html.c

this is the file used to browse web

#include "links.h"

struct list_head html_stack = {&html_stack, &html_stack};

static inline int atchr(unsigned char c)
{
	return /*isA(c) ||*/ (c > ' ' && c != '=' && c != '<' && c != '>');
}

int parse_element(unsigned char *e, unsigned char *eof, unsigned char **name, int *namelen, unsigned char **attr, unsigned char **end)
{
	if (eof - e < 3 || *(e++) != '<') return -1;
	if (name) *name = e;
	if (*e == '/') e++;
	if (!isA(*e)) return -1;
	goto x1;
	while (isA(*e) || *e == '=') {
		x1:
		e++;
		if (e >= eof) return -1;
	}
	/*if ((!WHITECHAR(*e) && *e != '>' && *e != '<' && *e != '/' && *e != ':')) return -1;*/
	if (name && namelen) *namelen = e - *name;
	while ((WHITECHAR(*e) || *e == '/' || *e == ':')) {
		e++;
		if (e >= eof) return -1;
	}
	if ((!atchr(*e) && *e != '>' && *e != '<')) return -1;
	if (attr) *attr = e;
	nextattr:
	while (WHITECHAR(*e)) {
		e++;
		if (e >= eof) return -1;
	}
	if ((!atchr(*e) && *e != '>' && *e != '<')) return -1;
	if (*e == '>' || *e == '<') goto en;
	while (atchr(*e)) {
		e++;
		if (e >= eof) return -1;
	}
	while (WHITECHAR(*e)) {
		e++;
		if (e >= eof) return -1;
	}
	if (*e != '=') goto endattr;
	goto x2;
	while (WHITECHAR(*e)) {
		x2:
		e++;
		if (e >= eof) return -1;
	}
	if (U(*e)) {
		unsigned char uu = *e;
		/*u:*/
		goto x3;
		while (e < eof && *e != uu && *e /*(WHITECHAR(*e) || *e > ' ')*/) {
			x3:
			e++;
			if (e >= eof) return -1;
		}
		if (*e < ' ') return -1;
		e++;
		if (e >= eof /*|| (!WHITECHAR(*e) && *e != uu && *e != '>' && *e != '<')*/) return -1;
		/*if (*e == uu) goto u;*/
	} else {
		while (!WHITECHAR(*e) && *e != '>' && *e != '<') {
			e++;
			if (e >= eof) return -1;
		}
	}
	while (WHITECHAR(*e)) {
		e++;
		if (e >= eof) return -1;
	}
	endattr:
	if (*e != '>' && *e != '<') goto nextattr;
	en:
	if (end) *end = e + (*e == '>');
	return 0;
}

#define add_chr(s, l, c)						\
do {									\
	if (!((l) & (32 - 1))) {					\
		if ((unsigned)(l) > MAXINT - 32) overalloc();		\
		(s) = mem_realloc((s), (l) + 32);			\
	}								\
	(s)[(l)++] = (c);						\
} while (0)

int get_attr_val_nl = 0;

