From 5fc124a9016cb3561059b1edc375bc4385969d3a Mon Sep 17 00:00:00 2001
From: jhawk <jhawk@NetBSD.org>
Date: Mon, 3 Mar 2003 01:13:36 +0000
Subject: [PATCH] Parse HTML tables from NANPA.COM (used by nanpa.awk to
 produce na.phone)

---
 share/misc/nanpa.sed | 48 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 share/misc/nanpa.sed

diff --git a/share/misc/nanpa.sed b/share/misc/nanpa.sed
new file mode 100644
index 000000000000..3de0db0cc3a7
--- /dev/null
+++ b/share/misc/nanpa.sed
@@ -0,0 +1,48 @@
+# $NetBSD: nanpa.sed,v 1.1 2003/03/03 01:13:36 jhawk Exp $
+#
+# Parse HTML tables output by 
+#   http://docs.nanpa.com/cgi-bin/npa_reports/nanpa
+# Specifically, for each html table row (TR),
+# print the <TD> elements seperated by colons.
+#
+# This could break on HTML comments.
+#
+:top
+#				Strip ^Ms
+s/
//g
+#				Join all lines with unterminated HTML tags
+/<[^>]*$/{
+	N
+	b top
+}
+#				Replace all </TR> with EOL tag
+s;</[Tt][Rr]>;$;g
+# 				Join lines with only <TR>.
+/<[Tt][Rr][^>]*>$/{
+	N
+	s/\n//g
+	b top
+}
+#				Also, join all lines starting with <TR>.
+/<[TtRr][^>]*>[^$]*$/{
+	N
+	s/\n//g
+	b top
+}
+#				Remove EOL markers
+s/\$$//
+#				Remove lines not starting with <TR>
+/<[Tt][Rr][^>]*>/!d
+#				Replace all <TD> with colon
+s/[ 	]*<TD[^>]*> */:/g
+#				Strip all HTML tags
+s/<[^>]*>//g
+#				Handle HTML characters
+s/&nbsp;/ /g
+#				Compress spaces/tabs
+s/[ 	][ 	]*/ /g
+#				Strip leading colons
+s/^://
+#				Strip leading/trailing whitespace
+s/^ //
+s/ $//