Rev 4212 | Rev 4224 | Go to most recent revision | Only display areas with differences | Regard whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4212 | Rev 4223 | ||
---|---|---|---|
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 String functions. |
35 | * @brief String functions. |
36 | * |
36 | * |
37 | * Strings and characters use the Universal Character Set (UCS). The standard |
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 |
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 |
39 | * in UTF-32) are supported to a limited degree. A single character is |
40 | * represented as wchar_t.@n |
40 | * represented as wchar_t.@n |
41 | * |
41 | * |
42 | * Overview of the terminology:@n |
42 | * Overview of the terminology:@n |
43 | * |
43 | * |
44 | * Term Meaning |
44 | * Term Meaning |
45 | * -------------------- ---------------------------------------------------- |
45 | * -------------------- ---------------------------------------------------- |
46 | * byte 8 bits stored in uint8_t (unsigned 8 bit integer) |
46 | * byte 8 bits stored in uint8_t (unsigned 8 bit integer) |
47 | * |
47 | * |
48 | * character UTF-32 encoded Unicode character, stored in wchar_t |
48 | * character UTF-32 encoded Unicode character, stored in wchar_t |
49 | * (signed 32 bit integer), code points 0 .. 1114111 |
49 | * (signed 32 bit integer), code points 0 .. 1114111 |
50 | * are valid |
50 | * are valid |
51 | * |
51 | * |
52 | * ASCII character 7 bit encoded ASCII character, stored in char |
52 | * ASCII character 7 bit encoded ASCII character, stored in char |
53 | * (usually signed 8 bit integer), code points 0 .. 127 |
53 | * (usually signed 8 bit integer), code points 0 .. 127 |
54 | * are valid |
54 | * are valid |
55 | * |
55 | * |
56 | * string UTF-8 encoded NULL-terminated Unicode string, char * |
56 | * string UTF-8 encoded NULL-terminated Unicode string, char * |
57 | * |
57 | * |
58 | * wide string UTF-32 encoded NULL-terminated Unicode string, |
58 | * wide string UTF-32 encoded NULL-terminated Unicode string, |
59 | * wchar_t * |
59 | * wchar_t * |
60 | * |
60 | * |
61 | * [wide] string size number of BYTES in a [wide] string (excluding |
61 | * [wide] string size number of BYTES in a [wide] string (excluding |
62 | * the NULL-terminator), size_t |
62 | * the NULL-terminator), size_t |
63 | * |
63 | * |
64 | * [wide] string length number of CHARACTERS in a [wide] string (excluding |
64 | * [wide] string length number of CHARACTERS in a [wide] string (excluding |
65 | * the NULL-terminator), count_t |
65 | * the NULL-terminator), count_t |
66 | * |
66 | * |
67 | * [wide] string width number of display cells on a monospace display taken |
67 | * [wide] string width number of display cells on a monospace display taken |
68 | * by a [wide] string, count_t |
68 | * by a [wide] string, count_t |
69 | * |
69 | * |
70 | * |
70 | * |
71 | * Overview of string metrics:@n |
71 | * Overview of string metrics:@n |
72 | * |
72 | * |
73 | * Metric Abbrev. Type Meaning |
73 | * Metric Abbrev. Type Meaning |
74 | * ------ ------ ------ ------------------------------------------------- |
74 | * ------ ------ ------ ------------------------------------------------- |
75 | * size n size_t number of BYTES in a string (excluding the |
75 | * size n size_t number of BYTES in a string (excluding the |
76 | * NULL-terminator) |
76 | * NULL-terminator) |
77 | * |
77 | * |
78 | * length l count_t number of CHARACTERS in a string (excluding the |
78 | * length l count_t number of CHARACTERS in a string (excluding the |
79 | * null terminator) |
79 | * null terminator) |
80 | * |
80 | * |
81 | * width w count_t number of display cells on a monospace display |
81 | * width w count_t number of display cells on a monospace display |
82 | * taken by a string |
82 | * taken by a string |
83 | * |
83 | * |
84 | * |
84 | * |
85 | * Function naming prefixes:@n |
85 | * Function naming prefixes:@n |
86 | * |
86 | * |
87 | * chr_ operate on characters |
87 | * chr_ operate on characters |
88 | * ascii_ operate on ASCII characters |
88 | * ascii_ operate on ASCII characters |
89 | * str_ operate on strings |
89 | * str_ operate on strings |
90 | * wstr_ operate on wide strings |
90 | * wstr_ operate on wide strings |
91 | * |
91 | * |
92 | * [w]str_[n|l|w] operate on a prefix limited by size, length |
92 | * [w]str_[n|l|w] operate on a prefix limited by size, length |
93 | * or width |
93 | * or width |
94 | * |
94 | * |
95 | * |
95 | * |
96 | * A specific character inside a [wide] string can be referred to by:@n |
96 | * A specific character inside a [wide] string can be referred to by:@n |
97 | * |
97 | * |
98 | * pointer (char *, wchar_t *) |
98 | * pointer (char *, wchar_t *) |
99 | * byte offset (size_t) |
99 | * byte offset (size_t) |
100 | * character index (count_t) |
