interscript-maps 2.4.2 → 2.5.0

data/maps/{un-ara-Arab-Latn-1971.imp → un-ara-Arab-Latn-1971.isc}

@@ -1,15 +1,16 @@
+system "UN:ara-Arab:Latn:1971" {
+
 metadata {
-  authority_id: un
-  id: 1971
-  language: iso-639-2:ara
-  source_script: Arab
-  destination_script: Latn
-  name: Romanization of Arabic -- Beirut system (1971)
-  url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
-  creation_date: 1971
-  confirmation_date: 2018-06
-  description: |
-    The current United Nations recommended romanization
+  authority_id un
+  id 1971
+  language iso-639-2:ara
+  source_script Arab
+  destination_script Latn
+  name Romanization of Arabic -- Beirut system (1971)
+  url https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
+  creation_date 1971
+  confirmation_date 2018-06
+  description {    The current United Nations recommended romanization
     system was approved in 2017 (resolution XI/3), based on
     the system adopted by Arabic experts at the conference
     held in Beirut in 2007, the Unified Arabic
@@ -53,85 +54,91 @@ metadata {
     letter sequences (dh, kh, sh, th) which may also point to
     combinations of Arabic characters in addition to the
     respective single characters.
-  notes:
-    - |
-      ث is t͟h (th with sub marcon)
-      خ is k͟h (kh with sub marcon)
-      ذ is d͟h (dh with sub marcon)
-      ش is s͟h (sh with sub marcon)
-      ظ is z͟h (zh with sub marcon)
-      غ is g͟h (gh witg sub marcon)
-      The previous UN 1972 System had the following differences:
-      the character (ظ) was romanized as z̧ instead of d͟h;
-      the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |
+  }
+  notes {
+    note "      ث is t͟h (th with sub marcon)\n      خ is k͟h (kh with sub marcon)\n      ذ is d͟h (dh with sub marcon)\n      ش is s͟h (sh with sub marcon)\n      ظ is z͟h (zh with sub marcon)\n      غ is g͟h (gh witg sub marcon)\n      The previous UN 1972 System had the following differences:\n      the character (ظ) was romanized as z̧ instead of d͟h;\n      the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |"
+  }
 }
 
 tests {
   # Examples taken from:
   # https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
   # page 31 (38 digital)
-  test "خَيبَر", "K͟haybar"
-  test "ظَهران", "Z͟hahrān"
-  test "القُدس", "Al Quds"
-  test "شَرم الشَيْخ", "S͟harm as͟h S͟hayk͟h"
+   "خَيبَر" ->  "K͟haybar"
+   "ظَهران" ->  "Z͟hahrān"
+   "القُدس" ->  "Al Quds"
+   "شَرم الشَيْخ" ->  "S͟harm as͟h S͟hayk͟h"
 }
 
-dependency "un-ara-Arab-Latn-2017", as: arablatn
+dependency "un-ara-Arab-Latn-2017" as arablatn
 
-stage {
+stage main {
 
 
   # CHARACTERS
   parallel {
 
     # sun letters
-    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "at͟h t͟h" # الث
-    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "ad͟h d͟h" # الذ
-    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "as͟h s͟h" # الش
-    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az͟h z͟h" # الظ
+    sub {
+    from boundary + "\u0627\u0644\u062b" + maybe("\u0651")
+    to "at͟h t͟h"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0630" + maybe("\u0651")
+    to "ad͟h d͟h"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0634" + maybe("\u0651")
+    to "as͟h s͟h"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0638" + maybe("\u0651")
+    to "az͟h z͟h"
+  }
 
