html.c

php-4.4.7学习linux时下载的源代码

	{ cs_utf_8, 		8465, 8501, ent_uni_8465_8501 },
	{ cs_utf_8, 		8592, 9002, ent_uni_8592_9002 },
	{ cs_utf_8, 		9674, 9674, ent_uni_9674 },
	{ cs_utf_8, 		9824, 9830, ent_uni_9824_9830 },
	{ cs_big5, 			0xa0, 0xff, ent_iso_8859_1 },
	{ cs_gb2312, 		0xa0, 0xff, ent_iso_8859_1 },
	{ cs_big5hkscs, 	0xa0, 0xff, ent_iso_8859_1 },
 	{ cs_sjis,			0xa0, 0xff, ent_iso_8859_1 },
 	{ cs_eucjp,			0xa0, 0xff, ent_iso_8859_1 },
	{ cs_koi8r,		    0xa3, 0xff, ent_koi8r },
	{ cs_cp1251,		0x80, 0xff, ent_cp_1251 },
	{ cs_8859_5,		0xc0, 0xff, ent_iso_8859_5 },
	{ cs_cp866,		    0xc0, 0xff, ent_cp_866 },
	{ cs_terminator }
};

static const struct {
	const char *codeset;
	enum entity_charset charset;
} charset_map[] = {
	{ "ISO-8859-1", 	cs_8859_1 },
	{ "ISO8859-1",	 	cs_8859_1 },
	{ "ISO-8859-15", 	cs_8859_15 },
	{ "ISO8859-15", 	cs_8859_15 },
	{ "utf-8", 			cs_utf_8 },
	{ "cp1252", 		cs_cp1252 },
	{ "Windows-1252", 	cs_cp1252 },
	{ "1252",           cs_cp1252 }, 
	{ "BIG5",			cs_big5 },
	{ "950",            cs_big5 },
	{ "GB2312",			cs_gb2312 },
	{ "936",            cs_gb2312 },
	{ "BIG5-HKSCS",		cs_big5hkscs },
	{ "Shift_JIS",		cs_sjis },
	{ "SJIS",   		cs_sjis },
	{ "932",            cs_sjis },
	{ "EUCJP",   		cs_eucjp },
	{ "EUC-JP",   		cs_eucjp },
	{ "KOI8-R",         cs_koi8r },
	{ "koi8-ru",        cs_koi8r },
	{ "koi8r",          cs_koi8r },
	{ "cp1251",         cs_cp1251 },
	{ "Windows-1251",   cs_cp1251 },
	{ "win-1251",       cs_cp1251 },
	{ "iso8859-5",      cs_8859_5 },
	{ "iso-8859-5",     cs_8859_5 },
	{ "cp866",          cs_cp866 },
	{ "866",            cs_cp866 },    
	{ "ibm866",         cs_cp866 },
	{ NULL }
};

static const struct {
	unsigned short charcode;
	char *entity;
	int entitylen;
	int flags;
} basic_entities[] = {
	{ '"',	""",	6,	ENT_HTML_QUOTE_DOUBLE },
	{ '\'',	"'",	6,	ENT_HTML_QUOTE_SINGLE },
	{ '\'',	"'",	5,	ENT_HTML_QUOTE_SINGLE },
	{ '<',	"&lt;",		4,	0 },
	{ '>',	"&gt;",		4,	0 },
	{ '&',	"&amp;",	5,	0 }, /* this should come last */
	{ 0, NULL, 0, 0 }
};
	
#define MB_RETURN { \
			*newpos = pos;       \
		  	mbseq[mbpos] = '\0'; \
		  	*mbseqlen = mbpos;   \
		  	return this_char; }
					
#define MB_WRITE(mbchar) { \
			mbspace--;  \
			if (mbspace == 0) {      \
				MB_RETURN;           \
			}                        \
			mbseq[mbpos++] = (mbchar); }

/* {{{ get_next_char
 */
inline static unsigned short get_next_char(enum entity_charset charset,
		unsigned char * str,
		int * newpos,
		unsigned char * mbseq,
		int * mbseqlen)
{
	int pos = *newpos;
	int mbpos = 0;
	int mbspace = *mbseqlen;
	unsigned short this_char = str[pos++];
	
	if (mbspace <= 0) {
		*mbseqlen = 0;
		return this_char;
	}
	
	MB_WRITE((unsigned char)this_char);
	
	switch (charset) {
		case cs_utf_8:
			{
				unsigned long utf = 0;
				int stat = 0;
				int more = 1;

				/* unpack utf-8 encoding into a wide char.
				 * Code stolen from the mbstring extension */

				do {
					if (this_char < 0x80) {
						more = 0;
						break;
					} else if (this_char < 0xc0) {
						switch (stat) {
							case 0x10:	/* 2, 2nd */
							case 0x21:	/* 3, 3rd */
							case 0x32:	/* 4, 4th */
							case 0x43:	/* 5, 5th */
							case 0x54:	/* 6, 6th */
								/* last byte in sequence */
								more = 0;
								utf |= (this_char & 0x3f);
								this_char = (unsigned short)utf;
								break;
							case 0x20:	/* 3, 2nd */
							case 0x31:	/* 4, 3rd */
							case 0x42:	/* 5, 4th */
							case 0x53:	/* 6, 5th */
								/* penultimate char */
								utf |= ((this_char & 0x3f) << 6);
								stat++;
								break;
							case 0x30:	/* 4, 2nd */
							case 0x41:	/* 5, 3rd */
							case 0x52:	/* 6, 4th */
								utf |= ((this_char & 0x3f) << 12);
								stat++;
								break;
							case 0x40:	/* 5, 2nd */
							case 0x51:
								utf |= ((this_char & 0x3f) << 18);
								stat++;
								break;
							case 0x50:	/* 6, 2nd */
								utf |= ((this_char & 0x3f) << 24);
								stat++;
								break;
							default:
								/* invalid */
								more = 0;
						}
					}
					/* lead byte */
					else if (this_char < 0xe0) {
						stat = 0x10;	/* 2 byte */
						utf = (this_char & 0x1f) << 6;
					} else if (this_char < 0xf0) {
						stat = 0x20;	/* 3 byte */
						utf = (this_char & 0xf) << 12;
					} else if (this_char < 0xf8) {
						stat = 0x30;	/* 4 byte */
						utf = (this_char & 0x7) << 18;
					} else if (this_char < 0xfc) {
						stat = 0x40;	/* 5 byte */
						utf = (this_char & 0x3) << 24;
					} else if (this_char < 0xfe) {
						stat = 0x50;	/* 6 byte */
						utf = (this_char & 0x1) << 30;
					} else {
						/* invalid; bail */
						more = 0;
						break;
					}

