364d2c69ff
New standalone Python/FastAPI service for automatic compliance document scanning, LLM-based classification, IPFS archival, and gap analysis. Includes extractors (PDF, DOCX, XLSX, PPTX), keyword fallback classifier, compliance matrix, and full REST API on port 8098. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
26 lines
729 B
Python
26 lines
729 B
Python
"""Routes files to the appropriate extractor by extension."""
|
|
|
|
from .pdf_extractor import extract_pdf
|
|
from .docx_extractor import extract_docx
|
|
from .xlsx_extractor import extract_xlsx
|
|
from .pptx_extractor import extract_pptx
|
|
|
|
EXTRACTORS = {
|
|
".pdf": extract_pdf,
|
|
".docx": extract_docx,
|
|
".xlsx": extract_xlsx,
|
|
".pptx": extract_pptx,
|
|
}
|
|
|
|
|
|
def extract_text(file_path: str, extension: str) -> str:
|
|
"""Extract text from a file based on its extension.
|
|
|
|
Returns extracted text or raises ValueError for unsupported types.
|
|
"""
|
|
ext = extension.lower()
|
|
extractor = EXTRACTORS.get(ext)
|
|
if extractor is None:
|
|
raise ValueError(f"Unsupported file extension: {ext}")
|
|
return extractor(file_path)
|