lycharsets.c

基于rtos开发的浏览器！

    } else if (!strncmp(LYchar_set_names[i], "ISO Latin 1", 11) ||
	       !strncmp(LYchar_set_names[i], "Chinese", 7) ||
	       !strncmp(LYchar_set_names[i], "Japanese (EUC)", 14) ||
	       !strncmp(LYchar_set_names[i], "Japanese (SJIS)", 15) ||
	       !strncmp(LYchar_set_names[i], "Korean", 6) ||
	       !strncmp(LYchar_set_names[i], "Taipei (Big5)", 13)) {
	if (modeflag == TRUE) {
	    LYUseDefaultRawMode = TRUE;
	} else {
	    LYUseDefaultRawMode = FALSE;
	}
    } else {
	if (modeflag == FALSE) {
	    LYUseDefaultRawMode = TRUE;
	} else {
	    LYUseDefaultRawMode = FALSE;
	}
    }
    return;
}

/*
 *  Function to set the LYHaveCJKCharacterSet value
 *  based on the selected character set. - FM
 */
PUBLIC void HTMLSetHaveCJKCharacterSet ARGS1(int,i)
{
    if (!strncmp(LYchar_set_names[i], "Chinese", 7) ||
	!strncmp(LYchar_set_names[i], "Japanese (EUC)", 14) ||
	!strncmp(LYchar_set_names[i], "Japanese (SJIS)", 15) ||
	!strncmp(LYchar_set_names[i], "Korean", 6) ||
	!strncmp(LYchar_set_names[i], "Taipei (Big5)", 13)) {
	LYHaveCJKCharacterSet = TRUE;
    } else {
	LYHaveCJKCharacterSet = FALSE;
    }
    return;
}

