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.
- data/COPYING +676 -0
- data/ChangeLog +6 -0
- data/README +53 -0
- data/Rakefile +30 -0
- data/bin/cinderella +186 -0
- data/bin/decode_entities +101 -0
- data/bin/guess_encoding +183 -0
- data/data/csets/iso_8859-1.yaml +195 -0
- data/data/csets/iso_8859-15.yaml +204 -0
- data/data/csets/latin1.yaml +195 -0
- data/data/csets/unicode/basic_latin.yaml +97 -0
- data/data/csets/unicode/cyrillic-supplement.yaml +17 -0
- data/data/csets/unicode/cyrillic.yaml +256 -0
- data/data/csets/unicode/greek.yaml +129 -0
- data/data/csets/unicode/ipa_extensions.yaml +97 -0
- data/data/csets/unicode/latin-extended-c.yaml +18 -0
- data/data/csets/unicode/latin-extended-d.yaml +3 -0
- data/data/csets/unicode/latin_1_supplement.yaml +128 -0
- data/data/csets/unicode/latin_extended_a.yaml +129 -0
- data/data/csets/unicode/latin_extended_additional.yaml +247 -0
- data/data/csets/unicode/latin_extended_b.yaml +209 -0
- data/data/csets/unicode/letterlike_symbols.yaml +80 -0
- data/data/csets/unicode/spacing_modifier_letters.yaml +81 -0
- data/data/csets/utf-8.yaml +1504 -0
- data/data/csets/utf8.yaml +1504 -0
- data/example/crop +127 -0
- data/example/crop_repaired +127 -0
- data/example/empty6-slash.txt +1495 -0
- data/example/empty6-slash_repaired.txt +1495 -0
- data/example/pot +1368 -0
- data/lib/cmess.rb +44 -0
- data/lib/cmess/cinderella.rb +63 -0
- data/lib/cmess/cli.rb +79 -0
- data/lib/cmess/decode_entities.rb +68 -0
- data/lib/cmess/guess_encoding.rb +372 -0
- data/lib/cmess/version.rb +51 -0
- metadata +119 -0
@@ -0,0 +1,195 @@
|
|
1
|
+
---
|
2
|
+
# ====[ basic_latin ]====
|
3
|
+
#- " " # SPACE
|
4
|
+
#- "!" # EXCLAMATION MARK
|
5
|
+
#- '"' # QUOTATION MARK
|
6
|
+
#- "#" # NUMBER SIGN
|
7
|
+
#- "$" # DOLLAR SIGN
|
8
|
+
#- "%" # PERCENT SIGN
|
9
|
+
#- "&" # AMPERSAND
|
10
|
+
#- "'" # APOSTROPHE
|
11
|
+
#- "(" # LEFT PARENTHESIS
|
12
|
+
#- ")" # RIGHT PARENTHESIS
|
13
|
+
#- "*" # ASTERISK
|
14
|
+
#- "+" # PLUS SIGN
|
15
|
+
#- "," # COMMA
|
16
|
+
#- "-" # HYPHEN-MINUS
|
17
|
+
#- "." # FULL STOP
|
18
|
+
#- "/" # SOLIDUS
|
19
|
+
#- "0" # DIGIT ZERO
|
20
|
+
#- "1" # DIGIT ONE
|
21
|
+
#- "2" # DIGIT TWO
|
22
|
+
#- "3" # DIGIT THREE
|
23
|
+
#- "4" # DIGIT FOUR
|
24
|
+
#- "5" # DIGIT FIVE
|
25
|
+
#- "6" # DIGIT SIX
|
26
|
+
#- "7" # DIGIT SEVEN
|
27
|
+
#- "8" # DIGIT EIGHT
|
28
|
+
#- "9" # DIGIT NINE
|
29
|
+
#- ":" # COLON
|
30
|
+
#- ";" # SEMICOLON
|
31
|
+
#- "<" # LESS-THAN SIGN
|
32
|
+
#- "=" # EQUALS SIGN
|
33
|
+
#- ">" # GREATER-THAN SIGN
|
34
|
+
#- "?" # QUESTION MARK
|
35
|
+
#- "@" # COMMERCIAL AT
|
36
|
+
#- "A" # LATIN CAPITAL LETTER A
|
37
|
+
#- "B" # LATIN CAPITAL LETTER B
|
38
|
+
#- "C" # LATIN CAPITAL LETTER C
|
39
|
+
#- "D" # LATIN CAPITAL LETTER D
|
40
|
+
#- "E" # LATIN CAPITAL LETTER E
|
41
|
+
#- "F" # LATIN CAPITAL LETTER F
|
42
|
+
#- "G" # LATIN CAPITAL LETTER G
|
43
|
+
#- "H" # LATIN CAPITAL LETTER H
|
44
|
+
#- "I" # LATIN CAPITAL LETTER I
|
45
|
+
#- "J" # LATIN CAPITAL LETTER J
|
46
|
+
#- "K" # LATIN CAPITAL LETTER K
|
47
|
+
#- "L" # LATIN CAPITAL LETTER L
|
48
|
+
#- "M" # LATIN CAPITAL LETTER M
|
49
|
+
#- "N" # LATIN CAPITAL LETTER N
|
50
|
+
#- "O" # LATIN CAPITAL LETTER O
|
51
|
+
#- "P" # LATIN CAPITAL LETTER P
|
52
|
+
#- "Q" # LATIN CAPITAL LETTER Q
|
53
|
+
#- "R" # LATIN CAPITAL LETTER R
|
54
|
+
#- "S" # LATIN CAPITAL LETTER S
