interscript-maps 2.1.0a9 → 2.1.0b4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 787f7a3ee5db4f80a918eccb4946d7b6dc0b79a9b9dc0bdb7d5dbe2492418661
-  data.tar.gz: 5394992e449ef98b9fd1013ed96c89227a2386c96a968986949749d1090720e5
+  metadata.gz: 69e1d269e2f63895ec1cdeb7f11f7b9144a3124a3e419e0712d8aada527f78fa
+  data.tar.gz: 216967e0955d3cd194b3cee6b6e11822c5bce004844913ca1b87e66fd72bfc35
 SHA512:
-  metadata.gz: 86ac00b08f434be0192a6dc2af179e51b4df6b688644f78a40b4671c82de6ad0672954bf156477f7be677fb96ad417dce2ca8c63e47b01e3bcdb078403b4a2ca
-  data.tar.gz: 545f34e8f83bf57d77064b50f8089ceb5ae4a062b027f25aefe16bf208df354efc4764067cd3ab7c02b576d5c89a41797e441abeaab73fb85a4d88d6776755ed
+  metadata.gz: eabcf9c7e79c863094e24308325d5f97737eafb77ca76116c6cfc0359f3100385d9441451aaa86eac45305dc38260a7106dc60560c0827e70cffc41216f0e89d
+  data.tar.gz: 500b3dbb2d912a93de57874920cd77ff268d6d92b5cec1d7d0057c85fd824ffb119b442e6cefa3d49fa1c738afa46837cef049858f18e4988fb4c502d2f14488

data/interscript-maps.gemspec

@@ -1,4 +1,4 @@
-INTERSCRIPT_MAPS_VERSION="2.1.0a9"
+INTERSCRIPT_MAPS_VERSION="2.1.0b4"
 
 Gem::Specification.new do |spec|
   spec.name          = "interscript-maps"

data/maps/hk-yue-Hani-Latn-1888.imp

@@ -7,15 +7,16 @@ metadata {
   name: Hong Kong Government Cantonese Romanisation
   url: http://caes.hku.hk/hkjalonline/issues/download_the_file.php?f=2008_v11_1_kataoka__n__lee.pdf
   creation_date: 2020-01
-  description:
-    - This system is commonly used for the transliteration of place names or
-      person's names in Hong Kong, as pronounced in Cantonese. There will be more
-      than one legitimate transliteration for the same syllable, or sometimes even
-      for the same character. For example, the character 仔 can be transcribed as
-      Chai or Tsai in this system. Some of the choice is context-depenedent (e.g.
-      the same character in the place name 灣仔 is almost always Chai, but more likely
-      to be Tsai elsewhere). There will be more variations and unpredictabilities in
-      person's names, and these conventions need to be hard-coded.
+  description: |
+    This system is commonly used for the transliteration of place names or
+    person's names in Hong Kong, as pronounced in Cantonese. There will be more
+    than one legitimate transliteration for the same syllable, or sometimes even
+    for the same character. For example, the character 仔 can be transcribed as
+    Chai or Tsai in this system. Some of the choice is context-dependent (e.g.
+    the same character in the place name 灣仔 is almost always Chai, but more
+    likely to be Tsai elsewhere). There will be more variations and
+    unpredictable conversions in person's names, and these conventions need to
+    be hard-coded.
 
   notes:
     - Tone is not represented in this system.
@@ -27,10 +28,9 @@ metadata {
       distinctions were represented by ’ or diacritics (e.g. á vs. a), but were
       removed in printed / typeset documents.
 
-
-  #A longer test list will be generated from GeoNames database
 }
 
+# TODO: A longer test list will be generated from GeoNames database
 tests {
   test "煎魚灣", "Tsin Yue Wan"
   test "分流廟灣", "Fan Lau Miu Wan"

data/maps/iso-ara-Arab-Latn-233-1984.imp

@@ -38,7 +38,7 @@ metadata {
       غ is ġ instead of gh
       ة is ẗ instead of h/t
       ى is ỳ
-      ـِي is iy instead of iy
+      ـِي is iy instead of ī
       ـُو is uw instead of ū
       ـَا is a’ instead of ā
       ـَى is aỳ instead of á
@@ -55,7 +55,6 @@ tests {
 
 stage {
 
-
   # CHARACTERS
   parallel {
 
@@ -105,7 +104,6 @@ stage {
 
     # Shadda
 
-
     sub "\u0628\u0651", "bb" # ب
     sub "\u062a\u0651", "tt" # ت
     sub "\u062b\u0651", "ṯṯ" # ث
@@ -133,7 +131,6 @@ stage {
     sub "\u0648\u0651", "ww" # و
     sub "\u064a\u0651", "yy" # ي
 
