unihan2 0.2.0 → 1.0.0

data/data/unicode-chars-ver.csv

@@ -111,6 +111,7 @@ cp1,cp2,age
 0616,061A,5.1
 061B,061B,1.1
 061C,061C,6.3
+061D,061D,14.0
 061E,061E,4.1
 061F,061F,1.1
 0620,0620,6.0
@@ -147,13 +148,16 @@ cp1,cp2,age
 0800,083E,5.2
 0840,085E,6.0
 0860,086A,10.0
+0870,089F,14.0
 08A0,08A0,6.1
 08A1,08A1,7.0
 08A2,08AC,6.1
 08AD,08B2,7.0
 08B3,08B4,8.0
+08B5,08B5,14.0
 08B6,08BD,9.0
 08BE,08C7,13.0
+08C8,08D2,14.0
 08D3,08D3,11.0
 08D4,08E2,9.0
 08E3,08E3,8.0
@@ -229,10 +233,12 @@ cp1,cp2,age
 0C05,0C33,1.1
 0C34,0C34,7.0
 0C35,0C39,1.1
+0C3C,0C3C,14.0
 0C3D,0C3D,5.1
 0C3E,0C56,1.1
 0C58,0C59,5.1
 0C5A,0C5A,8.0
+0C5D,0C5D,14.0
 0C60,0C61,1.1
 0C62,0C63,5.1
 0C66,0C6F,1.1
@@ -244,10 +250,13 @@ cp1,cp2,age
 0C84,0C84,11.0
 0C85,0CB9,1.1
 0CBC,0CBD,4.0
-0CBE,0CE1,1.1
+0CBE,0CD6,1.1
+0CDD,0CDD,14.0
+0CDE,0CE1,1.1
 0CE2,0CE3,5.0
 0CE6,0CEF,1.1
 0CF1,0CF2,5.0
+0CF3,0CF3,15.0
 0D00,0D00,10.0
 0D01,0D01,7.0
 0D02,0D03,1.1
@@ -294,7 +303,9 @@ cp1,cp2,age
 0EAC,0EAC,12.0
 0EAD,0EB9,1.1
 0EBA,0EBA,12.0
-0EBB,0EDD,1.1
+0EBB,0ECD,1.1
+0ECE,0ECE,15.0
+0ED0,0EDD,1.1
 0EDE,0EDF,6.1
 0F00,0F69,2.0
 0F6A,0F6A,3.0
@@ -373,12 +384,18 @@ cp1,cp2,age
 1677,167F,5.2
 1680,16F0,3.0
 16F1,16F8,7.0
-1700,1773,3.2
+1700,170C,3.2
+170D,170D,14.0
+170E,1714,3.2
+1715,171F,14.0
+1720,1773,3.2
 1780,17DC,3.0
 17DD,17DD,4.0
 17E0,17E9,3.0
 17F0,17F9,4.0
-1800,1877,3.0
+1800,180E,3.0
+180F,180F,14.0
+1810,1877,3.0
 1878,1878,11.0
 1880,18A9,3.0
 18AA,18AA,5.1
@@ -396,7 +413,11 @@ cp1,cp2,age
 1A20,1AAD,5.2
 1AB0,1ABE,7.0
 1ABF,1AC0,13.0
-1B00,1B7C,5.0
+1AC1,1ACE,14.0
+1B00,1B4B,5.0
+1B4C,1B4C,14.0
+1B50,1B7C,5.0
+1B7D,1B7E,14.0
 1B80,1BAA,5.1
 1BAB,1BAD,6.1
 1BAE,1BB9,5.1
@@ -417,6 +438,7 @@ cp1,cp2,age
 1DCB,1DE6,5.1
 1DE7,1DF5,7.0
 1DF6,1DF9,10.0
+1DFA,1DFA,14.0
 1DFB,1DFB,9.0
 1DFC,1DFC,6.0
 1DFD,1DFD,5.2
@@ -456,6 +478,7 @@ cp1,cp2,age
 20BB,20BD,7.0
 20BE,20BE,8.0
 20BF,20BF,10.0
+20C0,20C0,14.0
 20D0,20E1,1.1
 20E2,20E3,3.0
 20E4,20EA,3.2
@@ -591,7 +614,10 @@ cp1,cp2,age
 2BEC,2BEF,8.0
 2BF0,2BFE,11.0
 2BFF,2BFF,12.0
-2C00,2C5E,4.1
+2C00,2C2E,4.1
+2C2F,2C2F,14.0
+2C30,2C5E,4.1
+2C5F,2C5F,14.0
 2C60,2C6C,5.0
 2C6D,2C6F,5.1
 2C70,2C70,5.2
@@ -622,6 +648,7 @@ cp1,cp2,age
 2E4A,2E4E,11.0
 2E4F,2E4F,12.0
 2E50,2E52,13.0
+2E53,2E5D,14.0
 2E80,2FFB,3.0
 3000,3037,1.1
 3038,303A,3.0
