "u"
-    sub "וֹ" "o"
-    sub "וֹ" "o"
+  # 4. Pointed vav (shuruq, holam) - presentation forms and composed
+  sub "וּ" "u"
+  sub "וּ" "u"
+  sub "וֹ" "o"
+  sub "וֹ" "o"
 
-    # 5. Dagesh presentation forms and composed spellings
-    sub "בּ" "b"
-    sub "בּ" "b"
-    sub "גּ" "g"
-    sub "גּ" "g"
-    sub "דּ" "d"
-    sub "דּ" "d"
-    sub "כּ" "k"
-    sub "כּ" "k"
-    sub "ךּ" "k"
-    sub "ךּ" "k"
-    sub "פּ" "p"
-    sub "פּ" "p"
-    sub "תּ" "t"
-    sub "תּ" "t"
-    sub "שׂ" "ś"
-    sub "שׂ" "ś"
-    sub "ﭏ" "al"
+  # 5. Dagesh presentation forms and composed spellings
+  use hebr.hebr_common_b
+  sub "גּ" "g"
+  sub "גּ" "g"
+  sub "דּ" "d"
+  sub "דּ" "d"
+  use hebr.hebr_common_c
+  sub "פּ" "p"
+  sub "פּ" "p"
+  use hebr.hebr_common_d
+  use hebr.hebr_common_e
+  sub "ﭏ" "al"
 
-    # 6. Alef (general note 1): silent between adjacent matres and
-    #    word-initially before a vav/yod; a elsewhere. Word-final alef+he
-    #    carries the vowel cluster together (agwah: the alef is the a,
-    #    the he only h).
-    sub "אה" "ah"
-    sub {
+  # 6. Alef (general note 1): silent between adjacent matres and
+  #    word-initially before a vav/yod; a elsewhere. Word-final alef+he
+  #    carries the vowel cluster together (agwah: the alef is the a,
+  #    the he only h).
+  sub "אה" "ah"
+  sub {
     from "א"
     to ""
     before any("יו")
     after any("יו")
   }
-    sub {
+  sub {
     from boundary + "א"
     to ""
     after any("יו")
   }
-    sub "א" "a"
+  sub "א" "a"
 
-    # 7. He: word-final -ah (the row value), otherwise h (note 4, the
-    #    Hebrew-table reading of non-final he)
-    sub {
+  # 7. He: word-final -ah (the row value), otherwise h (note 4, the
+  #    Hebrew-table reading of non-final he)
+  sub {
     from "ה"
     to "ah"
     after boundary
   }
-    sub "ה" "h"
+  use hebr.hebr_common_f
 
-    # 8. Consonants with a single reading
-    sub "ב" "b"
-    sub "ג" "g"
-    sub "ד" "d"
-    sub "ז" "z"
-    sub "ח" "ḥ"
-    sub "ט" "ṭ"
-    sub "כ" "kh"
-    sub "ך" "kh"
-    sub "ל" "l"
-    sub "מ" "m"
-    sub "ם" "m"
-    sub "נ" "n"
-    sub "ן" "n"
-    sub "ס" "s"
-    sub "ע" "ʻ"
-    sub "פ" "p"
-    sub "ף" "p"
-    sub "צ" "ts"
-    sub "ץ" "ts"
-    sub "ק" "ḳ"
-    sub "ר" "r"
-    sub "ש" "sh"
-    sub "ת" "t"
+  # 8. Consonants with a single reading
+  use hebr.hebr_common_g
+  use hebr.hebr_common_h
+  sub "כ" "kh"
+  sub "ך" "kh"
+  use hebr.hebr_common_i
+  sub "ע" "ʻ"
+  sub "פ" "p"
+  sub "ף" "p"
+  sub "צ" "ts"
+  sub "ץ" "ts"
+  sub "ק" "ḳ"
+  use hebr.hebr_common_j
+  sub "ש" "sh"
+  use hebr.hebr_common_k
 
-    # 9. Double yod: ye before a consonant, y otherwise (note 3)
-    sub {
+  # 9. Double yod: ye before a consonant, y otherwise (note 3)
+  sub {
     from "יי"
     to "ye"
     after any("bcdfghjklmnpqrstvwxyz")
   }
-    sub "יי" "y"
+  sub "יי" "y"
 
