You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by vi...@apache.org on 2019/09/20 14:11:51 UTC
[incubator-hudi] branch asf-site updated: Updating site to reflect
recent doc changes (#896)
This is an automated email from the ASF dual-hosted git repository.
vinoth pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/incubator-hudi.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 4d78107 Updating site to reflect recent doc changes (#896)
4d78107 is described below
commit 4d7810788ff388f76c6fc89c5176672d9af245fc
Author: Bhavani Sudha Saktheeswaran <bh...@uber.com>
AuthorDate: Fri Sep 20 07:11:46 2019 -0700
Updating site to reflect recent doc changes (#896)
This comprises changes from recent commits into asf-site branch that happened after previous site update
---
content/404.html | 34 +-
content/Dockerfile | 30 ++
content/Gemfile | 11 +
content/Gemfile.lock | 71 +++++
content/README.md | 46 +++
content/admin_guide.html | 139 ++++-----
content/{ => cn}/404.html | 71 +++--
content/{ => cn}/admin_guide.html | 176 +++++------
content/{ => cn}/community.html | 77 ++---
content/{ => cn}/comparison.html | 71 +++--
content/{ => cn}/concepts.html | 83 ++---
content/{ => cn}/configurations.html | 81 ++---
content/{ => cn}/contributing.html | 71 +++--
content/{ => cn}/docker_demo.html | 191 ++++++------
.../events/2016-12-30-strata-talk-2017.html} | 91 +++---
.../events/2019-01-18-asf-incubation.html} | 90 +++---
content/{ => cn}/gcs_hoodie.html | 76 ++---
content/{ => cn}/index.html | 75 +++--
content/{ => cn}/migration_guide.html | 76 ++---
content/{ => cn}/news.html | 108 ++++---
content/{ => cn}/news_archive.html | 92 +++---
content/{ => cn}/performance.html | 92 +++---
content/{ => cn}/powered_by.html | 67 ++--
content/{ => cn}/privacy.html | 71 +++--
content/{ => cn}/querying_data.html | 93 +++---
content/{ => cn}/quickstart.html | 154 +++++-----
content/{ => cn}/s3_hoodie.html | 81 ++---
content/{powered_by.html => cn/use_cases.html} | 195 ++++++------
content/{ => cn}/writing_data.html | 101 +++---
content/community.html | 42 ++-
content/comparison.html | 34 +-
content/concepts.html | 46 ++-
content/configurations.html | 44 +--
content/contributing.html | 34 +-
content/docker-compose.yml | 13 +
content/docker_demo.html | 341 ++++++++++++++++-----
.../2016-12-30-strata-talk-2017.html} | 54 ++--
.../2019-01-18-asf-incubation.html} | 53 ++--
content/feed.xml | 39 +--
content/gcs_hoodie.html | 39 ++-
content/index.html | 38 ++-
content/js/mydoc_scroll.html | 34 +-
content/migration_guide.html | 39 ++-
content/news.html | 91 ++++--
content/news_archive.html | 55 ++--
content/performance.html | 55 ++--
content/powered_by.html | 26 +-
content/privacy.html | 34 +-
content/querying_data.html | 56 ++--
content/quickstart.html | 26 +-
content/s3_hoodie.html | 44 +--
content/search.json | 285 +++++++++++++++--
content/sitemap.xml | 180 +++++++++--
content/use_cases.html | 38 ++-
content/writing_data.html | 64 ++--
55 files changed, 2707 insertions(+), 1711 deletions(-)
diff --git a/content/404.html b/content/404.html
index acf9628..5c10429 100644
--- a/content/404.html
+++ b/content/404.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="">
