===================================================================
RCS file: /cvs/mandoc/html.c,v
retrieving revision 1.158
retrieving revision 1.165
diff -u -p -r1.158 -r1.165
--- mandoc/html.c	2014/07/22 22:41:35	1.158
+++ mandoc/html.c	2014/09/27 09:02:19	1.165
@@ -1,4 +1,4 @@
-/*	$Id: html.c,v 1.158 2014/07/22 22:41:35 schwarze Exp $ */
+/*	$Id: html.c,v 1.165 2014/09/27 09:02:19 kristaps Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -15,9 +15,7 @@
  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
-#ifdef HAVE_CONFIG_H
 #include "config.h"
-#endif
 
 #include <sys/types.h>
 
@@ -76,6 +74,7 @@ static	const struct htmldata htmltags[TAG_MAX] = {
 	{"i",		0 }, /* TAG_I */
 	{"code",	0 }, /* TAG_CODE */
 	{"small",	0 }, /* TAG_SMALL */
+	{"style",	HTML_CLRLINE}, /* TAG_STYLE */
 };
 
 static	const char	*const htmlattrs[ATTR_MAX] = {
@@ -93,6 +92,7 @@ static	const char	*const htmlattrs[ATTR_MAX] = {
 	"summary", /* ATTR_SUMMARY */
 	"align", /* ATTR_ALIGN */
 	"colspan", /* ATTR_COLSPAN */
+	"charset", /* ATTR_CHARSET */
 };
 
 static	const char	*const roffscales[SCALE_MAX] = {
@@ -110,6 +110,7 @@ static	const char	*const roffscales[SCALE_MAX] = {
 
 static	void	 bufncat(struct html *, const char *, size_t);
 static	void	 print_ctag(struct html *, enum htmltag);
+static	int	 print_escape(char);
 static	int	 print_encode(struct html *, const char *, int);
 static	void	 print_metaf(struct html *, enum mandoc_esc);
 static	void	 print_attr(struct html *, const char *, const char *);
@@ -193,18 +194,15 @@ void
 print_gen_head(struct html *h)
 {
 	struct htmlpair	 tag[4];
+	struct tag	*t;
 
-	tag[0].key = ATTR_HTTPEQUIV;
-	tag[0].val = "Content-Type";
-	tag[1].key = ATTR_CONTENT;
-	tag[1].val = "text/html; charset=utf-8";
-	print_otag(h, TAG_META, 2, tag);
+	tag[0].key = ATTR_CHARSET;
+	tag[0].val = "utf-8";
+	print_otag(h, TAG_META, 1, tag);
 
-	tag[0].key = ATTR_NAME;
-	tag[0].val = "resource-type";
-	tag[1].key = ATTR_CONTENT;
-	tag[1].val = "document";
-	print_otag(h, TAG_META, 2, tag);
+	t = print_otag(h, TAG_STYLE, 0, NULL);
+	print_text(h, "table.head, table.foot { width: 100%; }\n");
+	print_tagq(h, t);
 
 	if (h->style) {
 		tag[0].key = ATTR_REL;
@@ -324,6 +322,37 @@ html_strlen(const char *cp)
 }
 
 static int
+print_escape(char c)
+{
+
+	switch (c) {
+	case '<':
+		printf("&lt;");
+		break;
+	case '>':
+		printf("&gt;");
+		break;
+	case '&':
+		printf("&amp;");
+		break;
+	case '"':
+		printf("&quot;");
+		break;
+	case ASCII_NBRSP:
+		putchar('-');
+		break;
+	case ASCII_HYPH:
+		putchar('-');
+		/* FALLTHROUGH */
+	case ASCII_BREAK:
+		break;
+	default:
+		return(0);
+	}
+	return(1);
+}
+
+static int
 print_encode(struct html *h, const char *p, int norecurse)
 {
 	size_t		 sz;
@@ -350,30 +379,8 @@ print_encode(struct html *h, const char *p, int norecu
 		if ('\0' == *p)
 			break;
 
-		switch (*p++) {
-		case '<':
-			printf("&lt;");
+		if (print_escape(*p++))
 			continue;
-		case '>':
-			printf("&gt;");
-			continue;
-		case '&':
-			printf("&amp;");
-			continue;
-		case '"':
-			printf("&quot;");
-			continue;
-		case ASCII_NBRSP:
-			putchar('-');
-			continue;
-		case ASCII_HYPH:
-			putchar('-');
-			/* FALLTHROUGH */
-		case ASCII_BREAK:
-			continue;
-		default:
-			break;
-		}
 
 		esc = mandoc_escape(&p, &seq, &len);
 		if (ESCAPE_ERROR == esc)
@@ -408,21 +415,22 @@ print_encode(struct html *h, const char *p, int norecu
 
 		switch (esc) {
 		case ESCAPE_UNICODE:
-			/* Skip passed "u" header. */
+			/* Skip past "u" header. */
 			c = mchars_num2uc(seq + 1, len - 1);
 			if ('\0' != c)
 				printf("&#x%x;", c);
 			break;
 		case ESCAPE_NUMBERED:
 			c = mchars_num2char(seq, len);
-			if ('\0' != c)
+			if ( ! ('\0' == c || print_escape(c)))
 				putchar(c);
 			break;
 		case ESCAPE_SPECIAL:
 			c = mchars_spec2cp(h->symtab, seq, len);
 			if (c > 0)
 				printf("&#%d;", c);
-			else if (-1 == c && 1 == len)
+			else if (-1 == c && 1 == len &&
+			    !print_escape(*seq))
 				putchar((int)*seq);
 			break;
 		case ESCAPE_NOSPACE:
@@ -484,14 +492,6 @@ print_otag(struct html *h, enum htmltag tag,
 	for (i = 0; i < sz; i++)
 		print_attr(h, htmlattrs[p[i].key], p[i].val);
 
-	/* Add non-overridable attributes. */
-
-	if (TAG_HTML == tag && HTML_XHTML_1_0_STRICT == h->type) {
-		print_attr(h, "xmlns", "http://www.w3.org/1999/xhtml");
-		print_attr(h, "xml:lang", "en");
-		print_attr(h, "lang", "en");
-	}
-
 	/* Accommodate for XML "well-formed" singleton escaping. */
 
 	if (HTML_AUTOCLOSE & htmltags[tag].flags)
@@ -527,26 +527,8 @@ print_ctag(struct html *h, enum htmltag tag)
 void
 print_gen_decls(struct html *h)
 {
-	const char	*doctype;
-	const char	*dtd;
-	const char	*name;
 
-	switch (h->type) {
-	case HTML_HTML_4_01_STRICT:
-		name = "HTML";
-		doctype = "-//W3C//DTD HTML 4.01//EN";
-		dtd = "http://www.w3.org/TR/html4/strict.dtd";
-		break;
-	default:
-		puts("<?xml version=\"1.0\" encoding=\"UTF-8\"?>");
-		name = "html";
-		doctype = "-//W3C//DTD XHTML 1.0 Strict//EN";
-		dtd = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd";
-		break;
-	}
-
-	printf("<!DOCTYPE %s PUBLIC \"%s\" \"%s\">\n",
-	    name, doctype, dtd);
+	puts("<!DOCTYPE html>");
 }
 
 void
@@ -750,6 +732,8 @@ bufcat_su(struct html *h, const char *p, const struct 
 	v = su->scale;
 	if (SCALE_MM == su->unit && 0.0 == (v /= 100.0))
 		v = 1.0;
+	else if (SCALE_BU == su->unit)
+		v /= 24.0;
 
 	bufcat_fmt(h, "%s: %.2f%s;", p, v, roffscales[su->unit]);
 }