interscript-maps 2.5.1 → 3.0.0

data/maps/un-ara-Arab-Latn-2017.isc

@@ -66,6 +66,9 @@ metadata {
 }
 
 tests {
+   "بِيَا" ->  "Biyā"
+   "مَدِينَة" ->  "Madīnah"
+   "الْمَدِينَة" ->  "Al Madīnah"
   # Examples taken from:
   # https://unstats.un.org/unsd/geoinfo/geonames/
    "مِصر" ->  "Mis̱r"
@@ -87,6 +90,12 @@ tests {
    "الرِيَاض" ->  "Ar Riyāḏ"
 }
 
+aliases {
+  # every character of the Arabic block U+0600..U+06FF (letters, harakat,
+  # marks) — used by the ta' marboota lookbehind chains below
+  arab_block = any('؀؁؂؃؄؅؆؇؈؉؊؋،؍؎؏ؘؙؚؐؑؒؓؔؕؖؗ؛؜؝؞؟ؠءآأؤإئابةتثجحخدذرزسشصضطظعغػؼؽؾؿـفقكلمنهوىيًٌٍَُِّْٕٖٜٟٓٔٗ٘ٙٚٛٝٞ٠١٢٣٤٥٦٧٨٩٪٫٬٭ٮٯٰٱٲٳٴٵٶٷٸٹٺٻټٽپٿڀځڂڃڄڅچڇڈډڊڋڌڍڎڏڐڑڒړڔڕږڗژڙښڛڜڝڞڟڠڡڢڣڤڥڦڧڨکڪګڬڭڮگڰڱڲڳڴڵڶڷڸڹںڻڼڽھڿۀہۂۃۄۅۆۇۈۉۊۋیۍێۏېۑےۓ۔ەۖۗۘۙۚۛۜ۝۞ۣ۟۠ۡۢۤۥۦۧۨ۩۪ۭ۫۬ۮۯ۰۱۲۳۴۵۶۷۸۹ۺۻۼ۽۾ۿ')
+}
+
 stage main {
   # CHARACTERS
   parallel {
@@ -120,6 +129,7 @@ stage main {
 
     sub "\u0650\u064a" "ī"
     sub "\u0650\u064a\u0651\u064e" "īy"
+    sub "\u0650\u064a\u064e\u0627" "iyā"
     sub {
     from "\u0650\u064a"
     to "iy"
@@ -193,72 +203,176 @@ stage main {
     to "an n"
   }
 
-    # TODO: shorten this fragment
-    # ta' marboota
-    sub "\u0629" "at"
+    # ta' marboota (footnote C: romanized h, except in the construct form
+    # of feminine nouns, where it is romanized t; a preceding fatha already
+    # carries its own "a"):
+    #   word-final: ah (fatha+ah when vocalized)
+    sub {
+    from "\u064e\u0629" + line_end
+    to "ah"
+  }
     sub {
     from "\u0629" + line_end
     to "ah"
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
   }
     sub {
     from "\u0629"
     to "ah"
-    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u064e\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    sub {
+    from "\u0629"
+    to "ah"
+    before "\u0627\u0644" + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block + arab_block
+  }
+    #   construct form (default):
+    sub {
+    from "\u064e\u0629"
+    to "at"
+  }
+    sub {
+    from "\u0629"
+    to "at"
   }
 
     # shadda

data/maps/un-asm-Beng-Latn-1972.isc

@@ -38,10 +38,18 @@ metadata {
      note "       ৃ Exceptions: হৃ hṛ."
      note "       ্‌  Pronunciation without a vowel; special form: ৎ t."
      note "       Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya."
+    note "Diffed against the UN Romanization of Assamese for Geographical Names table\n as published in the WGRS Report on the Current Status of UN Romanization Systems\n for Geographical Names, version 4.0 (February 2013) (eki.ee/wgrs/rom1_as.htm;\n also unstats wgrr4assamese): all 11 independent vowels, 11 vowel signs, 3 other\n symbols, 34 consonants and the dotted variants verified. The ligature section\n is shared with Bengali (rom1_bn)."
+
+    note "Fixed against the source: the decomposed dotted variant ঢ় (U+09A2 U+09BC)\n rendered ya; source footnote A gives ṙha for ঢ় (corrected)."
   }
+
 }
 
 tests {
+   "ঢ়" ->  "ṙha"
+   "ড়" ->  "ṙa"
+   "য়" ->  "ya"
+   "ৱ" ->  "va"
    "অসমীয়া কবিতা" ->  "asamīyā kabitā"
    "কবিৰ আজি জন্মদিন" ->  "kabira āji janmadina"
    "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড" ->  "beruṭata emāhara pāchhate punara bhayaṁkara agnikāṇḍa"
@@ -338,7 +346,7 @@ stage main {
     sub "য়" "ya"
     sub "য়" "ya"
     sub "ড়" "ṙa"
-    sub "ঢ়" "ya"
+    sub "ঢ়" "ṙha"
   }
 
   compose

data/maps/un-bel-Cyrl-Latn-2007.isc

@@ -20,6 +20,13 @@ metadata {
     approved by the Decree of the Council of Ministers of the Republic of Belarus dated July 29, 2006
     No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
   }
+  notes {
+    note "Diffed against the Romanization of Belarusian for Geographical Names\n table as published in the WGRS Report on the Current Status of UN Romanization\n Systems for Geographical Names, version 4.0 (February 2013)\n (eki.ee/wgrs/rom1_be.htm; also unstats wgrr4belarusian): all 33 rows verified.\n The map's edition claim (national system adopted 11 June 2007, State Committee\n on Property resolution No. 38; presented as E/CONF.98/CRP.21) is the same table\n the UN approved in 2012 (X/6); no newer edition exists in the reference library."
+
+    note "The apostrophe of row 28, printed ’ (U+2019), is not romanized; the map\n now deletes U+2019 alongside the ASCII apostrophe (U+0027)."
+
+    note "Ь is romanized with a combining acute on the preceding letter only in the\n six combinations listed in the source footnote (дзь→dź, зь→ź, ль→ĺ, нь→ń,\n сь→ś, ць→ć), encoded by the dependency's digraph rows; an ь outside these\n combinations has no source equivalent and is dropped."
+  }
 }
 
 tests {
@@ -69,6 +76,11 @@ tests {
    "Баяры" ->  "Bajary"
    "Валяр'яны" ->  "Valiarjany"
    "Вязынка" ->  "Viazynka"
+   "Вераб’ёвічы" ->  "Vierabjovičy"
+   "сь" ->  "ś"
+   "ль" ->  "ĺ"
+   "ць" ->  "ć"
+   "дзь" ->  "dź"
 }
 
 dependency "by-bel-Cyrl-Latn-2007" as cyrllatn
@@ -77,5 +89,10 @@ stage main {
 
   run  map.cyrllatn.stage.main
 
+  parallel {
+    # row 28: ’ (U+2019) is not romanized
+    sub "’" ""
+  }
+
 }
 }