#!/bin/bash
infile=""
outfile=""
titleFile=""
outpath=""

getTitles() {
	cat $infile | \
		grep -A $(wc -l $_ | \
		awk '{print $1}') "Table of Contents" | \
		grep -B $(wc -l $_ | \
		awk '{print $1}') "How to Use this Book" | \
		grep -E "[\ \#\-\,\&\'\`\´\’\–A-Za-z0-9_]{1,999}\.{1,}" | \
		grep -v "Credits" | \
		grep -v "How to Use this Book" | \
		grep -Eo "^[\ \#\ffi\-\,\&\'\`\´\’\–A-Za-z0-9_]{1,999}[^.]" > $titleFile
}

fixScan(){
	sed -E s/ffi/ffi/gm $infile
}

GetListFromTitle() {
	local titlecount=$(wc -l $titleFile | awk '{print $1}')
	local currentlineinum=1
	while [ $currentlinenum -lt $titlecount ]; do
		local currentline=$(sed -n "$currentlinenum p")
		(($currentlinenum++))
		local nextline=$(sed -n "$currentlinenum p")
		grep -A $(wc - l $infile | awk '{print $1}') "$currentline" $infile | \
		grep -B $(wc - l $infile | awk '{print $1}') "$nextline" > "$path/$currentline.txt"
	done
}




echo "Fixing spelling from certain pdftotext bugs"
fixScan