From ab3271cb5a7bf9688323fff2c79ab8140105d101 Mon Sep 17 00:00:00 2001
From: Katy Baulch <46493669+katybaulch@users.noreply.github.com>
Date: Thu, 5 Sep 2024 10:55:40 +0100
Subject: [PATCH] Added pydantic to cpsell dict

---
 .trunk/configs/cspell.json          | 3 ++-
 gcf_data_mapper/parsers/document.py | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/.trunk/configs/cspell.json b/.trunk/configs/cspell.json
index 77c9350..226d7d8 100644
--- a/.trunk/configs/cspell.json
+++ b/.trunk/configs/cspell.json
@@ -38,7 +38,8 @@
     "conftest",
     "capsys",
     "dtypes",
-    "isin"
+    "isin",
+    "pydantic"
   ],
   "flagWords": ["hte"],
   "suggestionsTimeout": 5000
diff --git a/gcf_data_mapper/parsers/document.py b/gcf_data_mapper/parsers/document.py
index 074abbd..d33f7c2 100644
--- a/gcf_data_mapper/parsers/document.py
+++ b/gcf_data_mapper/parsers/document.py
@@ -64,6 +64,8 @@ def contains_invalid_paths(urls: list[str]) -> bool:
 def validate_urls(urls: list[str], doc_id: str) -> Optional[bool]:
     """Validate a list of URLs for empty, duplicate, & malformed entries.
 
+    TODO can we use Pydantic for this?
+
     param: list[str] urls : A list of urls
     param: str doc_id: The document id of the invalid source urls
     raises ValueError: If the list contains duplicate, empty or,