Merge pull request #3 from vinooganesh/vinooganesh/update-production

Update Production
vinooganesh · Feb 27, 2024 · 4515776 · 4515776
2 parents 7bc0b28 + 508110e
commit 4515776
Show file tree

Hide file tree

Showing 14 changed files with 75 additions and 21 deletions.
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -6,11 +6,11 @@ on:
 
 jobs:
   Build_and_Deploy_Site:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     concurrency:
       group: ${{ github.workflow }}-${{ github.ref }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           submodules: recursive
           fetch-depth: 0
@@ -21,12 +21,12 @@ jobs:
           hugo-version: 'latest'
           extended: true
 
-      - uses: actions/setup-node@v2
+      - uses: actions/setup-node@v4
         with:
-          node-version: '16'
+          node-version: '20'
 
       - name: Cache dependencies
-        uses: actions/cache@v1
+        uses: actions/cache@v4
         with:
           path: ~/.npm
           key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}

diff --git a/README.md b/README.md
@@ -37,7 +37,6 @@ To create documentation for a new release of `parquet-mr` create a new <releaseN
 # Website development and deployment
 
 ## Staging
-
 To make a change to the `staging` version of the website:
 1. Make a PR against the `staging` branch in the repository
 2. Once the PR is merged, the `Build and Deploy Parquet Site`

diff --git a/config.toml b/config.toml
@@ -10,9 +10,6 @@ enableMissingTranslationPlaceholders = true
 
 enableRobotsTXT = true
 
-# Base theme for website
-theme = ["docsy"]
-
 # Will give values to .Lastmod etc.
 enableGitInfo = true
 
@@ -47,9 +44,12 @@ anchor = "smart"
 
 [languages]
 [languages.en]
+languageName ="English"
+# Weight used for sorting.
+weight = 1
+[languages.en.params]
 title = "Apache Parquet"
 description = "The Apache Parquet Website"
-languageName ="English"
 contentDir = "content/en"
 # Weight used for sorting.
 weight = 1
@@ -98,13 +98,11 @@ url_latest_version = "https://parquet.apache.org"
 
 # Repository configuration (URLs for in-page links to opening issues and suggesting changes)
 github_repo = "https://github.com/apache/parquet-site"
+
 github_branch= "production"
 
 # Comment out to disable search.
-# gcs_engine_id = "7e3f91e3eadecceaa"
-
-# Enable Algolia DocSearch
-algolia_docsearch = true
+gcs_engine_id = "7e3f91e3eadecceaa"
 
 # Enable Lunr.js offline search
 offlineSearch = false
@@ -118,7 +116,7 @@ prism_syntax_highlighting = false
 #  Set to true to disable breadcrumb navigation.
 breadcrumb_disable = false
 # Set to true to disable the About link in the site footer
-footer_about_disable = false
+footer_about_enable = true
 # Set to false if you don't want to display a logo (/assets/icons/logo.svg) in the top navbar
 navbar_logo = true
 # Set to true if you don't want the top navbar to be translucent when over a `block/cover`, like on the homepage.
@@ -155,7 +153,7 @@ enable = false
   name ="Twitter"
   url = "https://twitter.com/ApacheParquet"
   icon = "fab fa-twitter"
-  desc = "Follow us on Twitter to get the latest news"
+  desc = "Follow us on Twitter to get the latest news!"
 [[params.links.user]]
   name = "Stack Overflow"
   url = "https://stackoverflow.com/questions/tagged/parquet"
@@ -166,7 +164,7 @@ enable = false
   name = "GitHub"
   url = "https://github.com/apache/parquet-mr"
   icon = "fab fa-github"
-  desc = "Development takes place here"
+  desc = "Development takes place here!"
 [[params.links.developer]]
   name = "Slack"
   url = "https://the-asf.slack.com/"
@@ -182,3 +180,13 @@ enable = false
   url = "https://issues.apache.org/jira/projects/PARQUET/issues"
   icon = "fas fa-bug"
   desc = "File/Track Open Bugs"
+
+[module]
+  # Uncomment the next line to build and serve using local docsy clone declared in the named Hugo workspace:
+  # workspace = "docsy.work"
+  [module.hugoVersion]
+    extended = true
+    min = "0.110.0"
+  [[module.imports]]
+    path = "github.com/google/docsy"
+    disable = false
diff --git a/content/en/_index.md b/content/en/_index.md
@@ -0,0 +1,31 @@
+---
+title: Parquet
+---
+
+{{< blocks/cover title="Apache Parquet" image_anchor="top" height="full" >}}
+<a class="btn btn-lg btn-primary me-3 mb-4" href="/docs/">
+  Documentation <i class="fas fa-arrow-alt-circle-right ms-2"></i>
+</a>
+<a class="btn btn-lg btn-secondary me-3 mb-4" href="/blog/">
+  Download <i class="fab fa-github ms-2 "></i>
+</a>
+<p class="lead mt-5">Apache Parquet is a columnar storage format available to any project in the Hadoop ecosystem, regardless of the choice of data processing framework, data model or programming language.</p>
+{{< blocks/link-down color="info" >}}
+{{< /blocks/cover >}}
+
+
+{{< blocks/section color="white" type="row">}}
+{{% blocks/feature icon="fab fa-jira" title="File an Issue" url="https://issues.apache.org/jira/projects/PARQUET/issues" %}}
+Or Search Open Issues
+{{% /blocks/feature %}}
+
+{{% blocks/feature icon="fab fa-github" title="Contributions welcome!" url="https://github.com/apache/parquet-mr" %}}
+We do a [Pull Request](https://github.com/apache/parquet-mr/pulls) contributions workflow on **GitHub**. New users are always welcome!
+{{% /blocks/feature %}}
+
+
+{{% blocks/feature icon="fab fa-twitter" title="Follow us on Twitter!" url="https://twitter.com/ApacheParquet" %}}
+For announcement of latest features etc.
+{{% /blocks/feature %}}
+
+{{% /blocks/section %}}
diff --git a/content/en/docs/Concepts/_index.md b/content/en/docs/Concepts/_index.md
@@ -5,6 +5,7 @@ weight: 4
 description: >
   Glossary of relevant terminology.
 ---
+
   - *Block (HDFS block)*: This means a block in HDFS and the meaning is
     unchanged for describing this file format.  The file format is
     designed to work well on top of HDFS.

