WebSVN – HelenOS – Diff – /trunk/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 bytes the string occupies.
 
 
 
 
 *
 * @param str A string.
 * @return Number of bytes in @a str excluding the null terminator.
 */
size_t str_size(const char *str)
{
    size_t size;
 
    size = 0;
    while (*str++ != '\0')
        ++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 4205	Rev 4207
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	*	-
73	*/	72	*/
74	wchar_t chr_decode(const char str, size_t offset, size_t sz)	73	wchar_t chr_decode(const char str, size_t offset, size_t sz)
75	{	74	{
76	uint8_t b0, b; /* Bytes read from str. */	75	uint8_t b0, b; /* Bytes read from str. */
77	wchar_t ch;	76	wchar_t ch;
78		77
79	int b0_bits; /* Data bits in first byte. */	78	int b0_bits; /* Data bits in first byte. */
80	int cbytes; /* Number of continuation bytes. */	79	int cbytes; /* Number of continuation bytes. */
81		80
82	if (*offset + 1 > sz)	81	if (*offset + 1 > sz)
83	return invalch;	82	return invalch;
84		83
85	b0 = (uint8_t) str[(*offset)++];	84	b0 = (uint8_t) str[(*offset)++];
86		85
87	/* Determine code length. */	86	/* Determine code length. */
88		87
89	if ((b0 & 0x80) == 0) {	88	if ((b0 & 0x80) == 0) {
90	/* 0xxxxxxx (Plain ASCII) */	89	/* 0xxxxxxx (Plain ASCII) */
91	b0_bits = 7;	90	b0_bits = 7;
92	cbytes = 0;	91	cbytes = 0;
93	} else if ((b0 & 0xe0) == 0xc0) {	92	} else if ((b0 & 0xe0) == 0xc0) {
94	/* 110xxxxx 10xxxxxx */	93	/* 110xxxxx 10xxxxxx */
95	b0_bits = 5;	94	b0_bits = 5;
96	cbytes = 1;	95	cbytes = 1;
97	} else if ((b0 & 0xf0) == 0xe0) {	96	} else if ((b0 & 0xf0) == 0xe0) {
98	/* 1110xxxx 10xxxxxx 10xxxxxx */	97	/* 1110xxxx 10xxxxxx 10xxxxxx */
99	b0_bits = 4;	98	b0_bits = 4;
100	cbytes = 2;	99	cbytes = 2;
101	} else if ((b0 & 0xf8) == 0xf0) {	100	} else if ((b0 & 0xf8) == 0xf0) {
102	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */	101	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
103	b0_bits = 3;	102	b0_bits = 3;
104	cbytes = 3;	103	cbytes = 3;
105	} else {	104	} else {
106	/* 10xxxxxx -- unexpected continuation byte. */	105	/* 10xxxxxx -- unexpected continuation byte. */
107	return invalch;	106	return invalch;
108	}	107	}
109		108
110	if (*offset + cbytes > sz) {	109	if (*offset + cbytes > sz) {
111	return invalch;	110	return invalch;
112	}	111	}
113		112
114	ch = b0 & LO_MASK_8(b0_bits);	113	ch = b0 & LO_MASK_8(b0_bits);
115		114
116	/* Decode continuation bytes. */	115	/* Decode continuation bytes. */
117	while (cbytes > 0) {	116	while (cbytes > 0) {
118	b = (uint8_t) str[(*offset)++];	117	b = (uint8_t) str[(*offset)++];
119		118
120	/* Must be 10xxxxxx. */	119	/* Must be 10xxxxxx. */
121	if ((b & 0xc0) != 0x80) {	120	if ((b & 0xc0) != 0x80) {
122	return invalch;	121	return invalch;
123	}	122	}
124		123
125	/* Shift data bits to ch. */	124	/* Shift data bits to ch. */
126	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));	125	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));
127	--cbytes;	126	--cbytes;
128	}	127	}
129		128
130	return ch;	129	return ch;
131	}	130	}
132		131
133	/** Encode a single character to string representation.	132	/** Encode a single character to string representation.
134	*	133	*
135	* Encode a single character to string representation (i.e. UTF-8) and store	134	* 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	135	* 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.	136	* is moved to the position where the next character can be written to.
138	*	137	*
139	* @param ch Input character.	138	* @param ch Input character.
140	* @param str Output buffer.	139	* @param str Output buffer.
141	* @param offset Offset (in bytes) where to start writing.	140	* @param offset Offset (in bytes) where to start writing.
142	* @param sz Size of the output buffer.	141	* @param sz Size of the output buffer.
143	*	142	*
144	* @return True if the character was encoded successfully or false if there	143	* @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	144	* was not enough space in the output buffer or the character code
146	* was invalid.	145	* was invalid.
147	*/	146	*/
148	bool chr_encode(const wchar_t ch, char str, size_t offset, size_t sz)	147	bool chr_encode(const wchar_t ch, char str, size_t offset, size_t sz)
149	{	148	{
150	uint32_t cc; /* Unsigned version of ch. */	149	uint32_t cc; /* Unsigned version of ch. */
151		150
152	int cbytes; /* Number of continuation bytes. */	151	int cbytes; /* Number of continuation bytes. */
153	int b0_bits; /* Number of data bits in first byte. */	152	int b0_bits; /* Number of data bits in first byte. */
154	int i;	153	int i;
155		154
156	if (*offset >= sz)	155	if (*offset >= sz)
157	return false;	156	return false;
158		157
159	if (ch < 0)	158	if (ch < 0)
160	return false;	159	return false;
161		160
162	/* Bit operations should only be done on unsigned numbers. */	161	/* Bit operations should only be done on unsigned numbers. */
163	cc = (uint32_t) ch;	162	cc = (uint32_t) ch;
164		163
165	/* Determine how many continuation bytes are needed. */	164	/* Determine how many continuation bytes are needed. */
166	if ((cc & ~LO_MASK_32(7)) == 0) {	165	if ((cc & ~LO_MASK_32(7)) == 0) {
167	b0_bits = 7;	166	b0_bits = 7;
168	cbytes = 0;	167	cbytes = 0;
169	} else if ((cc & ~LO_MASK_32(11)) == 0) {	168	} else if ((cc & ~LO_MASK_32(11)) == 0) {
170	b0_bits = 5;	169	b0_bits = 5;
171	cbytes = 1;	170	cbytes = 1;
172	} else if ((cc & ~LO_MASK_32(16)) == 0) {	171	} else if ((cc & ~LO_MASK_32(16)) == 0) {
173	b0_bits = 4;	172	b0_bits = 4;
174	cbytes = 2;	173	cbytes = 2;
175	} else if ((cc & ~LO_MASK_32(21)) == 0) {	174	} else if ((cc & ~LO_MASK_32(21)) == 0) {
176	b0_bits = 3;	175	b0_bits = 3;
177	cbytes = 3;	176	cbytes = 3;
178	} else {	177	} else {
179	/* Codes longer than 21 bits are not supported. */	178	/* Codes longer than 21 bits are not supported. */
180	return false;	179	return false;
181	}	180	}
182		181
183	/* Check for available space in buffer. */	182	/* Check for available space in buffer. */
184	if (*offset + cbytes >= sz)	183	if (*offset + cbytes >= sz)
185	return false;	184	return false;
186		185
187	/* Encode continuation bytes. */	186	/* Encode continuation bytes. */
188	for (i = cbytes; i > 0; --i) {	187	for (i = cbytes; i > 0; --i) {
189	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));	188	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));
190	cc = cc >> CONT_BITS;	189	cc = cc >> CONT_BITS;
191	}	190	}
192		191
193	/* Encode first byte. */	192	/* Encode first byte. */
194	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);	193	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);
195		194
196	/* Advance offset. */	195	/* Advance offset. */
197	*offset += (1 + cbytes);	196	*offset += (1 + cbytes);
198		197
199	return true;	198	return true;
200	}	199	}
201		200
202	/** Get size of string, with length limit.	201	/** Get size of string, with length limit.
203	*	202	*
204	* Get the number of bytes which are used by up to @a max_len first	203	* Get the number of bytes which are used by up to @a max_len first
205	* characters in the string @a str. If @a max_len is greater than	204	* characters in the string @a str. If @a max_len is greater than
206	* the length of @a str, the entire string is measured.	205	* the length of @a str, the entire string is measured.
207	*	206	*
208	* @param str String to consider.	207	* @param str String to consider.
209	* @param count Maximum number of characters to measure.	208	* @param count Maximum number of characters to measure.
210	*	209	*
211	* @return Number of bytes used by the characters.	210	* @return Number of bytes used by the characters.
