htstring.c

elinks下lynx是最重要的二个文本浏览器, 在linux下非常实用, lynx比elinks早的多, 目前好像停止开发, 这是lynx源代码

/*		Case-independent string comparison		HTString.c
**
**	Original version came with listserv implementation.
**	Version TBL Oct 91 replaces one which modified the strings.
**	02-Dec-91 (JFG) Added stralloccopy and stralloccat
**	23 Jan 92 (TBL) Changed strallocc* to 8 char HTSAC* for VM and suchlike
**	 6 Oct 92 (TBL) Moved WWW_TraceFlag in here to be in library
**	15 Nov 98 (TD)  Added HTSprintf.
*/

#include <HTUtils.h>

#include <LYLeaks.h>
#include <LYStrings.h>

#ifndef NO_LYNX_TRACE
PUBLIC BOOLEAN WWW_TraceFlag = 0;	/* Global trace flag for ALL W3 code */
PUBLIC int WWW_TraceMask = 0;		/* Global trace flag for ALL W3 code */
#endif

#ifndef VC
#define VC "unknown"
#endif /* !VC */

#ifdef _WINDOWS
CONST char * HTLibraryVersion = "2.14FM"; /* String for help screen etc */
#else
PUBLIC CONST char * HTLibraryVersion = VC; /* String for help screen etc */
#endif

/*
**     strcasecomp8 is a variant of strcasecomp (below)
**     ------------		    -----------
**     but uses 8bit upper/lower case information
**     from the current display charset.
**     It returns 0 if exact match.
*/
PUBLIC int strcasecomp8 ARGS2(
       CONST char*,    a,
       CONST char *,   b)
{
    CONST char *p = a;
    CONST char *q = b;

    for ( ; *p && *q; p++, q++) {
	int diff = UPPER8(*p, *q);
	if (diff) return diff;
    }
    if (*p)
	return 1;	/* p was longer than q */
    if (*q)
	return -1;	/* p was shorter than q */
    return 0;		/* Exact match */
}

/*
**     strncasecomp8 is a variant of strncasecomp (below)
**     -------------		     ------------
**     but uses 8bit upper/lower case information
**     from the current display charset.
**     It returns 0 if exact match.
*/
PUBLIC int strncasecomp8 ARGS3(
	CONST char*,	a,
	CONST char *,	b,
	int,		n)
{
    CONST char *p = a;
    CONST char *q = b;

    for ( ; ; p++, q++) {
	int diff;
	if (p == (a+n))
	    return 0;	/*   Match up to n characters */
	if (!(*p && *q))
	    return (*p - *q);
	diff = UPPER8(*p, *q);
	if (diff)
	    return diff;
    }
    /*NOTREACHED*/
}

#ifndef VM		/* VM has these already it seems */

#ifdef SH_EX	/* 1997/12/23 (Tue) 16:40:31 */

/*
 * This array is designed for mapping upper and lower case letter
 * together for a case independent comparison.  The mappings are
 * based upon ascii character sequences.
 */
static unsigned char charmap[] = {
	'\000', '\001', '\002', '\003', '\004', '\005', '\006', '\007',
	'\010', '\011', '\012', '\013', '\014', '\015', '\016', '\017',
	'\020', '\021', '\022', '\023', '\024', '\025', '\026', '\027',
	'\030', '\031', '\032', '\033', '\034', '\035', '\036', '\037',
	'\040', '\041', '\042', '\043', '\044', '\045', '\046', '\047',
	'\050', '\051', '\052', '\053', '\054', '\055', '\056', '\057',
	'\060', '\061', '\062', '\063', '\064', '\065', '\066', '\067',
	'\070', '\071', '\072', '\073', '\074', '\075', '\076', '\077',
	'\100', '\141', '\142', '\143', '\144', '\145', '\146', '\147',
	'\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157',
	'\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167',
	'\170', '\171', '\172', '\133', '\134', '\135', '\136', '\137',
	'\140', '\141', '\142', '\143', '\144', '\145', '\146', '\147',
	'\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157',
	'\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167',
	'\170', '\171', '\172', '\173', '\174', '\175', '\176', '\177',
	'\200', '\201', '\202', '\203', '\204', '\205', '\206', '\207',
	'\210', '\211', '\212', '\213', '\214', '\215', '\216', '\217',
	'\220', '\221', '\222', '\223', '\224', '\225', '\226', '\227',
	'\230', '\231', '\232', '\233', '\234', '\235', '\236', '\237',
	'\240', '\241', '\242', '\243', '\244', '\245', '\246', '\247',
	'\250', '\251', '\252', '\253', '\254', '\255', '\256', '\257',
	'\260', '\261', '\262', '\263', '\264', '\265', '\266', '\267',
	'\270', '\271', '\272', '\273', '\274', '\275', '\276', '\277',
	'\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
	'\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
	'\360', '\361', '\362', '\363', '\364', '\365', '\366', '\327',
	'\370', '\371', '\372', '\373', '\374', '\375', '\376', '\337',
	'\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
	'\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
	'\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367',
	'\370', '\371', '\372', '\373', '\374', '\375', '\376', '\377',
};