/* parses html element attributes */
/* e is attr pointer previously get from parse_element, DON'T PASS HERE ANY OTHER VALUE!!! */
/* name is searched attribute */
/* returns allocated string containing the attribute, or NULL on unsuccess */
unsigned char *get_attr_val(unsigned char *e, unsigned char *name)
{
	unsigned char *n;
	unsigned char *a = DUMMY;
	int l = 0;
	int f;
	aa:
	while (WHITECHAR(*e)) e++;
	if (*e == '>' || *e == '<') return NULL;
	n = name;
	while (*n && upcase(*e) == upcase(*n)) e++, n++;
	f = *n;
	while (atchr(*e)) f = 1, e++;
	while (WHITECHAR(*e)) e++;
	if (*e != '=') goto ea;
	e++;
	while (WHITECHAR(*e)) e++;
	if (!U(*e)) {
		while (!WHITECHAR(*e) && *e != '>' && *e != '<') {
			if (!f) add_chr(a, l, *e);
			e++;
		}
	} else {
		char uu = *e;
		/*a:*/
		e++;
		while (*e != uu) {
			if (!*e) {
				mem_free(a);
				return NULL;
			}
			if (!f) {
				if (get_attr_val_nl == 2) goto exact;
				if (*e != 13) {
					if (*e != 9 && *e != 10) exact:add_chr(a, l, *e);
					else if (!get_attr_val_nl) add_chr(a, l, ' ');
				}
			}
			e++;
		}
		e++;
		/*if (*e == uu) {
			if (!f) add_chr(a, l, *e);
			goto a;
		}*/
	}
	ea:
	if (!f) {
		unsigned char *b;
		add_chr(a, l, 0);
		if (strchr(a, '&')) {
			unsigned char *aa = a;
			int c = d_opt->cp;
			d_opt->cp = d_opt->real_cp;
			a = convert_string(NULL, aa, strlen(aa));
			d_opt->cp = c;
			mem_free(aa);
		}
		while ((b = strchr(a, 1))) *b = ' ';
		if (get_attr_val_nl != 2) {
			for (b = a; *b == ' '; b++);
			if (b != a) memmove(a, b, strlen(b) + 1);
			for (b = a + strlen(a) - 1; b >= a && *b == ' '; b--) *b = 0;
		}
		set_mem_comment(a, name, strlen(name));
		return a;
	}
	goto aa;
}

int has_attr(unsigned char *e, unsigned char *name)
{
	char *a;
	if (!(a = get_attr_val(e, name))) return 0;
	mem_free(a);
	return 1;
}

/*
unsigned char *get_url_val(unsigned char *e, unsigned char *name)
{
	int n = 0;
	unsigned char *p, *q, *pp;
	if (!(pp = get_attr_val(e, name))) return NULL;
	p = pp; q = pp;
	while (1) {
		if (*p == '#') n = 1;
		if ((*p = *q) != ' ' || n) p++;
		if (!*q) break;
		q++;
	}
	return pp;
}
*/

unsigned char *get_url_val(unsigned char *e, unsigned char *name)
{
	unsigned char *a;
	get_attr_val_nl = 1;
	a = get_attr_val(e, name);
	get_attr_val_nl = 0;
	return a;
}


unsigned char *get_exact_attr_val(unsigned char *e, unsigned char *name)
{
	unsigned char *a;
	get_attr_val_nl = 2;
	a = get_attr_val(e, name);
	get_attr_val_nl = 0;
	return a;
}

struct {
	unsigned short int n;
	char *s;
} roman_tbl[] = {
	{ 1000,	"m" },
	{ 999,	"im" },
/*	{ 995,	"vm" },*/
	{ 990,	"xm" },
/*	{ 950,	"lm" },*/
	{ 900,	"cm" },
	{ 500,	"d" },
	{ 499,	"id" },
/*	{ 495,	"vd" },*/
	{ 490,	"xd" },
/*	{ 450,	"ld" },*/
	{ 400,	"cd" },
	{ 100,	"c" },
	{ 99,	"ic" },
/*	{ 95,	"vc" },*/
	{ 90,	"xc" },
	{ 50,	"l" },
	{ 49,	"il" },
/*	{ 45,	"vl" },*/
	{ 40,	"xl" },
	{ 10,	"x" },
	{ 9,	"ix" },
	{ 5,	"v" },
	{ 4,	"iv" },
	{ 1,	"i" },
	{ 0,	NULL },
};

void roman(char *p, unsigned n)
{
	int i = 0;
	if (n >= 4000) {
		strcpy(p, "---");
		return;
	}
	if (!n) {
		strcpy(p, "o");
		return;
	}
	p[0] = 0;
	while (n) {
		while (roman_tbl[i].n <= n) {
			n -= roman_tbl[i].n;
			strcat(p, roman_tbl[i].s);
		}
		i++;
		if (n && !roman_tbl[i].n) {
			internal("BUG in roman number convertor");
			return;
		}
	}
}

struct color_spec {
	char *name;
	int rgb;
};

