htaautil.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

** ON ENTRY:
**	docname is the document pathname (from URL).
**
** ON EXIT:
**	returns a template matching docname, and other files
**		files in that directory.
**
**		E.g.  /foo/bar/x.html  =>  /foo/bar/ *
**						    ^
**				Space only to prevent it from
**				being a comment marker here,
**				there really isn't any space.
*/
PUBLIC char *HTAA_makeProtectionTemplate ARGS1(CONST char *, docname)
{
    char *template = NULL;
    char *slash = NULL;

    if (docname) {
	StrAllocCopy(template, docname);
	slash = strrchr(template, '/');
	if (slash)
	    slash++;
	else
	    slash = template;
	*slash = '\0';
	StrAllocCat(template, "*");
    }
    else
	StrAllocCopy(template, "*");

    CTRACE((tfp, "make_template: made template `%s' for file `%s'\n",
		template, docname));

    return template;
}


/*
** Skip leading whitespace from *s forward
*/
#define SKIPWS(s) while (*s==' ' || *s=='\t') s++;

/*
** Kill trailing whitespace starting from *(s-1) backwards
*/
#define KILLWS(s) {char *c=s-1; while (*c==' ' || *c=='\t') *(c--)='\0';}


/* PUBLIC						HTAA_parseArgList()
**		PARSE AN ARGUMENT LIST GIVEN IN A HEADER FIELD
** ON ENTRY:
**	str	is a comma-separated list:
**
**			item, item, item
**		where
**			item ::= value
**			       | name=value
**			       | name="value"
**
**		Leading and trailing whitespace is ignored
**		everywhere except inside quotes, so the following
**		examples are equal:
**
**			name=value,foo=bar
**			 name="value",foo="bar"
**			  name = value ,  foo = bar
**			   name = "value" ,  foo = "bar"
**
** ON EXIT:
**	returns a list of name-value pairs (actually HTAssocList*).
**		For items with no name, just value, the name is
**		the number of order number of that item. E.g.
**		"1" for the first, etc.
*/
PUBLIC HTAssocList *HTAA_parseArgList ARGS1(char *, str)
{
    HTAssocList *assoc_list = HTAssocList_new();
    char *cur = NULL;
    char *name = NULL;
    int n = 0;

    if (!str)
	return assoc_list;

    while (*str) {
	SKIPWS(str);				/* Skip leading whitespace */
	cur = str;
	n++;

	while (*cur  &&  *cur != '='  &&  *cur != ',')
	    cur++;	/* Find end of name (or lonely value without a name) */
	KILLWS(cur);	/* Kill trailing whitespace */

	if (*cur == '=') {			/* Name followed by a value */
	    *(cur++) = '\0';			/* Terminate name */
	    StrAllocCopy(name, str);
	    SKIPWS(cur);			/* Skip WS leading the value */
	    str = cur;
	    if (*str == '"') {			/* Quoted value */
		str++;
		cur = str;
		while (*cur  &&  *cur != '"')
		    cur++;
		if (*cur == '"')
		    *(cur++) = '\0';		/* Terminate value */
		/* else it is lacking terminating quote */
		SKIPWS(cur);			/* Skip WS leading comma */
		if (*cur == ',')
		    cur++;			/* Skip separating colon */
	    }
	    else {				/* Unquoted value */
		while (*cur  &&  *cur != ',')
		    cur++;
		KILLWS(cur);			/* Kill trailing whitespace */
		if (*cur == ',')
		    *(cur++) = '\0';
		/* else *cur already NULL */
	    }
	}
	else {	/* No name, just a value */
	    if (*cur == ',')
		*(cur++) = '\0';		/* Terminate value */
	    /* else last value on line (already terminated by NULL) */
	    HTSprintf0(&name, "%d", n);		/* Item order number for name */
	}
	HTAssocList_add(assoc_list, name, str);
	str = cur;
    } /* while *str */

    FREE(name);
    return assoc_list;
}


/************** HEADER LINE READER -- DOES UNFOLDING *************************/

#define BUFFER_SIZE	1024

PRIVATE size_t buffer_length;
PRIVATE char *buffer = 0;
PRIVATE char *start_pointer;
PRIVATE char *end_pointer;
PRIVATE int in_soc = -1;

#ifdef LY_FIND_LEAKS
PRIVATE void FreeHTAAUtil NOARGS
{
    FREE(buffer);
}
#endif /* LY_FIND_LEAKS */