-    # 10. Yod: word-initial consonant y, otherwise the vowel e (the
-    #     unmarked i quality is lexical, see notes)
-    sub {
+  # 10. Yod: word-initial consonant y, otherwise the vowel e (the
+  #     unmarked i quality is lexical, see notes)
+  sub {
     from boundary + "י"
     to "y"
   }
-    sub "י" "e"
+  sub "י" "e"
 
-    # 11. Vav: word-initial ṿ (note 4); consonantal w between a consonant
-    #     and a following vowel letter; otherwise the vowel o
-    sub {
+  # 11. Vav: word-initial ṿ (note 4); consonantal w between a consonant
+  #     and a following vowel letter; otherwise the vowel o
+  sub {
     from boundary + "ו"
     to "ṿ"
   }
-    sub {
+  sub {
     from "ו"
     to "w"
     after any(["a", "e", "i", "o", "u", "י", "ו"])
   }
-    sub "ו" "o"
-  }
+  sub "ו" "o"
 
 }
 

data/maps/alalc-vai-Vaii-Latn-2010.isc

@@ -56,6 +56,259 @@ tests {
   "ꗢ" -> "ɛ̃"
   "ꘋ" -> "ŋ"
   "ꔀꔤꕉꕱꖕꗡ" -> "eiaouɛ"
+
+# Exhaustive per-row tests for alalc-vai-Vaii-Latn-2010, generated from the source
+# document's table.
+# Source: ALA-LC Vai Romanization Table (2010), syllable grid pp. 1-2
+# (https://www.loc.gov/catdir/cpso/romanization/vai.pdf; local source
+# interscript-private-references/alalc/alalc-vai.pdf). Rows are in document
+# order: the grid's column streams, page 1 e i a o series then page 2 u
+# o-open e-open series, top-down within each column. Excludes the syllabic
+# lengthener U+A60C (an instruction, no romanization). The 'fi' ligature
+# glyph (U+FB01) in the PDF text layer is normalized to 'fi'; tilded vowels
+# are NFC-normalized.
+# Provenance artifact: scripts/row-sources/alalc-vai-Vaii-Latn-2010.json (240 rows).
+# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-12); regenerate from the artifact, do not hand-edit.
+  "ꔀ" -> "e"
+  "ꔁ" -> "ẽ"
