Rev 4209 | Rev 4224 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 4209 | Rev 4212 | ||
---|---|---|---|
Line 35... | Line 35... | ||
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. |
40 | * represented as wchar_t.@n |
41 | * |
41 | * |
42 | * Strings have the following metrics: |
42 | * Overview of the terminology:@n |
43 | * |
43 | * |
- | 44 | * Term Meaning |
|
- | 45 | * -------------------- ---------------------------------------------------- |
|
- | 46 | * byte 8 bits stored in uint8_t (unsigned 8 bit integer) |
|
- | 47 | * |
|
- | 48 | * character UTF-32 encoded Unicode character, stored in wchar_t |
|
- | 49 | * (signed 32 bit integer), code points 0 .. 1114111 |
|
- | 50 | * are valid |
|
- | 51 | * |
|
- | 52 | * ASCII character 7 bit encoded ASCII character, stored in char |
|
- | 53 | * (usually signed 8 bit integer), code points 0 .. 127 |
|
- | 54 | * are valid |
|
- | 55 | * |
|
- | 56 | * string UTF-8 encoded NULL-terminated Unicode string, char * |
|
- | 57 | * |
|
- | 58 | * wide string UTF-32 encoded NULL-terminated Unicode string, |
|
- | 59 | * wchar_t * |
|
- | 60 | * |
|
- | 61 | * [wide] string size number of BYTES in a [wide] string (excluding |
|
- | 62 | * the NULL-terminator), size_t |
|
- | 63 | * |
|
- | 64 | * [wide] string length number of CHARACTERS in a [wide] string (excluding |
|
- | 65 | * the NULL-terminator), count_t |
|
- | 66 | * |
|
- | 67 | * [wide] string width number of display cells on a monospace display taken |
|
- | 68 | * by a [wide] string, count_t |
|
- | 69 | * |
|
- | 70 | * |
|
- | 71 | * Overview of string metrics:@n |
|
- | 72 | * |
|
44 | * Metric Abbrev. Meaning |
73 | * Metric Abbrev. Type Meaning |
45 | * ------ ------ ------- |
74 | * ------ ------ ------ ------------------------------------------------- |
46 | * size n Number of bytes the string is encoded into, excluding |
75 | * size n size_t number of BYTES in a string (excluding the |
47 | * the null terminator. |
76 | * NULL-terminator) |
- | 77 | * |
|
48 | * length l The number of characters in the string, excluding |
78 | * length l count_t number of CHARACTERS in a string (excluding the |
49 | * the null terminator. |
79 | * null terminator) |
- | 80 | * |
|
50 | * width w The number of character cells the string takes up on a |
81 | * width w count_t number of display cells on a monospace display |
51 | * monospace display. |
82 | * taken by a string |
- | 83 | * |
|
52 | * |
84 | * |
53 | * Naming scheme: |
85 | * Function naming prefixes:@n |
54 | * |
86 | * |
55 | * chr_xxx operate on characters |
87 | * chr_ operate on characters |
- | 88 | * ascii_ operate on ASCII characters |
|
56 | * str_xxx operate on strings |
89 | * str_ operate on strings |
57 | * wstr_xxx operate on wide strings |
90 | * wstr_ operate on wide strings |
- | 91 | * |
|
- | 92 | * [w]str_[n|l|w] operate on a prefix limited by size, length |
|
- | 93 | * or width |
|
- | 94 | * |
|
- | 95 | * |
|
- | 96 | * A specific character inside a [wide] string can be referred to by:@n |
|
- | 97 | * |
|
- | 98 | * pointer (char *, wchar_t *) |
|
- | 99 | * byte offset (size_t) |
|
- | 100 | * character index (count_t) |
|
58 | * |
101 | * |
59 | * [w]str_[n|l|w]xxx operate on a prefix limited by size, length |
- | |
60 | * or width. |
- | |
61 | */ |
102 | */ |
62 | 103 | ||
63 | #include <string.h> |
104 | #include <string.h> |
64 | #include <print.h> |
105 | #include <print.h> |
65 | #include <cpu.h> |
106 | #include <cpu.h> |
66 | #include <arch/asm.h> |
107 | #include <arch/asm.h> |
67 | #include <arch.h> |
108 | #include <arch.h> |
68 | #include <errno.h> |
109 | #include <errno.h> |
69 | #include <console/kconsole.h> |
110 | #include <align.h> |
70 | 111 | ||
71 | char invalch = '?'; |
112 | char invalch = '?'; |
72 | 113 | ||
73 | /** Byte mask consisting of lowest @n bits (out of eight). */ |
114 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
74 | #define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1)) |
115 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
75 | 116 | ||
76 | /** Byte mask consisting of lowest @n bits (out of 32). */ |
117 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