PUBLIC int strcasecomp ARGS2(
	CONST char*,	s1,
	CONST char*,	s2)
{
    register unsigned char *cm = charmap;
    register unsigned char *us1 = (unsigned char *)s1;
    register unsigned char *us2 = (unsigned char *)s2;

    while (cm[*us1] == cm[*us2++])
	if (*us1++ == '\0')
	    return(0);
    return (cm[*us1] - cm[*--us2]);
}

PUBLIC int strncasecomp ARGS3(
	CONST char*,	a,
	CONST char*,	b,
	int,		n)
{
    register unsigned char *cm = charmap;
    register unsigned char *us1 = (unsigned char *)a;
    register unsigned char *us2 = (unsigned char *)b;

    while ((long)(--n) >= 0 && cm[*us1] == cm[*us2++])
	if (*us1++ == '\0')
	    return(0);
    return ((long)n < 0 ? 0 : cm[*us1] - cm[*--us2]);
}

#else	/* SH_EX */

/*	Strings of any length
**	---------------------
*/
PUBLIC int strcasecomp ARGS2(
	CONST char*,	a,
	CONST char *,	b)
{
    CONST char *p = a;
    CONST char *q = b;

    for ( ; *p && *q; p++, q++) {
	int diff = TOLOWER(*p) - TOLOWER(*q);
	if (diff) return diff;
    }
    if (*p)
	return 1;	/* p was longer than q */
    if (*q)
	return -1;	/* p was shorter than q */
    return 0;		/* Exact match */
}


/*	With count limit
**	----------------
*/
PUBLIC int strncasecomp ARGS3(
	CONST char*,	a,
	CONST char *,	b,
	int,		n)
{
    CONST char *p = a;
    CONST char *q = b;

    for ( ; ; p++, q++) {
	int diff;
	if (p == (a+n))
	    return 0;	/*   Match up to n characters */
	if (!(*p && *q))
	    return (*p - *q);
	diff = TOLOWER(*p) - TOLOWER(*q);
	if (diff)
	    return diff;
    }
    /*NOTREACHED*/
}

#endif	/* SH_EX */
#endif /* VM */

#ifdef NOT_ASCII

/*	Case-insensitive with ASCII collating sequence
**	----------------
*/
PUBLIC int AS_casecomp ARGS2(
	CONST char*,	p,
	CONST char*,	q)
{
    int diff;

    for ( ; ; p++, q++) {
	if (!(*p && *q))
	    return (UCH(*p)  - UCH(*q));
	diff = TOASCII(TOLOWER(*p))
	     - TOASCII(TOLOWER(*q));
	if (diff)
	    return diff;
    }
    /*NOTREACHED*/
}


/*	With count limit and ASCII collating sequence
**	----------------
**	AS_cmp uses n == -1 to compare indefinite length.
*/
PUBLIC int AS_ncmp ARGS3(
	CONST char *,	p,
	CONST char *,	q,
	unsigned int,	n)
{
    CONST char *a = p;
    int diff;

    for ( ; (p-a) < n; p++, q++) {
	if (!(*p && *q))
	    return (UCH(*p) - UCH(*q));
	diff = TOASCII(*p)
	     - TOASCII(*q);
	if (diff)
	    return diff;
    }
    return 0;	/*   Match up to n characters */
}


/*	With ASCII collating sequence
**	----------------
*/
PUBLIC int AS_cmp ARGS2(
	CONST char *,	p,
	CONST char *,	q)
{
    return( AS_ncmp( p, q, -1 ) );
}
#endif /* NOT_ASCII */


/*	Allocate a new copy of a string, and returns it
*/
PUBLIC char * HTSACopy ARGS2(
	char **,	dest,
	CONST char *,	src)
{
    if (src != 0) {
	if (src != *dest) {
	    size_t size = strlen(src) + 1;
	    FREE(*dest);
	    *dest = (char *) malloc(size);
	    if (*dest == NULL)
		outofmem(__FILE__, "HTSACopy");
	    memcpy(*dest, src, size);
	}
    } else {
	FREE(*dest);
    }
    return *dest;
}

