blob: 7305e20737631e259810cfc5addb0b6c3df94611 [file] [log] [blame]
Gerd Hoffmann44270bc2017-09-18 10:47:19 +02001/*
2 * code page 437 to unicode map
3 */
4
5#include "types.h"
6#include "biosvar.h"
7#include "cp437.h"
8
9static VAR16 u16 cp437_to_unicode_map[256] = {
10
11 /* https://en.wikipedia.org/wiki/Code_page_437 */
12 [ 0x00 ] = 0x0000,
13 [ 0x01 ] = 0x263A,
14 [ 0x02 ] = 0x263B,
15 [ 0x03 ] = 0x2665,
16 [ 0x04 ] = 0x2666,
17 [ 0x05 ] = 0x2663,
18 [ 0x06 ] = 0x2660,
19 [ 0x07 ] = 0x2022,
20 [ 0x08 ] = 0x25D8,
21 [ 0x09 ] = 0x25CB,
22 [ 0x0a ] = 0x25D9,
23 [ 0x0b ] = 0x2642,
24 [ 0x0c ] = 0x2640,
25 [ 0x0d ] = 0x266A,
26 [ 0x0e ] = 0x266B,
27 [ 0x0f ] = 0x263C,
28 [ 0x10 ] = 0x25BA,
29 [ 0x11 ] = 0x25C4,
30 [ 0x12 ] = 0x2195,
31 [ 0x13 ] = 0x203C,
32 [ 0x14 ] = 0x00B6,
33 [ 0x15 ] = 0x00A7,
34 [ 0x16 ] = 0x25AC,
35 [ 0x17 ] = 0x21A8,
36 [ 0x18 ] = 0x2191,
37 [ 0x19 ] = 0x2193,
38 [ 0x1a ] = 0x2192,
39 [ 0x1b ] = 0x2190,
40 [ 0x1c ] = 0x221F,
41 [ 0x1d ] = 0x2194,
42 [ 0x1e ] = 0x25B2,
43 [ 0x1f ] = 0x25BC,
44 [ 0x7f ] = 0x2302,
45
46 /* http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT */
47 [ 0x20 ] = 0x0020, // SPACE
48 [ 0x21 ] = 0x0021, // EXCLAMATION MARK
49 [ 0x22 ] = 0x0022, // QUOTATION MARK
50 [ 0x23 ] = 0x0023, // NUMBER SIGN
51 [ 0x24 ] = 0x0024, // DOLLAR SIGN
52 [ 0x25 ] = 0x0025, // PERCENT SIGN
53 [ 0x26 ] = 0x0026, // AMPERSAND
54 [ 0x27 ] = 0x0027, // APOSTROPHE
55 [ 0x28 ] = 0x0028, // LEFT PARENTHESIS
56 [ 0x29 ] = 0x0029, // RIGHT PARENTHESIS
57 [ 0x2a ] = 0x002a, // ASTERISK
58 [ 0x2b ] = 0x002b, // PLUS SIGN
59 [ 0x2c ] = 0x002c, // COMMA
60 [ 0x2d ] = 0x002d, // HYPHEN-MINUS
61 [ 0x2e ] = 0x002e, // FULL STOP
62 [ 0x2f ] = 0x002f, // SOLIDUS
63 [ 0x30 ] = 0x0030, // DIGIT ZERO
64 [ 0x31 ] = 0x0031, // DIGIT ONE
65 [ 0x32 ] = 0x0032, // DIGIT TWO
66 [ 0x33 ] = 0x0033, // DIGIT THREE
67 [ 0x34 ] = 0x0034, // DIGIT FOUR
68 [ 0x35 ] = 0x0035, // DIGIT FIVE
69 [ 0x36 ] = 0x0036, // DIGIT SIX
70 [ 0x37 ] = 0x0037, // DIGIT SEVEN
71 [ 0x38 ] = 0x0038, // DIGIT EIGHT
72 [ 0x39 ] = 0x0039, // DIGIT NINE
73 [ 0x3a ] = 0x003a, // COLON
74 [ 0x3b ] = 0x003b, // SEMICOLON
75 [ 0x3c ] = 0x003c, // LESS-THAN SIGN
76 [ 0x3d ] = 0x003d, // EQUALS SIGN
77 [ 0x3e ] = 0x003e, // GREATER-THAN SIGN
78 [ 0x3f ] = 0x003f, // QUESTION MARK
79 [ 0x40 ] = 0x0040, // COMMERCIAL AT
80 [ 0x41 ] = 0x0041, // LATIN CAPITAL LETTER A
81 [ 0x42 ] = 0x0042, // LATIN CAPITAL LETTER B
82 [ 0x43 ] = 0x0043, // LATIN CAPITAL LETTER C
83 [ 0x44 ] = 0x0044, // LATIN CAPITAL LETTER D