|
55
|
+
#- "T" # LATIN CAPITAL LETTER T
|
56
|
+
#- "U" # LATIN CAPITAL LETTER U
|
57
|
+
#- "V" # LATIN CAPITAL LETTER V
|
58
|
+
#- "W" # LATIN CAPITAL LETTER W
|
59
|
+
#- "X" # LATIN CAPITAL LETTER X
|
60
|
+
#- "Y" # LATIN CAPITAL LETTER Y
|
61
|
+
#- "Z" # LATIN CAPITAL LETTER Z
|
62
|
+
#- "[" # LEFT SQUARE BRACKET
|
63
|
+
#- "\\" # REVERSE SOLIDUS
|
64
|
+
#- "]" # RIGHT SQUARE BRACKET
|
65
|
+
#- "^" # CIRCUMFLEX ACCENT
|
66
|
+
#- "_" # LOW LINE
|
67
|
+
#- "`" # GRAVE ACCENT
|
68
|
+
#- "a" # LATIN SMALL LETTER A
|
69
|
+
#- "b" # LATIN SMALL LETTER B
|
70
|
+
#- "c" # LATIN SMALL LETTER C
|
71
|
+
#- "d" # LATIN SMALL LETTER D
|
72
|
+
#- "e" # LATIN SMALL LETTER E
|
73
|
+
#- "f" # LATIN SMALL LETTER F
|
74
|
+
#- "g" # LATIN SMALL LETTER G
|
75
|
+
#- "h" # LATIN SMALL LETTER H
|
76
|
+
#- "i" # LATIN SMALL LETTER I
|
77
|
+
#- "j" # LATIN SMALL LETTER J
|
78
|
+
#- "k" # LATIN SMALL LETTER K
|
79
|
+
#- "l" # LATIN SMALL LETTER L
|
80
|
+
#- "m" # LATIN SMALL LETTER M
|
81
|
+
#- "n" # LATIN SMALL LETTER N
|
82
|
+
#- "o" # LATIN SMALL LETTER O
|
83
|
+
#- "p" # LATIN SMALL LETTER P
|
84
|
+
#- "q" # LATIN SMALL LETTER Q
|
85
|
+
#- "r" # LATIN SMALL LETTER R
|
86
|
+
#- "s" # LATIN SMALL LETTER S
|
87
|
+
#- "t" # LATIN SMALL LETTER T
|
88
|
+
#- "u" # LATIN SMALL LETTER U
|
89
|
+
#- "v" # LATIN SMALL LETTER V
|
90
|
+
#- "w" # LATIN SMALL LETTER W
|
91
|
+
#- "x" # LATIN SMALL LETTER X
|
92
|
+
#- "y" # LATIN SMALL LETTER Y
|
93
|
+
#- "z" # LATIN SMALL LETTER Z
|
94
|
+
#- "{" # LEFT CURLY BRACKET
|
95
|
+
#- "|" # VERTICAL LINE
|
96
|
+
#- "}" # RIGHT CURLY BRACKET
|
97
|
+
#- "~" # TILDE
|
98
|
+
#- "" # DEL
|
99
|
+
|
100
|
+
# ====[ latin_1_supplement ]====
|
101
|
+
- "�" # INVERTED EXCLAMATION MARK
|
102
|
+
- "�" # CENT SIGN
|
103
|
+
- "�" # POUND SIGN
|
104
|
+
- "�" # CURRENCY SIGN
|
105
|
+
- "�" # YEN SIGN
|
106
|
+
- "�" # BROKEN BAR
|
107
|
+
- "�" # SECTION SIGN
|
108
|
+
- "�" # DIAERESIS
|
109
|
+
- "�" # COPYRIGHT SIGN (present in Symbol font)
|
110
|
+
- "�" # FEMININE ORDINAL INDICATOR
|
111
|
+
- "�" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
112
|
+
- "�" # NOT SIGN (present in Symbol font)
|
113
|
+
- "�" # SOFT HYPHEN
|
114
|
+
- "�" # REGISTERED SIGN (present in Symbol font)
|
115
|
+
- "�" # MACRON
|
116
|
+
- "�" # DEGREE SIGN
|
117
|
+
- "�" # PLUS-MINUS SIGN (present in Symbol font)
|
118
|
+
- "�" # SUPERSCRIPT TWO
|
119
|
+
- "�" # SUPERSCRIPT THREE
|
120
|
+
- "�" # ACUTE ACCENT
|
121
|
+
- "�" # MICRO SIGN
|
122
|
+
- "�" # PILCROW SIGN
|
123
|
+
- "�" # MIDDLE DOT
|
124
|
+
- "�" # CEDILLA
|
125
|
+
- "�" # SUPERSCRIPT ONE
|
126
|
+
- "�" # MASCULINE ORDINAL INDICATOR
|
127
|
+
- "�" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
128
|
+
- "�" # VULGAR FRACTION ONE QUARTER
|
129
|
+
- "�" # VULGAR FRACTION ONE HALF
|
130
|
+
- "�" # VULGAR FRACTION THREE QUARTERS
|
131
|
+
- "�" # INVERTED QUESTION MARK
|
132
|
+
- "�" # LATIN CAPITAL LETTER A WITH GRAVE
|
133
|
+
- "�" # LATIN CAPITAL LETTER A WITH ACUTE
|
134
|
+
- "�" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
135
|
+
- "�" # LATIN CAPITAL LETTER A WITH TILDE
|
136
|
+
- "�" # LATIN CAPITAL LETTER A WITH DIAERESIS
|
137
|
+
- "�" # LATIN CAPITAL LETTER A WITH RING ABOVE
|
138
|
+
- "�" # LATIN CAPITAL LETTER AE
|
139
|
+
- "�" # LATIN CAPITAL LETTER C WITH CEDILLA
|
140
|
+
