WebSVN – HelenOS – Diff – /branches/dd/kernel/generic/src/lib/string.c


/*
 * Copyright (c) 2001-2004 Jakub Jermar
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * - Redistributions of source code must retain the above copyright
 *   notice, this list of conditions and the following disclaimer.
 * - Redistributions in binary form must reproduce the above copyright
 *   notice, this list of conditions and the following disclaimer in the
 *   documentation and/or other materials provided with the distribution.
 * - The name of the author may not be used to endorse or promote products
 *   derived from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
 
/** @addtogroup generic
 * @{
 */
 
/**
 * @file
 * @brief Miscellaneous functions.
 */
 
#include <string.h>
#include <print.h>
#include <cpu.h>
#include <arch/asm.h>
#include <arch.h>
#include <console/kconsole.h>
 
char invalch = '?';
 
/** Byte mask consisting of lowest @n bits (out of eight). */
#define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1))
 
/** Byte mask consisting of lowest @n bits (out of 32). */
#define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1))
 
/** Byte mask consisting of highest @n bits (out of eight). */
#define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
 
/** Number of data bits in a UTF-8 continuation byte. */
#define CONT_BITS 6
 
/** Decode a single character from a substring.
 *
 * Decode a single character from a substring of size @a sz. Decoding starts
 * at @a offset and this offset is moved to the beginning of the next
 * character. In case of decoding error, offset generally advances at least
 * by one. However, offset is never moved beyond (str + sz).
 *
 * @param str   String (not necessarily NULL-terminated).
 * @param index Index (counted in plain characters) where to start
 *              the decoding.
 * @param limit Size of the substring.
 *
 * @return  Value of decoded character or '?' on decoding error.
 *
 */
wchar_t chr_decode(const char *str, size_t *offset, size_t sz)
{
    uint8_t b0, b;          /* Bytes read from str. */
    wchar_t ch;
 
    int b0_bits;        /* Data bits in first byte. */
    int cbytes;     /* Number of continuation bytes. */
 
    if (*offset + 1 > sz)
        return invalch;
 
    b0 = (uint8_t) str[(*offset)++];
 
    /* Determine code length. */
 
    if ((b0 & 0x80) == 0) {
        /* 0xxxxxxx (Plain ASCII) */
        b0_bits = 7;
        cbytes = 0;
    } else if ((b0 & 0xe0) == 0xc0) {
        /* 110xxxxx 10xxxxxx */
        b0_bits = 5;
        cbytes = 1;
    } else if ((b0 & 0xf0) == 0xe0) {
        /* 1110xxxx 10xxxxxx 10xxxxxx */
        b0_bits = 4;
        cbytes = 2;
    } else if ((b0 & 0xf8) == 0xf0) {
        /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
        b0_bits = 3;
        cbytes = 3;
    } else {
        /* 10xxxxxx -- unexpected continuation byte. */
        return invalch;
    }
 
    if (*offset + cbytes > sz) {
        return invalch;
    }
 
    ch = b0 & LO_MASK_8(b0_bits);
 
    /* Decode continuation bytes. */
    while (cbytes > 0) {
        b = (uint8_t) str[(*offset)++];
 
        /* Must be 10xxxxxx. */
        if ((b & 0xc0) != 0x80) {
            return invalch;
        }
 
        /* Shift data bits to ch. */
        ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS));
        --cbytes;
    }
 
    return ch;
}
 
/** Encode a single character to string representation.
 *
 * Encode a single character to string representation (i.e. UTF-8) and store
 * it into a buffer at @a offset. Encoding starts at @a offset and this offset
 * is moved to the position where the next character can be written to.
 *
 * @param ch        Input character.
 * @param str       Output buffer.
 * @param offset    Offset (in bytes) where to start writing.
 * @param sz        Size of the output buffer.
 *
 * @return True if the character was encoded successfully or false if there
 *     was not enough space in the output buffer or the character code
 *     was invalid.
 */
bool chr_encode(const wchar_t ch, char *str, size_t *offset, size_t sz)
{
    uint32_t cc;        /* Unsigned version of ch. */
 
    int cbytes;     /* Number of continuation bytes. */
    int b0_bits;        /* Number of data bits in first byte. */
    int i;
 
    if (*offset >= sz)
        return false;
 
    if (ch < 0)
        return false;
 
