Merge branch 'main' into main

.github/workflows/deploy-website.yml

@@ -0,0 +1,54 @@
+name: Deploy to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+    # Review gh actions docs if you want to further define triggers, paths, etc
+    # https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#on
+
+jobs:
+  build:
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: yarn
+          cache-dependency-path: ./docs/yarn.lock
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+        working-directory: ./docs
+      - name: Build website
+        run: yarn build
+        working-directory: ./docs
+
+      - name: Upload Build Artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ./docs/build # Override path to match your build output location
+
+  deploy:
+    name: Deploy to GitHub Pages
+    needs: build
+
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write # to deploy to Pages
+      id-token: write # to verify the deployment originates from an appropriate source
+
+    # Deploy to the github-pages environment
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/test-website.yml

@@ -0,0 +1,28 @@
+name: Test deployment
+
+on:
+  pull_request:
+    branches:
+      - main
+    # Review gh actions docs if you want to further define triggers, paths, etc
+    # https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#on
+
+jobs:
+  test-deploy:
+    name: Test deployment
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: yarn
+          cache-dependency-path: ./docs/yarn.lock
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+        working-directory: ./docs
+      - name: Test build website
+        run: yarn build
+        working-directory: ./docs

.gitpod.yml

@@ -1,6 +1,6 @@
 tasks:
   - command: |
-      DOCKER_BUILDKIT=1 ./docker/up.sh --seed
+      DOCKER_BUILDKIT=1 ./docker/up.sh --seed --no-search
 ports:
   - port: 3000
     visibility: public

CODE_QUALITY_AND_SECURITY.md

@@ -26,7 +26,7 @@ The specific security and analysis methodologies that we employ include but are
 
 For more information about our approach to quality and security, feel free to reach out to the Marquez development team:
 
-- Slack: [Marquezproject.slack.com](https://bit.ly/Marquez_Slack_invite)
+- Slack: [Marquezproject.slack.com](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A)
 - Twitter: [@MarquezProject](https://twitter.com/MarquezProject)
 
 ----

CONTRIBUTING.md

@@ -3,14 +3,14 @@
 We're excited you're interested in contributing to Marquez! We'd love your help, and there are plenty of ways to contribute:
 
 * Give the repo a star
-* Join our [slack](https://bit.ly/Marquez_Slack_invite) channel and leave us feedback or help with answering questions from the community
+* Join our [slack](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A) channel and leave us feedback or help with answering questions from the community
 * Fix or [report](https://github.com/MarquezProject/marquez/issues/new) a bug
 * Fix or improve documentation
 * For newcomers, pick up a ["good first issue"](https://github.com/MarquezProject/marquez/labels/good%20first%20issue), then send a pull request our way (see the [resources](#resources) section below for helpful links to get started)
 
 We feel that a welcoming community is important and we ask that you follow the [Contributor Covenant Code of Conduct](https://github.com/MarquezProject/marquez/blob/main/CODE_OF_CONDUCT.md) in all interactions with the community.
 
-If you’re interested in using or learning more about Marquez, reach out to us on our [slack](https://bit.ly/Marquez_Slack_invite) channel and follow [@MarquezProject](https://twitter.com/MarquezProject) for updates. We also encourage new comers to [join](https://lists.lfaidata.foundation/g/marquez-technical-discuss/ics/invite.ics?repeatid=32038) our monthly community meeting!
+If you’re interested in using or learning more about Marquez, reach out to us on our [slack](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A) channel and follow [@MarquezProject](https://twitter.com/MarquezProject) for updates. We also encourage new comers to [join](https://lists.lfaidata.foundation/g/marquez-technical-discuss/ics/invite.ics?repeatid=32038) our monthly community meeting!
 
 # Getting Your Changes Approved
 

GOVERNANCE.md

@@ -100,7 +100,7 @@ Or a meeting may be at an organization's offices that are required to maintain a
 
 ## Marquez on Slack
 
-Marquez uses [a Slack community](https://bit.ly/Marquez_Slack_invite) to provide an ongoing dialogue between members.
+Marquez uses [a Slack community](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A) to provide an ongoing dialogue between members.
 This creates a recorded discussion of design decisions and discussions that complement the project meetings.
 
 Follow the link above and register with the Slack service using your email address.