100 | * character index (count_t) |
101 | * |
101 | * |
102 | */ |
102 | */ |
103 | 103 | ||
104 | #include <string.h> |
104 | #include <string.h> |
105 | #include <print.h> |
105 | #include <print.h> |
106 | #include <cpu.h> |
106 | #include <cpu.h> |
107 | #include <arch/asm.h> |
107 | #include <arch/asm.h> |
108 | #include <arch.h> |
108 | #include <arch.h> |
109 | #include <errno.h> |
109 | #include <errno.h> |
110 | #include <align.h> |
110 | #include <align.h> |
111 | 111 | ||
112 | char invalch = '?'; |
- | |
113 | - | ||
114 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
112 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
115 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
113 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
116 | 114 | ||
117 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
115 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
118 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
116 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
119 | 117 | ||
120 | /** Byte mask consisting of highest @n bits (out of 8) */ |
118 | /** Byte mask consisting of highest @n bits (out of 8) */ |
121 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
119 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
122 | 120 | ||
123 | /** Number of data bits in a UTF-8 continuation byte */ |
121 | /** Number of data bits in a UTF-8 continuation byte */ |
124 | #define CONT_BITS 6 |
122 | #define CONT_BITS 6 |
125 | 123 | ||
126 | /** Decode a single character from a string. |
124 | /** Decode a single character from a string. |
127 | * |
125 | * |
128 | * Decode a single character from a string of size @a size. Decoding starts |
126 | * Decode a single character from a string of size @a size. Decoding starts |
129 | * at @a offset and this offset is moved to the beginning of the next |
127 | * at @a offset and this offset is moved to the beginning of the next |
130 | * character. In case of decoding error, offset generally advances at least |
128 | * character. In case of decoding error, offset generally advances at least |
131 | * by one. However, offset is never moved beyond size. |
129 | * by one. However, offset is never moved beyond size. |
132 | * |
130 | * |
133 | * @param str String (not necessarily NULL-terminated). |
131 | * @param str String (not necessarily NULL-terminated). |
134 | * @param offset Byte offset in string where to start decoding. |
132 | * @param offset Byte offset in string where to start decoding. |
135 | * @param size Size of the string (in bytes). |
133 | * @param size Size of the string (in bytes). |
136 | * |
134 | * |
137 | * @return Value of decoded character, invalch on decoding error or |
135 | * @return Value of decoded character, U_SPECIAL on decoding error or |
138 | * NULL if attempt to decode beyond @a size. |
136 | * NULL if attempt to decode beyond @a size. |
139 | * |
137 | * |
140 | */ |
138 | */ |
141 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
139 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
142 | { |
140 | { |
143 | if (*offset + 1 > size) |
141 | if (*offset + 1 > size) |
144 | return 0; |
142 | return 0; |
145 | 143 | ||
146 | /* First byte read from string */ |
144 | /* First byte read from string */ |
147 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
145 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
148 | 146 | ||
149 | /* Determine code length */ |
147 | /* Determine code length */ |
150 | 148 | ||
151 | unsigned int b0_bits; /* Data bits in first byte */ |
149 | unsigned int b0_bits; /* Data bits in first byte */ |
152 | unsigned int cbytes; /* Number of continuation bytes */ |
150 | unsigned int cbytes; /* Number of continuation bytes */ |
153 | 151 | ||
154 | if ((b0 & 0x80) == 0) { |
152 | if ((b0 & 0x80) == 0) { |
155 | /* 0xxxxxxx (Plain ASCII) */ |
153 | /* 0xxxxxxx (Plain ASCII) */ |
156 | b0_bits = 7; |
154 | b0_bits = 7; |
157 | cbytes = 0; |
155 | cbytes = 0; |
158 | } else if ((b0 & 0xe0) == 0xc0) { |
156 | } else if ((b0 & 0xe0) == 0xc0) { |
159 | /* 110xxxxx 10xxxxxx */ |
157 | /* 110xxxxx 10xxxxxx */ |
160 | b0_bits = 5; |
158 | b0_bits = 5; |
161 | cbytes = 1; |
159 | cbytes = 1; |
162 | } else if ((b0 & 0xf0) == 0xe0) { |
160 | } else if ((b0 & 0xf0) == 0xe0) { |
163 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
161 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
164 | b0_bits = 4; |
162 | b0_bits = 4; |
165 | cbytes = 2; |
163 | cbytes = 2; |
166 | } else if ((b0 & 0xf8) == 0xf0) { |
164 | } else if ((b0 & 0xf8) == 0xf0) { |
167 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
165 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
168 | b0_bits = 3; |
166 | b0_bits = 3; |
169 | cbytes = 3; |
167 | cbytes = 3; |
170 | } else { |
168 | } else { |
171 | /* 10xxxxxx -- unexpected continuation byte */ |
