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 bytes used by UTF-8 characters.
 *
 * Get the number of bytes (count of plain characters) which
 * are used by a given count of UTF-8 characters in a string.
 * As UTF-8 encoding is multibyte, there is no constant
 * correspondence between number of characters and used bytes.
 *
 * @param str   UTF-8 string to consider.
 * @param count Number of UTF-8 characters to count.
 *
 * @return Number of bytes used by the characters.
 *
 */
size_t utf8_count_bytes(const char *str, count_t count)
{
    size_t size = 0;
    index_t index = 0;
    index_t iprev;
    wchar_t ch;
   
    while (true) {
        iprev = index;
        if (size >= count)
            break;
        ch = chr_decode(str, &index, UTF8_NO_LIMIT);
        if (ch == '\0') break;
 
        size++;
    }
   
    return iprev;
}
 
/** 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 str.
 *
 */
size_t strlen(const char *str)
{
    size_t size;
    for (size = 0; str[size]; size++);
   
    return size;
}
 
/** Return number of UTF-8 characters in a string.
 *
 * @param str NULL-terminated UTF-8 string.
 *
 * @return Number of UTF-8 characters in str.
 *
 */
size_t strlen_utf8(const char *str)
{
    size_t size = 0;
    index_t index = 0;
   
    while (chr_decode(str, &index, UTF8_NO_LIMIT) != 0) {
        size++;
    }
   
    return size;
}
 
/** Return number of UTF-32 characters in a string.
 *
 * @param str NULL-terminated UTF-32 string.
 *
 * @return Number of UTF-32 characters in str.
 *
 */
size_t strlen_utf32(const wchar_t *str)
{
    size_t size;
    for (size = 0; str[size]; size++);
   
    return size;
}
 
/** 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 4199	Rev 4200
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 UTF-8 character from a NULL-terminated string.	59	/** Decode a single character from a substring.
60	*	60	*
61	* Decode a single UTF-8 character from a plain char NULL-terminated	61	* Decode a single character from a substring of size @a sz. Decoding starts
62	* string. Decoding starts at @index and this index is moved to the	62	* at @a offset and this offset is moved to the beginning of the next
63	* beginning of the next character. In case of decoding error,	63	* character. In case of decoding error, offset generally advances at least
64	* index advances. However, index is never moved beyond (str+limit).	64	* by one. However, offset is never moved beyond (str + sz).
65	*	65	*
66	* @param str Plain character NULL-terminated string.	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 Maximal allowed value of index.	69	* @param limit Size of the substring.
70	*	70	*
71	* @return Decoded character in UTF-32 or '?' if the encoding is wrong.	71	* @return Value of decoded character or '?' on decoding error.
72	*	72	*
73	*/	73	*/
74	wchar_t utf8_decode(const char str, index_t index, index_t limit)	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 (*index + 1 > limit)	82	if (*offset + 1 > sz)
83	return invalch;	83	return invalch;
84		84
85	b0 = (uint8_t) str[(*index)++];	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 (*index + cbytes > limit) {	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[(*index)++];	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 UTF-32 character as UTF-8	-
134	*	-
135	* Encode a single UTF-32 character as UTF-8 and store it into	133	/** Encode a single character to string representation.
136	* the given buffer at @index. Encoding starts at @index and	-
137	* this index is moved at the position where the next character	-
138	* can be written to.	-
139	*	-
140	* @param ch Input UTF-32 character.	-
141	* @param str Output buffer.	-
142	* @param index Index (counted in plain characters) where to start	-
143	* the encoding	-
144	* @param limit Maximal allowed value of index.	-
145	*	-
146	* @return True if the character was encoded or false if there is not	-
147	* enought space in the output buffer or the character is invalid	-
148	* Unicode code point.	-
149	*	134	*
-		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
-		137	* is moved to the position where the next character can be written to.
-		138	*
-		139	* @param ch Input character.
-		140	* @param str Output buffer.
-		141	* @param offset Offset (in bytes) where to start writing.
-		142	* @param sz Size of the output buffer.
-		143	*
-		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
-		146	* was invalid.
150	*/	147	*/
151	bool utf8_encode(const wchar_t ch, char str, index_t index, index_t limit)	148	bool chr_encode(const wchar_t ch, char str, size_t offset, size_t sz)
152	{	149	{
153	uint32_t cc; /* Unsigned version of ch. */	150	uint32_t cc; /* Unsigned version of ch. */
154		151
155	int cbytes; /* Number of continuation bytes. */	152	int cbytes; /* Number of continuation bytes. */
156	int b0_bits; /* Number of data bits in first byte. */	153	int b0_bits; /* Number of data bits in first byte. */
157	int i;	154	int i;
158		155
159	if (*index >= limit)	156	if (*offset >= sz)
160	return false;	157	return false;
161		158
162	if (ch < 0)	159	if (ch < 0)
163	return false;	160	return false;
164		161
165	/* Bit operations should only be done on unsigned numbers. */	162	/* Bit operations should only be done on unsigned numbers. */
166	cc = (uint32_t) ch;	163	cc = (uint32_t) ch;
167		164
168	/* Determine how many continuation bytes are needed. */	165	/* Determine how many continuation bytes are needed. */
169	if ((cc & ~LO_MASK_32(7)) == 0) {	166	if ((cc & ~LO_MASK_32(7)) == 0) {
170	b0_bits = 7;	167	b0_bits = 7;
171	cbytes = 0;	168	cbytes = 0;
172	} else if ((cc & ~LO_MASK_32(11)) == 0) {	169	} else if ((cc & ~LO_MASK_32(11)) == 0) {
173	b0_bits = 5;	170	b0_bits = 5;
174	cbytes = 1;	171	cbytes = 1;
175	} else if ((cc & ~LO_MASK_32(16)) == 0) {	172	} else if ((cc & ~LO_MASK_32(16)) == 0) {
176	b0_bits = 4;	173	b0_bits = 4;
177	cbytes = 2;	174	cbytes = 2;
178	} else if ((cc & ~LO_MASK_32(21)) == 0) {	175	} else if ((cc & ~LO_MASK_32(21)) == 0) {
179	b0_bits = 3;	176	b0_bits = 3;
180	cbytes = 3;	177	cbytes = 3;
181	} else {	178	} else {
182	/* Codes longer than 21 bits are not supported. */	179	/* Codes longer than 21 bits are not supported. */
183	return false;	180	return false;
184	}	181	}
185		182
186	/* Check for available space in buffer. */	183	/* Check for available space in buffer. */
187	if (*index + cbytes >= limit)	184	if (*offset + cbytes >= sz)
188	return false;	185	return false;
189		186
190	/* Encode continuation bytes. */	187	/* Encode continuation bytes. */
191	for (i = cbytes; i > 0; --i) {	188	for (i = cbytes; i > 0; --i) {
192	str[*index + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));	189	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));