77 | #define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1)) |
118 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
78 | 119 | ||
79 | /** Byte mask consisting of highest @n bits (out of eight). */ |
120 | /** Byte mask consisting of highest @n bits (out of 8) */ |
80 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
121 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
81 | 122 | ||
82 | /** Number of data bits in a UTF-8 continuation byte. */ |
123 | /** Number of data bits in a UTF-8 continuation byte */ |
83 | #define CONT_BITS 6 |
124 | #define CONT_BITS 6 |
84 | 125 | ||
85 | /** Decode a single character from a substring. |
126 | /** Decode a single character from a string. |
86 | * |
127 | * |
87 | * Decode a single character from a substring of size @a sz. Decoding starts |
128 | * Decode a single character from a string of size @a size. Decoding starts |
88 | * at @a offset and this offset is moved to the beginning of the next |
129 | * at @a offset and this offset is moved to the beginning of the next |
89 | * character. In case of decoding error, offset generally advances at least |
130 | * character. In case of decoding error, offset generally advances at least |
90 | * by one. However, offset is never moved beyond (str + sz). |
131 | * by one. However, offset is never moved beyond size. |
91 | * |
132 | * |
92 | * @param str String (not necessarily NULL-terminated). |
133 | * @param str String (not necessarily NULL-terminated). |
93 | * @param index Index (counted in plain characters) where to start |
134 | * @param offset Byte offset in string where to start decoding. |
94 | * the decoding. |
135 | * @param size Size of the string (in bytes). |
- | 136 | * |
|
- | 137 | * @return Value of decoded character, invalch on decoding error or |
|
95 | * @param limit Size of the substring. |
138 | * NULL if attempt to decode beyond @a size. |
96 | * |
139 | * |
97 | * @return Value of decoded character or '?' on decoding error. |
- | |
98 | */ |
140 | */ |
99 | wchar_t chr_decode(const char *str, size_t *offset, size_t sz) |
141 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
100 | { |
142 | { |
101 | uint8_t b0, b; /* Bytes read from str. */ |
143 | if (*offset + 1 > size) |
102 | wchar_t ch; |
144 | return 0; |
103 | 145 | ||
104 | int b0_bits; /* Data bits in first byte. */ |
146 | /* First byte read from string */ |
105 | int cbytes; /* Number of continuation bytes. */ |
147 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
106 | 148 | ||
107 | if (*offset + 1 > sz) |
- | |
108 | return invalch; |
149 | /* Determine code length */ |
109 | 150 | ||
110 | b0 = (uint8_t) str[(*offset)++]; |
151 | unsigned int b0_bits; /* Data bits in first byte */ |
111 | - | ||
112 | /* Determine code length. */ |
152 | unsigned int cbytes; /* Number of continuation bytes */ |
113 | 153 | ||
114 | if ((b0 & 0x80) == 0) { |
154 | if ((b0 & 0x80) == 0) { |
115 | /* 0xxxxxxx (Plain ASCII) */ |
155 | /* 0xxxxxxx (Plain ASCII) */ |
116 | b0_bits = 7; |
156 | b0_bits = 7; |
117 | cbytes = 0; |
157 | cbytes = 0; |
118 | } else if ((b0 & 0xe0) == 0xc0) { |
158 | } else if ((b0 & 0xe0) == 0xc0) { |
Line 126... | Line 166... | ||
126 | } else if ((b0 & 0xf8) == 0xf0) { |
166 | } else if ((b0 & 0xf8) == 0xf0) { |
127 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
167 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
128 | b0_bits = 3; |
168 | b0_bits = 3; |
129 | cbytes = 3; |
169 | cbytes = 3; |
130 | } else { |
170 | } else { |
131 | /* 10xxxxxx -- unexpected continuation byte. */ |
171 | /* 10xxxxxx -- unexpected continuation byte */ |
132 | return invalch; |
172 | return invalch; |
133 | } |
173 | } |
134 | 174 | ||
135 | if (*offset + cbytes > sz) { |
175 | if (*offset + cbytes > size) |
136 | return invalch; |
176 | return invalch; |
137 | } |
177 | |
138 | - | ||
139 | ch = b0 & LO_MASK_8(b0_bits); |
178 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
140 | 179 | ||
141 | /* Decode continuation bytes. */ |
180 | /* Decode continuation bytes */ |
142 | while (cbytes > 0) { |
181 | while (cbytes > 0) { |
143 | b = (uint8_t) str[(*offset)++]; |
182 | uint8_t b = (uint8_t) str[(*offset)++]; |
144 | 183 | ||
145 | /* Must be 10xxxxxx. */ |
184 | /* Must be 10xxxxxx */ |