169 | /* 10xxxxxx -- unexpected continuation byte */ |
172 | return invalch; |
170 | return U_SPECIAL; |
173 | } |
171 | } |
174 | 172 | ||
175 | if (*offset + cbytes > size) |
173 | if (*offset + cbytes > size) |
176 | return invalch; |
174 | return U_SPECIAL; |
177 | 175 | ||
178 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
176 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
179 | 177 | ||
180 | /* Decode continuation bytes */ |
178 | /* Decode continuation bytes */ |
181 | while (cbytes > 0) { |
179 | while (cbytes > 0) { |
182 | uint8_t b = (uint8_t) str[(*offset)++]; |
180 | uint8_t b = (uint8_t) str[(*offset)++]; |
183 | 181 | ||
184 | /* Must be 10xxxxxx */ |
182 | /* Must be 10xxxxxx */ |
185 | if ((b & 0xc0) != 0x80) |
183 | if ((b & 0xc0) != 0x80) |
186 | return invalch; |
184 | return U_SPECIAL; |
187 | 185 | ||
188 | /* Shift data bits to ch */ |
186 | /* Shift data bits to ch */ |
189 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
187 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
190 | cbytes--; |
188 | cbytes--; |
191 | } |
189 | } |
192 | 190 | ||
193 | return ch; |
191 | return ch; |
194 | } |
192 | } |
195 | 193 | ||
196 | /** Encode a single character to string representation. |
194 | /** Encode a single character to string representation. |
197 | * |
195 | * |
198 | * Encode a single character to string representation (i.e. UTF-8) and store |
196 | * Encode a single character to string representation (i.e. UTF-8) and store |
199 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
197 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
200 | * is moved to the position where the next character can be written to. |
198 | * is moved to the position where the next character can be written to. |
201 | * |
199 | * |
202 | * @param ch Input character. |
200 | * @param ch Input character. |
203 | * @param str Output buffer. |
201 | * @param str Output buffer. |
204 | * @param offset Byte offset where to start writing. |
202 | * @param offset Byte offset where to start writing. |
205 | * @param size Size of the output buffer (in bytes). |
203 | * @param size Size of the output buffer (in bytes). |
206 | * |
204 | * |
207 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
205 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
208 | * was not enough space in the output buffer or EINVAL if the character |
206 | * was not enough space in the output buffer or EINVAL if the character |
209 | * code was invalid. |
207 | * code was invalid. |
210 | */ |
208 | */ |
211 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
209 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
212 | { |
210 | { |
213 | if (*offset >= size) |
211 | if (*offset >= size) |
214 | return EOVERFLOW; |
212 | return EOVERFLOW; |
215 | 213 | ||
216 | if (!chr_check(ch)) |
214 | if (!chr_check(ch)) |
217 | return EINVAL; |
215 | return EINVAL; |
218 | 216 | ||
219 | /* Unsigned version of ch (bit operations should only be done |
217 | /* Unsigned version of ch (bit operations should only be done |
220 | on unsigned types). */ |
218 | on unsigned types). */ |
221 | uint32_t cc = (uint32_t) ch; |
219 | uint32_t cc = (uint32_t) ch; |
222 | 220 | ||
223 | /* Determine how many continuation bytes are needed */ |
221 | /* Determine how many continuation bytes are needed */ |
224 | 222 | ||
225 | unsigned int b0_bits; /* Data bits in first byte */ |
223 | unsigned int b0_bits; /* Data bits in first byte */ |
226 | unsigned int cbytes; /* Number of continuation bytes */ |
224 | unsigned int cbytes; /* Number of continuation bytes */ |
227 | 225 | ||
228 | if ((cc & ~LO_MASK_32(7)) == 0) { |
226 | if ((cc & ~LO_MASK_32(7)) == 0) { |
229 | b0_bits = 7; |
227 | b0_bits = 7; |
230 | cbytes = 0; |
228 | cbytes = 0; |
231 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
229 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
232 | b0_bits = 5; |
230 | b0_bits = 5; |
233 | cbytes = 1; |
231 | cbytes = 1; |
234 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
232 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
235 | b0_bits = 4; |
233 | b0_bits = 4; |
236 | cbytes = 2; |
234 | cbytes = 2; |
237 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
235 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
238 | b0_bits = 3; |
236 | b0_bits = 3; |
239 | cbytes = 3; |
237 | cbytes = 3; |
240 | } else { |
238 | } else { |
241 | /* Codes longer than 21 bits are not supported */ |
239 | /* Codes longer than 21 bits are not supported */ |
242 | return EINVAL; |
240 | return EINVAL; |
243 | } |
241 | } |
244 | 242 | ||
245 | /* Check for available space in buffer */ |
243 | /* Check for available space in buffer */ |
246 | if (*offset + cbytes >= size) |
244 | if (*offset + cbytes >= size) |
247 | return EOVERFLOW; |
245 | return EOVERFLOW; |
