WebSVN – HelenOS – Diff – /trunk/uspace/lib/libc/generic/string.c


/*
 * Copyright (c) 2005 Martin Decky
 * Copyright (c) 2008 Jiri Svoboda
 * 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 libc
 * @{
 */
/** @file
 */
 
#include <string.h>
#include <stdlib.h>
#include <limits.h>
#include <ctype.h>
#include <malloc.h>
#include <errno.h>
#include <align.h>
#include <mem.h>
#include <string.h>
 
/** Byte mask consisting of lowest @n bits (out of 8) */
#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 8) */
#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 string.
 *
 * Decode a single character from a string of size @a size. 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 size.
 *
 * @param str    String (not necessarily NULL-terminated).
 * @param offset Byte offset in string where to start decoding.
 * @param size   Size of the string (in bytes).
 *
 * @return Value of decoded character, U_SPECIAL on decoding error or
 *         NULL if attempt to decode beyond @a size.
 *
 */
wchar_t str_decode(const char *str, size_t *offset, size_t size)
{
    if (*offset + 1 > size)
        return 0;
   
    /* First byte read from string */
    uint8_t b0 = (uint8_t) str[(*offset)++];
   
    /* Determine code length */
   
    unsigned int b0_bits;  /* Data bits in first byte */
    unsigned int cbytes;   /* Number of continuation bytes */
   
    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 U_SPECIAL;
    }
   
    if (*offset + cbytes > size)
        return U_SPECIAL;
   
    wchar_t ch = b0 & LO_MASK_8(b0_bits);
   
    /* Decode continuation bytes */
    while (cbytes > 0) {
        uint8_t b = (uint8_t) str[(*offset)++];
       
        /* Must be 10xxxxxx */
        if ((b & 0xc0) != 0x80)
            return U_SPECIAL;
       
        /* 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 Byte offset where to start writing.
 * @param size   Size of the output buffer (in bytes).
 *
 * @return EOK if the character was encoded successfully, EOVERFLOW if there
 *     was not enough space in the output buffer or EINVAL if the character
 *     code was invalid.
 */
int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size)
{
    if (*offset >= size)
        return EOVERFLOW;
   
    if (!chr_check(ch))
        return EINVAL;
   
    /* Unsigned version of ch (bit operations should only be done
       on unsigned types). */
    uint32_t cc = (uint32_t) ch;
   
    /* Determine how many continuation bytes are needed */
   
    unsigned int b0_bits;  /* Data bits in first byte */
    unsigned int cbytes;   /* Number of continuation bytes */
   
    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 EINVAL;
    }
   
    /* Check for available space in buffer */
    if (*offset + cbytes >= size)
        return EOVERFLOW;
   
    /* Encode continuation bytes */
    unsigned int i;
    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 += cbytes + 1;
   
    return EOK;
}
 
/** Get size of string.
 *
 * Get the number of bytes which are used by the string @a str (excluding the
 * NULL-terminator).
 *
 * @param str String to consider.
 *
 * @return Number of bytes used by the string
 *
 */
size_t str_size(const char *str)
{
    size_t size = 0;
   
    while (*str++ != 0)
        size++;
   
    return size;
}
 
/** Get size of wide string.
 *
 * Get the number of bytes which are used by the wide string @a str (excluding the
 * NULL-terminator).
 *
 * @param str Wide string to consider.
 *
 * @return Number of bytes used by the wide string
 *
 */
size_t wstr_size(const wchar_t *str)
{
    return (wstr_length(str) * sizeof(wchar_t));
}
 
/** 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 (excluding the
 * NULL-terminator).
 *
 * @param str     String to consider.
 * @param max_len 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 offset = 0;
   
    while (len < max_len) {
        if (str_decode(str, &offset, STR_NO_LIMIT) == 0)
            break;
       
        len++;
    }
   
    return offset;
}
 
/** Get size of wide string with length limit.
 *
 * Get the number of bytes which are used by up to @a max_len first
 * wide characters in the wide string @a str. If @a max_len is greater than
 * the length of @a str, the entire wide string is measured (excluding the
 * NULL-terminator).
 *
 * @param str     Wide string to consider.
 * @param max_len Maximum number of wide characters to measure.
 *
 * @return Number of bytes used by the wide characters.
 *
 */
size_t wstr_lsize(const wchar_t *str, count_t max_len)
{
    return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t));
}
 
/** Get 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 (str_decode(str, &offset, STR_NO_LIMIT) != 0)
        len++;
   
    return len;
}
 
/** Get 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 = 0;
   
    while (*wstr++ != 0)
        len++;
   
    return len;
}
 
/** Get number of characters in a string with size limit.
 *
 * @param str  NULL-terminated string.
 * @param size Maximum number of bytes to consider.
 *
 * @return Number of characters in string.
 *
 */
count_t str_nlength(const char *str, size_t size)
{
    count_t len = 0;
    size_t offset = 0;
   
    while (str_decode(str, &offset, size) != 0)
        len++;
   
    return len;
}
 
/** Get number of characters in a string with size limit.
 *
 * @param str  NULL-terminated string.
 * @param size Maximum number of bytes to consider.
 *
 * @return Number of characters in string.
 *
 */
count_t wstr_nlength(const wchar_t *str, size_t size)
{
    count_t len = 0;
    count_t limit = ALIGN_DOWN(size, sizeof(wchar_t));
    count_t offset = 0;
   
    while ((offset < limit) && (*str++ != 0)) {
        len++;
        offset += sizeof(wchar_t);
    }
   
    return len;
}
 
/** Check whether character is plain ASCII.
 *
 * @return True if character is plain ASCII.
 *
 */
bool ascii_check(wchar_t ch)
{
    if ((ch >= 0) && (ch <= 127))
        return true;
   
    return false;
}
 
/** Check whether character is valid
 *
 * @return True if character is a valid Unicode code point.
 *
 */
bool chr_check(wchar_t ch)
{
    if ((ch >= 0) && (ch <= 1114111))
        return true;
   
