[16da5f8e] | 1 | /*
|
---|
| 2 | * Copyright (c) 2001-2004 Jakub Jermar
|
---|
| 3 | * All rights reserved.
|
---|
| 4 | *
|
---|
| 5 | * Redistribution and use in source and binary forms, with or without
|
---|
| 6 | * modification, are permitted provided that the following conditions
|
---|
| 7 | * are met:
|
---|
| 8 | *
|
---|
| 9 | * - Redistributions of source code must retain the above copyright
|
---|
| 10 | * notice, this list of conditions and the following disclaimer.
|
---|
| 11 | * - Redistributions in binary form must reproduce the above copyright
|
---|
| 12 | * notice, this list of conditions and the following disclaimer in the
|
---|
| 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
|
---|
| 15 | * derived from this software without specific prior written permission.
|
---|
| 16 | *
|
---|
| 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
|
---|
| 19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
---|
| 20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
---|
| 21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
---|
| 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
|
---|
| 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
|
---|
| 26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
---|
| 27 | */
|
---|
| 28 |
|
---|
[2f57690] | 29 | /** @addtogroup generic
|
---|
[16da5f8e] | 30 | * @{
|
---|
| 31 | */
|
---|
| 32 |
|
---|
| 33 | /**
|
---|
| 34 | * @file
|
---|
[82bb9c1] | 35 | * @brief String functions.
|
---|
| 36 | *
|
---|
| 37 | * Strings and characters use the Universal Character Set (UCS). The standard
|
---|
| 38 | * strings, called just strings are encoded in UTF-8. Wide strings (encoded
|
---|
| 39 | * in UTF-32) are supported to a limited degree. A single character is
|
---|
[b888d5f] | 40 | * represented as wchar_t.@n
|
---|
[82bb9c1] | 41 | *
|
---|
[b888d5f] | 42 | * Overview of the terminology:@n
|
---|
[82bb9c1] | 43 | *
|
---|
[b888d5f] | 44 | * Term Meaning
|
---|
| 45 | * -------------------- ----------------------------------------------------
|
---|
| 46 | * byte 8 bits stored in uint8_t (unsigned 8 bit integer)
|
---|
[82bb9c1] | 47 | *
|
---|
[b888d5f] | 48 | * character UTF-32 encoded Unicode character, stored in wchar_t
|
---|
| 49 | * (signed 32 bit integer), code points 0 .. 1114111
|
---|
| 50 | * are valid
|
---|
[82bb9c1] | 51 | *
|
---|
[b888d5f] | 52 | * ASCII character 7 bit encoded ASCII character, stored in char
|
---|
| 53 | * (usually signed 8 bit integer), code points 0 .. 127
|
---|
| 54 | * are valid
|
---|
| 55 | *
|
---|
| 56 | * string UTF-8 encoded NULL-terminated Unicode string, char *
|
---|
| 57 | *
|
---|
| 58 | * wide string UTF-32 encoded NULL-terminated Unicode string,
|
---|
| 59 | * wchar_t *
|
---|
| 60 | *
|
---|
| 61 | * [wide] string size number of BYTES in a [wide] string (excluding
|
---|
| 62 | * the NULL-terminator), size_t
|
---|
| 63 | *
|
---|
| 64 | * [wide] string length number of CHARACTERS in a [wide] string (excluding
|
---|
[98000fb] | 65 | * the NULL-terminator), size_t
|
---|
[b888d5f] | 66 | *
|
---|
| 67 | * [wide] string width number of display cells on a monospace display taken
|
---|
[98000fb] | 68 | * by a [wide] string, size_t
|
---|
[b888d5f] | 69 | *
|
---|
| 70 | *
|
---|
| 71 | * Overview of string metrics:@n
|
---|
| 72 | *
|
---|
| 73 | * Metric Abbrev. Type Meaning
|
---|
| 74 | * ------ ------ ------ -------------------------------------------------
|
---|
| 75 | * size n size_t number of BYTES in a string (excluding the
|
---|
| 76 | * NULL-terminator)
|
---|
| 77 | *
|
---|
[98000fb] | 78 | * length l size_t number of CHARACTERS in a string (excluding the
|
---|
[b888d5f] | 79 | * null terminator)
|
---|
| 80 | *
|
---|
[98000fb] | 81 | * width w size_t number of display cells on a monospace display
|
---|
[b888d5f] | 82 | * taken by a string
|
---|
| 83 | *
|
---|
| 84 | *
|
---|
| 85 | * Function naming prefixes:@n
|
---|
| 86 | *
|
---|
| 87 | * chr_ operate on characters
|
---|
| 88 | * ascii_ operate on ASCII characters
|
---|
| 89 | * str_ operate on strings
|
---|
| 90 | * wstr_ operate on wide strings
|
---|
| 91 | *
|
---|
| 92 | * [w]str_[n|l|w] operate on a prefix limited by size, length
|
---|
| 93 | * or width
|
---|
| 94 | *
|
---|
| 95 | *
|
---|
| 96 | * A specific character inside a [wide] string can be referred to by:@n
|
---|
| 97 | *
|
---|
| 98 | * pointer (char *, wchar_t *)
|
---|
| 99 | * byte offset (size_t)
|
---|
[98000fb] | 100 | * character index (size_t)
|
---|
[82bb9c1] | 101 | *
|
---|
[16da5f8e] | 102 | */
|
---|
| 103 |
|
---|
[19f857a] | 104 | #include <str.h>
|
---|
[16da5f8e] | 105 | #include <print.h>
|
---|
| 106 | #include <cpu.h>
|
---|
| 107 | #include <arch/asm.h>
|
---|
| 108 | #include <arch.h>
|
---|
[d09f84e6] | 109 | #include <errno.h>
|
---|
[b888d5f] | 110 | #include <align.h>
|
---|
[63e27ef] | 111 | #include <assert.h>
|
---|
[30a5470] | 112 | #include <macros.h>
|
---|
[1066041] | 113 | #include <mm/slab.h>
|
---|
[16da5f8e] | 114 |
|
---|
[8e893ae] | 115 | /** Check the condition if wchar_t is signed */
|
---|
[002fd5f] | 116 | #ifdef __WCHAR_UNSIGNED__
|
---|
[1433ecda] | 117 | #define WCHAR_SIGNED_CHECK(cond) (true)
|
---|
[8e893ae] | 118 | #else
|
---|
[1433ecda] | 119 | #define WCHAR_SIGNED_CHECK(cond) (cond)
|
---|
[8e893ae] | 120 | #endif
|
---|
| 121 |
|
---|
[b888d5f] | 122 | /** Byte mask consisting of lowest @n bits (out of 8) */
|
---|
| 123 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1))
|
---|
[0dd1d444] | 124 |
|
---|
[b888d5f] | 125 | /** Byte mask consisting of lowest @n bits (out of 32) */
|
---|
| 126 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1))
|
---|
[32704cb] | 127 |
|
---|
[b888d5f] | 128 | /** Byte mask consisting of highest @n bits (out of 8) */
|
---|
| 129 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
|
---|
[32704cb] | 130 |
|
---|
[b888d5f] | 131 | /** Number of data bits in a UTF-8 continuation byte */
|
---|
| 132 | #define CONT_BITS 6
|
---|
[0dd1d444] | 133 |
|
---|
[b888d5f] | 134 | /** Decode a single character from a string.