<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/404.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -375,7 +383,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/Dockerfile b/content/Dockerfile
new file mode 100644
index 0000000..89cc254
--- /dev/null
+++ b/content/Dockerfile
@@ -0,0 +1,30 @@
+FROM ruby:2.6
+
+RUN apt-get clean \
+ && mv /var/lib/apt/lists /var/lib/apt/lists.broke \
+ && mkdir -p /var/lib/apt/lists/partial
+
+RUN apt-get update
+
+RUN apt-get install -y \
+ nodejs \
+ python-pygments \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/
+
+WORKDIR /tmp
+ADD Gemfile /tmp/
+ADD Gemfile.lock /tmp/
+
+RUN gem install bundler
+RUN gem install jekyll
+RUN bundle install
+RUN bundle update --bundler
+
+
+VOLUME /src
+EXPOSE 4000
+
+WORKDIR /src
+ENTRYPOINT ["bundle", "exec", "jekyll", "serve", "--force_polling", "-H", "0.0.0.0", "-P", "4000"]
+
diff --git a/content/Gemfile b/content/Gemfile
new file mode 100644
index 0000000..23bd76e
--- /dev/null
+++ b/content/Gemfile
@@ -0,0 +1,11 @@
+source 'https://rubygems.org'
+
+gem 'jekyll', '3.7.2'
+gem 'addressable', '2.4.0'
+gem 'json', '2.0.4'
+gem 'jekyll-multiple-languages', '2.0.3'
+gem 'jekyll-paginate', '1.1.0'
+
+group :jekyll_plugins do
+ gem "jekyll-feed", "0.12.1"
+end
diff --git a/content/Gemfile.lock b/content/Gemfile.lock
new file mode 100644
index 0000000..5a31a59
--- /dev/null
+++ b/content/Gemfile.lock
@@ -0,0 +1,71 @@
+GEM
+ remote: https://rubygems.org/
+ specs:
+ addressable (2.4.0)
+ colorator (1.1.0)
+ concurrent-ruby (1.0.5)
+ em-websocket (0.5.1)
+ eventmachine (>= 0.12.9)
+ http_parser.rb (~> 0.6.0)
+ eventmachine (1.2.5)
+ ffi (1.9.18)
+ forwardable-extended (2.6.0)
+ http_parser.rb (0.6.0)
+ i18n (0.9.3)
+ concurrent-ruby (~> 1.0)
+ jekyll (3.7.2)
+ addressable (~> 2.4)
+ colorator (~> 1.0)
+ em-websocket (~> 0.5)
+ i18n (~> 0.7)
+ jekyll-sass-converter (~> 1.0)
+ jekyll-watch (~> 2.0)
+ kramdown (~> 1.14)
+ liquid (~> 4.0)
+ mercenary (~> 0.3.3)
+ pathutil (~> 0.9)
+ rouge (>= 1.7, < 4)
+ safe_yaml (~> 1.0)
+ jekyll-feed (0.12.1)
+ jekyll (>= 3.7, < 5.0)
+ jekyll-multiple-languages (2.0.3)
+ jekyll-paginate (1.1.0)
+ jekyll-sass-converter (1.5.1)
+ sass (~> 3.4)
+ jekyll-watch (2.0.0)
+ listen (~> 3.0)
+ json (2.0.4)
+ kramdown (1.16.2)
+ liquid (4.0.0)
+ listen (3.1.5)
+ rb-fsevent (~> 0.9, >= 0.9.4)
+ rb-inotify (~> 0.9, >= 0.9.7)
+ ruby_dep (~> 1.2)
+ mercenary (0.3.6)
+ pathutil (0.16.1)
+ forwardable-extended (~> 2.6)
+ rb-fsevent (0.10.2)
+ rb-inotify (0.9.10)
+ ffi (>= 0.5.0, < 2)
+ rouge (3.1.1)
+ ruby_dep (1.5.0)
+ safe_yaml (1.0.4)
+ sass (3.5.5)
+ sass-listen (~> 4.0.0)
+ sass-listen (4.0.0)
+ rb-fsevent (~> 0.9, >= 0.9.4)
+ rb-inotify (~> 0.9, >= 0.9.7)
+
+PLATFORMS
+ ruby
+
+DEPENDENCIES
+ addressable (= 2.4.0)
+ jekyll (= 3.7.2)
+ jekyll-feed (= 0.12.1)
+ jekyll-multiple-languages (= 2.0.3)
+ jekyll-paginate (= 1.1.0)
+ json (= 2.0.4)
+
+BUNDLED WITH
+ 1.17.2
diff --git a/content/README.md b/content/README.md
new file mode 100644
index 0000000..4307a6a
--- /dev/null
+++ b/content/README.md
@@ -0,0 +1,46 @@
+## Site Documentation
+
+This folder contains resources that build the [Apache Hudi website](https://hudi.apache.org)
+
+
+### Building docs
+
+The site is based on a [Jekyll](https://jekyllrb.com/) theme hosted [here](idratherbewriting.com/documentation-theme-jekyll/) with detailed instructions.
