Rev 4264 | Rev 4266 | Go to most recent revision | Only display areas with differences | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4264 | Rev 4265 | ||
---|---|---|---|
1 | /* |
1 | /* |
2 | * Copyright (c) 2005 Martin Decky |
2 | * Copyright (c) 2005 Martin Decky |
3 | * Copyright (c) 2008 Jiri Svoboda |
3 | * Copyright (c) 2008 Jiri Svoboda |
4 | * All rights reserved. |
4 | * All rights reserved. |
5 | * |
5 | * |
6 | * Redistribution and use in source and binary forms, with or without |
6 | * Redistribution and use in source and binary forms, with or without |
7 | * modification, are permitted provided that the following conditions |
7 | * modification, are permitted provided that the following conditions |
8 | * are met: |
8 | * are met: |
9 | * |
9 | * |
10 | * - Redistributions of source code must retain the above copyright |
10 | * - Redistributions of source code must retain the above copyright |
11 | * notice, this list of conditions and the following disclaimer. |
11 | * notice, this list of conditions and the following disclaimer. |
12 | * - Redistributions in binary form must reproduce the above copyright |
12 | * - Redistributions in binary form must reproduce the above copyright |
13 | * notice, this list of conditions and the following disclaimer in the |
13 | * notice, this list of conditions and the following disclaimer in the |
14 | * documentation and/or other materials provided with the distribution. |
14 | * documentation and/or other materials provided with the distribution. |
15 | * - The name of the author may not be used to endorse or promote products |
15 | * - The name of the author may not be used to endorse or promote products |
16 | * derived from this software without specific prior written permission. |
16 | * derived from this software without specific prior written permission. |
17 | * |
17 | * |
18 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR |
18 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR |
19 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
19 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
20 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. |
20 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. |
21 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, |
21 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, |
22 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
22 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
23 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
23 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
24 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
24 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
25 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
25 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
26 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
26 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
27 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
27 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
28 | */ |
28 | */ |
29 | 29 | ||
30 | /** @addtogroup libc |
30 | /** @addtogroup libc |
31 | * @{ |
31 | * @{ |
32 | */ |
32 | */ |
33 | /** @file |
33 | /** @file |
34 | */ |
34 | */ |
35 | 35 | ||
36 | #include <string.h> |
36 | #include <string.h> |
37 | #include <stdlib.h> |
37 | #include <stdlib.h> |
38 | #include <limits.h> |
38 | #include <limits.h> |
39 | #include <ctype.h> |
39 | #include <ctype.h> |
40 | #include <malloc.h> |
40 | #include <malloc.h> |
41 | #include <errno.h> |
41 | #include <errno.h> |
42 | #include <align.h> |
42 | #include <align.h> |
43 | #include <string.h> |
43 | #include <string.h> |
44 | 44 | ||
45 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
45 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
46 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
46 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
47 | 47 | ||
48 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
48 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
49 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
49 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
50 | 50 | ||
51 | /** Byte mask consisting of highest @n bits (out of 8) */ |
51 | /** Byte mask consisting of highest @n bits (out of 8) */ |
52 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
52 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
53 | 53 | ||
54 | /** Number of data bits in a UTF-8 continuation byte */ |
54 | /** Number of data bits in a UTF-8 continuation byte */ |
55 | #define CONT_BITS 6 |
55 | #define CONT_BITS 6 |
56 | 56 | ||
57 | /** Decode a single character from a string. |
57 | /** Decode a single character from a string. |
58 | * |
58 | * |
59 | * Decode a single character from a string of size @a size. Decoding starts |
59 | * Decode a single character from a string of size @a size. Decoding starts |
60 | * at @a offset and this offset is moved to the beginning of the next |
60 | * at @a offset and this offset is moved to the beginning of the next |
61 | * character. In case of decoding error, offset generally advances at least |
61 | * character. In case of decoding error, offset generally advances at least |
62 | * by one. However, offset is never moved beyond size. |
62 | * by one. However, offset is never moved beyond size. |
63 | * |
63 | * |
64 | * @param str String (not necessarily NULL-terminated). |
64 | * @param str String (not necessarily NULL-terminated). |
65 | * @param offset Byte offset in string where to start decoding. |
65 | * @param offset Byte offset in string where to start decoding. |
66 | * @param size Size of the string (in bytes). |
66 | * @param size Size of the string (in bytes). |
67 | * |
67 | * |
68 | * @return Value of decoded character, U_SPECIAL on decoding error or |
68 | * @return Value of decoded character, U_SPECIAL on decoding error or |
69 | * NULL if attempt to decode beyond @a size. |
69 | * NULL if attempt to decode beyond @a size. |
70 | * |
70 | * |
71 | */ |
71 | */ |
72 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
72 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
73 | { |
73 | { |
74 | if (*offset + 1 > size) |
74 | if (*offset + 1 > size) |
75 | return 0; |
75 | return 0; |
76 | 76 | ||
77 | /* First byte read from string */ |
77 | /* First byte read from string */ |
78 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
78 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
79 | 79 | ||