|
---|
[21a639b7] | 135 | *
|
---|
[b888d5f] | 136 | * Decode a single character from a string of size @a size. Decoding starts
|
---|
[e1813cf] | 137 | * at @a offset and this offset is moved to the beginning of the next
|
---|
| 138 | * character. In case of decoding error, offset generally advances at least
|
---|
[b888d5f] | 139 | * by one. However, offset is never moved beyond size.
|
---|
[21a639b7] | 140 | *
|
---|
[b888d5f] | 141 | * @param str String (not necessarily NULL-terminated).
|
---|
| 142 | * @param offset Byte offset in string where to start decoding.
|
---|
| 143 | * @param size Size of the string (in bytes).
|
---|
| 144 | *
|
---|
[c8bf88d] | 145 | * @return Value of decoded character, U_SPECIAL on decoding error or
|
---|
[b888d5f] | 146 | * NULL if attempt to decode beyond @a size.
|
---|
[21a639b7] | 147 | *
|
---|
| 148 | */
|
---|
[b888d5f] | 149 | wchar_t str_decode(const char *str, size_t *offset, size_t size)
|
---|
[21a639b7] | 150 | {
|
---|
[b888d5f] | 151 | if (*offset + 1 > size)
|
---|
| 152 | return 0;
|
---|
[a35b458] | 153 |
|
---|
[b888d5f] | 154 | /* First byte read from string */
|
---|
| 155 | uint8_t b0 = (uint8_t) str[(*offset)++];
|
---|
[a35b458] | 156 |
|
---|
[b888d5f] | 157 | /* Determine code length */
|
---|
[a35b458] | 158 |
|
---|
[b888d5f] | 159 | unsigned int b0_bits; /* Data bits in first byte */
|
---|
| 160 | unsigned int cbytes; /* Number of continuation bytes */
|
---|
[a35b458] | 161 |
|
---|
[0dd1d444] | 162 | if ((b0 & 0x80) == 0) {
|
---|
| 163 | /* 0xxxxxxx (Plain ASCII) */
|
---|
| 164 | b0_bits = 7;
|
---|
| 165 | cbytes = 0;
|
---|
| 166 | } else if ((b0 & 0xe0) == 0xc0) {
|
---|
| 167 | /* 110xxxxx 10xxxxxx */
|
---|
| 168 | b0_bits = 5;
|
---|
| 169 | cbytes = 1;
|
---|
| 170 | } else if ((b0 & 0xf0) == 0xe0) {
|
---|
| 171 | /* 1110xxxx 10xxxxxx 10xxxxxx */
|
---|
| 172 | b0_bits = 4;
|
---|
| 173 | cbytes = 2;
|
---|
| 174 | } else if ((b0 & 0xf8) == 0xf0) {
|
---|
| 175 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
|
---|
| 176 | b0_bits = 3;
|
---|
| 177 | cbytes = 3;
|
---|
| 178 | } else {
|
---|
[b888d5f] | 179 | /* 10xxxxxx -- unexpected continuation byte */
|
---|
[c8bf88d] | 180 | return U_SPECIAL;
|
---|
[74c8da2c] | 181 | }
|
---|
[a35b458] | 182 |
|
---|
[b888d5f] | 183 | if (*offset + cbytes > size)
|
---|
[c8bf88d] | 184 | return U_SPECIAL;
|
---|
[a35b458] | 185 |
|
---|
[b888d5f] | 186 | wchar_t ch = b0 & LO_MASK_8(b0_bits);
|
---|
[a35b458] | 187 |
|
---|
[b888d5f] | 188 | /* Decode continuation bytes */
|
---|
[0dd1d444] | 189 | while (cbytes > 0) {
|
---|
[b888d5f] | 190 | uint8_t b = (uint8_t) str[(*offset)++];
|
---|
[a35b458] | 191 |
|
---|
[b888d5f] | 192 | /* Must be 10xxxxxx */
|
---|
| 193 | if ((b & 0xc0) != 0x80)
|
---|
[c8bf88d] | 194 | return U_SPECIAL;
|
---|
[a35b458] | 195 |
|
---|
[b888d5f] | 196 | /* Shift data bits to ch */
|
---|
[0dd1d444] | 197 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS));
|
---|
[b888d5f] | 198 | cbytes--;
|
---|
[74c8da2c] | 199 | }
|
---|
[a35b458] | 200 |
|
---|
[0dd1d444] | 201 | return ch;
|
---|
[74c8da2c] | 202 | }
|
---|
| 203 |
|
---|
[e1813cf] | 204 | /** Encode a single character to string representation.
|
---|
[74c8da2c] | 205 | *
|
---|
[e1813cf] | 206 | * Encode a single character to string representation (i.e. UTF-8) and store
|
---|
| 207 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset
|
---|
| 208 | * is moved to the position where the next character can be written to.
|
---|
[74c8da2c] | 209 | *
|
---|
[b888d5f] | 210 | * @param ch Input character.
|
---|
| 211 | * @param str Output buffer.
|
---|
| 212 | * @param offset Byte offset where to start writing.
|
---|
| 213 | * @param size Size of the output buffer (in bytes).
|
---|
[74c8da2c] | 214 | *
|
---|
[d09f84e6] | 215 | * @return EOK if the character was encoded successfully, EOVERFLOW if there
|
---|
[8e893ae] | 216 | * was not enough space in the output buffer or EINVAL if the character
|
---|
| 217 | * code was invalid.
|
---|
[74c8da2c] | 218 | */
|
---|
[b7fd2a0] | 219 | errno_t chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size)
|
---|
[74c8da2c] | 220 | {
|
---|
[b888d5f] | 221 | if (*offset >= size)
|
---|
[d09f84e6] | 222 | return EOVERFLOW;
|
---|
[a35b458] | 223 |
|
---|
[b888d5f] | 224 | if (!chr_check(ch))
|
---|
[d09f84e6] | 225 | return EINVAL;
|
---|
[a35b458] | 226 |
|
---|
[7c3fb9b] | 227 | /*
|
---|
| 228 | * Unsigned version of ch (bit operations should only be done
|
---|
| 229 | * on unsigned types).