84 [ 0x45 ] = 0x0045, // LATIN CAPITAL LETTER E
85 [ 0x46 ] = 0x0046, // LATIN CAPITAL LETTER F
86 [ 0x47 ] = 0x0047, // LATIN CAPITAL LETTER G
87 [ 0x48 ] = 0x0048, // LATIN CAPITAL LETTER H
88 [ 0x49 ] = 0x0049, // LATIN CAPITAL LETTER I
89 [ 0x4a ] = 0x004a, // LATIN CAPITAL LETTER J
90 [ 0x4b ] = 0x004b, // LATIN CAPITAL LETTER K
91 [ 0x4c ] = 0x004c, // LATIN CAPITAL LETTER L
92 [ 0x4d ] = 0x004d, // LATIN CAPITAL LETTER M
93 [ 0x4e ] = 0x004e, // LATIN CAPITAL LETTER N
94 [ 0x4f ] = 0x004f, // LATIN CAPITAL LETTER O
95 [ 0x50 ] = 0x0050, // LATIN CAPITAL LETTER P
96 [ 0x51 ] = 0x0051, // LATIN CAPITAL LETTER Q
97 [ 0x52 ] = 0x0052, // LATIN CAPITAL LETTER R
98 [ 0x53 ] = 0x0053, // LATIN CAPITAL LETTER S
99 [ 0x54 ] = 0x0054, // LATIN CAPITAL LETTER T
100 [ 0x55 ] = 0x0055, // LATIN CAPITAL LETTER U
101 [ 0x56 ] = 0x0056, // LATIN CAPITAL LETTER V
102 [ 0x57 ] = 0x0057, // LATIN CAPITAL LETTER W
103 [ 0x58 ] = 0x0058, // LATIN CAPITAL LETTER X
104 [ 0x59 ] = 0x0059, // LATIN CAPITAL LETTER Y
105 [ 0x5a ] = 0x005a, // LATIN CAPITAL LETTER Z
106 [ 0x5b ] = 0x005b, // LEFT SQUARE BRACKET
107 [ 0x5c ] = 0x005c, // REVERSE SOLIDUS
108 [ 0x5d ] = 0x005d, // RIGHT SQUARE BRACKET
109 [ 0x5e ] = 0x005e, // CIRCUMFLEX ACCENT
110 [ 0x5f ] = 0x005f, // LOW LINE
111 [ 0x60 ] = 0x0060, // GRAVE ACCENT
112 [ 0x61 ] = 0x0061, // LATIN SMALL LETTER A
113 [ 0x62 ] = 0x0062, // LATIN SMALL LETTER B
114 [ 0x63 ] = 0x0063, // LATIN SMALL LETTER C
115 [ 0x64 ] = 0x0064, // LATIN SMALL LETTER D
116 [ 0x65 ] = 0x0065, // LATIN SMALL LETTER E
117 [ 0x66 ] = 0x0066, // LATIN SMALL LETTER F
118 [ 0x67 ] = 0x0067, // LATIN SMALL LETTER G
119 [ 0x68 ] = 0x0068, // LATIN SMALL LETTER H
120 [ 0x69 ] = 0x0069, // LATIN SMALL LETTER I
121 [ 0x6a ] = 0x006a, // LATIN SMALL LETTER J
122 [ 0x6b ] = 0x006b, // LATIN SMALL LETTER K
123 [ 0x6c ] = 0x006c, // LATIN SMALL LETTER L
124 [ 0x6d ] = 0x006d, // LATIN SMALL LETTER M
125 [ 0x6e ] = 0x006e, // LATIN SMALL LETTER N
126 [ 0x6f ] = 0x006f, // LATIN SMALL LETTER O
127 [ 0x70 ] = 0x0070, // LATIN SMALL LETTER P
128 [ 0x71 ] = 0x0071, // LATIN SMALL LETTER Q
129 [ 0x72 ] = 0x0072, // LATIN SMALL LETTER R
130 [ 0x73 ] = 0x0073, // LATIN SMALL LETTER S
131 [ 0x74 ] = 0x0074, // LATIN SMALL LETTER T
132 [ 0x75 ] = 0x0075, // LATIN SMALL LETTER U
133 [ 0x76 ] = 0x0076, // LATIN SMALL LETTER V
134 [ 0x77 ] = 0x0077, // LATIN SMALL LETTER W
135 [ 0x78 ] = 0x0078, // LATIN SMALL LETTER X
136 [ 0x79 ] = 0x0079, // LATIN SMALL LETTER Y
137 [ 0x7a ] = 0x007a, // LATIN SMALL LETTER Z
138 [ 0x7b ] = 0x007b, // LEFT CURLY BRACKET