    return false;
}
 
/** 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 s1 First string to compare.
 * @param s2 Second string to compare.
 *
 * @return 0 if the strings are equal, -1 if first is smaller,
 *         1 if second smaller.
 *
 */
int str_cmp(const char *s1, const char *s2)
{
    wchar_t c1 = 0;
    wchar_t c2 = 0;
   
    size_t off1 = 0;
    size_t off2 = 0;
 
    while (true) {
        c1 = str_decode(s1, &off1, STR_NO_LIMIT);
        c2 = str_decode(s2, &off2, STR_NO_LIMIT);
 
        if (c1 < c2)
            return -1;
       
        if (c1 > c2)
            return 1;
 
        if (c1 == 0 || c2 == 0)
            break;     
    }
 
    return 0;
}
 
/** Compare two NULL terminated strings with length limit.
 *
 * 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 the length limit.
 *
 * @param s1      First string to compare.
 * @param s2      Second string to compare.
 * @param max_len Maximum number of characters to consider.
 *
 * @return 0 if the strings are equal, -1 if first is smaller,
 *         1 if second smaller.
 *
 */
int str_lcmp(const char *s1, const char *s2, count_t max_len)
{
    wchar_t c1 = 0;
    wchar_t c2 = 0;
   
    size_t off1 = 0;
    size_t off2 = 0;
   
    count_t len = 0;
 
    while (true) {
        if (len >= max_len)
            break;
 
        c1 = str_decode(s1, &off1, STR_NO_LIMIT);
        c2 = str_decode(s2, &off2, STR_NO_LIMIT);
 
        if (c1 < c2)
            return -1;
 
        if (c1 > c2)
            return 1;
 
        if (c1 == 0 || c2 == 0)
            break;
 
        ++len; 
    }
 
    return 0;
 
}
 
/** Copy string.
 *
 * Copy source string @a src to destination buffer @a dest.
 * No more than @a size bytes are written. If the size of the output buffer
 * is at least one byte, the output string will always be well-formed, i.e.
 * null-terminated and containing only complete characters.
 *
 * @param dst   Destination buffer.
 * @param count Size of the destination buffer.
 * @param src   Source string.
 */
void str_cpy(char *dest, size_t size, const char *src)
{
    wchar_t ch;
    size_t src_off;
    size_t dest_off;
 
    /* No space for the NULL-terminator in the buffer. */
    if (size == 0)
        return;
   
    src_off = 0;
    dest_off = 0;
 
    while ((ch = str_decode(src, &src_off, STR_NO_LIMIT)) != 0) {
        if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
            break;
    }
 
    dest[dest_off] = '\0';
}
 
/** Copy size-limited substring.
 *
 * Copy source string @a src to destination buffer @a dest.
 * No more than @a size bytes are written. If the size of the output buffer
 * is at least one byte, the output string will always be well-formed, i.e.
 * null-terminated and containing only complete characters.
 *
 * No more than @a n bytes are read from the input string, so it does not
 * have to be null-terminated.
 *
 * @param dst   Destination buffer.
 * @param count Size of the destination buffer.
 * @param src   Source string.
 */
void str_ncpy(char *dest, size_t size, const char *src, size_t n)
{
    wchar_t ch;
    size_t src_off;
    size_t dest_off;
 
    /* No space for the null terminator in the buffer. */
    if (size == 0)
        return;
   
    src_off = 0;
    dest_off = 0;
 
    while ((ch = str_decode(src, &src_off, n)) != 0) {
        if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
            break;
    }
 
    dest[dest_off] = '\0';
}
 
/** Append one string to another.
 *
 * Append source string @a src to string in destination buffer @a dest.
 * Size of the destination buffer is @a dest. If the size of the output buffer
 * is at least one byte, the output string will always be well-formed, i.e.
 * null-terminated and containing only complete characters.
 *
 * @param dst   Destination buffer.
 * @param count Size of the destination buffer.
 * @param src   Source string.
 */
void str_append(char *dest, size_t size, const char *src)
{
    size_t dstr_size;
 
    dstr_size = str_size(dest);
    str_cpy(dest + dstr_size, size - dstr_size, src);
}
 
/** Copy NULL-terminated wide string to string
 *
 * Copy source wide string @a src to destination buffer @a dst.
 * No more than @a size bytes are written. NULL-terminator is always
 * written after the last succesfully copied character (i.e. if the
 * destination buffer is has at least 1 byte, it will be always
 * NULL-terminated).
 *
 * @param src   Source wide string.
 * @param dst   Destination buffer.
 * @param count Size of the destination buffer.
 *
 */
void wstr_nstr(char *dst, const wchar_t *src, size_t size)
{
    /* No space for the NULL-terminator in the buffer */
    if (size == 0)
        return;
   
    wchar_t ch;
    count_t src_idx = 0;
    size_t dst_off = 0;
   
    while ((ch = src[src_idx++]) != 0) {
        if (chr_encode(ch, dst, &dst_off, size) != EOK)
            break;
    }
   
    if (dst_off >= size)
        dst[size - 1] = 0;
    else
        dst[dst_off] = 0;
}
 
