src/services/file_proccess.py

import os
import re
import tempfile
import pandas as pd
import fitz  # PyMuPDF
from docx import Document
from fastapi import UploadFile

def extract_phone_numbers(text: str) -> list:
    phone_pattern = re.compile(r'\b\d{10}\b')
    matches = phone_pattern.findall(text)
    return [f'+91{number}' for number in matches]

def extract_text_from_pdf(file_path: str) -> str:
    doc = fitz.open(file_path)
    text = ""
    for page in doc:
        text += page.get_text()
    return text

def extract_text_from_docx(file_path: str) -> str:
    doc = Document(file_path)
    return "\n".join([para.text for para in doc.paragraphs])

def extract_text_from_file(file: UploadFile) -> str:
    suffix = os.path.splitext(file.filename)[-1].lower()
    print("File suffix:", suffix)

    with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
        tmp.write(file.file.read())
        tmp_path = tmp.name

    try:
        if suffix == ".pdf":
            return extract_text_from_pdf(tmp_path)

        elif suffix == ".docx":
            return extract_text_from_docx(tmp_path)

        elif suffix in [".txt"]:
            with open(tmp_path, "r", encoding="utf-8") as f:
                return f.read()

        elif suffix == ".csv":
            df = pd.read_csv(tmp_path)
            return " ".join(df.astype(str).values.flatten())

        elif suffix in [".xlsx", ".xls"]:
            df = pd.read_excel(tmp_path)
            return " ".join(df.astype(str).values.flatten())

        else:
            print("Unsupported file type, fallback to manual read")
            return file.file.read().decode("utf-8", errors="ignore")

    except Exception as e:
        print("Error while parsing file:", e)
        return ""