Files
paperless-prod/scripts/remove-blank-pages.sh
Bastian Schnorbus 5941117b86 update
2025-05-04 16:01:16 +02:00

52 lines
1.2 KiB
Bash
Executable File

#!/bin/bash
# https://github.com/paperless-ngx/paperless-ngx/wiki/Pre-Consume-Script-Examples#removing-blank-pages
# set -x -e -o pipefail
set -e -o pipefail
export LC_ALL=C
#IN="$1"
IN="$DOCUMENT_WORKING_PATH"
# Check for PDF format
TYPE=$(file -b "$IN")
if [ "${TYPE%%,*}" != "PDF document" ]; then
>&2 echo "Skipping $IN - non PDF [$TYPE]."
exit 0
fi
# PDF file - proceed
#PAGES=$(pdfinfo "$IN" | grep ^Pages: | tr -dc '0-9')
PAGES=$(pdfinfo "$IN" | awk '/Pages:/ {print $2}')
>&2 echo Total pages $PAGES
# Threshold for HP scanners
# THRESHOLD=1
# Threshold for Lexmar MC2425
THRESHOLD=0.8
non_blank() {
for i in $(seq 1 $PAGES) ; do
PERCENT=$(gs -o - -dFirstPage=${i} -dLastPage=${i} -sDEVICE=ink_cov "${IN}" | grep CMYK | nawk 'BEGIN { sum=0; } {sum += $1 + $2 + $3 + $4;} END { printf "%.5f\n", sum } ')
>&2 echo -n "Color-sum in page $i is $PERCENT: "
if awk "BEGIN { exit !($PERCENT > $THRESHOLD) }"; then
echo $i
>&2 echo "Page added to document"
else
>&2 echo "Page removed from document"
fi
done
}
NON_BLANK=$(non_blank)
if [ -n "$NON_BLANK" ]; then
NON_BLANK=$(echo $NON_BLANK | tr ' ' ",")
qpdf "$IN" --warning-exit-0 --replace-input --pages . $NON_BLANK --
fi