regextest 0.1.2

Sign up to get free protection for your applications and to get access to all the features.
Files changed (64) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +11 -0
  3. data/.rspec +2 -0
  4. data/.travis.yml +3 -0
  5. data/Gemfile +4 -0
  6. data/LICENSE.txt +25 -0
  7. data/README.md +88 -0
  8. data/Rakefile +55 -0
  9. data/bin/console +14 -0
  10. data/bin/regextest +4 -0
  11. data/bin/setup +7 -0
  12. data/contrib/Onigmo/RE.txt +522 -0
  13. data/contrib/Onigmo/UnicodeProps.txt +728 -0
  14. data/contrib/Onigmo/testpy.py +1319 -0
  15. data/contrib/unicode/Blocks.txt +298 -0
  16. data/contrib/unicode/CaseFolding.txt +1414 -0
  17. data/contrib/unicode/DerivedAge.txt +1538 -0
  18. data/contrib/unicode/DerivedCoreProperties.txt +11029 -0
  19. data/contrib/unicode/PropList.txt +1525 -0
  20. data/contrib/unicode/PropertyAliases.txt +193 -0
  21. data/contrib/unicode/PropertyValueAliases.txt +1420 -0
  22. data/contrib/unicode/README.txt +25 -0
  23. data/contrib/unicode/Scripts.txt +2539 -0
  24. data/contrib/unicode/UnicodeData.txt +29215 -0
  25. data/lib/pre-case-folding.rb +101 -0
  26. data/lib/pre-posix-char-class.rb +150 -0
  27. data/lib/pre-unicode.rb +116 -0
  28. data/lib/regextest.rb +268 -0
  29. data/lib/regextest/back.rb +58 -0
  30. data/lib/regextest/back/element.rb +151 -0
  31. data/lib/regextest/back/main.rb +356 -0
  32. data/lib/regextest/back/result.rb +498 -0
  33. data/lib/regextest/back/test-case.rb +268 -0
  34. data/lib/regextest/back/work-thread.rb +119 -0
  35. data/lib/regextest/common.rb +63 -0
  36. data/lib/regextest/front.rb +60 -0
  37. data/lib/regextest/front/anchor.rb +45 -0
  38. data/lib/regextest/front/back-refer.rb +120 -0
  39. data/lib/regextest/front/bracket-parser.rb +400 -0
  40. data/lib/regextest/front/bracket-parser.y +117 -0
  41. data/lib/regextest/front/bracket-scanner.rb +124 -0
  42. data/lib/regextest/front/bracket.rb +64 -0
  43. data/lib/regextest/front/builtin-functions.rb +31 -0
  44. data/lib/regextest/front/case-folding.rb +18 -0
  45. data/lib/regextest/front/char-class.rb +243 -0
  46. data/lib/regextest/front/empty.rb +43 -0
  47. data/lib/regextest/front/letter.rb +327 -0
  48. data/lib/regextest/front/manage-parentheses.rb +74 -0
  49. data/lib/regextest/front/parenthesis.rb +153 -0
  50. data/lib/regextest/front/parser.rb +1366 -0
  51. data/lib/regextest/front/parser.y +271 -0
  52. data/lib/regextest/front/range.rb +60 -0
  53. data/lib/regextest/front/repeat.rb +90 -0
  54. data/lib/regextest/front/repeatable.rb +77 -0
  55. data/lib/regextest/front/scanner.rb +187 -0
  56. data/lib/regextest/front/selectable.rb +65 -0
  57. data/lib/regextest/front/sequence.rb +73 -0
  58. data/lib/regextest/front/unicode.rb +1272 -0
  59. data/lib/regextest/regex-option.rb +144 -0
  60. data/lib/regextest/regexp.rb +44 -0
  61. data/lib/regextest/version.rb +5 -0
  62. data/lib/tst-reg-test.rb +159 -0
  63. data/regextest.gemspec +26 -0
  64. metadata +162 -0
@@ -0,0 +1,193 @@
1
+ # PropertyAliases-8.0.0.txt
2
+ # Date: 2015-02-14, 10:26:09 GMT [MD]
3
+ #
4
+ # Unicode Character Database
5
+ # Copyright (c) 1991-2015 Unicode, Inc.
6
+ # For terms of use, see http://www.unicode.org/terms_of_use.html
7
+ # For documentation, see http://www.unicode.org/reports/tr44/
8
+ #
9
+ # This file contains aliases for properties used in the UCD.
10
+ # These names can be used for XML formats of UCD data, for regular-expression
11
+ # property tests, and other programmatic textual descriptions of Unicode data.
12
+ #
13
+ # The names may be translated in appropriate environments, and additional
14
+ # aliases may be useful.
15
+ #
16
+ # FORMAT
17
+ #
18
+ # Each line has two or more fields, separated by semicolons.
19
+ #
20
+ # First Field: The first field is an abbreviated name for the property.
21
+ #
22
+ # Second Field: The second field is a long name
23
+ #
24
+ # The above are the preferred aliases. Other aliases may be listed in additional fields.
25
+ #
26
+ # Loose matching should be applied to all property names and property values, with
27
+ # the exception of String Property values. With loose matching of property names and
28
+ # values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
29
+ # values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
30
+ #
31
+ # NOTE: Property value names are NOT unique across properties. For example:
32
+ #
33
+ # AL means Arabic Letter for the Bidi_Class property, and
34
+ # AL means Above_Left for the Combining_Class property, and
35
+ # AL means Alphabetic for the Line_Break property.
36
+ #
37
+ # In addition, some property names may be the same as some property value names.
38
+ # For example:
39
+ #
40
+ # sc means the Script property, and
41
+ # Sc means the General_Category property value Currency_Symbol (Sc)
42
+ #
43
+ # The combination of property value and property name is, however, unique.
44
+ #
45
+ # For more information, see UTS #18: Unicode Regular Expressions
46
+ # ================================================
47
+
48
+
49
+ # ================================================
50
+ # Numeric Properties
51
+ # ================================================
52
+ cjkAccountingNumeric ; kAccountingNumeric
53
+ cjkOtherNumeric ; kOtherNumeric
54
+ cjkPrimaryNumeric ; kPrimaryNumeric
55
+ nv ; Numeric_Value
56
+
57
+ # ================================================
58
+ # String Properties
59
+ # ================================================
60
+ cf ; Case_Folding
61
+ cjkCompatibilityVariant ; kCompatibilityVariant
62
+ dm ; Decomposition_Mapping
63
+ FC_NFKC ; FC_NFKC_Closure
64
+ lc ; Lowercase_Mapping
65
+ NFKC_CF ; NFKC_Casefold
66
+ scf ; Simple_Case_Folding ; sfc
67
+ slc ; Simple_Lowercase_Mapping
68
+ stc ; Simple_Titlecase_Mapping
69
+ suc ; Simple_Uppercase_Mapping
70
+ tc ; Titlecase_Mapping
71
+ uc ; Uppercase_Mapping
72
+
73
+ # ================================================
74
+ # Miscellaneous Properties
75
+ # ================================================
76
+ bmg ; Bidi_Mirroring_Glyph
77
+ bpb ; Bidi_Paired_Bracket
78
+ cjkIICore ; kIICore
79
+ cjkIRG_GSource ; kIRG_GSource
80
+ cjkIRG_HSource ; kIRG_HSource
81
+ cjkIRG_JSource ; kIRG_JSource
82
+ cjkIRG_KPSource ; kIRG_KPSource
83
+ cjkIRG_KSource ; kIRG_KSource
84
+ cjkIRG_MSource ; kIRG_MSource
85
+ cjkIRG_TSource ; kIRG_TSource
86
+ cjkIRG_USource ; kIRG_USource
87
+ cjkIRG_VSource ; kIRG_VSource
88
+ cjkRSUnicode ; kRSUnicode ; Unicode_Radical_Stroke; URS