     # shadda
-    sub "\u062e\u0651", "k͟hk͟h" # خ
-    sub "\u0630\u0651", "d͟hd͟h" # ذ
-    sub "\u0634\u0651", "s͟h" # ش
-    sub "\u0638\u0651", "z͟hz͟h" # ظ
-    sub "\u063a\u0651", "g͟hg͟h" # غ
-
-    sub "\u062b", "t͟h" # ث
-    sub "\ufe9b", "t͟h" # ﺛ
-    sub "\ufe9c", "t͟h" # ﺜ
-    sub "\ufe9a", "t͟h" # ﺚ
-
-    sub "\u062e", "k͟h" # خ
-    sub "\ufea7", "k͟h" # ﺧ
-    sub "\ufea8", "k͟h" # ﺨ
-    sub "\ufea6", "k͟h" # ﺦ
-
-    sub "\u063a", "g͟h" # غ
-    sub "\ufecf", "g͟h" # ﻏ
-    sub "\ufed0", "g͟h" # ﻐ
-    sub "\ufece", "g͟h" # ﻎ
-
-    sub "\u0630", "d͟h" # ذ
-    sub "\ufeac", "d͟h" # ﺬ
-
-    sub "\u0634", "s͟h" # ش
-    sub "\ufeb7", "s͟h" # ﺷ
-    sub "\ufeb8", "s͟h" # ﺸ
-    sub "\ufeb6", "s͟h" # ﺶ
-
-    sub "\u0638", "z͟h" # ظ
-    sub "\ufec7", "z͟h" # ﻇ
-    sub "\ufec8", "z͟h" # ﻈ
-    sub "\ufec6", "z͟h" # ﻆ
+    sub "\u062e\u0651" "k͟hk͟h"
+    sub "\u0630\u0651" "d͟hd͟h"
+    sub "\u0634\u0651" "s͟h"
+    sub "\u0638\u0651" "z͟hz͟h"
+    sub "\u063a\u0651" "g͟hg͟h"
+
+    sub "\u062b" "t͟h"
+    sub "\ufe9b" "t͟h"
+    sub "\ufe9c" "t͟h"
+    sub "\ufe9a" "t͟h"
+
+    sub "\u062e" "k͟h"
+    sub "\ufea7" "k͟h"
+    sub "\ufea8" "k͟h"
+    sub "\ufea6" "k͟h"
+
+    sub "\u063a" "g͟h"
+    sub "\ufecf" "g͟h"
+    sub "\ufed0" "g͟h"
+    sub "\ufece" "g͟h"
+
+    sub "\u0630" "d͟h"
+    sub "\ufeac" "d͟h"
+
+    sub "\u0634" "s͟h"
+    sub "\ufeb7" "s͟h"
+    sub "\ufeb8" "s͟h"
+    sub "\ufeb6" "s͟h"
+
+    sub "\u0638" "z͟h"
+    sub "\ufec7" "z͟h"
+    sub "\ufec8" "z͟h"
+    sub "\ufec6" "z͟h"
   }
 
-  run map.arablatn.stage.main
+  run  map.arablatn.stage.main
 
   # POSTRULES
-  sub " At͟h T͟h", " at͟h T͟h" # الث
-  sub " Ad͟h D͟h", " ad͟h D͟h" # الذ
-  sub " As͟h S͟h", " as͟h S͟h" # الش
-  sub " Az͟h Z͟h", " az͟h Z͟h" # الظ
+  sub " At͟h T͟h" " at͟h T͟h"
+  sub " Ad͟h D͟h" " ad͟h D͟h"
+  sub " As͟h S͟h" " as͟h S͟h"
+  sub " Az͟h Z͟h" " az͟h Z͟h"
 
 }
+}

data/maps/{un-ara-Arab-Latn-1972.imp → un-ara-Arab-Latn-1972.isc}

@@ -1,15 +1,16 @@
+system "UN:ara-Arab:Latn:1972" {
+
 metadata {
-  authority_id: un
-  id: 1972
-  language: iso-639-2:ara
-  source_script: Arab
-  destination_script: Latn
-  name: Romanization of Arabic -- UNGEGN (1972)
-  url: http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
-  creation_date: 1972
-  confirmation_date: 2018-06
-  description: |
-    The United Nations recommended romanization
+  authority_id un
+  id 1972
+  language iso-639-2:ara
+  source_script Arab
+  destination_script Latn
+  name Romanization of Arabic -- UNGEGN (1972)
+  url http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
+  creation_date 1972
+  confirmation_date 2018-06
+  description {    The United Nations recommended romanization
     system was approved in 1972 (resolution II/8),
     based on the system adopted by Arabic experts at
     the conference held at Beirut in 1971 with the
@@ -78,78 +79,87 @@ metadata {
     may also point to combinations of Arabic
     characters in addition to the respective single
     characters.
-  notes:
-    - |
-      The previous UN 1972 System had the following differences:
-      the character (ظ) was romanized as z̧ instead of d͟h;
-      ح, ص, ض the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |
-      When the definite article al precedes a word beginning with one of the "sun letters" (t,
-      th, d, dh, r, z, s, sh, ş, ḑ, ţ, z, l, n ̧ ) the l of the definite article is assimilated with the first
-      consonant of the word: ash-Sh الشارقة āriqah.
+  }
+  notes {
+    note "      The previous UN 1972 System had the following differences:\n      the character (ظ) was romanized as z̧ instead of d͟h;\n      ح, ص, ض the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |\n      When the definite article al precedes a word beginning with one of the \"sun letters\" (t,\n      th, d, dh, r, z, s, sh, ş, ḑ, ţ, z, l, n ̧ ) the l of the definite article is assimilated with the first\n      consonant of the word: ash-Sh الشارقة āriqah."
+  }
 }
 
