From 78bce2d1e7984645df0d1f5f05307c2f688a841a Mon Sep 17 00:00:00 2001
From: Hongbo Wu <hongbo@omnivore.app>
Date: Tue, 4 Oct 2022 09:51:42 +0800
Subject: [PATCH] Add Dockerfile for cloud run

---
 packages/inbound-email-handler/Dockerfile   |  28 +++++
 packages/inbound-email-handler/package.json |   2 +-
 packages/puppeteer-parse/Dockerfile         |  11 +-
 packages/puppeteer-parse/Dockerfile-preview | 111 ++++++++++++++++++++
 packages/puppeteer-parse/package.json       |   6 +-
 yarn.lock                                   |  13 +--
 6 files changed, 152 insertions(+), 19 deletions(-)
 create mode 100644 packages/inbound-email-handler/Dockerfile
 create mode 100644 packages/puppeteer-parse/Dockerfile-preview

diff --git a/packages/inbound-email-handler/Dockerfile b/packages/inbound-email-handler/Dockerfile
new file mode 100644
index 000000000..e6cf56c11
--- /dev/null
+++ b/packages/inbound-email-handler/Dockerfile
@@ -0,0 +1,28 @@
+FROM node:14.18-alpine
+
+# Run everything after as non-privileged user.
+WORKDIR /app
+
+COPY package.json .
+COPY yarn.lock .
+COPY tsconfig.json .
+COPY .prettierrc .
+COPY .eslintrc .
+
+COPY /packages/content-handler/package.json ./packages/content-handler/package.json
+
+RUN yarn install --pure-lockfile
+
+ADD /packages/inbound-email-handler ./packages/inbound-email-handler
+ADD /packages/content-handler ./packages/content-handler
+RUN yarn workspace @omnivore/content-handler build
+
+# After building, fetch the production dependencies
+RUN rm -rf /app/packages/inbound-email-handler/node_modules
+RUN rm -rf /app/node_modules
+RUN yarn install --pure-lockfile --production
+
+EXPOSE 8080
+
+CMD ["yarn", "workspace", "@omnivore/inbound-email-handler", "start"]
+
diff --git a/packages/inbound-email-handler/package.json b/packages/inbound-email-handler/package.json
index 61173efcb..b11c89e31 100644
--- a/packages/inbound-email-handler/package.json
+++ b/packages/inbound-email-handler/package.json
@@ -29,7 +29,7 @@
   "dependencies": {
     "@google-cloud/functions-framework": "3.1.2",
     "@google-cloud/pubsub": "^2.18.4",
-    "@omnivore/content-handler": "file:./content-handler",
+    "@omnivore/content-handler": "file:./../content-handler",
     "@sendgrid/client": "^7.6.0",
     "@sentry/serverless": "^6.16.1",
     "addressparser": "^1.0.1",
diff --git a/packages/puppeteer-parse/Dockerfile b/packages/puppeteer-parse/Dockerfile
index d3ce96e20..771aa0f5b 100644
--- a/packages/puppeteer-parse/Dockerfile
+++ b/packages/puppeteer-parse/Dockerfile
@@ -92,13 +92,20 @@ COPY tsconfig.json .
 COPY .prettierrc .
 COPY .eslintrc .
 
-COPY /packages/puppeteer-parse/package.json ./packages/puppeteer-parse/package.json
+COPY /packages/content-handler/package.json ./packages/content-handler/package.json
 
 RUN yarn install --pure-lockfile
 
 ADD /packages/puppeteer-parse ./packages/puppeteer-parse
+ADD /packages/content-handler ./packages/content-handler
+RUN yarn workspace @omnivore/content-handler build
 
-EXPOSE 8080
+# After building, fetch the production dependencies
+RUN rm -rf /app/packages/puppeteer-parse/node_modules
+RUN rm -rf /app/node_modules
+RUN yarn install --pure-lockfile --production
+
+EXPOSE 9090
 
