v/sane-scan-pdf
1
0
Fork 0
mirror of https://github.com/rocketraman/sane-scan-pdf.git synced 2025-05-16 23:50:39 -07:00
Code Issues Projects Releases Wiki Activity

Remove empty pages based on cmd line option

Browse Source
This commit is contained in:
Stefan Armbruster 2018-10-29 13:55:03 +01:00 committed by Raman Gupta
parent 349e0a5dea
commit 573b1df2da
3 changed files with 77 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -24,6 +24,7 @@ Tested and run regularly on Fedora, but should work on other distributions with
* pnmtops (netpbm-progs) * pnmtops (netpbm-progs)
* ps2pdf (ghostscript) * ps2pdf (ghostscript)
* pdfunite * pdfunite
* ImageMagick (if --skip-empty-pages) is used
### Optional ### Optional
@ -68,9 +69,16 @@ OPTIONS
Run post-processing deskew and black edge detection (requires unpaper) Run post-processing deskew and black edge detection (requires unpaper)
--ocr --ocr
Run OCR to make the PDF searchable (requires tesseract) Run OCR to make the PDF searchable (requires tesseract)
--skip-empty-pages
remove empty pages from resulting PDF document (e.g. one sided doc in duplex mode)
OUTPUT OUTPUT
-o, --output <outputfile> -o, --output <outputfile>
Output to named file default=scan.pdf Output to named file default=scan.pdf
-l, --outputlist <outputfile-1...outputfile-n> Output to named files for each scanned page, can be used with append -l, --outputlist <outputfile-1...outputfile-n> Output to named files for each scanned page, can be used with append
``` ```
## Contributors
* [Raman Gupta](https://github.com/rocketraman/)
* [Stefan Armbruster](https://github.com/sarmbruster/)

37
scan
View File

@ -12,6 +12,7 @@ SCRIPT="$DIR/scan_perpage"
DUPLEX=0 DUPLEX=0
UNPAPER=0 UNPAPER=0
SEARCHABLE=0 SEARCHABLE=0
LANGUAGE=eng
MAXPAGE= MAXPAGE=
TRUNCPAGE=0 TRUNCPAGE=0
HELP=0 HELP=0
@ -23,6 +24,9 @@ PGWIDTHIN=
CROP=0 CROP=0
DESKEW=0 DESKEW=0
VERBOSE=0 VERBOSE=0
SKIP_EMPTY_PAGES=0
TMP_DIR=`mktemp -d`
trap "rm -rf $TMP_DIR" 0
# Parse command-line options # Parse command-line options
while [ $# -gt 0 ]; do while [ $# -gt 0 ]; do
@ -58,6 +62,10 @@ while [ $# -gt 0 ]; do
--searchable|--ocr) SEARCHABLE=1 ;; --searchable|--ocr) SEARCHABLE=1 ;;
--language) LANGUAGE=$1 ;;
--skip-empty-pages) SKIP_EMPTY_PAGES=1 ;;
-o|--output) shift; OUTPUT="$1" ;; -o|--output) shift; OUTPUT="$1" ;;
-l|--outputlist) shift; USEARRAY=1; OUTPUT=(); OUTPUT+=("$1") ;; -l|--outputlist) shift; USEARRAY=1; OUTPUT=(); OUTPUT+=("$1") ;;
@ -94,6 +102,8 @@ if [ $HELP -eq 1 ]; then
echo " Custom Page Height in mm" echo " Custom Page Height in mm"
echo " -pw, --page-width" echo " -pw, --page-width"
