Rev 4208 | Rev 4212 | Go to most recent revision | Only display areas with differences | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4208 | Rev 4209 | ||
---|---|---|---|
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 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 |
|
- | 40 | * represented as wchar_t. |
|
- | 41 | * |
|
- | 42 | * Strings have the following metrics: |
|
- | 43 | * |
|
- | 44 | * Metric Abbrev. Meaning |
|
- | 45 | * ------ ------ ------- |
|
- | 46 | * size n Number of bytes the string is encoded into, excluding |
|
- | 47 | * the null terminator. |
|
- | 48 | * length l The number of characters in the string, excluding |
|
- | 49 | * the null terminator. |
|
- | 50 | * width w The number of character cells the string takes up on a |
|
- | 51 | * monospace display. |
|
- | 52 | * |
|
- | 53 | * Naming scheme: |
|
- | 54 | * |
|
- | 55 | * chr_xxx operate on characters |
|
- | 56 | * str_xxx operate on strings |
|
- | 57 | * wstr_xxx operate on wide strings |
|
- | 58 | * |
|
- | 59 | * [w]str_[n|l|w]xxx operate on a prefix limited by size, length |
|
- | 60 | * or width. |
|
36 | */ |
61 | */ |
37 | 62 | ||
38 | #include <string.h> |
63 | #include <string.h> |
39 | #include <print.h> |
64 | #include <print.h> |
40 | #include <cpu.h> |
65 | #include <cpu.h> |
41 | #include <arch/asm.h> |
66 | #include <arch/asm.h> |
42 | #include <arch.h> |
67 | #include <arch.h> |
43 | #include <errno.h> |
68 | #include <errno.h> |
44 | #include <console/kconsole.h> |
69 | #include <console/kconsole.h> |
45 | 70 | ||
46 | char invalch = '?'; |
71 | char invalch = '?'; |
47 | 72 | ||
48 | /** Byte mask consisting of lowest @n bits (out of eight). */ |
73 | /** Byte mask consisting of lowest @n bits (out of eight). */ |
49 | #define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1)) |
74 | #define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1)) |
50 | 75 | ||
51 | /** Byte mask consisting of lowest @n bits (out of 32). */ |
76 | /** Byte mask consisting of lowest @n bits (out of 32). */ |
52 | #define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1)) |
77 | #define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1)) |
53 | 78 | ||
54 | /** Byte mask consisting of highest @n bits (out of eight). */ |
79 | /** Byte mask consisting of highest @n bits (out of eight). */ |
55 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
80 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
56 | 81 | ||
57 | /** Number of data bits in a UTF-8 continuation byte. */ |
82 | /** Number of data bits in a UTF-8 continuation byte. */ |
58 | #define CONT_BITS 6 |
83 | #define CONT_BITS 6 |
59 | 84 | ||
60 | /** Decode a single character from a substring. |
85 | /** Decode a single character from a substring. |
61 | * |
86 | * |
62 | * Decode a single character from a substring of size @a sz. Decoding starts |
87 | * Decode a single character from a substring of size @a sz. Decoding starts |
63 | * at @a offset and this offset is moved to the beginning of the next |
88 | * at @a offset and this offset is moved to the beginning of the next |
64 | * character. In case of decoding error, offset generally advances at least |
89 | * character. In case of decoding error, offset generally advances at least |
65 | * by one. However, offset is never moved beyond (str + sz). |
90 | * by one. However, offset is never moved beyond (str + sz). |
66 | * |
91 | * |
67 | * @param str String (not necessarily NULL-terminated). |
