| from PIL import Image |
| from typing import Dict, List, Any |
| import io |
|
|
|
|
| class TableDetectionAgent: |
| """Detects table structures in PDF pages.""" |
|
|
| def process( |
| self, pdf_page: Image.Image, extracted_text: str = None |
| ) -> Dict[str, Any]: |
| """Detect tables in the page.""" |
| return { |
| "tables_found": self._find_tables(extracted_text or ""), |
| "table_count": 0, |
| "table_regions": [], |
| } |
|
|
| def _find_tables(self, text: str) -> List[Dict]: |
| """Find table-like structures.""" |
| tables = [] |
| lines = text.split("\n") |
| in_table = False |
| current_table = [] |
|
|
| for line in lines: |
| if "|" in line or "\t" in line: |
| if not in_table: |
| in_table = True |
| current_table = [] |
| current_table.append(line) |
| else: |
| if in_table and current_table: |
| tables.append({"rows": len(current_table), "data": current_table}) |
| in_table = False |
| current_table = [] |
|
|
| if in_table and current_table: |
| tables.append({"rows": len(current_table), "data": current_table}) |
|
|
| return tables |
|
|
