From 94ad9332c0a8213ad384007707d68ac8fd1810cb Mon Sep 17 00:00:00 2001
From: Tom Ryder <tom@sanctum.geek.nz>
Date: Tue, 8 Aug 2017 10:45:17 +1200
Subject: Nicer handling of RFC control chars

---
 bin/rfct.awk | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'bin')

diff --git a/bin/rfct.awk b/bin/rfct.awk
index 5ceef43f..230ac42c 100644
--- a/bin/rfct.awk
+++ b/bin/rfct.awk
@@ -6,9 +6,12 @@ BEGIN {
     ORS = "\n\n"
 }
 
-# Skip paragraphs with ^L chars in them
-# We have to be literal here due to mawk's failures
-// { next }
+# Skip paragraphs with ^L chars in them, as they likely contain headers and
+# footers
+/\f/ { next }
 
-# If there's anything left, print it
+# Strip out other control characters, but allow newline and tab
+{ gsub(/[\a\b\r\v]/, "") }
+
+# If there's anything left after tha, print it
 length($0)
-- 
cgit v1.2.3