92 | * @param str String (not necessarily NULL-terminated). |
68 | * @param index Index (counted in plain characters) where to start |
93 | * @param index Index (counted in plain characters) where to start |
69 | * the decoding. |
94 | * the decoding. |
70 | * @param limit Size of the substring. |
95 | * @param limit Size of the substring. |
71 | * |
96 | * |
72 | * @return Value of decoded character or '?' on decoding error. |
97 | * @return Value of decoded character or '?' on decoding error. |
73 | */ |
98 | */ |
74 | wchar_t chr_decode(const char *str, size_t *offset, size_t sz) |
99 | wchar_t chr_decode(const char *str, size_t *offset, size_t sz) |
75 | { |
100 | { |
76 | uint8_t b0, b; /* Bytes read from str. */ |
101 | uint8_t b0, b; /* Bytes read from str. */ |
77 | wchar_t ch; |
102 | wchar_t ch; |
78 | 103 | ||
79 | int b0_bits; /* Data bits in first byte. */ |
104 | int b0_bits; /* Data bits in first byte. */ |
80 | int cbytes; /* Number of continuation bytes. */ |
105 | int cbytes; /* Number of continuation bytes. */ |
81 | 106 | ||
82 | if (*offset + 1 > sz) |
107 | if (*offset + 1 > sz) |
83 | return invalch; |
108 | return invalch; |
84 | 109 | ||
85 | b0 = (uint8_t) str[(*offset)++]; |
110 | b0 = (uint8_t) str[(*offset)++]; |
86 | 111 | ||
87 | /* Determine code length. */ |
112 | /* Determine code length. */ |
88 | 113 | ||
89 | if ((b0 & 0x80) == 0) { |
114 | if ((b0 & 0x80) == 0) { |
90 | /* 0xxxxxxx (Plain ASCII) */ |
115 | /* 0xxxxxxx (Plain ASCII) */ |
91 | b0_bits = 7; |
116 | b0_bits = 7; |
92 | cbytes = 0; |
117 | cbytes = 0; |
93 | } else if ((b0 & 0xe0) == 0xc0) { |
118 | } else if ((b0 & 0xe0) == 0xc0) { |
94 | /* 110xxxxx 10xxxxxx */ |
119 | /* 110xxxxx 10xxxxxx */ |
95 | b0_bits = 5; |
120 | b0_bits = 5; |
96 | cbytes = 1; |
121 | cbytes = 1; |
97 | } else if ((b0 & 0xf0) == 0xe0) { |
122 | } else if ((b0 & 0xf0) == 0xe0) { |
98 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
123 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
99 | b0_bits = 4; |
124 | b0_bits = 4; |
100 | cbytes = 2; |
125 | cbytes = 2; |
101 | } else if ((b0 & 0xf8) == 0xf0) { |
126 | } else if ((b0 & 0xf8) == 0xf0) { |
102 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
127 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
103 | b0_bits = 3; |
128 | b0_bits = 3; |
104 | cbytes = 3; |
129 | cbytes = 3; |
105 | } else { |
130 | } else { |
106 | /* 10xxxxxx -- unexpected continuation byte. */ |
131 | /* 10xxxxxx -- unexpected continuation byte. */ |
107 | return invalch; |
132 | return invalch; |
108 | } |
133 | } |
109 | 134 | ||
110 | if (*offset + cbytes > sz) { |
135 | if (*offset + cbytes > sz) { |
111 | return invalch; |
136 | return invalch; |
112 | } |
137 | } |
113 | 138 | ||
114 | ch = b0 & LO_MASK_8(b0_bits); |
139 | ch = b0 & LO_MASK_8(b0_bits); |
115 | 140 | ||
116 | /* Decode continuation bytes. */ |
141 | /* Decode continuation bytes. */ |
117 | while (cbytes > 0) { |
142 | while (cbytes > 0) { |
118 | b = (uint8_t) str[(*offset)++]; |
143 | b = (uint8_t) str[(*offset)++]; |
119 | 144 | ||
120 | /* Must be 10xxxxxx. */ |
145 | /* Must be 10xxxxxx. */ |
121 | if ((b & 0xc0) != 0x80) { |
146 | if ((b & 0xc0) != 0x80) { |
122 | return invalch; |
147 | return invalch; |
123 | } |
148 | } |
124 | 149 | ||
125 | /* Shift data bits to ch. */ |
150 | /* Shift data bits to ch. */ |
126 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
151 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
127 | --cbytes; |
152 | --cbytes; |
128 | } |
153 | } |
129 | 154 | ||
