app/documents/parser.py

# File : app/documents/parser.py
# Purpose : Extract text from PDF, DOCX, TXT files

import io
from pathlib import Path
from typing import List, Dict

import pdfplumber
from docx import Document as DocxDocument


def parse_pdf(file_bytes: bytes) -> List[Dict]:
    pages = []
    with pdfplumber.open(io.BytesIO(file_bytes)) as pdf:
        for i, page in enumerate(pdf.pages):
            text = page.extract_text() or ""
            text = text.strip()
            if text:
                pages.append({"page_number": i + 1, "content": text})
    return pages


def parse_docx(file_bytes: bytes) -> List[Dict]:
    doc = DocxDocument(io.BytesIO(file_bytes))
    full_text = "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
    return [{"page_number": 1, "content": full_text}]


def parse_txt(file_bytes: bytes) -> List[Dict]:
    text = file_bytes.decode("utf-8", errors="ignore").strip()
    return [{"page_number": 1, "content": text}]


def parse_document(file_bytes: bytes, filename: str) -> List[Dict]:
    ext = Path(filename).suffix.lower()
    if ext == ".pdf":
        return parse_pdf(file_bytes)
    elif ext == ".docx":
        return parse_docx(file_bytes)
    elif ext == ".txt":
        return parse_txt(file_bytes)
    else:
        raise ValueError(f"Unsupported file type: {ext}")