improved handling of addresses and spaced them out to more columns

Find_Missing_Addresses.sh

@@ -30,7 +30,7 @@ done
 #Create the csv and headers for the Addresses.  It is tab separated.
 mkdir $OUTPUTFOLDER/Non_Blank
 touch $OUTPUTFOLDER/Non_Blank/Addresses.csv
-echo -e "File\tUser\tAddress" > $OUTPUTFOLDER/Non_Blank/kkAddresses.csv
+echo -e "File,User,Street,City,State,Zip" > $OUTPUTFOLDER/Non_Blank/Addresses.csv
 
 #Create csv with all the files with missing addresses
 mkdir $OUTPUTFOLDER/Missing_Addresses
@@ -40,14 +40,13 @@ echo -e "File\tUser" > $OUTPUTFOLDER/Missing_Addresses/Missing_Addresses.csv
 
 cd $PDFDIR
 #FOLDER=$(ls | grep *.pdf)
-echo $FOLDER
+#echo $FOLDER
 #*.pdf represensts All files in the current directory with a pdf extention.
 for f in $PDFDIR/*
 do 
     echo "Processing file $f."
     #pdftotext converst the file to text and places it in the file name temp
     pdftotext "$f" - > TEMP
-    #cat TEMP
     #assigns the lines with relevant values to their variable
     USER=$(sed -n '12p' TEMP)
     ADDRESS1=$(sed -n '13p' TEMP)
@@ -62,7 +61,14 @@ do
         echo -e "$f\t$USER" >> "$OUTPUTFOLDER"/Missing_Addresses/Missing_Addresses.csv
         #Adds the row of variables to the csv.  >> appends to the file. \t represents tabs
     else
-        echo -e "$f\t$USER\t$ADDRESS1 $ADDRESS2" >> $OUTPUTFOLDER/Non_Blank/Addresses.csv
+    # Split Addresses 
+        CITY=$(echo $ADDRESS2 | cut -d, -f1)
+        ADDRESS2=$(echo $ADDRESS2 | sed -e "s/$CITY, //")
+
+        STATE=$(echo $ADDRESS2 | cut -d" " -f1)
+        ZIP=$(echo $ADDRESS2 | cut -d" " -f2)
+        
+        echo -e "$f,$USER,$ADDRESS1,$CITY,$STATE,$ZIP" >> $OUTPUTFOLDER/Non_Blank/Addresses.csv
         cp "$f" $OUTPUTFOLDER/Non_Blank/
         echo -e "Copying file to Non_Blank"
     fi