+
+#### Docker
+
+Simply run `docker-compose build --no-cache && docker-compose up` from the `docs` folder and the site should be up & running at `http://localhost:4000`
+
+To see edits reflect on the site, you may have to bounce the container
+
+ - Stop existing container by `ctrl+c` the docker-compose program
+ - (or) alternatively via `docker stop docs_server_1`
+ - Bring up container again using `docker-compose up`
+
+#### Host OS
+
+To build directly on host OS (\*nix), first you need to install
+
+- gem, ruby (using apt-get/brew)
+- bundler (`gem install bundler`)
+- jekyll (`gem install jekyll`)
+- Update bundler `bundle update --bundler`
+
+and then run the following commands from `docs` folder to install dependencies
+
+`bundle install`
+
+and serve a local site
+
+`bundle exec jekyll serve`
+
+### Submitting changes
+
+To submit changes to the docs, please make the changes on the `asf-site` branch, build the site locally, test it out and submit a pull request with the changes to .md and theme files under `docs`
+
+### Updating site
+
+At a regular cadence, one of the Hudi committers will regenerate the site. In order to do this, first build it locally, test and then move the generated site from `_site` locally to `docs/../content`. Submit changes as a PR.
+
+### Automation
+Coming soon.
diff --git a/content/admin_guide.html b/content/admin_guide.html
index 20323a4..62bcc74 100644
--- a/content/admin_guide.html
+++ b/content/admin_guide.html
@@ -6,25 +6,25 @@
<meta name="description" content="This section offers an overview of tools available to operate an ecosystem of Hudi datasets">
<meta name="keywords" content="hudi, administration, operation, devops">
<title>Administering Hudi Pipelines | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/admin_guide.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Administering Hudi Pipelines">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -351,7 +359,7 @@ Hudi library effectively manages this dataset internally, using .hoodie subfolde
<p>To initialize a hudi table, use the following command.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>18/09/06 15:56:52 INFO annotation.AutowiredAnnotationBeanPostProcessor: JSR-330 'javax.inject.Inject' annotation found and supported for autowiring
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>18/09/06 15:56:52 INFO annotation.AutowiredAnnotationBeanPostProcessor: JSR-330 'javax.inject.Inject' annotation found and supported for autowiring
============================================
* *
* _ _ _ _ *
@@ -367,12 +375,11 @@ Welcome to Hoodie CLI. Please type help if you are looking for help.
hudi->create --path /user/hive/warehouse/table1 --tableName hoodie_table_1 --tableType COPY_ON_WRITE
.....
18/09/06 15:57:15 INFO table.HoodieTableMetaClient: Finished Loading Table of type COPY_ON_WRITE from ...