146 | if ((b & 0xc0) != 0x80) { |
185 | if ((b & 0xc0) != 0x80) |
147 | return invalch; |
186 | return invalch; |
148 | } |
187 | |
149 | - | ||
150 | /* Shift data bits to ch. */ |
188 | /* Shift data bits to ch */ |
151 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
189 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
152 | --cbytes; |
190 | cbytes--; |
153 | } |
191 | } |
154 | 192 | ||
155 | return ch; |
193 | return ch; |
156 | } |
194 | } |
157 | 195 | ||
158 | /** Encode a single character to string representation. |
196 | /** Encode a single character to string representation. |
159 | * |
197 | * |
160 | * Encode a single character to string representation (i.e. UTF-8) and store |
198 | * Encode a single character to string representation (i.e. UTF-8) and store |
161 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
199 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
162 | * is moved to the position where the next character can be written to. |
200 | * is moved to the position where the next character can be written to. |
163 | * |
201 | * |
164 | * @param ch Input character. |
202 | * @param ch Input character. |
165 | * @param str Output buffer. |
203 | * @param str Output buffer. |
166 | * @param offset Offset (in bytes) where to start writing. |
204 | * @param offset Byte offset where to start writing. |
167 | * @param sz Size of the output buffer. |
205 | * @param size Size of the output buffer (in bytes). |
168 | * |
206 | * |
169 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
207 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
170 | * was not enough space in the output buffer or EINVAL if the character |
208 | * was not enough space in the output buffer or EINVAL if the character |
171 | * code was invalid. |
209 | * code was invalid. |
172 | */ |
210 | */ |
173 | int chr_encode(wchar_t ch, char *str, size_t *offset, size_t sz) |
211 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
174 | { |
212 | { |
175 | uint32_t cc; /* Unsigned version of ch. */ |
- | |
176 | - | ||
177 | int cbytes; /* Number of continuation bytes. */ |
- | |
178 | int b0_bits; /* Number of data bits in first byte. */ |
- | |
179 | int i; |
- | |
180 | - | ||
181 | if (*offset >= sz) |
213 | if (*offset >= size) |
182 | return EOVERFLOW; |
214 | return EOVERFLOW; |
183 | 215 | ||
184 | if (ch < 0) |
216 | if (!chr_check(ch)) |
185 | return EINVAL; |
217 | return EINVAL; |
186 | 218 | ||
187 | /* Bit operations should only be done on unsigned numbers. */ |
219 | /* Unsigned version of ch (bit operations should only be done |
- | 220 | on unsigned types). */ |
|
188 | cc = (uint32_t) ch; |
221 | uint32_t cc = (uint32_t) ch; |
189 | 222 | ||
190 | /* Determine how many continuation bytes are needed. */ |
223 | /* Determine how many continuation bytes are needed */ |
- | 224 | ||
- | 225 | unsigned int b0_bits; /* Data bits in first byte */ |
|
- | 226 | unsigned int cbytes; /* Number of continuation bytes */ |
|
- | 227 | ||
191 | if ((cc & ~LO_MASK_32(7)) == 0) { |
228 | if ((cc & ~LO_MASK_32(7)) == 0) { |
192 | b0_bits = 7; |
229 | b0_bits = 7; |
193 | cbytes = 0; |
230 | cbytes = 0; |
194 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
231 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
195 | b0_bits = 5; |
232 | b0_bits = 5; |
Line 199... | Line 236... | ||
199 | cbytes = 2; |
236 | cbytes = 2; |
200 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
237 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
201 | b0_bits = 3; |
238 | b0_bits = 3; |
202 | cbytes = 3; |
239 | cbytes = 3; |
203 | } else { |
240 | } else { |
204 | /* Codes longer than 21 bits are not supported. */ |
241 | /* Codes longer than 21 bits are not supported */ |
205 | return EINVAL; |
242 | return EINVAL; |
206 | } |
243 | } |
207 | 244 | ||
208 | /* Check for available space in buffer. */ |
245 | /* Check for available space in buffer */ |
209 | if (*offset + cbytes >= sz) |
246 | if (*offset + cbytes >= size) |
210 | return EOVERFLOW; |
247 | return EOVERFLOW; |
211 | 248 | ||
212 | /* Encode continuation bytes. */ |
249 | /* Encode continuation bytes */ |
- | 250 | unsigned int i; |
|
213 | for (i = cbytes; i > 0; --i) { |
