Rev 4175 | Rev 4198 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4175 | Rev 4179 | ||
---|---|---|---|
Line 40... | Line 40... | ||
40 | #include <cpu.h> |
40 | #include <cpu.h> |
41 | #include <arch/asm.h> |
41 | #include <arch/asm.h> |
42 | #include <arch.h> |
42 | #include <arch.h> |
43 | #include <console/kconsole.h> |
43 | #include <console/kconsole.h> |
44 | 44 | ||
- | 45 | char invalch = '?'; |
|
- | 46 | ||
45 | /** Decode a single UTF-8 character from a NULL-terminated string. |
47 | /** Decode a single UTF-8 character from a NULL-terminated string. |
46 | * |
48 | * |
47 | * Decode a single UTF-8 character from a plain char NULL-terminated |
49 | * Decode a single UTF-8 character from a plain char NULL-terminated |
48 | * string. Decoding starts at @index and this index is incremented |
50 | * string. Decoding starts at @index and this index is incremented |
49 | * if the current UTF-8 string is encoded in more than a single byte. |
51 | * if the current UTF-8 string is encoded in more than a single byte. |
50 | * |
52 | * |
51 | * @param str Plain character NULL-terminated string. |
53 | * @param str Plain character NULL-terminated string. |
52 | * @param index Index (counted in plain characters) where to start |
54 | * @param index Index (counted in plain characters) where to start |
53 | * the decoding. |
55 | * the decoding. |
- | 56 | * @param limit Maximal allowed value of index. |
|
54 | * |
57 | * |
55 | * @return Decoded character in UTF-32 or '?' if the encoding is wrong. |
58 | * @return Decoded character in UTF-32 or '?' if the encoding is wrong. |
56 | * |
59 | * |
57 | */ |
60 | */ |
58 | wchar_t utf8_decode(const char *str, index_t *index) |
61 | wchar_t utf8_decode(const char *str, index_t *index, index_t limit) |
59 | { |
62 | { |
60 | uint8_t c1; /* First plain character from str */ |
63 | uint8_t c1; /* First plain character from str */ |
61 | uint8_t c2; /* Second plain character from str */ |
64 | uint8_t c2; /* Second plain character from str */ |
62 | uint8_t c3; /* Third plain character from str */ |
65 | uint8_t c3; /* Third plain character from str */ |
63 | uint8_t c4; /* Fourth plain character from str */ |
66 | uint8_t c4; /* Fourth plain character from str */ |
64 | 67 | ||
- | 68 | if (*index > limit) |
|
- | 69 | return invalch; |
|
- | 70 | ||
65 | c1 = (uint8_t) str[*index]; |
71 | c1 = (uint8_t) str[*index]; |
66 | 72 | ||
67 | if ((c1 & 0x80) == 0) { |
73 | if ((c1 & 0x80) == 0) { |
68 | /* Plain ASCII (code points 0 .. 127) */ |
74 | /* Plain ASCII (code points 0 .. 127) */ |
69 | return (wchar_t) c1; |
75 | return (wchar_t) c1; |
- | 76 | } |
|
- | 77 | ||
70 | } else if ((c1 & 0xe0) == 0xc0) { |
78 | if ((c1 & 0xe0) == 0xc0) { |
71 | /* Code points 128 .. 2047 */ |
79 | /* Code points 128 .. 2047 */ |
- | 80 | if (*index + 1 > limit) |
|
- | 81 | return invalch; |
|
- | 82 | ||
72 | c2 = (uint8_t) str[*index + 1]; |
83 | c2 = (uint8_t) str[*index + 1]; |
73 | if ((c2 & 0xc0) == 0x80) { |