130 | return ch; |
155 | return ch; |
131 | } |
156 | } |
132 | 157 | ||
133 | /** Encode a single character to string representation. |
158 | /** Encode a single character to string representation. |
134 | * |
159 | * |
135 | * Encode a single character to string representation (i.e. UTF-8) and store |
160 | * 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 |
161 | * 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. |
162 | * is moved to the position where the next character can be written to. |
138 | * |
163 | * |
139 | * @param ch Input character. |
164 | * @param ch Input character. |
140 | * @param str Output buffer. |
165 | * @param str Output buffer. |
141 | * @param offset Offset (in bytes) where to start writing. |
166 | * @param offset Offset (in bytes) where to start writing. |
142 | * @param sz Size of the output buffer. |
167 | * @param sz Size of the output buffer. |
143 | * |
168 | * |
144 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
169 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
145 | * was not enough space in the output buffer or EINVAL if the character |
170 | * was not enough space in the output buffer or EINVAL if the character |
146 | * code was invalid. |
171 | * code was invalid. |
147 | */ |
172 | */ |
148 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t sz) |
173 | int chr_encode(wchar_t ch, char *str, size_t *offset, size_t sz) |
149 | { |
174 | { |
150 | uint32_t cc; /* Unsigned version of ch. */ |
175 | uint32_t cc; /* Unsigned version of ch. */ |
151 | 176 | ||
152 | int cbytes; /* Number of continuation bytes. */ |
177 | int cbytes; /* Number of continuation bytes. */ |
153 | int b0_bits; /* Number of data bits in first byte. */ |
178 | int b0_bits; /* Number of data bits in first byte. */ |
154 | int i; |
179 | int i; |
155 | 180 | ||
156 | if (*offset >= sz) |
181 | if (*offset >= sz) |
157 | return EOVERFLOW; |
182 | return EOVERFLOW; |
158 | 183 | ||
159 | if (ch < 0) |
184 | if (ch < 0) |
160 | return EINVAL; |
185 | return EINVAL; |
161 | 186 | ||
162 | /* Bit operations should only be done on unsigned numbers. */ |
187 | /* Bit operations should only be done on unsigned numbers. */ |
163 | cc = (uint32_t) ch; |
188 | cc = (uint32_t) ch; |
164 | 189 | ||
165 | /* Determine how many continuation bytes are needed. */ |
190 | /* Determine how many continuation bytes are needed. */ |
166 | if ((cc & ~LO_MASK_32(7)) == 0) { |
191 | if ((cc & ~LO_MASK_32(7)) == 0) { |
167 | b0_bits = 7; |
192 | b0_bits = 7; |
168 | cbytes = 0; |
193 | cbytes = 0; |
169 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
194 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
170 | b0_bits = 5; |
195 | b0_bits = 5; |
171 | cbytes = 1; |
196 | cbytes = 1; |
172 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
197 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
173 | b0_bits = 4; |
198 | b0_bits = 4; |
174 | cbytes = 2; |
199 | cbytes = 2; |
175 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
200 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
176 | b0_bits = 3; |
201 | b0_bits = 3; |
177 | cbytes = 3; |
202 | cbytes = 3; |
178 | } else { |
203 | } else { |
179 | /* Codes longer than 21 bits are not supported. */ |
204 | /* Codes longer than 21 bits are not supported. */ |
180 | return EINVAL; |
205 | return EINVAL; |
181 | } |
206 | } |
182 | 207 | ||
183 | /* Check for available space in buffer. */ |
208 | /* Check for available space in buffer. */ |
184 | if (*offset + cbytes >= sz) |
