From b2b6e0ad3078a4f11c7a17ad659fd2233d74ff32 Mon Sep 17 00:00:00 2001
From: Kuba <jakeic@st.amu.edu.pl>
Date: Tue, 21 Mar 2023 22:32:40 +0100
Subject: [PATCH] count number of occurances of each word in text

---
 analysis/word_freq.sh | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100755 analysis/word_freq.sh

diff --git a/analysis/word_freq.sh b/analysis/word_freq.sh
new file mode 100755
index 0000000..0abbf44
--- /dev/null
+++ b/analysis/word_freq.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+#calculate no occurances of each word
+bzcat $1 | tr -s '[:punct:][:space:]' '\n' | grep -E "^[^\x00-\x7F]*[[:alpha:]][^\x00-\x7F]*$" | sort | uniq -c | sort -nr > word_freq.txt
\ No newline at end of file