- "�" # LATIN CAPITAL LETTER E WITH GRAVE
|
141
|
+
- "�" # LATIN CAPITAL LETTER E WITH ACUTE
|
142
|
+
- "�" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
143
|
+
- "�" # LATIN CAPITAL LETTER E WITH DIAERESIS
|
144
|
+
- "�" # LATIN CAPITAL LETTER I WITH GRAVE
|
145
|
+
- "�" # LATIN CAPITAL LETTER I WITH ACUTE
|
146
|
+
- "�" # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
147
|
+
- "�" # LATIN CAPITAL LETTER I WITH DIAERESIS
|
148
|
+
- "�" # LATIN CAPITAL LETTER ETH
|
149
|
+
- "�" # LATIN CAPITAL LETTER N WITH TILDE
|
150
|
+
- "�" # LATIN CAPITAL LETTER O WITH GRAVE
|
151
|
+
- "�" # LATIN CAPITAL LETTER O WITH ACUTE
|
152
|
+
- "�" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
153
|
+
- "�" # LATIN CAPITAL LETTER O WITH TILDE
|
154
|
+
- "�" # LATIN CAPITAL LETTER O WITH DIAERESIS
|
155
|
+
- "�" # MULTIPLICATION SIGN (present in Symbol font)
|
156
|
+
- "�" # LATIN CAPITAL LETTER O WITH STROKE
|
157
|
+
- "�" # LATIN CAPITAL LETTER U WITH GRAVE
|
158
|
+
- "�" # LATIN CAPITAL LETTER U WITH ACUTE
|
159
|
+
- "�" # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
160
|
+
- "�" # LATIN CAPITAL LETTER U WITH DIAERESIS
|
161
|
+
- "�" # LATIN CAPITAL LETTER Y WITH ACUTE
|
162
|
+
- "�" # LATIN CAPITAL LETTER THORN
|
163
|
+
- "�" # LATIN SMALL LETTER SHARP S
|
164
|
+
- "�" # LATIN SMALL LETTER A WITH GRAVE
|
165
|
+
- "�" # LATIN SMALL LETTER A WITH ACUTE
|
166
|
+
- "�" # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
167
|
+
- "�" # LATIN SMALL LETTER A WITH TILDE
|
168
|
+
- "�" # LATIN SMALL LETTER A WITH DIAERESIS
|
169
|
+
- "�" # LATIN SMALL LETTER A WITH RING ABOVE
|
170
|
+
- "�" # LATIN SMALL LETTER AE
|
171
|
+
- "�" # LATIN SMALL LETTER C WITH CEDILLA
|
172
|
+
- "�" # LATIN SMALL LETTER E WITH GRAVE
|
173
|
+
- "�" # LATIN SMALL LETTER E WITH ACUTE
|
174
|
+
- "�" # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
175
|
+
- "�" # LATIN SMALL LETTER E WITH DIAERESIS
|
176
|
+
- "�" # LATIN SMALL LETTER I WITH GRAVE
|
177
|
+
- "�" # LATIN SMALL LETTER I WITH ACUTE
|
178
|
+
- "�" # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
179
|
+
- "�" # LATIN SMALL LETTER I WITH DIAERESIS
|
180
|
+
- "�" # LATIN SMALL LETTER ETH
|
181
|
+
- "�" # LATIN SMALL LETTER N WITH TILDE
|
182
|
+
- "�" # LATIN SMALL LETTER O WITH GRAVE
|
183
|
+
- "�" # LATIN SMALL LETTER O WITH ACUTE
|
184
|
+
- "�" # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
185
|
+
- "�" # LATIN SMALL LETTER O WITH TILDE
|
186
|
+
- "�" # LATIN SMALL LETTER O WITH DIAERESIS
|
187
|
+
- "�" # DIVISION SIGN (present in Symbol font)
|
188
|
+
- "�" # LATIN SMALL LETTER O WITH STROKE
|
189
|
+
- "�" # LATIN SMALL LETTER U WITH GRAVE
|
190
|
+
- "�" # LATIN SMALL LETTER U WITH ACUTE
|
191
|
+
- "�" # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
192
|
+
- "�" # LATIN SMALL LETTER U WITH DIAERESIS
|
193
|
+
- "�" # LATIN SMALL LETTER Y WITH ACUTE
|
194
|
+
- "�" # LATIN SMALL LETTER THORN
|
195
|
+
- "�" # LATIN SMALL LETTER Y WITH DIAERESIS
|
@@ -0,0 +1,204 @@
|
|
1
|
+
---
|
2
|
+
# ====[ basic_latin ]====
|
3
|
+
#- " " # SPACE
|
4
|
+
#- "!" # EXCLAMATION MARK
|
5
|
+
#- '"' # QUOTATION MARK
|
6
|
+
#- "#" # NUMBER SIGN
|
7
|
+
#- "$" # DOLLAR SIGN
|
8
|
+
#- "%" # PERCENT SIGN
|
9
|
+
#- "&" # AMPERSAND
|
10
|
+
#- "'" # APOSTROPHE
|
11
|
+
#- "(" # LEFT PARENTHESIS
|
12
|
+
#- ")" # RIGHT PARENTHESIS
|
13
|
+
#- "*" # ASTERISK