251 | for (i = cbytes; i > 0; i--) { |
214 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
252 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
215 | cc = cc >> CONT_BITS; |
253 | cc = cc >> CONT_BITS; |
216 | } |
254 | } |
217 | 255 | ||
218 | /* Encode first byte. */ |
256 | /* Encode first byte */ |
219 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
257 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
220 | 258 | ||
221 | /* Advance offset. */ |
259 | /* Advance offset */ |
222 | *offset += (1 + cbytes); |
260 | *offset += cbytes + 1; |
223 | 261 | ||
224 | return EOK; |
262 | return EOK; |
225 | } |
263 | } |
226 | 264 | ||
227 | /** Get display width of character. |
265 | /** Get size of string. |
- | 266 | * |
|
- | 267 | * Get the number of bytes which are used by the string @a str (excluding the |
|
- | 268 | * NULL-terminator). |
|
- | 269 | * |
|
- | 270 | * @param str String to consider. |
|
- | 271 | * |
|
- | 272 | * @return Number of bytes used by the string |
|
228 | * |
273 | * |
229 | * @param ch The character. |
- | |
230 | * @return Character width in display cells. |
- | |
231 | */ |
274 | */ |
232 | count_t chr_width(wchar_t ch) |
275 | size_t str_size(const char *str) |
233 | { |
276 | { |
- | 277 | size_t size = 0; |
|
- | 278 | ||
- | 279 | while (*str++ != 0) |
|
- | 280 | size++; |
|
- | 281 | ||
234 | return 1; |
282 | return size; |
235 | } |
283 | } |
236 | 284 | ||
- | 285 | /** Get size of wide string. |
|
- | 286 | * |
|
- | 287 | * Get the number of bytes which are used by the wide string @a str (excluding the |
|
- | 288 | * NULL-terminator). |
|
- | 289 | * |
|
- | 290 | * @param str Wide string to consider. |
|
- | 291 | * |
|
- | 292 | * @return Number of bytes used by the wide string |
|
- | 293 | * |
|
- | 294 | */ |
|
- | 295 | size_t wstr_size(const wchar_t *str) |
|
- | 296 | { |
|
- | 297 | return (wstr_length(str) * sizeof(wchar_t)); |
|
- | 298 | } |
|
- | 299 | ||
237 | /** Get size of string, with length limit. |
300 | /** Get size of string with length limit. |
238 | * |
301 | * |
239 | * Get the number of bytes which are used by up to @a max_len first |
302 | * Get the number of bytes which are used by up to @a max_len first |
240 | * characters in the string @a str. If @a max_len is greater than |
303 | * characters in the string @a str. If @a max_len is greater than |
241 | * the length of @a str, the entire string is measured. |
304 | * the length of @a str, the entire string is measured (excluding the |
- | 305 | * NULL-terminator). |
|
242 | * |
306 | * |
243 | * @param str String to consider. |
307 | * @param str String to consider. |
244 | * @param count Maximum number of characters to measure. |
308 | * @param max_len Maximum number of characters to measure. |
- | 309 | * |
|
- | 310 | * @return Number of bytes used by the characters. |
|
245 | * |
311 | * |
246 | * @return Number of bytes used by the characters. |
- | |
247 | */ |
312 | */ |
248 | size_t str_lsize(const char *str, count_t max_len) |
313 | size_t str_lsize(const char *str, count_t max_len) |
249 | { |
314 | { |
250 | count_t len = 0; |
315 | count_t len = 0; |
251 | size_t cur = 0; |
316 | size_t offset = 0; |
252 | size_t prev; |
- | |
253 | wchar_t ch; |
- | |
254 | 317 | ||
255 | while (true) { |
318 | while (len < max_len) { |
256 | prev = cur; |
- | |
257 | if (len >= max_len) |
319 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
258 | break; |
320 | break; |
259 | ch = chr_decode(str, &cur, UTF8_NO_LIMIT); |
- | |
260 | if (ch == '\0') break; |
- | |
261 | 321 | ||
262 | len++; |
322 | len++; |
263 | } |
323 | } |
264 | 324 | ||
265 | return prev; |
325 | return offset; |
266 | } |
326 | } |
267 | 327 | ||
268 | /** Get size of string, with width limit. |
328 | /** Get size of wide string with length limit. |
- | 329 | * |
|
- | 330 | * 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 |
|
- | 332 | * the length of @a str, the entire wide string is measured (excluding the |
|
- | 333 | * NULL-terminator). |
|
269 | * |
334 | * |
270 | * Get the number of bytes which are used by the longest prefix of @a str |
335 | * @param str Wide string to consider. |
271 | * that can fit into @a max_width display cells. |
