splitcsv

#!/bin/bash

# Updates at:
# https://github.com/johnkramlich/splitcsv

function print_usage {
	appname=`basename ${0}`
	echo "Usage: ${appname} [path] [max lines] [optional prefix]"
	echo ""
	echo "Arguments:"
	echo "    path      : the path to the CSV file with the first line being column headings"
	echo "    max lines : Max number of lines per split file, e.g. 1000"
	echo "    prefix    : Optional prefix for output files, default value is split_"
	echo ""
	echo "Split a CSV file that contains column headings as the first line"
	echo "into multiple smaller files with the first line being the column headings."
	echo "This script can be useful in importing a subset of a large dataset, or breaking"
	echo "an input into smaller batches."
	echo ""
	echo "Examples:"
	echo ""
	echo "${appname} input.csv 1000"
	echo "   Split input.csv into multiple smaller csv files, each no longer"
	echo "   than 1000 lines"
	echo ""
	echo "${appname} input.csv 200 sub_"
	echo "   Split input.csv into multiple smaller csv files, each no longer"
	echo "   than 200 lines in length, prefixed with sub_"
	echo ""
}

if [ "$#" -eq 0 ]; then
	print_usage
	exit
fi

if [ "$#" -eq 3 ]; then
	prefix="$3";
else
	prefix="split_";
fi

# Might be used later to automatically append the correct file extension
filename=`basename ${1}`
extension="${filename##*.}"
filename="${filename%.*}"

tail -n +2 $1 | split -l $2 - $prefix
for file in $prefix*
do
    head -n 1 $1 > tmp_file
    cat $file >> tmp_file
    mv -f tmp_file $file
done