    /* Bit operations should only be done on unsigned numbers. */
    cc = (uint32_t) ch;
 
    /* Determine how many continuation bytes are needed. */
    if ((cc & ~LO_MASK_32(7)) == 0) {
        b0_bits = 7;
        cbytes = 0;
    } else if ((cc & ~LO_MASK_32(11)) == 0) {
        b0_bits = 5;
        cbytes = 1;
    } else if ((cc & ~LO_MASK_32(16)) == 0) {
        b0_bits = 4;
        cbytes = 2;
    } else if ((cc & ~LO_MASK_32(21)) == 0) {
        b0_bits = 3;
        cbytes = 3;
    } else {
        /* Codes longer than 21 bits are not supported. */
        return false;
    }
 
    /* Check for available space in buffer. */
    if (*offset + cbytes >= sz)
        return false;
 
    /* Encode continuation bytes. */
    for (i = cbytes; i > 0; --i) {
        str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS));
        cc = cc >> CONT_BITS;
    }
 
    /* Encode first byte. */
    str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1);
 
    /* Advance offset. */
    *offset += (1 + cbytes);
   
    return true;
}
 
/** Get size of string, with length limit.
 *
 * Get the number of bytes which are used by up to @a max_len first
 * characters in the string @a str. If @a max_len is greater than
 * the length of @a str, the entire string is measured.
 
 *
 * @param str   String to consider.
 * @param count Maximum number of characters to measure.
 *
 * @return Number of bytes used by the characters.
 
 */
size_t str_lsize(const char *str, count_t max_len)
{
    count_t len = 0;
    size_t cur = 0;
    size_t prev;
    wchar_t ch;
 
    while (true) {
        prev = cur;
        if (len >= max_len)
            break;
        ch = chr_decode(str, &cur, UTF8_NO_LIMIT);
        if (ch == '\0') break;
 
        len++;
    }
 
    return prev;
}
 
/** Check whether character is plain ASCII.
 *
 * @return True if character is plain ASCII.
 *
 */
bool ascii_check(const wchar_t ch)
{
    if ((ch >= 0) && (ch <= 127))
        return true;
   
    return false;
}
 
/** Check whether character is Unicode.
 *
 * @return True if character is valid Unicode code point.
 *
 */
bool unicode_check(const wchar_t ch)
{
    if ((ch >= 0) && (ch <= 1114111))
        return true;
   
    return false;
}
 
/** Return number of plain characters in a string.
 *
 * @param str NULL-terminated string.
 *
 * @return Number of characters in @a str.
 *
 */
size_t strlen(const char *str)
{
    size_t size;
    for (size = 0; str[size]; size++);
   
    return size;
}
 
/** Return number of characters in a string.
 
 
 
 
 *
 * @param str NULL-terminated string.
 * @return Number of characters in string.
 */
count_t str_length(const char *str)
{
    count_t len = 0;
    size_t offset = 0;
 
    while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) {
        len++;
    }
 
    return len;
}
 
/** Return number of characters in a wide string.
 
 
 
 
 *
 * @param str NULL-terminated wide string.
 * @return Number of characters in @a str.
 */
count_t wstr_length(const wchar_t *wstr)
{
    count_t len;
 
    len = 0;
    while (*wstr++ != '\0')
        ++len;
 
    return len;
}
 
/** Compare two NULL terminated strings
 *
 * Do a char-by-char comparison of two NULL terminated strings.
 * The strings are considered equal iff they consist of the same
 * characters on the minimum of their lengths.
 *
 * @param src First string to compare.
 * @param dst Second string to compare.
 *
 * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
 *
 */
int strcmp(const char *src, const char *dst)
{
    for (; *src && *dst; src++, dst++) {
        if (*src < *dst)
            return -1;
        if (*src > *dst)
            return 1;
    }
    if (*src == *dst)
        return 0;
   
    if (!*src)
        return -1;
   
    return 1;
}
 
 
/** Compare two NULL terminated strings
 *
 * Do a char-by-char comparison of two NULL terminated strings.
 * The strings are considered equal iff they consist of the same
 * characters on the minimum of their lengths and specified maximal
 * length.
 *
 * @param src First string to compare.
 * @param dst Second string to compare.
 * @param len Maximal length for comparison.
 *
 * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
 *
 */
int strncmp(const char *src, const char *dst, size_t len)
{
    unsigned int i;
   
    for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) {
        if (*src < *dst)
            return -1;
       
        if (*src > *dst)
            return 1;
    }
   
    if (i == len || *src == *dst)
        return 0;
   
    if (!*src)
        return -1;
   
    return 1;
}
 
 
 
/** Copy NULL terminated string.
 *
 * Copy at most 'len' characters from string 'src' to 'dest'.
 * If 'src' is shorter than 'len', '\0' is inserted behind the
 * last copied character.
 *
 * @param src  Source string.
 * @param dest Destination buffer.
 * @param len  Size of destination buffer.
 *
 */
void strncpy(char *dest, const char *src, size_t len)
{
    unsigned int i;
   
    for (i = 0; i < len; i++) {
        if (!(dest[i] = src[i]))
            return;
    }
   
    dest[i - 1] = '\0';
}
 
/** Find first occurence of character in string.
 *
 * @param s String to search.
 * @param i Character to look for.
 *
 * @return Pointer to character in @a s or NULL if not found.
 */
extern char *strchr(const char *s, int i)
{
    while (*s != '\0') {
        if (*s == i)
            return (char *) s;
        ++s;
    }
   