80 | /* Determine code length */ |
80 | /* Determine code length */ |
81 | 81 | ||
82 | unsigned int b0_bits; /* Data bits in first byte */ |
82 | unsigned int b0_bits; /* Data bits in first byte */ |
83 | unsigned int cbytes; /* Number of continuation bytes */ |
83 | unsigned int cbytes; /* Number of continuation bytes */ |
84 | 84 | ||
85 | if ((b0 & 0x80) == 0) { |
85 | if ((b0 & 0x80) == 0) { |
86 | /* 0xxxxxxx (Plain ASCII) */ |
86 | /* 0xxxxxxx (Plain ASCII) */ |
87 | b0_bits = 7; |
87 | b0_bits = 7; |
88 | cbytes = 0; |
88 | cbytes = 0; |
89 | } else if ((b0 & 0xe0) == 0xc0) { |
89 | } else if ((b0 & 0xe0) == 0xc0) { |
90 | /* 110xxxxx 10xxxxxx */ |
90 | /* 110xxxxx 10xxxxxx */ |
91 | b0_bits = 5; |
91 | b0_bits = 5; |
92 | cbytes = 1; |
92 | cbytes = 1; |
93 | } else if ((b0 & 0xf0) == 0xe0) { |
93 | } else if ((b0 & 0xf0) == 0xe0) { |
94 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
94 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
95 | b0_bits = 4; |
95 | b0_bits = 4; |
96 | cbytes = 2; |
96 | cbytes = 2; |
97 | } else if ((b0 & 0xf8) == 0xf0) { |
97 | } else if ((b0 & 0xf8) == 0xf0) { |
98 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
98 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
99 | b0_bits = 3; |
99 | b0_bits = 3; |
100 | cbytes = 3; |
100 | cbytes = 3; |
101 | } else { |
101 | } else { |
102 | /* 10xxxxxx -- unexpected continuation byte */ |
102 | /* 10xxxxxx -- unexpected continuation byte */ |
103 | return U_SPECIAL; |
103 | return U_SPECIAL; |
104 | } |
104 | } |
105 | 105 | ||
106 | if (*offset + cbytes > size) |
106 | if (*offset + cbytes > size) |
107 | return U_SPECIAL; |
107 | return U_SPECIAL; |
108 | 108 | ||
109 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
109 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
110 | 110 | ||
111 | /* Decode continuation bytes */ |
111 | /* Decode continuation bytes */ |
112 | while (cbytes > 0) { |
112 | while (cbytes > 0) { |
113 | uint8_t b = (uint8_t) str[(*offset)++]; |
113 | uint8_t b = (uint8_t) str[(*offset)++]; |
114 | 114 | ||
115 | /* Must be 10xxxxxx */ |
115 | /* Must be 10xxxxxx */ |
116 | if ((b & 0xc0) != 0x80) |
116 | if ((b & 0xc0) != 0x80) |
117 | return U_SPECIAL; |
117 | return U_SPECIAL; |
118 | 118 | ||
119 | /* Shift data bits to ch */ |
119 | /* Shift data bits to ch */ |
120 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
120 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
121 | cbytes--; |
121 | cbytes--; |
122 | } |
122 | } |
123 | 123 | ||
124 | return ch; |
124 | return ch; |
125 | } |
125 | } |
126 | 126 | ||
127 | /** Encode a single character to string representation. |
127 | /** Encode a single character to string representation. |
128 | * |
128 | * |
129 | * Encode a single character to string representation (i.e. UTF-8) and store |
129 | * Encode a single character to string representation (i.e. UTF-8) and store |
130 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
130 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
131 | * is moved to the position where the next character can be written to. |
131 | * is moved to the position where the next character can be written to. |
132 | * |
132 | * |
133 | * @param ch Input character. |
133 | * @param ch Input character. |
134 | * @param str Output buffer. |
134 | * @param str Output buffer. |
135 | * @param offset Byte offset where to start writing. |
135 | * @param offset Byte offset where to start writing. |
136 | * @param size Size of the output buffer (in bytes). |
136 | * @param size Size of the output buffer (in bytes). |
137 | * |
137 | * |
138 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
138 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
139 | * was not enough space in the output buffer or EINVAL if the character |
139 | * was not enough space in the output buffer or EINVAL if the character |
140 | * code was invalid. |
140 | * code was invalid. |
141 | */ |
141 | */ |
142 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
142 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
143 | { |
143 | { |
144 | if (*offset >= size) |
144 | if (*offset >= size) |
145 | return EOVERFLOW; |
145 | return EOVERFLOW; |
146 | 146 | ||
147 | if (!chr_check(ch)) |
147 | if (!chr_check(ch)) |
148 | return EINVAL; |
148 | return EINVAL; |
149 | 149 | ||
150 | /* Unsigned version of ch (bit operations should only be done |
150 | /* Unsigned version of ch (bit operations should only be done |
151 | on unsigned types). */ |
151 | on unsigned types). */ |
152 | uint32_t cc = (uint32_t) ch; |
152 | uint32_t cc = (uint32_t) ch; |
153 | 153 | ||
154 | /* Determine how many continuation bytes are needed */ |
154 | /* Determine how many continuation bytes are needed */ |
155 | 155 | ||
156 | unsigned int b0_bits; /* Data bits in first byte */ |
156 | unsigned int b0_bits; /* Data bits in first byte */ |
157 | unsigned int cbytes; /* Number of continuation bytes */ |
157 | unsigned int cbytes; /* Number of continuation bytes */ |
158 | 158 | ||
159 | if ((cc & ~LO_MASK_32(7)) == 0) { |
159 | if ((cc & ~LO_MASK_32(7)) == 0) { |
160 | b0_bits = 7; |
160 | b0_bits = 7; |
161 | cbytes = 0; |
161 | cbytes = 0; |
162 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
162 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
163 | b0_bits = 5; |
163 | b0_bits = 5; |
164 | cbytes = 1; |
164 | cbytes = 1; |
165 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
165 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
166 | b0_bits = 4; |
166 | b0_bits = 4; |
167 | cbytes = 2; |
167 | cbytes = 2; |
168 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
168 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
169 | b0_bits = 3; |
169 | b0_bits = 3; |
170 | cbytes = 3; |
170 | cbytes = 3; |
171 | } else { |
171 | } else { |
172 | /* Codes longer than 21 bits are not supported */ |
172 | /* Codes longer than 21 bits are not supported */ |
173 | return EINVAL; |
173 | return EINVAL; |
174 | } |
174 | } |
175 | 175 | ||
176 | /* Check for available space in buffer */ |
176 | /* Check for available space in buffer */ |
177 | if (*offset + cbytes >= size) |
177 | if (*offset + cbytes >= size) |
178 | return EOVERFLOW; |
178 | return EOVERFLOW; |
179 | 179 | ||
180 | /* Encode continuation bytes */ |
180 | /* Encode continuation bytes */ |
181 | unsigned int i; |
181 | unsigned int i; |
182 | for (i = cbytes; i > 0; i--) { |
182 | for (i = cbytes; i > 0; i--) { |