 tests {
   # Examples taken from:
   # https://unstats.un.org/unsd/geoinfo/geonames/
-  test "مِصر", "Mişr"
-  test "قَطَر", "Qaţar"
-  test "الجُمهُورِيَّة العِراقِيَّة", "Al Jumhūrīyah al ‘Irāqīyah"
-  test "جُمهُورِيَّة مِصر العَرَبِيَّة", "Jumhūrīyat Mişr al ‘Arabīyah"
-  test "الرِيَاض", "Ar Riyāḑ"
-  test "الشارِقة", "Ash Shāriqah"
+   "مِصر" ->  "Mişr"
+   "قَطَر" ->  "Qaţar"
+   "الجُمهُورِيَّة العِراقِيَّة" ->  "Al Jumhūrīyah al ‘Irāqīyah"
+   "جُمهُورِيَّة مِصر العَرَبِيَّة" ->  "Jumhūrīyat Mişr al ‘Arabīyah"
+   "الرِيَاض" ->  "Ar Riyāḑ"
+   "الشارِقة" ->  "Ash Shāriqah"
+
+  # Note: UN card expects "Al" to be lowercase, but it would break other tests
+   "جَزيرة العَرَب" ->  "Jazyrat al ‘Arab"
 }
 
-dependency "un-ara-Arab-Latn-2017", as: arablatn
+dependency "un-ara-Arab-Latn-2017" as arablatn
 
-stage {
+stage main {
 
 
   # CHARACTERS
   parallel {
 
-    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
-    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḑ ḑ" # الض
-    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
-
-    sub "\u062d\u0651", "ḩḩ" # ح
-    sub "\u0635\u0651", "şş" # ص
-    sub "\u0636\u0651", "ḑḑ" # ض
-    sub "\u0637\u0651", "ţţ" # ط
-    sub "\u0638\u0651", "z̧z̧" # ظ
-
-    sub "\u062d", "ḩ" # ح
-    sub "\ufea3", "ḩ" # ﺣ
-    sub "\ufea4", "ḩ" # ﺤ
-    sub "\ufea2", "ḩ" # ﺢ
-
-    sub "\u0635", "ş" # ص
-    sub "\ufebb", "ş" # ﺻ
-    sub "\ufebc", "ş" # ﺼ
-    sub "\ufeba", "ş" # ﺺ
-
-    sub "\u0636", "ḑ" # ض
-    sub "\ufebf", "ḑ" # ﺿ
-    sub "\ufec0", "ḑ" # ﻀ
-    sub "\ufebe", "ḑ" # ﺾ
-
-    sub "\u0637", "ţ" # ط
-    sub "\ufec3", "ţ" # ﻃ
-    sub "\ufec4", "ţ" # ﻄ
-    sub "\ufec2", "ţ" # ﻂ
-
-    sub "\u0638", "z̧" # ظ
-    sub "\ufec7", "z̧" # ﻇ
-    sub "\ufec8", "z̧" # ﻈ
-    sub "\ufec6", "z̧" # ﻆ
+    sub {
+    from boundary + "\u0627\u0644\u0635" + maybe("\u0651")
+    to "aş ş"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0636" + maybe("\u0651")
+    to "aḑ ḑ"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0637" + maybe("\u0651")
+    to "aţ ţ"
+  }
+
+    sub "\u062d\u0651" "ḩḩ"
+    sub "\u0635\u0651" "şş"
+    sub "\u0636\u0651" "ḑḑ"
+    sub "\u0637\u0651" "ţţ"
+    sub "\u0638\u0651" "z̧z̧"
+
+    sub "\u062d" "ḩ"
+    sub "\ufea3" "ḩ"
+    sub "\ufea4" "ḩ"
+    sub "\ufea2" "ḩ"
+
+    sub "\u0635" "ş"
+    sub "\ufebb" "ş"
+    sub "\ufebc" "ş"
+    sub "\ufeba" "ş"
+
+    sub "\u0636" "ḑ"
+    sub "\ufebf" "ḑ"
+    sub "\ufec0" "ḑ"
+    sub "\ufebe" "ḑ"
+
+    sub "\u0637" "ţ"
+    sub "\ufec3" "ţ"
+    sub "\ufec4" "ţ"
+    sub "\ufec2" "ţ"
+
+    sub "\u0638" "z̧"
+    sub "\ufec7" "z̧"
+    sub "\ufec8" "z̧"
+    sub "\ufec6" "z̧"
   }
 
-  run map.arablatn.stage.main
+  run  map.arablatn.stage.main
 
   # POSTRULES
-  sub " Aş Ş", " aş Ş" # الص
-  sub " Aḑ Ḑ", " aḑ Ḑ" # الض
-  sub " Aţ Ţ", " aţ Ţ" # الط
+  sub " Aş Ş" " aş Ş"
+  sub " Aḑ Ḑ" " aḑ Ḑ"
+  sub " Aţ Ţ" " aţ Ţ"
 
 compose
 
 }
+}