Rev 4055 | Rev 4221 | Go to most recent revision | Only display areas with differences | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4055 | Rev 4201 | ||
---|---|---|---|
1 | /* |
1 | /* |
2 | * Copyright (c) 2001-2004 Jakub Jermar |
2 | * Copyright (c) 2001-2004 Jakub Jermar |
3 | * All rights reserved. |
3 | * All rights reserved. |
4 | * |
4 | * |
5 | * Redistribution and use in source and binary forms, with or without |
5 | * Redistribution and use in source and binary forms, with or without |
6 | * modification, are permitted provided that the following conditions |
6 | * modification, are permitted provided that the following conditions |
7 | * are met: |
7 | * are met: |
8 | * |
8 | * |
9 | * - Redistributions of source code must retain the above copyright |
9 | * - Redistributions of source code must retain the above copyright |
10 | * notice, this list of conditions and the following disclaimer. |
10 | * notice, this list of conditions and the following disclaimer. |
11 | * - Redistributions in binary form must reproduce the above copyright |
11 | * - Redistributions in binary form must reproduce the above copyright |
12 | * notice, this list of conditions and the following disclaimer in the |
12 | * notice, this list of conditions and the following disclaimer in the |
13 | * documentation and/or other materials provided with the distribution. |
13 | * documentation and/or other materials provided with the distribution. |
14 | * - The name of the author may not be used to endorse or promote products |
14 | * - The name of the author may not be used to endorse or promote products |
15 | * derived from this software without specific prior written permission. |
15 | * derived from this software without specific prior written permission. |
16 | * |
16 | * |
17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR |
17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR |
18 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
18 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. |
19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. |
20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, |
20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, |
21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
27 | */ |
27 | */ |
28 | 28 | ||
29 | /** @addtogroup generic |
29 | /** @addtogroup generic |
30 | * @{ |
30 | * @{ |
31 | */ |
31 | */ |
32 | 32 | ||
33 | /** |
33 | /** |
34 | * @file |
34 | * @file |
35 | * @brief Miscellaneous functions. |
35 | * @brief Miscellaneous functions. |
36 | */ |
36 | */ |
37 | 37 | ||
38 | #include <string.h> |
38 | #include <string.h> |
39 | #include <print.h> |
39 | #include <print.h> |
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 | ||
- | 47 | /** Byte mask consisting of lowest @n bits (out of eight). */ |
|
- | 48 | #define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1)) |
|
- | 49 | ||
- | 50 | /** Byte mask consisting of lowest @n bits (out of 32). */ |
|
- | 51 | #define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1)) |
|
- | 52 | ||
- | 53 | /** Byte mask consisting of highest @n bits (out of eight). */ |
|
- | 54 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
|
- | 55 | ||
- | 56 | /** Number of data bits in a UTF-8 continuation byte. */ |
|
- | 57 | #define CONT_BITS 6 |
|
- | 58 | ||
45 | /** Return number of characters in a string. |
59 | /** Decode a single character from a substring. |
- | 60 | * |
|
- | 61 | * Decode a single character from a substring of size @a sz. Decoding starts |
|
- | 62 | * at @a offset and this offset is moved to the beginning of the next |