183 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
183 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
184 | cc = cc >> CONT_BITS; |
184 | cc = cc >> CONT_BITS; |
185 | } |
185 | } |
186 | 186 | ||
187 | /* Encode first byte */ |
187 | /* Encode first byte */ |
188 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
188 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
189 | 189 | ||
190 | /* Advance offset */ |
190 | /* Advance offset */ |
191 | *offset += cbytes + 1; |
191 | *offset += cbytes + 1; |
192 | 192 | ||
193 | return EOK; |
193 | return EOK; |
194 | } |
194 | } |
195 | 195 | ||
196 | /** Get size of string. |
196 | /** Get size of string. |
197 | * |
197 | * |
198 | * Get the number of bytes which are used by the string @a str (excluding the |
198 | * Get the number of bytes which are used by the string @a str (excluding the |
199 | * NULL-terminator). |
199 | * NULL-terminator). |
200 | * |
200 | * |
201 | * @param str String to consider. |
201 | * @param str String to consider. |
202 | * |
202 | * |
203 | * @return Number of bytes used by the string |
203 | * @return Number of bytes used by the string |
204 | * |
204 | * |
205 | */ |
205 | */ |
206 | size_t str_size(const char *str) |
206 | size_t str_size(const char *str) |
207 | { |
207 | { |
208 | size_t size = 0; |
208 | size_t size = 0; |
209 | 209 | ||
210 | while (*str++ != 0) |
210 | while (*str++ != 0) |
211 | size++; |
211 | size++; |
212 | 212 | ||
213 | return size; |
213 | return size; |
214 | } |
214 | } |
215 | 215 | ||
216 | /** Get size of wide string. |
216 | /** Get size of wide string. |
217 | * |
217 | * |
218 | * Get the number of bytes which are used by the wide string @a str (excluding the |
218 | * Get the number of bytes which are used by the wide string @a str (excluding the |
219 | * NULL-terminator). |
219 | * NULL-terminator). |
220 | * |
220 | * |
221 | * @param str Wide string to consider. |
221 | * @param str Wide string to consider. |
222 | * |
222 | * |
223 | * @return Number of bytes used by the wide string |
223 | * @return Number of bytes used by the wide string |
224 | * |
224 | * |
225 | */ |
225 | */ |
226 | size_t wstr_size(const wchar_t *str) |
226 | size_t wstr_size(const wchar_t *str) |
227 | { |
227 | { |
228 | return (wstr_length(str) * sizeof(wchar_t)); |
228 | return (wstr_length(str) * sizeof(wchar_t)); |
229 | } |
229 | } |
230 | 230 | ||
231 | /** Get size of string with length limit. |
231 | /** Get size of string with length limit. |
232 | * |
232 | * |
233 | * Get the number of bytes which are used by up to @a max_len first |
233 | * Get the number of bytes which are used by up to @a max_len first |
234 | * characters in the string @a str. If @a max_len is greater than |
234 | * characters in the string @a str. If @a max_len is greater than |
235 | * the length of @a str, the entire string is measured (excluding the |
235 | * the length of @a str, the entire string is measured (excluding the |
236 | * NULL-terminator). |
236 | * NULL-terminator). |
237 | * |
237 | * |
238 | * @param str String to consider. |
238 | * @param str String to consider. |
239 | * @param max_len Maximum number of characters to measure. |
239 | * @param max_len Maximum number of characters to measure. |
240 | * |
240 | * |
241 | * @return Number of bytes used by the characters. |
241 | * @return Number of bytes used by the characters. |
242 | * |
242 | * |
243 | */ |
243 | */ |
244 | size_t str_lsize(const char *str, count_t max_len) |
244 | size_t str_lsize(const char *str, count_t max_len) |
245 | { |
245 | { |
246 | count_t len = 0; |
246 | count_t len = 0; |
247 | size_t offset = 0; |
247 | size_t offset = 0; |
248 | 248 | ||
249 | while (len < max_len) { |
249 | while (len < max_len) { |
250 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
250 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
251 | break; |
251 | break; |
252 | 252 | ||
253 | len++; |
253 | len++; |
254 | } |
254 | } |
255 | 255 | ||
256 | return offset; |
256 | return offset; |
257 | } |
257 | } |
258 | 258 | ||
259 | /** Get size of wide string with length limit. |
259 | /** Get size of wide string with length limit. |
260 | * |
260 | * |
261 | * Get the number of bytes which are used by up to @a max_len first |
261 | * Get the number of bytes which are used by up to @a max_len first |
262 | * wide characters in the wide string @a str. If @a max_len is greater than |
262 | * wide characters in the wide string @a str. If @a max_len is greater than |
263 | * the length of @a str, the entire wide string is measured (excluding the |
263 | * the length of @a str, the entire wide string is measured (excluding the |
264 | * NULL-terminator). |
264 | * NULL-terminator). |
265 | * |
265 | * |
266 | * @param str Wide string to consider. |
266 | * @param str Wide string to consider. |
267 | * @param max_len Maximum number of wide characters to measure. |
267 | * @param max_len Maximum number of wide characters to measure. |
268 | * |
268 | * |
269 | * @return Number of bytes used by the wide characters. |
269 | * @return Number of bytes used by the wide characters. |
270 | * |
270 | * |
271 | */ |
271 | */ |
272 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
272 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
273 | { |
273 | { |
274 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
274 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
275 | } |
275 | } |
276 | 276 | ||
277 | /** Get number of characters in a string. |
277 | /** Get number of characters in a string. |
278 | * |
278 | * |
279 | * @param str NULL-terminated string. |
279 | * @param str NULL-terminated string. |
280 | * |
280 | * |
281 | * @return Number of characters in string. |
281 | * @return Number of characters in string. |
282 | * |
282 | * |
283 | */ |
283 | */ |
284 | count_t str_length(const char *str) |
284 | count_t str_length(const char *str) |
285 | { |
285 | { |
286 | count_t len = 0; |
286 | count_t len = 0; |
287 | size_t offset = 0; |
287 | size_t offset = 0; |
288 | 288 | ||
289 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
289 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
290 | len++; |
290 | len++; |
291 | 291 | ||
292 | return len; |
292 | return len; |
293 | } |
293 | } |
294 | 294 | ||
295 | /** Get number of characters in a wide string. |
295 | /** Get number of characters in a wide string. |
296 | * |
296 | * |
297 | * @param str NULL-terminated wide string. |
