character_set 1.2.0 → 1.3.0

data/ext/character_set/unicode_casefold_table.h.tmpl

@@ -0,0 +1,11 @@
+// THIS FILE IS GENERATED BY $ rake sync_casefold_data - DO NOT EDIT
+// -*-C-*-
+
+typedef struct casefold_mapping {
+  unsigned long from;
+  unsigned long to;
+} casefold_mapping;
+
+#define CASEFOLD_COUNT 0
+
+static const casefold_mapping unicode_casefold_table[CASEFOLD_COUNT] = {};

data/lib/character_set/core_ext/string_ext.rb

@@ -6,11 +6,13 @@ class CharacterSet
       end
 
       {
+        count_by_character_set:    :count_in,
         covered_by_character_set?: :cover?,
         delete_character_set:      :delete_in,
         delete_character_set!:     :delete_in!,
         keep_character_set:        :keep_in,
         keep_character_set!:       :keep_in!,
+        scan_by_character_set:     :scan,
         uses_character_set?:       :used_by?,
       }.each do |string_method, set_method|
         class_eval <<-RUBY, __FILE__, __LINE__ + 1

data/lib/character_set/expression_converter.rb

@@ -26,34 +26,28 @@ class CharacterSet
 
       when Regexp::Expression::CharacterSet::Range
         start, finish = expression.map { |subexp| convert(subexp) }
-        CharacterSet.from_ranges((start.min)..(finish.max))
+        CharacterSet.new((start.min)..(finish.max))
 
       when Regexp::Expression::CharacterType::Any
         CharacterSet.unicode
 
-      when Regexp::Expression::CharacterType::Digit
-        CharacterSet.from_ranges(48..57)
-
-      when Regexp::Expression::CharacterType::NonDigit
-        CharacterSet.from_ranges(48..57).inversion
-
-      when Regexp::Expression::CharacterType::Hex
-        CharacterSet.from_ranges(48..57, 65..70, 97..102)
-
-      when Regexp::Expression::CharacterType::NonHex
-        CharacterSet.from_ranges(48..57, 65..70, 97..102).inversion
-
-      when Regexp::Expression::CharacterType::Space
-        CharacterSet["\t", "\n", "\v", "\f", "\r", "\x20"]
-
-      when Regexp::Expression::CharacterType::NonSpace
-        CharacterSet["\t", "\n", "\v", "\f", "\r", "\x20"].inversion
-
-      when Regexp::Expression::CharacterType::Word
-        CharacterSet.from_ranges(48..57, 65..90, 95..95, 97..122)
-
-      when Regexp::Expression::CharacterType::NonWord
-        CharacterSet.from_ranges(48..57, 65..90, 95..95, 97..122).inversion
+      when Regexp::Expression::CharacterType::Base
+        /(?<negative>non)?(?<base_name>.+)/ =~ expression.token
+        content =
+          if expression.unicode_classes?
+            # in u-mode, type shortcuts match the same as \p{<long type name>}
+            CharacterSet.of_property(base_name)
+          else
+            # in normal mode, types match only ascii chars
+            case base_name.to_sym
+            when :digit then CharacterSet.from_ranges(48..57)
+            when :hex   then CharacterSet.from_ranges(48..57, 65..70, 97..102)
+            when :space then CharacterSet.from_ranges(9..13, 32..32)
+            when :word  then CharacterSet.from_ranges(48..57, 65..90, 95..95, 97..122)
+            else raise Error, "Unsupported CharacterType #{base_name}"
+            end
+          end
+        negative ? content.inversion : content
 
       when Regexp::Expression::EscapeSequence::CodepointList
         CharacterSet.new(expression.codepoints)
@@ -93,6 +87,9 @@ class CharacterSet
       when Regexp::Expression::UnicodeProperty::Base,
            Regexp::Expression::PosixClass
         content = CharacterSet.of_property(expression.token)
+        if expression.type == :posixclass && expression.ascii_classes?
+          content = content.ascii_part
+        end
         expression.negative? ? content.inversion : content
 