@@ -677,6 +704,7 @@ cp1,cp2,age
 9FD6,9FEA,10.0
 9FEB,9FEF,11.0
 9FF0,9FFC,13.0
+9FFD,9FFF,14.0
 A000,A4A1,3.0
 A4A2,A4A3,3.2
 A4A4,A4B3,3.0
@@ -714,8 +742,12 @@ A7AF,A7AF,11.0
 A7B0,A7B1,7.0
 A7B2,A7B7,8.0
 A7B8,A7B9,11.0
-A7BA,A7C6,12.0
-A7C7,A7F6,13.0
+A7BA,A7BF,12.0
+A7C0,A7C1,14.0
+A7C2,A7C6,12.0
+A7C7,A7CA,13.0
+A7D0,A7F4,14.0
+A7F5,A7F6,13.0
 A7F7,A7F7,7.0
 A7F8,A7F9,6.1
 A7FA,A7FA,6.0
@@ -757,9 +789,15 @@ FB00,FB17,1.1
 FB1D,FB1D,3.0
 FB1E,FBB1,1.1
 FBB2,FBC1,6.0
-FBD3,FDFB,1.1
+FBC2,FBC2,14.0
+FBD3,FD3F,1.1
+FD40,FD4F,14.0
+FD50,FDC7,1.1
+FDCF,FDCF,14.0
+FDF0,FDFB,1.1
 FDFC,FDFC,3.2
 FDFD,FDFD,4.0
+FDFE,FDFF,14.0
 FE00,FE0F,3.2
 FE10,FE19,4.1
 FE20,FE23,1.1
@@ -799,7 +837,10 @@ FFFD,FFFD,1.1
 10428,1044D,3.1
 1044E,104A9,4.0
 104B0,104FB,9.0
-10500,10767,7.0
+10500,1056F,7.0
+10570,105BC,14.0
+10600,10767,7.0
+10780,107BA,14.0
 10800,1083F,4.0
 10840,1085F,5.2
 10860,108AF,7.0
@@ -826,12 +867,16 @@ FFFD,FFFD,1.1
 10D00,10D39,11.0
 10E60,10E7E,5.2
 10E80,10EB1,13.0
+10EFD,10EFF,15.0
 10F00,10F59,11.0
+10F70,10F89,14.0
 10FB0,10FCB,13.0
 10FE0,10FF6,12.0
 11000,1106F,6.0
+11070,11075,14.0
 1107F,1107F,7.0
 11080,110C1,5.2
+110C2,110C2,14.0
 110CD,110CD,11.0
 110D0,11143,6.1
 11144,11146,11.0
@@ -846,6 +891,7 @@ FFFD,FFFD,1.1
 111DB,111DF,8.0
 111E1,1123D,7.0
 1123E,1123E,9.0
+1123F,11241,15.0
 11280,112A9,8.0
 112B0,112F9,7.0
 11300,11300,8.0
@@ -866,10 +912,12 @@ FFFD,FFFD,1.1
 11660,1166C,9.0
 11680,116B7,6.1
 116B8,116B8,12.0
+116B9,116B9,14.0
 116C0,116C9,6.1
 11700,11719,8.0
 1171A,1171A,11.0
 1171D,1173F,8.0
+11740,11746,14.0
 11800,1183B,11.0
 118A0,118FF,7.0
 11900,11959,13.0
@@ -879,10 +927,13 @@ FFFD,FFFD,1.1
 11A86,11A9C,10.0
 11A9D,11A9D,11.0
 11A9E,11AA2,10.0
+11AB0,11ABF,14.0
 11AC0,11AF8,7.0
+11B00,11B09,15.0
 11C00,11CB6,9.0
 11D00,11D59,10.0
 11D60,11EF8,11.0
+11F00,11F59,15.0
 11FB0,11FB0,13.0
 11FC0,11FFF,12.0
 12000,1236E,5.0
@@ -893,11 +944,16 @@ FFFD,FFFD,1.1
 12470,12473,5.0
 12474,12474,7.0
 12480,12543,8.0
+12F90,12FF2,14.0
 13000,1342E,5.2
+1342F,1342F,15.0
 13430,13438,12.0
+13439,13455,15.0
 14400,14646,8.0
 16800,16A38,6.0
-16A40,16B8F,7.0
+16A40,16A6F,7.0
+16A70,16AC9,14.0
+16AD0,16B8F,7.0
 16E40,16E9A,11.0
 16F00,16F44,6.1
 16F45,16F4F,12.0
@@ -913,16 +969,24 @@ FFFD,FFFD,1.1
 187F2,187F7,12.0
 18800,18AF2,9.0
