From 2fb552ed8a90a9adb6ab1a9397567eb77dfbd26b Mon Sep 17 00:00:00 2001
From: btmccrea <sharkmccoy@gmail.com>
Date: Wed, 23 Dec 2020 16:26:31 -0500
Subject: [PATCH] Finished Find Addresses.  Starte Remove and Sort scripts

---
 Find_Missing_Addresses.sh | 21 +++++++++++++--------
 Removing_Files.sh         | 19 +++++++++++++++++++
 Sort_and_Merge_Files.sh   | 27 +++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 8 deletions(-)
 create mode 100644 Removing_Files.sh
 create mode 100644 Sort_and_Merge_Files.sh

diff --git a/Find_Missing_Addresses.sh b/Find_Missing_Addresses.sh
index 553c0d6..cf307a1 100755
--- a/Find_Missing_Addresses.sh
+++ b/Find_Missing_Addresses.sh
@@ -1,22 +1,23 @@
 #!/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/
+    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/Documents/output/
+    read OUTPUTFOLDER
+    #OUTPUTFOLDER=/home/btmccrea/Documents/output/
     if [ -d $PDFDIR ]; then
         break
         else 
@@ -24,19 +25,23 @@ do
     fi
 done
 
+#Create the csv and headers for the Addresses.  It is tab separated.
 touch "$OUTPUTFOLDER"Addresses.csv
-echo "File, User, Address" > "$OUTPUTFOLDER"Addresses.csv
+echo -e "File\tUser\tAddress" > "$OUTPUTFOLDER"Addresses.csv
 #FILES=$(ls $PDFDIR)
 cd $PDFDIR
 #echo $FILES
-#* represensts All files in the current directory
+#*.pdf represensts All files in the current directory with a pdf extention.
 for f in *.pdf ;
     do 
+        #pdftotext converst the file to text and places it in the file name temp
         pdftotext "$f" temp
+        #assigns the lines with relevant values to their variable
         USER=$(sed -n '13p' temp)
         ADDRESS1=$(sed -n '14p' temp)
         ADDRESS2=$(sed -n '15p' temp)
-        echo "$f, $USER, '$ADDRESS1 $ADDRESS2'" >> "$OUTPUTFOLDER"Addresses.csv
+        #Adds the row of variables to the csv.  >> appends to the file. \t represents tabs
+        echo -e "$f\t$USER\t$ADDRESS1 $ADDRESS2" >> "$OUTPUTFOLDER"Addresses.csv
     done
 exit
 
diff --git a/Removing_Files.sh b/Removing_Files.sh
new file mode 100644
index 0000000..9619424
--- /dev/null
+++ b/Removing_Files.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+#import list from csv
+echo "Please clear all feilds except for the file name feild from the csv."
+while IFS='\t' read (awk -F, 'NR > 1' { print $1})
+#cd to and then remove files
+
+#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
\ No newline at end of file
diff --git a/Sort_and_Merge_Files.sh b/Sort_and_Merge_Files.sh
new file mode 100644
index 0000000..30dedb1
--- /dev/null
+++ b/Sort_and_Merge_Files.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+
+#get directory for pdf files
+#get output directory for files
+
+#Get the location of the PDF files
+echo "What is the location of the PDF files" 
+read FILE
+
+for FILENAME in $FILE
+do
+#The next Line assigns the number of pages to the value LOCATION to be used for were the file goes
+	LOCATION=$(pdfinfo "$FILENAME" | grep Pages: | awk '{print $2}')
+#Test if the file exists and if it does move it to Temp.pdf to be merged back to its original location.  
+	if test -f /mnt/tmpfs/Statement-Pages-$LOCATION.pdf; then
+		mv /mnt/tmpfs/Statement-Pages-$LOCATION.pdf /mnt/tmpfs/temp.pdf
+	else
+	pdfunite "$FILENAME" /mnt/tmpfs/temp.pdf /mnt/tmpfs/Statement-Pages-$LOCATION.pdf
+#IF the file doesn't exist create the file with the merge.
+		pdfunite "$FILENAME" /mnt/tmpfs/Statement-Pages-$LOCATION.pdf
+	fi;
+#once everything else is doen Make the directory to place the files into 
+#and copy the finished files into it. 
+mkdir $FILE/Finished/
+cp -r /mnt/tmpfs/Statement-* $FILE/Finished/
+done
+exit
\ No newline at end of file