       when Regexp::Expression::Base

data/lib/character_set/predefined_sets.rb

@@ -1,266 +1,31 @@
 class CharacterSet
   module PredefinedSets
-    def ascii
-      @ascii ||= from_ranges(0..0x7F).freeze
-    end
-
-    def ascii_alnum
-      @ascii_alnum ||= from_ranges(0x30..0x39, 0x41..0x5A, 0x61..0x7A).freeze
-    end
-
-    def ascii_letters
-      @ascii_letters ||= from_ranges(0x41..0x5A, 0x61..0x7A).freeze
-    end
-
-    # basic multilingual plane
-    def bmp
-      @bmp ||= from_ranges(0..0xD7FF, 0xE000..0xFFFF).freeze
-    end
-
-    # ./0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
-    def crypt
-      @crypt ||= from_ranges(0x2E..0x5A, 0x61..0x7A).freeze
-    end
-
-    def newline
-      @newline ||= from_ranges(0xA..0xD, 0x85..0x85, 0x2028..0x2029).freeze
-    end
-
-    def unicode
-      @unicode ||= from_ranges(0..0xD7FF, 0xE000..0x10FFFF).freeze
-    end
-
-    def url_fragment
-      @url_fragment ||= from_ranges(
-        0x21..0x21,
-        0x24..0x24,
-        0x26..0x3B,
-        0x3D..0x3D,
-        0x3F..0x5A,
-        0x5F..0x5F,
-        0x61..0x7A,
-        0x7E..0x7E
-      ).freeze
-    end
-
-    def url_host
-      @url_host ||= from_ranges(
-        0x21..0x21,
-        0x24..0x24,
-        0x26..0x2E,
-        0x30..0x3B,
-        0x3D..0x3D,
-        0x41..0x5B,
-        0x5D..0x5D,
-        0x5F..0x5F,
-        0x61..0x7A,
-        0x7E..0x7E
-      ).freeze
-    end
-
-    def url_path
-      @url_path ||= from_ranges(
-        0x21..0x21,
-        0x24..0x3A,
-        0x3D..0x3D,
-        0x40..0x5A,
-        0x5F..0x5F,
-        0x61..0x7A,
-        0x7E..0x7E
-      ).freeze
-    end
-
-    def url_query
-      @url_query ||= from_ranges(
-        0x21..0x21,
-        0x24..0x24,
-        0x26..0x3B,
-        0x3D..0x3D,
-        0x3F..0x5A,
-        0x5F..0x5F,
-        0x61..0x7A,
-        0x7E..0x7E
-      ).freeze
-    end
-
-    def whitespace
-      @whitespace ||= from_ranges(
-        0x9..0x9,
-        0xA..0xD,
-        0x20..0x20,
-        0x85..0x85,
-        0xA0..0xA0,
-        0x1680..0x1680,
-        0x180E..0x180E,
-        0x2000..0x200A,
-        0x2028..0x2029,
-        0x202F..0x202F,
-        0x205F..0x205F,
-        0x3000..0x3000
-      ).freeze
-    end
-
-    def emoji
-      @emoji ||= from_ranges(
-        0x23..0x23,
-        0x2A..0x2A,
-        0x30..0x39,
-        0xA9..0xA9,
-        0xAE..0xAE,
-        0x203C..0x203C,
-        0x2049..0x2049,
-        0x2122..0x2122,
-        0x2139..0x2139,
-        0x2194..0x2199,
-        0x21A9..0x21AA,
-        0x231A..0x231B,
-        0x2328..0x2328,
-        0x23CF..0x23CF,
-        0x23E9..0x23F3,
-        0x23F8..0x23FA,
-        0x24C2..0x24C2,
-        0x25AA..0x25AB,
-        0x25B6..0x25B6,
-        0x25C0..0x25C0,
-        0x25FB..0x25FE,
-        0x2600..0x2604,
-        0x260E..0x260E,
-        0x2611..0x2611,
-        0x2614..0x2615,
-        0x2618..0x2618,
-        0x261D..0x261D,
-        0x2620..0x2620,
-        0x2622..0x2623,
-        0x2626..0x2626,
-        0x262A..0x262A,
-        0x262E..0x262F,
-        0x2638..0x263A,
-        0x2640..0x2640,
-        0x2642..0x2642,
-        0x2648..0x2653,
-        0x2660..0x2660,
-        0x2663..0x2663,
-        0x2665..0x2666,
-        0x2668..0x2668,
-        0x267B..0x267B,
-        0x267F..0x267F,
-        0x2692..0x2697,
-        0x2699..0x2699,
-        0x269B..0x269C,
-        0x26A0..0x26A1,
-        0x26AA..0x26AB,
-        0x26B0..0x26B1,
-        0x26BD..0x26BE,
-        0x26C4..0x26C5,
-        0x26C8..0x26C8,
-        0x26CE..0x26CF,
-        0x26D1..0x26D1,
-        0x26D3..0x26D4,
-        0x26E9..0x26EA,
-        0x26F0..0x26F5,