212	*/	211	*/
213	size_t str_lsize(const char *str, count_t max_len)	212	size_t str_lsize(const char *str, count_t max_len)
214	{	213	{
215	count_t len = 0;	214	count_t len = 0;
216	size_t cur = 0;	215	size_t cur = 0;
217	size_t prev;	216	size_t prev;
218	wchar_t ch;	217	wchar_t ch;
219		218
220	while (true) {	219	while (true) {
221	prev = cur;	220	prev = cur;
222	if (len >= max_len)	221	if (len >= max_len)
223	break;	222	break;
224	ch = chr_decode(str, &cur, UTF8_NO_LIMIT);	223	ch = chr_decode(str, &cur, UTF8_NO_LIMIT);
225	if (ch == '\0') break;	224	if (ch == '\0') break;
226		225
227	len++;	226	len++;
228	}	227	}
229		228
230	return prev;	229	return prev;
231	}	230	}
232		231
233	/** Check whether character is plain ASCII.	232	/** Check whether character is plain ASCII.
234	*	233	*
235	* @return True if character is plain ASCII.	234	* @return True if character is plain ASCII.
236	*	235	*
237	*/	236	*/
238	bool ascii_check(const wchar_t ch)	237	bool ascii_check(const wchar_t ch)
239	{	238	{
240	if ((ch >= 0) && (ch <= 127))	239	if ((ch >= 0) && (ch <= 127))
241	return true;	240	return true;
242		241
243	return false;	242	return false;
244	}	243	}
245		244
246	/** Check whether character is Unicode.	245	/** Check whether character is Unicode.
247	*	246	*
248	* @return True if character is valid Unicode code point.	247	* @return True if character is valid Unicode code point.
249	*	-
250	*/	248	*/
251	bool unicode_check(const wchar_t ch)	249	bool unicode_check(const wchar_t ch)
252	{	250	{
253	if ((ch >= 0) && (ch <= 1114111))	251	if ((ch >= 0) && (ch <= 1114111))
254	return true;	252	return true;
255		253
256	return false;	254	return false;
257	}	255	}
258		256
259	/** Return number of plain characters in a string.	257	/** Return number of bytes the string occupies.
260	*	-
261	* @param str NULL-terminated string.	-
262	*	-
263	* @return Number of characters in @a str.	-
264	*	258	*
-		259	* @param str A string.
-		260	* @return Number of bytes in @a str excluding the null terminator.
265	*/	261	*/
266	size_t strlen(const char *str)	262	size_t str_size(const char *str)
267	{	263	{
268	size_t size;	264	size_t size;
-		265
-		266	size = 0;
269	for (size = 0; str[size]; size++);	267	while (*str++ != '\0')
-		268	++size;
270		269
271	return size;	270	return size;
272	}	271	}
273		272
274	/** Return number of characters in a string.	273	/** Return number of characters in a string.
275	*	274	*
276	* @param str NULL-terminated string.	275	* @param str NULL-terminated string.
277	* @return Number of characters in string.	276	* @return Number of characters in string.
278	*/	277	*/
279	count_t str_length(const char *str)	278	count_t str_length(const char *str)
280	{	279	{
281	count_t len = 0;	280	count_t len = 0;
282	size_t offset = 0;	281	size_t offset = 0;
283		282
284	while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) {	283	while (chr_decode(str, &offset, UTF8_NO_LIMIT) != 0) {
285	len++;	284	len++;
286	}	285	}
287		286
288	return len;	287	return len;
289	}	288	}
290		289
291	/** Return number of characters in a wide string.	290	/** Return number of characters in a wide string.
292	*	291	*
293	* @param str NULL-terminated wide string.	292	* @param str NULL-terminated wide string.
294	* @return Number of characters in @a str.	293	* @return Number of characters in @a str.
295	*/	294	*/
296	count_t wstr_length(const wchar_t *wstr)	295	count_t wstr_length(const wchar_t *wstr)
297	{	296	{
298	count_t len;	297	count_t len;
299		298
300	len = 0;	299	len = 0;
301	while (*wstr++ != '\0')	300	while (*wstr++ != '\0')
302	++len;	301	++len;
303		302
304	return len;	303	return len;
305	}	304	}
306		305
307	/** Compare two NULL terminated strings	306	/** Compare two NULL terminated strings
308	*	307	*
309	* Do a char-by-char comparison of two NULL terminated strings.	308	* Do a char-by-char comparison of two NULL terminated strings.
310	* The strings are considered equal iff they consist of the same	309	* The strings are considered equal iff they consist of the same
311	* characters on the minimum of their lengths.	310	* characters on the minimum of their lengths.
312	*	311	*
313	* @param src First string to compare.	312	* @param src First string to compare.
314	* @param dst Second string to compare.	313	* @param dst Second string to compare.