-
     sub "\u0622", "’â" # آ
 
     sub "\u0627", "â" # ا
@@ -142,7 +139,6 @@ stage {
 
     sub "\u0626", "'" # ئ
 
-
     sub "\u0621", maybe("’") # ء# see note A
 
     sub "\u0623", "a" # أ

data/maps/iso-ara-Arab-Latn-233-2-1993.imp

@@ -0,0 +1,348 @@
+metadata {
+  authority_id: iso
+  id: 233-2-1993
+  language: iso-639-2:ara
+  source_script: Arab
+  destination_script: Latn
+  name: ISO 233-2:1993 Documentation — Transliteration of Arabic characters into Latin characters
+  url:
+    - https://www.iso.org/standard/4118.html
+    - https://cdn.standards.iteh.ai/samples/4118/2f03c828842c4055a5619c1bded39381/ISO-233-2-1993.pdf
+  creation_date: 1993-08
+  confirmation_date: 2018-06
+  description: |
+    Establishes a simplified system for the transliteration. This
+    simplification of the stringent rules established by ISO 233:1984
+    is especially intended to facilitate the processing of bibliographic
+    information (e.g. catalogues, indices, citations, etc.). Annex A
+    gives the diacritical signs used (taken from the code table of
+    ISO 5436:1983).
+  notes:
+    - |
+      4.1.1 In order to render a transliterated text more legible, the vowels
+      are supplied [method 2.1 c) of ISO 233:1984]. However sukün (`\u0652`) is
+      omitted, as well as the vowels and diphthongs which have only a flexional
+      function in nominal forms.
+
+    - |
+      4.1.2 The initial alif (`\u0627`) is not represented: the presence of an
+      initial vowel in the transliterated word is enough to indicate an alif in
+      the original script.
+
+    - |
+      4.1.3 A character bearing a hamzat (`\u0621`), which depends on the
+      vocalic context, is not represented.
+
+    - |
+      4.1.4 The definite article (`\u0627\u0644`), is always represented by the
+      characters “al-”, whatever its vocalization.
+
+    - |
+      4.1.5 The prepositions (li, bi, ka) as well as the conjunction wa, which
+      in Arabic are joined to the word, are separated by a hyphen in the
+      transliterated script.
+
+}
+
+tests {
+  test "مِصر", "Miṣr"
+  test "قَطَر", "Qaṭar"
+  test "الرِيَاض", "al-Riyāḍ"
+  test "الشارِقة", "al-Šâriqaẗ"
+  test "فِي نُورِ الْقَمَرِ", "Fī Nūr al-Qamar"
+  test "بِئْر", "Bi’r"
+  test "سَأَلَ", "Sa’al"
+  test "أَخْبَار", "Aẖbār"
+  test "قُرْآن", "Qur’ān"
+  test "آدَاب", "Ādāb"
+  test "الشَمْسُ", "al-Šams"
+  test "بِاللَيلِ", "bi-al-Layl"
+  test "لِلوَلَدِ", "li-l-Walad"
+}
+
+# Although this system inherits from iso-ara-Arab-Latn-233-1984,
+# it utilizes a set of simplified rules.
+# It is therefore easier to be implemented as a separate map instead
+# of using the inherit flag.
+# inherit: iso-ara-Arab-Latn-233-1984
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # pointing
+
+    # Table 2 No. 30
+    sub "\u064e", "a"                 # َ fatha
+    sub "\u064e", "", after: "\u0629" # َ fatha followed by ta' marboota
+
+    # Table 2, No. 31
+    sub "\u064f", "u"                 # ُ damma
+
+    # Table 2, No. 32
+    sub "\u0650", "i"                 # ِ kasra
+
+    # Table 3, No. 33