-        0x26F7..0x26FA,
-        0x26FD..0x26FD,
-        0x2702..0x2702,
-        0x2705..0x2705,
-        0x2708..0x270D,
-        0x270F..0x270F,
-        0x2712..0x2712,
-        0x2714..0x2714,
-        0x2716..0x2716,
-        0x271D..0x271D,
-        0x2721..0x2721,
-        0x2728..0x2728,
-        0x2733..0x2734,
-        0x2744..0x2744,
-        0x2747..0x2747,
-        0x274C..0x274C,
-        0x274E..0x274E,
-        0x2753..0x2755,
-        0x2757..0x2757,
-        0x2763..0x2764,
-        0x2795..0x2797,
-        0x27A1..0x27A1,
-        0x27B0..0x27B0,
-        0x27BF..0x27BF,
-        0x2934..0x2935,
-        0x2B05..0x2B07,
-        0x2B1B..0x2B1C,
-        0x2B50..0x2B50,
-        0x2B55..0x2B55,
-        0x3030..0x3030,
-        0x303D..0x303D,
-        0x3297..0x3297,
-        0x3299..0x3299,
-        0x1F004..0x1F004,
-        0x1F0CF..0x1F0CF,
-        0x1F170..0x1F171,
-        0x1F17E..0x1F17F,
-        0x1F18E..0x1F18E,
-        0x1F191..0x1F19A,
-        0x1F1E6..0x1F1FF,
-        0x1F201..0x1F202,
-        0x1F21A..0x1F21A,
-        0x1F22F..0x1F22F,
-        0x1F232..0x1F23A,
-        0x1F250..0x1F251,
-        0x1F300..0x1F321,
-        0x1F324..0x1F393,
-        0x1F396..0x1F397,
-        0x1F399..0x1F39B,
-        0x1F39E..0x1F3F0,
-        0x1F3F3..0x1F3F5,
-        0x1F3F7..0x1F4FD,
-        0x1F4FF..0x1F53D,
-        0x1F549..0x1F54E,
-        0x1F550..0x1F567,
-        0x1F56F..0x1F570,
-        0x1F573..0x1F57A,
-        0x1F587..0x1F587,
-        0x1F58A..0x1F58D,
-        0x1F590..0x1F590,
-        0x1F595..0x1F596,
-        0x1F5A4..0x1F5A5,
-        0x1F5A8..0x1F5A8,
-        0x1F5B1..0x1F5B2,
-        0x1F5BC..0x1F5BC,
-        0x1F5C2..0x1F5C4,
-        0x1F5D1..0x1F5D3,
-        0x1F5DC..0x1F5DE,
-        0x1F5E1..0x1F5E1,
-        0x1F5E3..0x1F5E3,
-        0x1F5E8..0x1F5E8,
-        0x1F5EF..0x1F5EF,
-        0x1F5F3..0x1F5F3,
-        0x1F5FA..0x1F64F,
-        0x1F680..0x1F6C5,
-        0x1F6CB..0x1F6D2,
-        0x1F6E0..0x1F6E5,
-        0x1F6E9..0x1F6E9,
-        0x1F6EB..0x1F6EC,
-        0x1F6F0..0x1F6F0,
-        0x1F6F3..0x1F6F8,
-        0x1F910..0x1F93A,
-        0x1F93C..0x1F93E,
-        0x1F940..0x1F945,
-        0x1F947..0x1F94C,
-        0x1F950..0x1F96B,
-        0x1F980..0x1F997,
-        0x1F9C0..0x1F9C0,
-        0x1F9D0..0x1F9E6
-      ).freeze
-    end
-
-    def respond_to_missing?(method_name, include_private = false)
-      (base = method_name[/^non_(.*)/, 1]) && respond_to?(base) || super
-    end
-
-    def method_missing(method_name, *args, &block)
-      if (base = method_name[/^non_(.*)/, 1])
-        ivar_name = "@#{method_name}"
-        return instance_variable_get(ivar_name) ||
-               instance_variable_set(ivar_name, send(base).inversion.freeze)
+    Dir[File.join(__dir__, 'predefined_sets', '*.cps')].each do |path|
+      set_name = File.basename(path, '.cps')
+
+      class_eval <<-RUBY, __FILE__, __LINE__ + 1
+        def #{set_name}
+          @#{set_name} ||= build_from_cps_file('#{path}').freeze
+        end
+
+        def non_#{set_name}
+          @non_#{set_name} ||= build_from_cps_file('#{path}').inversion.freeze
+        end
+      RUBY
+    end
+
+    alias all                      any
+    alias ascii_letters            ascii_letter
+    alias basic_multilingual_plane bmp
+    alias blank                    whitespace
+    alias invalid                  surrogate
+    alias valid                    unicode
+
+    def build_from_cps_file(path)
+      File.readlines(path).inject(new) do |set, line|
+        range_start, range_end = line.split(',')
+        set.merge((range_start.to_i(16))..(range_end.to_i(16)))
       end
-      super
     end
   end
 end

