examples/document_processing.py

"""
Example: Document Processing Pipeline

Demonstrates:
1. Processing a PDF document
2. Extracting text with OCR
3. Layout detection
4. Semantic chunking
"""

import asyncio
from pathlib import Path
from loguru import logger

# Import document processing components
from src.document.pipeline import (
    PipelineConfig,
    DocumentProcessor,
    process_document,
)
from src.document.ocr import OCRConfig


def example_basic_processing():
    """Basic document processing example."""
    print("=" * 50)
    print("Basic Document Processing")
    print("=" * 50)

    # Configure pipeline
    config = PipelineConfig(
        ocr=OCRConfig(engine="paddleocr"),
        render_dpi=300,
        max_pages=5,  # Limit for demo
    )

    # Create processor
    processor = DocumentProcessor(config)

    # Process a sample document
    # NOTE: Replace with actual document path
    sample_doc = Path("./data/sample.pdf")

    if not sample_doc.exists():
        print(f"Sample document not found: {sample_doc}")
        print("Create a sample PDF at ./data/sample.pdf to run this example")
        return

    # Process
    result = processor.process(sample_doc)

    # Display results
    print(f"\nDocument: {result.metadata.filename}")
    print(f"Pages: {result.metadata.num_pages}")
    print(f"Chunks: {result.metadata.total_chunks}")
    print(f"Characters: {result.metadata.total_characters}")
    print(f"OCR Confidence: {result.metadata.ocr_confidence_avg:.2%}")

    print("\n--- Sample Chunks ---")
    for i, chunk in enumerate(result.chunks[:3]):
        print(f"\n[Chunk {i+1}] Type: {chunk.chunk_type.value}, Page: {chunk.page+1}")
        print(f"Text: {chunk.text[:200]}...")
        print(f"BBox: ({chunk.bbox.x_min:.0f}, {chunk.bbox.y_min:.0f}) -> ({chunk.bbox.x_max:.0f}, {chunk.bbox.y_max:.0f})")


def example_with_layout():
    """Document processing with layout analysis."""
    print("\n" + "=" * 50)
    print("Document Processing with Layout Analysis")
    print("=" * 50)

    from src.document.layout import LayoutConfig, LayoutType

    # Configure with layout detection
    config = PipelineConfig(
        ocr=OCRConfig(engine="paddleocr"),
        layout=LayoutConfig(method="rule_based"),
        include_layout_regions=True,
    )

    processor = DocumentProcessor(config)

    sample_doc = Path("./data/sample.pdf")
    if not sample_doc.exists():
        print("Sample document not found")
        return

    result = processor.process(sample_doc)

    # Count layout types
    layout_counts = {}
    for region in result.layout_regions:
        layout_type = region.layout_type.value
        layout_counts[layout_type] = layout_counts.get(layout_type, 0) + 1

    print(f"\nLayout Analysis:")
    for layout_type, count in sorted(layout_counts.items()):
        print(f"  {layout_type}: {count} regions")

    # Show tables if found
    tables = [r for r in result.layout_regions if r.layout_type == LayoutType.TABLE]
    if tables:
        print(f"\n--- Tables Found ({len(tables)}) ---")
        for i, table in enumerate(tables[:2]):
            print(f"\nTable {i+1}: Page {table.page+1}")
            print(f"  Position: ({table.bbox.x_min:.0f}, {table.bbox.y_min:.0f})")
            print(f"  Size: {table.bbox.width:.0f} x {table.bbox.height:.0f}")


def example_convenience_function():
    """Using the convenience function."""
    print("\n" + "=" * 50)
    print("Using Convenience Function")
    print("=" * 50)

    sample_doc = Path("./data/sample.pdf")
    if not sample_doc.exists():
        print("Sample document not found")
        return

    # Simple one-liner
    result = process_document(sample_doc)

    print(f"Processed: {result.metadata.filename}")
    print(f"Chunks: {len(result.chunks)}")
    print(f"\nFull text preview:")
    print(result.full_text[:500] + "..." if len(result.full_text) > 500 else result.full_text)


if __name__ == "__main__":
    example_basic_processing()
    example_with_layout()
    example_convenience_function()