From 182c503fdbbc1ce241cd9966f9402ed9ea0b2143 Mon Sep 17 00:00:00 2001
From: Bastian Dehn <hhaalo@arcor.de>
Date: Sun, 22 Dec 2024 10:49:51 +0100
Subject: [PATCH] add scan to pdf scripts

---
 scantopdf     | 141 +++++++++++++++++++++++++++++++++++++++++++++++++
 scantopdfbw   | 142 ++++++++++++++++++++++++++++++++++++++++++++++++++
 scantopdfgray | 142 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 425 insertions(+)
 create mode 100755 scantopdf
 create mode 100755 scantopdfbw
 create mode 100755 scantopdfgray

diff --git a/scantopdf b/scantopdf
new file mode 100755
index 0000000..2cba38f
--- /dev/null
+++ b/scantopdf
@@ -0,0 +1,141 @@
+#!/bin/bash
+#
+optimize()
+{
+	local input=$1
+	local output=$input-out
+
+	qpdf --linearize $input $output
+	mv $output $input
+}
+
+addocr()
+{
+	local input=$1
+	local output=$input-out
+	local error=""
+
+	echo $input
+	error=$(ocrmypdf -l deu $input $output 2>&1)
+
+	if [ -n "$(echo $error | grep offset)" ]; then
+		printf "%s: %s\n" $input $error >> $HOME/addocr-error.log
+	fi
+
+	if [ -f $output ]; then
+		mv $output $input
+		optimize $input
+	fi
+}
+
+createonepdf()
+{
+	local output=$1
+
+	for i in scanned*.tiff; do
+		tiff2pdf $i -o ${i/.tiff/.pdf}
+		rm $i
+	done
+
+	pdftk scanned*.pdf output $output
+	rm scanned*.pdf
+	addocr $output
+}
+
+createpdf()
+{
+	local start=$1
+	local end=$2
+	local countno=
+	local pdfs=()
+
+	for i in $(seq $start $end); do
+		countno=$(printf "%02d" $i)
+		pdfs=$(echo $pdfs "scanned$countno.pdf")
+	done
+
+	pdftk $pdfs output out$(printf "%02d" $start).pdf
+	addocr out$(printf "%02d" $start).pdf
+
+	for i in $pdfs; do
+		rm $i
+	done
+}
+
+detectsplit()
+{
+	local pdf=$1
+	local trenn=
+
+	trenn=$(zbarimg --raw --quiet $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	trenn=$(dmtxread $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	echo "false"
+}
+
+createmultipdfs()
+{
+	local trenn=$1
+	local startcount=1
+	local endcount=1
+	local pdf=
+
+	for i in scanned*.tiff; do
+		pdf=${i/.tiff/.pdf}
+		tiff2pdf $i -o $pdf
+		trenn=$(detectsplit $pdf)
+		rm $i
+		if [ "$trenn" == "true" ]; then
+			createpdf $startcount $((endcount - 1))
+			startcount=$((endcount + 1))
+			rm $pdf
+		fi
+		((endcount++))
+	done
+}
+
+main()
+{
+	if [ -z "$1" ]; then
+		echo "ERROR: no page count"
+		exit 1
+	fi
+
+	if [ -z "$2" ]; then
+		echo "ERROR: no pdf file name"
+		exit 1
+	fi
+
+	local pagecount=$1
+	local output=$2
+
+	scanimage --resolution=300 \
+		--skip-blank-pages=yes \
+		--format=tiff \
+		--batch-count=$pagecount \
+		--batch-increment=1 \
+		--batch=scanned%02d.tiff
+
+	if [ $? -gt 0 ]; then
+		echo "ERROR: scan error"
+		exit 1
+	fi
+
+	if [ "$output" == "multi" ]; then
+		createmultipdfs $pagecount
+		exit 0
+	fi
+
+	createonepdf $output
+}
+
+main $*
diff --git a/scantopdfbw b/scantopdfbw
new file mode 100755
index 0000000..f149327
--- /dev/null
+++ b/scantopdfbw
@@ -0,0 +1,142 @@
+#!/bin/bash
+#
+optimize()
+{
+	local input=$1
+	local output=$input-out
+
+	qpdf --linearize $input $output
+	mv $output $input
+}
+
+addocr()
+{
+	local input=$1
+	local output=$input-out
+	local error=""
+
+	echo $input
+	error=$(ocrmypdf -l deu $input $output 2>&1)
+
+	if [ -n "$(echo $error | grep offset)" ]; then
+		printf "%s: %s\n" $input $error >> $HOME/addocr-error.log
+	fi
+
+	if [ -f $output ]; then
+		mv $output $input
+		optimize $input
+	fi
+}
+
+createonepdf()
+{
+	local output=$1
+
+	for i in scanned*.tiff; do
+		tiff2pdf $i -o ${i/.tiff/.pdf}
+		rm $i
+	done
+
+	pdftk scanned*.pdf output $output
+	rm scanned*.pdf
+	addocr $output
+}
+
+createpdf()
+{
+	local start=$1
+	local end=$2
+	local countno=
+	local pdfs=()
+
+	for i in $(seq $start $end); do