/*
 *  Entity names -- Ordered by ISO Latin 1 value.
 *  ---------------------------------------------
 *   For conversions of DECIMAL escaped entities.
 *   Must be in order of ascending value.
 */
PUBLIC CONST char * LYEntityNames[] = {
/*	 NAME		   DECIMAL VALUE */
	"nbsp", 	/* 160, non breaking space */
	"iexcl",	/* 161, inverted exclamation mark */
	"cent", 	/* 162, cent sign */
	"pound",	/* 163, pound sign */
	"curren",	/* 164, currency sign */
	"yen",		/* 165, yen sign */
	"brvbar",	/* 166, broken vertical bar, (brkbar) */
	"sect", 	/* 167, section sign */
	"uml",		/* 168, spacing dieresis */
	"copy", 	/* 169, copyright sign */
	"ordf", 	/* 170, feminine ordinal indicator */
	"laquo",	/* 171, angle quotation mark, left */
	"not",		/* 172, negation sign */
	"shy",		/* 173, soft hyphen */
	"reg",		/* 174, circled R registered sign */
	"hibar",	/* 175, spacing macron */
	"deg",		/* 176, degree sign */
	"plusmn",	/* 177, plus-or-minus sign */
	"sup2", 	/* 178, superscript 2 */
	"sup3", 	/* 179, superscript 3 */
	"acute",	/* 180, spacing acute (96) */
	"micro",	/* 181, micro sign */
	"para", 	/* 182, paragraph sign */
	"middot",	/* 183, middle dot */
	"cedil",	/* 184, spacing cedilla */
	"sup1", 	/* 185, superscript 1 */
	"ordm", 	/* 186, masculine ordinal indicator */
	"raquo",	/* 187, angle quotation mark, right */
	"frac14",	/* 188, fraction 1/4 */
	"frac12",	/* 189, fraction 1/2 */
	"frac34",	/* 190, fraction 3/4 */
	"iquest",	/* 191, inverted question mark */
	"Agrave",	/* 192, capital A, grave accent */
	"Aacute",	/* 193, capital A, acute accent */
	"Acirc",	/* 194, capital A, circumflex accent */
	"Atilde",	/* 195, capital A, tilde */
	"Auml", 	/* 196, capital A, dieresis or umlaut mark */
	"Aring",	/* 197, capital A, ring */
	"AElig",	/* 198, capital AE diphthong (ligature) */
	"Ccedil",	/* 199, capital C, cedilla */
	"Egrave",	/* 200, capital E, grave accent */
	"Eacute",	/* 201, capital E, acute accent */
	"Ecirc",	/* 202, capital E, circumflex accent */
	"Euml", 	/* 203, capital E, dieresis or umlaut mark */
	"Igrave",	/* 204, capital I, grave accent */
	"Iacute",	/* 205, capital I, acute accent */
	"Icirc",	/* 206, capital I, circumflex accent */
	"Iuml", 	/* 207, capital I, dieresis or umlaut mark */
	"ETH",		/* 208, capital Eth, Icelandic (or Latin2 Dstrok) */
	"Ntilde",	/* 209, capital N, tilde */
	"Ograve",	/* 210, capital O, grave accent */
	"Oacute",	/* 211, capital O, acute accent */
	"Ocirc",	/* 212, capital O, circumflex accent */
	"Otilde",	/* 213, capital O, tilde */
	"Ouml", 	/* 214, capital O, dieresis or umlaut mark */
	"times",	/* 215, multiplication sign */
	"Oslash",	/* 216, capital O, slash */
	"Ugrave",	/* 217, capital U, grave accent */
	"Uacute",	/* 218, capital U, acute accent */
	"Ucirc",	/* 219, capital U, circumflex accent */
	"Uuml", 	/* 220, capital U, dieresis or umlaut mark */
	"Yacute",	/* 221, capital Y, acute accent */
	"THORN",	/* 222, capital THORN, Icelandic */
	"szlig",	/* 223, small sharp s, German (sz ligature) */
	"agrave",	/* 224, small a, grave accent */
	"aacute",	/* 225, small a, acute accent */
	"acirc",	/* 226, small a, circumflex accent */
	"atilde",	/* 227, small a, tilde */
	"auml", 	/* 228, small a, dieresis or umlaut mark */
	"aring",	/* 229, small a, ring */
	"aelig",	/* 230, small ae diphthong (ligature) */
	"ccedil",	/* 231, small c, cedilla */
	"egrave",	/* 232, small e, grave accent */
	"eacute",	/* 233, small e, acute accent */
	"ecirc",	/* 234, small e, circumflex accent */
	"euml", 	/* 235, small e, dieresis or umlaut mark */
	"igrave",	/* 236, small i, grave accent */
	"iacute",	/* 237, small i, acute accent */
	"icirc",	/* 238, small i, circumflex accent */
	"iuml", 	/* 239, small i, dieresis or umlaut mark */
	"eth",		/* 240, small eth, Icelandic */
	"ntilde",	/* 241, small n, tilde */
	"ograve",	/* 242, small o, grave accent */
	"oacute",	/* 243, small o, acute accent */
	"ocirc",	/* 244, small o, circumflex accent */
	"otilde",	/* 245, small o, tilde */
	"ouml", 	/* 246, small o, dieresis or umlaut mark */
	"divide",	/* 247, division sign */
	"oslash",	/* 248, small o, slash */
	"ugrave",	/* 249, small u, grave accent */
	"uacute",	/* 250, small u, acute accent */
	"ucirc",	/* 251, small u, circumflex accent */
	"uuml", 	/* 252, small u, dieresis or umlaut mark */
	"yacute",	/* 253, small y, acute accent */
	"thorn",	/* 254, small thorn, Icelandic */
	"yuml", 	/* 255, small y, dieresis or umlaut mark */
};

/*
 *  Function to return the entity names of
 *  ISO-8859-1 8-bit characters. - FM
 */
PUBLIC CONST char * HTMLGetEntityName ARGS1(
	UCode_t,	code)
{
#define IntValue code
    int MaxValue = ((sizeof(LYEntityNames)/sizeof(char **)) - 1);

    if (IntValue < 0 || IntValue > MaxValue) {
	return "";
    }

    return LYEntityNames[IntValue];
}

/*
 *  Function to return the UCode_t (long int) value for entity names
 *  in the ISO_Latin1 and UC_entity_info unicode_entities arrays.
 *  It returns 0 if not found. - FM
 *
 *  unicode_entities[] now handles all the names from old style entities[] too.
 *  Lynx now calls unicode_entities[] only through this function:
 *  HTMLGetEntityUCValue().  Note, we need not check for special characters
 *  here in function or even before it, we should check them *after*
 *  invoking this function, see put_special_unicodes() in SGML.c.
 *
 *  In the future we will try to isolate all calls to entities[]
 *  in favor of new unicode-based chartrans scheme. - LP
 */
PUBLIC UCode_t HTMLGetEntityUCValue ARGS1(
	CONST char *,	name)
{
    UCode_t value = 0;
    size_t i, high, low;
    int diff = 0;
/*  CONST char ** entities = HTML_dtd.entity_names;  */
    CONST UC_entity_info * unicode_entities = HTML_dtd.unicode_entity_info;