336 | * @param max_len Maximum number of wide characters to measure. |
272 | * |
337 | * |
273 | * @param str String to consider. |
- | |
274 | * @param count Maximum number of display cells. |
338 | * @return Number of bytes used by the wide characters. |
275 | * |
339 | * |
276 | * @return Number of bytes used by the characters that fit. |
- | |
277 | */ |
340 | */ |
278 | size_t str_wsize(const char *str, count_t max_width) |
341 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
279 | { |
342 | { |
280 | count_t width = 0; |
- | |
281 | size_t cur = 0; |
- | |
282 | size_t prev; |
- | |
283 | wchar_t ch; |
- | |
284 | - | ||
285 | while (true) { |
- | |
286 | prev = cur; |
- | |
287 | if (width >= max_width) |
- | |
288 | break; |
- | |
289 | ch = chr_decode(str, &cur, UTF8_NO_LIMIT); |
343 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
290 | if (ch == '\0') break; |
- | |
291 | - | ||
292 | width += chr_width(ch); |
- | |
293 | } |
- | |
294 | - | ||
295 | return prev; |
- | |
296 | } |
344 | } |
297 | 345 | ||
298 | - | ||
299 | /** Get length of wide string, with width limit. |
346 | /** Get number of characters in a string. |
300 | * |
347 | * |
301 | * Get the number of characters in a wide string that can fit into @a max_width |
348 | * @param str NULL-terminated string. |
302 | * display cells. |
- | |
303 | * |
349 | * |
304 | * @param wstr Wide string to consider. |
350 | * @return Number of characters in string. |
305 | * @param count Maximum number of display cells. |
- | |
306 | * |
351 | * |
307 | * @return Number of bytes used by the characters that fit. |
- | |
308 | */ |
352 | */ |
309 | count_t wstr_wlength(const wchar_t *wstr, count_t max_width) |
353 | count_t str_length(const char *str) |
310 | { |
354 | { |
311 | count_t width = 0; |
355 | count_t len = 0; |
312 | index_t cur = 0; |
356 | size_t offset = 0; |
313 | 357 | ||
314 | while (true) { |
- | |
315 | if (width >= max_width) |
- | |
316 | break; |
- | |
317 | if (wstr[cur] == '\0') break; |
358 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
318 | - | ||
319 | width += chr_width(wstr[cur]); |
- | |
320 | ++cur; |
359 | len++; |
321 | } |
360 | |
322 | - | ||
323 | return (count_t) cur; |
361 | return len; |
324 | } |
362 | } |
325 | 363 | ||
326 | /** Check whether character is plain ASCII. |
364 | /** Get number of characters in a wide string. |
327 | * |
365 | * |
- | 366 | * @param str NULL-terminated wide string. |
|
- | 367 | * |
|
328 | * @return True if character is plain ASCII. |
368 | * @return Number of characters in @a str. |
329 | * |
369 | * |
330 | */ |
370 | */ |
331 | bool ascii_check(const wchar_t ch) |
371 | count_t wstr_length(const wchar_t *wstr) |
332 | { |
372 | { |
333 | if ((ch >= 0) && (ch <= 127)) |
- | |
334 | return true; |
373 | count_t len = 0; |
335 | 374 | ||
- | 375 | while (*wstr++ != 0) |
|
- | 376 | len++; |
|
- | 377 | ||
336 | return false; |
378 | return len; |
337 | } |
379 | } |
338 | 380 | ||
- | 381 | /** Get number of characters in a string with size limit. |
|
- | 382 | * |
|
- | 383 | * @param str NULL-terminated string. |
|
- | 384 | * @param size Maximum number of bytes to consider. |
|
- | 385 | * |
|
339 | /** Check whether character is Unicode. |
386 | * @return Number of characters in string. |
340 | * |
387 | * |
341 | * @return True if character is valid Unicode code point. |
- | |
342 | */ |
388 | */ |
343 | bool unicode_check(const wchar_t ch) |
389 | count_t str_nlength(const char *str, size_t size) |
344 | { |
390 | { |
345 | if ((ch >= 0) && (ch <= 1114111)) |
391 | count_t len = 0; |
346 | return true; |
392 | size_t offset = 0; |
347 | 393 | ||
- | 394 | while (str_decode(str, &offset, size) != 0) |
|
- | 395 | len++; |
|
- | 396 | ||
348 | return false; |
397 | return len; |
349 | } |
398 | } |
350 | 399 | ||
351 | /** Return number of bytes the string occupies. |
400 | /** Get number of characters in a string with size limit. |
352 | * |
401 | * |
353 | * @param str A string. |
402 | * @param str NULL-terminated string. |
354 | * @return Number of bytes in @a str excluding the null terminator. |
- | |
355 | */ |
- | |
356 | size_t str_size(const char *str) |
- | |
357 | { |
- | |
