From c28471ad93d1aee87572c548fd945375c38e8a68 Mon Sep 17 00:00:00 2001
From: Ikechukwu Uchendu <iuchendu@g.harvard.edu>
Date: Wed, 27 Sep 2023 09:41:22 -0400
Subject: [PATCH] Auto contributors will now try to merge with main before
 pushing

---
 .github/workflows/auto-add-contributors.yml   |  5 +-
 .../contributors/update_contributors.py       | 59 ++++++++-----------
 2 files changed, 26 insertions(+), 38 deletions(-)

diff --git a/.github/workflows/auto-add-contributors.yml b/.github/workflows/auto-add-contributors.yml
index 756bb6a4..280f9bed 100644
--- a/.github/workflows/auto-add-contributors.yml
+++ b/.github/workflows/auto-add-contributors.yml
@@ -31,13 +31,10 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r .github/workflows/contributors/requirements.txt       
 
-      - name: Retrieving all contributors from the main branch
+      - name: Auto add contributor job has been triggered
         run: |
           echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
           echo "🐧 This job is now running on a ${{ runner.os }} server hosted by GitHub!"
-          echo "🔎 Getting all contributors from the ${{ github.ref }} branch."
-          PUSHED_CONTRIBUTORS=$(git shortlog -sne --no-merges main)
-          echo "The contributors are: $PUSHED_CONTRIBUTORS"
       - name: Running Python Script to Update .all-contributorsrc
         run: |
           echo "Running Python Script to Update .all-contributorsrc"
diff --git a/.github/workflows/contributors/update_contributors.py b/.github/workflows/contributors/update_contributors.py
index 2acae10a..9f856645 100644
--- a/.github/workflows/contributors/update_contributors.py
+++ b/.github/workflows/contributors/update_contributors.py
@@ -2,32 +2,17 @@
 import os
 
 from absl import app
-from github import Github
 import requests
 
 CONTRIBUTORS_FILE = '.all-contributorsrc'
 
-EXCLUDED_USERS = ['web-flow', 'github-actions[bot]', 'mrdragonbear']
+EXCLUDED_USERS = {'web-flow', 'github-actions[bot]', 'mrdragonbear'}
 
 OWNER = "harvard-edge"
 REPO = "cs249r_book"
 BRANCH = "main"
 
 
-def split_name_email(s):
-    parts = s.rsplit(' ', 1)
-    return parts[0], parts[1][1:-1]  # Removing angle brackets from email
-
-
-def get_github_username(token, email):
-    g = Github(token)
-    users = g.search_users(email)
-    for user in users:
-        # Assuming the first user returned with the matching email is the correct user
-        return user.login
-    return None
-
-
 def main(_):
     token = os.environ["GH_TOKEN"]
 
@@ -39,35 +24,41 @@ def main(_):
     res = requests.get(web_address, headers=headers)
 
     print(web_address)
+    user_to_name_dict = dict()
 
     # Check if the request was successful
     if res.status_code == 200:
-        # Parse the JSON response
         data = res.json()
 
         # Extract the 'login' attribute for each committer
-        usernames = [commit['committer']['login'] for commit in data if commit['committer']]
-
-        # Print unique usernames
-        for username in sorted(set(usernames)):
-            print(username)
+        users_from_api = []
+        for commit in data:
+            if commit['committer']:
+                committer = commit['committer']
+                users_from_api.append(committer['login'])
+                user_to_name_dict[committer['login']] = committer['name']
+        users_from_api = set(users_from_api)
+        print('Users pulled from API: ', users_from_api)
 
         with open(CONTRIBUTORS_FILE, 'r') as contrib_file:
-            contributors_data = json.load(contrib_file)
-            user_to_name_dict = dict()
-            contributors = contributors_data['contributors']
+            existing_contributor_data = json.load(contrib_file)
+            existing_contributors = existing_contributor_data['contributors']
+
+            existing_contributor_logins = []
+            for existing_contributor in existing_contributors:
+                user_to_name_dict[existing_contributor['login']] = existing_contributor['name']
+                existing_contributor_logins.append(existing_contributor['login'])
+            existing_contributor_logins_set = set(existing_contributor_logins)
+            print('Existing contributors: ', existing_contributor_logins_set)
 
-            contributor_logins = []
-            for contrib in contributors:
-                user_to_name_dict[contrib['login']] = contrib['name']
-                contributor_logins.append(contrib['login'])
-            contributor_logins_set = set(contributor_logins)
+            # All contributors in the file should be in the API
+            assert existing_contributor_logins_set.issubset(
+                users_from_api), 'All contributors in the .all-contributorsrc file should be pulled using the API'
 
-            # Perform the set subtraction
-            # result = usernames_set - contributor_logins_set
-            result = contributor_logins_set - set(EXCLUDED_USERS)
+            new_contributor_logins = users_from_api - existing_contributor_logins_set
+            print('New contributors: ', new_contributor_logins)
 
-            print('New contributors: ', result)
+            result = users_from_api - EXCLUDED_USERS
 
             final_result = dict(
                 projectName=REPO,