Created
August 30, 2017 17:35
-
-
Save jcttrll/26b9b96253c5c654141399039fb528a2 to your computer and use it in GitHub Desktop.
Quick-'n'-dirty rename of scanned PDFs based on OCR of content (requires Tesseract, ImageMagick)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#/bin/bash -e | |
set -o pipefail | |
REGION_X=1920 | |
REGION_Y=2210 | |
REGION_WIDTH=320 | |
REGION_HEIGHT=100 | |
RENAME_PATTERN='foo-%s.pdf' | |
for file in "$@"; do | |
declare date=$( | |
convert -crop "${REGION_WIDTH}x${REGION_HEIGHT}+${REGION_X}+${REGION_Y}" \ | |
-density 300 -black-threshold 0.3 "$file" png:- | | |
tesseract stdin stdout 2>/dev/null | | |
grep -oP '\d[\s\d]*/[\d\s]+/[\d\s]+' | | |
tr -d ' ' | | |
awk -F/ '$3 < 100{$3 += 2000}{print $3 "-" $1 "-" $2}' | |
) | |
if [ -n "$date" ] && date -d "$date" >/dev/null; then | |
rename=$(printf "$RENAME_PATTERN" "$date") | |
if [ -e "$rename" ]; then | |
echo "Error: $rename would be overwritten; skipping" >&2 | |
else | |
mv -vn "$file" "$rename" | |
fi | |
else | |
echo "Error detecting date of $file; skipping" >&2 | |
fi | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment