From 319f946fc6e08f82eb36ea7df0e0cee6838de2d5 Mon Sep 17 00:00:00 2001
From: philipperolet <pr@dust.tt>
Date: Wed, 6 Sep 2023 19:34:05 +0200
Subject: [PATCH] migration script

---
 .../20230906_3_github_fill_parents_field.ts   | 101 ++++++++++++++++++
 .../connectors/github/temporal/activities.ts  |   7 +-
 2 files changed, 106 insertions(+), 2 deletions(-)
 create mode 100644 connectors/migrations/20230906_3_github_fill_parents_field.ts

diff --git a/connectors/migrations/20230906_3_github_fill_parents_field.ts b/connectors/migrations/20230906_3_github_fill_parents_field.ts
new file mode 100644
index 000000000000..ebe2e7aa52d7
--- /dev/null
+++ b/connectors/migrations/20230906_3_github_fill_parents_field.ts
@@ -0,0 +1,101 @@
+import {
+  getDiscussionDocumentId,
+  getIssueDocumentId,
+} from "@connectors/connectors/github/temporal/activities";
+import { updateDocumentParentsField } from "@connectors/lib/data_sources";
+import {
+  Connector,
+  GithubDiscussion,
+  GithubIssue,
+} from "@connectors/lib/models";
+
+async function main() {
+  // if first arg is "all", update all connectors, else update only the
+  // connector for the corresponding workspace id
+  const connectors =
+    process.argv[2] === "all"
+      ? await Connector.findAll({
+          where: {
+            type: "github",
+          },
+        })
+      : await Connector.findAll({
+          where: {
+            type: "github",
+            workspaceId: process.argv[2],
+          },
+        });
+
+  for (const connector of connectors) {
+    console.log(`Updating parents field for connector ${connector.id}`);
+    await updateDiscussionsParentsFieldForConnector(connector);
+    await updateIssuesParentsFieldForConnector(connector);
+  }
+}
+
+async function updateDiscussionsParentsFieldForConnector(connector: Connector) {
+  // get all distinct documentIds and their channel ids from slack messages in
+  // this connector
+  const documentData = await GithubDiscussion.findAll({
+    where: {
+      connectorId: connector.id,
+    },
+    attributes: ["repoId", "discussionNumber"],
+  });
+  // update all parents fields for all pages and databases by chunks of 128
+  const chunkSize = 128;
+  for (let i = 0; i < documentData.length; i += chunkSize) {
+    const chunk = documentData.slice(i, i + chunkSize);
+    console.log(`Updating ${chunk.length} documents`);
+    // update parents field for each document of the chunk, in parallel
+    await Promise.all(
+      chunk.map(async (document) => {
+        const docId = getDiscussionDocumentId(
+          document.repoId,
+          document.discussionNumber
+        );
+        await updateDocumentParentsField(connector, docId, [
+          document.discussionNumber.toString(),
+          document.repoId,
+        ]);
+      })
+    );
+  }
+}
+
+async function updateIssuesParentsFieldForConnector(connector: Connector) {
+  // get all distinct documentIds and their channel ids from slack messages in
+  // this connector
+  const documentData = await GithubIssue.findAll({
+    where: {
+      connectorId: connector.id,
+    },
+    attributes: ["repoId", "issueNumber"],
+  });
+  // update all parents fields for all pages and databases by chunks of 128
+  const chunkSize = 128;
+  for (let i = 0; i < documentData.length; i += chunkSize) {
+    const chunk = documentData.slice(i, i + chunkSize);
+    console.log(`Updating ${chunk.length} documents`);
+    // update parents field for each document of the chunk, in parallel
+    await Promise.all(
+      chunk.map(async (document) => {
+        const docId = getIssueDocumentId(document.repoId, document.issueNumber);
+        await updateDocumentParentsField(connector, docId, [
+          document.issueNumber.toString(),
+          document.repoId,
+        ]);
+      })
+    );
+  }
+}
+
+main()
+  .then(() => {
+    console.log("Done");
+    process.exit(0);
+  })
+  .catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
diff --git a/connectors/src/connectors/github/temporal/activities.ts b/connectors/src/connectors/github/temporal/activities.ts
index e6f1ad8a6f92..668d631f1dbc 100644
--- a/connectors/src/connectors/github/temporal/activities.ts
+++ b/connectors/src/connectors/github/temporal/activities.ts
@@ -585,11 +585,14 @@ function renderGithubUser(user: GithubUser | null): string {
   return `@${user.id}`;
 }
 
-function getIssueDocumentId(repoId: string, issueNumber: number): string {
+export function getIssueDocumentId(
+  repoId: string,
+  issueNumber: number
+): string {
   return `github-issue-${repoId}-${issueNumber}`;
 }
 
-function getDiscussionDocumentId(
+export function getDiscussionDocumentId(
   repoId: string,
   discussionNumber: number
 ): string {