modules/parser.py

import os
import re
import fitz  # PyMuPDF for reading PDFs
from typing import List

def extract_text_from_pdf(file_path: str) -> str:
    """
    Extracts plain text from a PDF file using PyMuPDF.
    """
    doc = fitz.open(file_path)
    text = ""
    for page in doc:
        text += page.get_text()  # Extract text from each page
    return text

def read_log_file(file_path: str) -> str:
    """
    Reads a .log or .txt file and returns its content as text.
    """
    with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
        return f.read()

def detect_log_format(text: str) -> str:
    """
    Detects the log format using basic pattern matching.
    Returns one of: 'syslog', 'json', 'cef', or 'unknown'.
    """
    if re.search(r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}", text):
        return "syslog"
    elif re.search(r"\{.*\}", text):
        return "json"
    elif "CEF:" in text:
        return "cef"
    else:
        return "unknown"

def parse_uploaded_files(files: List[str]) -> str:
    """
    Accepts a list of uploaded files, extracts content from each,
    and returns all logs as one combined string.
    """
    all_logs = ""
    for file_obj in files:
        file_path = file_obj.name

        if file_path.endswith('.pdf'):
            all_logs += extract_text_from_pdf(file_path) + "\n"
        elif file_path.endswith(('.log', '.txt')):
            all_logs += read_log_file(file_path) + "\n"
    
    return all_logs