Extract pull request feature

.github/workflows/build.yml

@@ -16,9 +16,9 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Use Node.js
-        uses: actions/setup-node@v2
+        uses: actions/setup-node@v4
         with:
           node-version: 18.x
       - run: npm ci

3a

@@ -0,0 +1,45 @@
+name: Build
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+defaults:
+  run:
+    working-directory: transcript-orchestration
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 18.x
+      - run: npm ci
+      - run: npm run audit
+      - run: npm test
+        env:
+          AWS_REGION: "eu-west-1"
+      - name: Coveralls Parallel
+        uses: coverallsapp/github-action@master
+        with:
+          github-token: ${{ secrets.github_token }}
+          flag-name: run-node-18
+          parallel: true
+          path-to-lcov: transcript-orchestration/coverage/lcov.info
+  finish:
+    needs: build
+    runs-on: ubuntu-latest
+    steps:
+      - name: Coveralls Finished
+        uses: coverallsapp/github-action@master
+        with:
+          github-token: ${{ secrets.github_token }}
+          parallel-finished: true
+          path-to-lcov: transcript-orchestration/coverage/lcov.info

README.md

@@ -12,28 +12,27 @@ This project uses:
 - AWS Lambda for:
   - Merging the Whisper and Transcribe results
   - Substituting commonly 'misheard' words/proper nouns
-  - Creating a GitHub Pull Request against the podcast's website repository with the generated transcript (this is an optional step)
 - ...and Step Functions to orchestrate the whole process!
 
 This project consists of a few components, each with their own CloudFormation Stack:
 
 1. 👂 [whisper-image](./whisper-image), for creating an ECR container image repository where we store the SageMaker container to run the Whisper model
 2. 🪣 [data-resources](./data-resources) for shared data stores, namely an S3 Bucket
 3. 🧠 [sagemaker-resources](./sagemaker-resources) for the SageMaker model and IAM role
-4. 🎙 [transcript-orchestration](./transcript-orchestration), for orchestration, custom transcript processing and creating the transcript pull request
+4. 🎙 [transcript-orchestration](./transcript-orchestration), for orchestration and transcript merging 
 
 This project uses AWS SAM with nested stacks to deploy all but the first of these components. That first component is special, since we need to create the container image respository with [Amazon ECR](https://aws.amazon.com/ecr/) where we can push our custom Whisper container image. That makes the image available to be loaded by the SageMaker resources we can then create.
 
 ## Prerequisites
 
 You will need the following build tooling installed.
-- Node.js 16.x and NPM 8.x
+- Node.js 18.x and NPM 8.x
 - Docker, or other tooling that can build a container image from a `Dockerfile` and push it to a repository.
 - [AWS SAM](https://aws.amazon.com/serverless/sam/), used to build and deploy most of the application
 - The [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html)
 - esbuild
+- SLIC Watch: By default, the target AWS account should have the [SLIC Watch](https://github.com/fourTheorem/slic-watch) SAR Application installed. It can be installed by going to _[this page](https://serverlessrepo.aws.amazon.com/applications/eu-west-1/949339270388/slic-watch-app) in the AWS Console. SLIC Watch is used to create alarms and dashboards for our transcription application. If you want to skip this option, just remove the single line referring to the `SlicWatch-v2` macro from the relevant template, [transcript-orchestration/template.yaml](https://github.com/fourTheorem/podwhisperer/blob/cc73c5d4d52dc01f2249a032a9e2186012e24201/transcript-orchestration/template.yaml#L4).
 
-By default, the target AWS account should have the [SLIC Watch](https://github.com/fourTheorem/slic-watch) SAR Application installed. It can be installed by going to _[this page](https://serverlessrepo.aws.amazon.com/applications/eu-west-1/949339270388/slic-watch-app) in the AWS Console. SLIC Watch is used to create alarms and dashboards for our transcription application. If you want to skip this option, just remove the single line referring to the `SlicWatch-v2` macro from the relevant template, [transcript-orchestration/template.yaml](https://github.com/fourTheorem/podwhisperer/blob/cc73c5d4d52dc01f2249a032a9e2186012e24201/transcript-orchestration/template.yaml#L4).
 
