From 125e938ec9e8effca3345cc446fd4b80a825c63c Mon Sep 17 00:00:00 2001
From: Jason Woofenden <jason@jasonwoof.com>
Date: Thu, 8 Nov 2012 02:34:59 -0500
Subject: [PATCH] script to find word-frequency of tree of files

---
 word-frequency-here.bash |   13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100755 word-frequency-here.bash

diff --git a/word-frequency-here.bash b/word-frequency-here.bash
new file mode 100755
index 0000000..ee16c58
--- /dev/null
+++ b/word-frequency-here.bash
@@ -0,0 +1,13 @@
+#!/bin/bash
+
+find . -type f -print0 \
+	| xargs -0 grep -I --no-filename -v '(notice)' \
+	| sed -e 's/<[^>]*>//g; s/&nbsp;/ /g; s/&[nm]dash;/-/' \
+	| sed -ne "s/^(..:..:.. ..) [a-zA-Z0-9@ _.-]\{1,25\}: \(.*\)$/\1/p" \
+	| perl -0777 -p -e's/\s+/\n/mg' \
+	| grep -v '^&.*;$' \
+	| sed -e 's/^\W\+//g; s/\W\+$//g' \
+	| grep '^[a-z.'\''-]\{3,16\}$' \
+	| sort \
+	| uniq -c \
+	| sort -nr
-- 
1.7.10.4