+		countno=$(printf "%02d" $i)
+		pdfs=$(echo $pdfs "scanned$countno.pdf")
+	done
+
+	pdftk $pdfs output out$(printf "%02d" $start).pdf
+	addocr out$(printf "%02d" $start).pdf
+
+	for i in $pdfs; do
+		rm $i
+	done
+}
+
+detectsplit()
+{
+	local pdf=$1
+	local trenn=
+
+	trenn=$(zbarimg --raw --quiet $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	trenn=$(dmtxread $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	echo "false"
+}
+
+createmultipdfs()
+{
+	local trenn=$1
+	local startcount=1
+	local endcount=1
+	local pdf=
+
+	for i in scanned*.tiff; do
+		pdf=${i/.tiff/.pdf}
+		tiff2pdf $i -o $pdf
+		trenn=$(detectsplit $pdf)
+		rm $i
+		if [ "$trenn" == "true" ]; then
+			createpdf $startcount $((endcount - 1))
+			startcount=$((endcount + 1))
+			rm $pdf
+		fi
+		((endcount++))
+	done
+}
+
+main()
+{
+	if [ -z "$1" ]; then
+		echo "ERROR: no page count"
+		exit 1
+	fi
+
+	if [ -z "$2" ]; then
+		echo "ERROR: no pdf file name"
+		exit 1
+	fi
+
+	local pagecount=$1
+	local output=$2
+
+	scanimage --resolution=300 \
+		--mode=BW \
+		--skip-blank-pages=yes \
+		--format=tiff \
+		--batch-count=$1 \
+		--batch-increment=1 \
+		--batch=scanned%02d.tiff
+
+	if [ $? -gt 0 ]; then
+		echo "ERROR: scan error"
+		exit 1
+	fi
+
+	if [ "$output" == "multi" ]; then
+		createmultipdfs $pagecount
+		exit 0
+	fi
+
+	createonepdf $output
+}
+
+main $*
diff --git a/scantopdfgray b/scantopdfgray
new file mode 100755
index 0000000..2abc9ab
--- /dev/null
+++ b/scantopdfgray
@@ -0,0 +1,142 @@
+#!/bin/bash
+#
+optimize()
+{
+	local input=$1
+	local output=$input-out
+
+	qpdf --linearize $input $output
+	mv $output $input
+}
+
+addocr()
+{
+	local input=$1
+	local output=$input-out
+	local error=""
+
+	echo $input
+	error=$(ocrmypdf -l deu $input $output 2>&1)
+
+	if [ -n "$(echo $error | grep offset)" ]; then
+		printf "%s: %s\n" $input $error >> $HOME/addocr-error.log
+	fi
+
+	if [ -f $output ]; then
+		mv $output $input
+		optimize $input
+	fi
+}
+
+createonepdf()
+{
+	local output=$1
+
+	for i in scanned*.tiff; do
+		tiff2pdf $i -o ${i/.tiff/.pdf}
+		rm $i
+	done
+
+	pdftk scanned*.pdf output $output
+	rm scanned*.pdf
+	addocr $output
+}
+
+createpdf()
+{
+	local start=$1
+	local end=$2
+	local countno=
+	local pdfs=()
+
+	for i in $(seq $start $end); do
+		countno=$(printf "%02d" $i)
+		pdfs=$(echo $pdfs "scanned$countno.pdf")
+	done
+
+	pdftk $pdfs output out$(printf "%02d" $start).pdf
+	addocr out$(printf "%02d" $start).pdf
+
+	for i in $pdfs; do
+		rm $i
+	done
+}
+
+detectsplit()
+{
+	local pdf=$1
+	local trenn=
+
+	trenn=$(zbarimg --raw --quiet $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	trenn=$(dmtxread $pdf)
+	if [ "$trenn" == "Trennblatt" ]; then
+		echo "true"
+		return
+	fi
+
+	echo "false"
+}
+
+createmultipdfs()
+{
+	local trenn=$1
+	local startcount=1
+	local endcount=1
+	local pdf=
+
+	for i in scanned*.tiff; do
+		pdf=${i/.tiff/.pdf}
+		tiff2pdf $i -o $pdf
+		trenn=$(detectsplit $pdf)
+		rm $i
+		if [ "$trenn" == "true" ]; then
+			createpdf $startcount $((endcount - 1))
+			startcount=$((endcount + 1))
+			rm $pdf
+		fi
+		((endcount++))
+	done
+}
+
+main()
+{
+	if [ -z "$1" ]; then
+		echo "ERROR: no page count"
+		exit 1
+	fi
+
+	if [ -z "$2" ]; then
+		echo "ERROR: no pdf file name"
+		exit 1
+	fi
+
+	local pagecount=$1
+	local output=$2
+
+	scanimage --resolution=300 \
+		--mode=Gray \
+		--skip-blank-pages=yes \
+		--format=tiff \
+		--batch-count=$1 \
+		--batch-increment=1 \
+		--batch=scanned%02d.tiff
+
+	if [ $? -gt 0 ]; then
+		echo "ERROR: scan error"
+		exit 1
+	fi
+
+	if [ "$output" == "multi" ]; then
+		createmultipdfs $pagecount
+		exit 0
+	fi
+
+	createonepdf $output
+}
+
+main $*
-- 
2.39.5