+    sub "\u0652", "" # ْ sokoon, see 4.1.1
+
+    # pointing omitted in the end of words
+    sub "\u064e" + boundary, ""                 # َ fatha
+    sub "\u064f" + boundary, ""                 # ُ damma
+    sub "\u0650" + boundary, ""                 # ِ kasra
+
+    # special pointed letters
+    sub "\u0639\u064e", "‘a"  # عَ
+    sub "\u0639\u0650", "‘i"  # عِ
+    sub "\u0639\u064f", "‘ū"  # عُ
+    # handle MacOS regex difference
+    sub "\u0639\u064f\u0648", "‘ū"  # عُو damma followed by و
+
+    sub "\u0650\u064a", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u064a\u0651\u064e", "iy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any("\u064e\u064f") # ـِي kasra followed by ي
+    sub "\u064e\u0627", "ā"  # ـَا fatha followed by ا
+    sub "\u064e\u0649", "aỳ"  # ـَى fatha followed by ى which is ا not ي
+    sub "\u064f\u0648", "ū"  # ـُو damma followed by و
+
+    # Table 2 No. 31, column 4
+    sub "\u064e\u0648\u0652", "aw"  # ـَوْ
+
+    # Table 2 No. 32, column 4
+    sub "\u064e\u064a\u0652", "ay"  # ـَيْ
+
+    # Table 1 No. 27a
+    # ta' marboota in iso-233-2-1993 is all the same `aẗ`
+    sub "\u0629", "aẗ" # ة in the middle of the sentence
+    # sub "\u0629", "ẗ" # ة
+
+    # Table 3, No. 34
+    # Shadda
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u062a\u0651", "tt" # ت
+    sub "\u062b\u0651", "ṯṯ" # ث
+    sub "\u062c\u0651", "ǧǧ" # ج
+    sub "\u062d\u0651", "ḥḥ" # ح
+    sub "\u062e\u0651", "ẖẖ" # خ
+    sub "\u062f\u0651", "dd" # د
+    sub "\u0630\u0651", "ḏḏ" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "šš" # ش
+    sub "\u0635\u0651", "ṣṣ" # ص
+    sub "\u0636\u0651", "ḍḍ" # ض
+    sub "\u0637\u0651", "ṭṭ" # ط
+    sub "\u0638\u0651", "ẓẓ" # ظ
+    sub "\u063a\u0651", "ġġ" # غ
+    sub "\u0641\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u0648\u0651", "ww" # و
+    sub "\u064a\u0651", "yy" # ي
+
+    sub "\u0627", "â"  # ا
+
+    sub "\u0649", "ỳ"  # ى
+
+    sub "\u0623", "’"  # أ
+    sub boundary + "\u0623", ""  # أ
+
+    # See 4.1.4
+    # '\uFE8E' : ''  # ﺎ
+
+    # Table 1 No. 3
+    sub "\u0628", "b" # ب
+    sub "\uFE91", "b" # ﺑ
+    sub "\uFE92", "b" # ﺒ
+    sub "\uFE90", "b" # ﺐ
+
+    # See note C
+    # Table 1 No. 4
+    sub "\u062a", "t" # ت
+    sub "\ufe97", "t" # ﺗ
+    sub "\ufe98", "t" # ﺘ
+    sub "\ufe96", "t" # ﺖ
+
+    # Table 1 No. 5
+    sub "\u062b", "ṯ" # ث
+    sub "\ufe9b", "ṯ" # ﺛ
+    sub "\ufe9c", "ṯ" # ﺜ
+    sub "\ufe9a", "ṯ" # ﺚ
+
+    # Table 1 No. 6
+    sub "\u062c", "ǧ" # ج
+    sub "\ufe9f", "ǧ" # ﺟ
+    sub "\ufea0", "ǧ" # ﺠ
+    sub "\ufe9e", "ǧ" # ﺞ
+
+    # Table 1 No. 7
+    sub "\u062d", "ḥ" # ح
+    sub "\ufea3", "ḥ" # ﺣ
+    sub "\ufea4", "ḥ" # ﺤ
+    sub "\ufea2", "ḥ" # ﺢ
+
+    # Table 1 No. 8
+    sub "\u062e", "ẖ" # خ
+    sub "\ufea7", "ẖ" # ﺧ
+    sub "\ufea8", "ẖ" # ﺨ
+    sub "\ufea6", "ẖ" # ﺦ
+
+    # Table 1 No. 9
+    sub "\u062f", "d" # د
+    sub "\ufeaa", "d" # ﺪ
+
+    # Table 1 No. 10
+    sub "\u0630", "ḏ" # ذ
+    sub "\ufeac", "ḏ" # ﺬ
+
+    # Table 1 No. 11
+    sub "\u0631", "r" # ر
+    sub "\ufeae", "r" # ﺮ
+