    return NULL;
}
 
/** @}
 */
 

Rev 4201	Rev 4221
1	/*	1	/*
2	* Copyright (c) 2001-2004 Jakub Jermar	2	* Copyright (c) 2001-2004 Jakub Jermar
3	* All rights reserved.	3	* All rights reserved.
4	*	4	*
5	* Redistribution and use in source and binary forms, with or without	5	* Redistribution and use in source and binary forms, with or without
6	* modification, are permitted provided that the following conditions	6	* modification, are permitted provided that the following conditions
7	* are met:	7	* are met:
8	*	8	*
9	* - Redistributions of source code must retain the above copyright	9	* - Redistributions of source code must retain the above copyright
10	* notice, this list of conditions and the following disclaimer.	10	* notice, this list of conditions and the following disclaimer.
11	* - Redistributions in binary form must reproduce the above copyright	11	* - Redistributions in binary form must reproduce the above copyright
12	* notice, this list of conditions and the following disclaimer in the	12	* notice, this list of conditions and the following disclaimer in the
13	* documentation and/or other materials provided with the distribution.	13	* documentation and/or other materials provided with the distribution.
14	* - The name of the author may not be used to endorse or promote products	14	* - The name of the author may not be used to endorse or promote products
15	* derived from this software without specific prior written permission.	15	* derived from this software without specific prior written permission.
16	*	16	*
17	* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR	17	* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
18	* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES	18	* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
19	* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.	19	* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
20	* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,	20	* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
21	* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT	21	* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
22	* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,	22	* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
23	* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY	23	* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
24	* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT	24	* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25	* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF	25	* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
26	* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.	26	* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27	*/	27	*/
28		28
29	/** @addtogroup generic	29	/** @addtogroup generic
30	* @{	30	* @{
31	*/	31	*/
32		32
33	/**	33	/**
34	* @file	34	* @file
35	* @brief Miscellaneous functions.	35	* @brief Miscellaneous functions.
36	*/	36	*/
37		37
38	#include <string.h>	38	#include <string.h>
39	#include <print.h>	39	#include <print.h>
40	#include <cpu.h>	40	#include <cpu.h>
41	#include <arch/asm.h>	41	#include <arch/asm.h>
42	#include <arch.h>	42	#include <arch.h>
43	#include <console/kconsole.h>	43	#include <console/kconsole.h>
44		44
45	char invalch = '?';	45	char invalch = '?';
46		46
47	/** Byte mask consisting of lowest @n bits (out of eight). */	47	/** Byte mask consisting of lowest @n bits (out of eight). */
48	#define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1))	48	#define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1))
49		49
50	/** Byte mask consisting of lowest @n bits (out of 32). */	50	/** Byte mask consisting of lowest @n bits (out of 32). */
51	#define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1))	51	#define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1))
52		52
53	/** Byte mask consisting of highest @n bits (out of eight). */	53	/** Byte mask consisting of highest @n bits (out of eight). */
54	#define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))	54	#define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
55		55
56	/** Number of data bits in a UTF-8 continuation byte. */	56	/** Number of data bits in a UTF-8 continuation byte. */
57	#define CONT_BITS 6	57	#define CONT_BITS 6
58		58
59	/** Decode a single character from a substring.	59	/** Decode a single character from a substring.