209 | if (*offset + cbytes >= sz) |
185 | return EOVERFLOW; |
210 | return EOVERFLOW; |
186 | 211 | ||
187 | /* Encode continuation bytes. */ |
212 | /* Encode continuation bytes. */ |
188 | for (i = cbytes; i > 0; --i) { |
213 | for (i = cbytes; i > 0; --i) { |
189 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
214 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
190 | cc = cc >> CONT_BITS; |
215 | cc = cc >> CONT_BITS; |
191 | } |
216 | } |
192 | 217 | ||
193 | /* Encode first byte. */ |
218 | /* Encode first byte. */ |
194 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
219 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
195 | 220 | ||
196 | /* Advance offset. */ |
221 | /* Advance offset. */ |
197 | *offset += (1 + cbytes); |
222 | *offset += (1 + cbytes); |
198 | 223 | ||
199 | return EOK; |
224 | return EOK; |
200 | } |
225 | } |
201 | 226 | ||
- | 227 | /** Get display width of character. |
|
- | 228 | * |
|
- | 229 | * @param ch The character. |
|
- | 230 | * @return Character width in display cells. |
|
- | 231 | */ |
|
- | 232 | count_t chr_width(wchar_t ch) |
|
- | 233 | { |
|
- | 234 | return 1; |
|
- | 235 | } |
|
- | 236 | ||
202 | /** Get size of string, with length limit. |
237 | /** Get size of string, with length limit. |
203 | * |
238 | * |
204 | * Get the number of bytes which are used by up to @a max_len first |
239 | * Get the number of bytes which are used by up to @a max_len first |
205 | * characters in the string @a str. If @a max_len is greater than |
240 | * characters in the string @a str. If @a max_len is greater than |
206 | * the length of @a str, the entire string is measured. |
241 | * the length of @a str, the entire string is measured. |
207 | * |
242 | * |
208 | * @param str String to consider. |
243 | * @param str String to consider. |
209 | * @param count Maximum number of characters to measure. |
244 | * @param count Maximum number of characters to measure. |
210 | * |
245 | * |
211 | * @return Number of bytes used by the characters. |
246 | * @return Number of bytes used by the characters. |
212 | */ |
247 | */ |
213 | size_t str_lsize(const char *str, count_t max_len) |
248 | size_t str_lsize(const char *str, count_t max_len) |
214 | { |
249 | { |
215 | count_t len = 0; |
250 | count_t len = 0; |
216 | size_t cur = 0; |
251 | size_t cur = 0; |
217 | size_t prev; |
252 | size_t prev; |
218 | wchar_t ch; |
253 | wchar_t ch; |
219 | 254 | ||
220 | while (true) { |
255 | while (true) { |
221 | prev = cur; |
256 | prev = cur; |
222 | if (len >= max_len) |
257 | if (len >= max_len) |
223 | break; |
258 | break; |
224 | ch = chr_decode(str, &cur, UTF8_NO_LIMIT); |
259 | ch = chr_decode(str, &cur, UTF8_NO_LIMIT); |
225 | if (ch == '\0') break; |
260 | if (ch == '\0') break; |
226 | 261 | ||
227 | len++; |
262 | len++; |
228 | } |
263 | } |
229 | 264 | ||
230 | return prev; |
265 | return prev; |
231 | } |
266 | } |
232 | 267 | ||
- | 268 | /** Get size of string, with width limit. |
|
- | 269 | * |
|
- | 270 | * Get the number of bytes which are used by the longest prefix of @a str |
|
- | 271 | * that can fit into @a max_width display cells. |
|
- | 272 | * |
|
- | 273 | * @param str String to consider. |
|
- | 274 | * @param count Maximum number of display cells. |
|
- | 275 | * |
|
- | 276 | * @return Number of bytes used by the characters that fit. |
|
- | 277 | */ |
|
- | 278 | size_t str_wsize(const char *str, count_t max_width) |
|
- | 279 | { |
|
- | 280 | count_t width = 0; |
|
- | 281 | size_t cur = 0; |
|
