# Process all PDFs in directory
for f in *.pdf; do
    ocrmypdf "$f" "output/$f"
done

# Use GNU parallel for faster processing
parallel ocrmypdf {} output/{/} ::: *.pdf

# Limit to 4 concurrent jobs
parallel -j 4 ocrmypdf {} output/{/} ::: *.pdf

# Process all PDFs in directory tree
find . -name "*.pdf" -exec ocrmypdf {} output/{/} \;

# Pull image
docker pull jbarlow83/ocrmypdf

# Basic usage
docker run --rm \
    -v $(pwd):/data \
    jbarlow83/ocrmypdf \
    input.pdf output.pdf

# Process all PDFs
docker run --rm \
    -v $(pwd):/data \
    jbar65t83/ocrmypdf \
    ocrmypdf /data/input/*.pdf /data/output/

version: '3'
services:
  ocrmypdf:
    image: jbarlow83/ocrmypdf
    volumes:
      - ./input:/data/input
      - ./output:/data/output
    command: sh -c "for f in /data/input/*.pdf; do ocrmypdf \"$f\" \"/data/output/$(basename $f)\"; done"

name: OCR PDFs
on: [push]
jobs:
  ocr:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Run OCR
        run: |
          docker run --rm \
            -v ${{ github.workspace }}:/data \
            jbarlow83/ocrmypdf \
            sh -c "for f in /data/*.pdf; do ocrmypdf \"$f\" \"/data/output/$(basename $f)\"; done"

ocr:
  image: jbarlow83/ocrmypdf
  script:
    - mkdir -p output
    - for f in *.pdf; do ocrmypdf "$f" "output/$f"; done
  artifacts:
    paths:
      - output/

#!/bin/bash
INPUT_DIR="input"
OUTPUT_DIR="output"
LANG="eng+chi_sim"

mkdir -p "$OUTPUT_DIR"

for pdf in "$INPUT_DIR"/*.pdf; do
    filename=$(basename "$pdf")
    echo "Processing: $filename"
    ocrmypdf -l "$LANG" --deskew --remove-bordering "$pdf" "$OUTPUT_DIR/$filename"
    echo "Done: $filename"
done

echo "Batch OCR complete!"

# Continue on error, log failures
for f in *.pdf; do
    if ! ocrmypdf "$f" "output/$f" 2>&1; then
        echo "FAILED: $f" >> failed.log
    fi
done