blackwinter-cmess 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (49) hide show
  1. data/COPYING +676 -0
  2. data/ChangeLog +54 -0
  3. data/README +63 -0
  4. data/Rakefile +51 -0
  5. data/bin/bconv +130 -0
  6. data/bin/cinderella +190 -0
  7. data/bin/decode_entities +106 -0
  8. data/bin/guess_encoding +223 -0
  9. data/data/chartab.yaml +26724 -0
  10. data/data/csets/iso_8859-1.yaml +195 -0
  11. data/data/csets/iso_8859-15.yaml +204 -0
  12. data/data/csets/latin1.yaml +195 -0
  13. data/data/csets/unicode/basic_latin.yaml +97 -0
  14. data/data/csets/unicode/cyrillic-supplement.yaml +17 -0
  15. data/data/csets/unicode/cyrillic.yaml +256 -0
  16. data/data/csets/unicode/greek.yaml +129 -0
  17. data/data/csets/unicode/ipa_extensions.yaml +97 -0
  18. data/data/csets/unicode/latin-extended-c.yaml +18 -0
  19. data/data/csets/unicode/latin-extended-d.yaml +3 -0
  20. data/data/csets/unicode/latin_1_supplement.yaml +128 -0
  21. data/data/csets/unicode/latin_extended_a.yaml +129 -0
  22. data/data/csets/unicode/latin_extended_additional.yaml +247 -0
  23. data/data/csets/unicode/latin_extended_b.yaml +209 -0
  24. data/data/csets/unicode/letterlike_symbols.yaml +80 -0
  25. data/data/csets/unicode/spacing_modifier_letters.yaml +81 -0
  26. data/data/csets/utf-8.yaml +1504 -0
  27. data/data/csets/utf8.yaml +1504 -0
  28. data/data/test_chars.yaml +14 -0
  29. data/example/cinderella/crop +127 -0
  30. data/example/cinderella/crop_repaired +127 -0
  31. data/example/cinderella/empty6-slash.txt +1495 -0
  32. data/example/cinderella/empty6-slash_repaired.txt +1495 -0
  33. data/example/cinderella/pot +1368 -0
  34. data/example/guess_encoding/check_results +60 -0
  35. data/example/guess_encoding/de.utf-8.txt +10030 -0
  36. data/example/guess_encoding/en.utf-8.txt +10030 -0
  37. data/example/guess_encoding/fr.utf-8.txt +10030 -0
  38. data/example/guess_encoding/it.utf-8.txt +10030 -0
  39. data/lib/cmess/bconv.rb +169 -0
  40. data/lib/cmess/cinderella.rb +66 -0
  41. data/lib/cmess/cli.rb +120 -0
  42. data/lib/cmess/decode_entities.rb +69 -0
  43. data/lib/cmess/guess_encoding/automatic.rb +343 -0
  44. data/lib/cmess/guess_encoding/encoding.rb +78 -0
  45. data/lib/cmess/guess_encoding/manual.rb +108 -0
  46. data/lib/cmess/guess_encoding.rb +61 -0
  47. data/lib/cmess/version.rb +51 -0
  48. data/lib/cmess.rb +49 -0
  49. metadata +136 -0
data/data/csets/unicode/latin_extended_a.yaml ADDED
@@ -0,0 +1,129 @@
1
+ ---
2
+ - "Ā" # LATIN CAPITAL LETTER A WITH MACRON
3
+ - "ā" # LATIN SMALL LETTER A WITH MACRON
4
+ - "Ă" # LATIN CAPITAL LETTER A WITH BREVE
5
+ - "ă" # LATIN SMALL LETTER A WITH BREVE
6
+ - "Ą" # LATIN CAPITAL LETTER A WITH OGONEK
7
+ - "ą" # LATIN SMALL LETTER A WITH OGONEK
8
+ - "Ć" # LATIN CAPITAL LETTER C WITH ACUTE
9
+ - "ć" # LATIN SMALL LETTER C WITH ACUTE
10
+ - "Ĉ" # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
11
+ - "ĉ" # LATIN SMALL LETTER C WITH CIRCUMFLEX
12
+ - "Ċ" # LATIN CAPITAL LETTER C WITH DOT ABOVE
13
+ - "ċ" # LATIN SMALL LETTER C WITH DOT ABOVE
14
+ - "Č" # LATIN CAPITAL LETTER C WITH CARON
15
+ - "č" # LATIN SMALL LETTER C WITH CARON
16
+ - "Ď" # LATIN CAPITAL LETTER D WITH CARON
17
+ - "ď" # LATIN SMALL LETTER D WITH CARON
18
+ - "Đ" # LATIN CAPITAL LETTER D WITH STROKE
19
+ - "đ" # LATIN SMALL LETTER D WITH STROKE
20
+ - "Ē" # LATIN CAPITAL LETTER E WITH MACRON
21
+ - "ē" # LATIN SMALL LETTER E WITH MACRON
22
+ - "Ĕ" # LATIN CAPITAL LETTER E WITH BREVE
23
+ - "ĕ" # LATIN SMALL LETTER E WITH BREVE
24
+ - "Ė" # LATIN CAPITAL LETTER E WITH DOT ABOVE
25
+ - "ė" # LATIN SMALL LETTER E WITH DOT ABOVE
26
+ - "Ę" # LATIN CAPITAL LETTER E WITH OGONEK
27
+ - "ę" # LATIN SMALL LETTER E WITH OGONEK
28
+ - "Ě" # LATIN CAPITAL LETTER E WITH CARON
29
+ - "ě" # LATIN SMALL LETTER E WITH CARON
30
+ - "Ĝ" # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
31
+ - "ĝ" # LATIN SMALL LETTER G WITH CIRCUMFLEX
32
+ - "Ğ" # LATIN CAPITAL LETTER G WITH BREVE
33
+ - "ğ" # LATIN SMALL LETTER G WITH BREVE
34
+ - "Ġ" # LATIN CAPITAL LETTER G WITH DOT ABOVE
35
+ - "ġ" # LATIN SMALL LETTER G WITH DOT ABOVE
36
+ - "Ģ" # LATIN CAPITAL LETTER G WITH CEDILLA
37
+ - "ģ" # LATIN SMALL LETTER G WITH CEDILLA
38
+ - "Ĥ" # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
39
+ - "ĥ" # LATIN SMALL LETTER H WITH CIRCUMFLEX
40
+ - "Ħ" # LATIN CAPITAL LETTER H WITH STROKE
41
+ - "ħ" # LATIN SMALL LETTER H WITH STROKE
42
+ - "Ĩ" # LATIN CAPITAL LETTER I WITH TILDE
43
+ - "ĩ" # LATIN SMALL LETTER I WITH TILDE
44
+ - "Ī" # LATIN CAPITAL LETTER I WITH MACRON
45
+ - "ī" # LATIN SMALL LETTER I WITH MACRON
46
+ - "Ĭ" # LATIN CAPITAL LETTER I WITH BREVE
47
+ - "ĭ" # LATIN SMALL LETTER I WITH BREVE
48
+ - "Į" # LATIN CAPITAL LETTER I WITH OGONEK
49
+ - "į" # LATIN SMALL LETTER I WITH OGONEK
50
+ - "İ" # LATIN CAPITAL LETTER I WITH DOT ABOVE
51
+ - "ı" # LATIN SMALL LETTER DOTLESS I
52
+ - "IJ" # LATIN CAPITAL LIGATURE IJ
53
+ - "ij" # LATIN SMALL LIGATURE IJ
54
+ - "Ĵ" # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
55
+ - "ĵ" # LATIN SMALL LETTER J WITH CIRCUMFLEX
56
+ - "Ķ" # LATIN CAPITAL LETTER K WITH CEDILLA
57
+ - "ķ" # LATIN SMALL LETTER K WITH CEDILLA
58
+ - "ĸ" # LATIN SMALL LETTER KRA
59
+ - "Ĺ" # LATIN CAPITAL LETTER L WITH ACUTE
60
+ - "ĺ" # LATIN SMALL LETTER L WITH ACUTE
61
+ - "Ļ" # LATIN CAPITAL LETTER L WITH CEDILLA
62
+ - "ļ" # LATIN SMALL LETTER L WITH CEDILLA
63
+ - "Ľ" # LATIN CAPITAL LETTER L WITH CARON
64
+ - "ľ" # LATIN SMALL LETTER L WITH CARON
65
+ - "Ŀ" # LATIN CAPITAL LETTER L WITH MIDDLE DOT
66
+ - "ŀ" # LATIN SMALL LETTER L WITH MIDDLE DOT
67
+ - "Ł" # LATIN CAPITAL LETTER L WITH STROKE
68
+ - "ł" # LATIN SMALL LETTER L WITH STROKE
69
+ - "Ń" # LATIN CAPITAL LETTER N WITH ACUTE
70
+ - "ń" # LATIN SMALL LETTER N WITH ACUTE
71
+ - "Ņ" # LATIN CAPITAL LETTER N WITH CEDILLA
72
+ - "ņ" # LATIN SMALL LETTER N WITH CEDILLA
73
+ - "Ň" # LATIN CAPITAL LETTER N WITH CARON
74
+ - "ň" # LATIN SMALL LETTER N WITH CARON
75
+ - "ʼn" # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
76
+ - "Ŋ" # LATIN CAPITAL LETTER ENG
77
+ - "ŋ" # LATIN SMALL LETTER ENG
78
+ - "Ō" # LATIN CAPITAL LETTER O WITH MACRON
79
+ - "ō" # LATIN SMALL LETTER O WITH MACRON
80
+ - "Ŏ" # LATIN CAPITAL LETTER O WITH BREVE
81
+ - "ŏ" # LATIN SMALL LETTER O WITH BREVE
82
+ - "Ő" # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
83
+ - "ő" # LATIN SMALL LETTER O WITH DOUBLE ACUTE
84
+ - "Œ" # LATIN CAPITAL LIGATURE OE
85
+ - "œ" # LATIN SMALL LIGATURE OE
86
+ - "Ŕ" # LATIN CAPITAL LETTER R WITH ACUTE
87
+ - "ŕ" # LATIN SMALL LETTER R WITH ACUTE
88
+ - "Ŗ" # LATIN CAPITAL LETTER R WITH CEDILLA
89
+ - "ŗ" # LATIN SMALL LETTER R WITH CEDILLA
90
+ - "Ř" # LATIN CAPITAL LETTER R WITH CARON
91
+ - "ř" # LATIN SMALL LETTER R WITH CARON
92
+ - "Ś" # LATIN CAPITAL LETTER S WITH ACUTE
93
+ - "ś" # LATIN SMALL LETTER S WITH ACUTE
94
+ - "Ŝ" # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
95
+ - "ŝ" # LATIN SMALL LETTER S WITH CIRCUMFLEX
96
+ - "Ş" # LATIN CAPITAL LETTER S WITH CEDILLA
97
+ - "ş" # LATIN SMALL LETTER S WITH CEDILLA
98
+ - "Š" # LATIN CAPITAL LETTER S WITH CARON
99
+ - "š" # LATIN SMALL LETTER S WITH CARON
100
+ - "Ţ" # LATIN CAPITAL LETTER T WITH CEDILLA
101
+ - "ţ" # LATIN SMALL LETTER T WITH CEDILLA
102
+ - "Ť" # LATIN CAPITAL LETTER T WITH CARON
103
+ - "ť" # LATIN SMALL LETTER T WITH CARON
104
+ - "Ŧ" # LATIN CAPITAL LETTER T WITH STROKE
105
+ - "ŧ" # LATIN SMALL LETTER T WITH STROKE
106
+ - "Ũ" # LATIN CAPITAL LETTER U WITH TILDE
107
+ - "ũ" # LATIN SMALL LETTER U WITH TILDE
108
+ - "Ū" # LATIN CAPITAL LETTER U WITH MACRON
109
+ - "ū" # LATIN SMALL LETTER U WITH MACRON
110
+ - "Ŭ" # LATIN CAPITAL LETTER U WITH BREVE
111
+ - "ŭ" # LATIN SMALL LETTER U WITH BREVE
112
+ - "Ů" # LATIN CAPITAL LETTER U WITH RING ABOVE
113
+ - "ů" # LATIN SMALL LETTER U WITH RING ABOVE
114
+ - "Ű" # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
115
+ - "ű" # LATIN SMALL LETTER U WITH DOUBLE ACUTE
116
+ - "Ų" # LATIN CAPITAL LETTER U WITH OGONEK
117
+ - "ų" # LATIN SMALL LETTER U WITH OGONEK
118
+ - "Ŵ" # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
119
+ - "ŵ" # LATIN SMALL LETTER W WITH CIRCUMFLEX
120
+ - "Ŷ" # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
121
+ - "ŷ" # LATIN SMALL LETTER Y WITH CIRCUMFLEX
122
+ - "Ÿ" # LATIN CAPITAL LETTER Y WITH DIAERESIS
123
+ - "Ź" # LATIN CAPITAL LETTER Z WITH ACUTE
124
+ - "ź" # LATIN SMALL LETTER Z WITH ACUTE
125
+ - "Ż" # LATIN CAPITAL LETTER Z WITH DOT ABOVE
126
+ - "ż" # LATIN SMALL LETTER Z WITH DOT ABOVE
127
+ - "Ž" # LATIN CAPITAL LETTER Z WITH CARON
128
+ - "ž" # LATIN SMALL LETTER Z WITH CARON
129
+ - "ſ" # LATIN SMALL LETTER LONG S
data/data/csets/unicode/latin_extended_additional.yaml ADDED
@@ -0,0 +1,247 @@
1
+ ---
2
+ - "Ḁ" # LATIN CAPITAL LETTER A WITH RING BELOW
3
+ - "ḁ" # LATIN SMALL LETTER A WITH RING BELOW
4
+ - "Ḃ" # LATIN CAPITAL LETTER B WITH DOT ABOVE
5
+ - "ḃ" # LATIN SMALL LETTER B WITH DOT ABOVE
6
+ - "Ḅ" # LATIN CAPITAL LETTER B WITH DOT BELOW
7