84 | if ((c2 & 0xc0) == 0x80) { |
74 | (*index)++; |
85 | (*index)++; |
75 | return ((wchar_t) ((c1 & 0x1f) << 6) | (c2 & 0x3f)); |
86 | return ((wchar_t) ((c1 & 0x1f) << 6) | (c2 & 0x3f)); |
76 | } else |
87 | } else |
77 | return ((wchar_t) '?'); |
88 | return invalch; |
- | 89 | } |
|
- | 90 | ||
78 | } else if ((c1 & 0xf0) == 0xe0) { |
91 | if ((c1 & 0xf0) == 0xe0) { |
79 | /* Code points 2048 .. 65535 */ |
92 | /* Code points 2048 .. 65535 */ |
- | 93 | if (*index + 2 > limit) |
|
- | 94 | return invalch; |
|
- | 95 | ||
80 | c2 = (uint8_t) str[*index + 1]; |
96 | c2 = (uint8_t) str[*index + 1]; |
81 | if ((c2 & 0xc0) == 0x80) { |
97 | if ((c2 & 0xc0) == 0x80) { |
82 | (*index)++; |
98 | (*index)++; |
83 | c3 = (uint8_t) str[*index + 1]; |
99 | c3 = (uint8_t) str[*index + 1]; |
84 | if ((c3 & 0xc0) == 0x80) { |
100 | if ((c3 & 0xc0) == 0x80) { |
85 | (*index)++; |
101 | (*index)++; |
86 | return ((wchar_t) ((c1 & 0x0f) << 12) | ((c2 & 0x3f) << 6) | (c3 & 0x3f)); |
102 | return ((wchar_t) ((c1 & 0x0f) << 12) | ((c2 & 0x3f) << 6) | (c3 & 0x3f)); |
87 | } else |
103 | } else |
88 | return ((wchar_t) '?'); |
104 | return invalch; |
89 | } else |
105 | } else |
90 | return ((wchar_t) '?'); |
106 | return invalch; |
- | 107 | } |
|
- | 108 | ||
91 | } else if ((c1 & 0xf8) == 0xf0) { |
109 | if ((c1 & 0xf8) == 0xf0) { |
92 | /* Code points 65536 .. 1114111 */ |
110 | /* Code points 65536 .. 1114111 */ |
- | 111 | if (*index + 3 > limit) |
|
- | 112 | return invalch; |
|
- | 113 | ||
93 | c2 = (uint8_t) str[*index + 1]; |
114 | c2 = (uint8_t) str[*index + 1]; |
94 | if ((c2 & 0xc0) == 0x80) { |
115 | if ((c2 & 0xc0) == 0x80) { |
95 | (*index)++; |
116 | (*index)++; |
96 | c3 = (uint8_t) str[*index + 1]; |
117 | c3 = (uint8_t) str[*index + 1]; |
97 | if ((c3 & 0xc0) == 0x80) { |
118 | if ((c3 & 0xc0) == 0x80) { |
Line 99... | Line 120... | ||
99 | c4 = (uint8_t) str[*index + 1]; |
120 | c4 = (uint8_t) str[*index + 1]; |
100 | if ((c4 & 0xc0) == 0x80) { |
121 | if ((c4 & 0xc0) == 0x80) { |
101 | (*index)++; |
122 | (*index)++; |
102 | return ((wchar_t) ((c1 & 0x07) << 18) | ((c2 & 0x3f) << 12) | ((c3 & 0x3f) << 6) | (c4 & 0x3f)); |
123 | return ((wchar_t) ((c1 & 0x07) << 18) | ((c2 & 0x3f) << 12) | ((c3 & 0x3f) << 6) | (c4 & 0x3f)); |
103 | } else |
124 | } else |
104 | return ((wchar_t) '?'); |
125 | return invalch; |
105 | } else |
126 | } else |
106 | return ((wchar_t) '?'); |
127 | return invalch; |
107 | } else |
128 | } else |
108 | return ((wchar_t) '?'); |
129 | return invalch; |
- | 130 | } |
|
- | 131 | ||
- | 132 | return invalch; |
|
- | 133 | } |
|
- | 134 | ||
- | 135 | /** Encode a single UTF-32 character as UTF-8 |
|
- | 136 | * |
|
- | 137 | * Encode a single UTF-32 character as UTF-8 and store it into |
|
- | 138 | * the given buffer at @index. Encoding starts at @index and |
|
- | 139 | * this index is incremented if the UTF-8 character takes |
|
- | 140 | * more than a single byte. |
|
- | 141 | * |
|
- | 142 | * @param ch Input UTF-32 character. |