echo " Custom Page Width in mm" echo " Custom Page Width in mm"
echo " -x, --device"
echo " Override scanner device name, defaulting to `fujitsu`"
echo " --crop" echo " --crop"
echo " Crop to contents (driver must support this)" echo " Crop to contents (driver must support this)"
echo " --deskew" echo " --deskew"
@ -102,6 +112,10 @@ if [ $HELP -eq 1 ]; then
echo " Run post-processing deskew and black edge detection (requires unpaper)" echo " Run post-processing deskew and black edge detection (requires unpaper)"
echo " --ocr" echo " --ocr"
echo " Run OCR to make the PDF searchable (requires tesseract)" echo " Run OCR to make the PDF searchable (requires tesseract)"
echo " --language <lang>"
echo " which language to use for OCR"
echo " --skip-empty-pages"
echo " remove empty pages from resulting PDF document (e.g. one sided doc in duplex mode)"
echo "" echo ""
echo "OUTPUT" echo "OUTPUT"
echo " -o, --output <outputfile>" echo " -o, --output <outputfile>"
@ -175,10 +189,12 @@ fi
export VERBOSE export VERBOSE
export UNPAPER export UNPAPER
export SEARCHABLE export SEARCHABLE
export LANGUAGE
export RESOLUTION export RESOLUTION
export PGWIDTHIN export PGWIDTHIN
export PGHEIGHTIN export PGHEIGHTIN
export PS2PDF_OPTS export PS2PDF_OPTS
export SKIP_EMPTY_PAGES
if [ $VERBOSE = 1 ]; then if [ $VERBOSE = 1 ]; then
LOCKFILE=$(mktemp) LOCKFILE=$(mktemp)
@ -186,12 +202,13 @@ if [ $VERBOSE = 1 ]; then
export LOCKFILE export LOCKFILE
fi; fi;
echo >&2 "Scanning..." echo >&2 "Scanning..."
#eval strace -f -o /tmp/scan-trace.txt scanadf -d $DEVICE $MAXPAGE $PGHEIGHT $PGWIDTH -S $SCRIPT --script-wait --resolution $RESOLUTION --mode $MODE $DESKEW $CROP $SOURCE -o scan-%04d #eval strace -f -o /tmp/scan-trace.txt scanadf -d $DEVICE $MAXPAGE $PGHEIGHT $PGWIDTH -S $SCRIPT --script-wait --resolution $RESOLUTION --mode $MODE $DESKEW $CROP $SOURCE -o scan-%04d
eval scanadf -d "$DEVICE" $MAXPAGE $PGHEIGHT $PGWIDTH -S $SCRIPT --script-wait --resolution $RESOLUTION --mode $MODE $DESKEW $CROP $SOURCE -o scan-%04d eval scanadf -d "$DEVICE" $MAXPAGE $PGHEIGHT $PGWIDTH -S $SCRIPT --script-wait --resolution $RESOLUTION --mode $MODE $DESKEW $CROP $SOURCE -o $TMP_DIR/scan-%04d
shopt -s extglob nullglob shopt -s extglob nullglob
pdffiles=(scan-[0-9]*.pdf) pdffiles=($TMP_DIR/scan-[0-9]*.pdf)
numscans=${#pdffiles[@]} numscans=${#pdffiles[@]}
if [ $numscans -gt 0 ]; then if [ $numscans -gt 0 ]; then
echo "Processing $numscans pages" echo "Processing $numscans pages"
@ -213,13 +230,13 @@ if [ $numscans -gt 0 ]; then
if [ -f "${OUTPUT[$index]}.orig" ]; then if [ -f "${OUTPUT[$index]}.orig" ]; then