/** Find first occurence of character in string.
 *
 * @param str String to search.
 * @param ch  Character to look for.
 *
 * @return Pointer to character in @a str or NULL if not found.
 */
const char *str_chr(const char *str, wchar_t ch)
{
    wchar_t acc;
    size_t off = 0;
   
    while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) {
        if (acc == ch)
            return (str + off);
    }
   
    return NULL;
}
 
/** Find last occurence of character in string.
 *
 * @param str String to search.
 * @param ch  Character to look for.
 *
 * @return Pointer to character in @a str or NULL if not found.
 */
const char *str_rchr(const char *str, wchar_t ch)
{
    wchar_t acc;
    size_t off = 0;
    char *res;
 
    res = NULL;
    while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) {
        if (acc == ch)
            res = (str + off);
    }
 
    return res;
}
 
/** Insert a wide character into a wide string.
 *
 * Insert a wide character into a wide string at position
 * @a pos. The characters after the position are shifted.
 *
 * @param str     String to insert to.
 * @param ch      Character to insert to.
 * @param pos     Character index where to insert.
 @ @param max_pos Characters in the buffer.
 *
 * @return True if the insertion was sucessful, false if the position
 *         is out of bounds.
 *
 */
bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos)
{
    count_t len = wstr_length(str);
   
    if ((pos > len) || (pos + 1 > max_pos))
        return false;
   
    count_t i;
    for (i = len; i + 1 > pos; i--)
        str[i + 1] = str[i];
   
    str[pos] = ch;
   
    return true;
}
 
/** Remove a wide character from a wide string.
 *
 * Remove a wide character from a wide string at position
 * @a pos. The characters after the position are shifted.
 *
 * @param str String to remove from.
 * @param pos Character index to remove.
 *
 * @return True if the removal was sucessful, false if the position
 *         is out of bounds.
 *
 */
bool wstr_remove(wchar_t *str, count_t pos)
{
    count_t len = wstr_length(str);
   
    if (pos >= len)
        return false;
   
    count_t i;
    for (i = pos + 1; i <= len; i++)
        str[i - 1] = str[i];
   
    return true;
}
 
int stricmp(const char *a, const char *b)
{
    int c = 0;
   
    while (a[c] && b[c] && (!(tolower(a[c]) - tolower(b[c]))))
        c++;
   
    return (tolower(a[c]) - tolower(b[c]));
}
 
/** Convert string to a number.
 * Core of strtol and strtoul functions.
 *
 * @param nptr      Pointer to string.
 * @param endptr    If not NULL, function stores here pointer to the first
 *          invalid character.
 * @param base      Zero or number between 2 and 36 inclusive.
 * @param sgn       It's set to 1 if minus found.
 * @return      Result of conversion.
 */
static unsigned long
_strtoul(const char *nptr, char **endptr, int base, char *sgn)
{
    unsigned char c;
    unsigned long result = 0;
    unsigned long a, b;
    const char *str = nptr;
    const char *tmpptr;
   
    while (isspace(*str))
        str++;
   
    if (*str == '-') {
        *sgn = 1;
        ++str;
    } else if (*str == '+')
        ++str;
   
    if (base) {
        if ((base == 1) || (base > 36)) {
            /* FIXME: set errno to EINVAL */
            return 0;
        }
        if ((base == 16) && (*str == '0') && ((str[1] == 'x') ||
            (str[1] == 'X'))) {
            str += 2;
        }
    } else {
        base = 10;
       
        if (*str == '0') {
            base = 8;
            if ((str[1] == 'X') || (str[1] == 'x'))  {
                base = 16;
                str += 2;
            }
        }
    }
   
    tmpptr = str;
 
    while (*str) {
        c = *str;
        c = (c >= 'a' ? c - 'a' + 10 : (c >= 'A' ? c - 'A' + 10 :
            (c <= '9' ? c - '0' : 0xff)));
        if (c > base) {
            break;
        }
       
        a = (result & 0xff) * base + c;
        b = (result >> 8) * base + (a >> 8);
       
        if (b > (ULONG_MAX >> 8)) {
            /* overflow */
            /* FIXME: errno = ERANGE*/
            return ULONG_MAX;
        }
   
        result = (b << 8) + (a & 0xff);
        ++str;
    }
   
    if (str == tmpptr) {
        /*
         * No number was found => first invalid character is the first
         * character of the string.
         */
        /* FIXME: set errno to EINVAL */
        str = nptr;
        result = 0;
    }
   
    if (endptr)
        *endptr = (char *) str;
 
    if (nptr == str) {
        /*FIXME: errno = EINVAL*/
        return 0;
    }
 
    return result;
}
 
/** Convert initial part of string to long int according to given base.
 * The number may begin with an arbitrary number of whitespaces followed by
 * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be
 * inserted and the number will be taken as hexadecimal one. If the base is 0
 * and the number begin with a zero, number will be taken as octal one (as with
 * base 8). Otherwise the base 0 is taken as decimal.
 *
 * @param nptr      Pointer to string.
 * @param endptr    If not NULL, function stores here pointer to the first
 *          invalid character.
 * @param base      Zero or number between 2 and 36 inclusive.
 * @return      Result of conversion.
 */
long int strtol(const char *nptr, char **endptr, int base)
{
    char sgn = 0;
    unsigned long number = 0;
   
    number = _strtoul(nptr, endptr, base, &sgn);
 
    if (number > LONG_MAX) {
        if ((sgn) && (number == (unsigned long) (LONG_MAX) + 1)) {
            /* FIXME: set 0 to errno */
            return number;     
        }
        /* FIXME: set ERANGE to errno */
        return (sgn ? LONG_MIN : LONG_MAX);
    }
   
    return (sgn ? -number : number);
}
 
 
/** Convert initial part of string to unsigned long according to given base.
 * The number may begin with an arbitrary number of whitespaces followed by
 * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be
 * inserted and the number will be taken as hexadecimal one. If the base is 0
 * and the number begin with a zero, number will be taken as octal one (as with
 * base 8). Otherwise the base 0 is taken as decimal.
 *
 * @param nptr      Pointer to string.
 * @param endptr    If not NULL, function stores here pointer to the first
 *          invalid character
 * @param base      Zero or number between 2 and 36 inclusive.
 * @return      Result of conversion.
 */
unsigned long strtoul(const char *nptr, char **endptr, int base)
{
    char sgn = 0;
    unsigned long number = 0;
   
    number = _strtoul(nptr, endptr, base, &sgn);
 
    return (sgn ? -number : number);
}
 
 
 
 
 
 
 
 
 
 
 
 
char *str_dup(const char *src)
{
    size_t size = str_size(src);
    void *dest = malloc(size + 1);
 
    if (dest == NULL)
        return (char *) NULL;
 
    return (char *) memcpy(dest, src, size + 1);
}
 
char *strtok(char *s, const char *delim)
{
    static char *next;
 
    return strtok_r(s, delim, &next);
}
 
char *strtok_r(char *s, const char *delim, char **next)
{
    char *start, *end;
 
    if (s == NULL)
        s = *next;
 
    /* Skip over leading delimiters. */
    while (*s && (str_chr(delim, *s) != NULL)) ++s;
    start = s;
 
    /* Skip over token characters. */
    while (*s && (str_chr(delim, *s) == NULL)) ++s;
    end = s;
    *next = (*s ? s + 1 : s);
 
    if (start == end) {
        return NULL;    /* No more tokens. */
    }
 
    /* Overwrite delimiter with NULL terminator. */
    *end = '\0';
    return start;
}
 
/** @}
 */
 

Rev 4279	Rev 4280
1	/*	1	/*
2	* Copyright (c) 2005 Martin Decky	2	* Copyright (c) 2005 Martin Decky
3	* Copyright (c) 2008 Jiri Svoboda	3	* Copyright (c) 2008 Jiri Svoboda
4	* All rights reserved.	4	* All rights reserved.
5	*	5	*
6	* Redistribution and use in source and binary forms, with or without	6	* Redistribution and use in source and binary forms, with or without
7	* modification, are permitted provided that the following conditions	7	* modification, are permitted provided that the following conditions
8	* are met:	8	* are met:
9	*	9	*
10	* - Redistributions of source code must retain the above copyright	10	* - Redistributions of source code must retain the above copyright
11	* notice, this list of conditions and the following disclaimer.	11	* notice, this list of conditions and the following disclaimer.
12	* - Redistributions in binary form must reproduce the above copyright	12	* - Redistributions in binary form must reproduce the above copyright
13	* notice, this list of conditions and the following disclaimer in the	13	* notice, this list of conditions and the following disclaimer in the
14	* documentation and/or other materials provided with the distribution.	14	* documentation and/or other materials provided with the distribution.
15	* - The name of the author may not be used to endorse or promote products	15	* - The name of the author may not be used to endorse or promote products
16	* derived from this software without specific prior written permission.	16	* derived from this software without specific prior written permission.
17	*	17	*
18	* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR	18	* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
19	* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES	19	* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
20	* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.	20	* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
21	* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,	21	* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
22	* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT	22	* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
23	* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,	23	* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
24	* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY	24	* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
25	* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT	25	* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
26	* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF	26	* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
27	* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.	27	* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
28	*/	28	*/
29		29
30	/** @addtogroup libc	30	/** @addtogroup libc
31	* @{	31	* @{
32	*/	32	*/
33	/** @file	33	/** @file
34	*/	34	*/
35		35
36	#include <string.h>	36	#include <string.h>
37	#include <stdlib.h>	37	#include <stdlib.h>
38	#include <limits.h>	38	#include <limits.h>
39	#include <ctype.h>	39	#include <ctype.h>
40	#include <malloc.h>	40	#include <malloc.h>
41	#include <errno.h>	41	#include <errno.h>
42	#include <align.h>	42	#include <align.h>
43	#include <mem.h>	43	#include <mem.h>
44	#include <string.h>	44	#include <string.h>
45		45
46	/** Byte mask consisting of lowest @n bits (out of 8) */	46	/** Byte mask consisting of lowest @n bits (out of 8) */
47	#define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1))	47	#define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1))
48		48
49	/** Byte mask consisting of lowest @n bits (out of 32) */	49	/** Byte mask consisting of lowest @n bits (out of 32) */
50	#define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1))	50	#define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1))
51		51
52	/** Byte mask consisting of highest @n bits (out of 8) */	52	/** Byte mask consisting of highest @n bits (out of 8) */
53	#define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))	53	#define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
54		54
55	/** Number of data bits in a UTF-8 continuation byte */	55	/** Number of data bits in a UTF-8 continuation byte */
56	#define CONT_BITS 6	56	#define CONT_BITS 6
57		57
58	/** Decode a single character from a string.	58	/** Decode a single character from a string.
59	*	59	*
60	* Decode a single character from a string of size @a size. Decoding starts	60	* Decode a single character from a string of size @a size. Decoding starts
61	* at @a offset and this offset is moved to the beginning of the next	61	* at @a offset and this offset is moved to the beginning of the next