60	*	60	*
61	* Decode a single character from a substring of size @a sz. Decoding starts	61	* Decode a single character from a substring of size @a sz. Decoding starts
62	* at @a offset and this offset is moved to the beginning of the next	62	* at @a offset and this offset is moved to the beginning of the next
63	* character. In case of decoding error, offset generally advances at least	63	* character. In case of decoding error, offset generally advances at least
64	* by one. However, offset is never moved beyond (str + sz).	64	* by one. However, offset is never moved beyond (str + sz).
65	*	65	*
66	* @param str String (not necessarily NULL-terminated).	66	* @param str String (not necessarily NULL-terminated).
67	* @param index Index (counted in plain characters) where to start	67	* @param index Index (counted in plain characters) where to start
68	* the decoding.	68	* the decoding.
69	* @param limit Size of the substring.	69	* @param limit Size of the substring.
70	*	70	*
71	* @return Value of decoded character or '?' on decoding error.	71	* @return Value of decoded character or '?' on decoding error.
72	*	72	*
73	*/	73	*/
74	wchar_t chr_decode(const char str, size_t offset, size_t sz)	74	wchar_t chr_decode(const char str, size_t offset, size_t sz)
75	{	75	{
76	uint8_t b0, b; /* Bytes read from str. */	76	uint8_t b0, b; /* Bytes read from str. */
77	wchar_t ch;	77	wchar_t ch;
78		78
79	int b0_bits; /* Data bits in first byte. */	79	int b0_bits; /* Data bits in first byte. */
80	int cbytes; /* Number of continuation bytes. */	80	int cbytes; /* Number of continuation bytes. */
81		81
82	if (*offset + 1 > sz)	82	if (*offset + 1 > sz)
83	return invalch;	83	return invalch;
84		84
85	b0 = (uint8_t) str[(*offset)++];	85	b0 = (uint8_t) str[(*offset)++];
86		86
87	/* Determine code length. */	87	/* Determine code length. */
88		88
89	if ((b0 & 0x80) == 0) {	89	if ((b0 & 0x80) == 0) {
90	/* 0xxxxxxx (Plain ASCII) */	90	/* 0xxxxxxx (Plain ASCII) */
91	b0_bits = 7;	91	b0_bits = 7;
92	cbytes = 0;	92	cbytes = 0;
93	} else if ((b0 & 0xe0) == 0xc0) {	93	} else if ((b0 & 0xe0) == 0xc0) {
94	/* 110xxxxx 10xxxxxx */	94	/* 110xxxxx 10xxxxxx */
95	b0_bits = 5;	95	b0_bits = 5;
96	cbytes = 1;	96	cbytes = 1;
97	} else if ((b0 & 0xf0) == 0xe0) {	97	} else if ((b0 & 0xf0) == 0xe0) {
98	/* 1110xxxx 10xxxxxx 10xxxxxx */	98	/* 1110xxxx 10xxxxxx 10xxxxxx */
99	b0_bits = 4;	99	b0_bits = 4;
100	cbytes = 2;	100	cbytes = 2;
101	} else if ((b0 & 0xf8) == 0xf0) {	101	} else if ((b0 & 0xf8) == 0xf0) {
102	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */	102	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
103	b0_bits = 3;	103	b0_bits = 3;
104	cbytes = 3;	104	cbytes = 3;
105	} else {	105	} else {
106	/* 10xxxxxx -- unexpected continuation byte. */	106	/* 10xxxxxx -- unexpected continuation byte. */
107	return invalch;	107	return invalch;
108	}	108	}
109		109
110	if (*offset + cbytes > sz) {	110	if (*offset + cbytes > sz) {
111	return invalch;	111	return invalch;
112	}	112	}
113		113
114	ch = b0 & LO_MASK_8(b0_bits);	114	ch = b0 & LO_MASK_8(b0_bits);
115		115
116	/* Decode continuation bytes. */	116	/* Decode continuation bytes. */
117	while (cbytes > 0) {	117	while (cbytes > 0) {
118	b = (uint8_t) str[(*offset)++];	118	b = (uint8_t) str[(*offset)++];
119		119
120	/* Must be 10xxxxxx. */	120	/* Must be 10xxxxxx. */
121	if ((b & 0xc0) != 0x80) {	121	if ((b & 0xc0) != 0x80) {
122	return invalch;	122	return invalch;
123	}	123	}
124		124
125	/* Shift data bits to ch. */	125	/* Shift data bits to ch. */
126	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));	126	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));
127	--cbytes;	127	--cbytes;
128	}	128	}
129		129
130	return ch;	130	return ch;
131	}	131	}
132		132
133	/** Encode a single character to string representation.	133	/** Encode a single character to string representation.
134	*	134	*
135	* Encode a single character to string representation (i.e. UTF-8) and store	135	* Encode a single character to string representation (i.e. UTF-8) and store
136	* it into a buffer at @a offset. Encoding starts at @a offset and this offset	136	* it into a buffer at @a offset. Encoding starts at @a offset and this offset
137	* is moved to the position where the next character can be written to.	137	* is moved to the position where the next character can be written to.