pdffiles+=("${OUTPUT[$index]}.orig") pdffiles+=("${OUTPUT[$index]}.orig")
fi fi
pdffiles+=(scan-*(0)$scanno.pdf) pdffiles+=($TMP_DIR/scan-*(0)$scanno.pdf)
pdfunite "${pdffiles[@]}" "${OUTPUT[$index]}" && rm scan-*(0)$scanno.pdf pdfunite "${pdffiles[@]}" "${OUTPUT[$index]}" && rm $TMP_DIR/scan-*(0)$scanno.pdf
else else
mv scan-*(0)$scanno.pdf "${OUTPUT[$index]}" mv $TMP_DIR/scan-*(0)$scanno.pdf "${OUTPUT[$index]}"
fi fi
else else
mv scan-*(0)$scanno.pdf "${OUTPUT[$index]}" mv $TMP_DIR/scan-*(0)$scanno.pdf "${OUTPUT[$index]}"
fi fi
let "index = $index + 1" let "index = $index + 1"
done done
@ -232,13 +249,13 @@ if [ $numscans -gt 0 ]; then
if [ -f "${OUTPUT}.orig" ]; then if [ -f "${OUTPUT}.orig" ]; then
pdffiles+=("${OUTPUT}.orig") pdffiles+=("${OUTPUT}.orig")
fi fi
pdffiles+=(scan-[0-9]*.pdf) pdffiles+=($TMP_DIR/scan-[0-9]*.pdf)
pdfunite "${pdffiles[@]}" "$OUTPUT" && rm scan-[0-9]*.pdf pdfunite "${pdffiles[@]}" "$OUTPUT" && rm $TMP_DIR/scan-[0-9]*.pdf
else else
if [ $USEARRAY = 1 ]; then if [ $USEARRAY = 1 ]; then
mv scan-0*.pdf "${OUTPUT[0]}" mv $TMP_DIR/scan-0*.pdf "${OUTPUT[0]}"
else else
mv scan-0*.pdf "$OUTPUT" mv $TMP_DIR/scan-0*.pdf "$OUTPUT"
fi fi
fi fi
echo "" echo ""

70
scan_perpage
View File

@ -9,9 +9,11 @@ usage()
echo "Set the following environment variables:" echo "Set the following environment variables:"
echo " UNPAPER" echo " UNPAPER"
echo " SEARCHABLE" echo " SEARCHABLE"
echo " LANGUAGE"
echo " RESOLUTION" echo " RESOLUTION"
echo " PGWIDTHIN" echo " PGWIDTHIN"
echo " PGHEIGHTIN" echo " PGHEIGHTIN"
echo " SKIP_EMPTY_PAGES"
echo " PS2PDF_OPTS (optional)" echo " PS2PDF_OPTS (optional)"
echo " VERBOSE (optional)" echo " VERBOSE (optional)"
echo " LOCKFILE (required if VERBOSE=1)" echo " LOCKFILE (required if VERBOSE=1)"
@ -38,53 +40,63 @@ if [ $# -lt 1 ]; then
exit 1 exit 1
fi fi
if [ "$UNPAPER" == "" -o "$SEARCHABLE" == "" -o "$RESOLUTION" == "" -o "$RESOLUTION" == "" ]; then if [ "$UNPAPER" == "" -o "$SEARCHABLE" == "" -o "$RESOLUTION" == "" -o "$RESOLUTION" == "" -o "$SKIP_EMPTY_PAGES" == "" ]; then
usage usage
exit 1 exit 1
fi fi
IMAGE_FILE=$1 IMAGE_PATH=$1
IMAGE_DIR=`dirname $1`
IMAGE_FILE=`basename $1`
process_page() { process_page() {
log "" log ""
log "-------------------------------------------------------------------------------" log "-------------------------------------------------------------------------------"
log "Post-processing scanned page ${IMAGE_FILE}, deskew=$UNPAPER, searchable=$SEARCHABLE..." log "Post-processing scanned page ${IMAGE_FILE}, deskew=$UNPAPER, searchable=$SEARCHABLE..."