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To see the description of hudi table, use the command:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:hoodie_table_1->desc
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:hoodie_table_1->desc
18/09/06 15:57:19 INFO timeline.HoodieActiveTimeline: Loaded instants []
_________________________________________________________
| Property | Value |
@@ -383,25 +390,23 @@ hudi->create --path /user/hive/warehouse/table1 --tableName hoodie_table_1 --
| hoodie.table.name | hoodie_table_1 |
| hoodie.table.type | COPY_ON_WRITE |
| hoodie.archivelog.folder| |
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Following is a sample command to connect to a Hudi dataset contains uber trips.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->connect --path /app/uber/trips
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->connect --path /app/uber/trips
16/10/05 23:20:37 INFO model.HoodieTableMetadata: Attempting to load the commits under /app/uber/trips/.hoodie with suffix .commit
16/10/05 23:20:37 INFO model.HoodieTableMetadata: Attempting to load the commits under /app/uber/trips/.hoodie with suffix .inflight
16/10/05 23:20:37 INFO model.HoodieTableMetadata: All commits :HoodieCommits{commitList=[20161002045850, 20161002052915, 20161002055918, 20161002065317, 20161002075932, 20161002082904, 20161002085949, 20161002092936, 20161002105903, 20161002112938, 20161002123005, 20161002133002, 20161002155940, 20161002165924, 20161002172907, 20161002175905, 20161002190016, 20161002192954, 20161002195925, 20161002205935, 20161002215928, 20161002222938, 20161002225915, 20161002232906, 20161003003028, 201 [...]
Metadata for table trips loaded
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Once connected to the dataset, a lot of other commands become available. The shell has contextual autocomplete help (press TAB) and below is a list of all commands, few of which are reviewed in this section
are reviewed</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help
* ! - Allows execution of operating system (OS) commands
* // - Inline comment markers (start of line only)
* ; - Inline comment markers (start of line only)
@@ -430,8 +435,7 @@ are reviewed</p>
* version - Displays shell version
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="inspecting-commits">Inspecting Commits</h4>
@@ -440,7 +444,7 @@ Each commit has a monotonically increasing string/number called the <strong>comm
<p>To view some basic information about the last 10 commits,</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commits show --sortBy "Total Bytes Written" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commits show --sortBy "Total Bytes Written" --desc true --limit 10
________________________________________________________________________________________________________________________________________________________________________
| CommitTime | Total Bytes Written| Total Files Added| Total Files Updated| Total Partitions Written| Total Records Written| Total Update Records Written| Total Errors|
|=======================================================================================================================================================================|
@@ -448,46 +452,42 @@ Each commit has a monotonically increasing string/number called the <strong>comm
....
....
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<p>At the start of each write, Hudi also writes a .inflight commit to the .hoodie folder. You can use the timestamp there to estimate how long the commit has been inflight</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>$ hdfs dfs -ls /app/uber/trips/.hoodie/*.inflight
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ hdfs dfs -ls /app/uber/trips/.hoodie/*.inflight
-rw-r--r-- 3 vinoth supergroup 321984 2016-10-05 23:18 /app/uber/trips/.hoodie/20161005225920.inflight
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="drilling-down-to-a-specific-commit">Drilling Down to a specific Commit</h4>
<p>To understand how the writes spread across specific partiions,</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commit showpartitions --commit 20161005165855 --sortBy "Total Bytes Written" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commit showpartitions --commit 20161005165855 --sortBy "Total Bytes Written" --desc true --limit 10
__________________________________________________________________________________________________________________________________________
| Partition Path| Total Files Added| Total Files Updated| Total Records Inserted| Total Records Updated| Total Bytes Written| Total Errors|
|=========================================================================================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<p>If you need file level granularity , we can do the following</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commit showfiles --commit 20161005165855 --sortBy "Partition Path"
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commit showfiles --commit 20161005165855 --sortBy "Partition Path"
________________________________________________________________________________________________________________________________________________________
| Partition Path| File ID | Previous Commit| Total Records Updated| Total Records Written| Total Bytes Written| Total Errors|
|=======================================================================================================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="filesystem-view">FileSystem View</h4>
<p>Hudi views each partition as a collection of file-groups with each file-group containing a list of file-slices in commit
order (See Concepts). The below commands allow users to view the file-slices for a data-set.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code> hoodie:stock_ticks_mor->show fsview all
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> hoodie:stock_ticks_mor->show fsview all
....