/*	String Allocate and Concatenate
*/
PUBLIC char * HTSACat ARGS2(
	char **,	dest,
	CONST char *,	src)
{
    if (src && *src && (src != *dest)) {
	if (*dest) {
	    size_t length = strlen(*dest);
	    *dest = (char *)realloc(*dest, length + strlen(src) + 1);
	    if (*dest == NULL)
		outofmem(__FILE__, "HTSACat");
	    strcpy (*dest + length, src);
	} else {
	    *dest = (char *)malloc(strlen(src) + 1);
	    if (*dest == NULL)
		outofmem(__FILE__, "HTSACat");
	    strcpy (*dest, src);
	}
    }
    return *dest;
}


/* optimized for heavily realloc'd strings, store length inside */

#define EXTRA_TYPE size_t		/* type we use for length */
#define EXTRA_SIZE sizeof(void *)	/* alignment >= sizeof(EXTRA_TYPE) */

PUBLIC void   HTSAFree_extra ARGS1(
	char *,		s)
{
    free(s - EXTRA_SIZE);
}

/* never shrink */
PUBLIC char * HTSACopy_extra ARGS2(
	char **,	dest,
	CONST char *,	src)
{
    if (src != 0) {
	size_t srcsize = strlen(src) + 1;
	EXTRA_TYPE size = 0;

	if (*dest != 0) {
	    size = *(EXTRA_TYPE *)((*dest) - EXTRA_SIZE);
	}
	if (size < srcsize) {
	    FREE_extra(*dest);
	    size = srcsize * 2;   /* x2 step */
	    *dest = (char *) malloc(size + EXTRA_SIZE);
	    if (*dest == NULL)
		outofmem(__FILE__, "HTSACopy_extra");
	    *(EXTRA_TYPE *)(*dest) = size;
	    *dest += EXTRA_SIZE;
	}
	memcpy(*dest, src, srcsize);
    } else {
	Clear_extra(*dest);
    }
    return *dest;
}

/*	Find next Field
**	---------------
**
** On entry,
**	*pstr	points to a string containig white space separated
**		field, optionlly quoted.
**
** On exit,
**	*pstr	has been moved to the first delimiter past the
**		field
**		THE STRING HAS BEEN MUTILATED by a 0 terminator
**
**	returns a pointer to the first field
*/
PUBLIC char * HTNextField ARGS1(
	char **,	pstr)
{
    char * p = *pstr;
    char * start;			/* start of field */

    while (*p && WHITE(*p))
	p++;				/* Strip white space */
    if (!*p) {
	*pstr = p;
	return NULL;		/* No first field */
    }
    if (*p == '"') {			/* quoted field */
	p++;
	start = p;
	for (; *p && *p!='"'; p++) {
	    if (*p == '\\' && p[1])
		p++;			/* Skip escaped chars */
	}
    } else {
	start = p;
	while (*p && !WHITE(*p))
	    p++;			/* Skip first field */
    }
    if (*p)
	*p++ = '\0';
    *pstr = p;
    return start;
}

/*	Find next Token
**	---------------
**	Finds the next token in a string
**	On entry,
**	*pstr	points to a string to be parsed.
**	delims	lists characters to be recognized as delimiters.
**		If NULL, default is white space "," ";" or "=".
**		The word can optionally be quoted or enclosed with
**		chars from bracks.
**		Comments surrrounded by '(' ')' are filtered out
**		unless they are specifically reqested by including
**		' ' or '(' in delims or bracks.
**	bracks	lists bracketing chars.  Some are recognized as
**		special, for those give the opening char.
**		If NULL, defaults to <"> and "<" ">".
**	found	points to location to fill with the ending delimiter
**		found, or is NULL.
**
**	On exit,
**	*pstr	has been moved to the first delimiter past the
**		field
**		THE STRING HAS BEEN MUTILATED by a 0 terminator
**	found	points to the delimiter found unless it was NULL.
**	Returns a pointer to the first word or NULL on error
*/
PUBLIC char * HTNextTok ARGS4(
	char **,	pstr,
	CONST char *,	delims,
	CONST char *,	bracks,
	char *,		found)
{
    char * p = *pstr;
    char * start = NULL;
    BOOL get_blanks, skip_comments;
    BOOL get_comments;
    BOOL get_closing_char_too = FALSE;
    char closer;

    if (isEmpty(pstr)) return NULL;