					if (more) {
						this_char = str[pos++];
						MB_WRITE((unsigned char)this_char);
					}
				} while (more);
			}
			break;
		case cs_big5:
		case cs_gb2312:
		case cs_big5hkscs:
			{
				/* check if this is the first of a 2-byte sequence */
				if (this_char >= 0xa1 && this_char <= 0xfe) {
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if ((next_char >= 0x40 && next_char <= 0x7e) ||
							(next_char >= 0xa1 && next_char <= 0xfe)) {
						/* yes, this a wide char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				}
				break;
			}
		case cs_sjis:
			{
				/* check if this is the first of a 2-byte sequence */
				if ( (this_char >= 0x81 && this_char <= 0x9f) ||
					 (this_char >= 0xe0 && this_char <= 0xef)
					) {
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if ((next_char >= 0x40 && next_char <= 0x7e) ||
						(next_char >= 0x80 && next_char <= 0xfc))
					{
						/* yes, this a wide char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				}
				break;
			}
		case cs_eucjp:
			{
				/* check if this is the first of a multi-byte sequence */
				if (this_char >= 0xa1 && this_char <= 0xfe) {
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if (next_char >= 0xa1 && next_char <= 0xfe) {
						/* yes, this a jis kanji char */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				} else if (this_char == 0x8e) {
					/* peek at the next char */
					unsigned char next_char = str[pos];
					if (next_char >= 0xa1 && next_char <= 0xdf) {
						/* JIS X 0201 kana */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
					}
					
				} else if (this_char == 0x8f) {
					/* peek at the next two char */
					unsigned char next_char = str[pos];
					unsigned char next2_char = str[pos+1];
					if ((next_char >= 0xa1 && next_char <= 0xfe) &&
						(next2_char >= 0xa1 && next2_char <= 0xfe)) {
						/* JIS X 0212 hojo-kanji */
						this_char <<= 8;
						MB_WRITE(next_char);
						this_char |= next_char;
						pos++;
						this_char <<= 8;
						MB_WRITE(next2_char);
						this_char |= next2_char;
						pos++;
					}
					
				}
				break;
			}
		default:
			break;
	}
	MB_RETURN;
}
/* }}} */

/* {{{ entity_charset determine_charset
 * returns the charset identifier based on current locale or a hint.
 * defaults to iso-8859-1 */
static enum entity_charset determine_charset(char *charset_hint TSRMLS_DC)
{
	int i;
	enum entity_charset charset = cs_8859_1;
	int len = 0;
	zval *uf_result = NULL;

	/* Guarantee default behaviour for backwards compatibility */
	if (charset_hint == NULL)
		return cs_8859_1;

	if ((len = strlen(charset_hint)) != 0) {
		goto det_charset;
	}
#if HAVE_MBSTRING
#if !defined(COMPILE_DL_MBSTRING)
	/* XXX: Ugly things. Why don't we look for a more sophisticated way? */
	switch (MBSTRG(current_internal_encoding)) {
		case mbfl_no_encoding_8859_1:
			return cs_8859_1;

		case mbfl_no_encoding_utf8:
			return cs_utf_8;

		case mbfl_no_encoding_euc_jp:
		case mbfl_no_encoding_eucjp_win:
			return cs_eucjp;

		case mbfl_no_encoding_sjis:
		case mbfl_no_encoding_sjis_win:
		case mbfl_no_encoding_sjis_mac:
			return cs_sjis;

		case mbfl_no_encoding_cp1252:
			return cs_cp1252;

		case mbfl_no_encoding_8859_15:
			return cs_8859_15;

		case mbfl_no_encoding_big5:
			return cs_big5;

		case mbfl_no_encoding_euc_cn:
		case mbfl_no_encoding_hz:
		case mbfl_no_encoding_cp936:
			return cs_gb2312;

		case mbfl_no_encoding_koi8r:
			return cs_koi8r;

		case mbfl_no_encoding_cp866:
			return cs_cp866;

		case mbfl_no_encoding_cp1251:
			return cs_cp1251;

		case mbfl_no_encoding_8859_5:
			return cs_8859_5;

		default:	
			;
	}
#else
	{
		zval nm_mb_internal_encoding;

		ZVAL_STRING(&nm_mb_internal_encoding, "mb_internal_encoding", 0);

		if (call_user_function_ex(CG(function_table), NULL, &nm_mb_internal_encoding, &uf_result, 0, NULL, 1, NULL TSRMLS_CC) != FAILURE) {

			charset_hint = Z_STRVAL_P(uf_result);
			len = Z_STRLEN_P(uf_result);
			
			goto det_charset;
		}
	}
#endif
#endif

	charset_hint = SG(default_charset);
	if (charset_hint != NULL && (len=strlen(charset_hint)) != 0) {
		goto det_charset;