+  "ꔂ" -> "he"
+  "ꔃ" -> "we"
+  "ꔄ" -> "wẽ"
+  "ꔅ" -> "pe"
+  "ꔆ" -> "be"
+  "ꔇ" -> "ɓe"
+  "ꔈ" -> "mɓe"
+  "ꔉ" -> "kpe"
+  "ꔊ" -> "mgbe"
+  "ꔋ" -> "gbe"
+  "ꔌ" -> "fe"
+  "ꔍ" -> "ve"
+  "ꔎ" -> "te"
+  "ꔐ" -> "de"
+  "ꔒ" -> "le"
+  "ꔓ" -> "re"
+  "ꔔ" -> "ɗe"
+  "ꔕ" -> "nɗe"
+  "ꔖ" -> "se"
+  "ꔘ" -> "ze"
+  "ꔚ" -> "che"
+  "ꔛ" -> "je"
+  "ꔜ" -> "nje"
+  "ꔝ" -> "ye"
+  "ꔞ" -> "ke"
+  "ꔟ" -> "ŋge"
+  "ꔠ" -> "ge"
+  "ꔡ" -> "me"
+  "ꔢ" -> "ne"
+  "ꔣ" -> "ɲe"
+  "ꔤ" -> "i"
+  "ꔥ" -> "ĩ"
+  "ꔦ" -> "hi"
+  "ꔧ" -> "hĩ"
+  "ꔨ" -> "wi"
+  "ꔩ" -> "wĩ"
+  "ꔪ" -> "pi"
+  "ꔫ" -> "bi"
+  "ꔬ" -> "ɓi"
+  "ꔭ" -> "mɓi"
+  "ꔮ" -> "kpi"
+  "ꔯ" -> "mgbi"
+  "ꔰ" -> "gbi"
+  "ꔱ" -> "fi"
+  "ꔲ" -> "vi"
+  "ꔳ" -> "ti"
+  "ꔵ" -> "di"
+  "ꔷ" -> "li"
+  "ꔸ" -> "ri"
+  "ꔹ" -> "ɗi"
+  "ꔺ" -> "nɗi"
+  "ꔻ" -> "si"
+  "ꔽ" -> "zi"
+  "ꔿ" -> "chi"
+  "ꕀ" -> "ji"
+  "ꕁ" -> "nji"
+  "ꕂ" -> "yi"
+  "ꕃ" -> "ki"
+  "ꕄ" -> "ŋgi"
+  "ꕅ" -> "gi"
+  "ꕆ" -> "mi"
+  "ꕇ" -> "ni"
+  "ꕈ" -> "ɲi"
+  "ꕉ" -> "a"
+  "ꕊ" -> "ã"
+  "ꕋ" -> "ŋã"
+  "ꕌ" -> "ha"
+  "ꕍ" -> "hã"
+  "ꕎ" -> "wa"
+  "ꕏ" -> "wã"
+  "ꕐ" -> "pa"
+  "ꕑ" -> "ba"
+  "ꕒ" -> "ɓa"
+  "ꕓ" -> "mɓa"
+  "ꕔ" -> "kpa"
+  "ꕕ" -> "kpã"
+  "ꕖ" -> "mgba"
+  "ꕗ" -> "gba"
+  "ꕘ" -> "fa"
+  "ꕙ" -> "va"
+  "ꕚ" -> "ta"
+  "ꕜ" -> "da"
+  "ꕞ" -> "la"
+  "ꕟ" -> "ra"
+  "ꕠ" -> "ɗa"
+  "ꕡ" -> "nɗa"
+  "ꕢ" -> "sa"
+  "ꕤ" -> "za"
+  "ꕦ" -> "cha"
+  "ꕨ" -> "ja"
+  "ꕧ" -> "nja"
+  "ꕩ" -> "ya"
+  "ꕪ" -> "ka"
+  "ꕫ" -> "kã"
+  "ꕬ" -> "ŋga"
+  "ꕭ" -> "ga"
+  "ꕮ" -> "ma"
+  "ꕯ" -> "na"
+  "ꕰ" -> "ɲa"
+  "ꕱ" -> "o"
+  "ꕲ" -> "õ"
+  "ꕳ" -> "ho"
+  "ꕴ" -> "wo"
+  "ꕵ" -> "wõ"
+  "ꕶ" -> "po"
+  "ꕷ" -> "bo"
+  "ꕸ" -> "ɓo"
+  "ꕹ" -> "mɓo"
+  "ꕺ" -> "kpo"
+  "ꕻ" -> "mgbo"
+  "ꕼ" -> "gbo"
+  "ꕽ" -> "fo"
+  "ꕾ" -> "vo"
+  "ꕿ" -> "to"
+  "ꖁ" -> "do"
+  "ꖃ" -> "lo"
+  "ꖄ" -> "ro"
+  "ꖅ" -> "ɗo"
+  "ꖆ" -> "nɗo"
+  "ꖇ" -> "so"