62	* character. In case of decoding error, offset generally advances at least	62	* character. In case of decoding error, offset generally advances at least
63	* by one. However, offset is never moved beyond size.	63	* by one. However, offset is never moved beyond size.
64	*	64	*
65	* @param str String (not necessarily NULL-terminated).	65	* @param str String (not necessarily NULL-terminated).
66	* @param offset Byte offset in string where to start decoding.	66	* @param offset Byte offset in string where to start decoding.
67	* @param size Size of the string (in bytes).	67	* @param size Size of the string (in bytes).
68	*	68	*
69	* @return Value of decoded character, U_SPECIAL on decoding error or	69	* @return Value of decoded character, U_SPECIAL on decoding error or
70	* NULL if attempt to decode beyond @a size.	70	* NULL if attempt to decode beyond @a size.
71	*	71	*
72	*/	72	*/
73	wchar_t str_decode(const char str, size_t offset, size_t size)	73	wchar_t str_decode(const char str, size_t offset, size_t size)
74	{	74	{
75	if (*offset + 1 > size)	75	if (*offset + 1 > size)
76	return 0;	76	return 0;
77		77
78	/* First byte read from string */	78	/* First byte read from string */
79	uint8_t b0 = (uint8_t) str[(*offset)++];	79	uint8_t b0 = (uint8_t) str[(*offset)++];
80		80
81	/* Determine code length */	81	/* Determine code length */
82		82
83	unsigned int b0_bits; /* Data bits in first byte */	83	unsigned int b0_bits; /* Data bits in first byte */
84	unsigned int cbytes; /* Number of continuation bytes */	84	unsigned int cbytes; /* Number of continuation bytes */
85		85
86	if ((b0 & 0x80) == 0) {	86	if ((b0 & 0x80) == 0) {
87	/* 0xxxxxxx (Plain ASCII) */	87	/* 0xxxxxxx (Plain ASCII) */
88	b0_bits = 7;	88	b0_bits = 7;
89	cbytes = 0;	89	cbytes = 0;
90	} else if ((b0 & 0xe0) == 0xc0) {	90	} else if ((b0 & 0xe0) == 0xc0) {
91	/* 110xxxxx 10xxxxxx */	91	/* 110xxxxx 10xxxxxx */
92	b0_bits = 5;	92	b0_bits = 5;
93	cbytes = 1;	93	cbytes = 1;
94	} else if ((b0 & 0xf0) == 0xe0) {	94	} else if ((b0 & 0xf0) == 0xe0) {
95	/* 1110xxxx 10xxxxxx 10xxxxxx */	95	/* 1110xxxx 10xxxxxx 10xxxxxx */
96	b0_bits = 4;	96	b0_bits = 4;
97	cbytes = 2;	97	cbytes = 2;
98	} else if ((b0 & 0xf8) == 0xf0) {	98	} else if ((b0 & 0xf8) == 0xf0) {
99	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */	99	/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
100	b0_bits = 3;	100	b0_bits = 3;
101	cbytes = 3;	101	cbytes = 3;
102	} else {	102	} else {
103	/* 10xxxxxx -- unexpected continuation byte */	103	/* 10xxxxxx -- unexpected continuation byte */
104	return U_SPECIAL;	104	return U_SPECIAL;
105	}	105	}
106		106
107	if (*offset + cbytes > size)	107	if (*offset + cbytes > size)
108	return U_SPECIAL;	108	return U_SPECIAL;
109		109
110	wchar_t ch = b0 & LO_MASK_8(b0_bits);	110	wchar_t ch = b0 & LO_MASK_8(b0_bits);
111		111
112	/* Decode continuation bytes */	112	/* Decode continuation bytes */
113	while (cbytes > 0) {	113	while (cbytes > 0) {
114	uint8_t b = (uint8_t) str[(*offset)++];	114	uint8_t b = (uint8_t) str[(*offset)++];
115		115
116	/* Must be 10xxxxxx */	116	/* Must be 10xxxxxx */
117	if ((b & 0xc0) != 0x80)	117	if ((b & 0xc0) != 0x80)
118	return U_SPECIAL;	118	return U_SPECIAL;
119		119
120	/* Shift data bits to ch */	120	/* Shift data bits to ch */
121	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));	121	ch = (ch << CONT_BITS) \| (wchar_t) (b & LO_MASK_8(CONT_BITS));
122	cbytes--;	122	cbytes--;
123	}	123	}
124		124
125	return ch;	125	return ch;
126	}	126	}
127		127
128	/** Encode a single character to string representation.	128	/** Encode a single character to string representation.
129	*	129	*
130	* Encode a single character to string representation (i.e. UTF-8) and store	130	* Encode a single character to string representation (i.e. UTF-8) and store
131	* it into a buffer at @a offset. Encoding starts at @a offset and this offset	131	* it into a buffer at @a offset. Encoding starts at @a offset and this offset
132	* is moved to the position where the next character can be written to.	132	* is moved to the position where the next character can be written to.
133	*	133	*
134	* @param ch Input character.	134	* @param ch Input character.
135	* @param str Output buffer.	135	* @param str Output buffer.
136	* @param offset Byte offset where to start writing.	136	* @param offset Byte offset where to start writing.
137	* @param size Size of the output buffer (in bytes).	137	* @param size Size of the output buffer (in bytes).
138	*	138	*
139	* @return EOK if the character was encoded successfully, EOVERFLOW if there	139	* @return EOK if the character was encoded successfully, EOVERFLOW if there
140	* was not enough space in the output buffer or EINVAL if the character	140	* was not enough space in the output buffer or EINVAL if the character
141	* code was invalid.	141	* code was invalid.
142	*/	142	*/
143	int chr_encode(const wchar_t ch, char str, size_t offset, size_t size)	143	int chr_encode(const wchar_t ch, char str, size_t offset, size_t size)
144	{	144	{
145	if (*offset >= size)	145	if (*offset >= size)
146	return EOVERFLOW;	146	return EOVERFLOW;
147		147
148	if (!chr_check(ch))	148	if (!chr_check(ch))
149	return EINVAL;	149	return EINVAL;
150		150
151	/* Unsigned version of ch (bit operations should only be done	151	/* Unsigned version of ch (bit operations should only be done
152	on unsigned types). */	152	on unsigned types). */
153	uint32_t cc = (uint32_t) ch;	153	uint32_t cc = (uint32_t) ch;
154		154
