src/labdaps/ingestion/pdf_extractor.py

from dataclasses import dataclass
from pathlib import Path
import pdfplumber


@dataclass
class RawPage:
    text: str
    page_number: int
    source_file: str


def extract_pdf(pdf_path: Path) -> list[RawPage]:
    pages = []
    source_file = pdf_path.name
    try:
        with pdfplumber.open(pdf_path) as pdf:
            for i, page in enumerate(pdf.pages, start=1):
                text = (page.extract_text() or "").strip()
                if len(text) > 50:
                    pages.append(RawPage(text=text, page_number=i, source_file=source_file))
    except Exception as e:
        print(f"[WARNING] Falha ao extrair {pdf_path.name}: {e}")
    return pages


def extract_all_pdfs(docs_dir: Path) -> list[RawPage]:
    all_pages = []
    for pdf_path in sorted(docs_dir.glob("*.pdf")):
        all_pages.extend(extract_pdf(pdf_path))
    return all_pages