_______________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________
| Partition | FileId | Base-Instant | Data-File | Data-File Size| Num Delta Files| Total Delta File Size| Delta Files |
@@ -504,33 +504,30 @@ order (See Concepts). The below commands allow users to view the file-slices for
| 2018/08/31| 111415c3-f26d-4639-86c8-f9956f245ac3| 20181002180759| hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/111415c3-f26d-4639-86c8-f9956f245ac3_0_20181002180759.parquet| 432.5 KB | 1 | 20.8 KB | 20.8 KB | 0.0 B | 0.0 B | 0.0 B | [HoodieLogFile {hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/.111415c3-f26d-4639-86c8-f9956f245ac3_20181002180759.log.1}]| [] |
hoodie:stock_ticks_mor->
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="statistics">Statistics</h4>
<p>Since Hudi directly manages file sizes for DFS dataset, it might be good to get an overall picture</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->stats filesizes --partitionPath 2016/09/01 --sortBy "95th" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->stats filesizes --partitionPath 2016/09/01 --sortBy "95th" --desc true --limit 10
________________________________________________________________________________________________
| CommitTime | Min | 10th | 50th | avg | 95th | Max | NumFiles| StdDev |
|===============================================================================================|
| <COMMIT_ID> | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 2 | 2.3 KB |
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<p>In case of Hudi write taking much longer, it might be good to see the write amplification for any sudden increases</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->stats wa
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->stats wa
__________________________________________________________________________
| CommitTime | Total Upserted| Total Written| Write Amplifiation Factor|
|=========================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="archived-commits">Archived Commits</h4>
@@ -542,30 +539,28 @@ This is a sequence file that contains a mapping from commitNumber => json wit
<p>To get an idea of the lag between compaction and writer applications, use the below command to list down all
pending compactions.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compactions show all
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compactions show all
___________________________________________________________________
| Compaction Instant Time| State | Total FileIds to be Compacted|
|==================================================================|
| <INSTANT_1> | REQUESTED| 35 |
| <INSTANT_2> | INFLIGHT | 27 |
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To inspect a specific compaction plan, use</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction show --instant <INSTANT_1>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction show --instant <INSTANT_1>
_________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________
| Partition Path| File Id | Base Instant | Data File Path | Total Delta Files| getMetrics |
|================================================================================================================================================================================================================================================
| 2018/07/17 | <UUID> | <INSTANT_1> | viewfs://ns-default/.../../UUID_<INSTANT>.parquet | 1 | {TOTAL_LOG_FILES=1.0, TOTAL_IO_READ_MB=1230.0, TOTAL_LOG_FILES_SIZE=2.51255751E8, TOTAL_IO_WRITE_MB=991.0, TOTAL_IO_MB=2221.0}|
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To manually schedule or run a compaction, use the below command. This command uses spark launcher to perform compaction
operations. NOTE : Make sure no other application is scheduling compaction for this dataset concurrently</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help compaction schedule
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help compaction schedule
Keyword: compaction schedule
Description: Schedule Compaction
Keyword: sparkMemory
@@ -575,10 +570,9 @@ Description: Schedule Compaction
Default if unspecified: '1G'
* compaction schedule - Schedule Compaction
-</code></pre>
-</div>
+</code></pre></div></div>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help compaction run
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help compaction run
Keyword: compaction run
Description: Run Compaction for given instant time
Keyword: tableName
@@ -618,14 +612,13 @@ Description: Run Compaction for given instant time
Default if unspecified: '__NULL__'
* compaction run - Run Compaction for given instant time
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="validate-compaction">Validate Compaction</h5>
<p>Validating a compaction plan : Check if all the files necessary for compactions are present and are valid</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction validate --instant 20181005222611
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction validate --instant 20181005222611
...