|
14
|
+
#- "+" # PLUS SIGN
|
15
|
+
#- "," # COMMA
|
16
|
+
#- "-" # HYPHEN-MINUS
|
17
|
+
#- "." # FULL STOP
|
18
|
+
#- "/" # SOLIDUS
|
19
|
+
#- "0" # DIGIT ZERO
|
20
|
+
#- "1" # DIGIT ONE
|
21
|
+
#- "2" # DIGIT TWO
|
22
|
+
#- "3" # DIGIT THREE
|
23
|
+
#- "4" # DIGIT FOUR
|
24
|
+
#- "5" # DIGIT FIVE
|
25
|
+
#- "6" # DIGIT SIX
|
26
|
+
#- "7" # DIGIT SEVEN
|
27
|
+
#- "8" # DIGIT EIGHT
|
28
|
+
#- "9" # DIGIT NINE
|
29
|
+
#- ":" # COLON
|
30
|
+
#- ";" # SEMICOLON
|
31
|
+
#- "<" # LESS-THAN SIGN
|
32
|
+
#- "=" # EQUALS SIGN
|
33
|
+
#- ">" # GREATER-THAN SIGN
|
34
|
+
#- "?" # QUESTION MARK
|
35
|
+
#- "@" # COMMERCIAL AT
|
36
|
+
#- "A" # LATIN CAPITAL LETTER A
|
37
|
+
#- "B" # LATIN CAPITAL LETTER B
|
38
|
+
#- "C" # LATIN CAPITAL LETTER C
|
39
|
+
#- "D" # LATIN CAPITAL LETTER D
|
40
|
+
#- "E" # LATIN CAPITAL LETTER E
|
41
|
+
#- "F" # LATIN CAPITAL LETTER F
|
42
|
+
#- "G" # LATIN CAPITAL LETTER G
|
43
|
+
#- "H" # LATIN CAPITAL LETTER H
|
44
|
+
#- "I" # LATIN CAPITAL LETTER I
|
45
|
+
#- "J" # LATIN CAPITAL LETTER J
|
46
|
+
#- "K" # LATIN CAPITAL LETTER K
|
47
|
+
#- "L" # LATIN CAPITAL LETTER L
|
48
|
+
#- "M" # LATIN CAPITAL LETTER M
|
49
|
+
#- "N" # LATIN CAPITAL LETTER N
|
50
|
+
#- "O" # LATIN CAPITAL LETTER O
|
51
|
+
#- "P" # LATIN CAPITAL LETTER P
|
52
|
+
#- "Q" # LATIN CAPITAL LETTER Q
|
53
|
+
#- "R" # LATIN CAPITAL LETTER R
|
54
|
+
#- "S" # LATIN CAPITAL LETTER S
|
55
|
+
#- "T" # LATIN CAPITAL LETTER T
|
56
|
+
#- "U" # LATIN CAPITAL LETTER U
|
57
|
+
#- "V" # LATIN CAPITAL LETTER V
|
58
|
+
#- "W" # LATIN CAPITAL LETTER W
|
59
|
+
#- "X" # LATIN CAPITAL LETTER X
|
60
|
+
#- "Y" # LATIN CAPITAL LETTER Y
|
61
|
+
#- "Z" # LATIN CAPITAL LETTER Z
|
62
|
+
#- "[" # LEFT SQUARE BRACKET
|
63
|
+
#- "\\" # REVERSE SOLIDUS
|
64
|
+
#- "]" # RIGHT SQUARE BRACKET
|
65
|
+
#- "^" # CIRCUMFLEX ACCENT
|
66
|
+
#- "_" # LOW LINE
|
67
|
+
#- "`" # GRAVE ACCENT
|
68
|
+
#- "a" # LATIN SMALL LETTER A
|
69
|
+
#- "b" # LATIN SMALL LETTER B
|
70
|
+
#- "c" # LATIN SMALL LETTER C
|
71
|
+
#- "d" # LATIN SMALL LETTER D
|
72
|
+
#- "e" # LATIN SMALL LETTER E
|
73
|
+
#- "f" # LATIN SMALL LETTER F
|
74
|
+
#- "g" # LATIN SMALL LETTER G
|
75
|
+
#- "h" # LATIN SMALL LETTER H
|
76
|
+
#- "i" # LATIN SMALL LETTER I
|
77
|
+
#- "j" # LATIN SMALL LETTER J
|
78
|
+
#- "k" # LATIN SMALL LETTER K
|
79
|
+
#- "l" # LATIN SMALL LETTER L
|
80
|
+
#- "m" # LATIN SMALL LETTER M
|
81
|
+
#- "n" # LATIN SMALL LETTER N
|
82
|
+
#- "o" # LATIN SMALL LETTER O
|
83
|
+
#- "p" # LATIN SMALL LETTER P
|
84
|
+
#- "q" # LATIN SMALL LETTER Q
|
85
|
+
#- "r" # LATIN SMALL LETTER R
|
86
|
+
#- "s" # LATIN SMALL LETTER S
|
87
|
+
#- "t" # LATIN SMALL LETTER T
|
88
|
+
#- "u" # LATIN SMALL LETTER U
|
89
|
+
#- "v" # LATIN SMALL LETTER V
|
90
|
+
#- "w" # LATIN SMALL LETTER W
|
91
|
+
#- "x" # LATIN SMALL LETTER X
|
92
|
+
#- "y" # LATIN SMALL LETTER Y
|
93
|
+
#- "z" # LATIN SMALL LETTER Z
|
94
|
+
#- "{" # LEFT CURLY BRACKET
|
95
|
+
#- "|" # VERTICAL LINE
|
96
|
+
#- "}" # RIGHT CURLY BRACKET
|
97
|
+
#- "~" # TILDE
|
98
|
+
#- "" # DEL
|
99
|
+
|
100
|
+
# ====[ latin_1_supplement ]====
|
101
|
+
- "�" # [ANSI - EURO SIGN; MacRoman - LATIN CAPITAL LETTER A WITH DIAERESIS]
|
102
|
+
- "�" # [ANSI - LATIN CAPITAL LETTER S WITH CARON; MacRoman - LATIN SMALL LETTER A WITH DIAERESIS]
|
103
|
+
- "�" # [ANSI - LATIN CAPITAL LETTER OE; MacRoman - LATIN SMALL LETTER A WITH RING ABOVE]
