33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
|
"""DOCX extractor."""
|
||
|
|
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
from docx import Document
|
||
|
|
|
||
|
|
from src.ingest.models import DocumentChunk, NormalizedDocument
|
||
|
|
|
||
|
|
|
||
|
|
def extract_docx(path: Path, document_id: str, project: str, doc_type: str) -> NormalizedDocument:
|
||
|
|
doc = Document(str(path))
|
||
|
|
parts: list[str] = []
|
||
|
|
for para in doc.paragraphs:
|
||
|
|
line = para.text.strip()
|
||
|
|
if line:
|
||
|
|
parts.append(line)
|
||
|
|
for table in doc.tables:
|
||
|
|
for row in table.rows:
|
||
|
|
cells = [cell.text.strip() for cell in row.cells if cell.text.strip()]
|
||
|
|
if cells:
|
||
|
|
parts.append(" | ".join(cells))
|
||
|
|
full_text = "\n".join(parts).strip()
|
||
|
|
return NormalizedDocument(
|
||
|
|
document_id=document_id,
|
||
|
|
filename=path.name,
|
||
|
|
doc_type=doc_type,
|
||
|
|
project=project,
|
||
|
|
full_text=full_text,
|
||
|
|
chunks=[DocumentChunk(text=full_text, source=path.name)] if full_text else [],
|
||
|
|
metadata={"format": "docx", "paragraphs": len(doc.paragraphs), "tables": len(doc.tables)},
|
||
|
|
mime_hint="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||
|
|
)
|