358 | size_t size; |
- | |
359 | - | ||
360 | size = 0; |
- | |
361 | while (*str++ != '\0') |
- | |
362 | ++size; |
- | |
363 | - | ||
364 | return size; |
- | |
365 | } |
- | |
366 | - | ||
367 | /** Return number of characters in a string. |
403 | * @param size Maximum number of bytes to consider. |
368 | * |
404 | * |
369 | * @param str NULL-terminated string. |
- | |
370 | * @return Number of characters in string. |
405 | * @return Number of characters in string. |
- | 406 | * |
|
371 | */ |
407 | */ |
372 | count_t str_length(const char *str) |
408 | count_t wstr_nlength(const wchar_t *str, size_t size) |
373 | { |
409 | { |
374 | count_t len = 0; |
410 | count_t len = 0; |
- | 411 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
|
375 | size_t offset = 0; |
412 | count_t offset = 0; |
376 | 413 | ||
377 | while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) { |
414 | while ((offset < limit) && (*str++ != 0)) { |
378 | len++; |
415 | len++; |
- | 416 | offset += sizeof(wchar_t); |
|
379 | } |
417 | } |
380 | 418 | ||
381 | return len; |
419 | return len; |
382 | } |
420 | } |
383 | 421 | ||
- | 422 | /** Check whether character is plain ASCII. |
|
- | 423 | * |
|
384 | /** Return number of characters in a wide string. |
424 | * @return True if character is plain ASCII. |
385 | * |
425 | * |
386 | * @param str NULL-terminated wide string. |
- | |
387 | * @return Number of characters in @a str. |
- | |
388 | */ |
426 | */ |
389 | count_t wstr_length(const wchar_t *wstr) |
427 | bool ascii_check(const wchar_t ch) |
390 | { |
428 | { |
- | 429 | if ((ch >= 0) && (ch <= 127)) |
|
391 | count_t len; |
430 | return true; |
392 | 431 | ||
393 | len = 0; |
432 | return false; |
394 | while (*wstr++ != '\0') |
- | |
395 | ++len; |
433 | } |
396 | 434 | ||
- | 435 | /** Check whether character is valid |
|
- | 436 | * |
|
- | 437 | * @return True if character is a valid Unicode code point. |
|
- | 438 | * |
|
- | 439 | */ |
|
- | 440 | bool chr_check(const wchar_t ch) |
|
- | 441 | { |
|
- | 442 | if ((ch >= 0) && (ch <= 1114111)) |
|
- | 443 | return true; |
|
- | 444 | ||
397 | return len; |
445 | return false; |
398 | } |
446 | } |
399 | 447 | ||
400 | /** Compare two NULL terminated strings |
448 | /** Compare two NULL terminated strings. |
401 | * |
449 | * |
402 | * Do a char-by-char comparison of two NULL terminated strings. |
450 | * Do a char-by-char comparison of two NULL-terminated strings. |
403 | * The strings are considered equal iff they consist of the same |
451 | * The strings are considered equal iff they consist of the same |
404 | * characters on the minimum of their lengths. |
452 | * characters on the minimum of their lengths. |
405 | * |
453 | * |
406 | * @param src First string to compare. |
454 | * @param s1 First string to compare. |
407 | * @param dst Second string to compare. |
455 | * @param s2 Second string to compare. |
408 | * |
456 | * |
409 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
457 | * @return 0 if the strings are equal, -1 if first is smaller, |
- | 458 | * 1 if second smaller. |
|
410 | * |
459 | * |
411 | */ |
460 | */ |
412 | int strcmp(const char *src, const char *dst) |
461 | int str_cmp(const char *s1, const char *s2) |
413 | { |
462 | { |
- | 463 | wchar_t c1; |
|
- | 464 | wchar_t c2; |
|
- | 465 | ||
- | 466 | size_t off1 = 0; |
|
- | 467 | size_t off2 = 0; |
|
- | 468 | ||
- | 469 | while ((c1 = str_decode(s1, &off1, STR_NO_LIMIT) != 0) |
|
414 | for (; *src && *dst; src++, dst++) { |
470 | && (c2 = str_decode(s2, &off2, STR_NO_LIMIT) != 0)) { |
- | 471 | ||
- | 472 | if (off1 != off2) |
|
- | 473 | break; |
|
- | 474 | ||
415 | if (*src < *dst) |
475 | if (c1 < c2) |
416 | return -1; |
476 | return -1; |
- | 477 | ||
417 | if (*src > *dst) |
478 | if (c1 > c2) |
418 | return 1; |
479 | return 1; |
419 | } |
480 | } |
- | 481 | ||
420 | if (*src == *dst) |
482 | if ((off1 == off2) && (c1 == c2)) |
421 | return 0; |
483 | return 0; |
422 | 484 | ||
423 | if (!*src) |
485 | if ((c1 == 0) || (off1 < off2)) |
424 | return -1; |
486 | return -1; |
425 | 487 | ||
426 | return 1; |
488 | return 1; |
427 | } |
489 | } |
428 | 490 | ||
429 | - | ||
430 | /** Compare two NULL terminated strings |