|
104
|
+
- "�" # [ANSI - LATIN CAPITAL LETTER Z WITH CARON; MacRoman - LATIN SMALL LETTER E WITH ACUTE]
|
105
|
+
- "�" # [ANSI - LATIN SMALL LETTER S WITH CARON; MacRoman - LATIN SMALL LETTER O WITH DIAERESIS]
|
106
|
+
- "�" # [ANSI - LATIN SMALL LETTER OE; MacRoman - LATIN SMALL LETTER U WITH ACUTE]
|
107
|
+
- "�" # [ANSI - LATIN SMALL LETTER Z WITH CARON; MacRoman - LATIN SMALL LETTER U WITH CIRCUMFLEX]
|
108
|
+
- "�" # [ANSI - LATIN CAPITAL LETTER Y WITH DIAERESIS; MacRoman - LATIN SMALL LETTER U WITH DIAERESIS]
|
109
|
+
- "�" # INVERTED EXCLAMATION MARK
|
110
|
+
- "�" # CENT SIGN
|
111
|
+
- "�" # POUND SIGN
|
112
|
+
- "�" # YEN SIGN
|
113
|
+
- "�" # SECTION SIGN
|
114
|
+
- "�" # COPYRIGHT SIGN (present in Symbol font)
|
115
|
+
- "�" # FEMININE ORDINAL INDICATOR
|
116
|
+
- "�" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
117
|
+
- "�" # NOT SIGN (present in Symbol font)
|
118
|
+
- "�" # SOFT HYPHEN
|
119
|
+
- "�" # REGISTERED SIGN (present in Symbol font)
|
120
|
+
- "�" # MACRON
|
121
|
+
- "�" # DEGREE SIGN
|
122
|
+
- "�" # PLUS-MINUS SIGN (present in Symbol font)
|
123
|
+
- "�" # SUPERSCRIPT TWO
|
124
|
+
- "�" # SUPERSCRIPT THREE
|
125
|
+
- "�" # MICRO SIGN
|
126
|
+
- "�" # PILCROW SIGN
|
127
|
+
- "�" # MIDDLE DOT
|
128
|
+
- "�" # SUPERSCRIPT ONE
|
129
|
+
- "�" # MASCULINE ORDINAL INDICATOR
|
130
|
+
- "�" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
131
|
+
- "�" # INVERTED QUESTION MARK
|
132
|
+
- "�" # LATIN CAPITAL LETTER A WITH GRAVE
|
133
|
+
- "�" # LATIN CAPITAL LETTER A WITH ACUTE
|
134
|
+
- "�" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
135
|
+
- "�" # LATIN CAPITAL LETTER A WITH TILDE
|
136
|
+
- "�" # LATIN CAPITAL LETTER A WITH DIAERESIS
|
137
|
+
- "�" # LATIN CAPITAL LETTER A WITH RING ABOVE
|
138
|
+
- "�" # LATIN CAPITAL LETTER AE
|
139
|
+
- "�" # LATIN CAPITAL LETTER C WITH CEDILLA
|
140
|
+
- "�" # LATIN CAPITAL LETTER E WITH GRAVE
|
141
|
+
- "�" # LATIN CAPITAL LETTER E WITH ACUTE
|
142
|
+
- "�" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
143
|
+
- "�" # LATIN CAPITAL LETTER E WITH DIAERESIS
|
144
|
+
- "�" # LATIN CAPITAL LETTER I WITH GRAVE
|
145
|
+
- "�" # LATIN CAPITAL LETTER I WITH ACUTE
|
146
|
+
- "�" # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
147
|
+
- "�" # LATIN CAPITAL LETTER I WITH DIAERESIS
|
148
|
+
- "�" # LATIN CAPITAL LETTER ETH
|
149
|
+
- "�" # LATIN CAPITAL LETTER N WITH TILDE
|
150
|
+
- "�" # LATIN CAPITAL LETTER O WITH GRAVE
|
151
|
+
- "�" # LATIN CAPITAL LETTER O WITH ACUTE
|
152
|
+
- "�" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
153
|
+
- "�" # LATIN CAPITAL LETTER O WITH TILDE
|
154
|
+
- "�" # LATIN CAPITAL LETTER O WITH DIAERESIS
|
155
|
+
- "�" # MULTIPLICATION SIGN (present in Symbol font)
|
156
|
+
- "�" # LATIN CAPITAL LETTER O WITH STROKE
|
157
|
+
- "�" # LATIN CAPITAL LETTER U WITH GRAVE
|
158
|
+
- "�" # LATIN CAPITAL LETTER U WITH ACUTE
|
159
|
+
- "�" # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
160
|
+
- "�" # LATIN CAPITAL LETTER U WITH DIAERESIS
|
161
|
+
- "�" # LATIN CAPITAL LETTER Y WITH ACUTE
|
162
|
+
- "�" # LATIN CAPITAL LETTER THORN
|
163
|
+
- "�" # LATIN SMALL LETTER SHARP S
|
164
|
+
- "�" # LATIN SMALL LETTER A WITH GRAVE
|
165
|
+
- "�" # LATIN SMALL LETTER A WITH ACUTE
|
166
|
+
- "�" # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
