1 files changed, 43 insertions, 0 deletions
diff --git a/rpkid/doc/tweak-doc.awk b/rpkid/doc/tweak-doc.awk
new file mode 100644
index 00000000..cd39a599
--- /dev/null
+++ b/rpkid/doc/tweak-doc.awk
@@ -0,0 +1,43 @@
+# $Id$
+#
+# Copyright (C) 2010  Internet Systems Consortium ("ISC")
+# 
+# Permission to use, copy, modify, and distribute this software for any
+# purpose with or without fee is hereby granted, provided that the above
+# copyright notice and this permission notice appear in all copies.
+# 
+# THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES WITH
+# REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
+# AND FITNESS.  IN NO EVENT SHALL ISC BE LIABLE FOR ANY SPECIAL, DIRECT,
+# INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
+# LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+# OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+# PERFORMANCE OF THIS SOFTWARE.
+#
+# Clean up html2text's output.  html2text is pretty good at the
+# impossible job of converting HTML to readable flat text, but has its
+# own peculiarities.  In particular, it tends to generate either too
+# few or too many blank lines, depending on how it's been configured.
+# Simplest fix is is to configure it to err on the side of too many
+# blank lines, then suppress the extraneous ones.
+#
+# We might add other fixups here later, but this will suffice for now.
+
+NF && want_blank {
+  print "";
+}
+
+NF {
+  seen_text = 1;
+  want_blank = 0;
+  print;
+}
+
+!NF && !seen_text {
+  next;
+}
+
+!NF && seen_text {
+  want_blank = 1;
+  next;
+}