From 0074ededdd3aed936f59b2a1c75a1bd8228ca622 Mon Sep 17 00:00:00 2001
From: Sean Hatfield <seanhatfield5@gmail.com>
Date: Mon, 21 Oct 2024 15:25:35 -0700
Subject: [PATCH] Github data connector improvements (#2439)

* fix tree/blob github urls from branches not being loaded

* improve ux of github data connector

* lint

* patch Github URL parser to just validate with `URL` native parser

* uncheck LocalStorage of PAT for security reasons

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
---
 .../RepoLoader/GithubRepo/RepoLoader/index.js | 42 +++++++++++++------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/collector/utils/extensions/RepoLoader/GithubRepo/RepoLoader/index.js b/collector/utils/extensions/RepoLoader/GithubRepo/RepoLoader/index.js
index 61f20874..61ef2036 100644
--- a/collector/utils/extensions/RepoLoader/GithubRepo/RepoLoader/index.js
+++ b/collector/utils/extensions/RepoLoader/GithubRepo/RepoLoader/index.js
@@ -29,20 +29,36 @@ class GitHubRepoLoader {
   }
 
   #validGithubUrl() {
-    const UrlPattern = require("url-pattern");
-    const pattern = new UrlPattern(
-      "https\\://github.com/(:author)/(:project(*))",
-      {
-        // fixes project names with special characters (.github)
-        segmentValueCharset: "a-zA-Z0-9-._~%/+",
-      }
-    );
-    const match = pattern.match(this.repo);
-    if (!match) return false;
+    try {
+      const url = new URL(this.repo);
 
-    this.author = match.author;
-    this.project = match.project;
-    return true;
+      // Not a github url at all.
+      if (url.hostname !== "github.com") {
+        console.log(
+          `[Github Loader]: Invalid Github URL provided! Hostname must be 'github.com'. Got ${url.hostname}`
+        );
+        return false;
+      }
+
+      // Assume the url is in the format of github.com/{author}/{project}
+      // Remove the first slash from the pathname so we can split it properly.
+      const [author, project, ..._rest] = url.pathname.slice(1).split("/");
+      if (!author || !project) {
+        console.log(
+          `[Github Loader]: Invalid Github URL provided! URL must be in the format of 'github.com/{author}/{project}'. Got ${url.pathname}`
+        );
+        return false;
+      }
+
+      this.author = author;
+      this.project = project;
+      return true;
+    } catch (e) {
+      console.log(
+        `[Github Loader]: Invalid Github URL provided! Error: ${e.message}`
+      );
+      return false;
+    }
   }
 
   // Ensure the branch provided actually exists