|
---|
| 230 | */
|
---|
[b888d5f] | 231 | uint32_t cc = (uint32_t) ch;
|
---|
[a35b458] | 232 |
|
---|
[b888d5f] | 233 | /* Determine how many continuation bytes are needed */
|
---|
[a35b458] | 234 |
|
---|
[b888d5f] | 235 | unsigned int b0_bits; /* Data bits in first byte */
|
---|
| 236 | unsigned int cbytes; /* Number of continuation bytes */
|
---|
[a35b458] | 237 |
|
---|
[32704cb] | 238 | if ((cc & ~LO_MASK_32(7)) == 0) {
|
---|
| 239 | b0_bits = 7;
|
---|
| 240 | cbytes = 0;
|
---|
| 241 | } else if ((cc & ~LO_MASK_32(11)) == 0) {
|
---|
| 242 | b0_bits = 5;
|
---|
| 243 | cbytes = 1;
|
---|
| 244 | } else if ((cc & ~LO_MASK_32(16)) == 0) {
|
---|
| 245 | b0_bits = 4;
|
---|
| 246 | cbytes = 2;
|
---|
| 247 | } else if ((cc & ~LO_MASK_32(21)) == 0) {
|
---|
| 248 | b0_bits = 3;
|
---|
| 249 | cbytes = 3;
|
---|
| 250 | } else {
|
---|
[b888d5f] | 251 | /* Codes longer than 21 bits are not supported */
|
---|
[d09f84e6] | 252 | return EINVAL;
|
---|
[74c8da2c] | 253 | }
|
---|
[a35b458] | 254 |
|
---|
[b888d5f] | 255 | /* Check for available space in buffer */
|
---|
| 256 | if (*offset + cbytes >= size)
|
---|
[d09f84e6] | 257 | return EOVERFLOW;
|
---|
[a35b458] | 258 |
|
---|
[b888d5f] | 259 | /* Encode continuation bytes */
|
---|
| 260 | unsigned int i;
|
---|
| 261 | for (i = cbytes; i > 0; i--) {
|
---|
[e1813cf] | 262 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS));
|
---|
[32704cb] | 263 | cc = cc >> CONT_BITS;
|
---|
[74c8da2c] | 264 | }
|
---|
[a35b458] | 265 |
|
---|
[b888d5f] | 266 | /* Encode first byte */
|
---|
[e1813cf] | 267 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1);
|
---|
[a35b458] | 268 |
|
---|
[b888d5f] | 269 | /* Advance offset */
|
---|
| 270 | *offset += cbytes + 1;
|
---|
[a35b458] | 271 |
|
---|
[d09f84e6] | 272 | return EOK;
|
---|
[74c8da2c] | 273 | }
|
---|
| 274 |
|
---|
[b888d5f] | 275 | /** Get size of string.
|
---|
| 276 | *
|
---|
| 277 | * Get the number of bytes which are used by the string @a str (excluding the
|
---|
| 278 | * NULL-terminator).
|
---|
| 279 | *
|
---|
| 280 | * @param str String to consider.
|
---|
| 281 | *
|
---|
| 282 | * @return Number of bytes used by the string
|
---|
[82bb9c1] | 283 | *
|
---|
| 284 | */
|
---|
[b888d5f] | 285 | size_t str_size(const char *str)
|
---|
[82bb9c1] | 286 | {
|
---|
[b888d5f] | 287 | size_t size = 0;
|
---|
[a35b458] | 288 |
|
---|
[b888d5f] | 289 | while (*str++ != 0)
|
---|
| 290 | size++;
|
---|
[a35b458] | 291 |
|
---|
[b888d5f] | 292 | return size;
|
---|
[82bb9c1] | 293 | }
|
---|
| 294 |
|
---|
[b888d5f] | 295 | /** Get size of wide string.
|
---|
| 296 | *
|
---|
| 297 | * Get the number of bytes which are used by the wide string @a str (excluding the
|
---|
| 298 | * NULL-terminator).
|
---|
| 299 | *
|
---|
| 300 | * @param str Wide string to consider.
|
---|
| 301 | *
|
---|
| 302 | * @return Number of bytes used by the wide string
|
---|
| 303 | *
|
---|
| 304 | */
|
---|
| 305 | size_t wstr_size(const wchar_t *str)
|
---|
| 306 | {
|
---|
| 307 | return (wstr_length(str) * sizeof(wchar_t));
|
---|
| 308 | }
|
---|
| 309 |
|
---|
| 310 | /** Get size of string with length limit.
|
---|
[74c8da2c] | 311 | *
|
---|
[f25b2819] | 312 | * Get the number of bytes which are used by up to @a max_len first
|
---|
| 313 | * characters in the string @a str. If @a max_len is greater than
|
---|
[b888d5f] | 314 | * the length of @a str, the entire string is measured (excluding the
|
---|
| 315 | * NULL-terminator).
|
---|
| 316 | *
|
---|
| 317 | * @param str String to consider.
|
---|
| 318 | * @param max_len Maximum number of characters to measure.
|
---|
[74c8da2c] | 319 | *
|
---|
[b888d5f] | 320 | * @return Number of bytes used by the characters.
|
---|
[74c8da2c] | 321 | *
|
---|
| 322 | */
|
---|
[98000fb] | 323 | size_t str_lsize(const char *str, size_t max_len)
|
---|
[74c8da2c] | 324 | {
|
---|
[98000fb] | 325 | size_t len = 0;
|
---|
[b888d5f] | 326 | size_t offset = 0;
|
---|
[a35b458] | 327 |
|
---|
[b888d5f] | 328 | while (len < max_len) {
|
---|
| 329 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0)
|
---|
[b54d2f1] | 330 | break;
|
---|
[a35b458] | 331 |
|
---|
[f25b2819] | 332 | len++;
|
---|
[21a639b7] | 333 | }
|
---|
[a35b458] | 334 |
|
---|
[b888d5f] | 335 | return offset;
|
---|
[74c8da2c] | 336 | }
|
---|
| 337 |
|
---|
[b888d5f] | 338 | /** Get size of wide string with length limit.
|
---|
[82bb9c1] | 339 | *
|
---|
[b888d5f] | 340 | * Get the number of bytes which are used by up to @a max_len first
|
---|
| 341 | * wide characters in the wide string @a str. If @a max_len is greater than
|
---|
| 342 | * the length of @a str, the entire wide string is measured (excluding the
|
---|
| 343 | * NULL-terminator).
|
---|
| 344 | *
|
---|
| 345 | * @param str Wide string to consider.
|
---|
| 346 | * @param max_len Maximum number of wide characters to measure.
|
---|
[82bb9c1] | 347 | *
|
---|
[b888d5f] | 348 | * @return Number of bytes used by the wide characters.
|
---|
[82bb9c1] | 349 | *
|
---|
| 350 | */
|
---|
[98000fb] | 351 | size_t wstr_lsize(const wchar_t *str, size_t max_len)
|
---|
[82bb9c1] | 352 | {
|
---|
[b888d5f] | 353 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t));
|
---|
[82bb9c1] | 354 | }
|
---|
| 355 |
|
---|
[b888d5f] | 356 | /** Get number of characters in a string.
|
---|
[82bb9c1] | 357 | *
|
---|
[b888d5f] | 358 | * @param str NULL-terminated string.
|
---|
[82bb9c1] | 359 | *
|
---|
[b888d5f] | 360 | * @return Number of characters in string.