167
|
+
- "�" # LATIN SMALL LETTER A WITH TILDE
|
168
|
+
- "�" # LATIN SMALL LETTER A WITH DIAERESIS
|
169
|
+
- "�" # LATIN SMALL LETTER A WITH RING ABOVE
|
170
|
+
- "�" # LATIN SMALL LETTER AE
|
171
|
+
- "�" # LATIN SMALL LETTER C WITH CEDILLA
|
172
|
+
- "�" # LATIN SMALL LETTER E WITH GRAVE
|
173
|
+
- "�" # LATIN SMALL LETTER E WITH ACUTE
|
174
|
+
- "�" # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
175
|
+
- "�" # LATIN SMALL LETTER E WITH DIAERESIS
|
176
|
+
- "�" # LATIN SMALL LETTER I WITH GRAVE
|
177
|
+
- "�" # LATIN SMALL LETTER I WITH ACUTE
|
178
|
+
- "�" # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
179
|
+
- "�" # LATIN SMALL LETTER I WITH DIAERESIS
|
180
|
+
- "�" # LATIN SMALL LETTER ETH
|
181
|
+
- "�" # LATIN SMALL LETTER N WITH TILDE
|
182
|
+
- "�" # LATIN SMALL LETTER O WITH GRAVE
|
183
|
+
- "�" # LATIN SMALL LETTER O WITH ACUTE
|
184
|
+
- "�" # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
185
|
+
- "�" # LATIN SMALL LETTER O WITH TILDE
|
186
|
+
- "�" # LATIN SMALL LETTER O WITH DIAERESIS
|
187
|
+
- "�" # DIVISION SIGN (present in Symbol font)
|
188
|
+
- "�" # LATIN SMALL LETTER O WITH STROKE
|
189
|
+
- "�" # LATIN SMALL LETTER U WITH GRAVE
|
190
|
+
- "�" # LATIN SMALL LETTER U WITH ACUTE
|
191
|
+
- "�" # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
192
|
+
- "�" # LATIN SMALL LETTER U WITH DIAERESIS
|
193
|
+
- "�" # LATIN SMALL LETTER Y WITH ACUTE
|
194
|
+
- "�" # LATIN SMALL LETTER THORN
|
195
|
+
- "�" # LATIN SMALL LETTER Y WITH DIAERESIS
|
196
|
+
|
197
|
+
# ====[ latin_extended_a ]====
|
198
|
+
- "�" # LATIN CAPITAL LIGATURE OE
|
199
|
+
- "�" # LATIN SMALL LIGATURE OE
|
200
|
+
- "�" # LATIN CAPITAL LETTER S WITH CARON
|
201
|
+
- "�" # LATIN SMALL LETTER S WITH CARON
|
202
|
+
- "�" # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
203
|
+
- "�" # LATIN CAPITAL LETTER Z WITH CARON
|
204
|
+
- "�" # LATIN SMALL LETTER Z WITH CARON
|
@@ -0,0 +1,195 @@
|
|
1
|
+
---
|
2
|
+
# ====[ basic_latin ]====
|
3
|
+
#- " " # SPACE
|
4
|
+
#- "!" # EXCLAMATION MARK
|
5
|
+
#- '"' # QUOTATION MARK
|
6
|
+
#- "#" # NUMBER SIGN
|
7
|
+
#- "$" # DOLLAR SIGN
|
8
|
+
#- "%" # PERCENT SIGN
|
9
|
+
#- "&" # AMPERSAND
|
10
|
+
#- "'" # APOSTROPHE
|
11
|
+
#- "(" # LEFT PARENTHESIS
|
12
|
+
#- ")" # RIGHT PARENTHESIS
|
13
|
+
#- "*" # ASTERISK
|
14
|
+
#- "+" # PLUS SIGN
|
15
|
+
#- "," # COMMA
|
16
|
+
#- "-" # HYPHEN-MINUS
|
17
|
+
#- "." # FULL STOP
|
18
|
+
#- "/" # SOLIDUS
|
19
|
+
#- "0" # DIGIT ZERO
|
20
|
+
#- "1" # DIGIT ONE
|
21
|
+
#- "2" # DIGIT TWO
|
22
|
+
#- "3" # DIGIT THREE
|
23
|
+
#- "4" # DIGIT FOUR
|
24
|
+
#- "5" # DIGIT FIVE
|
25
|
+
#- "6" # DIGIT SIX
|
26
|
+
#- "7" # DIGIT SEVEN
|
27
|
+
#- "8" # DIGIT EIGHT
|
28
|
+
#- "9" # DIGIT NINE
|
29
|
+
#- ":" # COLON
|
30
|
+
#- ";" # SEMICOLON
|
31
|
+
#- "<" # LESS-THAN SIGN
|
32
|
+
#- "=" # EQUALS SIGN
|
33
|
+
#- ">" # GREATER-THAN SIGN
|
34
|
+
#- "?" # QUESTION MARK
|
35
|
+
#- "@" # COMMERCIAL AT
|
36
|
+
#- "A" # LATIN CAPITAL LETTER A
|
37
|
+
#- "B" # LATIN CAPITAL LETTER B
|
38
|
+
#- "C" # LATIN CAPITAL LETTER C
|
39
|
+
#- "D" # LATIN CAPITAL LETTER D
|
40
|
+
#- "E" # LATIN CAPITAL LETTER E
|
41
|
+
#- "F" # LATIN CAPITAL LETTER F
|
42
|
+
#- "G" # LATIN CAPITAL LETTER G
|
43
|
+
#- "H" # LATIN CAPITAL LETTER H
|
44
|
+
#- "I" # LATIN CAPITAL LETTER I
|
45
|
+