193	cc = cc >> CONT_BITS;	190	cc = cc >> CONT_BITS;
194	}	191	}
195		192
196	/* Encode first byte. */	193	/* Encode first byte. */
197	str[*index] = (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);
198		195
199	/* Advance index. */	196	/* Advance offset. */
200	*index += (1 + cbytes);	197	*offset += (1 + cbytes);
201		198
202	return true;	199	return true;
203	}	200	}
204		201
205	/** Get bytes used by UTF-8 characters.	202	/** Get bytes used by UTF-8 characters.
206	*	203	*
207	* Get the number of bytes (count of plain characters) which	204	* Get the number of bytes (count of plain characters) which
208	* are used by a given count of UTF-8 characters in a string.	205	* are used by a given count of UTF-8 characters in a string.
209	* As UTF-8 encoding is multibyte, there is no constant	206	* As UTF-8 encoding is multibyte, there is no constant
210	* correspondence between number of characters and used bytes.	207	* correspondence between number of characters and used bytes.
211	*	208	*
212	* @param str UTF-8 string to consider.	209	* @param str UTF-8 string to consider.
213	* @param count Number of UTF-8 characters to count.	210	* @param count Number of UTF-8 characters to count.
214	*	211	*
215	* @return Number of bytes used by the characters.	212	* @return Number of bytes used by the characters.
216	*	213	*
217	*/	214	*/
218	size_t utf8_count_bytes(const char *str, count_t count)	215	size_t utf8_count_bytes(const char *str, count_t count)
219	{	216	{
220	size_t size = 0;	217	size_t size = 0;
221	index_t index = 0;	218	index_t index = 0;
222	index_t iprev;	219	index_t iprev;
223	wchar_t ch;	220	wchar_t ch;
224		221
225	while (true) {	222	while (true) {
226	iprev = index;	223	iprev = index;
227	if (size >= count)	224	if (size >= count)
228	break;	225	break;
229	ch = utf8_decode(str, &index, UTF8_NO_LIMIT);	226	ch = chr_decode(str, &index, UTF8_NO_LIMIT);
230	if (ch == '\0') break;	227	if (ch == '\0') break;
231		228
232	size++;	229	size++;
233	}	230	}
234		231
235	return iprev;	232	return iprev;
236	}	233	}
237		234
238	/** Check whether character is plain ASCII.	235	/** Check whether character is plain ASCII.
239	*	236	*
240	* @return True if character is plain ASCII.	237	* @return True if character is plain ASCII.
241	*	238	*
242	*/	239	*/
243	bool ascii_check(const wchar_t ch)	240	bool ascii_check(const wchar_t ch)
244	{	241	{
245	if ((ch >= 0) && (ch <= 127))	242	if ((ch >= 0) && (ch <= 127))
246	return true;	243	return true;
247		244
248	return false;	245	return false;
249	}	246	}
250		247
251	/** Check whether character is Unicode.	248	/** Check whether character is Unicode.
252	*	249	*
253	* @return True if character is valid Unicode code point.	250	* @return True if character is valid Unicode code point.
254	*	251	*
255	*/	252	*/
256	bool unicode_check(const wchar_t ch)	253	bool unicode_check(const wchar_t ch)
257	{	254	{
258	if ((ch >= 0) && (ch <= 1114111))	255	if ((ch >= 0) && (ch <= 1114111))
259	return true;	256	return true;
260		257
261	return false;	258	return false;
262	}	259	}
263		260
264	/** Return number of plain characters in a string.	261	/** Return number of plain characters in a string.
265	*	262	*
266	* @param str NULL-terminated string.	263	* @param str NULL-terminated string.
267	*	264	*
268	* @return Number of characters in str.	265	* @return Number of characters in str.
269	*	266	*
270	*/	267	*/
271	size_t strlen(const char *str)	268	size_t strlen(const char *str)
272	{	269	{
273	size_t size;	270	size_t size;
274	for (size = 0; str[size]; size++);	271	for (size = 0; str[size]; size++);
275		272
276	return size;	273	return size;
277	}	274	}
278		275
279	/** Return number of UTF-8 characters in a string.	276	/** Return number of UTF-8 characters in a string.
280	*	277	*
281	* @param str NULL-terminated UTF-8 string.	278	* @param str NULL-terminated UTF-8 string.
282	*	279	*
283	* @return Number of UTF-8 characters in str.	280	* @return Number of UTF-8 characters in str.
284	*	281	*
285	*/	282	*/
286	size_t strlen_utf8(const char *str)	283	size_t strlen_utf8(const char *str)
287	{	284	{
288	size_t size = 0;	285	size_t size = 0;
289	index_t index = 0;	286	index_t index = 0;
290		287
291	while (utf8_decode(str, &index, UTF8_NO_LIMIT) != 0) {	288	while (chr_decode(str, &index, UTF8_NO_LIMIT) != 0) {
292	size++;	289	size++;
293	}	290	}
294		291
295	return size;	292	return size;
296	}	293	}
297		294
298	/** Return number of UTF-32 characters in a string.	295	/** Return number of UTF-32 characters in a string.
299	*	296	*
300	* @param str NULL-terminated UTF-32 string.	297	* @param str NULL-terminated UTF-32 string.
301	*	298	*
302	* @return Number of UTF-32 characters in str.	299	* @return Number of UTF-32 characters in str.
303	*	300	*
304	*/	301	*/
305	size_t strlen_utf32(const wchar_t *str)	302	size_t strlen_utf32(const wchar_t *str)
306	{	303	{
307	size_t size;	304	size_t size;
308	for (size = 0; str[size]; size++);	305	for (size = 0; str[size]; size++);
309		306