|
---|
[82bb9c1] | 361 | *
|
---|
| 362 | */
|
---|
[98000fb] | 363 | size_t str_length(const char *str)
|
---|
[82bb9c1] | 364 | {
|
---|
[98000fb] | 365 | size_t len = 0;
|
---|
[b888d5f] | 366 | size_t offset = 0;
|
---|
[a35b458] | 367 |
|
---|
[b888d5f] | 368 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0)
|
---|
| 369 | len++;
|
---|
[a35b458] | 370 |
|
---|
[b888d5f] | 371 | return len;
|
---|
[82bb9c1] | 372 | }
|
---|
| 373 |
|
---|
[b888d5f] | 374 | /** Get number of characters in a wide string.
|
---|
[74c8da2c] | 375 | *
|
---|
[b888d5f] | 376 | * @param str NULL-terminated wide string.
|
---|
| 377 | *
|
---|
| 378 | * @return Number of characters in @a str.
|
---|
[74c8da2c] | 379 | *
|
---|
| 380 | */
|
---|
[98000fb] | 381 | size_t wstr_length(const wchar_t *wstr)
|
---|
[74c8da2c] | 382 | {
|
---|
[98000fb] | 383 | size_t len = 0;
|
---|
[a35b458] | 384 |
|
---|
[b888d5f] | 385 | while (*wstr++ != 0)
|
---|
| 386 | len++;
|
---|
[a35b458] | 387 |
|
---|
[b888d5f] | 388 | return len;
|
---|
[74c8da2c] | 389 | }
|
---|
| 390 |
|
---|
[b888d5f] | 391 | /** Get number of characters in a string with size limit.
|
---|
| 392 | *
|
---|
| 393 | * @param str NULL-terminated string.
|
---|
| 394 | * @param size Maximum number of bytes to consider.
|
---|
| 395 | *
|
---|
| 396 | * @return Number of characters in string.
|
---|
[74c8da2c] | 397 | *
|
---|
| 398 | */
|
---|
[98000fb] | 399 | size_t str_nlength(const char *str, size_t size)
|
---|
[74c8da2c] | 400 | {
|
---|
[98000fb] | 401 | size_t len = 0;
|
---|
[b888d5f] | 402 | size_t offset = 0;
|
---|
[a35b458] | 403 |
|
---|
[b888d5f] | 404 | while (str_decode(str, &offset, size) != 0)
|
---|
| 405 | len++;
|
---|
[a35b458] | 406 |
|
---|
[b888d5f] | 407 | return len;
|
---|
[21a639b7] | 408 | }
|
---|
| 409 |
|
---|
[b888d5f] | 410 | /** Get number of characters in a string with size limit.
|
---|
[2f57690] | 411 | *
|
---|
[b888d5f] | 412 | * @param str NULL-terminated string.
|
---|
| 413 | * @param size Maximum number of bytes to consider.
|
---|
[74c8da2c] | 414 | *
|
---|
[f25b2819] | 415 | * @return Number of characters in string.
|
---|
[b888d5f] | 416 | *
|
---|
[74c8da2c] | 417 | */
|
---|
[98000fb] | 418 | size_t wstr_nlength(const wchar_t *str, size_t size)
|
---|
[74c8da2c] | 419 | {
|
---|
[98000fb] | 420 | size_t len = 0;
|
---|
| 421 | size_t limit = ALIGN_DOWN(size, sizeof(wchar_t));
|
---|
| 422 | size_t offset = 0;
|
---|
[a35b458] | 423 |
|
---|
[b888d5f] | 424 | while ((offset < limit) && (*str++ != 0)) {
|
---|
[f25b2819] | 425 | len++;
|
---|
[b888d5f] | 426 | offset += sizeof(wchar_t);
|
---|
[74c8da2c] | 427 | }
|
---|
[a35b458] | 428 |
|
---|
[f25b2819] | 429 | return len;
|
---|
[74c8da2c] | 430 | }
|
---|
| 431 |
|
---|
[b888d5f] | 432 | /** Check whether character is plain ASCII.
|
---|
| 433 | *
|
---|
| 434 | * @return True if character is plain ASCII.
|
---|
[74c8da2c] | 435 | *
|
---|
| 436 | */
|
---|
[f2b8cdc] | 437 | bool ascii_check(wchar_t ch)
|
---|
[74c8da2c] | 438 | {
|
---|
[8e893ae] | 439 | if (WCHAR_SIGNED_CHECK(ch >= 0) && (ch <= 127))
|
---|
[b888d5f] | 440 | return true;
|
---|
[a35b458] | 441 |
|
---|
[b888d5f] | 442 | return false;
|
---|
| 443 | }
|
---|
[f25b2819] | 444 |
|
---|
[b888d5f] | 445 | /** Check whether character is valid
|
---|
| 446 | *
|
---|
| 447 | * @return True if character is a valid Unicode code point.
|
---|
| 448 | *
|
---|
| 449 | */
|
---|
[f2b8cdc] | 450 | bool chr_check(wchar_t ch)
|
---|
[b888d5f] | 451 | {
|
---|
[8e893ae] | 452 | if (WCHAR_SIGNED_CHECK(ch >= 0) && (ch <= 1114111))
|
---|
[b888d5f] | 453 | return true;
|
---|
[a35b458] | 454 |
|
---|
[b888d5f] | 455 | return false;
|
---|
[16da5f8e] | 456 | }
|
---|
| 457 |
|
---|
[b888d5f] | 458 | /** Compare two NULL terminated strings.
|
---|
[16da5f8e] | 459 | *
|
---|
[b888d5f] | 460 | * Do a char-by-char comparison of two NULL-terminated strings.
|
---|
[4efeab5] | 461 | * The strings are considered equal iff their length is equal
|
---|
| 462 | * and both strings consist of the same sequence of characters.
|
---|
| 463 | *
|
---|
[1772e6d] | 464 | * A string S1 is less than another string S2 if it has a character with
|
---|
| 465 | * lower value at the first character position where the strings differ.
|
---|
| 466 | * If the strings differ in length, the shorter one is treated as if
|
---|
| 467 | * padded by characters with a value of zero.
|
---|
[16da5f8e] | 468 | *
|
---|
[b888d5f] | 469 | * @param s1 First string to compare.
|
---|
| 470 | * @param s2 Second string to compare.
|
---|
[16da5f8e] | 471 | *
|
---|
[1772e6d] | 472 | * @return 0 if the strings are equal, -1 if the first is less than the second,
|
---|
| 473 | * 1 if the second is less than the first.
|
---|
[16da5f8e] | 474 | *
|
---|
| 475 | */
|
---|
[b888d5f] | 476 | int str_cmp(const char *s1, const char *s2)
|
---|
[16da5f8e] | 477 | {
|
---|
[a7b1071] | 478 | wchar_t c1 = 0;
|
---|
| 479 | wchar_t c2 = 0;
|
---|
[a35b458] | 480 |
|
---|
[b888d5f] | 481 | size_t off1 = 0;
|
---|
| 482 | size_t off2 = 0;
|
---|
[a7b1071] | 483 |
|
---|
| 484 | while (true) {
|
---|
| 485 | c1 = str_decode(s1, &off1, STR_NO_LIMIT);
|
---|
| 486 | c2 = str_decode(s2, &off2, STR_NO_LIMIT);
|
---|
| 487 |
|
---|
[b888d5f] | 488 | if (c1 < c2)
|
---|
[16da5f8e] | 489 | return -1;
|
---|
[a35b458] | 490 |
|
---|
[b888d5f] | 491 | if (c1 > c2)
|
---|
[16da5f8e] | 492 | return 1;
|
---|
[a7b1071] | 493 |
|
---|
| 494 | if (c1 == 0 || c2 == 0)
|
---|
[1b20da0] | 495 | break;
|
---|
[16da5f8e] | 496 | }
|
---|
[a7b1071] | 497 |
|
---|
| 498 | return 0;
|
---|
[16da5f8e] | 499 | }
|
---|
| 500 |
|
---|
[b888d5f] | 501 | /** Compare two NULL terminated strings with length limit.
|
---|
[16da5f8e] | 502 | *
|
---|
[b888d5f] | 503 | * Do a char-by-char comparison of two NULL-terminated strings.
|
---|
[4efeab5] | 504 | * The strings are considered equal iff
|
---|
| 505 | * min(str_length(s1), max_len) == min(str_length(s2), max_len)
|
---|
| 506 | * and both strings consist of the same sequence of characters,
|
---|
| 507 | * up to max_len characters.
|
---|
| 508 | *
|
---|
[1772e6d] | 509 | * A string S1 is less than another string S2 if it has a character with
|
---|
| 510 | * lower value at the first character position where the strings differ.
|
---|
| 511 | * If the strings differ in length, the shorter one is treated as if
|
---|
| 512 | * padded by characters with a value of zero. Only the first max_len
|
---|
| 513 | * characters are considered.
|
---|
[16da5f8e] | 514 | *
|
---|
[b888d5f] | 515 | * @param s1 First string to compare.
|
---|
| 516 | * @param s2 Second string to compare.
|
---|
| 517 | * @param max_len Maximum number of characters to consider.
|
---|
| 518 | *
|
---|
[1772e6d] | 519 | * @return 0 if the strings are equal, -1 if the first is less than the second,
|
---|
| 520 | * 1 if the second is less than the first.
|
---|
[16da5f8e] | 521 | *
|
---|
| 522 | */
|
---|
[98000fb] | 523 | int str_lcmp(const char *s1, const char *s2, size_t max_len)
|
---|
[16da5f8e] | 524 | {
|
---|
[b888d5f] | 525 | wchar_t c1 = 0;
|
---|
| 526 | wchar_t c2 = 0;
|
---|
[a35b458] | 527 |
|
---|
[b888d5f] | 528 | size_t off1 = 0;
|
---|
| 529 | size_t off2 = 0;
|
---|
[a35b458] | 530 |
|
---|
[98000fb] | 531 | size_t len = 0;
|
---|
[a7b1071] | 532 |
|
---|
| 533 | while (true) {
|
---|
| 534 | if (len >= max_len)
|
---|
[b888d5f] | 535 | break;
|
---|
[a7b1071] | 536 |
|
---|
| 537 | c1 = str_decode(s1, &off1, STR_NO_LIMIT);
|
---|
| 538 | c2 = str_decode(s2, &off2, STR_NO_LIMIT);
|
---|
| 539 |
|
---|
[b888d5f] | 540 | if (c1 < c2)
|
---|
[16da5f8e] | 541 | return -1;
|
---|
[a7b1071] | 542 |
|
---|
[b888d5f] | 543 | if (c1 > c2)
|
---|
[16da5f8e] | 544 | return 1;
|
---|
[a7b1071] | 545 |
|
---|
| 546 | if (c1 == 0 || c2 == 0)
|
---|
| 547 | break;
|
---|
| 548 |
|
---|
[1b20da0] | 549 | ++len;
|
---|
[16da5f8e] | 550 | }
|
---|
[a7b1071] | 551 |
|
---|
| 552 | return 0;
|
---|
| 553 |
|
---|
[16da5f8e] | 554 | }
|
---|
| 555 |
|
---|
[f4b1535] | 556 | /** Copy string.
|
---|
[b888d5f] | 557 | *
|
---|
[f4b1535] | 558 | * Copy source string @a src to destination buffer @a dest.
|
---|
| 559 | * No more than @a size bytes are written. If the size of the output buffer
|
---|
| 560 | * is at least one byte, the output string will always be well-formed, i.e.
|
---|
| 561 | * null-terminated and containing only complete characters.
|
---|
[b888d5f] | 562 | *
|
---|
[abf09311] | 563 | * @param dest Destination buffer.
|
---|
[6700ee2] | 564 | * @param count Size of the destination buffer (must be > 0).
|
---|
[f4b1535] | 565 | * @param src Source string.
|
---|
[abf09311] | 566 | *
|
---|
[b888d5f] | 567 | */
|
---|
[f4b1535] | 568 | void str_cpy(char *dest, size_t size, const char *src)
|
---|
[b888d5f] | 569 | {
|
---|
[6700ee2] | 570 | /* There must be space for a null terminator in the buffer. */
|
---|
[63e27ef] | 571 | assert(size > 0);
|
---|
| 572 | assert(src != NULL);
|
---|
[a35b458] | 573 |
|
---|
[abf09311] | 574 | size_t src_off = 0;
|
---|
| 575 | size_t dest_off = 0;
|
---|
[a35b458] | 576 |
|
---|
[abf09311] | 577 | wchar_t ch;
|
---|
[f4b1535] | 578 | while ((ch = str_decode(src, &src_off, STR_NO_LIMIT)) != 0) {
|
---|
| 579 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
| 580 | break;
|
---|
| 581 | }
|
---|
[a35b458] | 582 |
|
---|
[f4b1535] | 583 | dest[dest_off] = '\0';
|
---|
| 584 | }
|
---|
| 585 |
|
---|
| 586 | /** Copy size-limited substring.
|
---|
| 587 | *
|
---|
[6700ee2] | 588 | * Copy prefix of string @a src of max. size @a size to destination buffer
|
---|
| 589 | * @a dest. No more than @a size bytes are written. The output string will
|
---|
| 590 | * always be well-formed, i.e. null-terminated and containing only complete
|
---|
| 591 | * characters.
|
---|
[f4b1535] | 592 | *
|
---|
| 593 | * No more than @a n bytes are read from the input string, so it does not
|
---|
| 594 | * have to be null-terminated.
|
---|
| 595 | *
|
---|
[abf09311] | 596 | * @param dest Destination buffer.
|
---|
[6700ee2] | 597 | * @param count Size of the destination buffer (must be > 0).
|
---|
[f4b1535] | 598 | * @param src Source string.
|
---|
[abf09311] | 599 | * @param n Maximum number of bytes to read from @a src.