89
+ isc ; ISO_Comment
90
+ JSN ; Jamo_Short_Name
91
+ na ; Name
92
+ na1 ; Unicode_1_Name
93
+ Name_Alias ; Name_Alias
94
+ scx ; Script_Extensions
95
+
96
+ # ================================================
97
+ # Catalog Properties
98
+ # ================================================
99
+ age ; Age
100
+ blk ; Block
101
+ sc ; Script
102
+
103
+ # ================================================
104
+ # Enumerated Properties
105
+ # ================================================
106
+ bc ; Bidi_Class
107
+ bpt ; Bidi_Paired_Bracket_Type
108
+ ccc ; Canonical_Combining_Class
109
+ dt ; Decomposition_Type
110
+ ea ; East_Asian_Width
111
+ gc ; General_Category
112
+ GCB ; Grapheme_Cluster_Break
113
+ hst ; Hangul_Syllable_Type
114
+ InPC ; Indic_Positional_Category
115
+ InSC ; Indic_Syllabic_Category
116
+ jg ; Joining_Group
117
+ jt ; Joining_Type
118
+ lb ; Line_Break
119
+ NFC_QC ; NFC_Quick_Check
120
+ NFD_QC ; NFD_Quick_Check
121
+ NFKC_QC ; NFKC_Quick_Check
122
+ NFKD_QC ; NFKD_Quick_Check
123
+ nt ; Numeric_Type
124
+ SB ; Sentence_Break
125
+ WB ; Word_Break
126
+
127
+ # ================================================
128
+ # Binary Properties
129
+ # ================================================
130
+ AHex ; ASCII_Hex_Digit
131
+ Alpha ; Alphabetic
132
+ Bidi_C ; Bidi_Control
133
+ Bidi_M ; Bidi_Mirrored
134
+ Cased ; Cased
135
+ CE ; Composition_Exclusion
136
+ CI ; Case_Ignorable
137
+ Comp_Ex ; Full_Composition_Exclusion
138
+ CWCF ; Changes_When_Casefolded
139
+ CWCM ; Changes_When_Casemapped
140
+ CWKCF ; Changes_When_NFKC_Casefolded
141
+ CWL ; Changes_When_Lowercased
142
+ CWT ; Changes_When_Titlecased
143
+ CWU ; Changes_When_Uppercased
144
+ Dash ; Dash
145
+ Dep ; Deprecated
146
+ DI ; Default_Ignorable_Code_Point
147
+ Dia ; Diacritic
148
+ Ext ; Extender
149
+ Gr_Base ; Grapheme_Base
150
+ Gr_Ext ; Grapheme_Extend
151
+ Gr_Link ; Grapheme_Link
152
+ Hex ; Hex_Digit
153
+ Hyphen ; Hyphen
154
+ IDC ; ID_Continue
155
+ Ideo ; Ideographic
156
+ IDS ; ID_Start
157
+ IDSB ; IDS_Binary_Operator
158
+ IDST ; IDS_Trinary_Operator
159
+ Join_C ; Join_Control
160
+ LOE ; Logical_Order_Exception
161
+ Lower ; Lowercase
162
+ Math ; Math
163
+ NChar ; Noncharacter_Code_Point
164
+ OAlpha ; Other_Alphabetic
165
+ ODI ; Other_Default_Ignorable_Code_Point
166
+ OGr_Ext ; Other_Grapheme_Extend
167
+ OIDC ; Other_ID_Continue
168
+ OIDS ; Other_ID_Start
169
+ OLower ; Other_Lowercase
170
+ OMath ; Other_Math
171
+ OUpper ; Other_Uppercase
172
+ Pat_Syn ; Pattern_Syntax
173
+ Pat_WS ; Pattern_White_Space
174
+ QMark ; Quotation_Mark
175
+ Radical ; Radical
176
+ SD ; Soft_Dotted
177
+ STerm ; STerm
178
+ Term ; Terminal_Punctuation
179
+ UIdeo ; Unified_Ideograph
180
+ Upper ; Uppercase
181
+ VS ; Variation_Selector
182
+ WSpace ; White_Space ; space
183
+ XIDC ; XID_Continue
184
+ XIDS ; XID_Start
185
+ XO_NFC ; Expands_On_NFC
186
+ XO_NFD ; Expands_On_NFD
187
+ XO_NFKC ; Expands_On_NFKC
188
+ XO_NFKD ; Expands_On_NFKD
189
+
190
+ # ================================================
191
+ # Total: 117
192
+
193
+ # EOF
@@ -0,0 +1,1420 @@
1
+ # PropertyValueAliases-8.0.0.txt
2
+ # Date: 2015-03-11, 22:29:33 GMT [MD]
3
+ #
4
+ # Unicode Character Database
5
+ # Copyright (c) 1991-2015 Unicode, Inc.
6
+ # For terms of use, see http://www.unicode.org/terms_of_use.html
7
+ # For documentation, see http://www.unicode.org/reports/tr44/
8
+ #
9
+ # This file contains aliases for property values used in the UCD.
10
+ # These names can be used for XML formats of UCD data, for regular-expression
11
+ # property tests, and other programmatic textual descriptions of Unicode data.
12
+ #
13
+ # The names may be translated in appropriate environments, and additional
14
+ # aliases may be useful.
15
+ #
16
+ # FORMAT
17
+ #
18
+ # Each line describes a property value name.
19
+ # This consists of three or more fields, separated by semicolons.
20
+ #
21
+ # First Field: The first field describes the property for which that
22
+ # property value name is used.
23
+ #
24
+ # Second Field: The second field is an abbreviated name.
25
+ #
26
+ # Third Field: The third field is a long name.
27
+ #
28
+ # In the case of ccc, there are 4 fields. The second field is numeric, third
29
+ # is abbreviated, and fourth is long.
30
+ #
31
+ # The above are the preferred aliases. Other aliases may be listed in additional fields.
32
+ #
33
+ # Loose matching should be applied to all property names and property values, with
34
+ # the exception of String Property values. With loose matching of property names and
35
+ # values, the case distinctions, whitespace, hyphens, and '_' are ignored.
36
+ # For Numeric Property values, numeric equivalence is applied: thus "01.00"
37
+ # is equivalent to "1".
38
+ #
39
+ # NOTE: Property value names are NOT unique across properties. For example:
40
+ #
41
+ # AL means Arabic Letter for the Bidi_Class property, and
42
+ # AL means Above_Left for the Canonical_Combining_Class property, and
43
+ # AL means Alphabetic for the Line_Break property.
44
+ #
45
+ # In addition, some property names may be the same as some property value names.
46
+ # For example:
47
+ #
48
+ # sc means the Script property, and
49
+ # Sc means the General_Category property value Currency_Symbol (Sc)
50
+ #
51
+ # The combination of property value and property name is, however, unique.
52
+ #
53
+ # For more information, see UTS #18: Unicode Regular Expressions
54
+ # ================================================
55
+
56
+
57
+ # ASCII_Hex_Digit (AHex)
58
+
59
+ AHex; N ; No ; F ; False
60
+ AHex; Y ; Yes ; T ; True
61
+
62
+ # Age (age)
63
+
64
+ age; 1.1 ; V1_1
65
+ age; 2.0 ; V2_0
66
+ age; 2.1 ; V2_1
67
+ age; 3.0 ; V3_0
68
+ age; 3.1 ; V3_1
69
+ age; 3.2 ; V3_2
70
+ age; 4.0 ; V4_0
71
+ age; 4.1 ; V4_1
72
+ age; 5.0 ; V5_0
73
+ age; 5.1 ; V5_1
74
+ age; 5.2 ; V5_2
75
+ age; 6.0 ; V6_0
76
+ age; 6.1 ; V6_1
77
+ age; 6.2 ; V6_2
78
+ age; 6.3 ; V6_3
79
+ age; 7.0 ; V7_0
80
+ age; 8.0 ; V8_0
81
+ age; NA ; Unassigned
82
+
83
+ # Alphabetic (Alpha)
84
+
85
+ Alpha; N ; No ; F ; False
86
+ Alpha; Y ; Yes ; T ; True
87
+
88
+ # Bidi_Class (bc)
89
+
90
+ bc ; AL ; Arabic_Letter
91
+ bc ; AN ; Arabic_Number
92
+ bc ; B ; Paragraph_Separator
93
+ bc ; BN ; Boundary_Neutral
94
+ bc ; CS ; Common_Separator
95
+ bc ; EN ; European_Number
96
+ bc ; ES ; European_Separator
97
+ bc ; ET ; European_Terminator
98
+ bc ; FSI ; First_Strong_Isolate
99
+ bc ; L ; Left_To_Right
100