297 | * @param str NULL-terminated wide string. |
298 | * |
298 | * |
299 | * @return Number of characters in @a str. |
299 | * @return Number of characters in @a str. |
300 | * |
300 | * |
301 | */ |
301 | */ |
302 | count_t wstr_length(const wchar_t *wstr) |
302 | count_t wstr_length(const wchar_t *wstr) |
303 | { |
303 | { |
304 | count_t len = 0; |
304 | count_t len = 0; |
305 | 305 | ||
306 | while (*wstr++ != 0) |
306 | while (*wstr++ != 0) |
307 | len++; |
307 | len++; |
308 | 308 | ||
309 | return len; |
309 | return len; |
310 | } |
310 | } |
311 | 311 | ||
312 | /** Get number of characters in a string with size limit. |
312 | /** Get number of characters in a string with size limit. |
313 | * |
313 | * |
314 | * @param str NULL-terminated string. |
314 | * @param str NULL-terminated string. |
315 | * @param size Maximum number of bytes to consider. |
315 | * @param size Maximum number of bytes to consider. |
316 | * |
316 | * |
317 | * @return Number of characters in string. |
317 | * @return Number of characters in string. |
318 | * |
318 | * |
319 | */ |
319 | */ |
320 | count_t str_nlength(const char *str, size_t size) |
320 | count_t str_nlength(const char *str, size_t size) |
321 | { |
321 | { |
322 | count_t len = 0; |
322 | count_t len = 0; |
323 | size_t offset = 0; |
323 | size_t offset = 0; |
324 | 324 | ||
325 | while (str_decode(str, &offset, size) != 0) |
325 | while (str_decode(str, &offset, size) != 0) |
326 | len++; |
326 | len++; |
327 | 327 | ||
328 | return len; |
328 | return len; |
329 | } |
329 | } |
330 | 330 | ||
331 | /** Get number of characters in a string with size limit. |
331 | /** Get number of characters in a string with size limit. |
332 | * |
332 | * |
333 | * @param str NULL-terminated string. |
333 | * @param str NULL-terminated string. |
334 | * @param size Maximum number of bytes to consider. |
334 | * @param size Maximum number of bytes to consider. |
335 | * |
335 | * |
336 | * @return Number of characters in string. |
336 | * @return Number of characters in string. |
337 | * |
337 | * |
338 | */ |
338 | */ |
339 | count_t wstr_nlength(const wchar_t *str, size_t size) |
339 | count_t wstr_nlength(const wchar_t *str, size_t size) |
340 | { |
340 | { |
341 | count_t len = 0; |
341 | count_t len = 0; |
342 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
342 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
343 | count_t offset = 0; |
343 | count_t offset = 0; |
344 | 344 | ||
345 | while ((offset < limit) && (*str++ != 0)) { |
345 | while ((offset < limit) && (*str++ != 0)) { |
346 | len++; |
346 | len++; |
347 | offset += sizeof(wchar_t); |
347 | offset += sizeof(wchar_t); |
348 | } |
348 | } |
349 | 349 | ||
350 | return len; |
350 | return len; |
351 | } |
351 | } |
352 | 352 | ||
353 | /** Check whether character is plain ASCII. |
353 | /** Check whether character is plain ASCII. |
354 | * |
354 | * |
355 | * @return True if character is plain ASCII. |
355 | * @return True if character is plain ASCII. |
356 | * |
356 | * |
357 | */ |
357 | */ |
358 | bool ascii_check(wchar_t ch) |
358 | bool ascii_check(wchar_t ch) |
359 | { |
359 | { |
360 | if ((ch >= 0) && (ch <= 127)) |
360 | if ((ch >= 0) && (ch <= 127)) |
361 | return true; |
361 | return true; |
362 | 362 | ||
363 | return false; |
363 | return false; |
364 | } |
364 | } |
365 | 365 | ||
366 | /** Check whether character is valid |
366 | /** Check whether character is valid |
367 | * |
367 | * |
368 | * @return True if character is a valid Unicode code point. |
368 | * @return True if character is a valid Unicode code point. |
369 | * |
369 | * |
370 | */ |
370 | */ |
371 | bool chr_check(wchar_t ch) |
371 | bool chr_check(wchar_t ch) |
372 | { |
372 | { |
373 | if ((ch >= 0) && (ch <= 1114111)) |
373 | if ((ch >= 0) && (ch <= 1114111)) |
374 | return true; |
374 | return true; |
375 | 375 | ||
376 | return false; |
376 | return false; |
377 | } |
377 | } |
378 | 378 | ||
379 | /** Compare two NULL terminated strings. |
379 | /** Compare two NULL terminated strings. |
380 | * |
380 | * |
381 | * Do a char-by-char comparison of two NULL-terminated strings. |
381 | * Do a char-by-char comparison of two NULL-terminated strings. |
382 | * The strings are considered equal iff they consist of the same |
382 | * The strings are considered equal iff they consist of the same |
383 | * characters on the minimum of their lengths. |
383 | * characters on the minimum of their lengths. |
384 | * |
384 | * |
385 | * @param s1 First string to compare. |
385 | * @param s1 First string to compare. |
386 | * @param s2 Second string to compare. |
386 | * @param s2 Second string to compare. |
387 | * |
387 | * |
388 | * @return 0 if the strings are equal, -1 if first is smaller, |
388 | * @return 0 if the strings are equal, -1 if first is smaller, |
389 | * 1 if second smaller. |
389 | * 1 if second smaller. |
390 | * |
390 | * |
391 | */ |
391 | */ |
392 | int str_cmp(const char *s1, const char *s2) |
392 | int str_cmp(const char *s1, const char *s2) |
393 | { |
393 | { |
394 | wchar_t c1 = 0; |
394 | wchar_t c1 = 0; |
395 | wchar_t c2 = 0; |
395 | wchar_t c2 = 0; |
396 | 396 | ||
397 | size_t off1 = 0; |
397 | size_t off1 = 0; |
398 | size_t off2 = 0; |
398 | size_t off2 = 0; |
399 | 399 | ||
400 | while (true) { |
400 | while (true) { |
401 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
401 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
402 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
402 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
403 | 403 | ||
404 | if (c1 < c2) |
404 | if (c1 < c2) |
405 | return -1; |
405 | return -1; |
406 | 406 | ||
407 | if (c1 > c2) |
407 | if (c1 > c2) |
408 | return 1; |
408 | return 1; |
409 | 409 | ||
410 | if (c1 == 0 || c2 == 0) |
410 | if (c1 == 0 || c2 == 0) |
411 | break; |
411 | break; |
412 | } |
412 | } |
413 | 413 | ||
414 | return 0; |
414 | return 0; |
415 | } |
415 | } |
416 | 416 | ||
417 | /** Compare two NULL terminated strings with length limit. |
417 | /** Compare two NULL terminated strings with length limit. |
418 | * |
418 | * |
419 | * Do a char-by-char comparison of two NULL-terminated strings. |
419 | * Do a char-by-char comparison of two NULL-terminated strings. |
420 | * The strings are considered equal iff they consist of the same |
420 | * The strings are considered equal iff they consist of the same |
421 | * characters on the minimum of their lengths and the length limit. |
