cmess 0.0.4.136

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 (37) hide show
  1. data/COPYING +676 -0
  2. data/ChangeLog +6 -0
  3. data/README +53 -0
  4. data/Rakefile +30 -0
  5. data/bin/cinderella +186 -0
  6. data/bin/decode_entities +101 -0
  7. data/bin/guess_encoding +183 -0
  8. data/data/csets/iso_8859-1.yaml +195 -0
  9. data/data/csets/iso_8859-15.yaml +204 -0
  10. data/data/csets/latin1.yaml +195 -0
  11. data/data/csets/unicode/basic_latin.yaml +97 -0
  12. data/data/csets/unicode/cyrillic-supplement.yaml +17 -0
  13. data/data/csets/unicode/cyrillic.yaml +256 -0
  14. data/data/csets/unicode/greek.yaml +129 -0
  15. data/data/csets/unicode/ipa_extensions.yaml +97 -0
  16. data/data/csets/unicode/latin-extended-c.yaml +18 -0
  17. data/data/csets/unicode/latin-extended-d.yaml +3 -0
  18. data/data/csets/unicode/latin_1_supplement.yaml +128 -0
  19. data/data/csets/unicode/latin_extended_a.yaml +129 -0
  20. data/data/csets/unicode/latin_extended_additional.yaml +247 -0
  21. data/data/csets/unicode/latin_extended_b.yaml +209 -0
  22. data/data/csets/unicode/letterlike_symbols.yaml +80 -0
  23. data/data/csets/unicode/spacing_modifier_letters.yaml +81 -0
  24. data/data/csets/utf-8.yaml +1504 -0
  25. data/data/csets/utf8.yaml +1504 -0
  26. data/example/crop +127 -0
  27. data/example/crop_repaired +127 -0
  28. data/example/empty6-slash.txt +1495 -0
  29. data/example/empty6-slash_repaired.txt +1495 -0
  30. data/example/pot +1368 -0
  31. data/lib/cmess.rb +44 -0
  32. data/lib/cmess/cinderella.rb +63 -0
  33. data/lib/cmess/cli.rb +79 -0
  34. data/lib/cmess/decode_entities.rb +68 -0
  35. data/lib/cmess/guess_encoding.rb +372 -0
  36. data/lib/cmess/version.rb +51 -0
  37. metadata +119 -0
data/data/csets/unicode/ipa_extensions.yaml ADDED
@@ -0,0 +1,97 @@
1
+ ---
2
+ - "ɐ" # LATIN SMALL LETTER TURNED A
3
+ - "ɑ" # LATIN SMALL LETTER ALPHA
4
+ - "ɒ" # LATIN SMALL LETTER TURNED ALPHA
5
+ - "ɓ" # LATIN SMALL LETTER B WITH HOOK
6
+ - "ɔ" # LATIN SMALL LETTER OPEN O
7
+ - "ɕ" # LATIN SMALL LETTER C WITH CURL
8
+ - "ɖ" # LATIN SMALL LETTER D WITH TAIL
9
+ - "ɗ" # LATIN SMALL LETTER D WITH HOOK
10
+ - "ɘ" # LATIN SMALL LETTER REVERSED E
11
+ - "ə" # LATIN SMALL LETTER SCHWA
12
+ - "ɚ" # LATIN SMALL LETTER SCHWA WITH HOOK
13
+ - "ɛ" # LATIN SMALL LETTER OPEN E
14
+ - "ɜ" # LATIN SMALL LETTER REVERSED OPEN E
15
+ - "ɝ" # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