- | 282 | size_t prev; |
|
- | 283 | wchar_t ch; |
|
- | 284 | ||
- | 285 | while (true) { |
|
- | 286 | prev = cur; |
|
- | 287 | if (width >= max_width) |
|
- | 288 | break; |
|
- | 289 | ch = chr_decode(str, &cur, UTF8_NO_LIMIT); |
|
- | 290 | if (ch == '\0') break; |
|
- | 291 | ||
- | 292 | width += chr_width(ch); |
|
- | 293 | } |
|
- | 294 | ||
- | 295 | return prev; |
|
- | 296 | } |
|
- | 297 | ||
- | 298 | ||
- | 299 | /** Get length of wide string, with width limit. |
|
- | 300 | * |
|
- | 301 | * Get the number of characters in a wide string that can fit into @a max_width |
|
- | 302 | * display cells. |
|
- | 303 | * |
|
- | 304 | * @param wstr Wide string to consider. |
|
- | 305 | * @param count Maximum number of display cells. |
|
- | 306 | * |
|
- | 307 | * @return Number of bytes used by the characters that fit. |
|
- | 308 | */ |
|
- | 309 | count_t wstr_wlength(const wchar_t *wstr, count_t max_width) |
|
- | 310 | { |
|
- | 311 | count_t width = 0; |
|
- | 312 | index_t cur = 0; |
|
- | 313 | ||
- | 314 | while (true) { |
|
- | 315 | if (width >= max_width) |
|
- | 316 | break; |
|
- | 317 | if (wstr[cur] == '\0') break; |
|
- | 318 | ||
- | 319 | width += chr_width(wstr[cur]); |
|
- | 320 | ++cur; |
|
- | 321 | } |
|
- | 322 | ||
- | 323 | return (count_t) cur; |
|
- | 324 | } |
|
- | 325 | ||
233 | /** Check whether character is plain ASCII. |
326 | /** Check whether character is plain ASCII. |
234 | * |
327 | * |
235 | * @return True if character is plain ASCII. |
328 | * @return True if character is plain ASCII. |
236 | * |
329 | * |
237 | */ |
330 | */ |
238 | bool ascii_check(const wchar_t ch) |
331 | bool ascii_check(const wchar_t ch) |
239 | { |
332 | { |
240 | if ((ch >= 0) && (ch <= 127)) |
333 | if ((ch >= 0) && (ch <= 127)) |
241 | return true; |
334 | return true; |
242 | 335 | ||
243 | return false; |
336 | return false; |
244 | } |
337 | } |
245 | 338 | ||
246 | /** Check whether character is Unicode. |
339 | /** Check whether character is Unicode. |
247 | * |
340 | * |
248 | * @return True if character is valid Unicode code point. |
341 | * @return True if character is valid Unicode code point. |
249 | */ |
342 | */ |
250 | bool unicode_check(const wchar_t ch) |
343 | bool unicode_check(const wchar_t ch) |
251 | { |
344 | { |
252 | if ((ch >= 0) && (ch <= 1114111)) |
345 | if ((ch >= 0) && (ch <= 1114111)) |
253 | return true; |
346 | return true; |
254 | 347 | ||
255 | return false; |
348 | return false; |
256 | } |
349 | } |
257 | 350 | ||
258 | /** Return number of bytes the string occupies. |
351 | /** Return number of bytes the string occupies. |
259 | * |
352 | * |
260 | * @param str A string. |
353 | * @param str A string. |
261 | * @return Number of bytes in @a str excluding the null terminator. |
354 | * @return Number of bytes in @a str excluding the null terminator. |
262 | */ |
355 | */ |
263 | size_t str_size(const char *str) |
356 | size_t str_size(const char *str) |
264 | { |
357 | { |
265 | size_t size; |
358 | size_t size; |
266 | 359 | ||
267 | size = 0; |
360 | size = 0; |
268 | while (*str++ != '\0') |
361 | while (*str++ != '\0') |
269 | ++size; |
362 | ++size; |
270 | 363 | ||
271 | return size; |
364 | return size; |
272 | } |
365 | } |
273 | 366 | ||
274 | /** Return number of characters in a string. |
367 | /** Return number of characters in a string. |
275 | * |
368 | * |
276 | * @param str NULL-terminated string. |
369 | * @param str NULL-terminated string. |
277 | * @return Number of characters in string. |
370 | * @return Number of characters in string. |
278 | */ |
371 | */ |
279 | count_t str_length(const char *str) |
372 | count_t str_length(const char *str) |
280 | { |
373 | { |
281 | count_t len = 0; |
374 | count_t len = 0; |
282 | size_t offset = 0; |
375 | size_t offset = 0; |
283 | 376 | ||
284 | while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) { |
377 | while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) { |
285 | len++; |
378 | len++; |
286 | } |
379 | } |
287 | 380 | ||
288 | return len; |
381 | return len; |
289 | } |
382 | } |
290 | 383 | ||
291 | /** Return number of characters in a wide string. |
384 | /** Return number of characters in a wide string. |
292 | * |
385 | * |
293 | * @param str NULL-terminated wide string. |
386 | * @param str NULL-terminated wide string. |
294 | * @return Number of characters in @a str. |
387 | * @return Number of characters in @a str. |
295 | */ |
388 | */ |
296 | count_t wstr_length(const wchar_t *wstr) |
389 | count_t wstr_length(const wchar_t *wstr) |
297 | { |
390 | { |
298 | count_t len; |
391 | count_t len; |
299 | 392 | ||
300 | len = 0; |
393 | len = 0; |
301 | while (*wstr++ != '\0') |
394 | while (*wstr++ != '\0') |
302 | ++len; |
395 | ++len; |
303 | 396 | ||
304 | return len; |
397 | return len; |
305 | } |
398 | } |
306 | 399 | ||
307 | /** Compare two NULL terminated strings |
400 | /** Compare two NULL terminated strings |
308 | * |
401 | * |
309 | * Do a char-by-char comparison of two NULL terminated strings. |
402 | * Do a char-by-char comparison of two NULL terminated strings. |
310 | * The strings are considered equal iff they consist of the same |
403 | * The strings are considered equal iff they consist of the same |
311 | * characters on the minimum of their lengths. |
404 | * characters on the minimum of their lengths. |
312 | * |
405 | * |
313 | * @param src First string to compare. |
406 | * @param src First string to compare. |
314 | * @param dst Second string to compare. |
407 | * @param dst Second string to compare. |
315 | * |
408 | * |
316 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
409 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
317 | * |
410 | * |
318 | */ |
411 | */ |
319 | int strcmp(const char *src, const char *dst) |
412 | int strcmp(const char *src, const char *dst) |
320 | { |
413 | { |
321 | for (; *src && *dst; src++, dst++) { |
414 | for (; *src && *dst; src++, dst++) { |
322 | if (*src < *dst) |
415 | if (*src < *dst) |
323 | return -1; |
416 | return -1; |
324 | if (*src > *dst) |
417 | if (*src > *dst) |
325 | return 1; |
418 | return 1; |
326 | } |
419 | } |
327 | if (*src == *dst) |
420 | if (*src == *dst) |
328 | return 0; |
421 | return 0; |
329 | 422 | ||
330 | if (!*src) |
423 | if (!*src) |
331 | return -1; |
424 | return -1; |
332 | 425 | ||
333 | return 1; |
426 | return 1; |
334 | } |
427 | } |
335 | 428 | ||
336 | 429 | ||
337 | /** Compare two NULL terminated strings |
430 | /** Compare two NULL terminated strings |
338 | * |
431 | * |
339 | * Do a char-by-char comparison of two NULL terminated strings. |
432 | * Do a char-by-char comparison of two NULL terminated strings. |
340 | * The strings are considered equal iff they consist of the same |
433 | * The strings are considered equal iff they consist of the same |
341 | * characters on the minimum of their lengths and specified maximal |
434 | * characters on the minimum of their lengths and specified maximal |
342 | * length. |
435 | * length. |
343 | * |
436 | * |