data/lib/character_set/predefined_sets/any.cps

@@ -0,0 +1 @@
+0,10FFFF

data/lib/character_set/predefined_sets/ascii.cps

@@ -0,0 +1 @@
+0,7F

data/lib/character_set/predefined_sets/ascii_alnum.cps

@@ -0,0 +1,3 @@
+30,39
+41,5A
+61,7A

data/lib/character_set/predefined_sets/ascii_letter.cps

@@ -0,0 +1,2 @@
+41,5A
+61,7A

data/lib/character_set/predefined_sets/assigned.cps

@@ -0,0 +1,666 @@
+0,377
+37A,37F
+384,38A
+38C,38C
+38E,3A1
+3A3,52F
+531,556
+559,58A
+58D,58F
+591,5C7
+5D0,5EA
+5EF,5F4
+600,61C
+61E,70D
+70F,74A
+74D,7B1
+7C0,7FA
+7FD,82D
+830,83E
+840,85B
+85E,85E
+860,86A
+8A0,8B4
+8B6,8BD
+8D3,983
+985,98C
+98F,990
+993,9A8
+9AA,9B0
+9B2,9B2
+9B6,9B9
+9BC,9C4
+9C7,9C8
+9CB,9CE
+9D7,9D7
+9DC,9DD
+9DF,9E3
+9E6,9FE
+A01,A03
+A05,A0A
+A0F,A10
+A13,A28
+A2A,A30
+A32,A33
+A35,A36
+A38,A39
+A3C,A3C
+A3E,A42
+A47,A48
+A4B,A4D
+A51,A51
+A59,A5C
+A5E,A5E
+A66,A76
+A81,A83
+A85,A8D
+A8F,A91
+A93,AA8
+AAA,AB0
+AB2,AB3
+AB5,AB9
+ABC,AC5
+AC7,AC9
+ACB,ACD
+AD0,AD0
+AE0,AE3
+AE6,AF1
+AF9,AFF
+B01,B03
+B05,B0C
+B0F,B10
+B13,B28
+B2A,B30
+B32,B33
+B35,B39
+B3C,B44
+B47,B48
+B4B,B4D
+B56,B57
+B5C,B5D
+B5F,B63
+B66,B77
+B82,B83
+B85,B8A
+B8E,B90
+B92,B95
+B99,B9A
+B9C,B9C
+B9E,B9F
+BA3,BA4
+BA8,BAA
+BAE,BB9
+BBE,BC2
+BC6,BC8
+BCA,BCD
+BD0,BD0
+BD7,BD7
+BE6,BFA
+C00,C0C
+C0E,C10
+C12,C28
+C2A,C39
+C3D,C44
+C46,C48
+C4A,C4D
+C55,C56
+C58,C5A
+C60,C63
+C66,C6F
+C77,C8C
+C8E,C90
+C92,CA8
+CAA,CB3
+CB5,CB9
+CBC,CC4
+CC6,CC8
+CCA,CCD
+CD5,CD6
+CDE,CDE
+CE0,CE3
+CE6,CEF
+CF1,CF2
+D00,D03
+D05,D0C
+D0E,D10
+D12,D44
+D46,D48
+D4A,D4F
+D54,D63
+D66,D7F
+D82,D83
+D85,D96
+D9A,DB1
+DB3,DBB
+DBD,DBD
+DC0,DC6
+DCA,DCA
+DCF,DD4
+DD6,DD6
+DD8,DDF
+DE6,DEF
+DF2,DF4
+E01,E3A
+E3F,E5B
+E81,E82
+E84,E84
+E86,E8A
+E8C,EA3
+EA5,EA5
+EA7,EBD
+EC0,EC4
+EC6,EC6
+EC8,ECD
+ED0,ED9
+EDC,EDF
+F00,F47
+F49,F6C
+F71,F97
+F99,FBC
+FBE,FCC
+FCE,FDA
+1000,10C5
+10C7,10C7
+10CD,10CD
+10D0,1248
+124A,124D
+1250,1256
+1258,1258
+125A,125D
+1260,1288
+128A,128D
+1290,12B0
+12B2,12B5
+12B8,12BE
+12C0,12C0
+12C2,12C5
