In the past, generating comment nodes stopped at the .TH or .Dd

macro, which is usually close to the beginning of the file, right
after the Copyright header comments.  But espie@ found horrible
input files in the textproc/fstrcmp port that generate lots of parse
nodes before even getting to the header macro.  In some formatters,
comment nodes after some kinds of real content triggered assertions.

So make sure generation of comment nodes stops once real content is
encountered.

2 files changed, 10 insertions, 5 deletions

diff --git a/mandoc_parse.h b/mandoc_parse.h
index 61341f0d..b8b29dd9 100644
--- a/mandoc_parse.h
+++ b/mandoc_parse.h
@@ -1,4 +1,4 @@
-/*	$Id: mandoc_parse.h,v 1.4 2018/12/30 00:49:55 schwarze Exp $ */
+/*	$Id: mandoc_parse.h,v 1.5 2019/11/09 14:39:49 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2014,2015,2016,2017,2018 Ingo Schwarze <schwarze@openbsd.org>
@@ -29,6 +29,7 @@
 #define	MPARSE_UTF8	(1 << 4)  /* accept UTF-8 input */
 #define	MPARSE_LATIN1	(1 << 5)  /* accept ISO-LATIN-1 input */
 #define	MPARSE_VALIDATE	(1 << 6)  /* call validation functions */
+#define	MPARSE_COMMENT	(1 << 7)  /* save comments in the tree */
 
 
 struct	roff_meta;
diff --git a/roff.c b/roff.c
index f26d9f01..ca53b5f9 100644
--- a/roff.c
+++ b/roff.c
@@ -1,4 +1,4 @@
-/*	$Id: roff.c,v 1.366 2019/07/01 22:56:24 schwarze Exp $ */
+/*	$Id: roff.c,v 1.367 2019/11/09 14:39:49 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2012, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2015, 2017-2019 Ingo Schwarze <schwarze@openbsd.org>
@@ -771,6 +771,7 @@ void
 roff_reset(struct roff *r)
 {
 	roff_free1(r);
+	r->options |= MPARSE_COMMENT;
 	r->format = r->options & (MPARSE_MDOC | MPARSE_MAN);
 	r->control = '\0';
 	r->escape = '\\';
@@ -800,7 +801,7 @@ roff_alloc(int options)
 
 	r = mandoc_calloc(1, sizeof(struct roff));
 	r->reqtab = roffhash_alloc(0, ROFF_RENAMED);
-	r->options = options;
+	r->options = options | MPARSE_COMMENT;
 	r->format = options & (MPARSE_MDOC | MPARSE_MAN);
 	r->mstackpos = -1;
 	r->rstackpos = -1;
@@ -1246,7 +1247,7 @@ roff_expand(struct roff *r, struct buf *buf, int ln, int pos, char newesc)
 		 * in the syntax tree.
 		 */
 
-		if (newesc != ASCII_ESC && r->format == 0) {
+		if (newesc != ASCII_ESC && r->options & MPARSE_COMMENT) {
 			while (*ep == ' ' || *ep == '\t')
 				ep--;
 			ep[1] = '\0';
@@ -1815,8 +1816,10 @@ roff_parseln(struct roff *r, int ln, struct buf *buf, int *offs)
 		roff_addtbl(r->man, ln, r->tbl);
 		return e;
 	}
-	if ( ! ctl)
+	if ( ! ctl) {
+		r->options &= ~MPARSE_COMMENT;
 		return roff_parsetext(r, buf, pos, offs) | e;
+	}
 
 	/* Skip empty request lines. */
 
@@ -1839,6 +1842,7 @@ roff_parseln(struct roff *r, int ln, struct buf *buf, int *offs)
 
 	/* No scope is open.  This is a new request or macro. */
 
+	r->options &= ~MPARSE_COMMENT;
 	spos = pos;
 	t = roff_parse(r, buf->buf, &pos, ln, ppos);