|
---|
| 600 | *
|
---|
[f4b1535] | 601 | */
|
---|
| 602 | void str_ncpy(char *dest, size_t size, const char *src, size_t n)
|
---|
| 603 | {
|
---|
[6700ee2] | 604 | /* There must be space for a null terminator in the buffer. */
|
---|
[63e27ef] | 605 | assert(size > 0);
|
---|
[a35b458] | 606 |
|
---|
[abf09311] | 607 | size_t src_off = 0;
|
---|
| 608 | size_t dest_off = 0;
|
---|
[a35b458] | 609 |
|
---|
[abf09311] | 610 | wchar_t ch;
|
---|
[f4b1535] | 611 | while ((ch = str_decode(src, &src_off, n)) != 0) {
|
---|
| 612 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
[b888d5f] | 613 | break;
|
---|
| 614 | }
|
---|
[a35b458] | 615 |
|
---|
[f4b1535] | 616 | dest[dest_off] = '\0';
|
---|
[b888d5f] | 617 | }
|
---|
[16da5f8e] | 618 |
|
---|
[abf09311] | 619 | /** Duplicate string.
|
---|
| 620 | *
|
---|
| 621 | * Allocate a new string and copy characters from the source
|
---|
| 622 | * string into it. The duplicate string is allocated via sleeping
|
---|
| 623 | * malloc(), thus this function can sleep in no memory conditions.
|
---|
| 624 | *
|
---|
| 625 | * The allocation cannot fail and the return value is always
|
---|
| 626 | * a valid pointer. The duplicate string is always a well-formed
|
---|
| 627 | * null-terminated UTF-8 string, but it can differ from the source
|
---|
| 628 | * string on the byte level.
|
---|
| 629 | *
|
---|
| 630 | * @param src Source string.
|
---|
| 631 | *
|
---|
| 632 | * @return Duplicate string.
|
---|
| 633 | *
|
---|
| 634 | */
|
---|
| 635 | char *str_dup(const char *src)
|
---|
| 636 | {
|
---|
| 637 | size_t size = str_size(src) + 1;
|
---|
[11b285d] | 638 | char *dest = nfmalloc(size);
|
---|
[63e27ef] | 639 | assert(dest);
|
---|
[a35b458] | 640 |
|
---|
[abf09311] | 641 | str_cpy(dest, size, src);
|
---|
| 642 | return dest;
|
---|
| 643 | }
|
---|
| 644 |
|
---|
| 645 | /** Duplicate string with size limit.
|
---|
| 646 | *
|
---|
| 647 | * Allocate a new string and copy up to @max_size bytes from the source
|
---|
| 648 | * string into it. The duplicate string is allocated via sleeping
|
---|
| 649 | * malloc(), thus this function can sleep in no memory conditions.
|
---|
| 650 | * No more than @max_size + 1 bytes is allocated, but if the size
|
---|
| 651 | * occupied by the source string is smaller than @max_size + 1,
|
---|
| 652 | * less is allocated.
|
---|
| 653 | *
|
---|
| 654 | * The allocation cannot fail and the return value is always
|
---|
| 655 | * a valid pointer. The duplicate string is always a well-formed
|
---|
| 656 | * null-terminated UTF-8 string, but it can differ from the source
|
---|
| 657 | * string on the byte level.
|
---|
| 658 | *
|
---|
| 659 | * @param src Source string.
|
---|
| 660 | * @param n Maximum number of bytes to duplicate.
|
---|
| 661 | *
|
---|
| 662 | * @return Duplicate string.
|
---|
| 663 | *
|
---|
| 664 | */
|
---|
| 665 | char *str_ndup(const char *src, size_t n)
|
---|
| 666 | {
|
---|
| 667 | size_t size = str_size(src);
|
---|
| 668 | if (size > n)
|
---|
| 669 | size = n;
|
---|
[a35b458] | 670 |
|
---|
[11b285d] | 671 | char *dest = nfmalloc(size + 1);
|
---|
[63e27ef] | 672 | assert(dest);
|
---|
[a35b458] | 673 |
|
---|
[abf09311] | 674 | str_ncpy(dest, size + 1, src, size);
|
---|
| 675 | return dest;
|
---|
| 676 | }
|
---|
| 677 |
|
---|
[0f06dbc] | 678 | /** Convert wide string to string.
|
---|
[b888d5f] | 679 | *
|
---|
[0f06dbc] | 680 | * Convert wide string @a src to string. The output is written to the buffer
|
---|
| 681 | * specified by @a dest and @a size. @a size must be non-zero and the string
|
---|
| 682 | * written will always be well-formed.
|
---|
[16da5f8e] | 683 | *
|
---|
[0f06dbc] | 684 | * @param dest Destination buffer.
|
---|
| 685 | * @param size Size of the destination buffer.
|
---|
| 686 | * @param src Source wide string.
|
---|
[16da5f8e] | 687 | */
|
---|
[0f06dbc] | 688 | void wstr_to_str(char *dest, size_t size, const wchar_t *src)
|
---|
[16da5f8e] | 689 | {
|
---|
[b888d5f] | 690 | wchar_t ch;
|
---|
[0f06dbc] | 691 | size_t src_idx;
|
---|
| 692 | size_t dest_off;
|
---|
| 693 |
|
---|
| 694 | /* There must be space for a null terminator in the buffer. */
|
---|
[63e27ef] | 695 | assert(size > 0);
|
---|
[0f06dbc] | 696 |
|
---|
| 697 | src_idx = 0;
|
---|
| 698 | dest_off = 0;
|
---|
[a35b458] | 699 |
|
---|
[b888d5f] | 700 | while ((ch = src[src_idx++]) != 0) {
|
---|
[0f06dbc] | 701 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
[b888d5f] | 702 | break;
|
---|
[16da5f8e] | 703 | }
|
---|
[0f06dbc] | 704 |
|
---|
| 705 | dest[dest_off] = '\0';
|
---|
[16da5f8e] | 706 | }
|
---|
| 707 |
|
---|
[20f1597] | 708 | /** Find first occurence of character in string.
|
---|
| 709 | *
|
---|
[b888d5f] | 710 | * @param str String to search.
|
---|
| 711 | * @param ch Character to look for.
|
---|
| 712 | *
|
---|
| 713 | * @return Pointer to character in @a str or NULL if not found.
|
---|
[20f1597] | 714 | *
|
---|
| 715 | */
|
---|
[dd2cfa7] | 716 | char *str_chr(const char *str, wchar_t ch)
|
---|
[20f1597] | 717 | {
|
---|
[b888d5f] | 718 | wchar_t acc;
|
---|
| 719 | size_t off = 0;
|
---|
[f2d2c7ba] | 720 | size_t last = 0;
|
---|
[a35b458] | 721 |
|
---|
[a7b1071] | 722 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) {
|
---|
[b888d5f] | 723 | if (acc == ch)
|
---|
[dd2cfa7] | 724 | return (char *) (str + last);
|
---|
[f2d2c7ba] | 725 | last = off;
|
---|
[20f1597] | 726 | }
|
---|
[a35b458] | 727 |
|
---|
[20f1597] | 728 | return NULL;
|
---|
| 729 | }
|
---|
| 730 |
|
---|
[b888d5f] | 731 | /** Insert a wide character into a wide string.
|
---|
| 732 | *
|
---|
| 733 | * Insert a wide character into a wide string at position
|
---|
| 734 | * @a pos. The characters after the position are shifted.
|
---|
| 735 | *
|
---|
| 736 | * @param str String to insert to.
|
---|
| 737 | * @param ch Character to insert to.