155	/* Determine how many continuation bytes are needed */	155	/* Determine how many continuation bytes are needed */
156		156
157	unsigned int b0_bits; /* Data bits in first byte */	157	unsigned int b0_bits; /* Data bits in first byte */
158	unsigned int cbytes; /* Number of continuation bytes */	158	unsigned int cbytes; /* Number of continuation bytes */
159		159
160	if ((cc & ~LO_MASK_32(7)) == 0) {	160	if ((cc & ~LO_MASK_32(7)) == 0) {
161	b0_bits = 7;	161	b0_bits = 7;
162	cbytes = 0;	162	cbytes = 0;
163	} else if ((cc & ~LO_MASK_32(11)) == 0) {	163	} else if ((cc & ~LO_MASK_32(11)) == 0) {
164	b0_bits = 5;	164	b0_bits = 5;
165	cbytes = 1;	165	cbytes = 1;
166	} else if ((cc & ~LO_MASK_32(16)) == 0) {	166	} else if ((cc & ~LO_MASK_32(16)) == 0) {
167	b0_bits = 4;	167	b0_bits = 4;
168	cbytes = 2;	168	cbytes = 2;
169	} else if ((cc & ~LO_MASK_32(21)) == 0) {	169	} else if ((cc & ~LO_MASK_32(21)) == 0) {
170	b0_bits = 3;	170	b0_bits = 3;
171	cbytes = 3;	171	cbytes = 3;
172	} else {	172	} else {
173	/* Codes longer than 21 bits are not supported */	173	/* Codes longer than 21 bits are not supported */
174	return EINVAL;	174	return EINVAL;
175	}	175	}
176		176
177	/* Check for available space in buffer */	177	/* Check for available space in buffer */
178	if (*offset + cbytes >= size)	178	if (*offset + cbytes >= size)
179	return EOVERFLOW;	179	return EOVERFLOW;
180		180
181	/* Encode continuation bytes */	181	/* Encode continuation bytes */
182	unsigned int i;	182	unsigned int i;
183	for (i = cbytes; i > 0; i--) {	183	for (i = cbytes; i > 0; i--) {
184	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));	184	str[*offset + i] = 0x80 \| (cc & LO_MASK_32(CONT_BITS));
185	cc = cc >> CONT_BITS;	185	cc = cc >> CONT_BITS;
186	}	186	}
187		187
188	/* Encode first byte */	188	/* Encode first byte */
189	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);	189	str[*offset] = (cc & LO_MASK_32(b0_bits)) \| HI_MASK_8(8 - b0_bits - 1);
190		190
191	/* Advance offset */	191	/* Advance offset */
192	*offset += cbytes + 1;	192	*offset += cbytes + 1;
193		193
194	return EOK;	194	return EOK;
195	}	195	}
196		196
197	/** Get size of string.	197	/** Get size of string.
198	*	198	*
199	* Get the number of bytes which are used by the string @a str (excluding the	199	* Get the number of bytes which are used by the string @a str (excluding the
200	* NULL-terminator).	200	* NULL-terminator).
201	*	201	*
202	* @param str String to consider.	202	* @param str String to consider.
203	*	203	*
204	* @return Number of bytes used by the string	204	* @return Number of bytes used by the string
205	*	205	*
206	*/	206	*/
207	size_t str_size(const char *str)	207	size_t str_size(const char *str)
208	{	208	{
209	size_t size = 0;	209	size_t size = 0;
210		210
211	while (*str++ != 0)	211	while (*str++ != 0)
212	size++;	212	size++;
213		213
214	return size;	214	return size;
215	}	215	}
216		216
217	/** Get size of wide string.	217	/** Get size of wide string.
218	*	218	*
219	* Get the number of bytes which are used by the wide string @a str (excluding the	219	* Get the number of bytes which are used by the wide string @a str (excluding the
220	* NULL-terminator).	220	* NULL-terminator).
221	*	221	*
222	* @param str Wide string to consider.	222	* @param str Wide string to consider.
223	*	223	*
224	* @return Number of bytes used by the wide string	224	* @return Number of bytes used by the wide string
225	*	225	*
226	*/	226	*/
227	size_t wstr_size(const wchar_t *str)	227	size_t wstr_size(const wchar_t *str)
228	{	228	{
229	return (wstr_length(str) * sizeof(wchar_t));	229	return (wstr_length(str) * sizeof(wchar_t));
230	}	230	}
231		231
232	/** Get size of string with length limit.	232	/** Get size of string with length limit.
233	*	233	*
234	* Get the number of bytes which are used by up to @a max_len first	234	* Get the number of bytes which are used by up to @a max_len first
235	* characters in the string @a str. If @a max_len is greater than	235	* characters in the string @a str. If @a max_len is greater than
236	* the length of @a str, the entire string is measured (excluding the	236	* the length of @a str, the entire string is measured (excluding the
237	* NULL-terminator).	237	* NULL-terminator).
238	*	238	*
239	* @param str String to consider.	239	* @param str String to consider.
240	* @param max_len Maximum number of characters to measure.	240	* @param max_len Maximum number of characters to measure.
241	*	241	*
242	* @return Number of bytes used by the characters.	242	* @return Number of bytes used by the characters.
243	*	243	*
244	*/	244	*/
245	size_t str_lsize(const char *str, count_t max_len)	245	size_t str_lsize(const char *str, count_t max_len)
246	{	246	{
247	count_t len = 0;	247	count_t len = 0;
248	size_t offset = 0;	248	size_t offset = 0;
249		249
250	while (len < max_len) {	250	while (len < max_len) {
251	if (str_decode(str, &offset, STR_NO_LIMIT) == 0)	251	if (str_decode(str, &offset, STR_NO_LIMIT) == 0)
252	break;	252	break;
253		253
254	len++;	254	len++;
255	}	255	}
256		256
257	return offset;	257	return offset;
258	}	258	}
259		259
260	/** Get size of wide string with length limit.	260	/** Get size of wide string with length limit.
261	*	261	*
262	* Get the number of bytes which are used by up to @a max_len first	262	* Get the number of bytes which are used by up to @a max_len first
263	* wide characters in the wide string @a str. If @a max_len is greater than	263	* wide characters in the wide string @a str. If @a max_len is greater than
