UNIX for Dummies Questions & Answers

ls -R | grep .pdf > /tmp/dave_pdfs.out

# The Array
pdfs=("file1.pdf" "file2.pdf" "file3.pdf" "file4.pdf")

# Just a counter that gets incremented for each iteration
counter=1

# For every value in the array
for value in ${pdfs[@]}
do

# Tell the user which file is being searched for, and how far along in the overall process we are.
echo "Working on $value..."
echo "($counter of ${#pdfs[*]})"

# Add what is being searched for to the output file
echo "$value is linked to from" >> /tmp/dave_locations.out

# Find all .htm and .html files with the filename we are looking for in, and add it to the output file
find . -name "*.htm*" -exec grep -l $value {} \; >> /tmp/dave_locations.out

# Adding a space afterwards
echo " " >> /tmp/dave_locations.out

# Increment the counter.
counter=`expr $counter + 1`

done

find . -name "*.htm*" -exec grep -o "[a-zA-Z0-9_]\{1,\}\.pdf" {} \; > /tmp/dave.out

pdfs=("file1.pdf" "file2.pdf" "file3.pdf" "file4.pdf")

for value in ${pdfs[@]}
do

set | grep $value /tmp/dave.out

# If grep finds nothing...
if [ $? == 1 ]
then
  echo "$value" >> /tmp/dave_files.out
fi

done

if ! grep "$value" /tmp/dave.out >/dev/null
then
  echo "$value"" >>/tmp/dave_files.out
fi

fgrep -vxf pdfs.txt /tmp/dave.out >/tmp/dave_files.out

# Establishing a list of ALL PDFs

echo "Finding All PDFs..."
ls -R | grep .pdf > /tmp/pdfs/all_pdfs.out
echo "Done."

# Remove rubbish from list

echo "Removing Rubbish From List..."
sed 's|^\./[a-zA-Z0-9_ &./:]*$||g' /tmp/pdfs/all_pdfs.out > /tmp/pdfs/all_pdfs2.out
sed '/^$/d' /tmp/pdfs/all_pdfs2.out > /tmp/pdfs/all_pdfs.out
echo "Done."

# List all PDFs Linked to

echo "Gathering List of PDF Links..."
find . -name "*.htm*" -exec grep -o "[a-zA-Z0-9_]\{1,\}\.pdf" {} \; > /tmp/pdfs/all_links.out
find . -name "*.php" -exec grep -o "[a-zA-Z0-9_]\{1,\}\.pdf" {} \; >> /tmp/pdfs/all_links.out
echo "Done."

# Compare the two lists to see which aren't linked to (Thanks era)

echo "Establishing PDFs not Linked to..."
fgrep -vxf /tmp/pdfs/all_links.out /tmp/pdfs/all_pdfs.out > /tmp/pdfs/not_linked.out
echo "Done."

# Get full paths relative to the site root

echo "Gathering Full Paths Now..."
while read Value
do
  find . -name "$Value" >> /tmp/pdfs/not_linked_paths.out
done < /tmp/pdfs/not_linked.out
echo "Done."

# Attaching Real Full Path
sed 's/^\./\/home\/httpd\/site/g' /tmp/pdfs/not_linked_paths.out > /tmp/pdfs/not_linked_full_paths.out

# Archiving Files...
while read Value2
do
  cp "$Value2" /tmp/pdfs/backups/
  # mv "$Value2" /tmp/pdfs/backups/
done < /tmp/pdfs/not_linked_full_paths.out
echo "Done."

# mv is commented out until I've confirmed that it is ok with my manager. Just copying for now.

# Getting rid of the .out files.

echo "Cleaning Up..."
rm /tmp/pdfs/*.out
echo "Finished!"

# Finished.