310	return size;	307	return size;
311	}	308	}
312		309
313	/** Compare two NULL terminated strings	310	/** Compare two NULL terminated strings
314	*	311	*
315	* Do a char-by-char comparison of two NULL terminated strings.	312	* Do a char-by-char comparison of two NULL terminated strings.
316	* The strings are considered equal iff they consist of the same	313	* The strings are considered equal iff they consist of the same
317	* characters on the minimum of their lengths.	314	* characters on the minimum of their lengths.
318	*	315	*
319	* @param src First string to compare.	316	* @param src First string to compare.
320	* @param dst Second string to compare.	317	* @param dst Second string to compare.
321	*	318	*
322	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	319	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
323	*	320	*
324	*/	321	*/
325	int strcmp(const char src, const char dst)	322	int strcmp(const char src, const char dst)
326	{	323	{
327	for (; src && dst; src++, dst++) {	324	for (; src && dst; src++, dst++) {
328	if (src < dst)	325	if (src < dst)
329	return -1;	326	return -1;
330	if (src > dst)	327	if (src > dst)
331	return 1;	328	return 1;
332	}	329	}
333	if (src == dst)	330	if (src == dst)
334	return 0;	331	return 0;
335		332
336	if (!*src)	333	if (!*src)
337	return -1;	334	return -1;
338		335
339	return 1;	336	return 1;
340	}	337	}
341		338
342		339
343	/** Compare two NULL terminated strings	340	/** Compare two NULL terminated strings
344	*	341	*
345	* Do a char-by-char comparison of two NULL terminated strings.	342	* Do a char-by-char comparison of two NULL terminated strings.
346	* The strings are considered equal iff they consist of the same	343	* The strings are considered equal iff they consist of the same
347	* characters on the minimum of their lengths and specified maximal	344	* characters on the minimum of their lengths and specified maximal
348	* length.	345	* length.
349	*	346	*
350	* @param src First string to compare.	347	* @param src First string to compare.
351	* @param dst Second string to compare.	348	* @param dst Second string to compare.
352	* @param len Maximal length for comparison.	349	* @param len Maximal length for comparison.
353	*	350	*
354	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.	351	* @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
355	*	352	*
356	*/	353	*/
357	int strncmp(const char src, const char dst, size_t len)	354	int strncmp(const char src, const char dst, size_t len)
358	{	355	{
359	unsigned int i;	356	unsigned int i;
360		357
361	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {	358	for (i = 0; (src) && (dst) && (i < len); src++, dst++, i++) {
362	if (src < dst)	359	if (src < dst)
363	return -1;	360	return -1;
364		361
365	if (src > dst)	362	if (src > dst)
366	return 1;	363	return 1;
367	}	364	}
368		365
369	if (i == len \|\| src == dst)	366	if (i == len \|\| src == dst)
370	return 0;	367	return 0;
371		368
372	if (!*src)	369	if (!*src)
373	return -1;	370	return -1;
374		371
375	return 1;	372	return 1;
376	}	373	}
377		374
378		375
379		376
380	/** Copy NULL terminated string.	377	/** Copy NULL terminated string.
381	*	378	*
382	* Copy at most 'len' characters from string 'src' to 'dest'.	379	* Copy at most 'len' characters from string 'src' to 'dest'.
383	* If 'src' is shorter than 'len', '\0' is inserted behind the	380	* If 'src' is shorter than 'len', '\0' is inserted behind the
384	* last copied character.	381	* last copied character.
385	*	382	*
386	* @param src Source string.	383	* @param src Source string.
387	* @param dest Destination buffer.	384	* @param dest Destination buffer.
388	* @param len Size of destination buffer.	385	* @param len Size of destination buffer.
389	*	386	*
390	*/	387	*/
391	void strncpy(char dest, const char src, size_t len)	388	void strncpy(char dest, const char src, size_t len)
392	{	389	{
393	unsigned int i;	390	unsigned int i;
394		391
395	for (i = 0; i < len; i++) {	392	for (i = 0; i < len; i++) {
396	if (!(dest[i] = src[i]))	393	if (!(dest[i] = src[i]))
397	return;	394	return;
398	}	395	}
399		396
400	dest[i - 1] = '\0';	397	dest[i - 1] = '\0';
401	}	398	}
402		399
403	/** Find first occurence of character in string.	400	/** Find first occurence of character in string.
404	*	401	*
405	* @param s String to search.	402	* @param s String to search.
406	* @param i Character to look for.	403	* @param i Character to look for.
407	*	404	*
408	* @return Pointer to character in @a s or NULL if not found.	405	* @return Pointer to character in @a s or NULL if not found.
409	*/	406	*/
410	extern char strchr(const char s, int i)	407	extern char strchr(const char s, int i)
411	{	408	{
412	while (*s != '\0') {	409	while (*s != '\0') {
413	if (*s == i)	410	if (*s == i)
414	return (char *) s;	411	return (char *) s;
415	++s;	412	++s;
416	}	413	}
417		414
418	return NULL;	415	return NULL;
419	}	416	}
420		417
421	/** @}	418	/** @}
422	*/	419	*/
423		420

Subversion Repositories HelenOS

(root)/trunk/kernel/generic/src/lib/string.c @ 4275 – Rev 4199 → 4200