264	* the length of @a str, the entire wide string is measured (excluding the	264	* the length of @a str, the entire wide string is measured (excluding the
265	* NULL-terminator).	265	* NULL-terminator).
266	*	266	*
267	* @param str Wide string to consider.	267	* @param str Wide string to consider.
268	* @param max_len Maximum number of wide characters to measure.	268	* @param max_len Maximum number of wide characters to measure.
269	*	269	*
270	* @return Number of bytes used by the wide characters.	270	* @return Number of bytes used by the wide characters.
271	*	271	*
272	*/	272	*/
273	size_t wstr_lsize(const wchar_t *str, count_t max_len)	273	size_t wstr_lsize(const wchar_t *str, count_t max_len)
274	{	274	{
275	return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t));	275	return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t));
276	}	276	}
277		277
278	/** Get number of characters in a string.	278	/** Get number of characters in a string.
279	*	279	*
280	* @param str NULL-terminated string.	280	* @param str NULL-terminated string.
281	*	281	*
282	* @return Number of characters in string.	282	* @return Number of characters in string.
283	*	283	*
284	*/	284	*/
285	count_t str_length(const char *str)	285	count_t str_length(const char *str)
286	{	286	{
287	count_t len = 0;	287	count_t len = 0;
288	size_t offset = 0;	288	size_t offset = 0;
289		289
290	while (str_decode(str, &offset, STR_NO_LIMIT) != 0)	290	while (str_decode(str, &offset, STR_NO_LIMIT) != 0)
291	len++;	291	len++;
292		292
293	return len;	293	return len;
294	}	294	}
295		295
296	/** Get number of characters in a wide string.	296	/** Get number of characters in a wide string.
297	*	297	*
298	* @param str NULL-terminated wide string.	298	* @param str NULL-terminated wide string.
299	*	299	*
300	* @return Number of characters in @a str.	300	* @return Number of characters in @a str.
301	*	301	*
302	*/	302	*/
303	count_t wstr_length(const wchar_t *wstr)	303	count_t wstr_length(const wchar_t *wstr)
304	{	304	{
305	count_t len = 0;	305	count_t len = 0;
306		306
307	while (*wstr++ != 0)	307	while (*wstr++ != 0)
308	len++;	308	len++;
309		309
310	return len;	310	return len;
311	}	311	}
312		312
313	/** Get number of characters in a string with size limit.	313	/** Get number of characters in a string with size limit.
314	*	314	*
315	* @param str NULL-terminated string.	315	* @param str NULL-terminated string.
316	* @param size Maximum number of bytes to consider.	316	* @param size Maximum number of bytes to consider.
317	*	317	*
318	* @return Number of characters in string.	318	* @return Number of characters in string.
319	*	319	*
320	*/	320	*/
321	count_t str_nlength(const char *str, size_t size)	321	count_t str_nlength(const char *str, size_t size)
322	{	322	{
323	count_t len = 0;	323	count_t len = 0;
324	size_t offset = 0;	324	size_t offset = 0;
325		325
326	while (str_decode(str, &offset, size) != 0)	326	while (str_decode(str, &offset, size) != 0)
327	len++;	327	len++;
328		328
329	return len;	329	return len;
330	}	330	}
331		331
332	/** Get number of characters in a string with size limit.	332	/** Get number of characters in a string with size limit.
333	*	333	*
334	* @param str NULL-terminated string.	334	* @param str NULL-terminated string.
335	* @param size Maximum number of bytes to consider.	335	* @param size Maximum number of bytes to consider.
336	*	336	*
337	* @return Number of characters in string.	337	* @return Number of characters in string.
338	*	338	*
339	*/	339	*/
340	count_t wstr_nlength(const wchar_t *str, size_t size)	340	count_t wstr_nlength(const wchar_t *str, size_t size)
341	{	341	{
342	count_t len = 0;	342	count_t len = 0;
343	count_t limit = ALIGN_DOWN(size, sizeof(wchar_t));	343	count_t limit = ALIGN_DOWN(size, sizeof(wchar_t));
344	count_t offset = 0;	344	count_t offset = 0;
345		345
346	while ((offset < limit) && (*str++ != 0)) {	346	while ((offset < limit) && (*str++ != 0)) {
347	len++;	347	len++;
348	offset += sizeof(wchar_t);	348	offset += sizeof(wchar_t);
349	}	349	}
350		350
351	return len;	351	return len;
352	}	352	}
353		353
354	/** Check whether character is plain ASCII.	354	/** Check whether character is plain ASCII.
355	*	355	*
356	* @return True if character is plain ASCII.	356	* @return True if character is plain ASCII.
357	*	357	*
358	*/	358	*/
359	bool ascii_check(wchar_t ch)	359	bool ascii_check(wchar_t ch)
360	{	360	{
361	if ((ch >= 0) && (ch <= 127))	361	if ((ch >= 0) && (ch <= 127))
362	return true;	362	return true;
363		363
364	return false;	364	return false;
365	}	365	}
366		366
367	/** Check whether character is valid	367	/** Check whether character is valid
368	*	368	*
369	* @return True if character is a valid Unicode code point.	369	* @return True if character is a valid Unicode code point.
370	*	370	*
371	*/	371	*/
372	bool chr_check(wchar_t ch)	372	bool chr_check(wchar_t ch)
373	{	373	{
374	if ((ch >= 0) && (ch <= 1114111))	374	if ((ch >= 0) && (ch <= 1114111))
375	return true;	375	return true;
376		376
377	return false;	377	return false;
378	}	378	}
379		379
380	/** Compare two NULL terminated strings.	380	/** Compare two NULL terminated strings.
381	*	381	*
382	* Do a char-by-char comparison of two NULL-terminated strings.	382	* Do a char-by-char comparison of two NULL-terminated strings.
383	* The strings are considered equal iff they consist of the same	383	* The strings are considered equal iff they consist of the same
384	* characters on the minimum of their lengths.	384	* characters on the minimum of their lengths.
385	*	385	*
