From b7818d50b0dc1ffa662a64a02e53064395f396b3 Mon Sep 17 00:00:00 2001
From: Jan Pelikan <jan.pelikan@packeta.com>
Date: Tue, 24 Sep 2024 22:54:49 +0200
Subject: [PATCH] feat(parser): Add Docker support with new parameter for
 output path - review suggestions from PR accepted and implemented

- **Dockerfile**:
  - Fixed obsolete definition of ENVIROMENT variables to correct syntax.
  - Added source link for more information about depebdencies for Puppeteer respectivly Chromium/Chrome in Docker.
  - Dockerfiile moved to `parser` directory.
  - Updated path for `COPY` command.
  - Removed commented code for creataing a new user in Docker. This is not needed for the current implementation.

- **README.md**:
  - Section for Docker updated with new instructions.

- **app.ts**:
  -  Variable `outputPath`: Default value is set to `./out`. Variable is now validated twice.
  -  Variable `outputPath`: Always is checked if path exists. If not, it will be created.
  -  Added source link for more information about calling Chrome/Chromium with `--no-sandbox` flag in Docker while running Puppeteer.
---
 README.md                       |  3 ++-
 Dockerfile => parser/Dockerfile | 25 +++++++++----------------
 parser/src/app.ts               |  8 ++++++--
 3 files changed, 17 insertions(+), 19 deletions(-)
 rename Dockerfile => parser/Dockerfile (64%)

diff --git a/README.md b/README.md
index 57e5301..090b7d6 100644
--- a/README.md
+++ b/README.md
@@ -131,9 +131,10 @@ Fields:
 You can build a `Docker` image for the `azure-vm-pricing`:
 
 ```bash
+# Parser Docker image
+cd parser
 # For Linux machines running on x86_64 or in Windows WSL
 docker build -f ./Dockerfile --platform linux/amd64 --build-arg ARCH=amd64 -t azure-vm-pricing .
-
 # For Linux machines running on arm64, for example Apple Macbooks with Apple Silicon
 docker build -f ./Dockerfile --platform linux/arm64 --build-arg ARCH=arm64 -t azure-vm-pricing .
 ```
diff --git a/Dockerfile b/parser/Dockerfile
similarity index 64%
rename from Dockerfile
rename to parser/Dockerfile
index 0ed1aea..f8c8845 100644
--- a/Dockerfile
+++ b/parser/Dockerfile
@@ -5,9 +5,9 @@ ARG ARCH=amd64
 FROM $ARCH/node:22-slim
 
 # Do not download Chromium, will be installed manually from Debian repositories
-ENV PUPPETEER_SKIP_DOWNLOAD true
+ENV PUPPETEER_SKIP_DOWNLOAD=true
 # Set the path to the Chromium executable
-ENV PUPPETEER_EXECUTABLE_PATH "/usr/bin/chromium"
+ENV PUPPETEER_EXECUTABLE_PATH="/usr/bin/chromium"
 
 # Create a directory for the app
 WORKDIR /app
@@ -18,7 +18,9 @@ RUN mkdir /data
 # Set volume for the app data
 VOLUME /data
 
-# Install dependencies
+# Install dependencies for Puppeteer respectively Chromium/Chrome
+# https://github.com/puppeteer/puppeteer/blob/main/docs/troubleshooting.md#running-puppeteer-on-gitlabci
+# hadolint ignore=DL3008
 RUN apt-get update && apt-get install -y \
   wget \
   ca-certificates \
@@ -62,18 +64,9 @@ RUN apt-get update && apt-get install -y \
   && apt-get clean \
   && rm -rf /var/lib/apt/lists/*
 
-# Copy the app files (azure-vm-pricing) to the container
-COPY ./parser .
-
-# When use a non-root user, the processes under the user will not have access to mounted volumes for some reason
-# # Create a non-root user to run Puppeteer
-# RUN groupadd -r pptruser && useradd -r -g pptruser -G audio,video pptruser \
-#   && mkdir -p /home/pptruser/Downloads \
-#   && chown -R pptruser:pptruser /home/pptruser \
-#   && chown -R pptruser:pptruser /app
-
-# # Switch to the non-root user
-# USER pptruser
+# Copy the app files (azure-vm-pricing/parser) to the container
+COPY ./ .
 
 # Install Yarn and dependencies
-RUN yarn install
+RUN yarn install \
+  && yarn cache clean
diff --git a/parser/src/app.ts b/parser/src/app.ts
index 7949fd0..990ace9 100644
--- a/parser/src/app.ts
+++ b/parser/src/app.ts
@@ -8,7 +8,8 @@ import { isUrlBlocked } from './isUrlBlocked';
 import { writeCsv, writeJson } from './writeFile';
 import { AzurePortal, getPrice, getPricing } from './azurePortalExtensions';
 
-let outputPath: string | undefined;
+// If outputPath is not provided, the default value is './out'
+let outputPath: string | undefined = './out';
 
 let recordTiming = false;
 let previousPerformanceNow = 0;
@@ -96,10 +97,12 @@ function timeEvent(eventName: string): void {
         case '-p':
         case '--output-path':
           outputPath = args[offset + 1];
-          // If the output path is not defined or is an empty string, use the default path
+          // Assign default if undefined or empty
           if (outputPath === undefined || outputPath === '') {
             outputPath = './out';
           }
+          // Ensure the path exists
+          fs.mkdirSync(outputPath, { recursive: true });
           break;
         default:
           parsedBinaryArg = false;
@@ -131,6 +134,7 @@ function timeEvent(eventName: string): void {
 
   timeEvent('chromeStartedAt');
   // --no-sandbox and --disable-setuid-sandbox are required for running in a Docker container
+  // More info: https://github.com/puppeteer/puppeteer/blob/main/docs/troubleshooting.md#running-puppeteer-on-gitlabci
   const browser = await puppeteer.launch({headless: headlessMode, args: ['--no-sandbox', '--disable-setuid-sandbox']});
   const page = await browser.newPage();
   timeEvent('chromeLaunchedAt');