421 | * characters on the minimum of their lengths and the length limit. |
422 | * |
422 | * |
423 | * @param s1 First string to compare. |
423 | * @param s1 First string to compare. |
424 | * @param s2 Second string to compare. |
424 | * @param s2 Second string to compare. |
425 | * @param max_len Maximum number of characters to consider. |
425 | * @param max_len Maximum number of characters to consider. |
426 | * |
426 | * |
427 | * @return 0 if the strings are equal, -1 if first is smaller, |
427 | * @return 0 if the strings are equal, -1 if first is smaller, |
428 | * 1 if second smaller. |
428 | * 1 if second smaller. |
429 | * |
429 | * |
430 | */ |
430 | */ |
431 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
431 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
432 | { |
432 | { |
433 | wchar_t c1 = 0; |
433 | wchar_t c1 = 0; |
434 | wchar_t c2 = 0; |
434 | wchar_t c2 = 0; |
435 | 435 | ||
436 | size_t off1 = 0; |
436 | size_t off1 = 0; |
437 | size_t off2 = 0; |
437 | size_t off2 = 0; |
438 | 438 | ||
439 | count_t len = 0; |
439 | count_t len = 0; |
440 | 440 | ||
441 | while (true) { |
441 | while (true) { |
442 | if (len >= max_len) |
442 | if (len >= max_len) |
443 | break; |
443 | break; |
444 | 444 | ||
445 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
445 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
446 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
446 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
447 | 447 | ||
448 | if (c1 < c2) |
448 | if (c1 < c2) |
449 | return -1; |
449 | return -1; |
450 | 450 | ||
451 | if (c1 > c2) |
451 | if (c1 > c2) |
452 | return 1; |
452 | return 1; |
453 | 453 | ||
454 | if (c1 == 0 || c2 == 0) |
454 | if (c1 == 0 || c2 == 0) |
455 | break; |
455 | break; |
456 | 456 | ||
457 | ++len; |
457 | ++len; |
458 | } |
458 | } |
459 | 459 | ||
460 | return 0; |
460 | return 0; |
461 | 461 | ||
462 | } |
462 | } |
463 | 463 | ||
464 | /** Copy NULL-terminated string. |
464 | /** Copy NULL-terminated string. |
465 | * |
465 | * |
466 | * Copy source string @a src to destination buffer @a dst. |
466 | * Copy source string @a src to destination buffer @a dst. |
467 | * No more than @a size bytes are written. NULL-terminator is always |
467 | * No more than @a size bytes are written. NULL-terminator is always |
468 | * written after the last succesfully copied character (i.e. if the |
468 | * written after the last succesfully copied character (i.e. if the |
469 | * destination buffer is has at least 1 byte, it will be always |
469 | * destination buffer is has at least 1 byte, it will be always |
470 | * NULL-terminated). |
470 | * NULL-terminated). |
471 | * |
471 | * |
472 | * @param src Source string. |
472 | * @param src Source string. |
473 | * @param dst Destination buffer. |
473 | * @param dst Destination buffer. |
474 | * @param count Size of the destination buffer. |
474 | * @param count Size of the destination buffer. |
475 | * |
475 | * |
476 | */ |
476 | */ |
477 | void str_ncpy(char *dst, const char *src, size_t size) |
477 | void str_ncpy(char *dst, const char *src, size_t size) |
478 | { |
478 | { |
479 | /* No space for the NULL-terminator in the buffer */ |
479 | /* No space for the NULL-terminator in the buffer */ |
480 | if (size == 0) |
480 | if (size == 0) |
481 | return; |
481 | return; |
482 | 482 | ||
483 | wchar_t ch; |
483 | wchar_t ch; |
484 | size_t str_off = 0; |
484 | size_t str_off = 0; |
485 | size_t dst_off = 0; |
485 | size_t dst_off = 0; |
486 | 486 | ||
487 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT)) != 0) { |
487 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT)) != 0) { |
488 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
488 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
489 | break; |
489 | break; |
490 | } |
490 | } |
491 | 491 | ||
492 | if (dst_off >= size) |
492 | if (dst_off >= size) |
493 | dst[size - 1] = 0; |
493 | dst[size - 1] = 0; |
494 | else |
494 | else |
495 | dst[dst_off] = 0; |
495 | dst[dst_off] = 0; |
496 | } |
496 | } |
497 | 497 | ||
498 | /** Copy NULL-terminated wide string to string |
498 | /** Copy NULL-terminated wide string to string |
499 | * |
499 | * |
500 | * Copy source wide string @a src to destination buffer @a dst. |
500 | * Copy source wide string @a src to destination buffer @a dst. |
501 | * No more than @a size bytes are written. NULL-terminator is always |
501 | * No more than @a size bytes are written. NULL-terminator is always |
502 | * written after the last succesfully copied character (i.e. if the |
502 | * written after the last succesfully copied character (i.e. if the |
503 | * destination buffer is has at least 1 byte, it will be always |
503 | * destination buffer is has at least 1 byte, it will be always |
504 | * NULL-terminated). |
504 | * NULL-terminated). |
505 | * |
505 | * |
506 | * @param src Source wide string. |
506 | * @param src Source wide string. |
507 | * @param dst Destination buffer. |
507 | * @param dst Destination buffer. |
508 | * @param count Size of the destination buffer. |
508 | * @param count Size of the destination buffer. |
509 | * |
509 | * |
510 | */ |
510 | */ |
511 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
511 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
512 | { |
512 | { |
513 | /* No space for the NULL-terminator in the buffer */ |
513 | /* No space for the NULL-terminator in the buffer */ |
514 | if (size == 0) |
514 | if (size == 0) |
515 | return; |
515 | return; |
516 | 516 | ||
517 | wchar_t ch; |
517 | wchar_t ch; |
518 | count_t src_idx = 0; |
518 | count_t src_idx = 0; |
519 | size_t dst_off = 0; |
519 | size_t dst_off = 0; |
520 | 520 | ||
521 | while ((ch = src[src_idx++]) != 0) { |
521 | while ((ch = src[src_idx++]) != 0) { |
522 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
522 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
523 | break; |
523 | break; |
524 | } |
524 | } |
525 | 525 | ||
526 | if (dst_off >= size) |
526 | if (dst_off >= size) |
527 | dst[size - 1] = 0; |
527 | dst[size - 1] = 0; |
528 | else |
528 | else |
529 | dst[dst_off] = 0; |
529 | dst[dst_off] = 0; |
530 | } |
530 | } |
531 | 531 | ||
532 | /** Find first occurence of character in string. |
532 | /** Find first occurence of character in string. |
533 | * |
533 | * |
534 | * @param str String to search. |
534 | * @param str String to search. |
535 | * @param ch Character to look for. |