248 | 246 | ||
249 | /* Encode continuation bytes */ |
247 | /* Encode continuation bytes */ |
250 | unsigned int i; |
248 | unsigned int i; |
251 | for (i = cbytes; i > 0; i--) { |
249 | for (i = cbytes; i > 0; i--) { |
252 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
250 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
253 | cc = cc >> CONT_BITS; |
251 | cc = cc >> CONT_BITS; |
254 | } |
252 | } |
255 | 253 | ||
256 | /* Encode first byte */ |
254 | /* Encode first byte */ |
257 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
255 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
258 | 256 | ||
259 | /* Advance offset */ |
257 | /* Advance offset */ |
260 | *offset += cbytes + 1; |
258 | *offset += cbytes + 1; |
261 | 259 | ||
262 | return EOK; |
260 | return EOK; |
263 | } |
261 | } |
264 | 262 | ||
265 | /** Get size of string. |
263 | /** Get size of string. |
266 | * |
264 | * |
267 | * Get the number of bytes which are used by the string @a str (excluding the |
265 | * Get the number of bytes which are used by the string @a str (excluding the |
268 | * NULL-terminator). |
266 | * NULL-terminator). |
269 | * |
267 | * |
270 | * @param str String to consider. |
268 | * @param str String to consider. |
271 | * |
269 | * |
272 | * @return Number of bytes used by the string |
270 | * @return Number of bytes used by the string |
273 | * |
271 | * |
274 | */ |
272 | */ |
275 | size_t str_size(const char *str) |
273 | size_t str_size(const char *str) |
276 | { |
274 | { |
277 | size_t size = 0; |
275 | size_t size = 0; |
278 | 276 | ||
279 | while (*str++ != 0) |
277 | while (*str++ != 0) |
280 | size++; |
278 | size++; |
281 | 279 | ||
282 | return size; |
280 | return size; |
283 | } |
281 | } |
284 | 282 | ||
285 | /** Get size of wide string. |
283 | /** Get size of wide string. |
286 | * |
284 | * |
287 | * Get the number of bytes which are used by the wide string @a str (excluding the |
285 | * Get the number of bytes which are used by the wide string @a str (excluding the |
288 | * NULL-terminator). |
286 | * NULL-terminator). |
289 | * |
287 | * |
290 | * @param str Wide string to consider. |
288 | * @param str Wide string to consider. |
291 | * |
289 | * |
292 | * @return Number of bytes used by the wide string |
290 | * @return Number of bytes used by the wide string |
293 | * |
291 | * |
294 | */ |
292 | */ |
295 | size_t wstr_size(const wchar_t *str) |
293 | size_t wstr_size(const wchar_t *str) |
296 | { |
294 | { |
297 | return (wstr_length(str) * sizeof(wchar_t)); |
295 | return (wstr_length(str) * sizeof(wchar_t)); |
298 | } |
296 | } |
299 | 297 | ||
300 | /** Get size of string with length limit. |
298 | /** Get size of string with length limit. |
301 | * |
299 | * |
302 | * Get the number of bytes which are used by up to @a max_len first |
300 | * Get the number of bytes which are used by up to @a max_len first |
303 | * characters in the string @a str. If @a max_len is greater than |
301 | * characters in the string @a str. If @a max_len is greater than |
304 | * the length of @a str, the entire string is measured (excluding the |
302 | * the length of @a str, the entire string is measured (excluding the |
305 | * NULL-terminator). |
303 | * NULL-terminator). |
306 | * |
304 | * |
307 | * @param str String to consider. |
305 | * @param str String to consider. |
308 | * @param max_len Maximum number of characters to measure. |
306 | * @param max_len Maximum number of characters to measure. |
309 | * |
307 | * |
310 | * @return Number of bytes used by the characters. |
308 | * @return Number of bytes used by the characters. |
311 | * |
309 | * |
312 | */ |
310 | */ |
313 | size_t str_lsize(const char *str, count_t max_len) |
311 | size_t str_lsize(const char *str, count_t max_len) |
314 | { |
312 | { |
315 | count_t len = 0; |
313 | count_t len = 0; |
316 | size_t offset = 0; |
314 | size_t offset = 0; |
317 | 315 | ||
318 | while (len < max_len) { |
316 | while (len < max_len) { |
319 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
317 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
320 | break; |
318 | break; |
321 | 319 | ||
322 | len++; |
320 | len++; |
323 | } |
321 | } |
324 | 322 | ||
325 | return offset; |
323 | return offset; |
326 | } |
324 | } |
327 | 325 | ||
328 | /** Get size of wide string with length limit. |
326 | /** Get size of wide string with length limit. |
329 | * |
327 | * |
330 | * Get the number of bytes which are used by up to @a max_len first |
328 | * Get the number of bytes which are used by up to @a max_len first |
331 | * wide characters in the wide string @a str. If @a max_len is greater than |
329 | * wide characters in the wide string @a str. If @a max_len is greater than |
332 | * the length of @a str, the entire wide string is measured (excluding the |
