Remove low hanging fruit usages of GithubRandomKeyAuth

collectoss/tasks/data_analysis/contributor_breadth_worker/contributor_breadth_worker.py

@@ -7,7 +7,6 @@
 from collectoss.tasks.github.util.github_data_access import GithubDataAccess, UrlNotFoundException
 from collectoss.application.db.models import ContributorRepo
 from collectoss.application.db.lib import bulk_insert_dicts
-from collectoss.tasks.github.util.github_random_key_auth import GithubRandomKeyAuth
 
 ### This worker scans all the platform users in CollectOSS, and pulls their platform activity 
 ### logs. Those are then used to analyze what repos each is working in (which will include repos not
@@ -26,8 +25,6 @@ def contributor_breadth_model(self) -> None:
     tool_version = '0.0.1'
     data_source = 'GitHub API'
 
-    key_auth = GithubRandomKeyAuth(logger)
-
     # This version of the query pulls contributors who have not had any data collected yet
     # To the top of the list
     cntrb_login_query = s.sql.text("""
@@ -83,7 +80,7 @@ def contributor_breadth_model(self) -> None:
 
         cntrb_newest_events_map[gh_login] = newest_event_date
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     index = 1
     total = len(current_cntrb_logins)

collectoss/tasks/frontend.py

@@ -152,7 +152,7 @@ def get_org_repo_data(orgs, session):
 def add_new_github_repos(repo_data, group_id, session, logger):
 
       # get data for repos to determine type, src id, and if they exist
-    data = get_github_repos_data(repo_data, session, logger)
+    data = get_github_repos_data(repo_data, None, logger)
 
     for url, repo_group_id in repo_data:
 
@@ -200,7 +200,7 @@ def get_github_repos_data(repo_data, session, logger):
 
     repo_urls = [x[0] for x in repo_data]
 
-    github_graphql_data_access = GithubGraphQlDataAccess(session.oauths, logger, ingore_not_found_error=True)
+    github_graphql_data_access = GithubGraphQlDataAccess(None, logger, ingore_not_found_error=True)
 
     query_parts = []
     repo_map = {}

collectoss/tasks/github/contributors.py

@@ -82,6 +82,7 @@ def process_contributors():
 
 
 
+@deprecated("This function is deprecated. Use the GithubDataAccess class instead")
 def retrieve_dict_data(url: str, key_auth, logger):
 
     num_attempts = 0
@@ -133,8 +134,7 @@ def grab_comitters(self, repo_git,platform="github"):
     logger = logging.getLogger(grab_comitters.__name__)
 
     try:
-        key_auth = GithubRandomKeyAuth(logger)
-        grab_committer_list(logger, key_auth, repo_git, tool_source, tool_version, data_source, platform)
+        grab_committer_list(logger, None, repo_git, tool_source, tool_version, data_source, platform)
     except Exception as e:
         logger.error(f"Could not grab committers from github endpoint!\n Reason: {e} \n Traceback: {''.join(traceback.format_exception(None, e, e.__traceback__))}")
 

collectoss/tasks/github/events.py

@@ -39,7 +39,7 @@ def collect_events(repo_git: str, full_collection: bool):
 
     key_auth = GithubRandomKeyAuth(logger)
 
-    if bulk_events_collection_endpoint_contains_all_data(key_auth, logger, owner, repo):
+    if bulk_events_collection_endpoint_contains_all_data(None, logger, owner, repo):
         collection_strategy = BulkGithubEventCollection(logger)
     else:
         collection_strategy = ThoroughGithubEventCollection(logger)
@@ -50,7 +50,7 @@ def bulk_events_collection_endpoint_contains_all_data(key_auth, logger, owner, r
 
     url = f"https://api.github.com/repos/{owner}/{repo}/issues/events?per_page=100"
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     page_count = github_data_access.get_resource_page_count(url)
 
@@ -136,7 +136,7 @@ def _collect_events(self, repo_git: str, key_auth, since):
 
         url = f"https://api.github.com/repos/{owner}/{repo}/issues/events"
 
-        github_data_access = GithubDataAccess(key_auth, self._logger)
+        github_data_access = GithubDataAccess(None, self._logger)
 
         for event in github_data_access.paginate_resource(url):
 
@@ -308,7 +308,7 @@ def _collect_and_process_issue_events(self, owner, repo, repo_id, key_auth, sinc
 
         events = []
         contributors = []
-        github_data_access = GithubDataAccess(key_auth, self._logger)
+        github_data_access = GithubDataAccess(None, self._logger)
         for db_issue in issue_result:
             issue = db_issue._asdict()
 