315	*	314	*
316	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	315	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
317	*	316	*
318	*/	317	*/
319	int strcmp(const char src, const char dst)	318	int strcmp(const char src, const char dst)
320	{	319	{
321	for (; src && dst; src++, dst++) {	320	for (; src && dst; src++, dst++) {
322	if (src < dst)	321	if (src < dst)
323	return -1;	322	return -1;
324	if (src > dst)	323	if (src > dst)
325	return 1;	324	return 1;
326	}	325	}
327	if (src == dst)	326	if (src == dst)
328	return 0;	327	return 0;
329		328
330	if (!*src)	329	if (!*src)
331	return -1;	330	return -1;
332		331
333	return 1;	332	return 1;
334	}	333	}
335		334
336		335
337	/** Compare two NULL terminated strings	336	/** Compare two NULL terminated strings
338	*	337	*
339	* Do a char-by-char comparison of two NULL terminated strings.	338	* Do a char-by-char comparison of two NULL terminated strings.
340	* The strings are considered equal iff they consist of the same	339	* The strings are considered equal iff they consist of the same
341	* characters on the minimum of their lengths and specified maximal	340	* characters on the minimum of their lengths and specified maximal
342	* length.	341	* length.
343	*	342	*
344	* @param src First string to compare.	343	* @param src First string to compare.
345	* @param dst Second string to compare.	344	* @param dst Second string to compare.
346	* @param len Maximal length for comparison.	345	* @param len Maximal length for comparison.
347	*	346	*
348	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	347	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
349	*	-
350	*/	348	*/
351	int strncmp(const char src, const char dst, size_t len)	349	int strncmp(const char src, const char dst, size_t len)
352	{	350	{
353	unsigned int i;	351	unsigned int i;
354		352
355	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {	353	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {
356	if (src < dst)	354	if (src < dst)
357	return -1;	355	return -1;
358		356
359	if (src > dst)	357	if (src > dst)
360	return 1;	358	return 1;
361	}	359	}
362		360
363	if (i == len \|\| src == dst)	361	if (i == len \|\| src == dst)
364	return 0;	362	return 0;
365		363
366	if (!*src)	364	if (!*src)
367	return -1;	365	return -1;
368		366
369	return 1;	367	return 1;
370	}	368	}
371		369
372		370
373		371
374	/** Copy NULL terminated string.	372	/** Copy NULL terminated string.
375	*	373	*
376	* Copy at most 'len' characters from string 'src' to 'dest'.	374	* Copy at most 'len' characters from string 'src' to 'dest'.
377	* If 'src' is shorter than 'len', '\0' is inserted behind the	375	* If 'src' is shorter than 'len', '\0' is inserted behind the
378	* last copied character.	376	* last copied character.
379	*	377	*
380	* @param src Source string.	378	* @param src Source string.
381	* @param dest Destination buffer.	379	* @param dest Destination buffer.
382	* @param len Size of destination buffer.	380	* @param len Size of destination buffer.
383	*	-
384	*/	381	*/
385	void strncpy(char dest, const char src, size_t len)	382	void strncpy(char dest, const char src, size_t len)
386	{	383	{
387	unsigned int i;	384	unsigned int i;
388		385
389	for (i = 0; i < len; i++) {	386	for (i = 0; i < len; i++) {
390	if (!(dest[i] = src[i]))	387	if (!(dest[i] = src[i]))
391	return;	388	return;
392	}	389	}
393		390
394	dest[i - 1] = '\0';	391	dest[i - 1] = '\0';
395	}	392	}
396		393
397	/** Find first occurence of character in string.	394	/** Find first occurence of character in string.
398	*	395	*
399	* @param s String to search.	396	* @param s String to search.
400	* @param i Character to look for.	397	* @param i Character to look for.
401	*	398	*
402	* @return Pointer to character in @a s or NULL if not found.	399	* @return Pointer to character in @a s or NULL if not found.
403	*/	400	*/
404	extern char strchr(const char s, int i)	401	extern char strchr(const char s, int i)
405	{	402	{
406	while (*s != '\0') {	403	while (*s != '\0') {
407	if (*s == i)	404	if (*s == i)
408	return (char *) s;	405	return (char *) s;
409	++s;	406	++s;
410	}	407	}
411		408
412	return NULL;	409	return NULL;
413	}	410	}
414		411
415	/** @}	412	/** @}
416	*/	413	*/
417		414

Subversion Repositories HelenOS

(root)/trunk/kernel/generic/src/lib/string.c – Rev 4205 → 4207