+ - "ḅ" # LATIN SMALL LETTER B WITH DOT BELOW
8
+ - "Ḇ" # LATIN CAPITAL LETTER B WITH LINE BELOW
9
+ - "ḇ" # LATIN SMALL LETTER B WITH LINE BELOW
10
+ - "Ḉ" # LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE
11
+ - "ḉ" # LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
12
+ - "Ḋ" # LATIN CAPITAL LETTER D WITH DOT ABOVE
13
+ - "ḋ" # LATIN SMALL LETTER D WITH DOT ABOVE
14
+ - "Ḍ" # LATIN CAPITAL LETTER D WITH DOT BELOW
15
+ - "ḍ" # LATIN SMALL LETTER D WITH DOT BELOW
16
+ - "Ḏ" # LATIN CAPITAL LETTER D WITH LINE BELOW
17
+ - "ḏ" # LATIN SMALL LETTER D WITH LINE BELOW
18
+ - "Ḑ" # LATIN CAPITAL LETTER D WITH CEDILLA
19
+ - "ḑ" # LATIN SMALL LETTER D WITH CEDILLA
20
+ - "Ḓ" # LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW
21
+ - "ḓ" # LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW
22
+ - "Ḕ" # LATIN CAPITAL LETTER E WITH MACRON AND GRAVE
23
+ - "ḕ" # LATIN SMALL LETTER E WITH MACRON AND GRAVE
24
+ - "Ḗ" # LATIN CAPITAL LETTER E WITH MACRON AND ACUTE
25
+ - "ḗ" # LATIN SMALL LETTER E WITH MACRON AND ACUTE
26
+ - "Ḙ" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW
27
+ - "ḙ" # LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW
28
+ - "Ḛ" # LATIN CAPITAL LETTER E WITH TILDE BELOW
29
+ - "ḛ" # LATIN SMALL LETTER E WITH TILDE BELOW
30
+ - "Ḝ" # LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE
31
+ - "ḝ" # LATIN SMALL LETTER E WITH CEDILLA AND BREVE
32
+ - "Ḟ" # LATIN CAPITAL LETTER F WITH DOT ABOVE
33
+ - "ḟ" # LATIN SMALL LETTER F WITH DOT ABOVE
34
+ - "Ḡ" # LATIN CAPITAL LETTER G WITH MACRON
35
+ - "ḡ" # LATIN SMALL LETTER G WITH MACRON
36
+ - "Ḣ" # LATIN CAPITAL LETTER H WITH DOT ABOVE
37
+ - "ḣ" # LATIN SMALL LETTER H WITH DOT ABOVE
38
+ - "Ḥ" # LATIN CAPITAL LETTER H WITH DOT BELOW
39
+ - "ḥ" # LATIN SMALL LETTER H WITH DOT BELOW
40
+ - "Ḧ" # LATIN CAPITAL LETTER H WITH DIAERESIS
41
+ - "ḧ" # LATIN SMALL LETTER H WITH DIAERESIS
42
+ - "Ḩ" # LATIN CAPITAL LETTER H WITH CEDILLA
43
+ - "ḩ" # LATIN SMALL LETTER H WITH CEDILLA
44
+ - "Ḫ" # LATIN CAPITAL LETTER H WITH BREVE BELOW
45
+ - "ḫ" # LATIN SMALL LETTER H WITH BREVE BELOW
46
+ - "Ḭ" # LATIN CAPITAL LETTER I WITH TILDE BELOW
47
+ - "ḭ" # LATIN SMALL LETTER I WITH TILDE BELOW
48
+ - "Ḯ" # LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE
49
+ - "ḯ" # LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE
50
+ - "Ḱ" # LATIN CAPITAL LETTER K WITH ACUTE
51
+ - "ḱ" # LATIN SMALL LETTER K WITH ACUTE
52
+ - "Ḳ" # LATIN CAPITAL LETTER K WITH DOT BELOW
53
+ - "ḳ" # LATIN SMALL LETTER K WITH DOT BELOW
54
+ - "Ḵ" # LATIN CAPITAL LETTER K WITH LINE BELOW
55
+ - "ḵ" # LATIN SMALL LETTER K WITH LINE BELOW
56
+ - "Ḷ" # LATIN CAPITAL LETTER L WITH DOT BELOW
57
+ - "ḷ" # LATIN SMALL LETTER L WITH DOT BELOW
58
+ - "Ḹ" # LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON
59
+ - "ḹ" # LATIN SMALL LETTER L WITH DOT BELOW AND MACRON
60
+ - "Ḻ" # LATIN CAPITAL LETTER L WITH LINE BELOW
61
+ - "ḻ" # LATIN SMALL LETTER L WITH LINE BELOW
62
+ - "Ḽ" # LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW
63
+ - "ḽ" # LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW
64
+ - "Ḿ" # LATIN CAPITAL LETTER M WITH ACUTE
65
+ - "ḿ" # LATIN SMALL LETTER M WITH ACUTE
66
+ - "Ṁ" # LATIN CAPITAL LETTER M WITH DOT ABOVE
67
+ - "ṁ" # LATIN SMALL LETTER M WITH DOT ABOVE
68
+ - "Ṃ" # LATIN CAPITAL LETTER M WITH DOT BELOW
69
+ - "ṃ" # LATIN SMALL LETTER M WITH DOT BELOW
70
+ - "Ṅ" # LATIN CAPITAL LETTER N WITH DOT ABOVE
71
+ - "ṅ" # LATIN SMALL LETTER N WITH DOT ABOVE
72
+ - "Ṇ" # LATIN CAPITAL LETTER N WITH DOT BELOW
73
+ - "ṇ" # LATIN SMALL LETTER N WITH DOT BELOW
74
+ - "Ṉ" # LATIN CAPITAL LETTER N WITH LINE BELOW
75
+ - "ṉ" # LATIN SMALL LETTER N WITH LINE BELOW
76
+ - "Ṋ" # LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW
77
+ - "ṋ" # LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW
78
+ - "Ṍ" # LATIN CAPITAL LETTER O WITH TILDE AND ACUTE
79
+ - "ṍ" # LATIN SMALL LETTER O WITH TILDE AND ACUTE
80
+ - "Ṏ" # LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS
81
+ - "ṏ" # LATIN SMALL LETTER O WITH TILDE AND DIAERESIS
82
+ - "Ṑ" # LATIN CAPITAL LETTER O WITH MACRON AND GRAVE
83
+ - "ṑ" # LATIN SMALL LETTER O WITH MACRON AND GRAVE
84
+ - "Ṓ" # LATIN CAPITAL LETTER O WITH MACRON AND ACUTE
85
+ - "ṓ" # LATIN SMALL LETTER O WITH MACRON AND ACUTE
86
+ - "Ṕ" # LATIN CAPITAL LETTER P WITH ACUTE
87
+ - "ṕ" # LATIN SMALL LETTER P WITH ACUTE
88
+ - "Ṗ" # LATIN CAPITAL LETTER P WITH DOT ABOVE
89
+ - "ṗ" # LATIN SMALL LETTER P WITH DOT ABOVE
90