+12C8,12D6
+12D8,1310
+1312,1315
+1318,135A
+135D,137C
+1380,1399
+13A0,13F5
+13F8,13FD
+1400,169C
+16A0,16F8
+1700,170C
+170E,1714
+1720,1736
+1740,1753
+1760,176C
+176E,1770
+1772,1773
+1780,17DD
+17E0,17E9
+17F0,17F9
+1800,180E
+1810,1819
+1820,1878
+1880,18AA
+18B0,18F5
+1900,191E
+1920,192B
+1930,193B
+1940,1940
+1944,196D
+1970,1974
+1980,19AB
+19B0,19C9
+19D0,19DA
+19DE,1A1B
+1A1E,1A5E
+1A60,1A7C
+1A7F,1A89
+1A90,1A99
+1AA0,1AAD
+1AB0,1ABE
+1B00,1B4B
+1B50,1B7C
+1B80,1BF3
+1BFC,1C37
+1C3B,1C49
+1C4D,1C88
+1C90,1CBA
+1CBD,1CC7
+1CD0,1CFA
+1D00,1DF9
+1DFB,1F15
+1F18,1F1D
+1F20,1F45
+1F48,1F4D
+1F50,1F57
+1F59,1F59
+1F5B,1F5B
+1F5D,1F5D
+1F5F,1F7D
+1F80,1FB4
+1FB6,1FC4
+1FC6,1FD3
+1FD6,1FDB
+1FDD,1FEF
+1FF2,1FF4
+1FF6,1FFE
+2000,2064
+2066,2071
+2074,208E
+2090,209C
+20A0,20BF
+20D0,20F0
+2100,218B
+2190,2426
+2440,244A
+2460,2B73
+2B76,2B95
+2B98,2C2E
+2C30,2C5E
+2C60,2CF3
+2CF9,2D25
+2D27,2D27
+2D2D,2D2D
+2D30,2D67
+2D6F,2D70
+2D7F,2D96
+2DA0,2DA6
+2DA8,2DAE
+2DB0,2DB6
+2DB8,2DBE
+2DC0,2DC6
+2DC8,2DCE
+2DD0,2DD6
+2DD8,2DDE
+2DE0,2E4F
+2E80,2E99
+2E9B,2EF3
+2F00,2FD5
+2FF0,2FFB
+3000,303F
+3041,3096
+3099,30FF
+3105,312F
+3131,318E
+3190,31BA
+31C0,31E3
+31F0,321E
+3220,4DB5
+4DC0,9FEF
+A000,A48C
+A490,A4C6
+A4D0,A62B
+A640,A6F7
+A700,A7BF
+A7C2,A7C6
+A7F7,A82B
+A830,A839
+A840,A877
+A880,A8C5
+A8CE,A8D9
+A8E0,A953
+A95F,A97C
+A980,A9CD
+A9CF,A9D9
+A9DE,A9FE
+AA00,AA36
+AA40,AA4D
+AA50,AA59
+AA5C,AAC2
+AADB,AAF6
+AB01,AB06
+AB09,AB0E
+AB11,AB16
+AB20,AB26
+AB28,AB2E
+AB30,AB67
+AB70,ABED
+ABF0,ABF9
+AC00,D7A3
+D7B0,D7C6
+D7CB,D7FB
+D800,FA6D
+FA70,FAD9
+FB00,FB06
+FB13,FB17
+FB1D,FB36
+FB38,FB3C
+FB3E,FB3E
+FB40,FB41
+FB43,FB44
+FB46,FBC1
+FBD3,FD3F
+FD50,FD8F
+FD92,FDC7
+FDF0,FDFD
+FE00,FE19
+FE20,FE52
+FE54,FE66
+FE68,FE6B
+FE70,FE74
+FE76,FEFC
+FEFF,FEFF
+FF01,FFBE
+FFC2,FFC7
+FFCA,FFCF
+FFD2,FFD7
+FFDA,FFDC
+FFE0,FFE6
+FFE8,FFEE
+FFF9,FFFD
+10000,1000B
+1000D,10026
+10028,1003A
+1003C,1003D
+1003F,1004D
+10050,1005D
+10080,100FA
+10100,10102
+10107,10133
+10137,1018E