330 | * the length of @a str, the entire wide string is measured (excluding the |
333 | * NULL-terminator). |
331 | * NULL-terminator). |
334 | * |
332 | * |
335 | * @param str Wide string to consider. |
333 | * @param str Wide string to consider. |
336 | * @param max_len Maximum number of wide characters to measure. |
334 | * @param max_len Maximum number of wide characters to measure. |
337 | * |
335 | * |
338 | * @return Number of bytes used by the wide characters. |
336 | * @return Number of bytes used by the wide characters. |
339 | * |
337 | * |
340 | */ |
338 | */ |
341 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
339 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
342 | { |
340 | { |
343 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
341 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
344 | } |
342 | } |
345 | 343 | ||
346 | /** Get number of characters in a string. |
344 | /** Get number of characters in a string. |
347 | * |
345 | * |
348 | * @param str NULL-terminated string. |
346 | * @param str NULL-terminated string. |
349 | * |
347 | * |
350 | * @return Number of characters in string. |
348 | * @return Number of characters in string. |
351 | * |
349 | * |
352 | */ |
350 | */ |
353 | count_t str_length(const char *str) |
351 | count_t str_length(const char *str) |
354 | { |
352 | { |
355 | count_t len = 0; |
353 | count_t len = 0; |
356 | size_t offset = 0; |
354 | size_t offset = 0; |
357 | 355 | ||
358 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
356 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
359 | len++; |
357 | len++; |
360 | 358 | ||
361 | return len; |
359 | return len; |
362 | } |
360 | } |
363 | 361 | ||
364 | /** Get number of characters in a wide string. |
362 | /** Get number of characters in a wide string. |
365 | * |
363 | * |
366 | * @param str NULL-terminated wide string. |
364 | * @param str NULL-terminated wide string. |
367 | * |
365 | * |
368 | * @return Number of characters in @a str. |
366 | * @return Number of characters in @a str. |
369 | * |
367 | * |
370 | */ |
368 | */ |
371 | count_t wstr_length(const wchar_t *wstr) |
369 | count_t wstr_length(const wchar_t *wstr) |
372 | { |
370 | { |
373 | count_t len = 0; |
371 | count_t len = 0; |
374 | 372 | ||
375 | while (*wstr++ != 0) |
373 | while (*wstr++ != 0) |
376 | len++; |
374 | len++; |
377 | 375 | ||
378 | return len; |
376 | return len; |
379 | } |
377 | } |
380 | 378 | ||
381 | /** Get number of characters in a string with size limit. |
379 | /** Get number of characters in a string with size limit. |
382 | * |
380 | * |
383 | * @param str NULL-terminated string. |
381 | * @param str NULL-terminated string. |
384 | * @param size Maximum number of bytes to consider. |
382 | * @param size Maximum number of bytes to consider. |
385 | * |
383 | * |
386 | * @return Number of characters in string. |
384 | * @return Number of characters in string. |
387 | * |
385 | * |
388 | */ |
386 | */ |
389 | count_t str_nlength(const char *str, size_t size) |
387 | count_t str_nlength(const char *str, size_t size) |
390 | { |
388 | { |
391 | count_t len = 0; |
389 | count_t len = 0; |
392 | size_t offset = 0; |
390 | size_t offset = 0; |
393 | 391 | ||
394 | while (str_decode(str, &offset, size) != 0) |
392 | while (str_decode(str, &offset, size) != 0) |
395 | len++; |
393 | len++; |
396 | 394 | ||
397 | return len; |
395 | return len; |
398 | } |
396 | } |
399 | 397 | ||
400 | /** Get number of characters in a string with size limit. |
398 | /** Get number of characters in a string with size limit. |
401 | * |
399 | * |
402 | * @param str NULL-terminated string. |
400 | * @param str NULL-terminated string. |
403 | * @param size Maximum number of bytes to consider. |
401 | * @param size Maximum number of bytes to consider. |
404 | * |
402 | * |
405 | * @return Number of characters in string. |
403 | * @return Number of characters in string. |
406 | * |
404 | * |
407 | */ |
405 | */ |
408 | count_t wstr_nlength(const wchar_t *str, size_t size) |
406 | count_t wstr_nlength(const wchar_t *str, size_t size) |
409 | { |
407 | { |
410 | count_t len = 0; |
408 | count_t len = 0; |
411 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
409 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
412 | count_t offset = 0; |
410 | count_t offset = 0; |
413 | 411 | ||
414 | while ((offset < limit) && (*str++ != 0)) { |
412 | while ((offset < limit) && (*str++ != 0)) { |
415 | len++; |
413 | len++; |
416 | offset += sizeof(wchar_t); |
414 | offset += sizeof(wchar_t); |
417 | } |
415 | } |
418 | 416 | ||
419 | return len; |
417 | return len; |
420 | } |
418 | } |
421 | 419 | ||
422 | /** Check whether character is plain ASCII. |
420 | /** Check whether character is plain ASCII. |
423 | * |
421 | * |
424 | * @return True if character is plain ASCII. |
422 | * @return True if character is plain ASCII. |
425 | * |
423 | * |
426 | */ |
424 | */ |
427 | bool ascii_check(const wchar_t ch) |
425 | bool ascii_check(const wchar_t ch) |
428 | { |
426 | { |
429 | if ((ch >= 0) && (ch <= 127)) |
427 | if ((ch >= 0) && (ch <= 127)) |
430 | return true; |
428 | return true; |
431 | 429 | ||
432 | return false; |
430 | return false; |
433 | } |
431 | } |
434 | 432 | ||
435 | /** Check whether character is valid |
433 | /** Check whether character is valid |
436 | * |
434 | * |
437 | * @return True if character is a valid Unicode code point. |
435 | * @return True if character is a valid Unicode code point. |
438 | * |
436 | * |
439 | */ |
437 | */ |
440 | bool chr_check(const wchar_t ch) |
438 | bool chr_check(const wchar_t ch) |
441 | { |
439 | { |
442 | if ((ch >= 0) && (ch <= 1114111)) |
440 | if ((ch >= 0) && (ch <= 1114111)) |
443 | return true; |
441 | return true; |
444 | 442 | ||
445 | return false; |
443 | return false; |
446 | } |
444 | } |
447 | 445 | ||
448 | /** Compare two NULL terminated strings. |
446 | /** Compare two NULL terminated strings. |
449 | * |
447 | * |
450 | * Do a char-by-char comparison of two NULL-terminated strings. |
448 | * Do a char-by-char comparison of two NULL-terminated strings. |
451 | * The strings are considered equal iff they consist of the same |
449 | * The strings are considered equal iff they consist of the same |
452 | * characters on the minimum of their lengths. |
450 | * characters on the minimum of their lengths. |
453 | * |
451 | * |
454 | * @param s1 First string to compare. |
452 | * @param s1 First string to compare. |
455 | * @param s2 Second string to compare. |
453 | * @param s2 Second string to compare. |
456 | * |
454 | * |
457 | * @return 0 if the strings are equal, -1 if first is smaller, |
455 | * @return 0 if the strings are equal, -1 if first is smaller, |
458 | * 1 if second smaller. |
456 | * 1 if second smaller. |
459 | * |
457 | * |
460 | */ |
458 | */ |
461 | int str_cmp(const char *s1, const char *s2) |
459 | int str_cmp(const char *s1, const char *s2) |
462 | { |
460 | { |
463 | wchar_t c1; |
461 | wchar_t c1; |
464 | wchar_t c2; |
462 | wchar_t c2; |
465 | 463 | ||
466 | size_t off1 = 0; |
464 | size_t off1 = 0; |
467 | size_t off2 = 0; |
465 | size_t off2 = 0; |
468 | 466 | ||
469 | while ((c1 = str_decode(s1, &off1, STR_NO_LIMIT) != 0) |
467 | while ((c1 = str_decode(s1, &off1, STR_NO_LIMIT) != 0) |
470 | && (c2 = str_decode(s2, &off2, STR_NO_LIMIT) != 0)) { |
468 | && (c2 = str_decode(s2, &off2, STR_NO_LIMIT) != 0)) { |
471 | 469 | ||
472 | if (off1 != off2) |
470 | if (off1 != off2) |
473 | break; |
471 | break; |
474 | 472 | ||
475 | if (c1 < c2) |
473 | if (c1 < c2) |
476 | return -1; |
474 | return -1; |
477 | 475 | ||
478 | if (c1 > c2) |
476 | if (c1 > c2) |
479 | return 1; |
477 | return 1; |
480 | } |
478 | } |
481 | 479 | ||
482 | if ((off1 == off2) && (c1 == c2)) |
480 | if ((off1 == off2) && (c1 == c2)) |
483 | return 0; |
481 | return 0; |
484 | 482 | ||
485 | if ((c1 == 0) || (off1 < off2)) |
483 | if ((c1 == 0) || (off1 < off2)) |
486 | return -1; |
484 | return -1; |
487 | 485 | ||
488 | return 1; |
486 | return 1; |
489 | } |
487 | } |
490 | 488 | ||
491 | /** Compare two NULL terminated strings with length limit. |
489 | /** Compare two NULL terminated strings with length limit. |
492 | * |
490 | * |
493 | * Do a char-by-char comparison of two NULL-terminated strings. |
491 | * Do a char-by-char comparison of two NULL-terminated strings. |
494 | * The strings are considered equal iff they consist of the same |
492 | * The strings are considered equal iff they consist of the same |
495 | * characters on the minimum of their lengths and the length limit. |
493 | * characters on the minimum of their lengths and the length limit. |
496 | * |
494 | * |
497 | * @param s1 First string to compare. |
495 | * @param s1 First string to compare. |
498 | * @param s2 Second string to compare. |
496 | * @param s2 Second string to compare. |
499 | * @param max_len Maximum number of characters to consider. |
497 | * @param max_len Maximum number of characters to consider. |
500 | * |
498 | * |
501 | * @return 0 if the strings are equal, -1 if first is smaller, |
499 | * @return 0 if the strings are equal, -1 if first is smaller, |
502 | * 1 if second smaller. |
500 | * 1 if second smaller. |
503 | * |
501 | * |
504 | */ |
502 | */ |
505 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
503 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
506 | { |
504 | { |
507 | wchar_t c1 = 0; |
505 | wchar_t c1 = 0; |
508 | wchar_t c2 = 0; |
506 | wchar_t c2 = 0; |
509 | 507 | ||
510 | size_t off1 = 0; |
508 | size_t off1 = 0; |
511 | size_t off2 = 0; |
509 | size_t off2 = 0; |
512 | 510 | ||
513 | count_t len = 0; |
511 | count_t len = 0; |
514 | 512 | ||