138	*	138	*
139	* @param ch Input character.	139	* @param ch Input character.
140	* @param str Output buffer.	140	* @param str Output buffer.
141	* @param offset Offset (in bytes) where to start writing.	141	* @param offset Offset (in bytes) where to start writing.
142	* @param sz Size of the output buffer.	142	* @param sz Size of the output buffer.
143	*	143	*
144	* @return True if the character was encoded successfully or false if there	144	* @return True if the character was encoded successfully or false if there
145	* was not enough space in the output buffer or the character code	145	* was not enough space in the output buffer or the character code
146	* was invalid.	146	* was invalid.
147	*/	147	*/
148	bool chr_encode(const wchar_t ch, char str, size_t offset, size_t sz)	148	bool chr_encode(const wchar_t ch, char str, size_t offset, size_t sz)
149	{	149	{
150	uint32_t cc; /* Unsigned version of ch. */	150	uint32_t cc; /* Unsigned version of ch. */
151		151
152	int cbytes; /* Number of continuation bytes. */	152	int cbytes; /* Number of continuation bytes. */
153	int b0_bits; /* Number of data bits in first byte. */	153	int b0_bits; /* Number of data bits in first byte. */
154	int i;	154	int i;
155		155
156	if (*offset >= sz)	156	if (*offset >= sz)
157	return false;	157	return false;
158		158
159	if (ch < 0)	159	if (ch < 0)
160	return false;	160	return false;
161		161
162	/* Bit operations should only be done on unsigned numbers. */	162	/* Bit operations should only be done on unsigned numbers. */
163	cc = (uint32_t) ch;	163	cc = (uint32_t) ch;
164		164
165	/* Determine how many continuation bytes are needed. */	165	/* Determine how many continuation bytes are needed. */
166	if ((cc & ~LO_MASK_32(7)) == 0) {	166	if ((cc & ~LO_MASK_32(7)) == 0) {
167	b0_bits = 7;	167	b0_bits = 7;
168	cbytes = 0;	168	cbytes = 0;
169	} else if ((cc & ~LO_MASK_32(11)) == 0) {	169	} else if ((cc & ~LO_MASK_32(11)) == 0) {
170	b0_bits = 5;	170	b0_bits = 5;
171	cbytes = 1;	171	cbytes = 1;
172	} else if ((cc & ~LO_MASK_32(16)) == 0) {	172	} else if ((cc & ~LO_MASK_32(16)) == 0) {
173	b0_bits = 4;	173	b0_bits = 4;
174	cbytes = 2;	174	cbytes = 2;
175	} else if ((cc & ~LO_MASK_32(21)) == 0) {	175	} else if ((cc & ~LO_MASK_32(21)) == 0) {
176	b0_bits = 3;	176	b0_bits = 3;
177	cbytes = 3;	177	cbytes = 3;
178	} else {	178	} else {
179	/* Codes longer than 21 bits are not supported. */	179	/* Codes longer than 21 bits are not supported. */
180	return false;	180	return false;
181	}	181	}
182		182
183	/* Check for available space in buffer. */	183	/* Check for available space in buffer. */
184	if (*offset + cbytes >= sz)	184	if (*offset + cbytes >= sz)
185	return false;	185	return false;
186		186
187	/* Encode continuation bytes. */	187	/* Encode continuation bytes. */
188	for (i = cbytes; i > 0; --i) {	188	for (i = cbytes; i > 0; --i) {
189	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));	189	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));
190	cc = cc >> CONT_BITS;	190	cc = cc >> CONT_BITS;
191	}	191	}
192		192
193	/* Encode first byte. */	193	/* Encode first byte. */
194	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);	194	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);
195		195
196	/* Advance offset. */	196	/* Advance offset. */
197	*offset += (1 + cbytes);	197	*offset += (1 + cbytes);
198		198
199	return true;	199	return true;
200	}	200	}
201		201
202	/** Get bytes used by UTF-8 characters.	202	/** Get size of string, with length limit.
203	*	203	*
204	* Get the number of bytes (count of plain characters) which	204	* Get the number of bytes which are used by up to @a max_len first
205	* are used by a given count of UTF-8 characters in a string.	205	* characters in the string @a str. If @a max_len is greater than
206	* As UTF-8 encoding is multibyte, there is no constant	206	* the length of @a str, the entire string is measured.
207	* correspondence between number of characters and used bytes.	-
208	*	207	*
209	* @param str UTF-8 string to consider.	208	* @param str String to consider.
210	* @param count Number of UTF-8 characters to count.	209	* @param count Maximum number of characters to measure.
211	*	210	*
212	* @return Number of bytes used by the characters.	211	* @return Number of bytes used by the characters.