16
+ - "ɞ" # LATIN SMALL LETTER CLOSED REVERSED OPEN E
17
+ - "ɟ" # LATIN SMALL LETTER DOTLESS J WITH STROKE
18
+ - "ɠ" # LATIN SMALL LETTER G WITH HOOK
19
+ - "ɡ" # LATIN SMALL LETTER SCRIPT G
20
+ - "ɢ" # LATIN LETTER SMALL CAPITAL G
21
+ - "ɣ" # LATIN SMALL LETTER GAMMA
22
+ - "ɤ" # LATIN SMALL LETTER RAMS HORN
23
+ - "ɥ" # LATIN SMALL LETTER TURNED H
24
+ - "ɦ" # LATIN SMALL LETTER H WITH HOOK
25
+ - "ɧ" # LATIN SMALL LETTER HENG WITH HOOK
26
+ - "ɨ" # LATIN SMALL LETTER I WITH STROKE
27
+ - "ɩ" # LATIN SMALL LETTER IOTA
28
+ - "ɪ" # LATIN LETTER SMALL CAPITAL I
29
+ - "ɫ" # LATIN SMALL LETTER L WITH MIDDLE TILDE
30
+ - "ɬ" # LATIN SMALL LETTER L WITH BELT
31
+ - "ɭ" # LATIN SMALL LETTER L WITH RETROFLEX HOOK
32
+ - "ɮ" # LATIN SMALL LETTER LEZH
33
+ - "ɯ" # LATIN SMALL LETTER TURNED M
34
+ - "ɰ" # LATIN SMALL LETTER TURNED M WITH LONG LEG
35
+ - "ɱ" # LATIN SMALL LETTER M WITH HOOK
36
+ - "ɲ" # LATIN SMALL LETTER N WITH LEFT HOOK
37
+ - "ɳ" # LATIN SMALL LETTER N WITH RETROFLEX HOOK
38
+ - "ɴ" # LATIN LETTER SMALL CAPITAL N
39
+ - "ɵ" # LATIN SMALL LETTER BARRED O
40
+ - "ɶ" # LATIN LETTER SMALL CAPITAL OE
41
+ - "ɷ" # LATIN SMALL LETTER CLOSED OMEGA
42
+ - "ɸ" # LATIN SMALL LETTER PHI
43
+ - "ɹ" # LATIN SMALL LETTER TURNED R
44
+ - "ɺ" # LATIN SMALL LETTER TURNED R WITH LONG LEG
45
+ - "ɻ" # LATIN SMALL LETTER TURNED R WITH HOOK
46
+ - "ɼ" # LATIN SMALL LETTER R WITH LONG LEG
47
+ - "ɽ" # LATIN SMALL LETTER R WITH TAIL
48
+ - "ɾ" # LATIN SMALL LETTER R WITH FISHHOOK
49
+ - "ɿ" # LATIN SMALL LETTER REVERSED R WITH FISHHOOK
50
+ - "ʀ" # LATIN LETTER SMALL CAPITAL R
51
+ - "ʁ" # LATIN LETTER SMALL CAPITAL INVERTED R
52
+ - "ʂ" # LATIN SMALL LETTER S WITH HOOK
53
+ - "ʃ" # LATIN SMALL LETTER ESH
54
+ - "ʄ" # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
55
+ - "ʅ" # LATIN SMALL LETTER SQUAT REVERSED ESH
56
+ - "ʆ" # LATIN SMALL LETTER ESH WITH CURL
57
+ - "ʇ" # LATIN SMALL LETTER TURNED T
58
+ - "ʈ" # LATIN SMALL LETTER T WITH RETROFLEX HOOK
59
+ - "ʉ" # LATIN SMALL LETTER U BAR
60
+ - "ʊ" # LATIN SMALL LETTER UPSILON
61
+ - "ʋ" # LATIN SMALL LETTER V WITH HOOK
62
+ - "ʌ" # LATIN SMALL LETTER TURNED V
63
+ - "ʍ" # LATIN SMALL LETTER TURNED W
64
+ - "ʎ" # LATIN SMALL LETTER TURNED Y
65
+ - "ʏ" # LATIN LETTER SMALL CAPITAL Y
66
+ - "ʐ" # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
67
+ - "ʑ" # LATIN SMALL LETTER Z WITH CURL