/* PUBLIC						HTAA_setupReader()
**		SET UP HEADER LINE READER, i.e., give
**		the already-read-but-not-yet-processed
**		buffer of text to be read before more
**		is read from the socket.
** ON ENTRY:
**	start_of_headers is a pointer to a buffer containing
**			the beginning of the header lines
**			(rest will be read from a socket).
**	length		is the number of valid characters in
**			'start_of_headers' buffer.
**	soc		is the socket to use when start_of_headers
**			buffer is used up.
** ON EXIT:
**	returns		nothing.
**			Subsequent calls to HTAA_getUnfoldedLine()
**			will use this buffer first and then
**			proceed to read from socket.
*/
PUBLIC void HTAA_setupReader ARGS3(char *,	start_of_headers,
				   int,		length,
				   int,		soc)
{
    if (!start_of_headers)
	length = 0;	       /* initialize length (is this reached at all?) */
    if (buffer == NULL) {				       /* first call? */
	buffer_length = length;
	if (buffer_length < BUFFER_SIZE)     /* would fall below BUFFER_SIZE? */
	    buffer_length = BUFFER_SIZE;
	buffer = (char*)malloc((size_t)(sizeof(char)*(buffer_length + 1)));
    }
    else if (length > (int)buffer_length) {		  /* need more space? */
	buffer_length = length;
	buffer = (char*)realloc((char*)buffer,
				(size_t)(sizeof(char)*(buffer_length + 1)));
    }
    if (buffer == NULL) outofmem(__FILE__, "HTAA_setupReader");
#ifdef LY_FIND_LEAKS
    atexit(FreeHTAAUtil);
#endif
    start_pointer = buffer;
    if (start_of_headers) {
	strncpy(buffer, start_of_headers, length);
	buffer[length] = '\0';
	end_pointer = buffer + length;
    }
    else {
	*start_pointer = '\0';
	end_pointer = start_pointer;
    }
    in_soc = soc;
}


/* PUBLIC						HTAA_getUnfoldedLine()
**		READ AN UNFOLDED HEADER LINE FROM SOCKET
** ON ENTRY:
**	HTAA_setupReader must absolutely be called before
**	this function to set up internal buffer.
**
** ON EXIT:
**	returns a newly-allocated character string representing
**		the read line.	The line is unfolded, i.e.
**		lines that begin with whitespace are appended
**		to current line.  E.g.
**
**			Field-Name: Blaa-Blaa
**			 This-Is-A-Continuation-Line
**			 Here-Is_Another
**
**		is seen by the caller as:
**
**	Field-Name: Blaa-Blaa This-Is-A-Continuation-Line Here-Is_Another
**
*/
PUBLIC char *HTAA_getUnfoldedLine NOARGS
{
    char *line = NULL;
    char *cur;
    int count;
    BOOL peek_for_folding = NO;

    if (in_soc < 0) {
	CTRACE((tfp, "%s %s\n",
		    "HTAA_getUnfoldedLine: buffer not initialized",
		    "with function HTAA_setupReader()"));
	return NULL;
    }

    for(;;) {

	/* Reading from socket */

	if (start_pointer >= end_pointer) {/*Read the next block and continue*/
#ifdef USE_SSL
	    if (SSL_handle)
		count = SSL_read(SSL_handle, buffer, BUFFER_SIZE);
	    else
		count = NETREAD(in_soc, buffer, BUFFER_SIZE);
#else
	    count = NETREAD(in_soc, buffer, BUFFER_SIZE);
#endif /* USE_SSL */
	    if (count <= 0) {
		in_soc = -1;
		return line;
	    }
	    start_pointer = buffer;
	    end_pointer = buffer + count;
	    *end_pointer = '\0';
#ifdef NOT_ASCII
	    cur = start_pointer;
	    while (cur < end_pointer) {
		*cur = TOASCII(*cur);
		cur++;
	    }
#endif /*NOT_ASCII*/
	}
	cur = start_pointer;


	/* Unfolding */

	if (peek_for_folding) {
	    if (*cur != ' '  &&  *cur != '\t')
		return line;	/* Ok, no continuation line */
	    else		/* So this is a continuation line, continue */
		peek_for_folding = NO;
	}


	/* Finding end-of-line */

	while (cur < end_pointer && *cur != '\n') /* Find the end-of-line */
	    cur++;				  /* (or end-of-buffer).  */


	/* Terminating line */

	if (cur < end_pointer) {	/* So *cur==LF, terminate line */
	    *cur = '\0';		/* Overwrite LF */
	    if (*(cur-1) == '\r')
		*(cur-1) = '\0';	/* Overwrite CR */
	    peek_for_folding = YES;	/* Check for a continuation line */
	}


	/* Copying the result */

	if (line)
	    StrAllocCat(line, start_pointer);	/* Append */
	else
	    StrAllocCopy(line, start_pointer);	/* A new line */

	start_pointer = cur+1;	/* Skip the read line */

    } /* forever */
}