Update file README.md

Find_Missing_Addresses.sh

@@ -0,0 +1,82 @@
+#!/bin/bash
+
+#Get the folder with the pdf documents in it.
+#echo ""
+#echo "This will sort out the addresses in all the Statement PDF's into 2 folders so that you can then run the Merge file."
+#echo "To get started please answer 2 questions."
+#while :
+#do 
+#    echo -e "Where is the directory with ALL the pdf statments?"
+#    read PDFDIR
+#    if [ -d $PDFDIR ]
+#    then
+#       break
+#        else 
+#        echo "Directory not found."
+#    fi
+#done
+#Get the folder for the output file. 
+#echo ""
+#while :
+#do 
+#    echo -e "What output directory do you want for the sorted pdf's? This will sort into 2 folders, Missing_Addresses and Address"
+#    read OUTPUTFOLDER
+#    if [ -d $OUTPUTFOLDER ]
+#    then
+#        break
+#        else 
+#        echo "Directory not found."
+#    fi
+#done
+
+#Create the csv and headers for the Addresses.  It is tab separated.
+mkdir $OUTPUTFOLDER/Addresses
+touch $OUTPUTFOLDER/Addresses/Addresses.csv
+echo -e "File,User,Street,City,State,Zip" > $OUTPUTFOLDER/Addresses/Addresses.csv
+
+#Create csv with all the files with missing addresses
+mkdir $OUTPUTFOLDER/Missing_Addresses
+touch $OUTPUTFOLDER/Missing_Addresses/Missing_Addresses.csv
+
+echo -e "File\tUser" > $OUTPUTFOLDER/Missing_Addresses/Missing_Addresses.csv
+
+cd $PDFDIR
+#FOLDER=$(ls | grep *.pdf)
+#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
+    #assigns the lines with relevant values to their variable
+    USER=$(sed -n '12p' TEMP)
+    ADDRESS1=$(sed -n '13p' TEMP)
+    ADDRESS2=$(sed -n '14p' TEMP)
+    echo -e "User is $USER"
+    echo -e "Address is $ADDRESS1 $ADDRESS2"
+    if [ -z "$ADDRESS1" ]
+    then 
+        #Move the file with the Missing addresses to the Missing Address folder and make an note in its csv.
+        echo "Copying file to the folder called Missing_Addresses"
+        cp "$f" "$OUTPUTFOLDER"/Missing_Addresses/
+        echo -e "$f\t$USER" >> "$OUTPUTFOLDER"/Missing_Addresses/Missing_Addresses.csv
+        #Adds the row of variables to the csv.  >> appends to the file. \t represents tabs
+    else
+    # Split Addresses 
+        CITY=$(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" >> $OUTPUTFOLDER/Addresses/Addresses.csv
+        cp "$f" $OUTPUTFOLDER/Addresses/
+        echo "Copying file to the folder called Addresses"
+    fi
+done
+echo "All Done!" You can find all the Files in $OUTPUTFOLDER!"
+echo " "
+echo " "
+
+exit

README.md

@@ -1,3 +1,11 @@
-# EOY PDF Sortandmerge
+# EOY PDF Sort & Merge
+
+## Prerequisite
+1. Linux for Windows Subsystem (WSL2)
+2. Ubuntu installed from Windows Store
+
+To start make sure all files are downloaded and in the same directory. Then run the application.
+
+  ./Run.sh
 
 Project to sort, filter, and merge pdf files. 

Removing_Files.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+#Get the folder with the pdf documents in it.
+while :
+do 
+    echo -e "What is the directory with the pdfs?"
+    #read PDFDIR
+    PDFDIR="/home/btmccrea/Downloads/pdfs"
+    if [ -d $PDFDIR ]
+    then
+        break
+        else 
+        echo -e "Directory not found."
+    fi
+done
+#Get the folder for the output file. 
+while :
+do 
+    echo -e "What is the output directory for the pdf's with missing addresses?"
+    #read OUTPUTFOLDER
+    OUTPUTFOLDER="/home/btmccrea/Downloads/output/Final"
+    if [ -d $OUTPUTFOLDER ]
+    then
+        break
+        else 
+        echo -e "Directory not found."
+    fi
+done
+#Get the folder with the csv
+while :
+do 
+    echo -e "What path and file with?"
+    #read CSVFILE
+    if [ -f $CSVFILE ]
+    then
+        break
+        else 
+        echo -e "File not found."
+    fi
+done
+
+#import list from csv
+echo "Processing csv."
+while IFS=$'\t' read -r  FILE
+do
+    echo "FILE $FILE"
+#    echo "user $USER"
+#    echo "match $MATCH"
+#    echo "${array[0]}"
+#    if [[ "$MATCH" == "Match-Mailable" ]]
+#    then 
+#
+#        echo -e "Processing file $FILE"lY 
+        cp $PDFDIR/"$FILE" $OUTPUTFOLDER
+#    else 
+#        echo "no match"
+#    fi
+done < /home/btmccrea/Downloads/Smarty_Streets.csv
+#FILE=$(cat /home/btmccrea/Downloads/Smarty_Streets.csv)
+#echo $FILE
+#IFS=$'\t'
+#for f in Smarty_Streets.csv
+#do 
+#    echo "doing file $f"
+#    cp $PDFDIR/"$f" $OUTPUTFOLDER
+#done
+
+#cd to and then remove files

