#!/bin/bash
#########################################################
#Author: Marie D.
#
#(File)->String(s)
#
#		**Purpose:**
#		Given a textfile, the script returns the text 
#		tokenized and sentence split
#
#		**Usage:**
#		$sh baseline.sh myfile.txt
#
#		**Example of desired output:**
#		Hello
#		word
#		!
#
#		How
#		are
#		you
#		?
#
#########################################################
#
#

echo "This program will tokenize and sentence split '$1' and output '$2'."
sed 's/ /\n/g' $1 | sed -r 's/([\.\!\?])/\n&\n/g' > $2 #1) | #2)

##Tokenisation##
#1) Substitute sed command that replaces every space by a carriage return

##Sentence splitting##
#2) sed command that seperates ponctuations and adds a carriage return after them.