535 | * @param ch Character to look for. |
536 | * |
536 | * |
537 | * @return Pointer to character in @a str or NULL if not found. |
537 | * @return Pointer to character in @a str or NULL if not found. |
538 | * |
- | |
539 | */ |
538 | */ |
540 | const char *str_chr(const char *str, wchar_t ch) |
539 | const char *str_chr(const char *str, wchar_t ch) |
541 | { |
540 | { |
542 | wchar_t acc; |
541 | wchar_t acc; |
543 | size_t off = 0; |
542 | size_t off = 0; |
544 | 543 | ||
545 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) { |
544 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) { |
546 | if (acc == ch) |
545 | if (acc == ch) |
547 | return (str + off); |
546 | return (str + off); |
548 | } |
547 | } |
549 | 548 | ||
550 | return NULL; |
549 | return NULL; |
551 | } |
550 | } |
552 | 551 | ||
- | 552 | /** Find last occurence of character in string. |
|
- | 553 | * |
|
- | 554 | * @param str String to search. |
|
- | 555 | * @param ch Character to look for. |
|
- | 556 | * |
|
- | 557 | * @return Pointer to character in @a str or NULL if not found. |
|
- | 558 | */ |
|
- | 559 | const char *str_rchr(const char *str, wchar_t ch) |
|
- | 560 | { |
|
- | 561 | wchar_t acc; |
|
- | 562 | size_t off = 0; |
|
- | 563 | char *res; |
|
- | 564 | ||
- | 565 | res = NULL; |
|
- | 566 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) { |
|
- | 567 | if (acc == ch) |
|
- | 568 | res = (str + off); |
|
- | 569 | } |
|
- | 570 | ||
- | 571 | return res; |
|
- | 572 | } |
|
- | 573 | ||
553 | /** Insert a wide character into a wide string. |
574 | /** Insert a wide character into a wide string. |
554 | * |
575 | * |
555 | * Insert a wide character into a wide string at position |
576 | * Insert a wide character into a wide string at position |
556 | * @a pos. The characters after the position are shifted. |
577 | * @a pos. The characters after the position are shifted. |
557 | * |
578 | * |
558 | * @param str String to insert to. |
579 | * @param str String to insert to. |
559 | * @param ch Character to insert to. |
580 | * @param ch Character to insert to. |
560 | * @param pos Character index where to insert. |
581 | * @param pos Character index where to insert. |
561 | @ @param max_pos Characters in the buffer. |
582 | @ @param max_pos Characters in the buffer. |
562 | * |
583 | * |
563 | * @return True if the insertion was sucessful, false if the position |
584 | * @return True if the insertion was sucessful, false if the position |
564 | * is out of bounds. |
585 | * is out of bounds. |
565 | * |
586 | * |
566 | */ |
587 | */ |
567 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
588 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
568 | { |
589 | { |
569 | count_t len = wstr_length(str); |
590 | count_t len = wstr_length(str); |
570 | 591 | ||
571 | if ((pos > len) || (pos + 1 > max_pos)) |
592 | if ((pos > len) || (pos + 1 > max_pos)) |
572 | return false; |
593 | return false; |
573 | 594 | ||
574 | count_t i; |
595 | count_t i; |
575 | for (i = len; i + 1 > pos; i--) |
596 | for (i = len; i + 1 > pos; i--) |
576 | str[i + 1] = str[i]; |
597 | str[i + 1] = str[i]; |
577 | 598 | ||
578 | str[pos] = ch; |
599 | str[pos] = ch; |
579 | 600 | ||
580 | return true; |
601 | return true; |
581 | } |
602 | } |
582 | 603 | ||
583 | /** Remove a wide character from a wide string. |
604 | /** Remove a wide character from a wide string. |
584 | * |
605 | * |
585 | * Remove a wide character from a wide string at position |
606 | * Remove a wide character from a wide string at position |
586 | * @a pos. The characters after the position are shifted. |
607 | * @a pos. The characters after the position are shifted. |
587 | * |
608 | * |
588 | * @param str String to remove from. |
609 | * @param str String to remove from. |
589 | * @param pos Character index to remove. |
610 | * @param pos Character index to remove. |
590 | * |
611 | * |
591 | * @return True if the removal was sucessful, false if the position |
612 | * @return True if the removal was sucessful, false if the position |
592 | * is out of bounds. |
613 | * is out of bounds. |
593 | * |
614 | * |
594 | */ |
615 | */ |
595 | bool wstr_remove(wchar_t *str, count_t pos) |
616 | bool wstr_remove(wchar_t *str, count_t pos) |
596 | { |
617 | { |
597 | count_t len = wstr_length(str); |
618 | count_t len = wstr_length(str); |
598 | 619 | ||
599 | if (pos >= len) |
620 | if (pos >= len) |
600 | return false; |
621 | return false; |
601 | 622 | ||
602 | count_t i; |
623 | count_t i; |
603 | for (i = pos + 1; i <= len; i++) |
624 | for (i = pos + 1; i <= len; i++) |
604 | str[i - 1] = str[i]; |
625 | str[i - 1] = str[i]; |
605 | 626 | ||
606 | return true; |
627 | return true; |
607 | } |
628 | } |
608 | 629 | ||
609 | int strncmp(const char *a, const char *b, size_t n) |
630 | int strncmp(const char *a, const char *b, size_t n) |
610 | { |
631 | { |
611 | size_t c = 0; |
632 | size_t c = 0; |
612 | 633 | ||
613 | while (c < n && a[c] && b[c] && (!(a[c] - b[c]))) |
634 | while (c < n && a[c] && b[c] && (!(a[c] - b[c]))) |
614 | c++; |
635 | c++; |
615 | 636 | ||
616 | return ( c < n ? a[c] - b[c] : 0); |
637 | return ( c < n ? a[c] - b[c] : 0); |
617 | 638 | ||
618 | } |
639 | } |
619 | 640 | ||
620 | int stricmp(const char *a, const char *b) |
641 | int stricmp(const char *a, const char *b) |
621 | { |
642 | { |
622 | int c = 0; |
643 | int c = 0; |
623 | 644 | ||
624 | while (a[c] && b[c] && (!(tolower(a[c]) - tolower(b[c])))) |
645 | while (a[c] && b[c] && (!(tolower(a[c]) - tolower(b[c])))) |
625 | c++; |
646 | c++; |
626 | 647 | ||
627 | return (tolower(a[c]) - tolower(b[c])); |
648 | return (tolower(a[c]) - tolower(b[c])); |
628 | } |
649 | } |
629 | 650 | ||
630 | /** Return pointer to the first occurence of character c in string. |
- | |
631 | * |
- | |
632 | * @param str Scanned string. |
- | |
633 | * @param c Searched character (taken as one byte). |
- | |
634 | * @return Pointer to the matched character or NULL if it is not |
- | |
635 | * found in given string. |
- | |
636 | */ |
- | |
637 | char *strchr(const char *str, int c) |
- | |
638 | { |
- | |
639 | while (*str != '\0') { |
- | |
640 | if (*str == (char) c) |
- | |
641 | return (char *) str; |
- | |
642 | str++; |
- | |
643 | } |
- | |
644 | - | ||
645 | return NULL; |
- | |
646 | } |
- | |
647 | - | ||
648 | /** Return pointer to the last occurence of character c in string. |
- | |
649 | * |
- | |
650 | * @param str Scanned string. |