+ bc ; LRE ; Left_To_Right_Embedding
101
+ bc ; LRI ; Left_To_Right_Isolate
102
+ bc ; LRO ; Left_To_Right_Override
103
+ bc ; NSM ; Nonspacing_Mark
104
+ bc ; ON ; Other_Neutral
105
+ bc ; PDF ; Pop_Directional_Format
106
+ bc ; PDI ; Pop_Directional_Isolate
107
+ bc ; R ; Right_To_Left
108
+ bc ; RLE ; Right_To_Left_Embedding
109
+ bc ; RLI ; Right_To_Left_Isolate
110
+ bc ; RLO ; Right_To_Left_Override
111
+ bc ; S ; Segment_Separator
112
+ bc ; WS ; White_Space
113
+
114
+ # Bidi_Control (Bidi_C)
115
+
116
+ Bidi_C; N ; No ; F ; False
117
+ Bidi_C; Y ; Yes ; T ; True
118
+
119
+ # Bidi_Mirrored (Bidi_M)
120
+
121
+ Bidi_M; N ; No ; F ; False
122
+ Bidi_M; Y ; Yes ; T ; True
123
+
124
+ # Bidi_Mirroring_Glyph (bmg)
125
+
126
+ # @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
127
+
128
+ # Bidi_Paired_Bracket (bpb)
129
+
130
+ # @missing: 0000..10FFFF; Bidi_Paired_Bracket; <none>
131
+
132
+ # Bidi_Paired_Bracket_Type (bpt)
133
+
134
+ bpt; c ; Close
135
+ bpt; n ; None
136
+ bpt; o ; Open
137
+ # @missing: 0000..10FFFF; Bidi_Paired_Bracket_Type; n
138
+
139
+ # Block (blk)
140
+
141
+ blk; Aegean_Numbers ; Aegean_Numbers
142
+ blk; Ahom ; Ahom
143
+ blk; Alchemical ; Alchemical_Symbols
144
+ blk; Alphabetic_PF ; Alphabetic_Presentation_Forms
145
+ blk; Anatolian_Hieroglyphs ; Anatolian_Hieroglyphs
146
+ blk; Ancient_Greek_Music ; Ancient_Greek_Musical_Notation
147
+ blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers
148
+ blk; Ancient_Symbols ; Ancient_Symbols
149
+ blk; Arabic ; Arabic
150
+ blk; Arabic_Ext_A ; Arabic_Extended_A
151
+ blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols
152
+ blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
153
+ blk; Arabic_PF_B ; Arabic_Presentation_Forms_B
154
+ blk; Arabic_Sup ; Arabic_Supplement
155
+ blk; Armenian ; Armenian
156
+ blk; Arrows ; Arrows
157
+ blk; ASCII ; Basic_Latin
158
+ blk; Avestan ; Avestan
159
+ blk; Balinese ; Balinese
160
+ blk; Bamum ; Bamum
161
+ blk; Bamum_Sup ; Bamum_Supplement
162
+ blk; Bassa_Vah ; Bassa_Vah
163
+ blk; Batak ; Batak
164
+ blk; Bengali ; Bengali
165
+ blk; Block_Elements ; Block_Elements
166
+ blk; Bopomofo ; Bopomofo
167
+ blk; Bopomofo_Ext ; Bopomofo_Extended
168
+ blk; Box_Drawing ; Box_Drawing
169
+ blk; Brahmi ; Brahmi
170
+ blk; Braille ; Braille_Patterns
171
+ blk; Buginese ; Buginese
172
+ blk; Buhid ; Buhid
173
+ blk; Byzantine_Music ; Byzantine_Musical_Symbols
174
+ blk; Carian ; Carian
175
+ blk; Caucasian_Albanian ; Caucasian_Albanian
176
+ blk; Chakma ; Chakma
177
+ blk; Cham ; Cham
178
+ blk; Cherokee ; Cherokee
179
+ blk; Cherokee_Sup ; Cherokee_Supplement
180
+ blk; CJK ; CJK_Unified_Ideographs
181
+ blk; CJK_Compat ; CJK_Compatibility
182
+ blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
183
+ blk; CJK_Compat_Ideographs ; CJK_Compatibility_Ideographs
184
+ blk; CJK_Compat_Ideographs_Sup ; CJK_Compatibility_Ideographs_Supplement
185
+ blk; CJK_Ext_A ; CJK_Unified_Ideographs_Extension_A
186
+ blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B
187
+ blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C
188
+ blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D
189
+ blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E
190
+ blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
191
+ blk; CJK_Strokes ; CJK_Strokes
192
+ blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
193
+ blk; Compat_Jamo ; Hangul_Compatibility_Jamo
194
+ blk; Control_Pictures ; Control_Pictures
195
+ blk; Coptic ; Coptic
196
+ blk; Coptic_Epact_Numbers ; Coptic_Epact_Numbers
197
+ blk; Counting_Rod ; Counting_Rod_Numerals
198
+ blk; Cuneiform ; Cuneiform
199
+ blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
200
+ blk; Currency_Symbols ; Currency_Symbols
201
+ blk; Cypriot_Syllabary ; Cypriot_Syllabary
202
+ blk; Cyrillic ; Cyrillic
203
+ blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
204
+ blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
205
+ blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
206
+ blk; Deseret ; Deseret
207
+ blk; Devanagari ; Devanagari
208
+ blk; Devanagari_Ext ; Devanagari_Extended
209
+ blk; Diacriticals ; Combining_Diacritical_Marks
210
+ blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
211
+ blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
212
+ blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
213
+ blk; Dingbats ; Dingbats
214
+ blk; Domino ; Domino_Tiles
215
+ blk; Duployan ; Duployan
216
+ blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
217
+ blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
218
+ blk; Elbasan ; Elbasan
219
+ blk; Emoticons ; Emoticons
220
+ blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
221
+ blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
222
+ blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
223
+ blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
224
+ blk; Ethiopic ; Ethiopic
225
+ blk; Ethiopic_Ext ; Ethiopic_Extended
226
+ blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
227
+ blk; Ethiopic_Sup ; Ethiopic_Supplement
228
+ blk; Geometric_Shapes ; Geometric_Shapes
229
+ blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
230
+ blk; Georgian ; Georgian
231
+ blk; Georgian_Sup ; Georgian_Supplement
232
+ blk; Glagolitic ; Glagolitic
233
+ blk; Gothic ; Gothic
234
+ blk; Grantha ; Grantha
235
+ blk; Greek ; Greek_And_Coptic
236
+ blk; Greek_Ext ; Greek_Extended
237
+ blk; Gujarati ; Gujarati
238
+ blk; Gurmukhi ; Gurmukhi
239
+ blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
240
+ blk; Half_Marks ; Combining_Half_Marks
241
+ blk; Hangul ; Hangul_Syllables
242
+ blk; Hanunoo ; Hanunoo
243
+ blk; Hatran ; Hatran
244
+ blk; Hebrew ; Hebrew
245
+ blk; High_PU_Surrogates ; High_Private_Use_Surrogates
246
+ blk; High_Surrogates ; High_Surrogates
247
+ blk; Hiragana ; Hiragana
248
+ blk; IDC ; Ideographic_Description_Characters
249
+ blk; Imperial_Aramaic ; Imperial_Aramaic
250
+ blk; Indic_Number_Forms ; Common_Indic_Number_Forms
251
+ blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
252
+ blk; Inscriptional_Parthian ; Inscriptional_Parthian
253
+ blk; IPA_Ext ; IPA_Extensions
254
+ blk; Jamo ; Hangul_Jamo
255
+ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A
256
+ blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B
257
+ blk; Javanese ; Javanese
258
+ blk; Kaithi ; Kaithi
259
+ blk; Kana_Sup ; Kana_Supplement
260
+ blk; Kanbun ; Kanbun
261
+ blk; Kangxi ; Kangxi_Radicals
262