 ## Getting Started
 
@@ -96,11 +95,6 @@ aws s3 cp sample-audio/sample1.mp3 s3://pod-transcription-${AWS_ACCOUNT_ID}-${AW
 
 That S3 object upload will create an EventBridge event to trigger the transcription Step Function. You can watch its progress in the Step Functions Console.
 
-## Configuration
-
-By default, the transcription workflow will attempt to create a Pull Request against a static website's GitHub repository. The GitHub repository is configured in the Pull Request Lambda Function's [environment variables](https://github.com/fourTheorem/podwhisperer/blob/cc73c5d4d52dc01f2249a032a9e2186012e24201/transcript-orchestration/template.yaml#L230). You can modify this, and the [pull request creation code](https://github.com/fourTheorem/podwhisperer/blob/main/transcript-orchestration/functions/pull-request/app.ts) if you want to have PRs with new transcripts created as part of the workflow.
-If you want to turn this feature off altogether, you can simply change the `createPR` default value in the Step Function's inputs from `true` to `false` [here](https://github.com/fourTheorem/podwhisperer/blob/cc73c5d4d52dc01f2249a032a9e2186012e24201/transcript-orchestration/statemachine/transcription-step-function.asl.json#L12).
-
 ### Step function architecture
 
 To have a better feeling for what the process looks like you can check out the following picture for a visualization of the Step Function definition:

transcript-orchestration/functions/audio-transcoder/tests/unit/app.test.ts

@@ -3,11 +3,11 @@ import { writeFile } from 'node:fs/promises'
 import { resolve } from 'node:path'
 
 import { mockClient } from 'aws-sdk-client-mock'
-import { sdkStreamMixin } from '@aws-sdk/util-stream-node'
+import { sdkStreamMixin } from '@smithy/util-stream'
 import { S3Client, PutObjectCommand, GetObjectCommand } from '@aws-sdk/client-s3'
 import { mockedContext } from '../../../mock-utils/lambda-context'
 import { test, expect, vi } from 'vitest'
-process.env.BUCKET_NAME = 'test-bucket'
+
 import * as app from '../../app'
 import * as transcode from '../../transcode'
 

transcript-orchestration/functions/lib/envs.ts

@@ -8,7 +8,7 @@ interface Environment {
  * This eliminates the need to check the existence of each environment variable where it is used.
  */
 const envProxy: Environment = new Proxy({}, {
-  get(target: Record<string, string>, name: string): string {
+  get(_target: Record<string, string>, name: string): string {
     const value = process.env[name]
     if (!value) {
       throw new Error(`Environment variable ${name} is not set`)

transcript-orchestration/functions/s3-keys/tests/unit/app.test.ts

@@ -1,8 +1,6 @@
 import { test, expect } from 'vitest'
 import { handleEvent, S3KeysEvent } from '../../app'
 
-process.env.BUCKET_NAME = 'test-bucket'
-
 const testState: { options?: S3KeysEvent } = {}
 
 test('constructs keys from audio input key', async (t) => {

transcript-orchestration/functions/transcript-processor/tests/unit/app.test.ts

@@ -3,14 +3,13 @@ import { Readable } from 'node:stream'
 import { resolve } from 'node:path'
 
 import { mockClient } from 'aws-sdk-client-mock'
-import { sdkStreamMixin } from '@aws-sdk/util-stream-node'
+import { sdkStreamMixin } from '@smithy/util-stream'
 import { S3Client, PutObjectCommand, GetObjectCommand } from '@aws-sdk/client-s3'
 import { test, assert } from 'vitest'
 
 import { VocabularySubstitutions } from '../../vocabulary'
 import { MergedTranscript } from '../../types'
 
-process.env.BUCKET_NAME = 'test-bucket'
 import { handleEvent } from '../../app'
 
 const mockS3 = mockClient(S3Client)