491 | /** Compare two NULL terminated strings with length limit. |
431 | * |
492 | * |
432 | * Do a char-by-char comparison of two NULL terminated strings. |
493 | * Do a char-by-char comparison of two NULL-terminated strings. |
433 | * The strings are considered equal iff they consist of the same |
494 | * The strings are considered equal iff they consist of the same |
434 | * characters on the minimum of their lengths and specified maximal |
495 | * characters on the minimum of their lengths and the length limit. |
435 | * length. |
496 | * |
- | 497 | * @param s1 First string to compare. |
|
- | 498 | * @param s2 Second string to compare. |
|
- | 499 | * @param max_len Maximum number of characters to consider. |
|
436 | * |
500 | * |
437 | * @param src First string to compare. |
501 | * @return 0 if the strings are equal, -1 if first is smaller, |
438 | * @param dst Second string to compare. |
502 | * 1 if second smaller. |
439 | * @param len Maximal length for comparison. |
- | |
440 | * |
503 | * |
441 | * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller. |
- | |
442 | */ |
504 | */ |
443 | int strncmp(const char *src, const char *dst, size_t len) |
505 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
444 | { |
506 | { |
- | 507 | wchar_t c1 = 0; |
|
- | 508 | wchar_t c2 = 0; |
|
- | 509 | ||
445 | unsigned int i; |
510 | size_t off1 = 0; |
- | 511 | size_t off2 = 0; |
|
446 | 512 | ||
- | 513 | count_t len = 0; |
|
- | 514 | ||
- | 515 | while ((len < max_len) |
|
- | 516 | && ((c1 = str_decode(s1, &off1, STR_NO_LIMIT)) != 0) |
|
447 | for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) { |
517 | && ((c2 = str_decode(s2, &off2, STR_NO_LIMIT)) != 0)) { |
- | 518 | ||
- | 519 | if (off1 != off2) |
|
- | 520 | break; |
|
- | 521 | ||
448 | if (*src < *dst) |
522 | if (c1 < c2) |
449 | return -1; |
523 | return -1; |
450 | 524 | ||
451 | if (*src > *dst) |
525 | if (c1 > c2) |
452 | return 1; |
526 | return 1; |
- | 527 | ||
- | 528 | len++; |
|
453 | } |
529 | } |
454 | 530 | ||
455 | if (i == len || *src == *dst) |
531 | if ((off1 == off2) && (len == max_len) && (c1 == c2)) |
456 | return 0; |
532 | return 0; |
457 | 533 | ||
458 | if (!*src) |
534 | if ((c1 == 0) || (off1 < off2)) |
459 | return -1; |
535 | return -1; |
460 | 536 | ||
461 | return 1; |
537 | return 1; |
462 | } |
538 | } |
463 | 539 | ||
- | 540 | /** Copy NULL-terminated string. |
|
- | 541 | * |
|
- | 542 | * Copy source string @a src to destination buffer @a dst. |
|
- | 543 | * No more than @a size bytes are written. NULL-terminator is always |
|
- | 544 | * written after the last succesfully copied character (i.e. if the |
|
- | 545 | * destination buffer is has at least 1 byte, it will be always |
|
- | 546 | * NULL-terminated). |
|
- | 547 | * |
|
- | 548 | * @param src Source string. |
|
- | 549 | * @param dst Destination buffer. |
|
- | 550 | * @param count Size of the destination buffer. |
|
- | 551 | * |
|
- | 552 | */ |
|
- | 553 | void str_ncpy(char *dst, const char *src, size_t size) |
|
- | 554 | { |
|
- | 555 | /* No space for the NULL-terminator in the buffer */ |
|
- | 556 | if (size == 0) |
|
- | 557 | return; |
|
- | 558 | ||
- | 559 | wchar_t ch; |
|
- | 560 | size_t str_off = 0; |
|
- | 561 | size_t dst_off = 0; |
|
- | 562 | ||
- | 563 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT) != 0)) { |
|
- | 564 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
|
- | 565 | break; |
|
- | 566 | } |
|
- | 567 | ||
- | 568 | if (dst_off >= size) |
|
- | 569 | dst[size - 1] = 0; |
|
- | 570 | else |
|
- | 571 | dst[dst_off] = 0; |
|
- | 572 | } |
|
464 | 573 | ||
- | 574 | /** Copy NULL-terminated wide string to string |
|
465 | 575 | * |
|
- | 576 | * Copy source wide string @a src to destination buffer @a dst. |
|
- | 577 | * No more than @a size bytes are written. NULL-terminator is always |
|
- | 578 | * written after the last succesfully copied character (i.e. if the |
|
- | 579 | * destination buffer is has at least 1 byte, it will be always |
|
466 | /** Copy NULL terminated string. |
580 | * NULL-terminated). |
467 | * |
581 | * |
468 | * Copy at most 'len' characters from string 'src' to 'dest'. |
582 | * @param src Source wide string. |