#- "J" # LATIN CAPITAL LETTER J
|
46
|
+
#- "K" # LATIN CAPITAL LETTER K
|
47
|
+
#- "L" # LATIN CAPITAL LETTER L
|
48
|
+
#- "M" # LATIN CAPITAL LETTER M
|
49
|
+
#- "N" # LATIN CAPITAL LETTER N
|
50
|
+
#- "O" # LATIN CAPITAL LETTER O
|
51
|
+
#- "P" # LATIN CAPITAL LETTER P
|
52
|
+
#- "Q" # LATIN CAPITAL LETTER Q
|
53
|
+
#- "R" # LATIN CAPITAL LETTER R
|
54
|
+
#- "S" # LATIN CAPITAL LETTER S
|
55
|
+
#- "T" # LATIN CAPITAL LETTER T
|
56
|
+
#- "U" # LATIN CAPITAL LETTER U
|
57
|
+
#- "V" # LATIN CAPITAL LETTER V
|
58
|
+
#- "W" # LATIN CAPITAL LETTER W
|
59
|
+
#- "X" # LATIN CAPITAL LETTER X
|
60
|
+
#- "Y" # LATIN CAPITAL LETTER Y
|
61
|
+
#- "Z" # LATIN CAPITAL LETTER Z
|
62
|
+
#- "[" # LEFT SQUARE BRACKET
|
63
|
+
#- "\\" # REVERSE SOLIDUS
|
64
|
+
#- "]" # RIGHT SQUARE BRACKET
|
65
|
+
#- "^" # CIRCUMFLEX ACCENT
|
66
|
+
#- "_" # LOW LINE
|
67
|
+
#- "`" # GRAVE ACCENT
|
68
|
+
#- "a" # LATIN SMALL LETTER A
|
69
|
+
#- "b" # LATIN SMALL LETTER B
|
70
|
+
#- "c" # LATIN SMALL LETTER C
|
71
|
+
#- "d" # LATIN SMALL LETTER D
|
72
|
+
#- "e" # LATIN SMALL LETTER E
|
73
|
+
#- "f" # LATIN SMALL LETTER F
|
74
|
+
#- "g" # LATIN SMALL LETTER G
|
75
|
+
#- "h" # LATIN SMALL LETTER H
|
76
|
+
#- "i" # LATIN SMALL LETTER I
|
77
|
+
#- "j" # LATIN SMALL LETTER J
|
78
|
+
#- "k" # LATIN SMALL LETTER K
|
79
|
+
#- "l" # LATIN SMALL LETTER L
|
80
|
+
#- "m" # LATIN SMALL LETTER M
|
81
|
+
#- "n" # LATIN SMALL LETTER N
|
82
|
+
#- "o" # LATIN SMALL LETTER O
|
83
|
+
#- "p" # LATIN SMALL LETTER P
|
84
|
+
#- "q" # LATIN SMALL LETTER Q
|
85
|
+
#- "r" # LATIN SMALL LETTER R
|
86
|
+
#- "s" # LATIN SMALL LETTER S
|
87
|
+
#- "t" # LATIN SMALL LETTER T
|
88
|
+
#- "u" # LATIN SMALL LETTER U
|
89
|
+
#- "v" # LATIN SMALL LETTER V
|
90
|
+
#- "w" # LATIN SMALL LETTER W
|
91
|
+
#- "x" # LATIN SMALL LETTER X
|
92
|
+
#- "y" # LATIN SMALL LETTER Y
|
93
|
+
#- "z" # LATIN SMALL LETTER Z
|
94
|
+
#- "{" # LEFT CURLY BRACKET
|
95
|
+
#- "|" # VERTICAL LINE
|
96
|
+
#- "}" # RIGHT CURLY BRACKET
|
97
|
+
#- "~" # TILDE
|
98
|
+
#- "" # DEL
|
99
|
+
|
100
|
+
# ====[ latin_1_supplement ]====
|
101
|
+
- "�" # INVERTED EXCLAMATION MARK
|
102
|
+
- "�" # CENT SIGN
|
103
|
+
- "�" # POUND SIGN
|
104
|
+
- "�" # CURRENCY SIGN
|
105
|
+
- "�" # YEN SIGN
|
106
|
+
- "�" # BROKEN BAR
|
107
|
+
- "�" # SECTION SIGN
|
108
|
+
- "�" # DIAERESIS
|
109
|
+
- "�" # COPYRIGHT SIGN (present in Symbol font)
|
110
|
+
- "�" # FEMININE ORDINAL INDICATOR
|
111
|
+
- "�" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
112
|
+
- "�" # NOT SIGN (present in Symbol font)
|
113
|
+
- "�" # SOFT HYPHEN
|
114
|
+
- "�" # REGISTERED SIGN (present in Symbol font)
|
115
|
+
- "�" # MACRON
|
116
|
+
- "�" # DEGREE SIGN
|
117
|
+
- "�" # PLUS-MINUS SIGN (present in Symbol font)
|
118
|
+
- "�" # SUPERSCRIPT TWO
|
119
|
+
- "�" # SUPERSCRIPT THREE
|
120
|
+
- "�" # ACUTE ACCENT
|
121
|
+
- "�" # MICRO SIGN
|
122
|
+
- "�" # PILCROW SIGN
|
123
|
+
- "�" # MIDDLE DOT
|
124
|
+
- "�" # CEDILLA
|
125
|
+
- "�" # SUPERSCRIPT ONE
|
126
|
+
- "�" # MASCULINE ORDINAL INDICATOR
|
127
|
+
- "�" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
128
|
+
- "�" # VULGAR FRACTION ONE QUARTER
|
129
|
+
- "�" # VULGAR FRACTION ONE HALF
|
130
|
+
- "�" # VULGAR FRACTION THREE QUARTERS
|
131
|
+
- "�" # INVERTED QUESTION MARK
|
132
|
+
- "�" # LATIN CAPITAL LETTER A WITH GRAVE
|
133
|
+