68
+ - "ʒ" # LATIN SMALL LETTER EZH
69
+ - "ʓ" # LATIN SMALL LETTER EZH WITH CURL
70
+ - "ʔ" # LATIN LETTER GLOTTAL STOP
71
+ - "ʕ" # LATIN LETTER PHARYNGEAL VOICED FRICATIVE
72
+ - "ʖ" # LATIN LETTER INVERTED GLOTTAL STOP
73
+ - "ʗ" # LATIN LETTER STRETCHED C
74
+ - "ʘ" # LATIN LETTER BILABIAL CLICK
75
+ - "ʙ" # LATIN LETTER SMALL CAPITAL B
76
+ - "ʚ" # LATIN SMALL LETTER CLOSED OPEN E
77
+ - "ʛ" # LATIN LETTER SMALL CAPITAL G WITH HOOK
78
+ - "ʜ" # LATIN LETTER SMALL CAPITAL H
79
+ - "ʝ" # LATIN SMALL LETTER J WITH CROSSED-TAIL
80
+ - "ʞ" # LATIN SMALL LETTER TURNED K
81
+ - "ʟ" # LATIN LETTER SMALL CAPITAL L
82
+ - "ʠ" # LATIN SMALL LETTER Q WITH HOOK
83
+ - "ʡ" # LATIN LETTER GLOTTAL STOP WITH STROKE
84
+ - "ʢ" # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
85
+ - "ʣ" # LATIN SMALL LETTER DZ DIGRAPH
86
+ - "ʤ" # LATIN SMALL LETTER DEZH DIGRAPH
87
+ - "ʥ" # LATIN SMALL LETTER DZ DIGRAPH WITH CURL
88
+ - "ʦ" # LATIN SMALL LETTER TS DIGRAPH
89
+ - "ʧ" # LATIN SMALL LETTER TESH DIGRAPH
90
+ - "ʨ" # LATIN SMALL LETTER TC DIGRAPH WITH CURL
91
+ - "ʩ" # LATIN SMALL LETTER FENG DIGRAPH
92
+ - "ʪ" # LATIN SMALL LETTER LS DIGRAPH
93
+ - "ʫ" # LATIN SMALL LETTER LZ DIGRAPH
94
+ - "ʬ" # LATIN SMALL LETTER BILABIAL PERCUSSIVE
95
+ - "ʭ" # LATIN SMALL LETTER BIDENTAL PERCUSSIVE
96
+ - "ʮ" # LATIN SMALL LETTER TURNED H WITH FISHHOOK
97
+ - "ʯ" # LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
data/data/csets/unicode/latin-extended-c.yaml ADDED
@@ -0,0 +1,18 @@
1
+ ---
2
+ - "Ⱡ" # LATIN CAPITAL LETTER L WITH DOUBLE BAR
3
+ - "ⱡ" # LATIN SMALL LETTER L WITH DOUBLE BAR
4
+ - "Ɫ" # LATIN CAPITAL LETTER L WITH MIDDLE TILDE
5
+ - "Ᵽ" # LATIN CAPITAL LETTER P WITH STROKE
6
+ - "Ɽ" # LATIN CAPITAL LETTER R WITH TAIL
7
+ - "ⱥ" # LATIN SMALL LETTER A WITH STROKE
8
+ - "ⱦ" # LATIN SMALL LETTER T WITH DIAGONAL STROKE
9
+ - "Ⱨ" # LATIN CAPITAL LETTER H WITH DESCENDER
10
+ - "ⱨ" # LATIN SMALL LETTER H WITH DESCENDER
11
+ - "Ⱪ" # LATIN CAPITAL LETTER K WITH DESCENDER
12
+ - "ⱪ" # LATIN SMALL LETTER K WITH DESCENDER
13
+ - "Ⱬ" # LATIN CAPITAL LETTER Z WITH DESCENDER
14
+ - "ⱬ" # LATIN SMALL LETTER Z WITH DESCENDER
15
+ - "ⱴ" # LATIN SMALL LETTER V WITH CURL
16
+ - "Ⱶ" # LATIN CAPITAL LETTER HALF H
17
+ - "ⱶ" # LATIN SMALL LETTER HALF H
18
+ - "ⱷ" # LATIN SMALL LETTER TAILLESS PHI
data/data/csets/unicode/latin-extended-d.yaml ADDED
@@ -0,0 +1,3 @@
1
+ ---
2