+ blk; Kannada ; Kannada
263
+ blk; Katakana ; Katakana
264
+ blk; Katakana_Ext ; Katakana_Phonetic_Extensions
265
+ blk; Kayah_Li ; Kayah_Li
266
+ blk; Kharoshthi ; Kharoshthi
267
+ blk; Khmer ; Khmer
268
+ blk; Khmer_Symbols ; Khmer_Symbols
269
+ blk; Khojki ; Khojki
270
+ blk; Khudawadi ; Khudawadi
271
+ blk; Lao ; Lao
272
+ blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
273
+ blk; Latin_Ext_A ; Latin_Extended_A
274
+ blk; Latin_Ext_Additional ; Latin_Extended_Additional
275
+ blk; Latin_Ext_B ; Latin_Extended_B
276
+ blk; Latin_Ext_C ; Latin_Extended_C
277
+ blk; Latin_Ext_D ; Latin_Extended_D
278
+ blk; Latin_Ext_E ; Latin_Extended_E
279
+ blk; Lepcha ; Lepcha
280
+ blk; Letterlike_Symbols ; Letterlike_Symbols
281
+ blk; Limbu ; Limbu
282
+ blk; Linear_A ; Linear_A
283
+ blk; Linear_B_Ideograms ; Linear_B_Ideograms
284
+ blk; Linear_B_Syllabary ; Linear_B_Syllabary
285
+ blk; Lisu ; Lisu
286
+ blk; Low_Surrogates ; Low_Surrogates
287
+ blk; Lycian ; Lycian
288
+ blk; Lydian ; Lydian
289
+ blk; Mahajani ; Mahajani
290
+ blk; Mahjong ; Mahjong_Tiles
291
+ blk; Malayalam ; Malayalam
292
+ blk; Mandaic ; Mandaic
293
+ blk; Manichaean ; Manichaean
294
+ blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
295
+ blk; Math_Operators ; Mathematical_Operators
296
+ blk; Meetei_Mayek ; Meetei_Mayek
297
+ blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
298
+ blk; Mende_Kikakui ; Mende_Kikakui
299
+ blk; Meroitic_Cursive ; Meroitic_Cursive
300
+ blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
301
+ blk; Miao ; Miao
302
+ blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
303
+ blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
304
+ blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
305
+ blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
306
+ blk; Misc_Symbols ; Miscellaneous_Symbols
307
+ blk; Misc_Technical ; Miscellaneous_Technical
308
+ blk; Modi ; Modi
309
+ blk; Modifier_Letters ; Spacing_Modifier_Letters
310
+ blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
311
+ blk; Mongolian ; Mongolian
312
+ blk; Mro ; Mro
313
+ blk; Multani ; Multani
314
+ blk; Music ; Musical_Symbols
315
+ blk; Myanmar ; Myanmar
316
+ blk; Myanmar_Ext_A ; Myanmar_Extended_A
317
+ blk; Myanmar_Ext_B ; Myanmar_Extended_B
318
+ blk; Nabataean ; Nabataean
319
+ blk; NB ; No_Block
320
+ blk; New_Tai_Lue ; New_Tai_Lue
321
+ blk; NKo ; NKo
322
+ blk; Number_Forms ; Number_Forms
323
+ blk; OCR ; Optical_Character_Recognition
324
+ blk; Ogham ; Ogham
325
+ blk; Ol_Chiki ; Ol_Chiki
326
+ blk; Old_Hungarian ; Old_Hungarian
327
+ blk; Old_Italic ; Old_Italic
328
+ blk; Old_North_Arabian ; Old_North_Arabian
329
+ blk; Old_Permic ; Old_Permic
330
+ blk; Old_Persian ; Old_Persian
331
+ blk; Old_South_Arabian ; Old_South_Arabian
332
+ blk; Old_Turkic ; Old_Turkic
333
+ blk; Oriya ; Oriya
334
+ blk; Ornamental_Dingbats ; Ornamental_Dingbats
335
+ blk; Osmanya ; Osmanya
336
+ blk; Pahawh_Hmong ; Pahawh_Hmong
337
+ blk; Palmyrene ; Palmyrene
338
+ blk; Pau_Cin_Hau ; Pau_Cin_Hau
339
+ blk; Phags_Pa ; Phags_Pa
340
+ blk; Phaistos ; Phaistos_Disc
341
+ blk; Phoenician ; Phoenician
342
+ blk; Phonetic_Ext ; Phonetic_Extensions
343
+ blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
344
+ blk; Playing_Cards ; Playing_Cards
345
+ blk; Psalter_Pahlavi ; Psalter_Pahlavi
346
+ blk; PUA ; Private_Use_Area ; Private_Use
347
+ blk; Punctuation ; General_Punctuation
348
+ blk; Rejang ; Rejang
349
+ blk; Rumi ; Rumi_Numeral_Symbols
350
+ blk; Runic ; Runic
351
+ blk; Samaritan ; Samaritan
352
+ blk; Saurashtra ; Saurashtra
353
+ blk; Sharada ; Sharada
354
+ blk; Shavian ; Shavian
355
+ blk; Shorthand_Format_Controls ; Shorthand_Format_Controls
356
+ blk; Siddham ; Siddham
357
+ blk; Sinhala ; Sinhala
358
+ blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
359
+ blk; Small_Forms ; Small_Form_Variants
360
+ blk; Sora_Sompeng ; Sora_Sompeng
361
+ blk; Specials ; Specials
362
+ blk; Sundanese ; Sundanese
363
+ blk; Sundanese_Sup ; Sundanese_Supplement
364
+ blk; Sup_Arrows_A ; Supplemental_Arrows_A
365
+ blk; Sup_Arrows_B ; Supplemental_Arrows_B
366
+ blk; Sup_Arrows_C ; Supplemental_Arrows_C
367
+ blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
368
+ blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
369
+ blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
370
+ blk; Sup_Punctuation ; Supplemental_Punctuation
371
+ blk; Sup_Symbols_And_Pictographs ; Supplemental_Symbols_And_Pictographs
372
+ blk; Super_And_Sub ; Superscripts_And_Subscripts
373
+ blk; Sutton_SignWriting ; Sutton_SignWriting
374
+ blk; Syloti_Nagri ; Syloti_Nagri
375
+ blk; Syriac ; Syriac
376
+ blk; Tagalog ; Tagalog
377
+ blk; Tagbanwa ; Tagbanwa
378
+ blk; Tags ; Tags
379
+ blk; Tai_Le ; Tai_Le
380
+ blk; Tai_Tham ; Tai_Tham
381
+ blk; Tai_Viet ; Tai_Viet
382
+ blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
383
+ blk; Takri ; Takri
384
+ blk; Tamil ; Tamil
385
+ blk; Telugu ; Telugu
386
+ blk; Thaana ; Thaana
387
+ blk; Thai ; Thai
388
+ blk; Tibetan ; Tibetan
389
+ blk; Tifinagh ; Tifinagh
390
+ blk; Tirhuta ; Tirhuta
391
+ blk; Transport_And_Map ; Transport_And_Map_Symbols
392
+ blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
393
+ blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
394
+ blk; Ugaritic ; Ugaritic
395
+ blk; Vai ; Vai
396
+ blk; Vedic_Ext ; Vedic_Extensions
397
+ blk; Vertical_Forms ; Vertical_Forms
398
+ blk; VS ; Variation_Selectors
399
+ blk; VS_Sup ; Variation_Selectors_Supplement
400
+ blk; Warang_Citi ; Warang_Citi
401
+ blk; Yi_Radicals ; Yi_Radicals
402
+ blk; Yi_Syllables ; Yi_Syllables
403
+ blk; Yijing ; Yijing_Hexagram_Symbols
404
+
405
+ # Canonical_Combining_Class (ccc)
406
+
407
+ ccc; 0; NR ; Not_Reordered
408
+ ccc; 1; OV ; Overlay
409
+ ccc; 7; NK ; Nukta
410
+ ccc; 8; KV ; Kana_Voicing
411
+ ccc; 9; VR ; Virama
412
+ ccc; 10; CCC10 ; CCC10
413
+ ccc; 11; CCC11 ; CCC11
414
+ ccc; 12; CCC12 ; CCC12
415
+ ccc; 13; CCC13 ; CCC13
416
+ ccc; 14; CCC14 ; CCC14
417
+ ccc; 15; CCC15 ; CCC15
418
+ ccc; 16; CCC16 ; CCC16
419
+ ccc; 17; CCC17 ; CCC17
420
+ ccc; 18; CCC18 ; CCC18
421
+ ccc; 19; CCC19 ; CCC19
422
+ ccc; 20; CCC20 ; CCC20
423
+ ccc; 21; CCC21 ; CCC21
424
+ ccc; 22; CCC22 ; CCC22
425
+ ccc; 23; CCC23 ; CCC23
426
+ ccc; 24; CCC24 ; CCC24
427
+ ccc; 25; CCC25 ; CCC25
428
+ ccc; 26; CCC26 ; CCC26
429
+ ccc; 27; CCC27 ; CCC27
430
+ ccc; 28; CCC28 ; CCC28
431
+ ccc; 29; CCC29 ; CCC29
432
+ ccc; 30; CCC30 ; CCC30
433
+ ccc; 31; CCC31 ; CCC31
434
+ ccc; 32; CCC32 ; CCC32
435
+ ccc; 33; CCC33 ; CCC33
436
+ ccc; 34; CCC34 ; CCC34
437
+ ccc; 35; CCC35 ; CCC35
438
+ ccc; 36; CCC36 ; CCC36
439
+ ccc; 84; CCC84 ; CCC84
440
+ ccc; 91; CCC91 ; CCC91
441
+ ccc; 103; CCC103 ; CCC103
442
+ ccc; 107; CCC107 ; CCC107
443
+ ccc; 118; CCC118 ; CCC118
444
+ ccc; 122; CCC122 ; CCC122
445
+ ccc; 129; CCC129 ; CCC129
446
+ ccc; 130; CCC130 ; CCC130
447
+ ccc; 132; CCC132 ; CCC132
448
+ ccc; 133; CCC133 ; CCC133 # RESERVED
449
+ ccc; 200; ATBL ; Attached_Below_Left
450
+ ccc; 202; ATB ; Attached_Below
451
+ ccc; 214; ATA ; Attached_Above
452
+ ccc; 216; ATAR ; Attached_Above_Right
453
+ ccc; 218; BL ; Below_Left
454
+ ccc; 220; B ; Below
455
+ ccc; 222; BR ; Below_Right
456
+ ccc; 224; L ; Left
457
+ ccc; 226; R ; Right
458
+ ccc; 228; AL ; Above_Left
459
+ ccc; 230; A ; Above
460
+ ccc; 232; AR ; Above_Right
461
+ ccc; 233; DB ; Double_Below
462
+ ccc; 234; DA ; Double_Above
463
+ ccc; 240; IS ; Iota_Subscript
464
+
465
+ # Case_Folding (cf)
466
+
467
+ # @missing: 0000..10FFFF; Case_Folding; <code point>
468
+
469
+ # Case_Ignorable (CI)
470
+
471
+ CI ; N ; No ; F ; False
472
+ CI ; Y ; Yes ; T ; True
473
+
474
+ # Cased (Cased)
475
+
476
+ Cased; N ; No ; F ; False
477
+ Cased; Y ; Yes ; T ; True
478
+
479
+ # Changes_When_Casefolded (CWCF)
480
+
481
+ CWCF; N ; No ; F ; False
482
+ CWCF; Y ; Yes ; T ; True
483
+
484
+ # Changes_When_Casemapped (CWCM)
485
+
486
+ CWCM; N ; No ; F ; False
487
+ CWCM; Y ; Yes ; T ; True
488
+
489
+ # Changes_When_Lowercased (CWL)
490
+
491
+ CWL; N ; No ; F ; False
492
+ CWL; Y ; Yes ; T ; True
493
+
494
+ # Changes_When_NFKC_Casefolded (CWKCF)
495
+
496
+ CWKCF; N ; No ; F ; False
497
+ CWKCF; Y ; Yes ; T ; True
498
+
499
+ # Changes_When_Titlecased (CWT)
500
+
501
+ CWT; N ; No ; F ; False
502
+ CWT; Y ; Yes ; T ; True
503
+
504
+ # Changes_When_Uppercased (CWU)
505
+
506
+ CWU; N ; No ; F ; False
507
+ CWU; Y ; Yes ; T ; True
508
+
509
+ # Composition_Exclusion (CE)
510
+
511
+ CE ; N ; No ; F ; False
512
+ CE ; Y ; Yes ; T ; True
513
+
514
+ # Dash (Dash)
515
+
516
+ Dash; N ; No ; F ; False
517
+ Dash; Y ; Yes ; T ; True
518
+
519
+ # Decomposition_Mapping (dm)
520
+
521
+ # @missing: 0000..10FFFF; Decomposition_Mapping; <code point>
522
+
523
+ # Decomposition_Type (dt)
524
+
525
+ dt ; Can ; Canonical ; can
526
+ dt ; Com ; Compat ; com
527
+ dt ; Enc ; Circle ; enc
528
+ dt ; Fin ; Final ; fin
529
+ dt ; Font ; Font ; font
530
+ dt ; Fra ; Fraction ; fra
531
+ dt ; Init ; Initial ; init
532
+ dt ; Iso ; Isolated ; iso
533
+ dt ; Med ; Medial ; med
534
+ dt ; Nar ; Narrow ; nar
535
+ dt ; Nb ; Nobreak ; nb
536
+ dt ; None ; None ; none
537
+ dt ; Sml ; Small ; sml
538
+ dt ; Sqr ; Square ; sqr
539
+ dt ; Sub ; Sub ; sub
540
+ dt ; Sup ; Super ; sup
541
+ dt ; Vert ; Vertical ; vert
542
+ dt ; Wide ; Wide ; wide
543
+
544
+ # Default_Ignorable_Code_Point (DI)
545
+
546
+ DI ; N ; No ; F ; False
547
+ DI ; Y ; Yes ; T ; True
548
+
549
+ # Deprecated (Dep)
550
+
551
+ Dep; N ; No ; F ; False
552
+ Dep; Y ; Yes ; T ; True
553
+
554
+ # Diacritic (Dia)
555
+
556
+ Dia; N ; No ; F ; False
557
+ Dia; Y ; Yes ; T ; True
558
+
559
+ # East_Asian_Width (ea)
560
+
561
+ ea ; A ; Ambiguous
562
+ ea ; F ; Fullwidth
563
+ ea ; H ; Halfwidth
564
+ ea ; N ; Neutral
565
+ ea ; Na ; Narrow
566
+ ea ; W ; Wide
567
+
568
+ # Expands_On_NFC (XO_NFC)
569
+
570
+ XO_NFC; N ; No ; F ; False
571
+ XO_NFC; Y ; Yes ; T ; True
572
+
573
+ # Expands_On_NFD (XO_NFD)
574
+
575
+ XO_NFD; N ; No ; F ; False
576
+ XO_NFD; Y ; Yes ; T ; True
577
+
578
+ # Expands_On_NFKC (XO_NFKC)
579
+
580
+ XO_NFKC; N ; No ; F ; False
581
+ XO_NFKC; Y ; Yes ; T ; True
582
+
583
+ # Expands_On_NFKD (XO_NFKD)
584
+
585
+ XO_NFKD; N ; No ; F ; False
586
+ XO_NFKD; Y ; Yes ; T ; True
587
+
588
+ # Extender (Ext)
589
+
590
+ Ext; N ; No ; F ; False
591
+ Ext; Y ; Yes ; T ; True
592
+
593
+ # FC_NFKC_Closure (FC_NFKC)
594
+
595
+ # @missing: 0000..10FFFF; FC_NFKC_Closure; <code point>
596
+
597
+ # Full_Composition_Exclusion (Comp_Ex)
598
+
599
+ Comp_Ex; N ; No ; F ; False
600
+ Comp_Ex; Y ; Yes ; T ; True
601
+
602
+ # General_Category (gc)
603
+
604
+ gc ; C ; Other # Cc | Cf | Cn | Co | Cs
605
+ gc ; Cc ; Control ; cntrl
606
+ gc ; Cf ; Format
607
+ gc ; Cn ; Unassigned
608
+ gc ; Co ; Private_Use
609
+ gc ; Cs ; Surrogate
610
+ gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
611
+ gc ; LC ; Cased_Letter # Ll | Lt | Lu
612
+ gc ; Ll ; Lowercase_Letter
613
+ gc ; Lm ; Modifier_Letter
614
+ gc ; Lo ; Other_Letter
615
+ gc ; Lt ; Titlecase_Letter
616
+ gc ; Lu ; Uppercase_Letter
617
+ gc ; M ; Mark ; Combining_Mark # Mc | Me | Mn
618
+ gc ; Mc ; Spacing_Mark
619
+ gc ; Me ; Enclosing_Mark
620
+ gc ; Mn ; Nonspacing_Mark
621
+ gc ; N ; Number # Nd | Nl | No
622
+ gc ; Nd ; Decimal_Number ; digit
623
+ gc ; Nl ; Letter_Number
624
+ gc ; No ; Other_Number
625
+ gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
626
+ gc ; Pc ; Connector_Punctuation
627
+ gc ; Pd ; Dash_Punctuation
628
+ gc ; Pe ; Close_Punctuation
629
+ gc ; Pf ; Final_Punctuation
630
+ gc ; Pi ; Initial_Punctuation
631
+ gc ; Po ; Other_Punctuation
632
+ gc ; Ps ; Open_Punctuation
633
+ gc ; S ; Symbol # Sc | Sk | Sm | So
634
+ gc ; Sc ; Currency_Symbol
635
+ gc ; Sk ; Modifier_Symbol
636
+ gc ; Sm ; Math_Symbol
637
+ gc ; So ; Other_Symbol
638
+ gc ; Z ; Separator # Zl | Zp | Zs
639
+ gc ; Zl ; Line_Separator
640
+ gc ; Zp ; Paragraph_Separator
641
+ gc ; Zs ; Space_Separator
642
+ # @missing: 0000..10FFFF; General_Category; Unassigned
643
+
644
+ # Grapheme_Base (Gr_Base)
645
+
646
+ Gr_Base; N ; No ; F ; False
647
+ Gr_Base; Y ; Yes ; T ; True
648
+
649
+ # Grapheme_Cluster_Break (GCB)
650
+
651
+ GCB; CN ; Control
652
+ GCB; CR ; CR
653
+ GCB; EX ; Extend
654
+ GCB; L ; L
655
+ GCB; LF ; LF
656
+ GCB; LV ; LV
657
+ GCB; LVT ; LVT
658
+ GCB; PP ; Prepend
659
+ GCB; RI ; Regional_Indicator
660
+ GCB; SM ; SpacingMark
661
+ GCB; T ; T
662
+ GCB; V ; V
663
+ GCB; XX ; Other
664
+
665
+ # Grapheme_Extend (Gr_Ext)
666
+
667
+ Gr_Ext; N ; No ; F ; False
668
+ Gr_Ext; Y ; Yes ; T ; True
669
+
670
+ # Grapheme_Link (Gr_Link)
671
+
672
+ Gr_Link; N ; No ; F ; False
673
+ Gr_Link; Y ; Yes ; T ; True
674
+
675
+ # Hangul_Syllable_Type (hst)
676
+
677
+ hst; L ; Leading_Jamo
678
+ hst; LV ; LV_Syllable
679
+ hst; LVT ; LVT_Syllable
680
+ hst; NA ; Not_Applicable
681
+ hst; T ; Trailing_Jamo
682
+ hst; V ; Vowel_Jamo
683
+
684
+ # Hex_Digit (Hex)
685
+
686
+ Hex; N ; No ; F ; False
