===================================================================
RCS file: /cvs/docbook2mdoc/parse.c,v
retrieving revision 1.8
retrieving revision 1.9
diff -u -p -r1.8 -r1.9
--- docbook2mdoc/parse.c	2019/04/02 13:11:09	1.8
+++ docbook2mdoc/parse.c	2019/04/02 15:53:02	1.9
@@ -1,4 +1,4 @@
-/* $Id: parse.c,v 1.8 2019/04/02 13:11:09 schwarze Exp $ */
+/* $Id: parse.c,v 1.9 2019/04/02 15:53:02 schwarze Exp $ */
 /*
  * Copyright (c) 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2019 Ingo Schwarze <schwarze@openbsd.org>
@@ -189,6 +189,62 @@ static	const struct element elements[] = {
 	{ NULL,			NODE_IGNORE }
 };
 
+struct	entity {
+	const char	*name;
+	const char	*roff;
+};
+
+/*
+ * XML character entity references found in the wild.
+ * Those that don't have an exact mandoc_char(7) representation
+ * are approximated, and the desired codepoint is given as a comment.
+ * Encoding them as \\[u...] would leave -Tascii out in the cold.
+ */
+static	const struct entity entities[] = {
+	{ "alpha",	"\\(*a" },
+	{ "amp",	"&" },
+	{ "apos",	"'" },
+	{ "auml",	"\\(:a" },
+	{ "beta",	"\\(*b" },
+	{ "circ",	"^" },      /* U+02C6 */
+	{ "copy",	"\\(co" },
+	{ "dagger",	"\\(dg" },
+	{ "Delta",	"\\(*D" },
+	{ "eacute",	"\\('e" },
+	{ "emsp",	"\\ " },    /* U+2003 */
+	{ "gt",		">" },
+	{ "hairsp",	"\\^" },
+	{ "kappa",	"\\(*k" },
+	{ "larr",	"\\(<-" },
+	{ "ldquo",	"\\(lq" },
+	{ "le",		"\\(<=" },
+	{ "lowbar",	"_" },
+	{ "lsqb",	"[" },
+	{ "lt",		"<" },
+	{ "mdash",	"\\(em" },
+	{ "minus",	"\\-" },
+	{ "ndash",	"\\(en" },
+	{ "nbsp",	"\\ " },
+	{ "num",	"#" },
+	{ "oslash",	"\\(/o" },
+	{ "ouml",	"\\(:o" },
+	{ "percnt",	"%" },
+	{ "quot",	"\\(dq" },
+	{ "rarr",	"\\(->" },
+	{ "rArr",	"\\(rA" },
+	{ "rdquo",	"\\(rq" },
+	{ "reg",	"\\(rg" },
+	{ "rho",	"\\(*r" },
+	{ "rsqb",	"]" },
+	{ "sigma",	"\\(*s" },
+	{ "shy",	"\\&" },     /* U+00AD */
+	{ "tau",	"\\(*t" },
+	{ "tilde",	"\\[u02DC]" },
+	{ "times",	"\\[tmu]" },
+	{ "uuml",	"\\(:u" },
+	{ NULL,		NULL }
+};
+
 static void
 error_msg(struct parse *p, const char *fmt, ...)
 {
@@ -275,6 +331,52 @@ pnode_trim(struct pnode *pn)
 			break;
 }
 
+static void
+xml_entity(struct parse *p, const char *name)
+{
+	const struct entity	*entity;
+	struct pnode		*dat;
+
+	if (p->del > 0)
+		return;
+
+	if (p->cur == NULL) {
+		error_msg(p, "discarding entity before document: &%s;", name);
+		return;
+	}
+
+	/* Close out the text node, if there is one. */
+	if (p->cur->node == NODE_TEXT) {
+		pnode_trim(p->cur);
+		p->cur = p->cur->parent;
+	}
+
+	if (p->tree->flags & TREE_CLOSED && p->cur == p->tree->root)
+		warn_msg(p, "entity after end of document: &%s;", name);
+
+	for (entity = entities; entity->name != NULL; entity++)
+		if (strcmp(name, entity->name) == 0)
+			break;
+
+	if (entity->roff == NULL) {
+		error_msg(p, "unknown entity &%s;", name);
+		return;
+	}
+
+	/* Create, append, and close out an entity node. */
+	if ((dat = calloc(1, sizeof(*dat))) == NULL ||
+	    (dat->b = dat->real = strdup(entity->roff)) == NULL) {
+		perror(NULL);
+		exit(1);
+	}
+	dat->node = NODE_ESCAPE;
+	dat->bsz = strlen(dat->b);
+	dat->parent = p->cur;
+	TAILQ_INIT(&dat->childq);
+	TAILQ_INIT(&dat->attrq);
+	TAILQ_INSERT_TAIL(&p->cur->childq, dat, child);
+}
+
 /*
  * Begin an element.
  */
@@ -573,14 +675,14 @@ parse_file(struct parse *p, int fd, const char *fname)
 			}
 
 			/*
-			 * The following three cases (in_arg, in_tag,
-			 * and starting a tag) all parse a word or
-			 * quoted string.  If that extends beyond the
+			 * The following four cases (in_arg, in_tag, and
+			 * starting an entity or a tag) all parse a word
+			 * or quoted string.  If that extends beyond the
 			 * read buffer and the last read(2) still got
 			 * data, they all break out of the token loop
 			 * to request more data from the read loop.
 			 *
-			 * Also, they all detect self-closing tags,
+			 * Also, three of them detect self-closing tags,
 			 * those ending with "/>", setting the flag
 			 * elem_end and calling xml_elem_end() at the
 			 * very end, after handling the attribute value,
@@ -689,10 +791,21 @@ parse_file(struct parse *p, int fd, const char *fname)
 				if (elem_end)
 					xml_elem_end(p, b + poff);
 
-			/* Process text up to the next tag. */
+			/* Process an entity. */
 
+			} else if (b[poff] == '&') {
+				if (advance(p, b, rlen, &pend, ";") &&
+				    rsz > 0)
+					break;
+				b[pend] = '\0';
+				if (pend < rlen)
+					pend++;
+				xml_entity(p, b + poff + 1);
+
+			/* Process text up to the next tag or entity. */
+
 			} else {
-				if (advance(p, b, rlen, &pend, "<") == 0)
+				if (advance(p, b, rlen, &pend, "<&") == 0)
 					p->ncol--;
 				xml_char(p, b + poff, pend - poff);
 			}