+ - "꜠" # MODIFIER LETTER STRESS AND HIGH TONE
3
+ - "꜡" # MODIFIER LETTER STRESS AND LOW TONE
data/data/csets/unicode/latin_1_supplement.yaml ADDED
@@ -0,0 +1,128 @@
1
+ ---
2
+ - "€" # [ANSI - EURO SIGN; MacRoman - LATIN CAPITAL LETTER A WITH DIAERESIS]
3
+ - "" # [MacRoman - LATIN CAPITAL LETTER A WITH RING ABOVE]
4
+ - "‚" # [ANSI - SINGLE LOW-9 QUOTATION MARK; MacRoman - LATIN CAPITAL LETTER C WITH CEDILLA]
5
+ - "ƒ" # [ANSI - LATIN SMALL LETTER F WITH HOOK; MacRoman - LATIN CAPITAL LETTER E WITH ACUTE]
6
+ - "„" # [ANSI - DOUBLE LOW-9 QUOTATION MARK; MacRoman - LATIN CAPITAL LETTER N WITH TILDE]
7
+ - "…" # [ANSI - HORIZONTAL ELLIPSIS; MacRoman - LATIN CAPITAL LETTER O WITH DIAERESIS]
8
+ - "†" # [ANSI - DAGGER; MacRoman - LATIN CAPITAL LETTER U WITH DIAERESIS]
9
+ - "‡" # [ANSI - DOUBLE DAGGER; MacRoman - LATIN SMALL LETTER A WITH ACUTE]
10
+ - "ˆ" # [ANSI - MODIFIER LETTER CIRCUMFLEX ACCENT; MacRoman - LATIN SMALL LETTER A WITH GRAVE]
11
+ - "‰" # [ANSI - PER MILLE SIGN; MacRoman - LATIN SMALL LETTER A WITH CIRCUMFLEX]
12
+ - "Š" # [ANSI - LATIN CAPITAL LETTER S WITH CARON; MacRoman - LATIN SMALL LETTER A WITH DIAERESIS]
13
+ - "‹" # [ANSI - SINGLE LEFT-POINTING ANGLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER A WITH TILDE]
14
+ - "Œ" # [ANSI - LATIN CAPITAL LETTER OE; MacRoman - LATIN SMALL LETTER A WITH RING ABOVE]
15
+ - "" # [MacRoman - LATIN SMALL LETTER C WITH CEDILLA]
16
+ - "Ž" # [ANSI - LATIN CAPITAL LETTER Z WITH CARON; MacRoman - LATIN SMALL LETTER E WITH ACUTE]
17
+ - "" # [MacRoman - LATIN SMALL LETTER E WITH GRAVE]
18
+ - "" # [MacRoman - LATIN SMALL LETTER E WITH CIRCUMFLEX]
19
+ - "‘" # [ANSI - LEFT SINGLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER E WITH DIAERESIS]
20
+ - "’" # [ANSI - RIGHT SINGLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER I WITH ACUTE]
21
+ - "“" # [ANSI - LEFT DOUBLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER I WITH GRAVE]
22
+ - "”" # [ANSI - RIGHT DOUBLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER I WITH CIRCUMFLEX]
23
+ - "•" # [ANSI - BULLET; MacRoman - LATIN SMALL LETTER I WITH DIAERESIS]
24
+ - "–" # [ANSI - EN DASH; MacRoman - LATIN SMALL LETTER N WITH TILDE]
25
+ - "—" # [ANSI - EM DASH; MacRoman - LATIN SMALL LETTER O WITH ACUTE]
26
+ - "˜" # [ANSI - SMALL TILDE; MacRoman - LATIN SMALL LETTER O WITH GRAVE]
27
+ - "™" # [ANSI - TRADE MARK SIGN; MacRoman - LATIN SMALL LETTER O WITH CIRCUMFLEX]