139 [ 0x7c ] = 0x007c, // VERTICAL LINE
140 [ 0x7d ] = 0x007d, // RIGHT CURLY BRACKET
141 [ 0x7e ] = 0x007e, // TILDE
142 [ 0x80 ] = 0x00c7, // LATIN CAPITAL LETTER C WITH CEDILLA
143 [ 0x81 ] = 0x00fc, // LATIN SMALL LETTER U WITH DIAERESIS
144 [ 0x82 ] = 0x00e9, // LATIN SMALL LETTER E WITH ACUTE
145 [ 0x83 ] = 0x00e2, // LATIN SMALL LETTER A WITH CIRCUMFLEX
146 [ 0x84 ] = 0x00e4, // LATIN SMALL LETTER A WITH DIAERESIS
147 [ 0x85 ] = 0x00e0, // LATIN SMALL LETTER A WITH GRAVE
148 [ 0x86 ] = 0x00e5, // LATIN SMALL LETTER A WITH RING ABOVE
149 [ 0x87 ] = 0x00e7, // LATIN SMALL LETTER C WITH CEDILLA
150 [ 0x88 ] = 0x00ea, // LATIN SMALL LETTER E WITH CIRCUMFLEX
151 [ 0x89 ] = 0x00eb, // LATIN SMALL LETTER E WITH DIAERESIS
152 [ 0x8a ] = 0x00e8, // LATIN SMALL LETTER E WITH GRAVE
153 [ 0x8b ] = 0x00ef, // LATIN SMALL LETTER I WITH DIAERESIS
154 [ 0x8c ] = 0x00ee, // LATIN SMALL LETTER I WITH CIRCUMFLEX
155 [ 0x8d ] = 0x00ec, // LATIN SMALL LETTER I WITH GRAVE
156 [ 0x8e ] = 0x00c4, // LATIN CAPITAL LETTER A WITH DIAERESIS
157 [ 0x8f ] = 0x00c5, // LATIN CAPITAL LETTER A WITH RING ABOVE
158 [ 0x90 ] = 0x00c9, // LATIN CAPITAL LETTER E WITH ACUTE
159 [ 0x91 ] = 0x00e6, // LATIN SMALL LIGATURE AE
160 [ 0x92 ] = 0x00c6, // LATIN CAPITAL LIGATURE AE
161 [ 0x93 ] = 0x00f4, // LATIN SMALL LETTER O WITH CIRCUMFLEX
162 [ 0x94 ] = 0x00f6, // LATIN SMALL LETTER O WITH DIAERESIS
163 [ 0x95 ] = 0x00f2, // LATIN SMALL LETTER O WITH GRAVE
164 [ 0x96 ] = 0x00fb, // LATIN SMALL LETTER U WITH CIRCUMFLEX
165 [ 0x97 ] = 0x00f9, // LATIN SMALL LETTER U WITH GRAVE
166 [ 0x98 ] = 0x00ff, // LATIN SMALL LETTER Y WITH DIAERESIS
167 [ 0x99 ] = 0x00d6, // LATIN CAPITAL LETTER O WITH DIAERESIS
168 [ 0x9a ] = 0x00dc, // LATIN CAPITAL LETTER U WITH DIAERESIS
169 [ 0x9b ] = 0x00a2, // CENT SIGN
170 [ 0x9c ] = 0x00a3, // POUND SIGN
171 [ 0x9d ] = 0x00a5, // YEN SIGN
172 [ 0x9e ] = 0x20a7, // PESETA SIGN
173 [ 0x9f ] = 0x0192, // LATIN SMALL LETTER F WITH HOOK
174 [ 0xa0 ] = 0x00e1, // LATIN SMALL LETTER A WITH ACUTE
175 [ 0xa1 ] = 0x00ed, // LATIN SMALL LETTER I WITH ACUTE
176 [ 0xa2 ] = 0x00f3, // LATIN SMALL LETTER O WITH ACUTE
177 [ 0xa3 ] = 0x00fa, // LATIN SMALL LETTER U WITH ACUTE
178 [ 0xa4 ] = 0x00f1, // LATIN SMALL LETTER N WITH TILDE
179 [ 0xa5 ] = 0x00d1, // LATIN CAPITAL LETTER N WITH TILDE
180 [ 0xa6 ] = 0x00aa, // FEMININE ORDINAL INDICATOR
181 [ 0xa7 ] = 0x00ba, // MASCULINE ORDINAL INDICATOR
182 [ 0xa8 ] = 0x00bf, // INVERTED QUESTION MARK
183 [ 0xa9 ] = 0x2310, // REVERSED NOT SIGN
184 [ 0xaa ] = 0x00ac, // NOT SIGN
