List GCP cloud bucket files over a certain size

README.md

List bucket files over certain size node.js / Typescript

Install

Install gcloud https://cloud.google.com/sdk/docs/install

Login and set project

gcloud init
# or just authorize
gcloud auth login
# then set project to the one that contains bucket
gcloud config set project [project-name]

Install script dependencies

npm i ts-node firebase firebase-admin typescript yargs @types/node

Run

Run with ts-node and pass in bucket name and max file size (e.g. 10MB)

ts-node ./index.ts  -b your-bucket.appspot.com -m 10

Logs values to console and also creates a large-files.log file with path, url and size.

index.ts

import { initializeApp } from "firebase-admin/app";
import yargs from "yargs";
import fs from "fs";
import { hideBin } from "yargs/helpers";
import { getStorage } from "firebase-admin/storage";

const argv = yargs(hideBin(process.argv))
  .option("bucket", {
    alias: "b",
    description: "bucket to copy images to",
    type: "string",
    demandOption: true,
  })
  .option("maxSizeMB", {
    alias: "m",
    description: "Max file size in MB",
    type: "number",
    demandOption: true,
  })
  .parse();

// Initialize Firebase
initializeApp({
  storageBucket: argv["bucket"],
});

function logError(msg: string, file = "large-files-error.log") {
  console.error(msg);
  return fs.promises.appendFile(file, `${msg}\n`);
}

function log(msg: string, file = "large-files.log") {
  console.log(msg);
  return fs.promises.appendFile(file, `${msg}\n`);
}

const MB = 1024 * 1024;

try {
  const run = async () => {
    const storage = getStorage();
    const bucket = storage.bucket();

    bucket
      .getFilesStream()
      .on("data", (file) => {
        const size = parseInt(file.metadata.size, 10);
        if (size > argv["maxSizeMB"] * MB) {
          log(`${file.name}
URL: https://storage.googleapis.com/${argv["bucket"]}/${file.name}
Size: ${(size / 1024 / 1024).toFixed(2)}MB
--------------------`);
        }
      })
      .on("error", (e) => {
        console.error(e);
      })
      .on("end", () => {
        console.log("done");
      });
  };
  run();
} catch (e) {
  logError(e);
}