687
+ Hex; Y ; Yes ; T ; True
688
+
689
+ # Hyphen (Hyphen)
690
+
691
+ Hyphen; N ; No ; F ; False
692
+ Hyphen; Y ; Yes ; T ; True
693
+
694
+ # IDS_Binary_Operator (IDSB)
695
+
696
+ IDSB; N ; No ; F ; False
697
+ IDSB; Y ; Yes ; T ; True
698
+
699
+ # IDS_Trinary_Operator (IDST)
700
+
701
+ IDST; N ; No ; F ; False
702
+ IDST; Y ; Yes ; T ; True
703
+
704
+ # ID_Continue (IDC)
705
+
706
+ IDC; N ; No ; F ; False
707
+ IDC; Y ; Yes ; T ; True
708
+
709
+ # ID_Start (IDS)
710
+
711
+ IDS; N ; No ; F ; False
712
+ IDS; Y ; Yes ; T ; True
713
+
714
+ # ISO_Comment (isc)
715
+
716
+ # @missing: 0000..10FFFF; ISO_Comment; <none>
717
+
718
+ # Ideographic (Ideo)
719
+
720
+ Ideo; N ; No ; F ; False
721
+ Ideo; Y ; Yes ; T ; True
722
+
723
+ # Indic_Positional_Category (InPC)
724
+
725
+ InPC; Bottom ; Bottom
726
+ InPC; Bottom_And_Right ; Bottom_And_Right
727
+ InPC; Left ; Left
728
+ InPC; Left_And_Right ; Left_And_Right
729
+ InPC; NA ; NA
730
+ InPC; Overstruck ; Overstruck
731
+ InPC; Right ; Right
732
+ InPC; Top ; Top
733
+ InPC; Top_And_Bottom ; Top_And_Bottom
734
+ InPC; Top_And_Bottom_And_Right ; Top_And_Bottom_And_Right
735
+ InPC; Top_And_Left ; Top_And_Left
736
+ InPC; Top_And_Left_And_Right ; Top_And_Left_And_Right
737
+ InPC; Top_And_Right ; Top_And_Right
738
+ InPC; Visual_Order_Left ; Visual_Order_Left
739
+
740
+ # Indic_Syllabic_Category (InSC)
741
+
742
+ InSC; Avagraha ; Avagraha
743
+ InSC; Bindu ; Bindu
744
+ InSC; Brahmi_Joining_Number ; Brahmi_Joining_Number
745
+ InSC; Cantillation_Mark ; Cantillation_Mark
746
+ InSC; Consonant ; Consonant
747
+ InSC; Consonant_Dead ; Consonant_Dead
748
+ InSC; Consonant_Final ; Consonant_Final
749
+ InSC; Consonant_Head_Letter ; Consonant_Head_Letter
750
+ InSC; Consonant_Killer ; Consonant_Killer
751
+ InSC; Consonant_Medial ; Consonant_Medial
752
+ InSC; Consonant_Placeholder ; Consonant_Placeholder
753
+ InSC; Consonant_Preceding_Repha ; Consonant_Preceding_Repha
754
+ InSC; Consonant_Prefixed ; Consonant_Prefixed
755
+ InSC; Consonant_Subjoined ; Consonant_Subjoined
756
+ InSC; Consonant_Succeeding_Repha ; Consonant_Succeeding_Repha
757
+ InSC; Consonant_With_Stacker ; Consonant_With_Stacker
758
+ InSC; Gemination_Mark ; Gemination_Mark
759
+ InSC; Invisible_Stacker ; Invisible_Stacker
760
+ InSC; Joiner ; Joiner
761
+ InSC; Modifying_Letter ; Modifying_Letter
762
+ InSC; Non_Joiner ; Non_Joiner
763
+ InSC; Nukta ; Nukta
764
+ InSC; Number ; Number
765
+ InSC; Number_Joiner ; Number_Joiner
766
+ InSC; Other ; Other
767
+ InSC; Pure_Killer ; Pure_Killer
768
+ InSC; Register_Shifter ; Register_Shifter
769
+ InSC; Syllable_Modifier ; Syllable_Modifier
770
+ InSC; Tone_Letter ; Tone_Letter
771
+ InSC; Tone_Mark ; Tone_Mark
772
+ InSC; Virama ; Virama
773
+ InSC; Visarga ; Visarga
774
+ InSC; Vowel ; Vowel
775
+ InSC; Vowel_Dependent ; Vowel_Dependent
776
+ InSC; Vowel_Independent ; Vowel_Independent
777
+
778
+ # Jamo_Short_Name (JSN)
779
+
780
+ JSN; A ; A
781
+ JSN; AE ; AE
782
+ JSN; B ; B
783
+ JSN; BB ; BB
784
+ JSN; BS ; BS
785
+ JSN; C ; C
786
+ JSN; D ; D
787
+ JSN; DD ; DD
788
+ JSN; E ; E
789
+ JSN; EO ; EO
790
+ JSN; EU ; EU
791
+ JSN; G ; G
792
+ JSN; GG ; GG
793
+ JSN; GS ; GS
794
+ JSN; H ; H
795
+ JSN; I ; I
796
+ JSN; J ; J
797
+ JSN; JJ ; JJ
798
+ JSN; K ; K
799
+ JSN; L ; L
800
+ JSN; LB ; LB
801
+ JSN; LG ; LG
802
+ JSN; LH ; LH
803
+ JSN; LM ; LM
804
+ JSN; LP ; LP
805
+ JSN; LS ; LS
806
+ JSN; LT ; LT
807
+ JSN; M ; M
808
+ JSN; N ; N
809
+ JSN; NG ; NG
810
+ JSN; NH ; NH
811
+ JSN; NJ ; NJ
812
+ JSN; O ; O
813
+ JSN; OE ; OE
814
+ JSN; P ; P
815
+ JSN; R ; R
816
+ JSN; S ; S
817
+ JSN; SS ; SS
818
+ JSN; T ; T
819
+ JSN; U ; U
820
+ JSN; WA ; WA
821
+ JSN; WAE ; WAE
822
+ JSN; WE ; WE
823
+ JSN; WEO ; WEO
824
+ JSN; WI ; WI
825
+ JSN; YA ; YA
826
+ JSN; YAE ; YAE
827
+ JSN; YE ; YE
828
+ JSN; YEO ; YEO
829
+ JSN; YI ; YI
830
+ JSN; YO ; YO
831
+ JSN; YU ; YU
832
+ # @missing: 0000..10FFFF; Jamo_Short_Name; <none>
833
+
834
+ # Join_Control (Join_C)
835
+
836
+ Join_C; N ; No ; F ; False
837
+ Join_C; Y ; Yes ; T ; True
838
+
839
+ # Joining_Group (jg)
840
+
841
+ jg ; Ain ; Ain
842
+ jg ; Alaph ; Alaph
843
+ jg ; Alef ; Alef
844
+ jg ; Beh ; Beh
845
+ jg ; Beth ; Beth
846
+ jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
847
+ jg ; Dal ; Dal
848
+ jg ; Dalath_Rish ; Dalath_Rish
849
+ jg ; E ; E
850
+ jg ; Farsi_Yeh ; Farsi_Yeh
851
+ jg ; Fe ; Fe
852
+ jg ; Feh ; Feh
853
+ jg ; Final_Semkath ; Final_Semkath
854
+ jg ; Gaf ; Gaf
855
+ jg ; Gamal ; Gamal
856
+ jg ; Hah ; Hah
857
+ jg ; He ; He
858
+ jg ; Heh ; Heh
859
+ jg ; Heh_Goal ; Heh_Goal
860
+ jg ; Heth ; Heth
861
+ jg ; Kaf ; Kaf
862
+ jg ; Kaph ; Kaph
863
+ jg ; Khaph ; Khaph
864
+ jg ; Knotted_Heh ; Knotted_Heh
865
+ jg ; Lam ; Lam
866
+ jg ; Lamadh ; Lamadh
867
+ jg ; Manichaean_Aleph ; Manichaean_Aleph
868
+ jg ; Manichaean_Ayin ; Manichaean_Ayin
869
+ jg ; Manichaean_Beth ; Manichaean_Beth
870
+ jg ; Manichaean_Daleth ; Manichaean_Daleth
871
+ jg ; Manichaean_Dhamedh ; Manichaean_Dhamedh
872
+ jg ; Manichaean_Five ; Manichaean_Five
873
+ jg ; Manichaean_Gimel ; Manichaean_Gimel
874
+ jg ; Manichaean_Heth ; Manichaean_Heth
875
+ jg ; Manichaean_Hundred ; Manichaean_Hundred
876
+ jg ; Manichaean_Kaph ; Manichaean_Kaph
877
+ jg ; Manichaean_Lamedh ; Manichaean_Lamedh
878
+ jg ; Manichaean_Mem ; Manichaean_Mem
879
+ jg ; Manichaean_Nun ; Manichaean_Nun
880
+ jg ; Manichaean_One ; Manichaean_One
881
+ jg ; Manichaean_Pe ; Manichaean_Pe
882
+ jg ; Manichaean_Qoph ; Manichaean_Qoph
883
+ jg ; Manichaean_Resh ; Manichaean_Resh
884
+ jg ; Manichaean_Sadhe ; Manichaean_Sadhe
885
+ jg ; Manichaean_Samekh ; Manichaean_Samekh
886
+ jg ; Manichaean_Taw ; Manichaean_Taw
887
+ jg ; Manichaean_Ten ; Manichaean_Ten
888
+ jg ; Manichaean_Teth ; Manichaean_Teth
889
+ jg ; Manichaean_Thamedh ; Manichaean_Thamedh
890
+ jg ; Manichaean_Twenty ; Manichaean_Twenty
891
+ jg ; Manichaean_Waw ; Manichaean_Waw
892
+ jg ; Manichaean_Yodh ; Manichaean_Yodh
893
+ jg ; Manichaean_Zayin ; Manichaean_Zayin
894
+ jg ; Meem ; Meem
895
+ jg ; Mim ; Mim
896
+ jg ; No_Joining_Group ; No_Joining_Group
897
+ jg ; Noon ; Noon
898
+ jg ; Nun ; Nun
899
+ jg ; Nya ; Nya
900
+ jg ; Pe ; Pe
901
+ jg ; Qaf ; Qaf
902
+ jg ; Qaph ; Qaph
903
+ jg ; Reh ; Reh
904
+ jg ; Reversed_Pe ; Reversed_Pe
905
+ jg ; Rohingya_Yeh ; Rohingya_Yeh
906
+ jg ; Sad ; Sad
907
+ jg ; Sadhe ; Sadhe
908
+ jg ; Seen ; Seen
909
+ jg ; Semkath ; Semkath
910
+ jg ; Shin ; Shin
911
+ jg ; Straight_Waw ; Straight_Waw