+  "ꖉ" -> "zo"
+  "ꖋ" -> "cho"
+  "ꖌ" -> "jo"
+  "ꖍ" -> "njo"
+  "ꖎ" -> "yo"
+  "ꖏ" -> "ko"
+  "ꖐ" -> "ŋgo"
+  "ꖑ" -> "go"
+  "ꖒ" -> "mo"
+  "ꖓ" -> "no"
+  "ꖔ" -> "ɲo"
+  "ꖕ" -> "u"
+  "ꖖ" -> "ũ"
+  "ꖗ" -> "hu"
+  "ꖘ" -> "hũ"
+  "ꖙ" -> "wu"
+  "ꖚ" -> "wũ"
+  "ꖛ" -> "pu"
+  "ꖜ" -> "bu"
+  "ꖝ" -> "ɓu"
+  "ꖞ" -> "mɓu"
+  "ꖟ" -> "kpu"
+  "ꖠ" -> "mgbu"
+  "ꖡ" -> "gbu"
+  "ꖢ" -> "fu"
+  "ꖣ" -> "vu"
+  "ꖤ" -> "tu"
+  "ꖦ" -> "du"
+  "ꖨ" -> "lu"
+  "ꖩ" -> "ru"
+  "ꖪ" -> "ɗu"
+  "ꖫ" -> "nɗu"
+  "ꖬ" -> "su"
+  "ꖮ" -> "zu"
+  "ꖰ" -> "chu"
+  "ꖱ" -> "ju"
+  "ꖲ" -> "nju"
+  "ꖳ" -> "yu"
+  "ꖴ" -> "ku"
+  "ꖵ" -> "ŋgu"
+  "ꖶ" -> "gu"
+  "ꖷ" -> "mu"
+  "ꖸ" -> "nu"
+  "ꖹ" -> "ɲu"
+  "ꘋ" -> "ŋ"
+  "ꖺ" -> "ɔ"
+  "ꖻ" -> "ɔ̃"
+  "ꖼ" -> "ŋɔ̃"
+  "ꖽ" -> "hɔ"
+  "ꖾ" -> "hɔ̃"
+  "ꖿ" -> "wɔ"
+  "ꗀ" -> "wɔ̃"
+  "ꗁ" -> "pɔ"
+  "ꗂ" -> "bɔ"
+  "ꗃ" -> "ɓɔ"
+  "ꗄ" -> "mɓɔ"
+  "ꗅ" -> "kpɔ"
+  "ꗆ" -> "mgbɔ"
+  "ꗇ" -> "gbɔ"
+  "ꗈ" -> "gbɔ̃"
+  "ꗉ" -> "fɔ"
+  "ꗊ" -> "vɔ"
+  "ꗋ" -> "tɔ"
+  "ꗍ" -> "dɔ"
+  "ꗏ" -> "lɔ"
+  "ꗐ" -> "rɔ"
+  "ꗑ" -> "ɗɔ"
+  "ꗒ" -> "nɗɔ"
+  "ꗓ" -> "sɔ"
+  "ꗕ" -> "zɔ"
+  "ꗗ" -> "chɔ"
+  "ꗘ" -> "jɔ"
+  "ꗙ" -> "njɔ"
+  "ꗚ" -> "yɔ"
+  "ꗛ" -> "kɔ"
+  "ꗜ" -> "ŋgɔ"
+  "ꗝ" -> "gɔ"
+  "ꗞ" -> "mɔ"
+  "ꗟ" -> "nɔ"
+  "ꗠ" -> "ɲɔ"
+  "ꗡ" -> "ɛ"
+  "ꗢ" -> "ɛ̃"
+  "ꗣ" -> "ŋɛ̃"
+  "ꗤ" -> "hɛ"
+  "ꗥ" -> "hɛ̃"
+  "ꗦ" -> "wɛ"
+  "ꗧ" -> "wɛ̃"
+  "ꗨ" -> "pɛ"
+  "ꗩ" -> "bɛ"
+  "ꗪ" -> "ɓɛ"
+  "ꗫ" -> "mɓɛ"
+  "ꗬ" -> "kpɛ"
+  "ꗭ" -> "kpɛ̃"
+  "ꗮ" -> "mgbɛ"
+  "ꗯ" -> "gbɛ"
+  "ꗰ" -> "gbɛ̃"
+  "ꗱ" -> "fɛ"
+  "ꗲ" -> "vɛ"
+  "ꗳ" -> "tɛ"
+  "ꗵ" -> "dɛ"
+  "ꗷ" -> "lɛ"
+  "ꗸ" -> "rɛ"
+  "ꗹ" -> "ɗɛ"
+  "ꗺ" -> "nɗɛ"
+  "ꗻ" -> "sɛ"
+  "ꗽ" -> "zɛ"
+  "ꗿ" -> "chɛ"
+  "ꘀ" -> "jɛ"
+  "ꘁ" -> "njɛ"
+  "ꘂ" -> "yɛ"
+  "ꘃ" -> "kɛ"
+  "ꘄ" -> "ŋgɛ"
+  "ꘅ" -> "ŋgɛ̃"
+  "ꘆ" -> "gɛ"
+  "ꘇ" -> "gɛ̃"
+  "ꘈ" -> "mɛ"
+  "ꘉ" -> "nɛ"
+  "ꘊ" -> "ɲɛ"
 }
 