|
---|
| 738 | * @param pos Character index where to insert.
|
---|
[7c3fb9b] | 739 | * @param max_pos Characters in the buffer.
|
---|
[b888d5f] | 740 | *
|
---|
| 741 | * @return True if the insertion was sucessful, false if the position
|
---|
| 742 | * is out of bounds.
|
---|
| 743 | *
|
---|
| 744 | */
|
---|
[98000fb] | 745 | bool wstr_linsert(wchar_t *str, wchar_t ch, size_t pos, size_t max_pos)
|
---|
[b888d5f] | 746 | {
|
---|
[98000fb] | 747 | size_t len = wstr_length(str);
|
---|
[a35b458] | 748 |
|
---|
[b888d5f] | 749 | if ((pos > len) || (pos + 1 > max_pos))
|
---|
| 750 | return false;
|
---|
[a35b458] | 751 |
|
---|
[98000fb] | 752 | size_t i;
|
---|
[b888d5f] | 753 | for (i = len; i + 1 > pos; i--)
|
---|
| 754 | str[i + 1] = str[i];
|
---|
[a35b458] | 755 |
|
---|
[b888d5f] | 756 | str[pos] = ch;
|
---|
[a35b458] | 757 |
|
---|
[b888d5f] | 758 | return true;
|
---|
| 759 | }
|
---|
| 760 |
|
---|
| 761 | /** Remove a wide character from a wide string.
|
---|
| 762 | *
|
---|
| 763 | * Remove a wide character from a wide string at position
|
---|
| 764 | * @a pos. The characters after the position are shifted.
|
---|
| 765 | *
|
---|
| 766 | * @param str String to remove from.
|
---|
| 767 | * @param pos Character index to remove.
|
---|
| 768 | *
|
---|
| 769 | * @return True if the removal was sucessful, false if the position
|
---|
| 770 | * is out of bounds.
|
---|
| 771 | *
|
---|
| 772 | */
|
---|
[98000fb] | 773 | bool wstr_remove(wchar_t *str, size_t pos)
|
---|
[b888d5f] | 774 | {
|
---|
[98000fb] | 775 | size_t len = wstr_length(str);
|
---|
[a35b458] | 776 |
|
---|
[b888d5f] | 777 | if (pos >= len)
|
---|
| 778 | return false;
|
---|
[a35b458] | 779 |
|
---|
[98000fb] | 780 | size_t i;
|
---|
[b888d5f] | 781 | for (i = pos + 1; i <= len; i++)
|
---|
| 782 | str[i - 1] = str[i];
|
---|
[a35b458] | 783 |
|
---|
[b888d5f] | 784 | return true;
|
---|
| 785 | }
|
---|
| 786 |
|
---|
[30a5470] | 787 | /** Convert string to uint64_t (internal variant).
|
---|
| 788 | *
|
---|
| 789 | * @param nptr Pointer to string.
|
---|
| 790 | * @param endptr Pointer to the first invalid character is stored here.
|
---|
| 791 | * @param base Zero or number between 2 and 36 inclusive.
|
---|
| 792 | * @param neg Indication of unary minus is stored here.
|
---|
| 793 | * @apram result Result of the conversion.
|
---|
| 794 | *
|
---|
| 795 | * @return EOK if conversion was successful.
|
---|
| 796 | *
|
---|
| 797 | */
|
---|
[b7fd2a0] | 798 | static errno_t str_uint(const char *nptr, char **endptr, unsigned int base,
|
---|
[30a5470] | 799 | bool *neg, uint64_t *result)
|
---|
| 800 | {
|
---|
[63e27ef] | 801 | assert(endptr != NULL);
|
---|
| 802 | assert(neg != NULL);
|
---|
| 803 | assert(result != NULL);
|
---|
[a35b458] | 804 |
|
---|
[30a5470] | 805 | *neg = false;
|
---|
| 806 | const char *str = nptr;
|
---|
[a35b458] | 807 |
|
---|
[30a5470] | 808 | /* Ignore leading whitespace */
|
---|
| 809 | while (isspace(*str))
|
---|
| 810 | str++;
|
---|
[a35b458] | 811 |
|
---|
[30a5470] | 812 | if (*str == '-') {
|
---|
| 813 | *neg = true;
|
---|
| 814 | str++;
|
---|
| 815 | } else if (*str == '+')
|
---|
| 816 | str++;
|
---|
[a35b458] | 817 |
|
---|
[30a5470] | 818 | if (base == 0) {
|
---|
| 819 | /* Decode base if not specified */
|
---|
| 820 | base = 10;
|
---|
[a35b458] | 821 |
|
---|
[30a5470] | 822 | if (*str == '0') {
|
---|
| 823 | base = 8;
|
---|
| 824 | str++;
|
---|
[a35b458] | 825 |
|
---|
[30a5470] | 826 | switch (*str) {
|
---|
| 827 | case 'b':
|
---|
| 828 | case 'B':
|
---|
| 829 | base = 2;
|
---|
| 830 | str++;
|
---|
| 831 | break;
|
---|
| 832 | case 'o':
|
---|
| 833 | case 'O':
|
---|
| 834 | base = 8;
|
---|
| 835 | str++;
|
---|
| 836 | break;
|
---|
| 837 | case 'd':
|
---|
| 838 | case 'D':
|
---|
| 839 | case 't':
|
---|
| 840 | case 'T':
|
---|
| 841 | base = 10;
|
---|
| 842 | str++;
|
---|
| 843 | break;
|
---|
| 844 | case 'x':
|
---|
| 845 | case 'X':
|
---|
| 846 | base = 16;
|
---|
| 847 | str++;
|
---|
| 848 | break;
|
---|
[4ce914d4] | 849 | default:
|
---|
| 850 | str--;
|
---|
[30a5470] | 851 | }
|
---|
| 852 | }
|
---|
| 853 | } else {
|
---|
| 854 | /* Check base range */
|
---|
| 855 | if ((base < 2) || (base > 36)) {
|
---|
| 856 | *endptr = (char *) str;
|
---|
| 857 | return EINVAL;
|
---|
| 858 | }
|
---|
| 859 | }
|
---|
[a35b458] | 860 |
|
---|
[30a5470] | 861 | *result = 0;
|
---|
| 862 | const char *startstr = str;
|
---|
[a35b458] | 863 |
|
---|
[30a5470] | 864 | while (*str != 0) {
|
---|
| 865 | unsigned int digit;
|
---|
[a35b458] | 866 |
|
---|
[30a5470] | 867 | if ((*str >= 'a') && (*str <= 'z'))
|
---|
| 868 | digit = *str - 'a' + 10;
|
---|
| 869 | else if ((*str >= 'A') && (*str <= 'Z'))
|
---|
| 870 | digit = *str - 'A' + 10;
|
---|
| 871 | else if ((*str >= '0') && (*str <= '9'))
|
---|
| 872 | digit = *str - '0';
|
---|
| 873 | else
|
---|
| 874 | break;
|
---|
[a35b458] | 875 |
|
---|
[30a5470] | 876 | if (digit >= base)
|
---|
| 877 | break;
|
---|
[a35b458] | 878 |
|
---|
[30a5470] | 879 | uint64_t prev = *result;
|
---|
| 880 | *result = (*result) * base + digit;
|
---|
[a35b458] | 881 |
|
---|
[30a5470] | 882 | if (*result < prev) {
|
---|
| 883 | /* Overflow */
|
---|
| 884 | *endptr = (char *) str;
|
---|
| 885 | return EOVERFLOW;
|
---|
| 886 | }
|
---|
[a35b458] | 887 |
|
---|
[30a5470] | 888 | str++;
|
---|
| 889 | }
|
---|
[a35b458] | 890 |
|
---|
[30a5470] | 891 | if (str == startstr) {
|
---|
| 892 | /*
|
---|
| 893 | * No digits were decoded => first invalid character is
|
---|
| 894 | * the first character of the string.