515 | while ((len < max_len) |
513 | while ((len < max_len) |
516 | && ((c1 = str_decode(s1, &off1, STR_NO_LIMIT)) != 0) |
514 | && ((c1 = str_decode(s1, &off1, STR_NO_LIMIT)) != 0) |
517 | && ((c2 = str_decode(s2, &off2, STR_NO_LIMIT)) != 0)) { |
515 | && ((c2 = str_decode(s2, &off2, STR_NO_LIMIT)) != 0)) { |
518 | 516 | ||
519 | if (off1 != off2) |
517 | if (off1 != off2) |
520 | break; |
518 | break; |
521 | 519 | ||
522 | if (c1 < c2) |
520 | if (c1 < c2) |
523 | return -1; |
521 | return -1; |
524 | 522 | ||
525 | if (c1 > c2) |
523 | if (c1 > c2) |
526 | return 1; |
524 | return 1; |
527 | 525 | ||
528 | len++; |
526 | len++; |
529 | } |
527 | } |
530 | 528 | ||
531 | if ((off1 == off2) && (len == max_len) && (c1 == c2)) |
529 | if ((off1 == off2) && (len == max_len) && (c1 == c2)) |
532 | return 0; |
530 | return 0; |
533 | 531 | ||
534 | if ((c1 == 0) || (off1 < off2)) |
532 | if ((c1 == 0) || (off1 < off2)) |
535 | return -1; |
533 | return -1; |
536 | 534 | ||
537 | return 1; |
535 | return 1; |
538 | } |
536 | } |
539 | 537 | ||
540 | /** Copy NULL-terminated string. |
538 | /** Copy NULL-terminated string. |
541 | * |
539 | * |
542 | * Copy source string @a src to destination buffer @a dst. |
540 | * Copy source string @a src to destination buffer @a dst. |
543 | * No more than @a size bytes are written. NULL-terminator is always |
541 | * No more than @a size bytes are written. NULL-terminator is always |
544 | * written after the last succesfully copied character (i.e. if the |
542 | * written after the last succesfully copied character (i.e. if the |
545 | * destination buffer is has at least 1 byte, it will be always |
543 | * destination buffer is has at least 1 byte, it will be always |
546 | * NULL-terminated). |
544 | * NULL-terminated). |
547 | * |
545 | * |
548 | * @param src Source string. |
546 | * @param src Source string. |
549 | * @param dst Destination buffer. |
547 | * @param dst Destination buffer. |
550 | * @param count Size of the destination buffer. |
548 | * @param count Size of the destination buffer. |
551 | * |
549 | * |
552 | */ |
550 | */ |
553 | void str_ncpy(char *dst, const char *src, size_t size) |
551 | void str_ncpy(char *dst, const char *src, size_t size) |
554 | { |
552 | { |
555 | /* No space for the NULL-terminator in the buffer */ |
553 | /* No space for the NULL-terminator in the buffer */ |
556 | if (size == 0) |
554 | if (size == 0) |
557 | return; |
555 | return; |
558 | 556 | ||
559 | wchar_t ch; |
557 | wchar_t ch; |
560 | size_t str_off = 0; |
558 | size_t str_off = 0; |
561 | size_t dst_off = 0; |
559 | size_t dst_off = 0; |
562 | 560 | ||
563 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT) != 0)) { |
561 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT) != 0)) { |
564 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
562 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
565 | break; |
563 | break; |
566 | } |
564 | } |
567 | 565 | ||
568 | if (dst_off >= size) |
566 | if (dst_off >= size) |
569 | dst[size - 1] = 0; |
567 | dst[size - 1] = 0; |
570 | else |
568 | else |
571 | dst[dst_off] = 0; |
569 | dst[dst_off] = 0; |
572 | } |
570 | } |
573 | 571 | ||
574 | /** Copy NULL-terminated wide string to string |
572 | /** Copy NULL-terminated wide string to string |
575 | * |
573 | * |
576 | * Copy source wide string @a src to destination buffer @a dst. |
574 | * Copy source wide string @a src to destination buffer @a dst. |
577 | * No more than @a size bytes are written. NULL-terminator is always |
575 | * No more than @a size bytes are written. NULL-terminator is always |
578 | * written after the last succesfully copied character (i.e. if the |
576 | * written after the last succesfully copied character (i.e. if the |
579 | * destination buffer is has at least 1 byte, it will be always |
577 | * destination buffer is has at least 1 byte, it will be always |
580 | * NULL-terminated). |
578 | * NULL-terminated). |
581 | * |
579 | * |
582 | * @param src Source wide string. |
580 | * @param src Source wide string. |
583 | * @param dst Destination buffer. |
581 | * @param dst Destination buffer. |
584 | * @param count Size of the destination buffer. |
582 | * @param count Size of the destination buffer. |
585 | * |
583 | * |
586 | */ |
584 | */ |
587 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
585 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
588 | { |
586 | { |
589 | /* No space for the NULL-terminator in the buffer */ |
587 | /* No space for the NULL-terminator in the buffer */ |
590 | if (size == 0) |
588 | if (size == 0) |
591 | return; |
589 | return; |
592 | 590 | ||
593 | wchar_t ch; |
591 | wchar_t ch; |
594 | count_t src_idx = 0; |
592 | count_t src_idx = 0; |
595 | size_t dst_off = 0; |
593 | size_t dst_off = 0; |
596 | 594 | ||
597 | while ((ch = src[src_idx++]) != 0) { |