@@ -371,7 +371,7 @@ def _collect_and_process_pr_events(self, owner, repo, repo_id, key_auth, since):
 
         events = []
         contributors = []
-        github_data_access = GithubDataAccess(key_auth, self._logger)
+        github_data_access = GithubDataAccess(None, self._logger)
         for db_pr in pr_result:
             pr = db_pr._asdict()
 

collectoss/tasks/github/facade_github/contributor_interfaceable/contributor_interface.py

@@ -296,7 +296,7 @@ def fetch_username_from_email(logger, auth, commit) -> dict | None:
         return login_json
 
     try:
-        github_data_access = GithubDataAccess(auth, logger, feature="search")
+        github_data_access = GithubDataAccess(None, logger, feature="search")
         login_json = github_data_access.get_resource(url)
     except Exception as e:
         logger.error(f"Couldn't resolve email URL with given data. Reason: {e}")
@@ -328,7 +328,7 @@ def get_login_with_supplemental_data(logger, auth, commit_data):
 
     # Try to get login from all possible emails
     # Is None upon failure.
-    login_json = fetch_username_from_email(logger,auth,commit_data)
+    login_json = fetch_username_from_email(logger,None,commit_data)
 
     # total_count is the count of username's found by the endpoint.
     # This Checks if the email result got anything.
@@ -367,7 +367,7 @@ def get_login_with_commit_hash(logger, auth, commit_data, repo_id):
 
     #TODO: here.
     # Send api request
-    github_data_access = GithubDataAccess(auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
     login_json = github_data_access.get_resource(url)
 
     # TODO: Why are we returning None if 'sha' is not in response if we aren't even using it?

collectoss/tasks/github/facade_github/core.py

@@ -40,7 +40,7 @@ def query_github_contributors(logger, key_auth, github_url, tool_source:str, too
     update_col_map = {'cntrb_email': 'email'}
     duplicate_col_map = {'cntrb_login': 'login'}
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     contributor_count = github_data_access.get_resource_count(contributors_url)
 
@@ -79,5 +79,5 @@ def query_github_contributors(logger, key_auth, github_url, tool_source:str, too
 def grab_committer_list(logger, key_auth, repo_git, tool_source: str, tool_version: str, data_source: str, platform="github" ):
 
     # Create API endpoint from repo_id
-    query_github_contributors(logger, key_auth, repo_git, tool_source, tool_version, data_source)
+    query_github_contributors(logger, None, repo_git, tool_source, tool_version, data_source)
 

collectoss/tasks/github/facade_github/tasks.py

@@ -17,7 +17,7 @@
 
 def process_commit_metadata(logger, auth, contributorQueue, repo_id, platform_id, tool_source:str, tool_version:str, data_source:str):
 
-    github_data_access = GithubDataAccess(auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     for contributor in contributorQueue:
         # Get the email from the commit data
@@ -63,12 +63,12 @@ def process_commit_metadata(logger, auth, contributorQueue, repo_id, platform_id
 
         # Try to get the login from the commit sha
         if login == None or login == "":
-            login = get_login_with_commit_hash(logger, auth, contributor, repo_id)
+            login = get_login_with_commit_hash(logger, None, contributor, repo_id)
 
         if login == None or login == "":
             logger.warning("Failed to get login from commit hash")
             # Try to get the login from supplemental data if not found with the commit hash
-            login = get_login_with_supplemental_data(logger, auth,contributor)
+            login = get_login_with_supplemental_data(logger, None,contributor)
 
         if login == None or login == "":
             logger.error("Failed to get login from supplemental data!")
@@ -229,8 +229,6 @@ def insert_facade_contributors(self, repo_git):
     #             'repo_id': repo_id}).to_json(orient="records"))
 
 
-    key_auth = GithubRandomKeyAuth(logger)
-
     facade_batch_size = get_batch_size()
 
     # Process results in batches to reduce memory usage
@@ -240,12 +238,12 @@ def insert_facade_contributors(self, repo_git):
         batch.append(dict(row))
 
         if len(batch) >= facade_batch_size:
-            process_commit_metadata(logger, key_auth, batch, repo_id, platform_id, tool_source, tool_version, data_source)
+            process_commit_metadata(logger, None, batch, repo_id, platform_id, tool_source, tool_version, data_source)
             batch.clear()
 