|
---|
| 895 | */
|
---|
| 896 | str = nptr;
|
---|
| 897 | }
|
---|
[a35b458] | 898 |
|
---|
[30a5470] | 899 | *endptr = (char *) str;
|
---|
[a35b458] | 900 |
|
---|
[30a5470] | 901 | if (str == nptr)
|
---|
| 902 | return EINVAL;
|
---|
[a35b458] | 903 |
|
---|
[30a5470] | 904 | return EOK;
|
---|
| 905 | }
|
---|
| 906 |
|
---|
| 907 | /** Convert string to uint64_t.
|
---|
| 908 | *
|
---|
| 909 | * @param nptr Pointer to string.
|
---|
| 910 | * @param endptr If not NULL, pointer to the first invalid character
|
---|
| 911 | * is stored here.
|
---|
| 912 | * @param base Zero or number between 2 and 36 inclusive.
|
---|
| 913 | * @param strict Do not allow any trailing characters.
|
---|
[4ce914d4] | 914 | * @param result Result of the conversion.
|
---|
[30a5470] | 915 | *
|
---|
| 916 | * @return EOK if conversion was successful.
|
---|
| 917 | *
|
---|
| 918 | */
|
---|
[b7fd2a0] | 919 | errno_t str_uint64_t(const char *nptr, char **endptr, unsigned int base,
|
---|
[30a5470] | 920 | bool strict, uint64_t *result)
|
---|
| 921 | {
|
---|
[63e27ef] | 922 | assert(result != NULL);
|
---|
[a35b458] | 923 |
|
---|
[30a5470] | 924 | bool neg;
|
---|
| 925 | char *lendptr;
|
---|
[b7fd2a0] | 926 | errno_t ret = str_uint(nptr, &lendptr, base, &neg, result);
|
---|
[a35b458] | 927 |
|
---|
[30a5470] | 928 | if (endptr != NULL)
|
---|
| 929 | *endptr = (char *) lendptr;
|
---|
[a35b458] | 930 |
|
---|
[30a5470] | 931 | if (ret != EOK)
|
---|
| 932 | return ret;
|
---|
[a35b458] | 933 |
|
---|
[30a5470] | 934 | /* Do not allow negative values */
|
---|
| 935 | if (neg)
|
---|
| 936 | return EINVAL;
|
---|
[a35b458] | 937 |
|
---|
[7c3fb9b] | 938 | /*
|
---|
| 939 | * Check whether we are at the end of
|
---|
| 940 | * the string in strict mode
|
---|
| 941 | */
|
---|
[30a5470] | 942 | if ((strict) && (*lendptr != 0))
|
---|
| 943 | return EINVAL;
|
---|
[a35b458] | 944 |
|
---|
[30a5470] | 945 | return EOK;
|
---|
| 946 | }
|
---|
| 947 |
|
---|
[e535eeb] | 948 | void order_suffix(const uint64_t val, uint64_t *rv, char *suffix)
|
---|
| 949 | {
|
---|
[933cadf] | 950 | if (val > UINT64_C(10000000000000000000)) {
|
---|
| 951 | *rv = val / UINT64_C(1000000000000000000);
|
---|
[e535eeb] | 952 | *suffix = 'Z';
|
---|
[933cadf] | 953 | } else if (val > UINT64_C(1000000000000000000)) {
|
---|
| 954 | *rv = val / UINT64_C(1000000000000000);
|
---|
[e535eeb] | 955 | *suffix = 'E';
|
---|
[933cadf] | 956 | } else if (val > UINT64_C(1000000000000000)) {
|
---|
| 957 | *rv = val / UINT64_C(1000000000000);
|
---|
[e535eeb] | 958 | *suffix = 'T';
|
---|
[933cadf] | 959 | } else if (val > UINT64_C(1000000000000)) {
|
---|
| 960 | *rv = val / UINT64_C(1000000000);
|
---|
[e535eeb] | 961 | *suffix = 'G';
|
---|
[933cadf] | 962 | } else if (val > UINT64_C(1000000000)) {
|
---|
| 963 | *rv = val / UINT64_C(1000000);
|
---|
[e535eeb] | 964 | *suffix = 'M';
|
---|
[933cadf] | 965 | } else if (val > UINT64_C(1000000)) {
|
---|
| 966 | *rv = val / UINT64_C(1000);
|
---|
[e535eeb] | 967 | *suffix = 'k';
|
---|
| 968 | } else {
|
---|
| 969 | *rv = val;
|
---|
| 970 | *suffix = ' ';
|
---|
| 971 | }
|
---|
| 972 | }
|
---|
| 973 |
|
---|
[933cadf] | 974 | void bin_order_suffix(const uint64_t val, uint64_t *rv, const char **suffix,
|
---|
| 975 | bool fixed)
|
---|
| 976 | {
|
---|
| 977 | if (val > UINT64_C(1152921504606846976)) {
|
---|
| 978 | *rv = val / UINT64_C(1125899906842624);
|
---|
| 979 | *suffix = "EiB";
|
---|
| 980 | } else if (val > UINT64_C(1125899906842624)) {
|
---|
| 981 | *rv = val / UINT64_C(1099511627776);
|
---|
| 982 | *suffix = "TiB";
|
---|
| 983 | } else if (val > UINT64_C(1099511627776)) {
|
---|
| 984 | *rv = val / UINT64_C(1073741824);
|
---|
| 985 | *suffix = "GiB";
|
---|
| 986 | } else if (val > UINT64_C(1073741824)) {
|
---|
| 987 | *rv = val / UINT64_C(1048576);
|
---|
| 988 | *suffix = "MiB";
|
---|
| 989 | } else if (val > UINT64_C(1048576)) {
|
---|
| 990 | *rv = val / UINT64_C(1024);
|
---|
| 991 | *suffix = "KiB";
|
---|
| 992 | } else {
|
---|
| 993 | *rv = val;
|
---|
| 994 | if (fixed)
|
---|
| 995 | *suffix = "B ";
|
---|
| 996 | else
|
---|
| 997 | *suffix = "B";
|
---|
| 998 | }
|
---|
| 999 | }
|
---|
| 1000 |
|
---|
[16da5f8e] | 1001 | /** @}
|
---|
| 1002 | */
|
---|