- | |
651 | * @param c Searched character (taken as one byte). |
- | |
652 | * @return Pointer to the matched character or NULL if it is not |
- | |
653 | * found in given string. |
- | |
654 | */ |
- | |
655 | char *strrchr(const char *str, int c) |
- | |
656 | { |
- | |
657 | char *retval = NULL; |
- | |
658 | - | ||
659 | while (*str != '\0') { |
- | |
660 | if (*str == (char) c) |
- | |
661 | retval = (char *) str; |
- | |
662 | str++; |
- | |
663 | } |
- | |
664 | - | ||
665 | return (char *) retval; |
- | |
666 | } |
- | |
667 | - | ||
668 | /** Convert string to a number. |
651 | /** Convert string to a number. |
669 | * Core of strtol and strtoul functions. |
652 | * Core of strtol and strtoul functions. |
670 | * |
653 | * |
671 | * @param nptr Pointer to string. |
654 | * @param nptr Pointer to string. |
672 | * @param endptr If not NULL, function stores here pointer to the first |
655 | * @param endptr If not NULL, function stores here pointer to the first |
673 | * invalid character. |
656 | * invalid character. |
674 | * @param base Zero or number between 2 and 36 inclusive. |
657 | * @param base Zero or number between 2 and 36 inclusive. |
675 | * @param sgn It's set to 1 if minus found. |
658 | * @param sgn It's set to 1 if minus found. |
676 | * @return Result of conversion. |
659 | * @return Result of conversion. |
677 | */ |
660 | */ |
678 | static unsigned long |
661 | static unsigned long |
679 | _strtoul(const char *nptr, char **endptr, int base, char *sgn) |
662 | _strtoul(const char *nptr, char **endptr, int base, char *sgn) |
680 | { |
663 | { |
681 | unsigned char c; |
664 | unsigned char c; |
682 | unsigned long result = 0; |
665 | unsigned long result = 0; |
683 | unsigned long a, b; |
666 | unsigned long a, b; |
684 | const char *str = nptr; |
667 | const char *str = nptr; |
685 | const char *tmpptr; |
668 | const char *tmpptr; |
686 | 669 | ||
687 | while (isspace(*str)) |
670 | while (isspace(*str)) |
688 | str++; |
671 | str++; |
689 | 672 | ||
690 | if (*str == '-') { |
673 | if (*str == '-') { |
691 | *sgn = 1; |
674 | *sgn = 1; |
692 | ++str; |
675 | ++str; |
693 | } else if (*str == '+') |
676 | } else if (*str == '+') |
694 | ++str; |
677 | ++str; |
695 | 678 | ||
696 | if (base) { |
679 | if (base) { |
697 | if ((base == 1) || (base > 36)) { |
680 | if ((base == 1) || (base > 36)) { |
698 | /* FIXME: set errno to EINVAL */ |
681 | /* FIXME: set errno to EINVAL */ |
699 | return 0; |
682 | return 0; |
700 | } |
683 | } |
701 | if ((base == 16) && (*str == '0') && ((str[1] == 'x') || |
684 | if ((base == 16) && (*str == '0') && ((str[1] == 'x') || |
702 | (str[1] == 'X'))) { |
685 | (str[1] == 'X'))) { |
703 | str += 2; |
686 | str += 2; |
704 | } |
687 | } |
705 | } else { |
688 | } else { |
706 | base = 10; |
689 | base = 10; |
707 | 690 | ||
708 | if (*str == '0') { |
691 | if (*str == '0') { |
709 | base = 8; |
692 | base = 8; |
710 | if ((str[1] == 'X') || (str[1] == 'x')) { |
693 | if ((str[1] == 'X') || (str[1] == 'x')) { |
711 | base = 16; |
694 | base = 16; |
712 | str += 2; |
695 | str += 2; |
713 | } |
696 | } |
714 | } |
697 | } |
715 | } |
698 | } |
716 | 699 | ||
717 | tmpptr = str; |
700 | tmpptr = str; |
718 | 701 | ||
719 | while (*str) { |
702 | while (*str) { |
720 | c = *str; |
703 | c = *str; |
721 | c = (c >= 'a' ? c - 'a' + 10 : (c >= 'A' ? c - 'A' + 10 : |
704 | c = (c >= 'a' ? c - 'a' + 10 : (c >= 'A' ? c - 'A' + 10 : |
722 | (c <= '9' ? c - '0' : 0xff))); |
705 | (c <= '9' ? c - '0' : 0xff))); |
723 | if (c > base) { |
706 | if (c > base) { |
724 | break; |
707 | break; |
725 | } |
708 | } |
726 | 709 | ||
727 | a = (result & 0xff) * base + c; |
710 | a = (result & 0xff) * base + c; |
728 | b = (result >> 8) * base + (a >> 8); |
711 | b = (result >> 8) * base + (a >> 8); |
729 | 712 | ||
730 | if (b > (ULONG_MAX >> 8)) { |
713 | if (b > (ULONG_MAX >> 8)) { |
731 | /* overflow */ |
714 | /* overflow */ |
732 | /* FIXME: errno = ERANGE*/ |
715 | /* FIXME: errno = ERANGE*/ |
733 | return ULONG_MAX; |
716 | return ULONG_MAX; |
734 | } |
717 | } |
735 | 718 | ||
736 | result = (b << 8) + (a & 0xff); |
719 | result = (b << 8) + (a & 0xff); |
737 | ++str; |
720 | ++str; |
738 | } |
721 | } |
739 | 722 | ||
740 | if (str == tmpptr) { |
723 | if (str == tmpptr) { |
741 | /* |
724 | /* |
742 | * No number was found => first invalid character is the first |
725 | * No number was found => first invalid character is the first |
743 | * character of the string. |
726 | * character of the string. |
744 | */ |
727 | */ |
745 | /* FIXME: set errno to EINVAL */ |
728 | /* FIXME: set errno to EINVAL */ |
746 | str = nptr; |
729 | str = nptr; |
747 | result = 0; |
730 | result = 0; |
748 | } |
731 | } |
749 | 732 | ||
750 | if (endptr) |
733 | if (endptr) |
751 | *endptr = (char *) str; |
734 | *endptr = (char *) str; |
752 | 735 | ||
753 | if (nptr == str) { |
736 | if (nptr == str) { |
754 | /*FIXME: errno = EINVAL*/ |
737 | /*FIXME: errno = EINVAL*/ |
755 | return 0; |
738 | return 0; |
756 | } |
739 | } |
757 | 740 | ||
758 | return result; |
741 | return result; |
759 | } |
742 | } |
760 | 743 | ||
761 | /** Convert initial part of string to long int according to given base. |
744 | /** Convert initial part of string to long int according to given base. |
762 | * The number may begin with an arbitrary number of whitespaces followed by |
745 | * The number may begin with an arbitrary number of whitespaces followed by |
763 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
746 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
764 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
747 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
765 | * and the number begin with a zero, number will be taken as octal one (as with |
748 | * and the number begin with a zero, number will be taken as octal one (as with |
766 | * base 8). Otherwise the base 0 is taken as decimal. |
749 | * base 8). Otherwise the base 0 is taken as decimal. |
767 | * |
750 | * |
768 | * @param nptr Pointer to string. |
751 | * @param nptr Pointer to string. |
769 | * @param endptr If not NULL, function stores here pointer to the first |
752 | * @param endptr If not NULL, function stores here pointer to the first |
770 | * invalid character. |
753 | * invalid character. |
771 | * @param base Zero or number between 2 and 36 inclusive. |
754 | * @param base Zero or number between 2 and 36 inclusive. |
