Update output on pixels-to-pdf to have one line per page

This commit is contained in:
Micah Lee 2020-01-07 16:29:35 -08:00
parent 3ea50a477d
commit 757a30794d
No known key found for this signature in database
GPG key ID: 403C2657CD994F73

View file

@ -21,23 +21,20 @@ for PAGE in $(seq 1 $NUM_PAGES); do
OCR_FILENAME=/tmp/page-$PAGE OCR_FILENAME=/tmp/page-$PAGE
PDF_FILENAME=/tmp/page-$PAGE.pdf PDF_FILENAME=/tmp/page-$PAGE.pdf
echo "Converting page $PAGE from pixels to PNG"
IMG_WIDTH=$(cat $WIDTH_FILENAME) IMG_WIDTH=$(cat $WIDTH_FILENAME)
IMG_HEIGHT=$(cat $HEIGHT_FILENAME) IMG_HEIGHT=$(cat $HEIGHT_FILENAME)
echo "Converting page $PAGE from pixels to searchable PDF"
CONVERT_MSGS=$(convert -size "${IMG_WIDTH}x${IMG_HEIGHT}" -depth ${IMG_DEPTH} rgb:"$RGB_FILENAME" png:"$PNG_FILENAME" 2>&1) CONVERT_MSGS=$(convert -size "${IMG_WIDTH}x${IMG_HEIGHT}" -depth ${IMG_DEPTH} rgb:"$RGB_FILENAME" png:"$PNG_FILENAME" 2>&1)
if [ $? -ne 0 ]; then if [ $? -ne 0 ]; then
die "Page $PAGE conversion failed: $CONVERT_MSGS" die "Page $PAGE conversion failed: $CONVERT_MSGS"
fi fi
echo "Converting page $PAGE from PNG to searchable PDF"
CONVERT_MSGS=$(tesseract $PNG_FILENAME $OCR_FILENAME pdf 2>&1) CONVERT_MSGS=$(tesseract $PNG_FILENAME $OCR_FILENAME pdf 2>&1)
if [ $? -ne 0 ]; then if [ $? -ne 0 ]; then
die "Page $PAGE conversion failed: $CONVERT_MSGS" die "Page $PAGE conversion failed: $CONVERT_MSGS"
fi fi
echo
done done
echo echo