Run.sh

@@ -0,0 +1,94 @@
+
+echo "Welcome! It must be the start of a new year! In order to get started with sorting and merging the PDF documents I need to know a little more information."
+echo
+echo
+read -p 'Where is the directory that has the PDF statments with address? ' PDFDIR
+#read PDFDIR
+#Get the folder for the output file. 
+echo
+read -p 'What output directory do you want for the sorted PDFs? ' OUTPUTFOLDER
+#read OUTPUTFOLDER
+echo
+echo "The PDFs statments are in $PDFDIR?"
+echo "The output folder will be $OUTPUTFOLDER."
+echo
+read -p "Press Enter to continue" </dev/tty
+echo
+
+
+#./Find_Missing_Addresses.sh $PDFDIR $OUTPUTFOLDER
+
+#Create the csv and headers for the Addresses.  It is tab separated.
+mkdir $OUTPUTFOLDER/Addresses
+touch $OUTPUTFOLDER/Addresses/Addresses.csv
+echo -e "File,User,Street,City,State,Zip" > $OUTPUTFOLDER/Addresses/Addresses.csv
+
+#Create csv with all the files with missing addresses
+mkdir $OUTPUTFOLDER/Missing_Addresses
+touch $OUTPUTFOLDER/Missing_Addresses/Missing_Addresses.csv
+
+echo -e "File\tUser" > $OUTPUTFOLDER/Missing_Addresses/Missing_Addresses.csv
+
+cd $PDFDIR
+#FOLDER=$(ls | grep *.pdf)
+#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
+    #assigns the lines with relevant values to their variable
+    USER=$(sed -n '12p' TEMP)
+    ADDRESS1=$(sed -n '13p' TEMP)
+    ADDRESS2=$(sed -n '14p' TEMP)
+    echo -e "User is $USER"
+    echo -e "Address is $ADDRESS1 $ADDRESS2"
+    if [ -z "$ADDRESS1" ]
+    then 
+        #Move the file with the Missing addresses to the Missing Address folder and make an note in its csv.
+        echo "Copying file to the folder called Missing_Addresses"
+        cp "$f" "$OUTPUTFOLDER"/Missing_Addresses/
+        echo -e "$f\t$USER" >> "$OUTPUTFOLDER"/Missing_Addresses/Missing_Addresses.csv
+        #Adds the row of variables to the csv.  >> appends to the file. \t represents tabs
+    else
+    # Split Addresses 
+        CITY=$(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" >> $OUTPUTFOLDER/Addresses/Addresses.csv
+        cp "$f" $OUTPUTFOLDER/Addresses/
+        echo "Copying file to the folder called Addresses"
+    fi
+done
+echo "All done sorting! You can find all the Files in $OUTPUTFOLDER!"
+echo
+echo
+read -r -p "Do you want to continue? [Y/n]" response
+response=${response,,} # tolower
+if [[ $response =~ ^(y| ) ]] || [[ -z $response ]]; then
+    cd $PDFDIR
+    for FILENAME in $PDFDIR/*
+        do
+	    echo $FILENAME
+#The next Line assigns the number of pages to the value LOCATION to be used for were the file goes
+	    LOCATION=$(pdfinfo "$FILENAME" | grep Pages: | awk '{print $2}')
+#Test if the file exists and if it does move it to Temp.pdf to be merged back to its original location.  
+	    if test -f $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	    then
+		    mv $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf $OUTPUTFOLDER/temp.pdf
+		    pdfunite "$FILENAME" $OUTPUTFOLDER/temp.pdf $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	    else
+		#IF the file doesn't exist create the file with the merge.
+		    pdfunite "$FILENAME" $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	fi
+done
+echo
+echo
+echo "All done, you can find the PDF statments at $OUTPUTFOLDER."
+echo
+echo
+exit

Sort_and_Merge_Files.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+
+#get directory for pdf files
+#get output directory for files
+
+
+#Get the folder with the pdf documents in it.
+#echo "This will take the PDF statements that have been sorted and will merge them into PDF files based on the numbers of pages in the statement."
+#echo ""
+#echo "Before we begin we need a little information."
+#echo ""
+#while :
+#do 
+#    echo "Where is the directory that has the PDF statments with address?"
+#    read PDFDIR
+#    if [ -d $PDFDIR ]
+#    then
+#        break
+#        else 
+#        echo "Directory not found."
+#    fi
+#done
+
+#Get the folder for the output file. 
+#while :
+#do 
+#    echo ""
+#    echo "What output directory do you want for the sorted PDF's?"
+#    read OUTPUTFOLDER
+#    #OUTPUTFOLDER="/home/btmccrea/Downloads/output"
+#    if [ -d $OUTPUTFOLDER ]
+#    then
+#        break
+#        else 
+#        echo "Directory not found."
+#    fi
+#done
+
+cd $PDFDIR
+for FILENAME in $PDFDIR/*
+do
+	echo $FILENAME
+#The next Line assigns the number of pages to the value LOCATION to be used for were the file goes
+	LOCATION=$(pdfinfo "$FILENAME" | grep Pages: | awk '{print $2}')
+#Test if the file exists and if it does move it to Temp.pdf to be merged back to its original location.  
+	if test -f $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	then
+		mv $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf $OUTPUTFOLDER/temp.pdf
+		pdfunite "$FILENAME" $OUTPUTFOLDER/temp.pdf $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	else
+		#IF the file doesn't exist create the file with the merge.
+		pdfunite "$FILENAME" $OUTPUTFOLDER/Statement-Pages-$LOCATION.pdf
+	fi
+
+done
+
+echo ""
+echo ""
+echo "All done, you can find the PDF statments at $OUTPUTFOLDER.
+echo ""
+echo ""
+exit