htmlparser.c

SIP 1.5.0源代码

{ 8596,	"harr",	"left right arrow, U+2194 ISOamsa" },
{ 8629,	"crarr","downwards arrow with corner leftwards = carriage return, U+21B5 NEW" },
{ 8656,	"lArr",	"leftwards double arrow, U+21D0 ISOtech" },
{ 8657,	"uArr",	"upwards double arrow, U+21D1 ISOamsa" },
{ 8658,	"rArr",	"rightwards double arrow, U+21D2 ISOtech" },
{ 8659,	"dArr",	"downwards double arrow, U+21D3 ISOamsa" },
{ 8660,	"hArr",	"left right double arrow, U+21D4 ISOamsa" },


{ 8704,	"forall","for all, U+2200 ISOtech" },
{ 8706,	"part",	"partial differential, U+2202 ISOtech" },
{ 8707,	"exist","there exists, U+2203 ISOtech" },
{ 8709,	"empty","empty set = null set = diameter, U+2205 ISOamso" },
{ 8711,	"nabla","nabla = backward difference, U+2207 ISOtech" },
{ 8712,	"isin",	"element of, U+2208 ISOtech" },
{ 8713,	"notin","not an element of, U+2209 ISOtech" },
{ 8715,	"ni",	"contains as member, U+220B ISOtech" },
{ 8719,	"prod",	"n-ary product = product sign, U+220F ISOamsb" },
{ 8721,	"sum",	"n-ary sumation, U+2211 ISOamsb" },
{ 8722,	"minus","minus sign, U+2212 ISOtech" },
{ 8727,	"lowast","asterisk operator, U+2217 ISOtech" },
{ 8730,	"radic","square root = radical sign, U+221A ISOtech" },
{ 8733,	"prop",	"proportional to, U+221D ISOtech" },
{ 8734,	"infin","infinity, U+221E ISOtech" },
{ 8736,	"ang",	"angle, U+2220 ISOamso" },
{ 8743,	"and",	"logical and = wedge, U+2227 ISOtech" },
{ 8744,	"or",	"logical or = vee, U+2228 ISOtech" },
{ 8745,	"cap",	"intersection = cap, U+2229 ISOtech" },
{ 8746,	"cup",	"union = cup, U+222A ISOtech" },
{ 8747,	"int",	"integral, U+222B ISOtech" },
{ 8756,	"there4","therefore, U+2234 ISOtech" },
{ 8764,	"sim",	"tilde operator = varies with = similar to, U+223C ISOtech" },
{ 8773,	"cong",	"approximately equal to, U+2245 ISOtech" },
{ 8776,	"asymp","almost equal to = asymptotic to, U+2248 ISOamsr" },
{ 8800,	"ne",	"not equal to, U+2260 ISOtech" },
{ 8801,	"equiv","identical to, U+2261 ISOtech" },
{ 8804,	"le",	"less-than or equal to, U+2264 ISOtech" },
{ 8805,	"ge",	"greater-than or equal to, U+2265 ISOtech" },
{ 8834,	"sub",	"subset of, U+2282 ISOtech" },
{ 8835,	"sup",	"superset of, U+2283 ISOtech" },
{ 8836,	"nsub",	"not a subset of, U+2284 ISOamsn" },
{ 8838,	"sube",	"subset of or equal to, U+2286 ISOtech" },
{ 8839,	"supe",	"superset of or equal to, U+2287 ISOtech" },
{ 8853,	"oplus","circled plus = direct sum, U+2295 ISOamsb" },
{ 8855,	"otimes","circled times = vector product, U+2297 ISOamsb" },
{ 8869,	"perp",	"up tack = orthogonal to = perpendicular, U+22A5 ISOtech" },
{ 8901,	"sdot",	"dot operator, U+22C5 ISOamsb" },
{ 8968,	"lceil","left ceiling = apl upstile, U+2308 ISOamsc" },
{ 8969,	"rceil","right ceiling, U+2309 ISOamsc" },
{ 8970,	"lfloor","left floor = apl downstile, U+230A ISOamsc" },
{ 8971,	"rfloor","right floor, U+230B ISOamsc" },
{ 9001,	"lang",	"left-pointing angle bracket = bra, U+2329 ISOtech" },
{ 9002,	"rang",	"right-pointing angle bracket = ket, U+232A ISOtech" },
{ 9674,	"loz",	"lozenge, U+25CA ISOpub" },

{ 9824,	"spades","black spade suit, U+2660 ISOpub" },
{ 9827,	"clubs","black club suit = shamrock, U+2663 ISOpub" },
{ 9829,	"hearts","black heart suit = valentine, U+2665 ISOpub" },
{ 9830,	"diams","black diamond suit, U+2666 ISOpub" },