struct color_spec color_specs[] = {
	{"aliceblue",		0xF0F8FF},
	{"antiquewhite",	0xFAEBD7},
	{"aqua",		0x00FFFF},
	{"aquamarine",		0x7FFFD4},
	{"azure",		0xF0FFFF},
	{"beige",		0xF5F5DC},
	{"bisque",		0xFFE4C4},
	{"black",		0x000000},
	{"blanchedalmond",	0xFFEBCD},
	{"blue",		0x0000FF},
	{"blueviolet",		0x8A2BE2},
	{"brown",		0xA52A2A},
	{"burlywood",		0xDEB887},
	{"cadetblue",		0x5F9EA0},
	{"chartreuse",		0x7FFF00},
	{"chocolate",		0xD2691E},
	{"coral",		0xFF7F50},
	{"cornflowerblue",	0x6495ED},
	{"cornsilk",		0xFFF8DC},
	{"crimson",		0xDC143C},
	{"cyan",		0x00FFFF},
	{"darkblue",		0x00008B},
	{"darkcyan",		0x008B8B},
	{"darkgoldenrod",	0xB8860B},
	{"darkgray",		0xA9A9A9},
	{"darkgreen",		0x006400},
	{"darkkhaki",		0xBDB76B},
	{"darkmagenta",		0x8B008B},
	{"darkolivegreen",	0x556B2F},
	{"darkorange",		0xFF8C00},
	{"darkorchid",		0x9932CC},
	{"darkred",		0x8B0000},
	{"darksalmon",		0xE9967A},
	{"darkseagreen",	0x8FBC8F},
	{"darkslateblue",	0x483D8B},
	{"darkslategray",	0x2F4F4F},
	{"darkturquoise",	0x00CED1},
	{"darkviolet",		0x9400D3},
	{"deeppink",		0xFF1493},
	{"deepskyblue",		0x00BFFF},
	{"dimgray",		0x696969},
	{"dodgerblue",		0x1E90FF},
	{"firebrick",		0xB22222},
	{"floralwhite",		0xFFFAF0},
	{"forestgreen",		0x228B22},
	{"fuchsia",		0xFF00FF},
	{"gainsboro",		0xDCDCDC},
	{"ghostwhite",		0xF8F8FF},
	{"gold",		0xFFD700},
	{"goldenrod",		0xDAA520},
	{"gray",		0x808080},
	{"green",		0x008000},
	{"greenyellow",		0xADFF2F},
	{"honeydew",		0xF0FFF0},
	{"hotpink",		0xFF69B4},
	{"indianred",		0xCD5C5C},
	{"indigo",		0x4B0082},
	{"ivory",		0xFFFFF0},
	{"khaki",		0xF0E68C},
	{"lavender",		0xE6E6FA},
	{"lavenderblush",	0xFFF0F5},
	{"lawngreen",		0x7CFC00},
	{"lemonchiffon",	0xFFFACD},
	{"lightblue",		0xADD8E6},
	{"lightcoral",		0xF08080},
	{"lightcyan",		0xE0FFFF},
	{"lightgoldenrodyellow",	0xFAFAD2},
	{"lightgreen",		0x90EE90},
	{"lightgrey",		0xD3D3D3},
	{"lightpink",		0xFFB6C1},
	{"lightsalmon",		0xFFA07A},
	{"lightseagreen",	0x20B2AA},
	{"lightskyblue",	0x87CEFA},
	{"lightslategray",	0x778899},
	{"lightsteelblue",	0xB0C4DE},
	{"lightyellow",		0xFFFFE0},
	{"lime",		0x00FF00},
	{"limegreen",		0x32CD32},
	{"linen",		0xFAF0E6},
	{"magenta",		0xFF00FF},
	{"maroon",		0x800000},
	{"mediumaquamarine",	0x66CDAA},
	{"mediumblue",		0x0000CD},
	{"mediumorchid",	0xBA55D3},
	{"mediumpurple",	0x9370DB},
	{"mediumseagreen",	0x3CB371},
	{"mediumslateblue",	0x7B68EE},
	{"mediumspringgreen",	0x00FA9A},
	{"mediumturquoise",	0x48D1CC},
	{"mediumvioletred",	0xC71585},
	{"midnightblue",	0x191970},
	{"mintcream",		0xF5FFFA},
	{"mistyrose",		0xFFE4E1},
	{"moccasin",		0xFFE4B5},
	{"navajowhite",		0xFFDEAD},
	{"navy",		0x000080},
	{"oldlace",		0xFDF5E6},
	{"olive",		0x808000},
	{"olivedrab",		0x6B8E23},
	{"orange",		0xFFA500},
	{"orangered",		0xFF4500},
	{"orchid",		0xDA70D6},
	{"palegoldenrod",	0xEEE8AA},
	{"palegreen",		0x98FB98},
	{"paleturquoise",	0xAFEEEE},
	{"palevioletred",	0xDB7093},
	{"papayawhip",		0xFFEFD5},
	{"peachpuff",		0xFFDAB9},
	{"peru",		0xCD853F},
	{"pink",		0xFFC0CB},
	{"plum",		0xDDA0DD},
	{"powderblue",		0xB0E0E6},
	{"purple",		0x800080},
	{"red",			0xFF0000},
	{"rosybrown",		0xBC8F8F},
	{"royalblue",		0x4169E1},
	{"saddlebrown",		0x8B4513},
	{"salmon",		0xFA8072},
	{"sandybrown",		0xF4A460},
	{"seagreen",		0x2E8B57},
	{"seashell",		0xFFF5EE},
	{"sienna",		0xA0522D},
	{"silver",		0xC0C0C0},
	{"skyblue",		0x87CEEB},
	{"slateblue",		0x6A5ACD},
	{"slategray",		0x708090},
	{"snow",		0xFFFAFA},
	{"springgreen",		0x00FF7F},
	{"steelblue",		0x4682B4},
	{"tan",			0xD2B48C},
	{"teal",		0x008080},
	{"thistle",		0xD8BFD8},
	{"tomato",		0xFF6347},
	{"turquoise",		0x40E0D0},
	{"violet",		0xEE82EE},
	{"wheat",		0xF5DEB3},
	{"white",		0xFFFFFF},
	{"whitesmoke",		0xF5F5F5},
	{"yellow",		0xFFFF00},
	{"yellowgreen",		0x9ACD32},
};