+    # Table 1 No. 12
+    sub "\u0632", "z" # ز
+    sub "\ufeb0", "z" # ﺰ
+
+    # Table 1 No. 13
+    sub "\u0633", "s" # س
+    sub "\ufeb3", "s" # ﺳ
+    sub "\ufeb4", "s" # ﺴ
+    sub "\ufeb2", "s" # ﺲ
+
+    # Table 1 No. 14
+    sub "\u0634", "š" # ش
+    sub "\ufeb7", "š" # ﺷ
+    sub "\ufeb8", "š" # ﺸ
+    sub "\ufeb6", "š" # ﺶ
+
+    # Table 1 No. 15
+    sub "\u0635", "ṣ" # ص
+    sub "\ufebb", "ṣ" # ﺻ
+    sub "\ufebc", "ṣ" # ﺼ
+    sub "\ufeba", "ṣ" # ﺺ
+
+    # Table 1 No. 16
+    sub "\u0636", "ḍ" # ض
+    sub "\ufebf", "ḍ" # ﺿ
+    sub "\ufec0", "ḍ" # ﻀ
+    sub "\ufebe", "ḍ" # ﺾ
+
+    # Table 1 No. 17
+    sub "\u0637", "ṭ" # ط
+    sub "\ufec3", "ṭ" # ﻃ
+    sub "\ufec4", "ṭ" # ﻄ
+    sub "\ufec2", "ṭ" # ﻂ
+
+    # Table 1 No. 18
+    sub "\u0638", "ẓ" # ظ
+    sub "\ufec7", "ẓ" # ﻇ
+    sub "\ufec8", "ẓ" # ﻈ
+    sub "\ufec6", "ẓ" # ﻆ
+
+    # Table 1 No. 19
+    sub "\u0639", "‘" # ع
+    sub "\ufecb", "‘" # ﻋ
+    sub "\ufecc", "‘" # ﻌ
+    sub "\ufeca", "‘" # ﻊ
+
+    # Table 1 No. 20
+    sub "\u063a", "ġ" # غ
+    sub "\ufecf", "ġ" # ﻏ
+    sub "\ufed0", "ġ" # ﻐ
+    sub "\ufece", "ġ" # ﻎ
+
+    # Table 1 No. 21
+    sub "\u0641", "f" # ف
+    sub "\ufed3", "f" # ﻓ
+    sub "\ufed4", "f" # ﻔ
+    sub "\ufed2", "f" # ﻒ
+    sub "\u06a2", "f" # ڢ Maghrebi form
+
+    # Table 1 No. 22
+    sub "\u0642", "q" # ق
+    sub "\ufed7", "q" # ﻗ
+    sub "\ufed8", "q" # ﻘ
+    sub "\ufed6", "q" # ﻖ
+    sub "\u06a8", "q" # ڧ Maghrebi form
+
+    # Table 1 No. 23
+    sub "\u0643", "k" # ك
+    sub "\ufedb", "k" # ﻛ
+    sub "\ufedc", "k" # ﻜ
+    sub "\ufeda", "k" # ﻚ
+
+    # Table 1 No. 24
+    sub "\u0644", "l" # ل
+    sub "\ufedf", "l" # ﻟ
+    sub "\ufee0", "l" # ﻠ
+    sub "\ufede", "l" # ﻞ
+
+    # Table 1 No. 25
+    sub "\u0645", "m" # م
+    sub "\ufee3", "m" # ﻣ
+    sub "\ufee4", "m" # ﻤ
+    sub "\ufee2", "m" # ﻢ
+
+    # Table 1 No. 26
+    sub "\u0646", "n" # ن
+    sub "\ufee7", "n" # ﻧ
+    sub "\ufee8", "n" # ﻨ
+    sub "\ufee6", "n" # ﻦ
+
+    # Table 1 No. 27
+    sub "\u0647", "h" # ه
+    sub "\ufeeb", "h" # ﻫ
+    sub "\ufeec", "h" # ﻬ
+    sub "\ufeea", "h" # ﻪ
+
+    # Table 1 No. 28
+    sub "\u0648", "w" # و
+    sub "\ufeee", "w" # ﻮ
+
+    # Table 1 No. 29
+    sub "\u064a", "y" # ي
+    sub "\ufef3", "y" # ﻳ
+    sub "\ufef4", "y" # ﻴ
+    sub "\ufef1", "y" # ﻱ
+
+    # Table 4 row 1
+    sub "\u060c", "," # ،
+
+    # Table 4 row 2
+    sub "\u061b", ";" # ؛
+
+    # Table 4 row 3
+    sub "\u061f", "?" # ؟
+
+    # 4.3 Notes to Tables
+    sub "\u0626", "’" # ئ
+
+    sub "\u0622", "’ā"  # آ
+
+    sub boundary + "\u0622", "ā"  # آ
+
+    # definite article
+
+    sub boundary + "\u0627\u0644", "al-" # ال
+
+    sub "\u0627\u0644", "al-", before: "\u0628\u0650" # بِال
+
+    sub boundary + "\u0628\u0650", "bi-", after: "\u0627\u0644" # بـِ
+
+    sub boundary + "\u0644\u0650\u0644", "li-l-" # لِل
+
+  }
+
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'")
+  # don't capitalize defined article in the middle of a sentence
+  sub "Al-", "al-" # ال
+  sub "Bi-", "bi-" # بِ
+  sub "Li-L-", "li-l-" # بِل
+}