[[ $SKIP_EMPTY_PAGES -eq 1 ]] && PERCENTAGE_WHITE=`convert "$IMAGE_PATH" -fuzz 0% -negate -threshold 0 -negate -format "%[fx:100*mean]" info:` || PERCENTAGE_WHITE=0
log "$IMAGE_PATH has $PERCENTAGE_WHITE % white"
PP_PREFIX= PP_PREFIX=
if [ $UNPAPER -eq 1 ]; then if (( $(echo "$PERCENTAGE_WHITE < 99.99" |bc -l) )); then
log "Applying unpaper post-processing to image data..." if [ $UNPAPER -eq 1 ]; then
PP_PREFIX="unpaper-" log "Applying unpaper post-processing to image data..."
if [ $VERBOSE = 1 ]; then PP_PREFIX="unpaper-"
UNPAPERVERBOSE="-v" if [ $VERBOSE = 1 ]; then
UNPAPERVERBOSE="-v"
fi
#unpaper $UNPAPERVERBOSE --no-mask-scan --overwrite --dpi $RESOLUTION --no-blackfilter $IMAGE_FILE $PP_PREFIX$IMAGE_FILE | logstdout
unpaper $UNPAPERVERBOSE --overwrite --dpi $RESOLUTION $IMAGE_PATH $IMAGE_DIR/$PP_PREFIX$IMAGE_FILE | logstdout
fi fi
#unpaper $UNPAPERVERBOSE --no-mask-scan --overwrite --dpi $RESOLUTION --no-blackfilter $IMAGE_FILE $PP_PREFIX$IMAGE_FILE | logstdout log ""
unpaper $UNPAPERVERBOSE --overwrite --dpi $RESOLUTION $IMAGE_FILE $PP_PREFIX$IMAGE_FILE | logstdout log "-------------------------------------------------------------------------------"
fi
log ""
log "-------------------------------------------------------------------------------"
log "Converting image data to pdf..."
if [ $SEARCHABLE -eq 1 ]; then
log "Converting image data to searchable pdf..."
tesseract $PP_PREFIX$IMAGE_FILE ${IMAGE_FILE%.*} -l eng pdf | logstdout
else
log "Converting image data to pdf..." log "Converting image data to pdf..."
PNMVERBOSE= if [ $SEARCHABLE -eq 1 ]; then
if [ $VERBOSE = 1 ]; then log "Converting image data to searchable pdf..."
PNMVERBOSE="-verbose" tesseract $IMAGE_DIR/$PP_PREFIX$IMAGE_FILE $IMAGE_DIR/${IMAGE_FILE%.*} -l $LANGUAGE pdf | logstdout
fi
if [ "$PGWIDTHIN" == "" -o "$PGHEIGHTIN" == "" ]; then
PAGEOPTS="-equalpixels -dpi=$RESOLUTION -noturn"
else else
PAGEOPTS="-imagewidth $PGWIDTHIN -imageheight $PGHEIGHTIN" log "Converting image data to pdf..."
PNMVERBOSE=
if [ $VERBOSE = 1 ]; then
PNMVERBOSE="-verbose"
fi
if [ "$PGWIDTHIN" == "" -o "$PGHEIGHTIN" == "" ]; then
PAGEOPTS="-equalpixels -dpi=$RESOLUTION -noturn"
else
PAGEOPTS="-imagewidth $PGWIDTHIN -imageheight $PGHEIGHTIN"
fi
log "Using page options: $PAGEOPTS"
pnmtops $PNMVERBOSE $PAGEOPTS $IMAGE_DIR/$PP_PREFIX$IMAGE_FILE | ps2pdf $PS2PDF_OPTS - > $IMAGE_DIR/${IMAGE_FILE%.*}.pdf | logstdout
fi fi
log "Using page options: $PAGEOPTS" else
pnmtops $PNMVERBOSE $PAGEOPTS $PP_PREFIX$IMAGE_FILE | ps2pdf $PS2PDF_OPTS - > ${IMAGE_FILE%.*}.pdf | logstdout log "skipping empty page $IMAGE_FILE"
fi fi
status=$? status=$?
rm $IMAGE_FILE rm $IMAGE_PATH
if [ -f $PP_PREFIX$IMAGE_FILE ]; then if [ -f $IMAGE_DIR/$PP_PREFIX$IMAGE_FILE ]; then
rm $PP_PREFIX$IMAGE_FILE rm $IMAGE_DIR/$PP_PREFIX$IMAGE_FILE
fi fi
log "" log ""