HTMLparser

HTMLparser —

Synopsis




typedef     htmlParserCtxt;
typedef     htmlParserCtxtPtr;
typedef     htmlParserNodeInfo;
typedef     htmlSAXHandler;
typedef     htmlSAXHandlerPtr;
typedef     htmlParserInput;
typedef     htmlParserInputPtr;
typedef     htmlDocPtr;
typedef     htmlNodePtr;
struct      htmlElemDesc;
typedef     htmlElemDescPtr;
struct      htmlEntityDesc;
typedef     htmlEntityDescPtr;
enum        htmlParserOption;

Description

Details

htmlParserCtxt

typedef xmlParserCtxt htmlParserCtxt;

htmlParserCtxtPtr

typedef xmlParserCtxtPtr htmlParserCtxtPtr;

htmlParserNodeInfo

typedef xmlParserNodeInfo htmlParserNodeInfo;

htmlSAXHandler

typedef xmlSAXHandler htmlSAXHandler;

htmlSAXHandlerPtr

typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;

htmlParserInput

typedef xmlParserInput htmlParserInput;

htmlParserInputPtr

typedef xmlParserInputPtr htmlParserInputPtr;

htmlDocPtr

typedef xmlDocPtr htmlDocPtr;

htmlNodePtr

typedef xmlNodePtr htmlNodePtr;

struct htmlElemDesc

struct htmlElemDesc {

    const char *name;	/* The tag name */
    char startTag;      /* Whether the start tag can be implied */
    char endTag;        /* Whether the end tag can be implied */
    char saveEndTag;    /* Whether the end tag should be saved */
    char empty;         /* Is this an empty element ? */
    char depr;          /* Is this a deprecated element ? */
    char dtd;           /* 1: only in Loose DTD, 2: only Frameset one */
    char isinline;      /* is this a block 0 or inline 1 element */
    const char *desc;   /* the description */

/* NRK Jan.2003
 * New fields encapsulating HTML structure
 *
 * Bugs:
 *	This is a very limited representation.  It fails to tell us when
 *	an element *requires* subelements (we only have whether they're
 *	allowed or not), and it doesn't tell us where CDATA and PCDATA
 *	are allowed.  Some element relationships are not fully represented:
 *	these are flagged with the word MODIFIER
 */
    const char** subelts;		/* allowed sub-elements of this element */
    const char* defaultsubelt;	/* subelement for suggested auto-repair
					   if necessary or NULL */
    const char** attrs_opt;		/* Optional Attributes */
    const char** attrs_depr;		/* Additional deprecated attributes */
    const char** attrs_req;		/* Required attributes */
};

htmlElemDescPtr

typedef htmlElemDesc *htmlElemDescPtr;

struct htmlEntityDesc

struct htmlEntityDesc {

    unsigned int value;	/* the UNICODE value for the character */
    const char *name;	/* The entity name */
    const char *desc;   /* the description */
};

htmlEntityDescPtr

typedef htmlEntityDesc *htmlEntityDescPtr;

enum htmlParserOption

typedef enum {
    HTML_PARSE_NOERROR	= 1<<5,	/* suppress error reports */
    HTML_PARSE_NOWARNING= 1<<6,	/* suppress warning reports */
    HTML_PARSE_PEDANTIC	= 1<<7,	/* pedantic error reporting */
    HTML_PARSE_NOBLANKS	= 1<<8,	/* remove blank nodes */
    HTML_PARSE_NONET	= 1<<11 /* Forbid network access */
} htmlParserOption;