Skip carriage return before newline, if any.

As pointed out by Joerg Sonnenberger, this is useful
because we use mmap(3) and look for '\n' by hand.
"check it in" kristaps@

1 files changed, 20 insertions, 3 deletions

diff --git a/main.c b/main.c
index 6075d520..30aab3ad 100644
--- a/main.c
+++ b/main.c
@@ -1,7 +1,7 @@
 /*	$Id$ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
- * Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
+ * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>
  *
  * Permission to use, copy, modify, and distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -684,6 +684,16 @@ parsebuf(struct curparse *curp, struct buf blk, int start)
 		}
 
 		while (i < (int)blk.sz && (start || '\0' != blk.buf[i])) {
+
+			/*
+			 * When finding an unescaped newline character,
+			 * leave the character loop to process the line.
+			 * Skip a preceding carriage return, if any.
+			 */
+
+			if ('\r' == blk.buf[i] && i + 1 < (int)blk.sz &&
+			    '\n' == blk.buf[i + 1])
+				++i;
 			if ('\n' == blk.buf[i]) {
 				++i;
 				++lnn;
@@ -718,11 +728,18 @@ parsebuf(struct curparse *curp, struct buf blk, int start)
 				continue;
 			}
 
-			/* Found escape & at least one other char. */
+			/*
+			 * Found escape and at least one other character.
+			 * When it's a newline character, skip it.
+			 * When there is a carriage return in between,
+			 * skip that one as well.
+			 */
 
+			if ('\r' == blk.buf[i + 1] && i + 2 < (int)blk.sz &&
+			    '\n' == blk.buf[i + 2])
+				++i;
 			if ('\n' == blk.buf[i + 1]) {
 				i += 2;
-				/* Escaped newlines are skipped over */
 				++lnn;
 				continue;
 			}