 stage main {

data/maps/alalc-zsm-Arab-Latn-2011.isc

@@ -134,113 +134,11 @@ tests {
    "راماي" ->  "ramai"
 }
 
-stage main {
-  sequence {
-    # Marked vowels (Vowels and Diphthongs rows)
-    sub "وُ" "u"
-    sub "وَ" "o"
-    sub "يِ" "i"
-    sub "يَ" "e"
-
-    # Rule 8 - hamzah
-    sub "ٴ" ""  # the high-hamza separator mark (rule 8b) is not represented
-    sub "أ" ""  # alef-hamza separator (rule 8b)
-    sub "ئ" ""  # yeh-hamza (rule 8b/8c; the elided vowel value is lexical)
-    sub "ؤ" "u"  # waw-hamza
-    sub {
-    from "ء"
-    to "k"
-    after boundary
-  }  # rule 8e word-final glottal stop
-    sub "ء" "ʼ"  # rule 8a Arabic reading
-
-    # Rule 5 - alif gantung: the superscript alif marks the final a of the
-    # word, which romanizes before the nasal it sits over (tiang); swap the
-    # mark order before the letters convert
-    sub "ڠٰ" "aڠ"
-    sub "ٰ" "a"
-
-    # Marks not represented (rule 11) and leftover vowel signs
-    sub "ْ" ""
-    sub "ّ" ""
-    sub "َ" ""
-    sub "ُ" ""
-    sub "ِ" ""
-    sub "ـ" ""
-
-    # Final-form yad (alef maksura codepoint) joins the yad rules
-    sub "ى" "ي"
-
-    # Letters of the alphabet (Malay values)
-    sub "ب" "b"
-    sub "ت" "t"
-    sub "ث" "s"
-    sub "ج" "j"
-    sub "چ" "c"
-    sub "ح" "h"
-    sub "خ" "kh"
-    sub "د" "d"
-    sub "ذ" "z"
-    sub "ر" "r"
-    sub "ز" "z"
-    sub "س" "s"
-    sub "ش" "sy"
-    sub "ص" "s"
-    sub "ض" "d"
-    sub "ط" "t"
-    sub "ظ" "z"
-    sub "ع" ""
-    sub "غ" "gh"
-    sub "ڠ" "ng"
-    sub "ف" "p"
-    sub "ق" "k"
-    sub "ڤ" "p"
-    sub "ك̇" "g"
-    sub "ک̇" "g"
-    sub "ك" "k"
-    sub "ک" "k"
-    sub "ل" "l"
-    sub "م" "m"
-    sub "ن" "n"
-    sub "ڽ" "ny"
-    sub "ه" "h"
-    sub "ة" "h"
-
-    # Rule 4 - bare alif as the vowel a
-    sub "ا" "a"
-
-    # Rule 7 - yad: word-initial and inter-vocalic y, else the vowel i
-    sub {
-    from boundary + "ي"
-    to "y"
-  }
-    sub {
-    from "ي"
-    to "y"
-    before any(["a", "e", "i", "o", "u"])
-    after any(["a", "e", "i", "o", "u"])
-  }
-    sub "ي" "i"
-
-    # Rule 6 - wau: word-initial and post-vocalic w, word-final and
-    # post-consonantal u
-    sub {
-    from boundary + "و"
-    to "w"
-  }
-    sub {
-    from "و"
-    to "u"
-    after boundary
-  }
-    sub {
-    from "و"
-    to "w"
-    before any(["a", "e", "i", "o", "u"])
-  }
-    sub "و" "u"
-  }
+dependency "jawi-latn" as jawi
 
+stage main {
+  use jawi.malay_jawi_common_a
+  use jawi.malay_jawi_common_b
 }
 
 }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: interscript-maps
 version: !ruby/object:Gem::Version
-  version: 3.1.0
+  version: 3.2.0
 platform: ruby
 authors:
 - Ribose Inc.
@@ -20,6 +20,8 @@ files:
 - README.adoc
 - interscript-maps.gemspec
 - interscript-maps.yaml
+- libs/hebr-latn.isc
+- libs/jawi-latn.isc
 - libs/posix.iml
 - libs/posix.isc
 - libs/thai-latn.isc