213	*	-
214	*/	212	*/
215	size_t utf8_count_bytes(const char *str, count_t count)	213	size_t str_lsize(const char *str, count_t max_len)
216	{	214	{
217	size_t size = 0;	215	count_t len = 0;
218	index_t index = 0;	216	size_t cur = 0;
219	index_t iprev;	217	size_t prev;
220	wchar_t ch;	218	wchar_t ch;
221		219
222	while (true) {	220	while (true) {
223	iprev = index;	221	prev = cur;
224	if (size >= count)	222	if (len >= max_len)
225	break;	223	break;
226	ch = chr_decode(str, &index, UTF8_NO_LIMIT);	224	ch = chr_decode(str, &cur, UTF8_NO_LIMIT);
227	if (ch == '\0') break;	225	if (ch == '\0') break;
228		226
229	size++;	227	len++;
230	}	228	}
231		229
232	return iprev;	230	return prev;
233	}	231	}
234		232
235	/** Check whether character is plain ASCII.	233	/** Check whether character is plain ASCII.
236	*	234	*
237	* @return True if character is plain ASCII.	235	* @return True if character is plain ASCII.
238	*	236	*
239	*/	237	*/
240	bool ascii_check(const wchar_t ch)	238	bool ascii_check(const wchar_t ch)
241	{	239	{
242	if ((ch >= 0) && (ch <= 127))	240	if ((ch >= 0) && (ch <= 127))
243	return true;	241	return true;
244		242
245	return false;	243	return false;
246	}	244	}
247		245
248	/** Check whether character is Unicode.	246	/** Check whether character is Unicode.
249	*	247	*
250	* @return True if character is valid Unicode code point.	248	* @return True if character is valid Unicode code point.
251	*	249	*
252	*/	250	*/
253	bool unicode_check(const wchar_t ch)	251	bool unicode_check(const wchar_t ch)
254	{	252	{
255	if ((ch >= 0) && (ch <= 1114111))	253	if ((ch >= 0) && (ch <= 1114111))
256	return true;	254	return true;
257		255
258	return false;	256	return false;
259	}	257	}
260		258
261	/** Return number of plain characters in a string.	259	/** Return number of plain characters in a string.
262	*	260	*
263	* @param str NULL-terminated string.	261	* @param str NULL-terminated string.
264	*	262	*
265	* @return Number of characters in str.	263	* @return Number of characters in @a str.
266	*	264	*
267	*/	265	*/
268	size_t strlen(const char *str)	266	size_t strlen(const char *str)
269	{	267	{
270	size_t size;	268	size_t size;
271	for (size = 0; str[size]; size++);	269	for (size = 0; str[size]; size++);
272		270
273	return size;	271	return size;
274	}	272	}
275		273
276	/** Return number of UTF-8 characters in a string.	274	/** Return number of characters in a string.
277	*	-
278	* @param str NULL-terminated UTF-8 string.	-
279	*	-
280	* @return Number of UTF-8 characters in str.	-
281	*	275	*
-		276	* @param str NULL-terminated string.
-		277	* @return Number of characters in string.
282	*/	278	*/
283	size_t strlen_utf8(const char *str)	279	count_t str_length(const char *str)
284	{	280	{
285	size_t size = 0;	281	count_t len = 0;
286	index_t index = 0;	282	size_t offset = 0;
287		283
288	while (chr_decode(str, &index, UTF8_NO_LIMIT) != 0) {	284	while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) {
289	size++;	285	len++;
290	}	286	}
291		287
292	return size;	288	return len;
293	}	289	}
294		290
295	/** Return number of UTF-32 characters in a string.	291	/** Return number of characters in a wide string.
296	*	-
297	* @param str NULL-terminated UTF-32 string.	-
298	*	-
299	* @return Number of UTF-32 characters in str.	-
300	*	292	*
-		293	* @param str NULL-terminated wide string.
-		294	* @return Number of characters in @a str.
301	*/	295	*/
302	size_t strlen_utf32(const wchar_t *str)	296	count_t wstr_length(const wchar_t *wstr)
303	{	297	{
304	size_t size;	298	count_t len;
-		299
-		300	len = 0;
305	for (size = 0; str[size]; size++);	301	while (*wstr++ != '\0')
-		302	++len;
306		303
307	return size;	304	return len;
308	}	305	}
309		306
310	/** Compare two NULL terminated strings	307	/** Compare two NULL terminated strings
311	*	308	*
312	* Do a char-by-char comparison of two NULL terminated strings.	309	* Do a char-by-char comparison of two NULL terminated strings.
313	* The strings are considered equal iff they consist of the same	310	* The strings are considered equal iff they consist of the same
314	* characters on the minimum of their lengths.	311	* characters on the minimum of their lengths.
315	*	312	*
316	* @param src First string to compare.	313	* @param src First string to compare.
317	* @param dst Second string to compare.	314	* @param dst Second string to compare.
