Updating migration script

README.md

@@ -127,6 +127,14 @@ Set these when Wasabi image storage is ready:
 
 Use a dedicated private bucket and access key for FlockPal images. Grant only the S3 permissions the app needs for that bucket. When `S3_PUBLIC_BASE_URL` is blank, FlockPal stores private object keys and returns short-lived signed URLs for bird photos.
 
+Migrate existing Postgres-stored bird photos after deploying S3 image storage:
+
+```bash
+docker compose -f docker-compose.prod.yml exec backend npm run migrate:bird-photos-to-s3 -- --apply
+```
+
+Run a dry run first by omitting `--apply`. Use `--limit=10` to migrate a small batch, and `--keep-data-url` if you want to leave the original inline image in Postgres during an initial verification pass.
+
 Bucket settings recommendation:
 
 - Enable bucket versioning if you want rollback protection from accidental overwrites or deletes. Add a lifecycle policy once upload volume is known because every object version contributes to stored data.

backend/package.json

@@ -8,6 +8,8 @@
     "worker:dev": "tsx watch src/worker.ts",
     "build": "tsc",
     "test": "tsx --test src/**/*.test.ts",
+    "migrate:bird-photos-to-s3": "node dist/scripts/migrateBirdPhotosToS3.js",
+    "migrate:bird-photos-to-s3:dev": "tsx src/scripts/migrateBirdPhotosToS3.ts",
     "start": "node dist/app.js",
     "worker": "node dist/worker.js"
   },

backend/src/scripts/migrateBirdPhotosToS3.ts

@@ -0,0 +1,134 @@
+import { db } from '../db/client.js';
+import { ensureSchema } from '../db/schema.js';
+import { buildBirdPhotoObjectKey, getImageExtensionFromContentType, getS3ImageStorageConfig } from '../storage/imageStorageConfig.js';
+import { deleteS3Object, putS3Object } from '../storage/s3Client.js';
+
+type BirdPhotoMigrationRow = {
+  id: string;
+  workspace_id: number;
+  name: string;
+  photo_data_url: string;
+};
+
+const parseDataImage = (dataUrl: string) => {
+  const match = /^data:(image\/[a-zA-Z0-9.+-]+);base64,(.+)$/.exec(dataUrl);
+  if (!match) {
+    return null;
+  }
+
+  return {
+    contentType: match[1],
+    content: Buffer.from(match[2], 'base64'),
+  };
+};
+
+const getArgValue = (name: string) => {
+  const prefix = `${name}=`;
+  const match = process.argv.find((arg) => arg.startsWith(prefix));
+  return match ? match.slice(prefix.length) : null;
+};
+
+const dryRun = !process.argv.includes('--apply');
+const keepDataUrl = process.argv.includes('--keep-data-url');
+const limitArg = getArgValue('--limit');
+const limit = limitArg ? Number(limitArg) : null;
+
+if (limit !== null && (!Number.isInteger(limit) || limit <= 0)) {
+  console.error('Invalid --limit value. Use a positive integer.');
+  process.exit(2);
+}
+
+const run = async () => {
+  await ensureSchema();
+
+  const s3Config = getS3ImageStorageConfig();
+
+  if (!s3Config) {
+    throw new Error('S3 image storage is not fully configured. Set IMAGE_STORAGE_PROVIDER=s3 and the S3_* environment variables.');
+  }
+
+  const result = await db.query<BirdPhotoMigrationRow>(
+    `SELECT id, workspace_id, name, photo_data_url
+     FROM birds
+     WHERE photo_object_key IS NULL
+       AND photo_data_url LIKE 'data:image/%'
+     ORDER BY created_at ASC
+     ${limit ? 'LIMIT $1' : ''}`,
+    limit ? [limit] : undefined,
+  );
+
+  if (dryRun) {
+    console.log(`Dry run: ${result.rows.length} bird photo(s) would be migrated to bucket ${s3Config.bucket}.`);
+    console.log('Run with --apply to upload objects and update rows.');
+    return;
+  }
+
+  let migrated = 0;
+  let skipped = 0;
+  let failed = 0;
+
+  for (const bird of result.rows) {
+    const parsedImage = parseDataImage(bird.photo_data_url);
+
+    if (!parsedImage) {
+      skipped += 1;
+      console.warn(`Skipping bird ${bird.id} (${bird.name}): invalid data URL.`);
+      continue;
+    }
+
+    const objectKey = buildBirdPhotoObjectKey({
+      workspaceId: bird.workspace_id,
+      birdId: bird.id,
+      extension: getImageExtensionFromContentType(parsedImage.contentType),
+    });
+
+    try {
+      await putS3Object({
+        config: s3Config,
+        objectKey,
+        content: parsedImage.content,
+        contentType: parsedImage.contentType,
+      });
+
+      const updateResult = await db.query(
+        `UPDATE birds
+         SET photo_object_key = $2,
+             photo_content_type = $3,
+             photo_updated_at = CURRENT_TIMESTAMP,
+             photo_data_url = CASE WHEN $4::boolean THEN photo_data_url ELSE NULL END
+         WHERE id = $1
+           AND photo_object_key IS NULL
+           AND photo_data_url LIKE 'data:image/%'`,
+        [bird.id, objectKey, parsedImage.contentType, keepDataUrl],
+      );
+
+      if (updateResult.rowCount !== 1) {
+        await deleteS3Object({ config: s3Config, objectKey });
+        skipped += 1;
+        console.warn(`Skipped bird ${bird.id} (${bird.name}): row changed before update.`);
+        continue;
+      }
+
+      migrated += 1;
+      console.log(`Migrated bird ${bird.id} (${bird.name}) -> ${objectKey}`);
+    } catch (error) {
+      failed += 1;
+      console.error(`Failed to migrate bird ${bird.id} (${bird.name}):`, error);
+    }
+  }
+
+  console.log(`Migration complete: migrated=${migrated}, skipped=${skipped}, failed=${failed}`);
+
+  if (failed > 0) {
+    process.exitCode = 1;
+  }
+};
+
+run()
+  .catch((error) => {
+    console.error('Bird photo migration failed:', error);
+    process.exitCode = 1;
+  })
+  .finally(async () => {
+    await db.close();
+  });