     # Process remaining items in batch
     if batch:
-        process_commit_metadata(logger, key_auth, batch, repo_id, platform_id, tool_source, tool_version, data_source)
+        process_commit_metadata(logger, None, batch, repo_id, platform_id, tool_source, tool_version, data_source)
 
     logger.debug("DEBUG: Got through the new_contribs")
 

collectoss/tasks/github/issues.py

@@ -9,7 +9,6 @@
 from collectoss.tasks.init.celery_app import CoreRepoCollectionTask
 from collectoss.application.db.data_parse import *
 from collectoss.tasks.github.util.github_data_access import GithubDataAccess
-from collectoss.tasks.github.util.github_random_key_auth import GithubRandomKeyAuth
 from collectoss.tasks.github.util.util import add_key_value_pair_to_dicts, get_owner_repo
 from collectoss.tasks.util.worker_util import remove_duplicate_dicts
 from collectoss.application.db.models import Issue, IssueLabel, IssueAssignee
@@ -47,12 +46,8 @@ def collect_issues(repo_git: str, full_collection: bool) -> int:
         # Subtract 2 days to ensure all data is collected
         core_data_last_collected = (get_core_data_last_collected(repo_id) - timedelta(days=2)).replace(tzinfo=timezone.utc)
 
-    key_auth = GithubRandomKeyAuth(logger)
-
-    logger.info(f'this is the manifest.key_auth value: {str(key_auth)}')
-
     try:
-        issue_data_generator = retrieve_all_issue_data(repo_git, logger, key_auth, core_data_last_collected)
+        issue_data_generator = retrieve_all_issue_data(repo_git, logger, None, core_data_last_collected)
 
         issue_batch_size = get_batch_size()
 
@@ -86,7 +81,7 @@ def collect_issues(repo_git: str, full_collection: bool) -> int:
 
 
 
-def retrieve_all_issue_data(repo_git: str, logger: logging.Logger, key_auth: GithubRandomKeyAuth, since: datetime | None = None):
+def retrieve_all_issue_data(repo_git: str, logger: logging.Logger, key_auth: None, since: datetime | None = None):
     """
     Retrieve all issue data for a repository as a generator.
 
@@ -96,7 +91,7 @@ def retrieve_all_issue_data(repo_git: str, logger: logging.Logger, key_auth: Git
     Args:
         repo_git (str): The GitHub repository in "owner/repo" format.
         logger (logging.Logger): Logger for logging messages.
-        key_auth (GithubRandomKeyAuth): Auth handler for GitHub API.
+        key_auth (GithubRandomKeyAuth): Auth handler for GitHub API. unused and deprecated, use KeyClient instead.
         since (datetime, optional): Only issues updated since this datetime will be retrieved.
     """
     owner, repo = get_owner_repo(repo_git)
@@ -108,7 +103,7 @@ def retrieve_all_issue_data(repo_git: str, logger: logging.Logger, key_auth: Git
     if since:
         url += f"&since={since.isoformat()}"
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     num_pages = github_data_access.get_resource_page_count(url)
     logger.info(f"{owner}/{repo}: Retrieving {num_pages} pages of issues")

collectoss/tasks/github/messages.py

@@ -40,7 +40,7 @@ def collect_github_messages(repo_git: str, full_collection: bool) -> None:
 
 
         if is_repo_small(repo_id):
-            message_data = fast_retrieve_all_pr_and_issue_messages(repo_git, logger, manifest.key_auth, task_name, core_data_last_collected)
+            message_data = fast_retrieve_all_pr_and_issue_messages(repo_git, logger, None, task_name, core_data_last_collected)
 
             if message_data:
                 process_messages(message_data, task_name, repo_id, logger, db_session)
@@ -49,7 +49,7 @@ def collect_github_messages(repo_git: str, full_collection: bool) -> None:
                 logger.info(f"{owner}/{repo} has no messages")
 
         else:
-            process_large_issue_and_pr_message_collection(repo_id, repo_git, logger, manifest.key_auth, task_name, db_session, core_data_last_collected)
+            process_large_issue_and_pr_message_collection(repo_id, repo_git, logger, None, task_name, db_session, core_data_last_collected)
 
 
 def is_repo_small(repo_id):
@@ -73,7 +73,7 @@ def fast_retrieve_all_pr_and_issue_messages(repo_git: str, logger, key_auth, tas
     # define logger for task
     logger.info(f"Collecting github comments for {owner}/{repo}")
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     message_count = github_data_access.get_resource_count(url)
 
@@ -113,7 +113,7 @@ def process_large_issue_and_pr_message_collection(repo_id, repo_git: str, logger
         result = connection.execute(query).fetchall()
     comment_urls = [x[0] for x in result if x[0] is not None]
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     logger.info(f"{task_name}: Collecting github messages for {len(comment_urls)} prs/issues")
 

collectoss/tasks/github/pull_requests/commits_model/core.py

@@ -46,7 +46,7 @@ def pull_request_commits_model(repo_id,logger, db_session, key_auth, full_collec
 
     logger.info(f"Getting pull request commits for repo: {repo.repo_git}")
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     pr_commits_natural_keys = ["pull_request_id", "repo_id", "pr_cmt_sha"]
     all_data = []

collectoss/tasks/github/pull_requests/commits_model/tasks.py

@@ -16,4 +16,4 @@ def process_pull_request_commits(repo_git: str, full_collection: bool) -> None:
 
     with GithubTaskManifest(logger) as manifest:
 