 18AF3,18D08,13.0
+1AFF0,1AFFE,14.0
 1B000,1B001,6.0
 1B002,1B11E,10.0
-1B150,1B167,12.0
+1B11F,1B122,14.0
+1B132,1B132,15.0
+1B150,1B152,12.0
+1B155,1B155,15.0
+1B164,1B167,12.0
 1B170,1B2FB,10.0
 1BC00,1BCA3,7.0
+1CF00,1CFC3,14.0
 1D000,1D126,3.1
 1D129,1D129,5.1
 1D12A,1D1DD,3.1
 1D1DE,1D1E8,8.0
+1D1E9,1D1EA,14.0
 1D200,1D245,4.1
+1D2C0,1D2D3,15.0
 1D2E0,1D2F3,11.0
 1D300,1D356,4.0
 1D360,1D371,5.0
@@ -935,8 +999,15 @@ FFFD,FFFD,1.1
 1D7CA,1D7CB,5.0
 1D7CE,1D7FF,3.1
 1D800,1DAAF,8.0
+1DF00,1DF1E,14.0
+1DF25,1DF2A,15.0
 1E000,1E02A,9.0
-1E100,1E2FF,12.0
+1E030,1E08F,15.0
+1E100,1E14F,12.0
+1E290,1E2AE,14.0
+1E2C0,1E2FF,12.0
+1E4D0,1E4F9,15.0
+1E7E0,1E7FE,14.0
 1E800,1E8D6,7.0
 1E900,1E94A,9.0
 1E94B,1E94B,12.0
@@ -1069,6 +1140,8 @@ FFFD,FFFD,1.1
 1F6D3,1F6D4,10.0
 1F6D5,1F6D5,12.0
 1F6D6,1F6D7,13.0
+1F6DC,1F6DC,15.0
+1F6DD,1F6DF,14.0
 1F6E0,1F6F3,7.0
 1F6F4,1F6F6,9.0
 1F6F7,1F6F8,10.0
@@ -1076,9 +1149,12 @@ FFFD,FFFD,1.1
 1F6FA,1F6FA,12.0
 1F6FB,1F6FC,13.0
 1F700,1F773,6.0
+1F774,1F77F,15.0
 1F780,1F7D4,7.0
 1F7D5,1F7D8,11.0
+1F7D9,1F7D9,15.0
 1F7E0,1F7EB,12.0
+1F7F0,1F7F0,14.0
 1F800,1F8AD,7.0
 1F8B0,1F8B1,13.0
 1F900,1F90B,10.0
@@ -1103,6 +1179,7 @@ FFFD,FFFD,1.1
 1F972,1F972,13.0
 1F973,1F976,11.0
 1F977,1F978,13.0
+1F979,1F979,14.0
 1F97A,1F97A,11.0
 1F97B,1F97B,12.0
 1F97C,1F97F,11.0
@@ -1120,6 +1197,7 @@ FFFD,FFFD,1.1
 1F9C1,1F9C2,11.0
 1F9C3,1F9CA,12.0
 1F9CB,1F9CB,13.0
+1F9CC,1F9CC,14.0
 1F9CD,1F9CF,12.0
 1F9D0,1F9E6,10.0
 1F9E7,1F9FF,11.0
@@ -1127,18 +1205,42 @@ FFFD,FFFD,1.1
 1FA60,1FA6D,11.0
 1FA70,1FA73,12.0
 1FA74,1FA74,13.0
-1FA78,1FA82,12.0
+1FA75,1FA77,15.0
+1FA78,1FA7A,12.0
+1FA7B,1FA7C,14.0
+1FA80,1FA82,12.0
 1FA83,1FA86,13.0
+1FA87,1FA88,15.0
 1FA90,1FA95,12.0
-1FA96,1FBF9,13.0
+1FA96,1FAA8,13.0
+1FAA9,1FAAC,14.0
+1FAAD,1FAAF,15.0
+1FAB0,1FAB6,13.0
+1FAB7,1FABA,14.0
+1FABB,1FABF,15.0
+1FAC0,1FAC2,13.0
+1FAC3,1FAC5,14.0
+1FACE,1FACF,15.0
+1FAD0,1FAD6,13.0
+1FAD7,1FAD9,14.0
+1FADA,1FADB,15.0
+1FAE0,1FAE7,14.0
+1FAE8,1FAE8,15.0
+1FAF0,1FAF6,14.0
+1FAF7,1FAF8,15.0
+1FB00,1FBF9,13.0
 20000,2A6D6,3.1
 2A6D7,2A6DD,13.0
+2A6DE,2A6DF,14.0
 2A700,2B734,5.2
+2B735,2B738,14.0
+2B739,2B739,15.0
 2B740,2B81D,6.0
 2B820,2CEA1,8.0
 2CEB0,2EBE0,10.0
 2F800,2FA1D,3.1
 30000,3134A,13.0
+31350,323AF,15.0
 E0001,E007F,3.1
 E0100,E01EF,4.0
 F0000,FFFFD,2.0