595 | while ((ch = src[src_idx++]) != 0) { |
598 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
596 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
599 | break; |
597 | break; |
600 | } |
598 | } |
601 | 599 | ||
602 | if (dst_off >= size) |
600 | if (dst_off >= size) |
603 | dst[size - 1] = 0; |
601 | dst[size - 1] = 0; |
604 | else |
602 | else |
605 | dst[dst_off] = 0; |
603 | dst[dst_off] = 0; |
606 | } |
604 | } |
607 | 605 | ||
608 | /** Find first occurence of character in string. |
606 | /** Find first occurence of character in string. |
609 | * |
607 | * |
610 | * @param str String to search. |
608 | * @param str String to search. |
611 | * @param ch Character to look for. |
609 | * @param ch Character to look for. |
612 | * |
610 | * |
613 | * @return Pointer to character in @a str or NULL if not found. |
611 | * @return Pointer to character in @a str or NULL if not found. |
614 | * |
612 | * |
615 | */ |
613 | */ |
616 | const char *str_chr(const char *str, wchar_t ch) |
614 | const char *str_chr(const char *str, wchar_t ch) |
617 | { |
615 | { |
618 | wchar_t acc; |
616 | wchar_t acc; |
619 | size_t off = 0; |
617 | size_t off = 0; |
620 | 618 | ||
621 | while ((acc = str_decode(str, &off, STR_NO_LIMIT) != 0)) { |
619 | while ((acc = str_decode(str, &off, STR_NO_LIMIT) != 0)) { |
622 | if (acc == ch) |
620 | if (acc == ch) |
623 | return (str + off); |
621 | return (str + off); |
624 | } |
622 | } |
625 | 623 | ||
626 | return NULL; |
624 | return NULL; |
627 | } |
625 | } |
628 | 626 | ||
629 | /** Insert a wide character into a wide string. |
627 | /** Insert a wide character into a wide string. |
630 | * |
628 | * |
631 | * Insert a wide character into a wide string at position |
629 | * Insert a wide character into a wide string at position |
632 | * @a pos. The characters after the position are shifted. |
630 | * @a pos. The characters after the position are shifted. |
633 | * |
631 | * |
634 | * @param str String to insert to. |
632 | * @param str String to insert to. |
635 | * @param ch Character to insert to. |
633 | * @param ch Character to insert to. |
636 | * @param pos Character index where to insert. |
634 | * @param pos Character index where to insert. |
637 | @ @param max_pos Characters in the buffer. |
635 | @ @param max_pos Characters in the buffer. |
638 | * |
636 | * |
639 | * @return True if the insertion was sucessful, false if the position |
637 | * @return True if the insertion was sucessful, false if the position |
640 | * is out of bounds. |
638 | * is out of bounds. |
641 | * |
639 | * |
642 | */ |
640 | */ |
643 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
641 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
644 | { |
642 | { |
645 | count_t len = wstr_length(str); |
643 | count_t len = wstr_length(str); |
646 | 644 | ||
647 | if ((pos > len) || (pos + 1 > max_pos)) |
645 | if ((pos > len) || (pos + 1 > max_pos)) |
648 | return false; |
646 | return false; |
649 | 647 | ||
650 | count_t i; |
648 | count_t i; |
651 | for (i = len; i + 1 > pos; i--) |
649 | for (i = len; i + 1 > pos; i--) |
652 | str[i + 1] = str[i]; |
650 | str[i + 1] = str[i]; |
653 | 651 | ||
654 | str[pos] = ch; |
652 | str[pos] = ch; |
655 | 653 | ||
656 | return true; |
654 | return true; |
657 | } |
655 | } |
658 | 656 | ||
659 | /** Remove a wide character from a wide string. |
657 | /** Remove a wide character from a wide string. |
660 | * |
658 | * |
661 | * Remove a wide character from a wide string at position |
659 | * Remove a wide character from a wide string at position |
662 | * @a pos. The characters after the position are shifted. |
660 | * @a pos. The characters after the position are shifted. |
663 | * |
661 | * |
664 | * @param str String to remove from. |
662 | * @param str String to remove from. |
665 | * @param pos Character index to remove. |
663 | * @param pos Character index to remove. |
666 | * |
664 | * |
667 | * @return True if the removal was sucessful, false if the position |
665 | * @return True if the removal was sucessful, false if the position |
668 | * is out of bounds. |
666 | * is out of bounds. |
669 | * |
667 | * |
670 | */ |
668 | */ |
671 | bool wstr_remove(wchar_t *str, count_t pos) |
669 | bool wstr_remove(wchar_t *str, count_t pos) |
672 | { |
670 | { |
673 | count_t len = wstr_length(str); |
671 | count_t len = wstr_length(str); |
674 | 672 | ||
675 | if (pos >= len) |
673 | if (pos >= len) |
676 | return false; |
674 | return false; |
677 | 675 | ||
678 | count_t i; |
676 | count_t i; |
679 | for (i = pos + 1; i <= len; i++) |
677 | for (i = pos + 1; i <= len; i++) |
680 | str[i - 1] = str[i]; |
678 | str[i - 1] = str[i]; |
681 | 679 | ||
682 | return true; |
680 | return true; |
683 | } |
681 | } |
684 | 682 | ||
685 | /** @} |
683 | /** @} |
686 | */ |
684 | */ |
687 | 685 |