469 | * If 'src' is shorter than 'len', '\0' is inserted behind the |
583 | * @param dst Destination buffer. |
470 | * last copied character. |
584 | * @param count Size of the destination buffer. |
471 | * |
585 | * |
472 | * @param src Source string. |
- | |
473 | * @param dest Destination buffer. |
- | |
474 | * @param len Size of destination buffer. |
- | |
475 | */ |
586 | */ |
476 | void strncpy(char *dest, const char *src, size_t len) |
587 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
477 | { |
588 | { |
- | 589 | /* No space for the NULL-terminator in the buffer */ |
|
478 | unsigned int i; |
590 | if (size == 0) |
- | 591 | return; |
|
- | 592 | ||
- | 593 | wchar_t ch; |
|
- | 594 | count_t src_idx = 0; |
|
- | 595 | size_t dst_off = 0; |
|
479 | 596 | ||
480 | for (i = 0; i < len; i++) { |
597 | while ((ch = src[src_idx++]) != 0) { |
481 | if (!(dest[i] = src[i])) |
598 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
482 | return; |
599 | break; |
483 | } |
600 | } |
484 | 601 | ||
- | 602 | if (dst_off >= size) |
|
485 | dest[i - 1] = '\0'; |
603 | dst[size - 1] = 0; |
- | 604 | else |
|
- | 605 | dst[dst_off] = 0; |
|
486 | } |
606 | } |
487 | 607 | ||
488 | /** Find first occurence of character in string. |
608 | /** Find first occurence of character in string. |
489 | * |
609 | * |
490 | * @param s String to search. |
610 | * @param str String to search. |
491 | * @param i Character to look for. |
611 | * @param ch Character to look for. |
- | 612 | * |
|
- | 613 | * @return Pointer to character in @a str or NULL if not found. |
|
492 | * |
614 | * |
493 | * @return Pointer to character in @a s or NULL if not found. |
- | |
494 | */ |
615 | */ |
495 | extern char *strchr(const char *s, int i) |
616 | const char *str_chr(const char *str, wchar_t ch) |
496 | { |
617 | { |
- | 618 | wchar_t acc; |
|
497 | while (*s != '\0') { |
619 | size_t off = 0; |
- | 620 | ||
- | 621 | while ((acc = str_decode(str, &off, STR_NO_LIMIT) != 0)) { |
|
498 | if (*s == i) |
622 | if (acc == ch) |
499 | return (char *) s; |
623 | return (str + off); |
500 | ++s; |
- | |
501 | } |
624 | } |
502 | 625 | ||
503 | return NULL; |
626 | return NULL; |
504 | } |
627 | } |
505 | 628 | ||
- | 629 | /** Insert a wide character into a wide string. |
|
- | 630 | * |
|
- | 631 | * Insert a wide character into a wide string at position |
|
- | 632 | * @a pos. The characters after the position are shifted. |
|
- | 633 | * |
|
- | 634 | * @param str String to insert to. |
|
- | 635 | * @param ch Character to insert to. |
|
- | 636 | * @param pos Character index where to insert. |
|
- | 637 | @ @param max_pos Characters in the buffer. |
|
- | 638 | * |
|
- | 639 | * @return True if the insertion was sucessful, false if the position |
|
- | 640 | * is out of bounds. |
|
- | 641 | * |
|
- | 642 | */ |
|
- | 643 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
|
- | 644 | { |
|
- | 645 | count_t len = wstr_length(str); |
|
- | 646 | ||
- | 647 | if ((pos > len) || (pos + 1 > max_pos)) |
|
- | 648 | return false; |
|
- | 649 | ||
- | 650 | count_t i; |
|
- | 651 | for (i = len; i + 1 > pos; i--) |
|
- | 652 | str[i + 1] = str[i]; |
|
- | 653 | ||
- | 654 | str[pos] = ch; |
|
- | 655 | ||
- | 656 | return true; |
|
- | 657 | } |
|
- | 658 | ||
- | 659 | /** Remove a wide character from a wide string. |
|
- | 660 | * |
|
- | 661 | * Remove a wide character from a wide string at position |
|
- | 662 | * @a pos. The characters after the position are shifted. |
|
- | 663 | * |
|
- | 664 | * @param str String to remove from. |
|
- | 665 | * @param pos Character index to remove. |
|
- | 666 | * |
|
- | 667 | * @return True if the removal was sucessful, false if the position |
|
- | 668 | * is out of bounds. |
|
- | 669 | * |
|
- | 670 | */ |
|
- | 671 | bool wstr_remove(wchar_t *str, count_t pos) |
|
- | 672 | { |
|
- | 673 | count_t len = wstr_length(str); |
|
- | 674 | ||
- | 675 | if (pos >= len) |
|
- | 676 | return false; |
|
- | 677 | ||
- | 678 | count_t i; |
|
- | 679 | for (i = pos + 1; i <= len; i++) |
|
- | 680 | str[i - 1] = str[i]; |
|
- | 681 | ||
- | 682 | return true; |
|
- | 683 | } |
|
- | 684 | ||
506 | /** @} |
685 | /** @} |
507 | */ |
686 | */ |