{ 338,	"OElig","latin capital ligature OE, U+0152 ISOlat2" },
{ 339,	"oelig","latin small ligature oe, U+0153 ISOlat2" },
{ 352,	"Scaron","latin capital letter S with caron, U+0160 ISOlat2" },
{ 353,	"scaron","latin small letter s with caron, U+0161 ISOlat2" },
{ 376,	"Yuml",	"latin capital letter Y with diaeresis, U+0178 ISOlat2" },
{ 710,	"circ",	"modifier letter circumflex accent, U+02C6 ISOpub" },
{ 732,	"tilde","small tilde, U+02DC ISOdia" },

{ 8194,	"ensp",	"en space, U+2002 ISOpub" },
{ 8195,	"emsp",	"em space, U+2003 ISOpub" },
{ 8201,	"thinsp","thin space, U+2009 ISOpub" },
{ 8204,	"zwnj",	"zero width non-joiner, U+200C NEW RFC 2070" },
{ 8205,	"zwj",	"zero width joiner, U+200D NEW RFC 2070" },
{ 8206,	"lrm",	"left-to-right mark, U+200E NEW RFC 2070" },
{ 8207,	"rlm",	"right-to-left mark, U+200F NEW RFC 2070" },
{ 8211,	"ndash","en dash, U+2013 ISOpub" },
{ 8212,	"mdash","em dash, U+2014 ISOpub" },
{ 8216,	"lsquo","left single quotation mark, U+2018 ISOnum" },
{ 8217,	"rsquo","right single quotation mark, U+2019 ISOnum" },
{ 8218,	"sbquo","single low-9 quotation mark, U+201A NEW" },
{ 8220,	"ldquo","left double quotation mark, U+201C ISOnum" },
{ 8221,	"rdquo","right double quotation mark, U+201D ISOnum" },
{ 8222,	"bdquo","double low-9 quotation mark, U+201E NEW" },
{ 8224,	"dagger","dagger, U+2020 ISOpub" },
{ 8225,	"Dagger","double dagger, U+2021 ISOpub" },
{ 8240,	"permil","per mille sign, U+2030 ISOtech" },
{ 8249,	"lsaquo","single left-pointing angle quotation mark, U+2039 ISO proposed" },
{ 8250,	"rsaquo","single right-pointing angle quotation mark, U+203A ISO proposed" },
{ 8364,	"euro",	"euro sign, U+20AC NEW" }
};

/************************************************************************
 *									*
 *		Commodity functions to handle entities			*
 *									*
 ************************************************************************/

/*
 * Macro used to grow the current buffer.
 */
#define growBuffer(buffer) {						\
    buffer##_size *= 2;							\
    buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar));	\
    if (buffer == NULL) {						\
	perror("realloc failed");					\
	return(NULL);							\
    }									\
}

/**
 * htmlEntityLookup:
 * @name: the entity name
 *
 * Lookup the given entity in EntitiesTable
 *
 * TODO: the linear scan is really ugly, an hash table is really needed.
 *
 * Returns the associated htmlEntityDescPtr if found, NULL otherwise.
 */
htmlEntityDescPtr
htmlEntityLookup(const xmlChar *name) {
    int i;

    for (i = 0;i < (sizeof(html40EntitiesTable)/
                    sizeof(html40EntitiesTable[0]));i++) {
        if (!xmlStrcmp(name, BAD_CAST html40EntitiesTable[i].name)) {
#ifdef DEBUG
            fprintf(stderr,"Found entity %s\n", name);
#endif
            return(&html40EntitiesTable[i]);
	}
    }
    return(NULL);
}


/**
 * htmlDecodeEntities:
 * @ctxt:  the parser context
 * @len:  the len to decode (in bytes !), -1 for no size limit
 * @end:  an end marker xmlChar, 0 if none
 * @end2:  an end marker xmlChar, 0 if none
 * @end3:  an end marker xmlChar, 0 if none
 *
 * Subtitute the HTML entities by their value
 *
 * DEPRECATED !!!!
 *
 * Returns A newly allocated string with the substitution done. The caller
 *      must deallocate it !
 */
xmlChar *
htmlDecodeEntities(htmlParserCtxtPtr ctxt, int len,
                  xmlChar end, xmlChar  end2, xmlChar end3) {
    xmlChar *buffer = NULL;
    int buffer_size = 0;
    xmlChar *out = NULL;
    xmlChar *name = NULL;

    xmlChar *cur = NULL;
    htmlEntityDescPtr ent;
    int nbchars = 0;
    unsigned int max = (unsigned int) len;

    /*
     * allocate a translation buffer.
     */
    buffer_size = HTML_PARSER_BIG_BUFFER_SIZE;
    buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
    if (buffer == NULL) {
	perror("htmlDecodeEntities: malloc failed");
	return(NULL);
    }
    out = buffer;