|
- | 143 | * @param str Output buffer. |
|
- | 144 | * @param index Index (counted in plain characters) where to start |
|
- | 145 | * the encoding |
|
- | 146 | * @param limit Maximal allowed value of index. |
|
- | 147 | * |
|
- | 148 | * @return True if the character was encoded or false if there is not |
|
- | 149 | * enought space in the output buffer or the character is invalid |
|
- | 150 | * Unicode code point. |
|
- | 151 | * |
|
- | 152 | */ |
|
- | 153 | bool utf8_encode(const wchar_t ch, char *str, index_t *index, index_t limit) |
|
- | 154 | { |
|
- | 155 | if (*index > limit) |
|
- | 156 | return false; |
|
- | 157 | ||
- | 158 | if ((ch >= 0) && (ch <= 127)) { |
|
- | 159 | /* Plain ASCII (code points 0 .. 127) */ |
|
- | 160 | str[*index] = ch & 0x7f; |
|
- | 161 | return true; |
|
- | 162 | } |
|
- | 163 | ||
- | 164 | if ((ch >= 128) && (ch <= 2047)) { |
|
- | 165 | /* Code points 128 .. 2047 */ |
|
- | 166 | if (*index + 1 > limit) |
|
- | 167 | return false; |
|
- | 168 | ||
- | 169 | str[*index] = 0xc0 | ((ch >> 6) & 0x1f); |
|
- | 170 | (*index)++; |
|
- | 171 | str[*index] = 0x80 | (ch & 0x3f); |
|
- | 172 | return true; |
|
- | 173 | } |
|
- | 174 | ||
- | 175 | if ((ch >= 2048) && (ch <= 65535)) { |
|
- | 176 | /* Code points 2048 .. 65535 */ |
|
- | 177 | if (*index + 2 > limit) |
|
- | 178 | return false; |
|
- | 179 | ||
- | 180 | str[*index] = 0xe0 | ((ch >> 12) & 0x0f); |
|
- | 181 | (*index)++; |
|
- | 182 | str[*index] = 0x80 | ((ch >> 6) & 0x3f); |
|
- | 183 | (*index)++; |
|
- | 184 | str[*index] = 0x80 | (ch & 0x3f); |
|
- | 185 | return true; |
|
- | 186 | } |
|
- | 187 | ||
- | 188 | if ((ch >= 65536) && (ch <= 1114111)) { |
|
- | 189 | /* Code points 65536 .. 1114111 */ |
|
- | 190 | if (*index + 3 > limit) |
|
- | 191 | return false; |
|
- | 192 | ||
- | 193 | str[*index] = 0xf0 | ((ch >> 18) & 0x07); |
|
- | 194 | (*index)++; |
|
- | 195 | str[*index] = 0x80 | ((ch >> 12) & 0x3f); |
|
- | 196 | (*index)++; |
|
- | 197 | str[*index] = 0x80 | ((ch >> 6) & 0x3f); |
|
- | 198 | (*index)++; |
|
- | 199 | str[*index] = 0x80 | (ch & 0x3f); |
|
- | 200 | return true; |
|
- | 201 | } |
|
- | 202 | ||
- | 203 | return false; |
|
- | 204 | } |
|
- | 205 | ||
- | 206 | /** Get bytes used by UTF-8 characters. |
|
- | 207 | * |
|
- | 208 | * Get the number of bytes (count of plain characters) which |
|
- | 209 | * are used by a given count of UTF-8 characters in a string. |
|
- | 210 | * As UTF-8 encoding is multibyte, there is no constant |
|
- | 211 | * correspondence between number of characters and used bytes. |
|
- | 212 | * |
|
- | 213 | * @param str UTF-8 string to consider. |
|
- | 214 | * @param count Number of UTF-8 characters to count. |
|
- | 215 | * |
|
- | 216 | * @return Number of bytes used by the characters. |
|
- | 217 | * |
|
- | 218 | */ |
|
- | 219 | size_t utf8_count_bytes(const char *str, count_t count) |
|
- | 220 | { |
|
- | 221 | size_t size = 0; |
|
- | 222 | index_t index = 0; |
|
- | 223 | ||