diff --git a/content/en/docs/File Format/Data Pages/compression.md b/content/en/docs/File Format/Data Pages/compression.md
@@ -3,7 +3,6 @@ title: "Compression"
 linkTitle: "Compression"
 weight: 1
 ---
-
 ## Overview
 
 Parquet allows the data block inside dictionary pages and data pages to

diff --git a/content/en/docs/File Format/Data Pages/encryption.md b/content/en/docs/File Format/Data Pages/encryption.md
@@ -3,7 +3,6 @@ title: "Parquet Modular Encryption"
 linkTitle: "Encryption"
 weight: 1
 ---
-
 Parquet files containing sensitive information can be protected by the modular encryption 
 mechanism that encrypts and authenticates the file data and metadata - while allowing 
 for a regular Parquet functionality (columnar projection, predicate pushdown, encoding 

diff --git a/content/en/docs/File Format/Types/_index.md b/content/en/docs/File Format/Types/_index.md
@@ -4,6 +4,7 @@ linkTitle: "Types"
 weight: 5
 ---
 
+
 The types supported by the file format are intended to be as minimal as possible,
 with a focus on how the types effect on disk storage.  For example, 16-bit ints
 are not explicitly supported in the storage format since they are covered by

diff --git a/content/en/docs/File Format/Types/logicaltypes.md b/content/en/docs/File Format/Types/logicaltypes.md
@@ -10,4 +10,4 @@ of primitive types to a minimum and reuses parquet's efficient encodings. For
 example, strings are stored as byte arrays (binary) with a UTF8 annotation.
 These annotations define how to further decode and interpret the data.
 Annotations are stored as `LogicalType` fields in the file metadata and are
-documented in LogicalTypes.md.
+documented in LogicalTypes.md.
diff --git a/content/en/docs/File Format/configurations.md b/content/en/docs/File Format/configurations.md
@@ -5,6 +5,7 @@ weight: 5
 ---
 
 ### Row Group Size
+
 Larger row groups allow for larger column chunks which makes it
 possible to do larger sequential IO.  Larger groups also require more buffering in
 the write path (or a two pass write).  We recommend large row groups (512MB - 1GB).
@@ -18,4 +19,4 @@ Data pages should be considered indivisible so smaller data pages
 allow for more fine grained reading (e.g. single row lookup).  Larger page sizes
 incur less space overhead (less page headers) and potentially less parsing overhead
 (processing headers).  Note: for sequential scans, it is not expected to read a page
-at a time; this is not the IO chunk.  We recommend 8KB for page sizes.
+at a time; this is not the IO chunk.  We recommend 8KB for page sizes.
diff --git a/content/en/docs/File Format/metadata.md b/content/en/docs/File Format/metadata.md
@@ -6,4 +6,5 @@ weight: 5
 There are three types of metadata: file metadata, column (chunk) metadata and page
 header metadata.  All thrift structures are serialized using the TCompactProtocol.
 
+
 ![File Layout](/images/FileFormat.gif)
diff --git a/content/en/search.md b/content/en/search.md
@@ -0,0 +1,5 @@
+---
+title: Search Results
+layout: search
+
+---
diff --git a/go.mod b/go.mod
@@ -0,0 +1,5 @@
+module github.com/apache/parquet-site
+
+go 1.23
+
+require github.com/google/docsy v0.9.1 // indirect
diff --git a/go.sum b/go.sum
@@ -0,0 +1,4 @@
+github.com/FortAwesome/Font-Awesome v0.0.0-20240108205627-a1232e345536/go.mod h1:IUgezN/MFpCDIlFezw3L8j83oeiIuYoj28Miwr/KUYo=
+github.com/google/docsy v0.9.1 h1:+jqges1YCd+yHeuZ1BUvD8V8mEGVtPxULg5j/vaJ984=
+github.com/google/docsy v0.9.1/go.mod h1:saOqKEUOn07Bc0orM/JdIF3VkOanHta9LU5Y53bwN2U=
+github.com/twbs/bootstrap v5.2.3+incompatible/go.mod h1:fZTSrkpSf0/HkL0IIJzvVspTt1r9zuf7XlZau8kpcY0=