    /*
     *	Make sure we have a non-zero length name. - FM
     */
    if (!(name && *name))
	return(value);


#ifdef NOTDEFINED
/*
**  unicode_entities[] now handles all names from entities[], so disable latter.
**  Let us keep this some sort of comment until we remove
**  all calls to old-style entities[] from the code. - LP
*/

    /*
     *	Handle names that have control characters
     *	or strings in ISO_Latin1[]. - FM
     */
    if (!strcmp(name, "nbsp")) {
	return(160);
    }
    if (!strcmp(name, "shy")) {
	return(173);
    }
    if (!strcmp(name, "ensp")) {
	return(8194);
    }
    if (!strcmp(name, "emsp")) {
	return(8195);
    }
    if (!strcmp(name, "thinsp")) {
	return(8201);
    }
    if (!strcmp(name, "ndash") ||
	!strcmp(name, "endash")) {
	return(8211);
    }
    if (!strcmp(name, "mdash") ||
	!strcmp(name, "emdash")) {
	return(8212);
    }
    if (!strcmp(name, "trade")) {
	return(8482);
    }

    /*
     *	Now try ISO_Latin1[]. - FM
     */
    for (low = 0, high = HTML_dtd.number_of_entities;
	 high > low;
	 diff < 0 ? (low = i+1) : (high = i)) {
	/*
	**  Binary search.
	*/
	i = (low + (high-low)/2);
	diff = strcmp(entities[i], name);
	if (diff == 0) {
	    if (strlen(ISO_Latin1[i]) == 1) {
		value = (unsigned char)(ISO_Latin1[i][0]);
	    }
	    break;
	}
    }
    if (value > 0) {
	return(value);
    }

    /*
     *	Not yet found...    - FM
     */
#endif /* NOTDEFINED */

    /*
     *	Try UC_entity_info unicode_entities[].
     */
    for (low = 0, high = HTML_dtd.number_of_unicode_entities;
	 high > low;
	 diff < 0 ? (low = i+1) : (high = i)) {
	/*
	**  Binary search.
	*/
	i = (low + (high-low)/2);
	diff = strcmp(unicode_entities[i].name, name);	/* Case sensitive! */
	if (diff == 0) {
	    value = unicode_entities[i].code;
	    break;
	}
    }

    return(value);
}

/*
 *  Function to select a character set and then set the
 *  character handling and LYHaveCJKCharacterSet flag. - FM
 */
PUBLIC void HTMLUseCharacterSet ARGS1(int,i)
{
    p_entity_values = LYCharSets[i];
    HTMLSetCharacterHandling(i);
    HTMLSetHaveCJKCharacterSet(i);
    return;
}

/*
 *  Initializer, calls initialization function for the
 *  CHARTRANS handling. - KW
 */
PUBLIC int LYCharSetsDeclared NOPARAMS
{
    UCInit();

    if (UCAssume_MIMEcharset && *UCAssume_MIMEcharset) {
	UCLYhndl_for_unspec = UCGetLYhndl_byMIME(UCAssume_MIMEcharset);
    } else {
	UCLYhndl_for_unspec = 0;
    }
    if (UCAssume_localMIMEcharset && *UCAssume_localMIMEcharset)
	UCLYhndl_HTFile_for_unspec =
	    UCGetLYhndl_byMIME(UCAssume_localMIMEcharset);
    if (UCAssume_unrecMIMEcharset && *UCAssume_unrecMIMEcharset)
	UCLYhndl_for_unrec =
	    UCGetLYhndl_byMIME(UCAssume_unrecMIMEcharset);

    return UCInitialized;
}