28
+ - "š" # [ANSI - LATIN SMALL LETTER S WITH CARON; MacRoman - LATIN SMALL LETTER O WITH DIAERESIS]
29
+ - "›" # [ANSI - SINGLE RIGHT-POINTING ANGLE QUOTATION MARK; MacRoman - LATIN SMALL LETTER O WITH TILDE]
30
+ - "œ" # [ANSI - LATIN SMALL LETTER OE; MacRoman - LATIN SMALL LETTER U WITH ACUTE]
31
+ - "" # [MacRoman - LATIN SMALL LETTER U WITH GRAVE]
32
+ - "ž" # [ANSI - LATIN SMALL LETTER Z WITH CARON; MacRoman - LATIN SMALL LETTER U WITH CIRCUMFLEX]
33
+ - "Ÿ" # [ANSI - LATIN CAPITAL LETTER Y WITH DIAERESIS; MacRoman - LATIN SMALL LETTER U WITH DIAERESIS]
34
+ - "¡" # INVERTED EXCLAMATION MARK
35
+ - "¢" # CENT SIGN
36
+ - "£" # POUND SIGN [lira sign is ₤]
37
+ - "¤" # CURRENCY SIGN
38
+ - "¥" # YEN SIGN
39
+ - "¦" # BROKEN BAR
40
+ - "§" # SECTION SIGN
41
+ - "¨" # DIAERESIS
42
+ - "©" # COPYRIGHT SIGN (present in Symbol font)
43
+ - "ª" # FEMININE ORDINAL INDICATOR
44
+ - "«" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
45
+ - "¬" # NOT SIGN (present in Symbol font)
46
+ - "­" # SOFT HYPHEN
47
+ - "®" # REGISTERED SIGN (present in Symbol font)
48
+ - "¯" # MACRON
49
+ - "°" # DEGREE SIGN
50
+ - "±" # PLUS-MINUS SIGN (present in Symbol font)
51
+ - "²" # SUPERSCRIPT TWO
52
+ - "³" # SUPERSCRIPT THREE
53
+ - "´" # ACUTE ACCENT
54
+ - "µ" # MICRO SIGN
55
+ - "¶" # PILCROW SIGN
56
+ - "·" # MIDDLE DOT
57
+ - "¸" # CEDILLA
58
+ - "¹" # SUPERSCRIPT ONE
59
+ - "º" # MASCULINE ORDINAL INDICATOR
60
+ - "»" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
61
+ - "¼" # VULGAR FRACTION ONE QUARTER
62
+ - "½" # VULGAR FRACTION ONE HALF
63
+ - "¾" # VULGAR FRACTION THREE QUARTERS
64
+ - "¿" # INVERTED QUESTION MARK
65
+ - "À" # LATIN CAPITAL LETTER A WITH GRAVE
66
+ - "Á" # LATIN CAPITAL LETTER A WITH ACUTE
67
+ - "Â" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
68
+ - "Ã" # LATIN CAPITAL LETTER A WITH TILDE
69
+ - "Ä" # LATIN CAPITAL LETTER A WITH DIAERESIS
70
+ - "Å" # LATIN CAPITAL LETTER A WITH RING ABOVE
71
+ - "Æ" # LATIN CAPITAL LETTER AE
72
+ - "Ç" # LATIN CAPITAL LETTER C WITH CEDILLA
73
+ - "È" # LATIN CAPITAL LETTER E WITH GRAVE
74
+ - "É" # LATIN CAPITAL LETTER E WITH ACUTE
75
+ - "Ê" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
76
+ - "Ë" # LATIN CAPITAL LETTER E WITH DIAERESIS
77
+ - "Ì" # LATIN CAPITAL LETTER I WITH GRAVE
78
+ - "Í" # LATIN CAPITAL LETTER I WITH ACUTE
79
+ - "Î" # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