185 [ 0xab ] = 0x00bd, // VULGAR FRACTION ONE HALF
186 [ 0xac ] = 0x00bc, // VULGAR FRACTION ONE QUARTER
187 [ 0xad ] = 0x00a1, // INVERTED EXCLAMATION MARK
188 [ 0xae ] = 0x00ab, // LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
189 [ 0xaf ] = 0x00bb, // RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
190 [ 0xb0 ] = 0x2591, // LIGHT SHADE
191 [ 0xb1 ] = 0x2592, // MEDIUM SHADE
192 [ 0xb2 ] = 0x2593, // DARK SHADE
193 [ 0xb3 ] = 0x2502, // BOX DRAWINGS LIGHT VERTICAL
194 [ 0xb4 ] = 0x2524, // BOX DRAWINGS LIGHT VERTICAL AND LEFT
195 [ 0xb5 ] = 0x2561, // BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
196 [ 0xb6 ] = 0x2562, // BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
197 [ 0xb7 ] = 0x2556, // BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
198 [ 0xb8 ] = 0x2555, // BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
199 [ 0xb9 ] = 0x2563, // BOX DRAWINGS DOUBLE VERTICAL AND LEFT
200 [ 0xba ] = 0x2551, // BOX DRAWINGS DOUBLE VERTICAL
201 [ 0xbb ] = 0x2557, // BOX DRAWINGS DOUBLE DOWN AND LEFT
202 [ 0xbc ] = 0x255d, // BOX DRAWINGS DOUBLE UP AND LEFT
203 [ 0xbd ] = 0x255c, // BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
204 [ 0xbe ] = 0x255b, // BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
205 [ 0xbf ] = 0x2510, // BOX DRAWINGS LIGHT DOWN AND LEFT
206 [ 0xc0 ] = 0x2514, // BOX DRAWINGS LIGHT UP AND RIGHT
207 [ 0xc1 ] = 0x2534, // BOX DRAWINGS LIGHT UP AND HORIZONTAL
208 [ 0xc2 ] = 0x252c, // BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
209 [ 0xc3 ] = 0x251c, // BOX DRAWINGS LIGHT VERTICAL AND RIGHT
210 [ 0xc4 ] = 0x2500, // BOX DRAWINGS LIGHT HORIZONTAL
211 [ 0xc5 ] = 0x253c, // BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
212 [ 0xc6 ] = 0x255e, // BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
213 [ 0xc7 ] = 0x255f, // BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
214 [ 0xc8 ] = 0x255a, // BOX DRAWINGS DOUBLE UP AND RIGHT
215 [ 0xc9 ] = 0x2554, // BOX DRAWINGS DOUBLE DOWN AND RIGHT
216 [ 0xca ] = 0x2569, // BOX DRAWINGS DOUBLE UP AND HORIZONTAL
217 [ 0xcb ] = 0x2566, // BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
218 [ 0xcc ] = 0x2560, // BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
219 [ 0xcd ] = 0x2550, // BOX DRAWINGS DOUBLE HORIZONTAL
220 [ 0xce ] = 0x256c, // BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
221 [ 0xcf ] = 0x2567, // BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
222 [ 0xd0 ] = 0x2568, // BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