|
- | 63 | * character. In case of decoding error, offset generally advances at least |
|
- | 64 | * by one. However, offset is never moved beyond (str + sz). |
|
- | 65 | * |
|
- | 66 | * @param str String (not necessarily NULL-terminated). |
|
- | 67 | * @param index Index (counted in plain characters) where to start |
|
- | 68 | * the decoding. |
|
- | 69 | * @param limit Size of the substring. |
|
- | 70 | * |
|
- | 71 | * @return Value of decoded character or '?' on decoding error. |
|
- | 72 | * |
|
- | 73 | */ |
|
- | 74 | wchar_t chr_decode(const char *str, size_t *offset, size_t sz) |
|
- | 75 | { |
|
- | 76 | uint8_t b0, b; /* Bytes read from str. */ |
|
- | 77 | wchar_t ch; |
|
- | 78 | ||
- | 79 | int b0_bits; /* Data bits in first byte. */ |
|
- | 80 | int cbytes; /* Number of continuation bytes. */ |
|
- | 81 | ||
- | 82 | if (*offset + 1 > sz) |
|
- | 83 | return invalch; |
|
- | 84 | ||
- | 85 | b0 = (uint8_t) str[(*offset)++]; |
|
- | 86 | ||
- | 87 | /* Determine code length. */ |
|
- | 88 | ||
- | 89 | if ((b0 & 0x80) == 0) { |
|
- | 90 | /* 0xxxxxxx (Plain ASCII) */ |
|
- | 91 | b0_bits = 7; |
|
- | 92 | cbytes = 0; |
|
- | 93 | } else if ((b0 & 0xe0) == 0xc0) { |
|
- | 94 | /* 110xxxxx 10xxxxxx */ |
|
- | 95 | b0_bits = 5; |
|
- | 96 | cbytes = 1; |
|
- | 97 | } else if ((b0 & 0xf0) == 0xe0) { |
|
- | 98 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
|
- | 99 | b0_bits = 4; |
|
- | 100 | cbytes = 2; |
|
- | 101 | } else if ((b0 & 0xf8) == 0xf0) { |
|
- | 102 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
|
- | 103 | b0_bits = 3; |
|
- | 104 | cbytes = 3; |
|
- | 105 | } else { |
|
- | 106 | /* 10xxxxxx -- unexpected continuation byte. */ |
|
- | 107 | return invalch; |
|
- | 108 | } |
|
- | 109 | ||
- | 110 | if (*offset + cbytes > sz) { |
|
- | 111 | return invalch; |
|
- | 112 | } |
|
- | 113 | ||
- | 114 | ch = b0 & LO_MASK_8(b0_bits); |
|
- | 115 | ||
- | 116 | /* Decode continuation bytes. */ |
|
- | 117 | while (cbytes > 0) { |
|
- | 118 | b = (uint8_t) str[(*offset)++]; |
|
- | 119 | ||
- | 120 | /* Must be 10xxxxxx. */ |
|
- | 121 | if ((b & 0xc0) != 0x80) { |
|
- | 122 | return invalch; |
|
- | 123 | } |
|
- | 124 | ||
- | 125 | /* Shift data bits to ch. */ |
|
- | 126 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
|
- | 127 | --cbytes; |
|
- | 128 | } |
|
- | 129 | ||
- | 130 | return ch; |
|
- | 131 | } |
|
- | 132 | ||
- | 133 | /** Encode a single character to string representation. |
|
- | 134 | * |
|
- | 135 | * Encode a single character to string representation (i.e. UTF-8) and store |
|
- | 136 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
|
- | 137 | * is moved to the position where the next character can be written to. |
|
- | 138 | * |
|
- | 139 | * @param ch Input character. |
|
- | 140 | * @param str Output buffer. |
|
- | 141 | * @param offset Offset (in bytes) where to start writing. |
|
- | 142 | * @param sz Size of the output buffer. |
|
- | 143 | * |
|
- | 144 | * @return True if the character was encoded successfully or false if there |
|
- | 145 | * was not enough space in the output buffer or the character code |
|
- | 146 | * was invalid. |
|
- | 147 | */ |
|
- | 148 | bool chr_encode(const wchar_t ch, char *str, size_t *offset, size_t sz) |
|
- | 149 | { |
|
- | 150 | uint32_t cc; /* Unsigned version of ch. */ |
|
- | 151 | ||
- | 152 | int cbytes; /* Number of continuation bytes. */ |
|
- | 153 | int b0_bits; /* Number of data bits in first byte. */ |
|
- | 154 | int i; |
|
- | 155 | ||
- | 156 | if (*offset >= sz) |
|
