import sys import os # Add parent directory to path current_dir = os.path.dirname(os.path.abspath(__file__)) parent_dir = os.path.dirname(current_dir) sys.path.append(parent_dir) from app.services.content_processor import SemanticChunker def test_chunker(): html = """ Test Page

Main Header

Intro paragraph.

Section 1: Details

This is the first section content.

More details here.

Section 2: Conclusion

Final thoughts.

""" chunker = SemanticChunker() chunks = chunker.chunk_document(html, "http://example.com") print(f"Generated {len(chunks)} chunks:") for i, c in enumerate(chunks): print(f"--- Chunk {i} ({c.chunk_type}) ---") print(f"Hash: {c.content_hash}") print(f"Parent: {c.parent_id}") print(f"Metadata: {c.metadata}") print(f"Text Preview: {c.text[:50]}...") print("") if __name__ == "__main__": test_chunker()