+ - "Ṙ" # LATIN CAPITAL LETTER R WITH DOT ABOVE
91
+ - "ṙ" # LATIN SMALL LETTER R WITH DOT ABOVE
92
+ - "Ṛ" # LATIN CAPITAL LETTER R WITH DOT BELOW
93
+ - "ṛ" # LATIN SMALL LETTER R WITH DOT BELOW
94
+ - "Ṝ" # LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON
95
+ - "ṝ" # LATIN SMALL LETTER R WITH DOT BELOW AND MACRON
96
+ - "Ṟ" # LATIN CAPITAL LETTER R WITH LINE BELOW
97
+ - "ṟ" # LATIN SMALL LETTER R WITH LINE BELOW
98
+ - "Ṡ" # LATIN CAPITAL LETTER S WITH DOT ABOVE
99
+ - "ṡ" # LATIN SMALL LETTER S WITH DOT ABOVE
100
+ - "Ṣ" # LATIN CAPITAL LETTER S WITH DOT BELOW
101
+ - "ṣ" # LATIN SMALL LETTER S WITH DOT BELOW
102
+ - "Ṥ" # LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE
103
+ - "ṥ" # LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE
104
+ - "Ṧ" # LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE
105
+ - "ṧ" # LATIN SMALL LETTER S WITH CARON AND DOT ABOVE
106
+ - "Ṩ" # LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE
107
+ - "ṩ" # LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE
108
+ - "Ṫ" # LATIN CAPITAL LETTER T WITH DOT ABOVE
109
+ - "ṫ" # LATIN SMALL LETTER T WITH DOT ABOVE
110
+ - "Ṭ" # LATIN CAPITAL LETTER T WITH DOT BELOW
111
+ - "ṭ" # LATIN SMALL LETTER T WITH DOT BELOW
112
+ - "Ṯ" # LATIN CAPITAL LETTER T WITH LINE BELOW
113
+ - "ṯ" # LATIN SMALL LETTER T WITH LINE BELOW
114
+ - "Ṱ" # LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW
115
+ - "ṱ" # LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW
116
+ - "Ṳ" # LATIN CAPITAL LETTER U WITH DIAERESIS BELOW
117
+ - "ṳ" # LATIN SMALL LETTER U WITH DIAERESIS BELOW
118
+ - "Ṵ" # LATIN CAPITAL LETTER U WITH TILDE BELOW
119
+ - "ṵ" # LATIN SMALL LETTER U WITH TILDE BELOW
120
+ - "Ṷ" # LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW
121
+ - "ṷ" # LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW
122
+ - "Ṹ" # LATIN CAPITAL LETTER U WITH TILDE AND ACUTE
123
+ - "ṹ" # LATIN SMALL LETTER U WITH TILDE AND ACUTE
124
+ - "Ṻ" # LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS
125
+ - "ṻ" # LATIN SMALL LETTER U WITH MACRON AND DIAERESIS
126
+ - "Ṽ" # LATIN CAPITAL LETTER V WITH TILDE
127
+ - "ṽ" # LATIN SMALL LETTER V WITH TILDE
128
+ - "Ṿ" # LATIN CAPITAL LETTER V WITH DOT BELOW
129
+ - "ṿ" # LATIN SMALL LETTER V WITH DOT BELOW
130
+ - "Ẁ" # LATIN CAPITAL LETTER W WITH GRAVE (present in WGL4)
131
+ - "ẁ" # LATIN SMALL LETTER W WITH GRAVE (present in WGL4)
132
+ - "Ẃ" # LATIN CAPITAL LETTER W WITH ACUTE (present in WGL4)
133
+ - "ẃ" # LATIN SMALL LETTER W WITH ACUTE (present in WGL4)
134
+ - "Ẅ" # LATIN CAPITAL LETTER W WITH DIAERESIS (present in WGL4)
135
+ - "ẅ" # LATIN SMALL LETTER W WITH DIAERESIS (present in WGL4)
136
+ - "Ẇ" # LATIN CAPITAL LETTER W WITH DOT ABOVE
137
+ - "ẇ" # LATIN SMALL LETTER W WITH DOT ABOVE
138
+ - "Ẉ" # LATIN CAPITAL LETTER W WITH DOT BELOW
139
+ - "ẉ" # LATIN SMALL LETTER W WITH DOT BELOW
140
+ - "Ẋ" # LATIN CAPITAL LETTER X WITH DOT ABOVE
141
+ - "ẋ" # LATIN SMALL LETTER X WITH DOT ABOVE
142
+ - "Ẍ" # LATIN CAPITAL LETTER X WITH DIAERESIS
143
+ - "ẍ" # LATIN SMALL LETTER X WITH DIAERESIS
144
+ - "Ẏ" # LATIN CAPITAL LETTER Y WITH DOT ABOVE
145
+ - "ẏ" # LATIN SMALL LETTER Y WITH DOT ABOVE
146
+ - "Ẑ" # LATIN CAPITAL LETTER Z WITH CIRCUMFLEX
147
+ - "ẑ" # LATIN SMALL LETTER Z WITH CIRCUMFLEX
148
+ - "Ẓ" # LATIN CAPITAL LETTER Z WITH DOT BELOW
149
+ - "ẓ" # LATIN SMALL LETTER Z WITH DOT BELOW
150
+ - "Ẕ" # LATIN CAPITAL LETTER Z WITH LINE BELOW
151
+ - "ẕ" # LATIN SMALL LETTER Z WITH LINE BELOW
152
+ - "ẖ" # LATIN SMALL LETTER H WITH LINE BELOW
153
+ - "ẗ" # LATIN SMALL LETTER T WITH DIAERESIS
154
+ - "ẘ" # LATIN SMALL LETTER W WITH RING ABOVE
155
+ - "ẙ" # LATIN SMALL LETTER Y WITH RING ABOVE
156
+ - "ẚ" # LATIN SMALL LETTER A WITH RIGHT HALF RING
157
+ - "ẛ" # LATIN SMALL LETTER LONG S WITH DOT ABOVE
158
+ - "Ạ" # LATIN CAPITAL LETTER A WITH DOT BELOW
159
+ - "ạ" # LATIN SMALL LETTER A WITH DOT BELOW
160
+ - "Ả" # LATIN CAPITAL LETTER A WITH HOOK ABOVE
161
+ - "ả" # LATIN SMALL LETTER A WITH HOOK ABOVE
162
+ - "Ấ" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE
163
+ - "ấ" # LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE
164
+ - "Ầ" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE
165
+ - "ầ" # LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE
166
+ - "Ẩ" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
167
+ - "ẩ" # LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
168
+ - "Ẫ" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE
169