data/lib/unihan2/unicode-chars-ver.rb

@@ -0,0 +1,59 @@
+require 'nokogiri'
+require 'csv'
+
+class UnicodeCharsVer
+  # @param xml_file_in [String] input unicode xml file path, ex: "ucd.all.flat.xml"
+  # @param csv_file_out [String] csv file path for output
+  def convert(xml_file_in, csv_file_out)
+    print "parse xml..."
+    doc = File.open(xml_file_in) { |f| Nokogiri::XML(f) }
+    doc.remove_namespaces!
+    puts 'done.'
+
+    @rows = []
+    read_chars(doc)
+    
+    CSV.open(csv_file_out, 'wb', headers: true) do |csv|
+      csv << %w[cp1 cp2 age]
+      @rows.each do |row|
+        csv << [row[:cp1], row[:cp2], row[:age]]
+      end
+    end
+
+    true
+  end
+
+  private
+
+  def new_range(e)
+    @rows << { 
+      cp1: e.key?('cp') ? e['cp'] : e['first-cp'],
+      cp2: e.key?('cp') ? e['cp'] : e['last-cp'],
+      age: e['age']
+    }
+  end
+
+  def read_chars(doc)
+    doc.xpath('//char').each do |e|
+      if @rows.empty?
+        new_range(e)
+        next
+      end
+    
+      row = @rows.last
+      if e.key?('cp')
+        if e['age'] == row[:age]
+          row[:cp2] = e['cp']
+        else
+          new_range(e)
+        end
+      else
+        new_range(e)
+      end
+    end
+  end 
+end
+
+IN = '../13.0.0/ucd.all.flat.xml'
+OUT = '../out/unicode-chars-ver.csv'
+

data/lib/unihan2.rb

@@ -8,6 +8,12 @@ class Unihan2
     read_version
   end
 
+  # 將 Unicode XML 轉為 CSV, 內含 code range 的 unicode 版本
+  # @param xml_file_in [String] input unicode xml file path, ex: "ucd.all.flat.xml"
+  # @param csv_file_out [String] csv file path for output
+  def self.chars_ver(xml_file_in, csv_file_out)
+    UnicodeCharsVer.new.convert(xml_file_in, csv_file_out)
+  end
 
   # return total strokes of the character char
   # @param char [String] the character
@@ -17,7 +23,7 @@ class Unihan2
   end
 
   # return unicode version of specific character
-  # @param code [String] character or codepoing
+  # @param code [String] character or codepoint
   # @return [Float] unicode version
   def ver(code)
     return nil if code.nil?
@@ -36,7 +42,7 @@ class Unihan2
   private
 
   def read_strokes
-    fn = File.join(DATA_DIR, 'Unihan_DictionaryLikeData.txt')
+    fn = File.join(DATA_DIR, 'Unihan_IRGSources.txt')
     @strokes = {}
     File.foreach(fn) do |line|
       next if line.start_with? '#'
@@ -78,5 +84,6 @@ class Unihan2
       end
     end
   end
+end
 
-end
+require_relative 'unihan2/unicode-chars-ver'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unihan2
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Ray Chou
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-12-31 00:00:00.000000000 Z
+date: 2023-07-11 00:00:00.000000000 Z
 dependencies: []
 description: Unihan Database Utilities
 email: zhoubx@gmail.com
@@ -16,14 +16,16 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- data/Unihan_DictionaryLikeData.txt
+- data/README.md
+- data/Unihan_IRGSources.txt
 - data/unicode-chars-ver.csv
 - lib/unihan2.rb
+- lib/unihan2/unicode-chars-ver.rb
 homepage: https://github.com/RayCHOU/unihan2
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -38,8 +40,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
-signing_key: 
+rubygems_version: 3.4.14
+signing_key:
 specification_version: 4
 summary: Chinese
 test_files: []