386	* @param s1 First string to compare.	386	* @param s1 First string to compare.
387	* @param s2 Second string to compare.	387	* @param s2 Second string to compare.
388	*	388	*
389	* @return 0 if the strings are equal, -1 if first is smaller,	389	* @return 0 if the strings are equal, -1 if first is smaller,
390	* 1 if second smaller.	390	* 1 if second smaller.
391	*	391	*
392	*/	392	*/
393	int str_cmp(const char s1, const char s2)	393	int str_cmp(const char s1, const char s2)
394	{	394	{
395	wchar_t c1 = 0;	395	wchar_t c1 = 0;
396	wchar_t c2 = 0;	396	wchar_t c2 = 0;
397		397
398	size_t off1 = 0;	398	size_t off1 = 0;
399	size_t off2 = 0;	399	size_t off2 = 0;
400		400
401	while (true) {	401	while (true) {
402	c1 = str_decode(s1, &off1, STR_NO_LIMIT);	402	c1 = str_decode(s1, &off1, STR_NO_LIMIT);
403	c2 = str_decode(s2, &off2, STR_NO_LIMIT);	403	c2 = str_decode(s2, &off2, STR_NO_LIMIT);
404		404
405	if (c1 < c2)	405	if (c1 < c2)
406	return -1;	406	return -1;
407		407
408	if (c1 > c2)	408	if (c1 > c2)
409	return 1;	409	return 1;
410		410
411	if (c1 == 0 \|\| c2 == 0)	411	if (c1 == 0 \|\| c2 == 0)
412	break;	412	break;
413	}	413	}
414		414
415	return 0;	415	return 0;
416	}	416	}
417		417
418	/** Compare two NULL terminated strings with length limit.	418	/** Compare two NULL terminated strings with length limit.
419	*	419	*
420	* Do a char-by-char comparison of two NULL-terminated strings.	420	* Do a char-by-char comparison of two NULL-terminated strings.
421	* The strings are considered equal iff they consist of the same	421	* The strings are considered equal iff they consist of the same
422	* characters on the minimum of their lengths and the length limit.	422	* characters on the minimum of their lengths and the length limit.
423	*	423	*
424	* @param s1 First string to compare.	424	* @param s1 First string to compare.
425	* @param s2 Second string to compare.	425	* @param s2 Second string to compare.
426	* @param max_len Maximum number of characters to consider.	426	* @param max_len Maximum number of characters to consider.
427	*	427	*
428	* @return 0 if the strings are equal, -1 if first is smaller,	428	* @return 0 if the strings are equal, -1 if first is smaller,
429	* 1 if second smaller.	429	* 1 if second smaller.
430	*	430	*
431	*/	431	*/
432	int str_lcmp(const char s1, const char s2, count_t max_len)	432	int str_lcmp(const char s1, const char s2, count_t max_len)
433	{	433	{
434	wchar_t c1 = 0;	434	wchar_t c1 = 0;
435	wchar_t c2 = 0;	435	wchar_t c2 = 0;
436		436
437	size_t off1 = 0;	437	size_t off1 = 0;
438	size_t off2 = 0;	438	size_t off2 = 0;
439		439
440	count_t len = 0;	440	count_t len = 0;
441		441
442	while (true) {	442	while (true) {
443	if (len >= max_len)	443	if (len >= max_len)
444	break;	444	break;
445		445
446	c1 = str_decode(s1, &off1, STR_NO_LIMIT);	446	c1 = str_decode(s1, &off1, STR_NO_LIMIT);
447	c2 = str_decode(s2, &off2, STR_NO_LIMIT);	447	c2 = str_decode(s2, &off2, STR_NO_LIMIT);
448		448
449	if (c1 < c2)	449	if (c1 < c2)
450	return -1;	450	return -1;
451		451
452	if (c1 > c2)	452	if (c1 > c2)
453	return 1;	453	return 1;
454		454
455	if (c1 == 0 \|\| c2 == 0)	455	if (c1 == 0 \|\| c2 == 0)
456	break;	456	break;
457		457
458	++len;	458	++len;
459	}	459	}
460		460
461	return 0;	461	return 0;
462		462
463	}	463	}
464		464
465	/** Copy string.	465	/** Copy string.
466	*	466	*
467	* Copy source string @a src to destination buffer @a dest.	467	* Copy source string @a src to destination buffer @a dest.
468	* No more than @a size bytes are written. If the size of the output buffer	468	* No more than @a size bytes are written. If the size of the output buffer
469	* is at least one byte, the output string will always be well-formed, i.e.	469	* is at least one byte, the output string will always be well-formed, i.e.
470	* null-terminated and containing only complete characters.	470	* null-terminated and containing only complete characters.
471	*	471	*
472	* @param dst Destination buffer.	472	* @param dst Destination buffer.
473	* @param count Size of the destination buffer.	473	* @param count Size of the destination buffer.
474	* @param src Source string.	474	* @param src Source string.
475	*/	475	*/
476	void str_cpy(char dest, size_t size, const char src)	476	void str_cpy(char dest, size_t size, const char src)
477	{	477	{
478	wchar_t ch;	478	wchar_t ch;
479	size_t src_off;	479	size_t src_off;
480	size_t dest_off;	480	size_t dest_off;
481		481
482	/* No space for the NULL-terminator in the buffer. */	482	/* No space for the NULL-terminator in the buffer. */
483	if (size == 0)	483	if (size == 0)
484	return;	484	return;
485		485
486	src_off = 0;	486	src_off = 0;
487	dest_off = 0;	487	dest_off = 0;
488		488
489	while ((ch = str_decode(src, &src_off, STR_NO_LIMIT)) != 0) {	489	while ((ch = str_decode(src, &src_off, STR_NO_LIMIT)) != 0) {
490	if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)	490	if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
491	break;	491	break;
492	}	492	}
493		493
494	dest[dest_off] = '\0';	494	dest[dest_off] = '\0';
495	}	495	}
496		496
497	/** Copy size-limited substring.	497	/** Copy size-limited substring.
498	*	498	*
499	* Copy source string @a src to destination buffer @a dest.	499	* Copy source string @a src to destination buffer @a dest.
500	* No more than @a size bytes are written. If the size of the output buffer	500	* No more than @a size bytes are written. If the size of the output buffer

Subversion Repositories HelenOS

(root)/trunk/uspace/lib/libc/generic/string.c @ 3463 – Rev 4279 → 4280