912
+ jg ; Swash_Kaf ; Swash_Kaf
913
+ jg ; Syriac_Waw ; Syriac_Waw
914
+ jg ; Tah ; Tah
915
+ jg ; Taw ; Taw
916
+ jg ; Teh_Marbuta ; Teh_Marbuta
917
+ jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
918
+ jg ; Teth ; Teth
919
+ jg ; Waw ; Waw
920
+ jg ; Yeh ; Yeh
921
+ jg ; Yeh_Barree ; Yeh_Barree
922
+ jg ; Yeh_With_Tail ; Yeh_With_Tail
923
+ jg ; Yudh ; Yudh
924
+ jg ; Yudh_He ; Yudh_He
925
+ jg ; Zain ; Zain
926
+ jg ; Zhain ; Zhain
927
+
928
+ # Joining_Type (jt)
929
+
930
+ jt ; C ; Join_Causing
931
+ jt ; D ; Dual_Joining
932
+ jt ; L ; Left_Joining
933
+ jt ; R ; Right_Joining
934
+ jt ; T ; Transparent
935
+ jt ; U ; Non_Joining
936
+
937
+ # Line_Break (lb)
938
+
939
+ lb ; AI ; Ambiguous
940
+ lb ; AL ; Alphabetic
941
+ lb ; B2 ; Break_Both
942
+ lb ; BA ; Break_After
943
+ lb ; BB ; Break_Before
944
+ lb ; BK ; Mandatory_Break
945
+ lb ; CB ; Contingent_Break
946
+ lb ; CJ ; Conditional_Japanese_Starter
947
+ lb ; CL ; Close_Punctuation
948
+ lb ; CM ; Combining_Mark
949
+ lb ; CP ; Close_Parenthesis
950
+ lb ; CR ; Carriage_Return
951
+ lb ; EX ; Exclamation
952
+ lb ; GL ; Glue
953
+ lb ; H2 ; H2
954
+ lb ; H3 ; H3
955
+ lb ; HL ; Hebrew_Letter
956
+ lb ; HY ; Hyphen
957
+ lb ; ID ; Ideographic
958
+ lb ; IN ; Inseparable ; Inseperable
959
+ lb ; IS ; Infix_Numeric
960
+ lb ; JL ; JL
961
+ lb ; JT ; JT
962
+ lb ; JV ; JV
963
+ lb ; LF ; Line_Feed
964
+ lb ; NL ; Next_Line
965
+ lb ; NS ; Nonstarter
966
+ lb ; NU ; Numeric
967
+ lb ; OP ; Open_Punctuation
968
+ lb ; PO ; Postfix_Numeric
969
+ lb ; PR ; Prefix_Numeric
970
+ lb ; QU ; Quotation
971
+ lb ; RI ; Regional_Indicator
972
+ lb ; SA ; Complex_Context
973
+ lb ; SG ; Surrogate
974
+ lb ; SP ; Space
975
+ lb ; SY ; Break_Symbols
976
+ lb ; WJ ; Word_Joiner
977
+ lb ; XX ; Unknown
978
+ lb ; ZW ; ZWSpace
979
+
980
+ # Logical_Order_Exception (LOE)
981
+
982
+ LOE; N ; No ; F ; False
983
+ LOE; Y ; Yes ; T ; True
984
+
985
+ # Lowercase (Lower)
986
+
987
+ Lower; N ; No ; F ; False
988
+ Lower; Y ; Yes ; T ; True
989
+
990
+ # Lowercase_Mapping (lc)
991
+
992
+ # @missing: 0000..10FFFF; Lowercase_Mapping; <code point>
993
+
994
+ # Math (Math)
995
+
996
+ Math; N ; No ; F ; False
997
+ Math; Y ; Yes ; T ; True
998
+
999
+ # NFC_Quick_Check (NFC_QC)
1000
+
1001
+ NFC_QC; M ; Maybe
1002
+ NFC_QC; N ; No
1003
+ NFC_QC; Y ; Yes
1004
+
1005
+ # NFD_Quick_Check (NFD_QC)
1006
+
1007
+ NFD_QC; N ; No
1008
+ NFD_QC; Y ; Yes
1009
+
1010
+ # NFKC_Casefold (NFKC_CF)
1011
+
1012
+ # @missing: 0000..10FFFF; NFKC_Casefold; <code point>
1013
+
1014
+ # NFKC_Quick_Check (NFKC_QC)
1015
+
1016
+ NFKC_QC; M ; Maybe
1017
+ NFKC_QC; N ; No
1018
+ NFKC_QC; Y ; Yes
1019
+
1020
+ # NFKD_Quick_Check (NFKD_QC)
1021
+
1022
+ NFKD_QC; N ; No
1023
+ NFKD_QC; Y ; Yes
1024
+
1025
+ # Name (na)
1026
+
1027
+ # @missing: 0000..10FFFF; Name; <none>
1028
+
1029
+ # Name_Alias (Name_Alias)
1030
+
1031
+ # @missing: 0000..10FFFF; Name_Alias; <none>
1032
+
1033
+ # Noncharacter_Code_Point (NChar)
1034
+
1035
+ NChar; N ; No ; F ; False
1036
+ NChar; Y ; Yes ; T ; True
1037
+
1038
+ # Numeric_Type (nt)
1039
+
1040
+ nt ; De ; Decimal
1041
+ nt ; Di ; Digit
1042
+ nt ; None ; None
1043
+ nt ; Nu ; Numeric
1044
+
1045
+ # Numeric_Value (nv)
1046
+
1047
+ # @missing: 0000..10FFFF; Numeric_Value; NaN
1048
+
1049
+ # Other_Alphabetic (OAlpha)
1050
+
1051
+ OAlpha; N ; No ; F ; False
1052
+ OAlpha; Y ; Yes ; T ; True
1053
+
1054
+ # Other_Default_Ignorable_Code_Point (ODI)
1055
+
1056
+ ODI; N ; No ; F ; False
1057
+ ODI; Y ; Yes ; T ; True
1058
+
1059
+ # Other_Grapheme_Extend (OGr_Ext)
1060
+
1061
+ OGr_Ext; N ; No ; F ; False
1062
+ OGr_Ext; Y ; Yes ; T ; True
1063
+
1064
+ # Other_ID_Continue (OIDC)
1065
+
1066
+ OIDC; N ; No ; F ; False
1067
+ OIDC; Y ; Yes ; T ; True
1068
+
1069
+ # Other_ID_Start (OIDS)
1070
+
1071
+ OIDS; N ; No ; F ; False
1072
+ OIDS; Y ; Yes ; T ; True
1073
+
1074
+ # Other_Lowercase (OLower)
1075
+
1076
+ OLower; N ; No ; F ; False
1077
+ OLower; Y ; Yes ; T ; True
1078
+
1079
+ # Other_Math (OMath)
1080
+
1081
+ OMath; N ; No ; F ; False
1082
+ OMath; Y ; Yes ; T ; True
1083
+
1084
+ # Other_Uppercase (OUpper)
1085
+
1086
+ OUpper; N ; No ; F ; False
1087
+ OUpper; Y ; Yes ; T ; True
1088
+
1089
+ # Pattern_Syntax (Pat_Syn)
1090
+
1091
+ Pat_Syn; N ; No ; F ; False
1092
+ Pat_Syn; Y ; Yes ; T ; True
1093
+
1094
+ # Pattern_White_Space (Pat_WS)
1095
+
1096
+ Pat_WS; N ; No ; F ; False
1097
+ Pat_WS; Y ; Yes ; T ; True
1098
+
1099
+ # Quotation_Mark (QMark)
1100
+
1101
+ QMark; N ; No ; F ; False
1102
+ QMark; Y ; Yes ; T ; True
1103
+
1104
+ # Radical (Radical)
1105
+
1106
+ Radical; N ; No ; F ; False
1107
+ Radical; Y ; Yes ; T ; True
1108
+
1109
+ # STerm (STerm)
1110
+
1111
+ STerm; N ; No ; F ; False
1112
+ STerm; Y ; Yes ; T ; True
1113
+
1114
+ # Script (sc)
1115
+
1116
+ sc ; Aghb ; Caucasian_Albanian
1117
+ sc ; Ahom ; Ahom
1118
+ sc ; Arab ; Arabic
1119
+ sc ; Armi ; Imperial_Aramaic
1120
+ sc ; Armn ; Armenian
1121
+ sc ; Avst ; Avestan
1122
+ sc ; Bali ; Balinese
1123
+ sc ; Bamu ; Bamum
1124
+ sc ; Bass ; Bassa_Vah
1125
+ sc ; Batk ; Batak
1126
+ sc ; Beng ; Bengali
1127
+ sc ; Bopo ; Bopomofo
1128
+ sc ; Brah ; Brahmi
1129
+ sc ; Brai ; Braille
1130
+ sc ; Bugi ; Buginese
1131
+ sc ; Buhd ; Buhid
1132
+ sc ; Cakm ; Chakma
1133
+ sc ; Cans ; Canadian_Aboriginal
1134
+ sc ; Cari ; Carian
1135
+ sc ; Cham ; Cham
1136
+ sc ; Cher ; Cherokee
1137
+ sc ; Copt ; Coptic ; Qaac
1138
+ sc ; Cprt ; Cypriot
1139
+ sc ; Cyrl ; Cyrillic
1140
+ sc ; Deva ; Devanagari
1141
+ sc ; Dsrt ; Deseret
1142
+ sc ; Dupl ; Duployan
1143
+ sc ; Egyp ; Egyptian_Hieroglyphs
1144
+ sc ; Elba ; Elbasan
1145
+ sc ; Ethi ; Ethiopic
1146
+ sc ; Geor ; Georgian
1147
+ sc ; Glag ; Glagolitic
1148
+ sc ; Goth ; Gothic
1149
+ sc ; Gran ; Grantha
1150
+ sc ; Grek ; Greek
1151
+ sc ; Gujr ; Gujarati
1152
+ sc ; Guru ; Gurmukhi
1153
+ sc ; Hang ; Hangul
1154
+ sc ; Hani ; Han
1155
+ sc ; Hano ; Hanunoo
1156
+ sc ; Hatr ; Hatran
1157
+ sc ; Hebr ; Hebrew
1158
+ sc ; Hira ; Hiragana
1159
+ sc ; Hluw ; Anatolian_Hieroglyphs
1160
+ sc ; Hmng ; Pahawh_Hmong
1161
+ sc ; Hrkt ; Katakana_Or_Hiragana
1162
+ sc ; Hung ; Old_Hungarian
1163
+ sc ; Ital ; Old_Italic
1164
+ sc ; Java ; Javanese
1165
+ sc ; Kali ; Kayah_Li
1166
+ sc ; Kana ; Katakana
1167
+ sc ; Khar ; Kharoshthi
1168
+ sc ; Khmr ; Khmer
1169
+ sc ; Khoj ; Khojki
1170
+ sc ; Knda ; Kannada
1171
+ sc ; Kthi ; Kaithi
1172
+ sc ; Lana ; Tai_Tham
1173
+ sc ; Laoo ; Lao
1174