+10190,1019B
+101A0,101A0
+101D0,101FD
+10280,1029C
+102A0,102D0
+102E0,102FB
+10300,10323
+1032D,1034A
+10350,1037A
+10380,1039D
+1039F,103C3
+103C8,103D5
+10400,1049D
+104A0,104A9
+104B0,104D3
+104D8,104FB
+10500,10527
+10530,10563
+1056F,1056F
+10600,10736
+10740,10755
+10760,10767
+10800,10805
+10808,10808
+1080A,10835
+10837,10838
+1083C,1083C
+1083F,10855
+10857,1089E
+108A7,108AF
+108E0,108F2
+108F4,108F5
+108FB,1091B
+1091F,10939
+1093F,1093F
+10980,109B7
+109BC,109CF
+109D2,10A03
+10A05,10A06
+10A0C,10A13
+10A15,10A17
+10A19,10A35
+10A38,10A3A
+10A3F,10A48
+10A50,10A58
+10A60,10A9F
+10AC0,10AE6
+10AEB,10AF6
+10B00,10B35
+10B39,10B55
+10B58,10B72
+10B78,10B91
+10B99,10B9C
+10BA9,10BAF
+10C00,10C48
+10C80,10CB2
+10CC0,10CF2
+10CFA,10D27
+10D30,10D39
+10E60,10E7E
+10F00,10F27
+10F30,10F59
+10FE0,10FF6
+11000,1104D
+11052,1106F
+1107F,110C1
+110CD,110CD
+110D0,110E8
+110F0,110F9
+11100,11134
+11136,11146
+11150,11176
+11180,111CD
+111D0,111DF
+111E1,111F4
+11200,11211
+11213,1123E
+11280,11286
+11288,11288
+1128A,1128D
+1128F,1129D
+1129F,112A9
+112B0,112EA
+112F0,112F9
+11300,11303
+11305,1130C
+1130F,11310
+11313,11328
+1132A,11330
+11332,11333
+11335,11339
+1133B,11344
+11347,11348
+1134B,1134D
+11350,11350
+11357,11357
+1135D,11363
+11366,1136C
+11370,11374
+11400,11459
+1145B,1145B
+1145D,1145F
+11480,114C7
+114D0,114D9
+11580,115B5
+115B8,115DD
+11600,11644
+11650,11659
+11660,1166C
+11680,116B8
+116C0,116C9
+11700,1171A
+1171D,1172B
+11730,1173F
+11800,1183B
+118A0,118F2
+118FF,118FF
+119A0,119A7
+119AA,119D7
+119DA,119E4
+11A00,11A47
+11A50,11AA2
+11AC0,11AF8
+11C00,11C08
+11C0A,11C36
+11C38,11C45
+11C50,11C6C
+11C70,11C8F
+11C92,11CA7
+11CA9,11CB6
+11D00,11D06
+11D08,11D09
+11D0B,11D36
+11D3A,11D3A
+11D3C,11D3D
+11D3F,11D47
+11D50,11D59
+11D60,11D65
+11D67,11D68
+11D6A,11D8E
+11D90,11D91
+11D93,11D98
+11DA0,11DA9
+11EE0,11EF8
+11FC0,11FF1
+11FFF,12399
+12400,1246E
+12470,12474
+12480,12543
+13000,1342E
+13430,13438
+14400,14646
+16800,16A38
+16A40,16A5E