344 | * @param src First string to compare. |
437 | * @param src First string to compare. |
345 | * @param dst Second string to compare. |
438 | * @param dst Second string to compare. |
346 | * @param len Maximal length for comparison. |
439 | * @param len Maximal length for comparison. |
347 | * |
440 | * |
348 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
441 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
349 | */ |
442 | */ |
350 | int strncmp(const char *src, const char *dst, size_t len) |
443 | int strncmp(const char *src, const char *dst, size_t len) |
351 | { |
444 | { |
352 | unsigned int i; |
445 | unsigned int i; |
353 | 446 | ||
354 | for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) { |
447 | for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) { |
355 | if (*src < *dst) |
448 | if (*src < *dst) |
356 | return -1; |
449 | return -1; |
357 | 450 | ||
358 | if (*src > *dst) |
451 | if (*src > *dst) |
359 | return 1; |
452 | return 1; |
360 | } |
453 | } |
361 | 454 | ||
362 | if (i == len || *src == *dst) |
455 | if (i == len || *src == *dst) |
363 | return 0; |
456 | return 0; |
364 | 457 | ||
365 | if (!*src) |
458 | if (!*src) |
366 | return -1; |
459 | return -1; |
367 | 460 | ||
368 | return 1; |
461 | return 1; |
369 | } |
462 | } |
370 | 463 | ||
371 | 464 | ||
372 | 465 | ||
373 | /** Copy NULL terminated string. |
466 | /** Copy NULL terminated string. |
374 | * |
467 | * |
375 | * Copy at most 'len' characters from string 'src' to 'dest'. |
468 | * Copy at most 'len' characters from string 'src' to 'dest'. |
376 | * If 'src' is shorter than 'len', '\0' is inserted behind the |
469 | * If 'src' is shorter than 'len', '\0' is inserted behind the |
377 | * last copied character. |
470 | * last copied character. |
378 | * |
471 | * |
379 | * @param src Source string. |
472 | * @param src Source string. |
380 | * @param dest Destination buffer. |
473 | * @param dest Destination buffer. |
381 | * @param len Size of destination buffer. |
474 | * @param len Size of destination buffer. |
382 | */ |
475 | */ |
383 | void strncpy(char *dest, const char *src, size_t len) |
476 | void strncpy(char *dest, const char *src, size_t len) |
384 | { |
477 | { |
385 | unsigned int i; |
478 | unsigned int i; |
386 | 479 | ||
387 | for (i = 0; i < len; i++) { |
480 | for (i = 0; i < len; i++) { |
388 | if (!(dest[i] = src[i])) |
481 | if (!(dest[i] = src[i])) |
389 | return; |
482 | return; |
390 | } |
483 | } |
391 | 484 | ||
392 | dest[i - 1] = '\0'; |
485 | dest[i - 1] = '\0'; |
393 | } |
486 | } |
394 | 487 | ||
395 | /** Find first occurence of character in string. |
488 | /** Find first occurence of character in string. |
396 | * |
489 | * |
397 | * @param s String to search. |
490 | * @param s String to search. |
398 | * @param i Character to look for. |
491 | * @param i Character to look for. |
399 | * |
492 | * |
400 | * @return Pointer to character in @a s or NULL if not found. |
493 | * @return Pointer to character in @a s or NULL if not found. |
401 | */ |
494 | */ |
402 | extern char *strchr(const char *s, int i) |
495 | extern char *strchr(const char *s, int i) |
403 | { |
496 | { |
404 | while (*s != '\0') { |
497 | while (*s != '\0') { |
405 | if (*s == i) |
498 | if (*s == i) |
406 | return (char *) s; |
499 | return (char *) s; |
407 | ++s; |
500 | ++s; |
408 | } |
501 | } |
409 | 502 | ||
410 | return NULL; |
503 | return NULL; |
411 | } |
504 | } |
412 | 505 | ||
413 | /** @} |
506 | /** @} |
414 | */ |
507 | */ |
415 | 508 |