From d4bb3fb8dc00d2f8c8bdee00def5731fa5a053c3 Mon Sep 17 00:00:00 2001
From: rmgr <jake@rmgr.dev>
Date: Thu, 7 Mar 2024 21:12:19 +1030
Subject: [PATCH] Tidy up index.py

---
 src/index.py | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/src/index.py b/src/index.py
index c80b5e7..227815e 100644
--- a/src/index.py
+++ b/src/index.py
@@ -1,18 +1,10 @@
 #!/usr/bin/python3
 import argparse
-import requests
-import hashlib
-from urllib.parse import urlparse, urljoin
-import urllib.robotparser
-import os
-from time import sleep
-from bs4 import BeautifulSoup
 from sqlalchemy import create_engine
 from config import DATABASE_URI
 from models import Base, Documents, Document_Tokens, Tokens
 from sqlalchemy.orm import sessionmaker
-from sqlalchemy import create_engine
-import datetime
+import uuid
 
 engine = create_engine(DATABASE_URI)
 Base.metadata.create_all(engine)
@@ -30,16 +22,11 @@ def build_index():
             word = word.lower()
             token = session.query(Tokens).filter_by(token=word).first()
             if token is None:
-                token = Tokens(token=word)
+                token = Tokens(token=word, id=uuid.uuid4())
                 session.add(token)
             document_token = Document_Tokens(document_id=document.id, token_id=token.id)
             session.add(document_token)
         session.commit()
- 
-    # Foreach document, break into words
-    # Check if word exists in database
-    # Create if not exist
-    # Link to document
 
 
 if __name__ == "__main__":