- | 157 | return false; |
|
- | 158 | ||
- | 159 | if (ch < 0) |
|
- | 160 | return false; |
|
- | 161 | ||
- | 162 | /* Bit operations should only be done on unsigned numbers. */ |
|
- | 163 | cc = (uint32_t) ch; |
|
- | 164 | ||
- | 165 | /* Determine how many continuation bytes are needed. */ |
|
- | 166 | if ((cc & ~LO_MASK_32(7)) == 0) { |
|
- | 167 | b0_bits = 7; |
|
- | 168 | cbytes = 0; |
|
- | 169 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
|
- | 170 | b0_bits = 5; |
|
- | 171 | cbytes = 1; |
|
- | 172 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
|
- | 173 | b0_bits = 4; |
|
- | 174 | cbytes = 2; |
|
- | 175 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
|
- | 176 | b0_bits = 3; |
|
- | 177 | cbytes = 3; |
|
- | 178 | } else { |
|
- | 179 | /* Codes longer than 21 bits are not supported. */ |
|
- | 180 | return false; |
|
- | 181 | } |
|
- | 182 | ||
- | 183 | /* Check for available space in buffer. */ |
|
- | 184 | if (*offset + cbytes >= sz) |
|
- | 185 | return false; |
|
- | 186 | ||
- | 187 | /* Encode continuation bytes. */ |
|
- | 188 | for (i = cbytes; i > 0; --i) { |
|
- | 189 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
|
- | 190 | cc = cc >> CONT_BITS; |
|
- | 191 | } |
|
- | 192 | ||
- | 193 | /* Encode first byte. */ |
|
- | 194 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
|
- | 195 | ||
- | 196 | /* Advance offset. */ |
|
- | 197 | *offset += (1 + cbytes); |
|
- | 198 | ||
- | 199 | return true; |
|
- | 200 | } |
|
- | 201 | ||
- | 202 | /** Get bytes used by UTF-8 characters. |
|
46 | * |
203 | * |
- | 204 | * Get the number of bytes (count of plain characters) which |
|
- | 205 | * are used by a given count of UTF-8 characters in a string. |
|
- | 206 | * As UTF-8 encoding is multibyte, there is no constant |
|
- | 207 | * correspondence between number of characters and used bytes. |
|
- | 208 | * |
|
- | 209 | * @param str UTF-8 string to consider. |
|
- | 210 | * @param count Number of UTF-8 characters to count. |
|
- | 211 | * |
|
- | 212 | * @return Number of bytes used by the characters. |
|
- | 213 | * |
|
- | 214 | */ |
|
- | 215 | size_t utf8_count_bytes(const char *str, count_t count) |
|
- | 216 | { |
|
- | 217 | size_t size = 0; |
|
- | 218 | index_t index = 0; |
|
- | 219 | index_t iprev; |
|
- | 220 | wchar_t ch; |
|
- | 221 | ||
- | 222 | while (true) { |
|
- | 223 | iprev = index; |
|
- | 224 | if (size >= count) |
|
- | 225 | break; |
|
- | 226 | ch = chr_decode(str, &index, UTF8_NO_LIMIT); |
|
- | 227 | if (ch == '\0') break; |
|
- | 228 | ||
- | 229 | size++; |
|
- | 230 | } |
|
- | 231 | ||
- | 232 | return iprev; |
|
- | 233 | } |
|
- | 234 | ||
- | 235 | /** Check whether character is plain ASCII. |
|
- | 236 | * |
|
- | 237 | * @return True if character is plain ASCII. |
|
- | 238 | * |
|
- | 239 | */ |
|
- | 240 | bool ascii_check(const wchar_t ch) |
|
- | 241 | { |
|
- | 242 | if ((ch >= 0) && (ch <= 127)) |
|
- | 243 | return true; |
|
- | 244 | ||
- | 245 | return false; |
|
- | 246 | } |
|
- | 247 | ||
- | 248 | /** Check whether character is Unicode. |
|
- | 249 | * |
|
- | 250 | * @return True if character is valid Unicode code point. |
|
- | 251 | * |
|
- | 252 | */ |
|
- | 253 | bool unicode_check(const wchar_t ch) |
|
- | 254 | { |
|
- | 255 | if ((ch >= 0) && (ch <= 1114111)) |
|
- | 256 | return true; |
|
- | 257 | ||
- | 258 | return false; |
|
- | 259 | } |
|
- | 260 | ||
- | 261 | /** Return number of plain characters in a string. |
|
- | 262 | * |
|
47 | * @param str NULL terminated string. |
263 | * @param str NULL-terminated string. |