#define endof(T) ((T)+sizeof(T)/sizeof(*(T)))

int decode_color(unsigned char *str, struct rgb *col)
{
	unsigned long ch;
	if (*str != '#') {
		struct color_spec *cs;
		for (cs = color_specs; cs < endof(color_specs); cs++)
			if (!strcasecmp(cs->name, str)) {
				ch = cs->rgb;
				goto found;
			}
		str--;
	}
	str++;
	if (strlen(str) == 6) {
		char *end;
		ch = strtoul(str, &end, 16);
		if (!*end && ch < 0x1000000) {
found:
			col->r = ch / 0x10000;
			col->g = ch / 0x100 % 0x100;
			col->b = ch % 0x100;
			return 0;
		}
	}
	return -1;
}

int get_color(unsigned char *a, unsigned char *c, struct rgb *rgb)
{
	char *at;
	int r = -1;
	if (d_opt->col >= 1) if ((at = get_attr_val(a, c))) {
		r = decode_color(at, rgb);
		mem_free(at);
	}
	return r;
}

int get_bgcolor(unsigned char *a, struct rgb *rgb)
{
	if (d_opt->col < 2) return -1;
	return get_color(a, "bgcolor", rgb);
}

unsigned char *get_target(unsigned char *a)
{
	unsigned char *v = get_attr_val(a, "target");
	if (v) {
		if (!strcasecmp(v, "_self")) {
			mem_free(v);
			v = stracpy(d_opt->framename);
		}
	}
	return v;
}

void kill_html_stack_item(struct html_element *e)
{
	if (e->dontkill == 2) {
		internal("trying to kill unkillable element");
		return;
	}
	if (!e || (void *)e == &html_stack) {
		internal("trying to free bad html element");
		return;
	}
	if (e->attr.link) mem_free(e->attr.link);
	if (e->attr.target) mem_free(e->attr.target);