- | 224 | while ((utf8_decode(str, &index, UTF8_NO_LIMIT) != 0) && (size < count)) { |
|
- | 225 | size++; |
|
- | 226 | index++; |
|
109 | } |
227 | } |
110 | 228 | ||
- | 229 | return index; |
|
- | 230 | } |
|
- | 231 | ||
- | 232 | /** Check whether character is plain ASCII. |
|
- | 233 | * |
|
- | 234 | * @return True if character is plain ASCII. |
|
- | 235 | * |
|
- | 236 | */ |
|
- | 237 | bool ascii_check(const wchar_t ch) |
|
- | 238 | { |
|
- | 239 | if ((ch >= 0) && (ch <= 127)) |
|
- | 240 | return true; |
|
- | 241 | ||
111 | return ((wchar_t) '?'); |
242 | return false; |
- | 243 | } |
|
- | 244 | ||
- | 245 | /** Check whether character is Unicode. |
|
- | 246 | * |
|
- | 247 | * @return True if character is valid Unicode code point. |
|
- | 248 | * |
|
- | 249 | */ |
|
- | 250 | bool unicode_check(const wchar_t ch) |
|
- | 251 | { |
|
- | 252 | if ((ch >= 0) && (ch <= 1114111)) |
|
- | 253 | return true; |
|
- | 254 | ||
- | 255 | return false; |
|
112 | } |
256 | } |
113 | 257 | ||
114 | /** Return number of characters in a string. |
258 | /** Return number of plain characters in a string. |
115 | * |
259 | * |
116 | * @param str NULL terminated string. |
260 | * @param str NULL-terminated string. |
117 | * |
261 | * |
118 | * @return Number of characters in str. |
262 | * @return Number of characters in str. |
119 | * |
263 | * |
120 | */ |
264 | */ |
121 | size_t strlen(const char *str) |
265 | size_t strlen(const char *str) |
122 | { |
266 | { |
123 | int i; |
267 | size_t size; |
- | 268 | for (size = 0; str[size]; size++); |
|
- | 269 | ||
- | 270 | return size; |
|
- | 271 | } |
|
- | 272 | ||
- | 273 | /** Return number of UTF-8 characters in a string. |
|
- | 274 | * |
|
- | 275 | * @param str NULL-terminated UTF-8 string. |
|
- | 276 | * |
|
- | 277 | * @return Number of UTF-8 characters in str. |
|
- | 278 | * |
|
- | 279 | */ |
|
- | 280 | size_t strlen_utf8(const char *str) |
|
- | 281 | { |
|
- | 282 | size_t size = 0; |
|
- | 283 | index_t index = 0; |
|
124 | 284 | ||
- | 285 | while (utf8_decode(str, &index, UTF8_NO_LIMIT) != 0) { |
|
- | 286 | size++; |
|
- | 287 | index++; |
|
- | 288 | } |
|
- | 289 | ||
- | 290 | return size; |
|
- | 291 | } |
|
- | 292 | ||
- | 293 | /** Return number of UTF-32 characters in a string. |
|
- | 294 | * |
|
- | 295 | * @param str NULL-terminated UTF-32 string. |
|
- | 296 | * |
|
- | 297 | * @return Number of UTF-32 characters in str. |
|
- | 298 | * |
|
- | 299 | */ |
|
- | 300 | size_t strlen_utf32(const wchar_t *str) |
|
- | 301 | { |
|
- | 302 | size_t size; |
|
125 | for (i = 0; str[i]; i++); |
303 | for (size = 0; str[size]; size++); |
126 | 304 | ||
127 | return i; |
305 | return size; |
128 | } |
306 | } |
129 | 307 | ||
130 | /** Compare two NULL terminated strings |
308 | /** Compare two NULL terminated strings |
131 | * |
309 | * |
132 | * Do a char-by-char comparison of two NULL terminated strings. |
310 | * Do a char-by-char comparison of two NULL terminated strings. |