 # USER pptruser
 ENTRYPOINT ["yarn", "workspace", "@omnivore/puppeteer-parse", "start"]
diff --git a/packages/puppeteer-parse/Dockerfile-preview b/packages/puppeteer-parse/Dockerfile-preview
new file mode 100644
index 000000000..7379c0c31
--- /dev/null
+++ b/packages/puppeteer-parse/Dockerfile-preview
@@ -0,0 +1,111 @@
+# FROM node:14-slim
+
+# # Taken from pu
+
+# # Install latest chrome dev package and fonts to support major charsets (Chinese, Japanese, Arabic, Hebrew, Thai and a few others)
+# # Note: this installs the necessary libs to make the bundled version of Chromium that Puppeteer
+# # installs, work.
+# RUN apt-get update \
+#     && apt-get install -y wget gnupg \
+#     && wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
+#     && sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google.list' \
+#     && apt-get update \
+#     && apt-get install -y google-chrome-stable fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst fonts-freefont-ttf libxss1 \
+#       --no-install-recommends \
+#     && rm -rf /var/lib/apt/lists/*
+
+# ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD true
+# ENV CHROMIUM_PATH "/usr/bin/google-chrome-stable"
+
+# ------------------------
+
+# FROM --platform=linux/arm64 node:14.18
+
+# RUN apt-get update \
+#   && apt-get install -y chromium \
+#   && apt-get install -y ca-certificates \
+#   fonts-liberation \
+#   libappindicator3-1 \
+#   libasound2 \
+#   libatk-bridge2.0-0 \
+#   libatk1.0-0 \
+#   libc6 \
+#   libcairo2 \
+#   libcups2 \
+#   libdbus-1-3 \
+#   libexpat1 \
+#   libfontconfig1 \
+#   libgbm1 \
+#   libgcc1 \
+#   libglib2.0-0 \
+#   libgtk-3-0 \
+#   libnspr4 \
+#   libnss3 \
+#   libpango-1.0-0 \
+#   libpangocairo-1.0-0 \
+#   libstdc++6 \
+#   libx11-6 \
+#   libx11-xcb1 \
+#   libxcb1 \
+#   libxcomposite1 \
+#   libxcursor1 \
+#   libxdamage1 \
+#   libxext6 \
+#   libxfixes3 \
+#   libxi6 \
+#   libxrandr2 \
+#   libxrender1 \
+#   libxss1 \
+#   libxtst6 \
+#   lsb-release \
+#   wget \
+#   xdg-utils
+
+FROM node:14.18-alpine
+
+# Installs latest Chromium (92) package.
+RUN apk add --no-cache \
+      chromium \
+      nss \
+      freetype \
+      harfbuzz \
+      ca-certificates \
+      ttf-freefont \
+      nodejs \
+      yarn
+
+# Add user so we don't need --no-sandbox.
+RUN addgroup -S pptruser && adduser -S -g pptruser pptruser \
+    && mkdir -p /home/pptruser/Downloads /app \
+    && chown -R pptruser:pptruser /home/pptruser \
+    && chown -R pptruser:pptruser /app
+
+# Run everything after as non-privileged user.
+WORKDIR /app
+
+ENV CHROMIUM_PATH /usr/bin/chromium-browser
+ENV LAUNCH_HEADLESS=true
+
+COPY package.json .
+COPY yarn.lock .
+COPY tsconfig.json .
+COPY .prettierrc .
+COPY .eslintrc .
+
+COPY /packages/content-handler/package.json ./packages/content-handler/package.json
+
+RUN yarn install --pure-lockfile
+
+ADD /packages/puppeteer-parse ./packages/puppeteer-parse
+ADD /packages/content-handler ./packages/content-handler
+RUN yarn workspace @omnivore/content-handler build
+
+# After building, fetch the production dependencies
+RUN rm -rf /app/packages/puppeteer-parse/node_modules
+RUN rm -rf /app/node_modules
+RUN yarn install --pure-lockfile --production
+
+EXPOSE 8080
+
+# USER pptruser
+ENTRYPOINT ["yarn", "workspace", "@omnivore/puppeteer-parse", "start_preview"]
diff --git a/packages/puppeteer-parse/package.json b/packages/puppeteer-parse/package.json
index 8db80fc53..96109b9d1 100644
--- a/packages/puppeteer-parse/package.json
+++ b/packages/puppeteer-parse/package.json
@@ -4,9 +4,10 @@
   "description": "Google Cloud Function that accepts URL of the article and parses its content",
   "main": "index.js",
   "dependencies": {
+    "@google-cloud/functions-framework": "^3.1.2",
     "@google-cloud/logging-winston": "^5.1.1",
     "@google-cloud/storage": "^5.18.1",
-    "@omnivore/content-handler": "file:./content-handler",
+    "@omnivore/content-handler": "file:./../content-handler",
     "@sentry/serverless": "^6.13.3",
     "axios": "^0.27.2",
     "chrome-aws-lambda": "^10.1.0",
@@ -18,9 +19,6 @@
     "underscore": "^1.13.4",
     "winston": "^3.3.3"
   },
-  "devDependencies": {
-    "@google-cloud/functions-framework": "^3.0.0"
-  },
   "scripts": {
     "start": "npx functions-framework --port=9090 --target=puppeteer",
     "start_preview": "npx functions-framework --target=preview",
diff --git a/yarn.lock b/yarn.lock
index f60474b2a..ed80ba88e 100644
--- a/yarn.lock
+++ b/yarn.lock
@@ -2390,7 +2390,7 @@
     google-gax "^2.24.1"
     protobufjs "^6.8.6"
 
-"@google-cloud/functions-framework@3.1.2", "@google-cloud/functions-framework@^3.0.0":
+"@google-cloud/functions-framework@3.1.2", "@google-cloud/functions-framework@^3.1.2":
   version "3.1.2"
   resolved "https://registry.yarnpkg.com/@google-cloud/functions-framework/-/functions-framework-3.1.2.tgz#2cd92ce4307bf7f32555d028dca22e398473b410"
   integrity sha512-pYvEH65/Rqh1JNPdcBmorcV7Xoom2/iOSmbtYza8msro7Inl+qOYxbyMiQfySD2gwAyn38WyWPRqsDRcf/BFLg==
@@ -4323,17 +4323,6 @@
     underscore "^1.13.6"
     uuid "^9.0.0"
 
-"@omnivore/content-handler@file:./packages/inbound-email-handler/content-handler":
-  version "1.0.0"
-  dependencies:
-    addressparser "^1.0.1"
-    axios "^0.27.2"
-    linkedom "^0.14.16"
-    luxon "^3.0.4"
-    rfc2047 "^4.0.1"
-    underscore "^1.13.6"
-    uuid "^9.0.0"
-
 "@opentelemetry/api-metrics@0.27.0":
   version "0.27.0"
   resolved "https://registry.yarnpkg.com/@opentelemetry/api-metrics/-/api-metrics-0.27.0.tgz#d8eca344ed1155f3ea8a8133ade827b4bb90efbf"