+ - "ẫ" # LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE
170
+ - "Ậ" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW
171
+ - "ậ" # LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW
172
+ - "Ắ" # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE
173
+ - "ắ" # LATIN SMALL LETTER A WITH BREVE AND ACUTE
174
+ - "Ằ" # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE
175
+ - "ằ" # LATIN SMALL LETTER A WITH BREVE AND GRAVE
176
+ - "Ẳ" # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE
177
+ - "ẳ" # LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE
178
+ - "Ẵ" # LATIN CAPITAL LETTER A WITH BREVE AND TILDE
179
+ - "ẵ" # LATIN SMALL LETTER A WITH BREVE AND TILDE
180
+ - "Ặ" # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW
181
+ - "ặ" # LATIN SMALL LETTER A WITH BREVE AND DOT BELOW
182
+ - "Ẹ" # LATIN CAPITAL LETTER E WITH DOT BELOW
183
+ - "ẹ" # LATIN SMALL LETTER E WITH DOT BELOW
184
+ - "Ẻ" # LATIN CAPITAL LETTER E WITH HOOK ABOVE
185
+ - "ẻ" # LATIN SMALL LETTER E WITH HOOK ABOVE
186
+ - "Ẽ" # LATIN CAPITAL LETTER E WITH TILDE
187
+ - "ẽ" # LATIN SMALL LETTER E WITH TILDE
188
+ - "Ế" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE
189
+ - "ế" # LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE
190
+ - "Ề" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE
191
+ - "ề" # LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE
192
+ - "Ể" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
193
+ - "ể" # LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
194
+ - "Ễ" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE
195
+ - "ễ" # LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE
196
+ - "Ệ" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW
197
+ - "ệ" # LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW
198
+ - "Ỉ" # LATIN CAPITAL LETTER I WITH HOOK ABOVE
199
+ - "ỉ" # LATIN SMALL LETTER I WITH HOOK ABOVE
200
+ - "Ị" # LATIN CAPITAL LETTER I WITH DOT BELOW
201
+ - "ị" # LATIN SMALL LETTER I WITH DOT BELOW
202
+ - "Ọ" # LATIN CAPITAL LETTER O WITH DOT BELOW
203
+ - "ọ" # LATIN SMALL LETTER O WITH DOT BELOW
204
+ - "Ỏ" # LATIN CAPITAL LETTER O WITH HOOK ABOVE
205
+ - "ỏ" # LATIN SMALL LETTER O WITH HOOK ABOVE
206
+ - "Ố" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE
207
+ - "ố" # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE
208
+ - "Ồ" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE
209
+ - "ồ" # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE
210
+ - "Ổ" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
211
+ - "ổ" # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
212
+ - "Ỗ" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE
213
+ - "ỗ" # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE
214
+ - "Ộ" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW
215
+ - "ộ" # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW
216
+ - "Ớ" # LATIN CAPITAL LETTER O WITH HORN AND ACUTE
217
+ - "ớ" # LATIN SMALL LETTER O WITH HORN AND ACUTE
218
+ - "Ờ" # LATIN CAPITAL LETTER O WITH HORN AND GRAVE
219
+ - "ờ" # LATIN SMALL LETTER O WITH HORN AND GRAVE
220
+ - "Ở" # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE
221
+ - "ở" # LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE
222
+ - "Ỡ" # LATIN CAPITAL LETTER O WITH HORN AND TILDE
223
+ - "ỡ" # LATIN SMALL LETTER O WITH HORN AND TILDE
224
+ - "Ợ" # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW
225
+ - "ợ" # LATIN SMALL LETTER O WITH HORN AND DOT BELOW
226
+ - "Ụ" # LATIN CAPITAL LETTER U WITH DOT BELOW
227
+ - "ụ" # LATIN SMALL LETTER U WITH DOT BELOW
228
+ - "Ủ" # LATIN CAPITAL LETTER U WITH HOOK ABOVE
229
+ - "ủ" # LATIN SMALL LETTER U WITH HOOK ABOVE
230
+ - "Ứ" # LATIN CAPITAL LETTER U WITH HORN AND ACUTE
231
+ - "ứ" # LATIN SMALL LETTER U WITH HORN AND ACUTE
232
+ - "Ừ" # LATIN CAPITAL LETTER U WITH HORN AND GRAVE
233
+ - "ừ" # LATIN SMALL LETTER U WITH HORN AND GRAVE
234
+ - "Ử" # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE
235
+ - "ử" # LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE
236
+ - "Ữ" # LATIN CAPITAL LETTER U WITH HORN AND TILDE
237
+ - "ữ" # LATIN SMALL LETTER U WITH HORN AND TILDE
238
+ - "Ự" # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW
239
+ - "ự" # LATIN SMALL LETTER U WITH HORN AND DOT BELOW
240
+ - "Ỳ" # LATIN CAPITAL LETTER Y WITH GRAVE (present in WGL4)
241
+ - "ỳ" # LATIN SMALL LETTER Y WITH GRAVE (present in WGL4)
242
+ - "Ỵ" # LATIN CAPITAL LETTER Y WITH DOT BELOW
243
+ - "ỵ" # LATIN SMALL LETTER Y WITH DOT BELOW
244
+ - "Ỷ" # LATIN CAPITAL LETTER Y WITH HOOK ABOVE
245
+ - "ỷ" # LATIN SMALL LETTER Y WITH HOOK ABOVE
246
+ - "Ỹ" # LATIN CAPITAL LETTER Y WITH TILDE
247
+ - "ỹ" # LATIN SMALL LETTER Y WITH TILDE
data/data/csets/unicode/latin_extended_b.yaml ADDED
@@ -0,0 +1,209 @@
1
+ ---
2
+ - "ƀ" # LATIN SMALL LETTER B WITH STROKE
3
+ - "Ɓ" # LATIN CAPITAL LETTER B WITH HOOK
4
+ - "Ƃ" # LATIN CAPITAL LETTER B WITH TOPBAR
5
+ - "ƃ" # LATIN SMALL LETTER B WITH TOPBAR
6
+ - "Ƅ" # LATIN CAPITAL LETTER TONE SIX
7
+ - "ƅ" # LATIN SMALL LETTER TONE SIX
8
+ - "Ɔ" # LATIN CAPITAL LETTER OPEN O
9
+ - "Ƈ" # LATIN CAPITAL LETTER C WITH HOOK
10
+ - "ƈ" # LATIN SMALL LETTER C WITH HOOK
11
+ - "Ɖ" # LATIN CAPITAL LETTER AFRICAN D
12
+ - "Ɗ" # LATIN CAPITAL LETTER D WITH HOOK
13
+ - "Ƌ" # LATIN CAPITAL LETTER D WITH TOPBAR
14
+ - "ƌ" # LATIN SMALL LETTER D WITH TOPBAR
15
+ - "ƍ" # LATIN SMALL LETTER TURNED DELTA
16
+ - "Ǝ" # LATIN CAPITAL LETTER REVERSED E
17
+ - "Ə" # LATIN CAPITAL LETTER SCHWA
18
+ - "Ɛ" # LATIN CAPITAL LETTER OPEN E
19
+ - "Ƒ" # LATIN CAPITAL LETTER F WITH HOOK
20
+ - "ƒ" # LATIN SMALL LETTER F WITH HOOK (present in WGL4, ANSI and MacRoman; Florin or Guilder in Symbol font)
21
+ - "Ɠ" # LATIN CAPITAL LETTER G WITH HOOK
22
+ - "Ɣ" # LATIN CAPITAL LETTER GAMMA
23
+ - "ƕ" # LATIN SMALL LETTER HV
24
+ - "Ɩ" # LATIN CAPITAL LETTER IOTA
25
+ - "Ɨ" # LATIN CAPITAL LETTER I WITH STROKE
26
+ - "Ƙ" # LATIN CAPITAL LETTER K WITH HOOK
27
+ - "ƙ" # LATIN SMALL LETTER K WITH HOOK
28
+ - "ƚ" # LATIN SMALL LETTER L WITH BAR
29
+ - "ƛ" # LATIN SMALL LETTER LAMBDA WITH STROKE
30
+ - "Ɯ" # LATIN CAPITAL LETTER TURNED M
31
+ - "Ɲ" # LATIN CAPITAL LETTER N WITH LEFT HOOK
32
+ - "ƞ" # LATIN SMALL LETTER N WITH LONG RIGHT LEG
33
+ - "Ɵ" # LATIN CAPITAL LETTER O WITH MIDDLE TILDE
34
+ - "Ơ" # LATIN CAPITAL LETTER O WITH HORN
35
+ - "ơ" # LATIN SMALL LETTER O WITH HORN
36
+ - "Ƣ" # LATIN CAPITAL LETTER OI
37
+ - "ƣ" # LATIN SMALL LETTER OI
38
+ - "Ƥ" # LATIN CAPITAL LETTER P WITH HOOK
39
+ - "ƥ" # LATIN SMALL LETTER P WITH HOOK
40
+ - "Ʀ" # LATIN LETTER YR
41
+ - "Ƨ" # LATIN CAPITAL LETTER TONE TWO
42
+ - "ƨ" # LATIN SMALL LETTER TONE TWO
43
+ - "Ʃ" # LATIN CAPITAL LETTER ESH
44
+ - "ƪ" # LATIN LETTER REVERSED ESH LOOP
45
+ - "ƫ" # LATIN SMALL LETTER T WITH PALATAL HOOK
46
+ - "Ƭ" # LATIN CAPITAL LETTER T WITH HOOK
47
+ - "ƭ" # LATIN SMALL LETTER T WITH HOOK
48
+ - "Ʈ" # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
49
+ - "Ư" # LATIN CAPITAL LETTER U WITH HORN
50
+ - "ư" # LATIN SMALL LETTER U WITH HORN
51
+ - "Ʊ" # LATIN CAPITAL LETTER UPSILON
52
+ - "Ʋ" # LATIN CAPITAL LETTER V WITH HOOK
53
+ - "Ƴ" # LATIN CAPITAL LETTER Y WITH HOOK
54
+ - "ƴ" # LATIN SMALL LETTER Y WITH HOOK
55
+ - "Ƶ" # LATIN CAPITAL LETTER Z WITH STROKE
56
+ - "ƶ" # LATIN SMALL LETTER Z WITH STROKE
57
+ - "Ʒ" # LATIN CAPITAL LETTER EZH
58
+ - "Ƹ" # LATIN CAPITAL LETTER EZH REVERSED
59
+ - "ƹ" # LATIN SMALL LETTER EZH REVERSED
60
+ - "ƺ" # LATIN SMALL LETTER EZH WITH TAIL
61
+ - "ƻ" # LATIN LETTER TWO WITH STROKE
62
+ - "Ƽ" # LATIN CAPITAL LETTER TONE FIVE
63
+ - "ƽ" # LATIN SMALL LETTER TONE FIVE
64
+ - "ƾ" # LATIN LETTER INVERTED GLOTTAL STOP WITH STROKE
65
+ - "ƿ" # LATIN LETTER WYNN
66
+ - "ǀ" # LATIN LETTER DENTAL CLICK
67
+ - "ǁ" # LATIN LETTER LATERAL CLICK
68
+ - "ǂ" # LATIN LETTER ALVEOLAR CLICK
69
+ - "ǃ" # LATIN LETTER RETROFLEX CLICK
70
+ - "DŽ" # LATIN CAPITAL LETTER DZ WITH CARON
71
+ - "Dž" # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
72
+ - "dž" # LATIN SMALL LETTER DZ WITH CARON
73
+ - "LJ" # LATIN CAPITAL LETTER LJ
74
+ - "Lj" # LATIN CAPITAL LETTER L WITH SMALL LETTER J
75
+ - "lj" # LATIN SMALL LETTER LJ
76
+ - "NJ" # LATIN CAPITAL LETTER NJ
77
+ - "Nj" # LATIN CAPITAL LETTER N WITH SMALL LETTER J
78
+ - "nj" # LATIN SMALL LETTER NJ
79
+ - "Ǎ" # LATIN CAPITAL LETTER A WITH CARON
80
+ - "ǎ" # LATIN SMALL LETTER A WITH CARON
81
+ - "Ǐ" # LATIN CAPITAL LETTER I WITH CARON
82
+ - "ǐ" # LATIN SMALL LETTER I WITH CARON
83
+ - "Ǒ" # LATIN CAPITAL LETTER O WITH CARON
84
+ - "ǒ" # LATIN SMALL LETTER O WITH CARON
85
+ - "Ǔ" # LATIN CAPITAL LETTER U WITH CARON
86
+ - "ǔ" # LATIN SMALL LETTER U WITH CARON
87
+ - "Ǖ" # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON
88
+ - "ǖ" # LATIN SMALL LETTER U WITH DIAERESIS AND MACRON
89
+ - "Ǘ" # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE
90
+ - "ǘ" # LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE
91
+ - "Ǚ" # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON
92
+ - "ǚ" # LATIN SMALL LETTER U WITH DIAERESIS AND CARON