README.md

@@ -12,7 +12,7 @@ Marquez is an open source **metadata service** for the **collection**, **aggrega
 [![CircleCI](https://circleci.com/gh/MarquezProject/marquez/tree/main.svg?style=shield)](https://circleci.com/gh/MarquezProject/marquez/tree/main)
 [![codecov](https://codecov.io/gh/MarquezProject/marquez/branch/main/graph/badge.svg)](https://codecov.io/gh/MarquezProject/marquez/branch/main)
 [![status](https://img.shields.io/badge/status-active-brightgreen.svg)](#status)
-[![Slack](https://img.shields.io/badge/slack-chat-blue.svg)](https://bit.ly/Marquez_Slack_invite)
+[![Slack](https://img.shields.io/badge/slack-chat-blue.svg)](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A)
 [![license](https://img.shields.io/badge/license-Apache_2.0-blue.svg)](https://raw.githubusercontent.com/MarquezProject/marquez/main/LICENSE)
 [![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-v2.0%20adopted-ff69b4.svg)](CODE_OF_CONDUCT.md)
 [![maven](https://img.shields.io/maven-central/v/io.github.marquezproject/marquez-api.svg)](https://search.maven.org/search?q=g:io.github.marquezproject)
@@ -32,6 +32,7 @@ Want to be added? Send a pull request our way!
 * [Datakin](https://datakin.com)
 * [Northwestern Mutual](https://www.northwesternmutual.com)
 * [Ilum](https://ilum.cloud)
+* [CsvPath](https://www.csvpath.org)
 
 ## Try it!
 
@@ -177,9 +178,9 @@ Marquez listens on port `8080` for all API calls and port `8081` for the admin i
 
 ## Getting Involved
 
-* Website: https://marquezproject.ai
+* Website: https://marquezproject.github.io/marquez/
 * Source: https://github.com/MarquezProject/marquez
-* Chat: [MarquezProject Slack](https://bit.ly/Marquez_Slack_invite)
+* Chat: [MarquezProject Slack](https://join.slack.com/t/marquezproject/shared_invite/zt-2iylxasbq-GG_zXNcJdNrhC9uUMr3B7A)
 * X: [@MarquezProject](https://twitter.com/MarquezProject)
 
 ## Contributing

api/src/main/java/marquez/db/DatasetFacetsDao.java

@@ -153,9 +153,9 @@ default void insertDatasetFacetsFor(
   default void insertInputDatasetFacetsFor(
       @NonNull UUID datasetUuid,
       @NonNull UUID datasetVersionUuid,
-      @NonNull UUID runUuid,
+      @Nullable UUID runUuid,
       @NonNull Instant lineageEventTime,
-      @NonNull String lineageEventType,
+      @Nullable String lineageEventType,
       @NonNull LineageEvent.InputDatasetFacets inputFacets) {
     final Instant now = Instant.now();
 
@@ -179,9 +179,9 @@ default void insertInputDatasetFacetsFor(
   default void insertOutputDatasetFacetsFor(
       @NonNull UUID datasetUuid,
       @NonNull UUID datasetVersionUuid,
-      @NonNull UUID runUuid,
+      @Nullable UUID runUuid,
       @NonNull Instant lineageEventTime,
-      @NonNull String lineageEventType,
+      @Nullable String lineageEventType,
       @NonNull LineageEvent.OutputDatasetFacets outputFacets) {
     final Instant now = Instant.now();
 

api/src/main/java/marquez/db/OpenLineageDao.java

@@ -815,6 +815,9 @@ default void updateMarquezOnStreamingJob(
   }
 
   default String getUrlOrNull(String uri) {
+    if (uri == null) {
+      return "";
+    }
     try {
       return new URI(uri).toASCIIString();
     } catch (URISyntaxException e) {

api/src/test/java/marquez/db/OpenLineageDaoTest.java

@@ -310,6 +310,11 @@ void testUpdateMarquezModelDatasetWithColumnLineageFacetWhenOutputFieldDoesNotEx
     assertEquals(0, writeJob.getOutputs().get().get(0).getColumnLineageRows().size());
   }
 
+  @Test
+  void testGetUrlOrNullReturnsEmptyString() {
+    assertEquals("", dao.getUrlOrNull(null));
+  }
+
   @Test
   /**
    * When trying to insert new column level lineage data, do not create additional row if triad

chart/templates/web/deployment.yaml

@@ -45,6 +45,8 @@ spec:
               value: {{ include "common.names.fullname" . }}
             - name: MARQUEZ_PORT
               value: {{ .Values.service.port | quote }}
+            - name: WEB_PORT
+              value: {{ .Values.web.port | quote }}
           {{- if .Values.web.resources }}
           resources: {{- toYaml .Values.web.resources | nindent 12 }}
           {{- end }}

clients/python/setup.py

@@ -15,6 +15,7 @@
     "six",
     "pyrfc3339",
     "deprecation",
+    "pytz",
 ]
 
 extras_require = {

docker-compose.yml

@@ -6,6 +6,7 @@ services:
     environment:
       - MARQUEZ_PORT=${API_PORT}
       - MARQUEZ_ADMIN_PORT=${API_ADMIN_PORT}
+      - POSTGRES_HOST=db
       - SEARCH_ENABLED=${SEARCH_ENABLED}
     ports:
       - "${API_PORT}:${API_PORT}"