Created
April 16, 2017 18:29
-
-
Save gordonmurray/58cb12f2f58fa59259bc73942175e2eb to your computer and use it in GitHub Desktop.
A small script to take a larger text based file and break it down to several smaller files
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env bash | |
# A small script to take a larger text based file and break it down to several smaller files | |
# of 500 lines each for easier processing, keeping the headings at the top of each file | |
FILENAME=${1} | |
if [ -z ${FILENAME} ]; then | |
echo "Please provide a filename, for example: bash split.sh /path/to/data.csv"; | |
else | |
CLEAN_FILENAME="${FILENAME/-*\./.}" | |
CLEAN_FILENAME=${CLEAN_FILENAME%.*} | |
tail -n +2 ${FILENAME} | split -a 5 -d -l 500 - ${CLEAN_FILENAME}_ | |
for file in ${CLEAN_FILENAME}_* | |
do | |
head -n 1 ${FILENAME} > tmp_file | |
cat ${file} >> tmp_file | |
mv -f tmp_file ${file}.csv | |
rm ${file} | |
done | |
echo ${CLEAN_FILENAME} | |
fi |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment