From f925a5e7eb4dc7ae7cc519f871ff494cff222c9f Mon Sep 17 00:00:00 2001 From: Adrian Edwards <17362949+MoralCode@users.noreply.github.com> Date: Mon, 14 Sep 2026 20:03:59 -0400 Subject: [PATCH] dont use repo_id as part of the natural key for a pull request Signed-off-by: Adrian Edwards <17362949+MoralCode@users.noreply.github.com> --- collectoss/tasks/github/pull_requests/tasks.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/collectoss/tasks/github/pull_requests/tasks.py b/collectoss/tasks/github/pull_requests/tasks.py index 3efaddf3b..98a74c61c 100644 --- a/collectoss/tasks/github/pull_requests/tasks.py +++ b/collectoss/tasks/github/pull_requests/tasks.py @@ -127,7 +127,7 @@ def process_pull_requests(pull_requests, task_name, repo_id, logger, db_session) # pr_urls are gloablly unique across github so we are using it to determine whether a pull_request we collected is already in the table # specified in pr_return_columns is the columns of data we want returned. This data will return in this form; {"pr_url": url, "pull_request_id": id} logger.info(f"{task_name}: Inserting prs of length: {len(pr_dicts)}") - pr_natural_keys = ["repo_id", "pr_src_id"] + pr_natural_keys = ["pr_src_id"] pr_return_columns = ["pull_request_id", "pr_url"] pr_string_fields = ["pr_src_title", "pr_body"] pr_return_data = db_session.insert_data(pr_dicts, PullRequest, pr_natural_keys,