#!/bin/bash
"""
COMPLETE BOOK SCANNER - Orchestrates persistent session chunks to scan entire book
Uses proven working persistent session approach
"""

TOTAL_PAGES=226
CHUNK_SIZE=25  # Conservative chunk size for reliability
PROGRESS_FILE="scan_progress.json"

echo "📚 COMPLETE KINDLE BOOK SCANNER"
echo "==============================="
echo "Total pages: $TOTAL_PAGES"
echo "Chunk size: $CHUNK_SIZE pages"
echo ""

# Function to get last completed page
get_last_page() {
    if [ -f "$PROGRESS_FILE" ]; then
        python3 -c "
import json
try:
    with open('$PROGRESS_FILE', 'r') as f:
        data = json.load(f)
        print(data.get('last_completed_page', 0))
except:
    print(0)
"
    else
        echo 0
    fi
}

# Check if session state exists
if [ ! -f "kindle_session_state.json" ]; then
    echo "❌ No session state found. Initializing..."
    python3 persistent_scanner.py --init

    if [ $? -ne 0 ]; then
        echo "❌ Session initialization failed. Exiting."
        exit 1
    fi
    echo ""
fi

# Main scanning loop
chunk_number=1
total_chunks=$(( (TOTAL_PAGES + CHUNK_SIZE - 1) / CHUNK_SIZE ))

echo "🚀 Starting complete book scan..."
echo ""

while true; do
    last_completed=$(get_last_page)
    next_start=$((last_completed + 1))

    if [ "$next_start" -gt "$TOTAL_PAGES" ]; then
        echo "🏁 SCANNING COMPLETE!"
        echo "✅ All $TOTAL_PAGES pages have been scanned"
        break
    fi

    next_end=$((next_start + CHUNK_SIZE - 1))
    if [ "$next_end" -gt "$TOTAL_PAGES" ]; then
        next_end=$TOTAL_PAGES
    fi

    echo "📦 CHUNK $chunk_number/$total_chunks"
    echo "   Pages: $next_start to $next_end"
    echo "   Progress: $last_completed/$TOTAL_PAGES completed ($(( last_completed * 100 / TOTAL_PAGES ))%)"
    echo ""

    # Run the persistent scanner
    python3 persistent_scanner.py --start-page "$next_start" --chunk-size "$CHUNK_SIZE"

    # Check if chunk completed successfully
    new_last_completed=$(get_last_page)

    if [ "$new_last_completed" -le "$last_completed" ]; then
        echo "❌ ERROR: Chunk failed or made no progress"
        echo "   Last completed before: $last_completed"
        echo "   Last completed after: $new_last_completed"
        echo ""
        echo "🔄 Retrying chunk in 10 seconds..."
        sleep 10
    else
        echo "✅ Chunk completed successfully"
        echo "   Scanned pages: $next_start to $new_last_completed"
        echo ""
        chunk_number=$((chunk_number + 1))

        # Brief pause between chunks
        echo "⏳ Waiting 3 seconds before next chunk..."
        sleep 3
    fi
done

echo ""
echo "📊 FINAL SUMMARY"
echo "================"
final_count=$(get_last_page)
echo "Total pages scanned: $final_count/$TOTAL_PAGES"
echo "Files location: ./scanned_pages/"
echo "Progress file: $PROGRESS_FILE"

# Count actual files
file_count=$(ls scanned_pages/page_*.png 2>/dev/null | wc -l)
echo "Screenshot files: $file_count"

if [ "$final_count" -eq "$TOTAL_PAGES" ]; then
    echo ""
    echo "🎉 SUCCESS: Complete book scan finished!"
    echo "📖 All $TOTAL_PAGES pages captured successfully"
    echo "💾 Ready for OCR processing and translation"

    # Show file size summary
    echo ""
    echo "📁 File size summary:"
    if [ -d "scanned_pages" ]; then
        total_size=$(du -sh scanned_pages | cut -f1)
        echo "   Total size: $total_size"
        echo "   Average per page: $(du -sk scanned_pages | awk -v pages=$file_count '{printf "%.1fKB", $1/pages}')"
    fi
else
    echo ""
    echo "⚠️  Partial completion: $final_count/$TOTAL_PAGES pages"
    echo "You can resume by running this script again."
fi

echo ""
echo "🎯 SCAN COMPLETED - Check scanned_pages/ directory for results"