93
+ - "Ǜ" # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE
94
+ - "ǜ" # LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE
95
+ - "ǝ" # LATIN SMALL LETTER TURNED E
96
+ - "Ǟ" # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON
97
+ - "ǟ" # LATIN SMALL LETTER A WITH DIAERESIS AND MACRON
98
+ - "Ǡ" # LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON
99
+ - "ǡ" # LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON
100
+ - "Ǣ" # LATIN CAPITAL LETTER AE WITH MACRON
101
+ - "ǣ" # LATIN SMALL LETTER AE WITH MACRON
102
+ - "Ǥ" # LATIN CAPITAL LETTER G WITH STROKE
103
+ - "ǥ" # LATIN SMALL LETTER G WITH STROKE
104
+ - "Ǧ" # LATIN CAPITAL LETTER G WITH CARON
105
+ - "ǧ" # LATIN SMALL LETTER G WITH CARON
106
+ - "Ǩ" # LATIN CAPITAL LETTER K WITH CARON
107
+ - "ǩ" # LATIN SMALL LETTER K WITH CARON
108
+ - "Ǫ" # LATIN CAPITAL LETTER O WITH OGONEK
109
+ - "ǫ" # LATIN SMALL LETTER O WITH OGONEK
110
+ - "Ǭ" # LATIN CAPITAL LETTER O WITH OGONEK AND MACRON
111
+ - "ǭ" # LATIN SMALL LETTER O WITH OGONEK AND MACRON
112
+ - "Ǯ" # LATIN CAPITAL LETTER EZH WITH CARON
113
+ - "ǯ" # LATIN SMALL LETTER EZH WITH CARON
114
+ - "ǰ" # LATIN SMALL LETTER J WITH CARON
115
+ - "DZ" # LATIN CAPITAL LETTER DZ
116
+ - "Dz" # LATIN CAPITAL LETTER D WITH SMALL LETTER Z
117
+ - "dz" # LATIN SMALL LETTER DZ
118
+ - "Ǵ" # LATIN CAPITAL LETTER G WITH ACUTE
119
+ - "ǵ" # LATIN SMALL LETTER G WITH ACUTE
120
+ - "Ƕ" # LATIN CAPITAL LETTER HWAIR
121
+ - "Ƿ" # LATIN CAPITAL LETTER WYNN
122
+ - "Ǹ" # LATIN CAPITAL LETTER N WITH GRAVE
123
+ - "ǹ" # LATIN SMALL LETTER N WITH GRAVE
124
+ - "Ǻ" # LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE (present in WGL4)
125
+ - "ǻ" # LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE (present in WGL4)
126
+ - "Ǽ" # LATIN CAPITAL LETTER AE WITH ACUTE (present in WGL4)
127
+ - "ǽ" # LATIN SMALL LETTER AE WITH ACUTE (present in WGL4)
128
+ - "Ǿ" # LATIN CAPITAL LETTER O WITH STROKE AND ACUTE (present in WGL4)
129
+ - "ǿ" # LATIN SMALL LETTER O WITH STROKE AND ACUTE (present in WGL4)
130
+ - "Ȁ" # LATIN CAPITAL LETTER A WITH DOUBLE GRAVE
131
+ - "ȁ" # LATIN SMALL LETTER A WITH DOUBLE GRAVE
132
+ - "Ȃ" # LATIN CAPITAL LETTER A WITH INVERTED BREVE
133
+ - "ȃ" # LATIN SMALL LETTER A WITH INVERTED BREVE
134
+ - "Ȅ" # LATIN CAPITAL LETTER E WITH DOUBLE GRAVE
135
+ - "ȅ" # LATIN SMALL LETTER E WITH DOUBLE GRAVE
136
+ - "Ȇ" # LATIN CAPITAL LETTER E WITH INVERTED BREVE
137
+ - "ȇ" # LATIN SMALL LETTER E WITH INVERTED BREVE
138
+ - "Ȉ" # LATIN CAPITAL LETTER I WITH DOUBLE GRAVE
139
+ - "ȉ" # LATIN SMALL LETTER I WITH DOUBLE GRAVE
140
+ - "Ȋ" # LATIN CAPITAL LETTER I WITH INVERTED BREVE
141
+ - "ȋ" # LATIN SMALL LETTER I WITH INVERTED BREVE
142
+ - "Ȍ" # LATIN CAPITAL LETTER O WITH DOUBLE GRAVE
143
+ - "ȍ" # LATIN SMALL LETTER O WITH DOUBLE GRAVE
144
+ - "Ȏ" # LATIN CAPITAL LETTER O WITH INVERTED BREVE
145
+ - "ȏ" # LATIN SMALL LETTER O WITH INVERTED BREVE
146
+ - "Ȑ" # LATIN CAPITAL LETTER R WITH DOUBLE GRAVE
147
+ - "ȑ" # LATIN SMALL LETTER R WITH DOUBLE GRAVE
148
+ - "Ȓ" # LATIN CAPITAL LETTER R WITH INVERTED BREVE
149
+ - "ȓ" # LATIN SMALL LETTER R WITH INVERTED BREVE
150
+ - "Ȕ" # LATIN CAPITAL LETTER U WITH DOUBLE GRAVE
151
+ - "ȕ" # LATIN SMALL LETTER U WITH DOUBLE GRAVE
152
+ - "Ȗ" # LATIN CAPITAL LETTER U WITH INVERTED BREVE
153
+ - "ȗ" # LATIN SMALL LETTER U WITH INVERTED BREVE
154
+ - "Ș" # LATIN CAPITAL LETTER S WITH COMMA BELOW
155
+ - "ș" # LATIN SMALL LETTER S WITH COMMA BELOW
156
+ - "Ț" # LATIN CAPITAL LETTER T WITH COMMA BELOW
157
+ - "ț" # LATIN SMALL LETTER T WITH COMMA BELOW
158
+ - "Ȝ" # LATIN CAPITAL LETTER YOGH
159
+ - "ȝ" # LATIN SMALL LETTER YOGH
160
+ - "Ȟ" # LATIN CAPITAL LETTER H WITH CARON
161
+ - "ȟ" # LATIN SMALL LETTER H WITH CARON
162
+ - "Ƞ" # LATIN CAPITAL LETTER N WITH LONG RIGHT LEG
163
+ - "ȡ" # LATIN SMALL LETTER D WITH CURL
164
+ - "Ȣ" # LATIN CAPITAL LETTER OU
165
+ - "ȣ" # LATIN SMALL LETTER OU
166
+ - "Ȥ" # LATIN CAPITAL LETTER Z WITH HOOK
167
+ - "ȥ" # LATIN SMALL LETTER Z WITH HOOK
168
+ - "Ȧ" # LATIN CAPITAL LETTER A WITH DOT ABOVE
169
+ - "ȧ" # LATIN SMALL LETTER A WITH DOT ABOVE
170
+ - "Ȩ" # LATIN CAPITAL LETTER E WITH CEDILLA
171
+ - "ȩ" # LATIN SMALL LETTER E WITH CEDILLA
172
+ - "Ȫ" # LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON
173
+ - "ȫ" # LATIN SMALL LETTER O WITH DIAERESIS AND MACRON
174
+ - "Ȭ" # LATIN CAPITAL LETTER O WITH TILDE AND MACRON
175
+ - "ȭ" # LATIN SMALL LETTER O WITH TILDE AND MACRON
176
+ - "Ȯ" # LATIN CAPITAL LETTER O WITH DOT ABOVE
177
+ - "ȯ" # LATIN SMALL LETTER O WITH DOT ABOVE
178
+ - "Ȱ" # LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON
179
+ - "ȱ" # LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON
180
+ - "Ȳ" # LATIN CAPITAL LETTER Y WITH MACRON
181
+ - "ȳ" # LATIN SMALL LETTER Y WITH MACRON
182
+ - "ȴ" # LATIN SMALL LETTER L WITH CURL
183
+ - "ȵ" # LATIN SMALL LETTER N WITH CURL
184
+ - "ȶ" # LATIN SMALL LETTER T WITH CURL
185
+ - "ȷ" # LATIN SMALL LETTER DOTLESS J
186
+ - "ȸ" # LATIN SMALL LETTER DB DIGRAPH
187
+ - "ȹ" # LATIN SMALL LETTER QP DIGRAPH
188
+ - "Ⱥ" # LATIN CAPITAL LETTER A WITH STROKE
189
+ - "Ȼ" # LATIN CAPITAL LETTER C WITH STROKE
190
+ - "ȼ" # LATIN SMALL LETTER C WITH STROKE
191
+ - "Ƚ" # LATIN CAPITAL LETTER L WITH BAR
192
+ - "Ⱦ" # LATIN CAPITAL LETTER T WITH DIAGONAL STROKE
193
+ - "ȿ" # LATIN SMALL LETTER S WITH SWASH TAIL
194
+ - "ɀ" # LATIN SMALL LETTER Z WITH SWASH TAIL
195
+ - "Ɂ" # LATIN CAPITAL LETTER GLOTTAL STOP
196
+ - "ɂ" # LATIN SMALL LETTER GLOTTAL STOP
197
+ - "Ƀ" # LATIN CAPITAL LETTER B WITH STROKE
198
+ - "Ʉ" # LATIN CAPITAL LETTER U BAR
199
+ - "Ʌ" # LATIN CAPITAL LETTER TURNED V
200
+ - "Ɇ" # LATIN CAPITAL LETTER E WITH STROKE
201
+ - "ɇ" # LATIN SMALL LETTER E WITH STROKE
202
+ - "Ɉ" # LATIN CAPITAL LETTER J WITH STROKE
203
+ - "ɉ" # LATIN SMALL LETTER J WITH STROKE
204
+ - "Ɋ" # LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL
205
+ - "ɋ" # LATIN SMALL LETTER Q WITH HOOK TAIL
206
+ - "Ɍ" # LATIN CAPITAL LETTER R WITH STROKE
207
+ - "ɍ" # LATIN SMALL LETTER R WITH STROKE
208
+ - "Ɏ" # LATIN CAPITAL LETTER Y WITH STROKE
209
+ - "ɏ" # LATIN SMALL LETTER Y WITH STROKE
data/data/csets/unicode/letterlike_symbols.yaml ADDED
@@ -0,0 +1,80 @@
1
+ ---
2
+ - "℀" # ACCOUNT OF
3
+ - "℁" # ADDRESSED TO THE SUBJECT
4
+ - "ℂ" # DOUBLE-STRUCK CAPITAL C
5
+ - "℃" # DEGREE CELSIUS
6
+ - "℄" # CENTRE LINE SYMBOL
7
+ - "℅" # CARE OF (present in WGL4)
8
+ - "℆" # CADA UNA
9
+ - "ℇ" # EULER CONSTANT
10
+ - "℈" # SCRUPLE
11
+ - "℉" # DEGREE FAHRENHEIT
12
+ - "ℊ" # SCRIPT SMALL G
13
+ - "ℋ" # SCRIPT CAPITAL H
14
+ - "ℌ" # BLACK-LETTER CAPITAL H
15
+ - "ℍ" # DOUBLE-STRUCK CAPITAL H
16
+ - "ℎ" # PLANCK CONSTANT
17
+ - "ℏ" # PLANCK CONSTANT OVER TWO PI
18
+ - "ℐ" # SCRIPT CAPITAL I
19
+ - "ℑ" # BLACK-LETTER CAPITAL I (I fraktur in Symbol font)
20
+ - "ℒ" # SCRIPT CAPITAL L
21
+ - "ℓ" # SCRIPT SMALL L (present in WGL4)
22
+ - "℔" # L B BAR SYMBOL
23
+ - "ℕ" # DOUBLE-STRUCK CAPITAL N
24
+ - "№" # NUMERO SIGN (present in WGL4)
25
+ - "℗" # SOUND RECORDING COPYRIGHT
26
+ - "℘" # SCRIPT CAPITAL P (Weierstrass in Symbol font)
27
+ - "ℙ" # DOUBLE-STRUCK CAPITAL P
28
+ - "ℚ" # DOUBLE-STRUCK CAPITAL Q
29
+ - "ℛ" # SCRIPT CAPITAL R
30
+ - "ℜ" # BLACK-LETTER CAPITAL R (R fraktur in Symbol font)
31
+ - "ℝ" # DOUBLE-STRUCK CAPITAL R
32
+ - "℞" # PRESCRIPTION TAKE
33
+ - "℟" # RESPONSE
34
+ - "℠" # SERVICE MARK
35
+ - "℡" # TELEPHONE SIGN
36
+ - "™" # TRADE MARK SIGN (present in WGL4, in MacRoman, and in Symbol font)
37
+ - "℣" # VERSICLE
38
+ - "ℤ" # DOUBLE-STRUCK CAPITAL Z
39
+ - "℥" # OUNCE SIGN
40
+ - "Ω" # OHM SIGN (present in WGL4)
41
+ - "℧" # INVERTED OHM SIGN
42
+ - "ℨ" # BLACK-LETTER CAPITAL Z
43
+ - "℩" # TURNED GREEK SMALL LETTER IOTA
44
+ - "K" # KELVIN SIGN
45
+ - "Å" # ANGSTROM SIGN
46
+ - "ℬ" # SCRIPT CAPITAL B
47
+ - "ℭ" # BLACK-LETTER CAPITAL C
48
+ - "℮" # ESTIMATED SYMBOL (present in WGL4)
49
+ - "ℯ" # SCRIPT SMALL E
50
+ - "ℰ" # SCRIPT CAPITAL E
51
+ - "ℱ" # SCRIPT CAPITAL F
52
+ - "Ⅎ" # TURNED CAPITAL F
53
+ - "ℳ" # SCRIPT CAPITAL M
54
+ - "ℴ" # SCRIPT SMALL O
55
+ - "ℵ" # ALEF SYMBOL (present in Symbol font)
56
+ - "ℶ" # BET SYMBOL
57
+ - "ℷ" # GIMEL SYMBOL
58
+ - "ℸ" # DALET SYMBOL
59
+ - "ℹ" # INFORMATION SOURCE
60
+ - "℺" # ROTATED CAPITAL Q
61
+ - "℻" # FACSIMILE SIGN
62
+ - "ℼ" # DOUBLE-STRUCK SMALL PI
63
+ - "ℽ" # DOUBLE-STRUCK SMALL GAMMA
64
+ - "ℾ" # DOUBLE-STRUCK CAPITAL GAMMA
65
+ - "ℿ" # DOUBLE-STRUCK CAPITAL PI
66
+ - "⅀" # DOUBLE-STRUCK N-ARY SUMMATION
67
+ - "⅁" # TURNED SANS-SERIF CAPITAL G
68
+ - "⅂" # TURNED SANS-SERIF CAPITAL L
69
+ - "⅃" # REVERSED SANS-SERIF CAPITAL L
70
+ - "⅄" # TURNED SANS-SERIF CAPITAL Y
71
+ - "ⅅ" # DOUBLE-STRUCK ITALIC CAPITAL D
72
+ - "ⅆ" # DOUBLE-STRUCK ITALIC SMALL D
73
+ - "ⅇ" # DOUBLE-STRUCK ITALIC SMALL E
74
+ - "ⅈ" # DOUBLE-STRUCK ITALIC SMALL I
75
+ - "ⅉ" # DOUBLE-STRUCK ITALIC SMALL J
76
+ - "⅊" # PROPERTY LINE
77
+ - "⅋" # TURNED AMPERSAND
78
+ - "⅌" # PER SIGN
79
+ - "⅍" # AKTIESELSKAB
80
+ - "ⅎ" # TURNED SMALL F