48 | * |
264 | * |
49 | * @return Number of characters in str. |
265 | * @return Number of characters in str. |
50 | * |
266 | * |
51 | */ |
267 | */ |
52 | size_t strlen(const char *str) |
268 | size_t strlen(const char *str) |
53 | { |
269 | { |
54 | int i; |
270 | size_t size; |
- | 271 | for (size = 0; str[size]; size++); |
|
55 | 272 | ||
- | 273 | return size; |
|
- | 274 | } |
|
- | 275 | ||
- | 276 | /** Return number of UTF-8 characters in a string. |
|
- | 277 | * |
|
- | 278 | * @param str NULL-terminated UTF-8 string. |
|
- | 279 | * |
|
- | 280 | * @return Number of UTF-8 characters in str. |
|
- | 281 | * |
|
- | 282 | */ |
|
- | 283 | size_t strlen_utf8(const char *str) |
|
- | 284 | { |
|
- | 285 | size_t size = 0; |
|
- | 286 | index_t index = 0; |
|
- | 287 | ||
- | 288 | while (chr_decode(str, &index, UTF8_NO_LIMIT) != 0) { |
|
- | 289 | size++; |
|
- | 290 | } |
|
- | 291 | ||
- | 292 | return size; |
|
- | 293 | } |
|
- | 294 | ||
- | 295 | /** Return number of UTF-32 characters in a string. |
|
- | 296 | * |
|
- | 297 | * @param str NULL-terminated UTF-32 string. |
|
- | 298 | * |
|
- | 299 | * @return Number of UTF-32 characters in str. |
|
- | 300 | * |
|
- | 301 | */ |
|
- | 302 | size_t strlen_utf32(const wchar_t *str) |
|
- | 303 | { |
|
- | 304 | size_t size; |
|
56 | for (i = 0; str[i]; i++); |
305 | for (size = 0; str[size]; size++); |
57 | 306 | ||
58 | return i; |
307 | return size; |
59 | } |
308 | } |
60 | 309 | ||
61 | /** Compare two NULL terminated strings |
310 | /** Compare two NULL terminated strings |
62 | * |
311 | * |
63 | * Do a char-by-char comparison of two NULL terminated strings. |
312 | * Do a char-by-char comparison of two NULL terminated strings. |
64 | * The strings are considered equal iff they consist of the same |
313 | * The strings are considered equal iff they consist of the same |
65 | * characters on the minimum of their lengths. |
314 | * characters on the minimum of their lengths. |
66 | * |
315 | * |
67 | * @param src First string to compare. |
316 | * @param src First string to compare. |
68 | * @param dst Second string to compare. |
317 | * @param dst Second string to compare. |
69 | * |
318 | * |
70 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
319 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
71 | * |
320 | * |
72 | */ |
321 | */ |
73 | int strcmp(const char *src, const char *dst) |
322 | int strcmp(const char *src, const char *dst) |
74 | { |
323 | { |
75 | for (; *src && *dst; src++, dst++) { |
324 | for (; *src && *dst; src++, dst++) { |
76 | if (*src < *dst) |
325 | if (*src < *dst) |
77 | return -1; |
326 | return -1; |
78 | if (*src > *dst) |
327 | if (*src > *dst) |
79 | return 1; |
328 | return 1; |
80 | } |
329 | } |
81 | if (*src == *dst) |
330 | if (*src == *dst) |
82 | return 0; |
331 | return 0; |
83 | 332 | ||
84 | if (!*src) |
333 | if (!*src) |
85 | return -1; |
334 | return -1; |
86 | 335 | ||
87 | return 1; |
336 | return 1; |
88 | } |
337 | } |
89 | 338 | ||
90 | 339 | ||
91 | /** Compare two NULL terminated strings |
340 | /** Compare two NULL terminated strings |
92 | * |
341 | * |
93 | * Do a char-by-char comparison of two NULL terminated strings. |
342 | * Do a char-by-char comparison of two NULL terminated strings. |
94 | * The strings are considered equal iff they consist of the same |
343 | * The strings are considered equal iff they consist of the same |
95 | * characters on the minimum of their lengths and specified maximal |
344 | * characters on the minimum of their lengths and specified maximal |
96 | * length. |