+16A60,16A69
+16A6E,16A6F
+16AD0,16AED
+16AF0,16AF5
+16B00,16B45
+16B50,16B59
+16B5B,16B61
+16B63,16B77
+16B7D,16B8F
+16E40,16E9A
+16F00,16F4A
+16F4F,16F87
+16F8F,16F9F
+16FE0,16FE3
+17000,187F7
+18800,18AF2
+1B000,1B11E
+1B150,1B152
+1B164,1B167
+1B170,1B2FB
+1BC00,1BC6A
+1BC70,1BC7C
+1BC80,1BC88
+1BC90,1BC99
+1BC9C,1BCA3
+1D000,1D0F5
+1D100,1D126
+1D129,1D1E8
+1D200,1D245
+1D2E0,1D2F3
+1D300,1D356
+1D360,1D378
+1D400,1D454
+1D456,1D49C
+1D49E,1D49F
+1D4A2,1D4A2
+1D4A5,1D4A6
+1D4A9,1D4AC
+1D4AE,1D4B9
+1D4BB,1D4BB
+1D4BD,1D4C3
+1D4C5,1D505
+1D507,1D50A
+1D50D,1D514
+1D516,1D51C
+1D51E,1D539
+1D53B,1D53E
+1D540,1D544
+1D546,1D546
+1D54A,1D550
+1D552,1D6A5
+1D6A8,1D7CB
+1D7CE,1DA8B
+1DA9B,1DA9F
+1DAA1,1DAAF
+1E000,1E006
+1E008,1E018
+1E01B,1E021
+1E023,1E024
+1E026,1E02A
+1E100,1E12C
+1E130,1E13D
+1E140,1E149
+1E14E,1E14F
+1E2C0,1E2F9
+1E2FF,1E2FF
+1E800,1E8C4
+1E8C7,1E8D6
+1E900,1E94B
+1E950,1E959
+1E95E,1E95F
+1EC71,1ECB4
+1ED01,1ED3D
+1EE00,1EE03
+1EE05,1EE1F
+1EE21,1EE22
+1EE24,1EE24
+1EE27,1EE27
+1EE29,1EE32
+1EE34,1EE37
+1EE39,1EE39
+1EE3B,1EE3B
+1EE42,1EE42
+1EE47,1EE47
+1EE49,1EE49
+1EE4B,1EE4B
+1EE4D,1EE4F
+1EE51,1EE52
+1EE54,1EE54
+1EE57,1EE57
+1EE59,1EE59
+1EE5B,1EE5B
+1EE5D,1EE5D
+1EE5F,1EE5F
+1EE61,1EE62
+1EE64,1EE64
+1EE67,1EE6A
+1EE6C,1EE72
+1EE74,1EE77
+1EE79,1EE7C
+1EE7E,1EE7E
+1EE80,1EE89
+1EE8B,1EE9B
+1EEA1,1EEA3
+1EEA5,1EEA9
+1EEAB,1EEBB
+1EEF0,1EEF1
+1F000,1F02B
+1F030,1F093
+1F0A0,1F0AE
+1F0B1,1F0BF
+1F0C1,1F0CF
+1F0D1,1F0F5
+1F100,1F10C
+1F110,1F16C
+1F170,1F1AC
+1F1E6,1F202
+1F210,1F23B
+1F240,1F248
+1F250,1F251
+1F260,1F265
+1F300,1F6D5
+1F6E0,1F6EC
+1F6F0,1F6FA
+1F700,1F773
+1F780,1F7D8
+1F7E0,1F7EB
+1F800,1F80B
+1F810,1F847
+1F850,1F859
+1F860,1F887
+1F890,1F8AD
+1F900,1F90B
+1F90D,1F971
+1F973,1F976
+1F97A,1F9A2
+1F9A5,1F9AA
+1F9AE,1F9CA
+1F9CD,1FA53
+1FA60,1FA6D
+1FA70,1FA73
+1FA78,1FA7A
+1FA80,1FA82
+1FA90,1FA95
+20000,2A6D6
+2A700,2B734
+2B740,2B81D
+2B820,2CEA1
+2CEB0,2EBE0
+2F800,2FA1D
+E0001,E0001
+E0020,E007F
+E0100,E01EF
+F0000,FFFFD
+100000,10FFFD