223 [ 0xd1 ] = 0x2564, // BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
224 [ 0xd2 ] = 0x2565, // BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
225 [ 0xd3 ] = 0x2559, // BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
226 [ 0xd4 ] = 0x2558, // BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
227 [ 0xd5 ] = 0x2552, // BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
228 [ 0xd6 ] = 0x2553, // BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
229 [ 0xd7 ] = 0x256b, // BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
230 [ 0xd8 ] = 0x256a, // BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
231 [ 0xd9 ] = 0x2518, // BOX DRAWINGS LIGHT UP AND LEFT
232 [ 0xda ] = 0x250c, // BOX DRAWINGS LIGHT DOWN AND RIGHT
233 [ 0xdb ] = 0x2588, // FULL BLOCK
234 [ 0xdc ] = 0x2584, // LOWER HALF BLOCK
235 [ 0xdd ] = 0x258c, // LEFT HALF BLOCK
236 [ 0xde ] = 0x2590, // RIGHT HALF BLOCK
237 [ 0xdf ] = 0x2580, // UPPER HALF BLOCK
238 [ 0xe0 ] = 0x03b1, // GREEK SMALL LETTER ALPHA
239 [ 0xe1 ] = 0x00df, // LATIN SMALL LETTER SHARP S
240 [ 0xe2 ] = 0x0393, // GREEK CAPITAL LETTER GAMMA
241 [ 0xe3 ] = 0x03c0, // GREEK SMALL LETTER PI
242 [ 0xe4 ] = 0x03a3, // GREEK CAPITAL LETTER SIGMA
243 [ 0xe5 ] = 0x03c3, // GREEK SMALL LETTER SIGMA
244 [ 0xe6 ] = 0x00b5, // MICRO SIGN
245 [ 0xe7 ] = 0x03c4, // GREEK SMALL LETTER TAU
246 [ 0xe8 ] = 0x03a6, // GREEK CAPITAL LETTER PHI
247 [ 0xe9 ] = 0x0398, // GREEK CAPITAL LETTER THETA
248 [ 0xea ] = 0x03a9, // GREEK CAPITAL LETTER OMEGA
249 [ 0xeb ] = 0x03b4, // GREEK SMALL LETTER DELTA
250 [ 0xec ] = 0x221e, // INFINITY
251 [ 0xed ] = 0x03c6, // GREEK SMALL LETTER PHI
252 [ 0xee ] = 0x03b5, // GREEK SMALL LETTER EPSILON
253 [ 0xef ] = 0x2229, // INTERSECTION
254 [ 0xf0 ] = 0x2261, // IDENTICAL TO
255 [ 0xf1 ] = 0x00b1, // PLUS-MINUS SIGN
256 [ 0xf2 ] = 0x2265, // GREATER-THAN OR EQUAL TO
257 [ 0xf3 ] = 0x2264, // LESS-THAN OR EQUAL TO
258 [ 0xf4 ] = 0x2320, // TOP HALF INTEGRAL
259 [ 0xf5 ] = 0x2321, // BOTTOM HALF INTEGRAL
260 [ 0xf6 ] = 0x00f7, // DIVISION SIGN
261 [ 0xf7 ] = 0x2248, // ALMOST EQUAL TO
262 [ 0xf8 ] = 0x00b0, // DEGREE SIGN
263 [ 0xf9 ] = 0x2219, // BULLET OPERATOR
264 [ 0xfa ] = 0x00b7, // MIDDLE DOT
265 [ 0xfb ] = 0x221a, // SQUARE ROOT
266 [ 0xfc ] = 0x207f, // SUPERSCRIPT LATIN SMALL LETTER N
267 [ 0xfd ] = 0x00b2, // SUPERSCRIPT TWO
268 [ 0xfe ] = 0x25a0, // BLACK SQUARE
269 [ 0xff ] = 0x00a0, // NO-BREAK SPACE
270};
271
272u16 cp437_to_unicode(u8 cp437)
273{
274 return GET_GLOBAL(cp437_to_unicode_map[cp437]);
275}