345 | * length. |
97 | * |
346 | * |
98 | * @param src First string to compare. |
347 | * @param src First string to compare. |
99 | * @param dst Second string to compare. |
348 | * @param dst Second string to compare. |
100 | * @param len Maximal length for comparison. |
349 | * @param len Maximal length for comparison. |
101 | * |
350 | * |
102 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
351 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
103 | * |
352 | * |
104 | */ |
353 | */ |
105 | int strncmp(const char *src, const char *dst, size_t len) |
354 | int strncmp(const char *src, const char *dst, size_t len) |
106 | { |
355 | { |
107 | unsigned int i; |
356 | unsigned int i; |
108 | 357 | ||
109 | for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) { |
358 | for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) { |
110 | if (*src < *dst) |
359 | if (*src < *dst) |
111 | return -1; |
360 | return -1; |
112 | 361 | ||
113 | if (*src > *dst) |
362 | if (*src > *dst) |
114 | return 1; |
363 | return 1; |
115 | } |
364 | } |
116 | 365 | ||
117 | if (i == len || *src == *dst) |
366 | if (i == len || *src == *dst) |
118 | return 0; |
367 | return 0; |
119 | 368 | ||
120 | if (!*src) |
369 | if (!*src) |
121 | return -1; |
370 | return -1; |
122 | 371 | ||
123 | return 1; |
372 | return 1; |
124 | } |
373 | } |
125 | 374 | ||
126 | 375 | ||
127 | 376 | ||
128 | /** Copy NULL terminated string. |
377 | /** Copy NULL terminated string. |
129 | * |
378 | * |
130 | * Copy at most 'len' characters from string 'src' to 'dest'. |
379 | * Copy at most 'len' characters from string 'src' to 'dest'. |
131 | * If 'src' is shorter than 'len', '\0' is inserted behind the |
380 | * If 'src' is shorter than 'len', '\0' is inserted behind the |
132 | * last copied character. |
381 | * last copied character. |
133 | * |
382 | * |
134 | * @param src Source string. |
383 | * @param src Source string. |
135 | * @param dest Destination buffer. |
384 | * @param dest Destination buffer. |
136 | * @param len Size of destination buffer. |
385 | * @param len Size of destination buffer. |
137 | * |
386 | * |
138 | */ |
387 | */ |
139 | void strncpy(char *dest, const char *src, size_t len) |
388 | void strncpy(char *dest, const char *src, size_t len) |
140 | { |
389 | { |
141 | unsigned int i; |
390 | unsigned int i; |
142 | 391 | ||
143 | for (i = 0; i < len; i++) { |
392 | for (i = 0; i < len; i++) { |
144 | if (!(dest[i] = src[i])) |
393 | if (!(dest[i] = src[i])) |
145 | return; |
394 | return; |
146 | } |
395 | } |
147 | 396 | ||
148 | dest[i - 1] = '\0'; |
397 | dest[i - 1] = '\0'; |
149 | } |
398 | } |
150 | 399 | ||
151 | /** Find first occurence of character in string. |
400 | /** Find first occurence of character in string. |
152 | * |
401 | * |
153 | * @param s String to search. |
402 | * @param s String to search. |
154 | * @param i Character to look for. |
403 | * @param i Character to look for. |
155 | * |
404 | * |
156 | * @return Pointer to character in @a s or NULL if not found. |
405 | * @return Pointer to character in @a s or NULL if not found. |
157 | */ |
406 | */ |
158 | extern char *strchr(const char *s, int i) |
407 | extern char *strchr(const char *s, int i) |
159 | { |
408 | { |
160 | while (*s != '\0') { |
409 | while (*s != '\0') { |
161 | if (*s == i) |
410 | if (*s == i) |
162 | return (char *) s; |
411 | return (char *) s; |
163 | ++s; |
412 | ++s; |
164 | } |
413 | } |
165 | 414 | ||
166 | return NULL; |
415 | return NULL; |
167 | } |
416 | } |
168 | 417 | ||
169 | /** @} |
418 | /** @} |
170 | */ |
419 | */ |
171 | 420 |