80
+ - "Ï" # LATIN CAPITAL LETTER I WITH DIAERESIS
81
+ - "Ð" # LATIN CAPITAL LETTER ETH
82
+ - "Ñ" # LATIN CAPITAL LETTER N WITH TILDE
83
+ - "Ò" # LATIN CAPITAL LETTER O WITH GRAVE
84
+ - "Ó" # LATIN CAPITAL LETTER O WITH ACUTE
85
+ - "Ô" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
86
+ - "Õ" # LATIN CAPITAL LETTER O WITH TILDE
87
+ - "Ö" # LATIN CAPITAL LETTER O WITH DIAERESIS
88
+ - "×" # MULTIPLICATION SIGN (present in Symbol font)
89
+ - "Ø" # LATIN CAPITAL LETTER O WITH STROKE
90
+ - "Ù" # LATIN CAPITAL LETTER U WITH GRAVE
91
+ - "Ú" # LATIN CAPITAL LETTER U WITH ACUTE
92
+ - "Û" # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
93
+ - "Ü" # LATIN CAPITAL LETTER U WITH DIAERESIS
94
+ - "Ý" # LATIN CAPITAL LETTER Y WITH ACUTE
95
+ - "Þ" # LATIN CAPITAL LETTER THORN
96
+ - "ß" # LATIN SMALL LETTER SHARP S
97
+ - "à" # LATIN SMALL LETTER A WITH GRAVE
98
+ - "á" # LATIN SMALL LETTER A WITH ACUTE
99
+ - "â" # LATIN SMALL LETTER A WITH CIRCUMFLEX
100
+ - "ã" # LATIN SMALL LETTER A WITH TILDE
101
+ - "ä" # LATIN SMALL LETTER A WITH DIAERESIS
102
+ - "å" # LATIN SMALL LETTER A WITH RING ABOVE
103
+ - "æ" # LATIN SMALL LETTER AE
104
+ - "ç" # LATIN SMALL LETTER C WITH CEDILLA
105
+ - "è" # LATIN SMALL LETTER E WITH GRAVE
106
+ - "é" # LATIN SMALL LETTER E WITH ACUTE
107
+ - "ê" # LATIN SMALL LETTER E WITH CIRCUMFLEX
108
+ - "ë" # LATIN SMALL LETTER E WITH DIAERESIS
109
+ - "ì" # LATIN SMALL LETTER I WITH GRAVE
110
+ - "í" # LATIN SMALL LETTER I WITH ACUTE
111
+ - "î" # LATIN SMALL LETTER I WITH CIRCUMFLEX
112
+ - "ï" # LATIN SMALL LETTER I WITH DIAERESIS
113
+ - "ð" # LATIN SMALL LETTER ETH
114
+ - "ñ" # LATIN SMALL LETTER N WITH TILDE
115
+ - "ò" # LATIN SMALL LETTER O WITH GRAVE
116
+ - "ó" # LATIN SMALL LETTER O WITH ACUTE
117
+ - "ô" # LATIN SMALL LETTER O WITH CIRCUMFLEX
118
+ - "õ" # LATIN SMALL LETTER O WITH TILDE
119
+ - "ö" # LATIN SMALL LETTER O WITH DIAERESIS
120
+ - "÷" # DIVISION SIGN (present in Symbol font)
121
+ - "ø" # LATIN SMALL LETTER O WITH STROKE
122
+ - "ù" # LATIN SMALL LETTER U WITH GRAVE
123
+ - "ú" # LATIN SMALL LETTER U WITH ACUTE
124
+ - "û" # LATIN SMALL LETTER U WITH CIRCUMFLEX
125
+ - "ü" # LATIN SMALL LETTER U WITH DIAERESIS
126
+ - "ý" # LATIN SMALL LETTER Y WITH ACUTE
127
+ - "þ" # LATIN SMALL LETTER THORN
128
+ - "ÿ" # LATIN SMALL LETTER Y WITH DIAERESIS
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