data/maps/mvd-bel-Cyrl-Latn-2008.imp

@@ -86,14 +86,14 @@ tests {
 stage {
 
   # RULES
-  sub capture("\u2019\u0415"), "Je" # Е
-  sub capture("\u2019\u0435"), "je" # е
-  sub capture("\u2019\u0401"), "Jo" # Ë
-  sub capture("\u2019\u0451"), "jo" # ё
-  sub capture("\u2019\u042E"), "Ju" # Ю
-  sub capture("\u2019\u044E"), "ju" # ю
-  sub capture("\u2019\u042F"), "Ja" # Я
-  sub capture("\u2019\u044F"), "ja" # я
+  sub "\u2019\u0415", "Je" # Е
+  sub "\u2019\u0435", "je" # е
+  sub "\u2019\u0401", "Jo" # Ë
+  sub "\u2019\u0451", "jo" # ё
+  sub "\u2019\u042E", "Ju" # Ю
+  sub "\u2019\u044E", "ju" # ю
+  sub "\u2019\u042F", "Ja" # Я
+  sub "\u2019\u044F", "ja" # я
 
   sub "\u0415", "Je", before: any("АаЕеЁёИиОоУуЭэЮюЯяЬьЎў") # Е after vowels
   sub "\u0435", "je", before: any("АаЕеЁёИиОоУуЭэЮюЯяЬьЎў") # е after vowels

data/maps/mvd-bel-Cyrl-Latn-2010.imp

@@ -43,8 +43,9 @@ stage {
 
   # RULES
   # note[5]
-  sub "\u044C", ref( 1 ), before: any("ЗзЛлНнСсЦц") # ь after consonants
-  sub "\u02B9", ref( 1 ), before: any("ЗзЛлНнСсЦц") # Ь after consonants
+  # Those two are nonsense and harmful for reversibility
+  # sub "\u044C", ref( 1 ), before: any("ЗзЛлНнСсЦц") # ь after consonants
+  # sub "\u02B9", ref( 1 ), before: any("ЗзЛлНнСсЦц") # Ь after consonants
   # Й at end
   sub "\u0419" + line_end, "", before: any("ЕеЁёЫыЮюЯя") # Я after vowels
   sub "\u0439" + line_end, "", before: any("ЕеЁёЫыЮюЯя") # я after vowels

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: interscript-maps
 version: !ruby/object:Gem::Version
-  version: 2.1.0a9
+  version: 2.1.0b4
 platform: ruby
 authors:
 - Ribose Inc.
@@ -184,6 +184,7 @@ files:
 - maps/icao-srp-Cyrl-Latn-9303.imp
 - maps/icao-ukr-Cyrl-Latn-9303.imp
 - maps/iso-ara-Arab-Latn-233-1984.imp
+- maps/iso-ara-Arab-Latn-233-2-1993.imp
 - maps/iso-asm-Beng-Latn-15919-2001.imp
 - maps/iso-ben-Beng-Latn-15919-2001.imp
 - maps/iso-ell-Grek-Latn-843-1997-t1.imp