+ sc ; Latn ; Latin
1175
+ sc ; Lepc ; Lepcha
1176
+ sc ; Limb ; Limbu
1177
+ sc ; Lina ; Linear_A
1178
+ sc ; Linb ; Linear_B
1179
+ sc ; Lisu ; Lisu
1180
+ sc ; Lyci ; Lycian
1181
+ sc ; Lydi ; Lydian
1182
+ sc ; Mahj ; Mahajani
1183
+ sc ; Mand ; Mandaic
1184
+ sc ; Mani ; Manichaean
1185
+ sc ; Mend ; Mende_Kikakui
1186
+ sc ; Merc ; Meroitic_Cursive
1187
+ sc ; Mero ; Meroitic_Hieroglyphs
1188
+ sc ; Mlym ; Malayalam
1189
+ sc ; Modi ; Modi
1190
+ sc ; Mong ; Mongolian
1191
+ sc ; Mroo ; Mro
1192
+ sc ; Mtei ; Meetei_Mayek
1193
+ sc ; Mult ; Multani
1194
+ sc ; Mymr ; Myanmar
1195
+ sc ; Narb ; Old_North_Arabian
1196
+ sc ; Nbat ; Nabataean
1197
+ sc ; Nkoo ; Nko
1198
+ sc ; Ogam ; Ogham
1199
+ sc ; Olck ; Ol_Chiki
1200
+ sc ; Orkh ; Old_Turkic
1201
+ sc ; Orya ; Oriya
1202
+ sc ; Osma ; Osmanya
1203
+ sc ; Palm ; Palmyrene
1204
+ sc ; Pauc ; Pau_Cin_Hau
1205
+ sc ; Perm ; Old_Permic
1206
+ sc ; Phag ; Phags_Pa
1207
+ sc ; Phli ; Inscriptional_Pahlavi
1208
+ sc ; Phlp ; Psalter_Pahlavi
1209
+ sc ; Phnx ; Phoenician
1210
+ sc ; Plrd ; Miao
1211
+ sc ; Prti ; Inscriptional_Parthian
1212
+ sc ; Rjng ; Rejang
1213
+ sc ; Runr ; Runic
1214
+ sc ; Samr ; Samaritan
1215
+ sc ; Sarb ; Old_South_Arabian
1216
+ sc ; Saur ; Saurashtra
1217
+ sc ; Sgnw ; SignWriting
1218
+ sc ; Shaw ; Shavian
1219
+ sc ; Shrd ; Sharada
1220
+ sc ; Sidd ; Siddham
1221
+ sc ; Sind ; Khudawadi
1222
+ sc ; Sinh ; Sinhala
1223
+ sc ; Sora ; Sora_Sompeng
1224
+ sc ; Sund ; Sundanese
1225
+ sc ; Sylo ; Syloti_Nagri
1226
+ sc ; Syrc ; Syriac
1227
+ sc ; Tagb ; Tagbanwa
1228
+ sc ; Takr ; Takri
1229
+ sc ; Tale ; Tai_Le
1230
+ sc ; Talu ; New_Tai_Lue
1231
+ sc ; Taml ; Tamil
1232
+ sc ; Tavt ; Tai_Viet
1233
+ sc ; Telu ; Telugu
1234
+ sc ; Tfng ; Tifinagh
1235
+ sc ; Tglg ; Tagalog
1236
+ sc ; Thaa ; Thaana
1237
+ sc ; Thai ; Thai
1238
+ sc ; Tibt ; Tibetan
1239
+ sc ; Tirh ; Tirhuta
1240
+ sc ; Ugar ; Ugaritic
1241
+ sc ; Vaii ; Vai
1242
+ sc ; Wara ; Warang_Citi
1243
+ sc ; Xpeo ; Old_Persian
1244
+ sc ; Xsux ; Cuneiform
1245
+ sc ; Yiii ; Yi
1246
+ sc ; Zinh ; Inherited ; Qaai
1247
+ sc ; Zyyy ; Common
1248
+ sc ; Zzzz ; Unknown
1249
+
1250
+ # Script_Extensions (scx)
1251
+
1252
+ # @missing: 0000..10FFFF; Script_Extensions; <script>
1253
+
1254
+ # Sentence_Break (SB)
1255
+
1256
+ SB ; AT ; ATerm
1257
+ SB ; CL ; Close
1258
+ SB ; CR ; CR
1259
+ SB ; EX ; Extend
1260
+ SB ; FO ; Format
1261
+ SB ; LE ; OLetter
1262
+ SB ; LF ; LF
1263
+ SB ; LO ; Lower
1264
+ SB ; NU ; Numeric
1265
+ SB ; SC ; SContinue
1266
+ SB ; SE ; Sep
1267
+ SB ; SP ; Sp
1268
+ SB ; ST ; STerm
1269
+ SB ; UP ; Upper
1270
+ SB ; XX ; Other
1271
+
1272
+ # Simple_Case_Folding (scf)
1273
+
1274
+ # @missing: 0000..10FFFF; Simple_Case_Folding; <code point>
1275
+
1276
+ # Simple_Lowercase_Mapping (slc)
1277
+
1278
+ # @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
1279
+
1280
+ # Simple_Titlecase_Mapping (stc)
1281
+
1282
+ # @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
1283
+
1284
+ # Simple_Uppercase_Mapping (suc)
1285
+
1286
+ # @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
1287
+
1288
+ # Soft_Dotted (SD)
1289
+
1290
+ SD ; N ; No ; F ; False
1291
+ SD ; Y ; Yes ; T ; True
1292
+
1293
+ # Terminal_Punctuation (Term)
1294
+
1295
+ Term; N ; No ; F ; False
1296
+ Term; Y ; Yes ; T ; True
1297
+
1298
+ # Titlecase_Mapping (tc)
1299
+
1300
+ # @missing: 0000..10FFFF; Titlecase_Mapping; <code point>
1301
+
1302
+ # Unicode_1_Name (na1)
1303
+
1304
+ # @missing: 0000..10FFFF; Unicode_1_Name; <none>
1305
+
1306
+ # Unified_Ideograph (UIdeo)
1307
+
1308
+ UIdeo; N ; No ; F ; False
1309
+ UIdeo; Y ; Yes ; T ; True
1310
+
1311
+ # Uppercase (Upper)
1312
+
1313
+ Upper; N ; No ; F ; False
1314
+ Upper; Y ; Yes ; T ; True
1315
+
1316
+ # Uppercase_Mapping (uc)
1317
+
1318
+ # @missing: 0000..10FFFF; Uppercase_Mapping; <code point>
1319
+
1320
+ # Variation_Selector (VS)
1321
+
1322
+ VS ; N ; No ; F ; False
1323
+ VS ; Y ; Yes ; T ; True
1324
+
1325
+ # White_Space (WSpace)
1326
+
1327
+ WSpace; N ; No ; F ; False
1328
+ WSpace; Y ; Yes ; T ; True
1329
+
1330
+ # Word_Break (WB)
1331
+
1332
+ WB ; CR ; CR
1333
+ WB ; DQ ; Double_Quote
1334
+ WB ; EX ; ExtendNumLet
1335
+ WB ; Extend ; Extend
1336
+ WB ; FO ; Format
1337
+ WB ; HL ; Hebrew_Letter
1338
+ WB ; KA ; Katakana
1339
+ WB ; LE ; ALetter
1340
+ WB ; LF ; LF
1341
+ WB ; MB ; MidNumLet
1342
+ WB ; ML ; MidLetter
1343
+ WB ; MN ; MidNum
1344
+ WB ; NL ; Newline
1345
+ WB ; NU ; Numeric
1346
+ WB ; RI ; Regional_Indicator
1347
+ WB ; SQ ; Single_Quote
1348
+ WB ; XX ; Other
1349
+
1350
+ # XID_Continue (XIDC)
1351
+
1352
+ XIDC; N ; No ; F ; False
1353
+ XIDC; Y ; Yes ; T ; True
1354
+
1355
+ # XID_Start (XIDS)
1356
+
1357
+ XIDS; N ; No ; F ; False
1358
+ XIDS; Y ; Yes ; T ; True
1359
+
1360
+ # cjkAccountingNumeric (cjkAccountingNumeric)
1361
+
1362
+ # @missing: 0000..10FFFF; cjkAccountingNumeric; NaN
1363
+
1364
+ # cjkCompatibilityVariant (cjkCompatibilityVariant)
1365
+
1366
+ # @missing: 0000..10FFFF; cjkCompatibilityVariant; <code point>
1367
+
1368
+ # cjkIICore (cjkIICore)
1369
+
1370
+ # @missing: 0000..10FFFF; cjkIICore; <none>
1371
+
1372
+ # cjkIRG_GSource (cjkIRG_GSource)
1373
+
1374
+ # @missing: 0000..10FFFF; cjkIRG_GSource; <none>
1375
+
1376
+ # cjkIRG_HSource (cjkIRG_HSource)
1377
+
1378
+ # @missing: 0000..10FFFF; cjkIRG_HSource; <none>
1379
+
1380
+ # cjkIRG_JSource (cjkIRG_JSource)
1381
+
1382
+ # @missing: 0000..10FFFF; cjkIRG_JSource; <none>
1383
+
1384
+ # cjkIRG_KPSource (cjkIRG_KPSource)
1385
+
1386
+ # @missing: 0000..10FFFF; cjkIRG_KPSource; <none>
1387
+
1388
+ # cjkIRG_KSource (cjkIRG_KSource)
1389
+
1390
+ # @missing: 0000..10FFFF; cjkIRG_KSource; <none>
1391
+
1392
+ # cjkIRG_MSource (cjkIRG_MSource)
1393
+
1394
+ # @missing: 0000..10FFFF; cjkIRG_MSource; <none>
1395
+
1396
+ # cjkIRG_TSource (cjkIRG_TSource)
1397
+
1398
+ # @missing: 0000..10FFFF; cjkIRG_TSource; <none>
1399
+
1400
+ # cjkIRG_USource (cjkIRG_USource)
1401
+
1402
+ # @missing: 0000..10FFFF; cjkIRG_USource; <none>
1403
+
1404
+ # cjkIRG_VSource (cjkIRG_VSource)
1405
+
1406
+ # @missing: 0000..10FFFF; cjkIRG_VSource; <none>
1407
+
1408
+ # cjkOtherNumeric (cjkOtherNumeric)
1409
+
1410
+ # @missing: 0000..10FFFF; cjkOtherNumeric; NaN
1411
+
1412
+ # cjkPrimaryNumeric (cjkPrimaryNumeric)
1413
+
1414
+ # @missing: 0000..10FFFF; cjkPrimaryNumeric; NaN
1415
+
1416
+ # cjkRSUnicode (cjkRSUnicode)
1417
+
1418
+ # @missing: 0000..10FFFF; cjkRSUnicode; <none>
1419
+
1420
+ # EOF