772 | * @return Result of conversion. |
755 | * @return Result of conversion. |
773 | */ |
756 | */ |
774 | long int strtol(const char *nptr, char **endptr, int base) |
757 | long int strtol(const char *nptr, char **endptr, int base) |
775 | { |
758 | { |
776 | char sgn = 0; |
759 | char sgn = 0; |
777 | unsigned long number = 0; |
760 | unsigned long number = 0; |
778 | 761 | ||
779 | number = _strtoul(nptr, endptr, base, &sgn); |
762 | number = _strtoul(nptr, endptr, base, &sgn); |
780 | 763 | ||
781 | if (number > LONG_MAX) { |
764 | if (number > LONG_MAX) { |
782 | if ((sgn) && (number == (unsigned long) (LONG_MAX) + 1)) { |
765 | if ((sgn) && (number == (unsigned long) (LONG_MAX) + 1)) { |
783 | /* FIXME: set 0 to errno */ |
766 | /* FIXME: set 0 to errno */ |
784 | return number; |
767 | return number; |
785 | } |
768 | } |
786 | /* FIXME: set ERANGE to errno */ |
769 | /* FIXME: set ERANGE to errno */ |
787 | return (sgn ? LONG_MIN : LONG_MAX); |
770 | return (sgn ? LONG_MIN : LONG_MAX); |
788 | } |
771 | } |
789 | 772 | ||
790 | return (sgn ? -number : number); |
773 | return (sgn ? -number : number); |
791 | } |
774 | } |
792 | 775 | ||
793 | 776 | ||
794 | /** Convert initial part of string to unsigned long according to given base. |
777 | /** Convert initial part of string to unsigned long according to given base. |
795 | * The number may begin with an arbitrary number of whitespaces followed by |
778 | * The number may begin with an arbitrary number of whitespaces followed by |
796 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
779 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
797 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
780 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
798 | * and the number begin with a zero, number will be taken as octal one (as with |
781 | * and the number begin with a zero, number will be taken as octal one (as with |
799 | * base 8). Otherwise the base 0 is taken as decimal. |
782 | * base 8). Otherwise the base 0 is taken as decimal. |
800 | * |
783 | * |
801 | * @param nptr Pointer to string. |
784 | * @param nptr Pointer to string. |
802 | * @param endptr If not NULL, function stores here pointer to the first |
785 | * @param endptr If not NULL, function stores here pointer to the first |
803 | * invalid character |
786 | * invalid character |
804 | * @param base Zero or number between 2 and 36 inclusive. |
787 | * @param base Zero or number between 2 and 36 inclusive. |
805 | * @return Result of conversion. |
788 | * @return Result of conversion. |
806 | */ |
789 | */ |
807 | unsigned long strtoul(const char *nptr, char **endptr, int base) |
790 | unsigned long strtoul(const char *nptr, char **endptr, int base) |
808 | { |
791 | { |
809 | char sgn = 0; |
792 | char sgn = 0; |
810 | unsigned long number = 0; |
793 | unsigned long number = 0; |
811 | 794 | ||
812 | number = _strtoul(nptr, endptr, base, &sgn); |
795 | number = _strtoul(nptr, endptr, base, &sgn); |
813 | 796 | ||
814 | return (sgn ? -number : number); |
797 | return (sgn ? -number : number); |
815 | } |
798 | } |
816 | 799 | ||
817 | char *strcpy(char *dest, const char *src) |
800 | char *strcpy(char *dest, const char *src) |
818 | { |
801 | { |
819 | char *orig = dest; |
802 | char *orig = dest; |
820 | 803 | ||
821 | while ((*(dest++) = *(src++))) |
804 | while ((*(dest++) = *(src++))) |
822 | ; |
805 | ; |
823 | return orig; |
806 | return orig; |
824 | } |
807 | } |
825 | 808 | ||
826 | char *strncpy(char *dest, const char *src, size_t n) |
809 | char *strncpy(char *dest, const char *src, size_t n) |
827 | { |
810 | { |
828 | char *orig = dest; |
811 | char *orig = dest; |
829 | 812 | ||
830 | while ((*(dest++) = *(src++)) && --n) |
813 | while ((*(dest++) = *(src++)) && --n) |
831 | ; |
814 | ; |
832 | return orig; |
815 | return orig; |
833 | } |
816 | } |
834 | 817 | ||
835 | char *strcat(char *dest, const char *src) |
818 | char *strcat(char *dest, const char *src) |
836 | { |
819 | { |
837 | char *orig = dest; |
820 | char *orig = dest; |
838 | while (*dest++) |
821 | while (*dest++) |
839 | ; |
822 | ; |
840 | --dest; |
823 | --dest; |
841 | while ((*dest++ = *src++)) |
824 | while ((*dest++ = *src++)) |
842 | ; |
825 | ; |
843 | return orig; |
826 | return orig; |
844 | } |
827 | } |
845 | 828 | ||
846 | char * strdup(const char *s1) |
829 | char * strdup(const char *s1) |
847 | { |
830 | { |
848 | size_t len = str_size(s1) + 1; |
831 | size_t len = str_size(s1) + 1; |
849 | void *ret = malloc(len); |
832 | void *ret = malloc(len); |
850 | 833 | ||
851 | if (ret == NULL) |
834 | if (ret == NULL) |
852 | return (char *) NULL; |
835 | return (char *) NULL; |
853 | 836 | ||
854 | return (char *) memcpy(ret, s1, len); |
837 | return (char *) memcpy(ret, s1, len); |
855 | } |
838 | } |
856 | 839 | ||
857 | char *strtok(char *s, const char *delim) |
840 | char *strtok(char *s, const char *delim) |
858 | { |
841 | { |
859 | static char *next; |
842 | static char *next; |
860 | 843 | ||
861 | return strtok_r(s, delim, &next); |
844 | return strtok_r(s, delim, &next); |
862 | } |
845 | } |
863 | 846 | ||
864 | char *strtok_r(char *s, const char *delim, char **next) |
847 | char *strtok_r(char *s, const char *delim, char **next) |
865 | { |
848 | { |
866 | char *start, *end; |
849 | char *start, *end; |
867 | 850 | ||
868 | if (s == NULL) |
851 | if (s == NULL) |
869 | s = *next; |
852 | s = *next; |
870 | 853 | ||
871 | /* Skip over leading delimiters. */ |
854 | /* Skip over leading delimiters. */ |
872 | while (*s && (strchr(delim, *s) != NULL)) ++s; |
855 | while (*s && (str_chr(delim, *s) != NULL)) ++s; |
873 | start = s; |
856 | start = s; |
874 | 857 | ||
875 | /* Skip over token characters. */ |
858 | /* Skip over token characters. */ |
876 | while (*s && (strchr(delim, *s) == NULL)) ++s; |
859 | while (*s && (str_chr(delim, *s) == NULL)) ++s; |
877 | end = s; |
860 | end = s; |
878 | *next = (*s ? s + 1 : s); |
861 | *next = (*s ? s + 1 : s); |
879 | 862 | ||
880 | if (start == end) { |
863 | if (start == end) { |
881 | return NULL; /* No more tokens. */ |
864 | return NULL; /* No more tokens. */ |
882 | } |
865 | } |
883 | 866 | ||
884 | /* Overwrite delimiter with NULL terminator. */ |
867 | /* Overwrite delimiter with NULL terminator. */ |
885 | *end = '\0'; |
868 | *end = '\0'; |
886 | return start; |
869 | return start; |
887 | } |
870 | } |
888 | 871 | ||
889 | /** @} |
872 | /** @} |
890 | */ |
873 | */ |
891 | 874 |