318	*	315	*
319	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	316	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
320	*	317	*
321	*/	318	*/
322	int strcmp(const char src, const char dst)	319	int strcmp(const char src, const char dst)
323	{	320	{
324	for (; src && dst; src++, dst++) {	321	for (; src && dst; src++, dst++) {
325	if (src < dst)	322	if (src < dst)
326	return -1;	323	return -1;
327	if (src > dst)	324	if (src > dst)
328	return 1;	325	return 1;
329	}	326	}
330	if (src == dst)	327	if (src == dst)
331	return 0;	328	return 0;
332		329
333	if (!*src)	330	if (!*src)
334	return -1;	331	return -1;
335		332
336	return 1;	333	return 1;
337	}	334	}
338		335
339		336
340	/** Compare two NULL terminated strings	337	/** Compare two NULL terminated strings
341	*	338	*
342	* Do a char-by-char comparison of two NULL terminated strings.	339	* Do a char-by-char comparison of two NULL terminated strings.
343	* The strings are considered equal iff they consist of the same	340	* The strings are considered equal iff they consist of the same
344	* characters on the minimum of their lengths and specified maximal	341	* characters on the minimum of their lengths and specified maximal
345	* length.	342	* length.
346	*	343	*
347	* @param src First string to compare.	344	* @param src First string to compare.
348	* @param dst Second string to compare.	345	* @param dst Second string to compare.
349	* @param len Maximal length for comparison.	346	* @param len Maximal length for comparison.
350	*	347	*
351	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	348	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
352	*	349	*
353	*/	350	*/
354	int strncmp(const char src, const char dst, size_t len)	351	int strncmp(const char src, const char dst, size_t len)
355	{	352	{
356	unsigned int i;	353	unsigned int i;
357		354
358	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {	355	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {
359	if (src < dst)	356	if (src < dst)
360	return -1;	357	return -1;
361		358
362	if (src > dst)	359	if (src > dst)
363	return 1;	360	return 1;
364	}	361	}
365		362
366	if (i == len \|\| src == dst)	363	if (i == len \|\| src == dst)
367	return 0;	364	return 0;
368		365
369	if (!*src)	366	if (!*src)
370	return -1;	367	return -1;
371		368
372	return 1;	369	return 1;
373	}	370	}
374		371
375		372
376		373
377	/** Copy NULL terminated string.	374	/** Copy NULL terminated string.
378	*	375	*
379	* Copy at most 'len' characters from string 'src' to 'dest'.	376	* Copy at most 'len' characters from string 'src' to 'dest'.
380	* If 'src' is shorter than 'len', '\0' is inserted behind the	377	* If 'src' is shorter than 'len', '\0' is inserted behind the
381	* last copied character.	378	* last copied character.
382	*	379	*
383	* @param src Source string.	380	* @param src Source string.
384	* @param dest Destination buffer.	381	* @param dest Destination buffer.
385	* @param len Size of destination buffer.	382	* @param len Size of destination buffer.
386	*	383	*
387	*/	384	*/
388	void strncpy(char dest, const char src, size_t len)	385	void strncpy(char dest, const char src, size_t len)
389	{	386	{
390	unsigned int i;	387	unsigned int i;
391		388
392	for (i = 0; i < len; i++) {	389	for (i = 0; i < len; i++) {
393	if (!(dest[i] = src[i]))	390	if (!(dest[i] = src[i]))
394	return;	391	return;
395	}	392	}
396		393
397	dest[i - 1] = '\0';	394	dest[i - 1] = '\0';
398	}	395	}
399		396
400	/** Find first occurence of character in string.	397	/** Find first occurence of character in string.
401	*	398	*
402	* @param s String to search.	399	* @param s String to search.
403	* @param i Character to look for.	400	* @param i Character to look for.
404	*	401	*
405	* @return Pointer to character in @a s or NULL if not found.	402	* @return Pointer to character in @a s or NULL if not found.
406	*/	403	*/
407	extern char strchr(const char s, int i)	404	extern char strchr(const char s, int i)
408	{	405	{
409	while (*s != '\0') {	406	while (*s != '\0') {
410	if (*s == i)	407	if (*s == i)
411	return (char *) s;	408	return (char *) s;
412	++s;	409	++s;
413	}	410	}
414		411
415	return NULL;	412	return NULL;
416	}	413	}
417		414
418	/** @}	415	/** @}
419	*/	416	*/
420		417

Subversion Repositories HelenOS

(root)/branches/dd/kernel/generic/src/lib/string.c – Rev 4201 → 4221