- "�" # LATIN CAPITAL LETTER A WITH ACUTE
|
134
|
+
- "�" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
135
|
+
- "�" # LATIN CAPITAL LETTER A WITH TILDE
|
136
|
+
- "�" # LATIN CAPITAL LETTER A WITH DIAERESIS
|
137
|
+
- "�" # LATIN CAPITAL LETTER A WITH RING ABOVE
|
138
|
+
- "�" # LATIN CAPITAL LETTER AE
|
139
|
+
- "�" # LATIN CAPITAL LETTER C WITH CEDILLA
|
140
|
+
- "�" # LATIN CAPITAL LETTER E WITH GRAVE
|
141
|
+
- "�" # LATIN CAPITAL LETTER E WITH ACUTE
|
142
|
+
- "�" # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
143
|
+
- "�" # LATIN CAPITAL LETTER E WITH DIAERESIS
|
144
|
+
- "�" # LATIN CAPITAL LETTER I WITH GRAVE
|
145
|
+
- "�" # LATIN CAPITAL LETTER I WITH ACUTE
|
146
|
+
- "�" # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
147
|
+
- "�" # LATIN CAPITAL LETTER I WITH DIAERESIS
|
148
|
+
- "�" # LATIN CAPITAL LETTER ETH
|
149
|
+
- "�" # LATIN CAPITAL LETTER N WITH TILDE
|
150
|
+
- "�" # LATIN CAPITAL LETTER O WITH GRAVE
|
151
|
+
- "�" # LATIN CAPITAL LETTER O WITH ACUTE
|
152
|
+
- "�" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
153
|
+
- "�" # LATIN CAPITAL LETTER O WITH TILDE
|
154
|
+
- "�" # LATIN CAPITAL LETTER O WITH DIAERESIS
|
155
|
+
- "�" # MULTIPLICATION SIGN (present in Symbol font)
|
156
|
+
- "�" # LATIN CAPITAL LETTER O WITH STROKE
|
157
|
+
- "�" # LATIN CAPITAL LETTER U WITH GRAVE
|
158
|
+
- "�" # LATIN CAPITAL LETTER U WITH ACUTE
|
159
|
+
- "�" # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
160
|
+
- "�" # LATIN CAPITAL LETTER U WITH DIAERESIS
|
161
|
+
- "�" # LATIN CAPITAL LETTER Y WITH ACUTE
|
162
|
+
- "�" # LATIN CAPITAL LETTER THORN
|
163
|
+
- "�" # LATIN SMALL LETTER SHARP S
|
164
|
+
- "�" # LATIN SMALL LETTER A WITH GRAVE
|
165
|
+
- "�" # LATIN SMALL LETTER A WITH ACUTE
|
166
|
+
- "�" # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
167
|
+
- "�" # LATIN SMALL LETTER A WITH TILDE
|
168
|
+
- "�" # LATIN SMALL LETTER A WITH DIAERESIS
|
169
|
+
- "�" # LATIN SMALL LETTER A WITH RING ABOVE
|
170
|
+
- "�" # LATIN SMALL LETTER AE
|
171
|
+
- "�" # LATIN SMALL LETTER C WITH CEDILLA
|
172
|
+
- "�" # LATIN SMALL LETTER E WITH GRAVE
|
173
|
+
- "�" # LATIN SMALL LETTER E WITH ACUTE
|
174
|
+
- "�" # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
175
|
+
- "�" # LATIN SMALL LETTER E WITH DIAERESIS
|
176
|
+
- "�" # LATIN SMALL LETTER I WITH GRAVE
|
177
|
+
- "�" # LATIN SMALL LETTER I WITH ACUTE
|
178
|
+
- "�" # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
179
|
+
- "�" # LATIN SMALL LETTER I WITH DIAERESIS
|
180
|
+
- "�" # LATIN SMALL LETTER ETH
|
181
|
+
- "�" # LATIN SMALL LETTER N WITH TILDE
|
182
|
+
- "�" # LATIN SMALL LETTER O WITH GRAVE
|
183
|
+
- "�" # LATIN SMALL LETTER O WITH ACUTE
|
184
|
+
- "�" # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
185
|
+
- "�" # LATIN SMALL LETTER O WITH TILDE
|
186
|
+
- "�" # LATIN SMALL LETTER O WITH DIAERESIS
|
187
|
+
- "�" # DIVISION SIGN (present in Symbol font)
|
188
|
+
- "�" # LATIN SMALL LETTER O WITH STROKE
|
189
|
+
- "�" # LATIN SMALL LETTER U WITH GRAVE
|
190
|
+
- "�" # LATIN SMALL LETTER U WITH ACUTE
|
191
|
+
- "�" # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
192
|
+
- "�" # LATIN SMALL LETTER U WITH DIAERESIS
|
193
|
+
- "�" # LATIN SMALL LETTER Y WITH ACUTE
|
194
|
+
- "�" # LATIN SMALL LETTER THORN
|
195
|
+
- "�" # LATIN SMALL LETTER Y WITH DIAERESIS
|