-        pull_request_commits_model(repo.repo_id, logger, manifest.db_session, manifest.key_auth, full_collection)
+        pull_request_commits_model(repo.repo_id, logger, manifest.db_session, None, full_collection)

collectoss/tasks/github/pull_requests/files_model/core.py

@@ -42,7 +42,7 @@ def pull_request_files_model(repo_id,logger, db_session, key_auth, full_collecti
 
     task_name = f"{owner}/{name} Pr files"
 
-    github_graphql_data_access = GithubGraphQlDataAccess(key_auth, logger)
+    github_graphql_data_access = GithubGraphQlDataAccess(None, logger)
 
     pr_file_natural_keys = ["pull_request_id", "repo_id", "pr_file_path"]
     pr_file_rows = []

collectoss/tasks/github/pull_requests/files_model/tasks.py

@@ -15,4 +15,4 @@ def process_pull_request_files(repo_git: str, full_collection: bool) -> None:
         query = db_session.session.query(Repo).filter(Repo.repo_git == repo_git)
         repo = execute_session_query(query, 'one')
 
-        pull_request_files_model(repo.repo_id, logger, db_session, manifest.key_auth, full_collection)
+        pull_request_files_model(repo.repo_id, logger, db_session, None, full_collection)

collectoss/tasks/github/pull_requests/tasks.py

@@ -10,7 +10,6 @@
 from collectoss.tasks.github.util.util import add_key_value_pair_to_dicts, get_owner_repo
 from collectoss.application.db.models import PullRequest, Message, PullRequestReview, PullRequestLabel, PullRequestReviewer, PullRequestMeta, PullRequestAssignee, PullRequestReviewMessageRef, Contributor, Repo
 from collectoss.tasks.github.util.github_task_session import GithubTaskManifest
-from collectoss.tasks.github.util.github_random_key_auth import GithubRandomKeyAuth
 from collectoss.application.db.lib import get_repo_by_repo_git, bulk_insert_dicts, get_pull_request_reviews_by_repo_id, batch_insert_contributors, get_batch_size
 from collectoss.application.db.util import execute_session_query
 from ..messages import process_github_comment_contributors
@@ -46,7 +45,7 @@ def collect_pull_requests(repo_git: str, full_collection: bool) -> int:
 
         total_count = 0
         all_data = []
-        for pr in retrieve_all_pr_data(repo_git, logger, manifest.key_auth, core_data_last_collected):
+        for pr in retrieve_all_pr_data(repo_git, logger, None, core_data_last_collected):
 
             all_data.append(pr)
 
@@ -75,7 +74,7 @@ def retrieve_all_pr_data(repo_git: str, logger, key_auth, since): #-> Generator[
 
     logger.debug(f"Collecting pull requests for {owner}/{repo}")
 
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     search_args = {"state": "all", "direction": "desc", "sort": "updated"}
     url = github_data_access.endpoint_url(f"repos/{owner}/{repo}/pulls", search_args)
@@ -257,8 +256,7 @@ def collect_pull_request_review_comments(repo_git: str, full_collection: bool) -
     tool_version = "2.0"
     data_source = "Github API"
 
-    key_auth = GithubRandomKeyAuth(logger)
-    github_data_access = GithubDataAccess(key_auth, logger)
+    github_data_access = GithubDataAccess(None, logger)
 
     pr_review_comment_batch_size = get_batch_size()
 
@@ -495,7 +493,7 @@ def collect_pull_request_reviews(repo_git: str, full_collection: bool) -> None:
 
         logger.info(f"{owner}/{repo}: Collecting reviews for {pr_count} PRs")
 
-        github_data_access = GithubDataAccess(manifest.key_auth, logger)
+        github_data_access = GithubDataAccess(None, logger)
 
         pr_review_batch_size = get_batch_size()
 

collectoss/tasks/github/releases/core.py

@@ -6,7 +6,7 @@
 from collectoss.tasks.github.util.gh_graphql_entities import request_graphql_dict
 from collectoss.application.db.util import execute_session_query
 from collectoss.application.db.lib import bulk_insert_dicts
-
+from typing_extensions import deprecated
 
 def get_release_inf(repo_id, release, tag_only):
     if not tag_only:
@@ -153,7 +153,7 @@ def get_query(logger, owner, repo, tag_only):
     return query
 
 
-
+@deprecated("This function is deprecated. Use the GithubGraphQlDataAccess class instead")
 def fetch_data(key_auth, logger, github_url, repo_id, tag_only = False):
 
     logger.info("Beginning filling the releases model for repo: " + github_url + "\n")