    /*
     * Ok loop until we reach one of the ending char or a size limit.
     */
    while ((nbchars < max) && (CUR != end) &&
           (CUR != end2) && (CUR != end3)) {

        if (CUR == '&') {
	    if (NXT(1) == '#') {
		int val = htmlParseCharRef(ctxt);
		/* invalid for UTF-8 variable encoding !!!!! */
		*out++ = val;
		nbchars += 3; /* !!!! */
	    } else {
		ent = htmlParseEntityRef(ctxt, &name);
		if (name != NULL) {
		    if ((ent == NULL) || (ent->value <= 0) ||
		        (ent->value >= 255)) {
		        *out++ = '&';
		        cur = name;
			while (*cur != 0) {
			    if (out - buffer > buffer_size - 100) {
				int index = out - buffer;

				growBuffer(buffer);
				out = &buffer[index];
			    }
			    *out++ = *cur++;
			}
		        *out++ = ';';
		    } else {
			/* invalid for UTF-8 variable encoding !!!!! */
			*out++ = (xmlChar)ent->value;
			if (out - buffer > buffer_size - 100) {
			    int index = out - buffer;

			    growBuffer(buffer);
			    out = &buffer[index];
			}
		    }
		    nbchars += 2 + xmlStrlen(name);
		    xmlFree(name);
		}
	    }
	} else {
	    /*  invalid for UTF-8 , use COPY(out); !!!!! */
	    *out++ = CUR;
	    nbchars++;
	    if (out - buffer > buffer_size - 100) {
	      int index = out - buffer;
	      
	      growBuffer(buffer);
	      out = &buffer[index];
	    }
	    NEXT;
	}
    }
    *out++ = 0;
    return(buffer);
}


/************************************************************************
 *									*
 *		Commodity functions to handle encodings			*
 *									*
 ************************************************************************/

/**
 * htmlSwitchEncoding:
 * @ctxt:  the parser context
 * @len:  the len of @cur
 *
 * change the input functions when discovering the character encoding
 * of a given entity.
 *
 */
void
htmlSwitchEncoding(htmlParserCtxtPtr ctxt, xmlCharEncoding enc)
{
    switch (enc) {
        case XML_CHAR_ENCODING_ERROR:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	        ctxt->sax->error(ctxt->userData, "encoding unknown\n");
	    ctxt->wellFormed = 0;
            break;
        case XML_CHAR_ENCODING_NONE:
	    /* let's assume it's UTF-8 without the XML decl */
            return;
        case XML_CHAR_ENCODING_UTF8:
	    /* default encoding, no conversion should be needed */
            return;
        case XML_CHAR_ENCODING_UTF16LE:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding UTF16 little endian not supported\n");
            break;
        case XML_CHAR_ENCODING_UTF16BE:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding UTF16 big endian not supported\n");
            break;
        case XML_CHAR_ENCODING_UCS4LE:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding USC4 little endian not supported\n");
            break;
        case XML_CHAR_ENCODING_UCS4BE:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding USC4 big endian not supported\n");
            break;
        case XML_CHAR_ENCODING_EBCDIC:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding EBCDIC not supported\n");
            break;
        case XML_CHAR_ENCODING_UCS4_2143:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding UCS4 2143 not supported\n");
            break;
        case XML_CHAR_ENCODING_UCS4_3412:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding UCS4 3412 not supported\n");
            break;
        case XML_CHAR_ENCODING_UCS2:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding UCS2 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_1:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_1 ISO Latin 1 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_2:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_2 ISO Latin 2 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_3:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_3 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_4:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_4 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_5:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_5 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_6:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_6 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_7:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_7 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_8:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_8 not supported\n");
            break;
        case XML_CHAR_ENCODING_8859_9:
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
		  "char encoding ISO_8859_9 not supported\n");
            break;
        case XML_CHAR_ENCODING_2022_JP:
            if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
                  "char encoding ISO-2022-JPnot supported\n");
            break;
        case XML_CHAR_ENCODING_SHIFT_JIS:
            if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
                  "char encoding Shift_JISnot supported\n");
            break;
        case XML_CHAR_ENCODING_EUC_JP:
            if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
                ctxt->sax->error(ctxt->userData,
                  "char encoding EUC-JPnot supported\n");
            break;
    }
}

/************************************************************************
 *									*
 *		Commodity functions to handle streams			*
 *									*
 ************************************************************************/

/**
 * htmlFreeInputStream:
 * @input:  an htmlParserInputPtr
 *
 * Free up an input stream.
 */
void
htmlFreeInputStream(htmlParserInputPtr input) {
    if (input == NULL) return;

    if (input->filename != NULL) xmlFree((char *) input->filename);
    if (input->directory != NULL) xmlFree((char *) input->directory);
    if ((input->free != NULL) && (input->base != NULL))
        input->free((xmlChar *) input->base);
    if (input->buf != NULL) 
        xmlFreeParserInputBuffer(input->buf);
    memset(input, -1, sizeof(htmlParserInput));
    xmlFree(input);
}

/**
 * htmlNewInputStream:
 * @ctxt:  an HTML parser context
 *
 * Create a new input stream structure