COMPACTION PLAN VALID
@@ -645,8 +638,7 @@ hoodie:stock_ticks_mor->compaction validate --instant 20181005222601
| File Id | Base Instant Time| Base Data File | Num Delta Files| Valid| Error |
|=====================================================================================================================================================================================================================================================================================================|
| 05320e98-9a57-4c38-b809-a6beaaeb36bd| 20181005222445 | hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/05320e98-9a57-4c38-b809-a6beaaeb36bd_0_20181005222445.parquet| 1 | false| All log files specified in compaction operation is not present. Missing .... |
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="note">NOTE</h5>
@@ -658,19 +650,17 @@ so that are preserved. Hudi provides the following CLI to support it</p>
<h5 id="unscheduling-compaction">UnScheduling Compaction</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction unscheduleFileId --fileId <FileUUID>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction unscheduleFileId --fileId <FileUUID>
....
No File renames needed to unschedule file from pending compaction. Operation successful.
-</code></pre>
-</div>
+</code></pre></div></div>
<p>In other cases, an entire compaction plan needs to be reverted. This is supported by the following CLI</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction unschedule --compactionInstant <compactionInstant>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction unschedule --compactionInstant <compactionInstant>
.....
No File renames needed to unschedule pending compaction. Operation successful.
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="repair-compaction">Repair Compaction</h5>
@@ -680,12 +670,11 @@ partial failures, the compaction operation could become inconsistent with the st
command comes to the rescue, it will rearrange the file-slices so that there is no loss and the file-slices are
consistent with the compaction plan</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction repair --instant 20181005222611
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction repair --instant 20181005222611
......
Compaction successfully repaired
.....
-</code></pre>
-</div>
+</code></pre></div></div>
<h2 id="metrics">Metrics</h2>
@@ -701,7 +690,9 @@ Compaction successfully repaired
<p>These metrics can then be plotted on a standard tool like grafana. Below is a sample commit duration chart.</p>
-<figure><img class="docimage" src="images/hudi_commit_duration.png" alt="hudi_commit_duration.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_commit_duration.png" alt="hudi_commit_duration.png" style="max-width: 1000px" />
+</figure>
<h2 id="troubleshooting">Troubleshooting Failures</h2>
@@ -714,7 +705,7 @@ Compaction successfully repaired
<li><strong>_hoodie_partition_path</strong> - Path from basePath that identifies the partition containing this record</li>
</ul>
-<div class="bs-callout bs-callout-warning">Note that as of now, Hudi assumes the application passes in the same deterministic partitionpath for a given recordKey. i.e the uniqueness of record key is only enforced within each partition</div>
+<p>Note that as of now, Hudi assumes the application passes in the same deterministic partitionpath for a given recordKey. i.e the uniqueness of record key is only enforced within each partition</p>
<h4 id="missing-records">Missing records</h4>
@@ -736,7 +727,9 @@ If you do find errors, then the record was not actually written by Hudi, but han
<p>Typical upsert() DAG looks like below. Note that Hudi client also caches intermediate RDDs to intelligently profile workload and size files and spark parallelism.
Also Spark UI shows sortByKey twice due to the probe job also being shown, nonetheless its just a single sort.</p>
-<figure><img class="docimage" src="images/hudi_upsert_dag.png" alt="hudi_upsert_dag.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_upsert_dag.png" alt="hudi_upsert_dag.png" style="max-width: 1000px" />
+</figure>
<p>At a high level, there are two steps</p>
@@ -778,7 +771,7 @@ In the future, a more sophisticated debug/management UI would be added to the pr
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/404.html b/content/cn/404.html
similarity index 85%
copy from content/404.html
copy to content/cn/404.html
index acf9628..5806e32 100644
--- a/content/404.html
+++ b/content/cn/404.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="">
<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/404.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -375,7 +382,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/admin_guide.html b/content/cn/admin_guide.html
similarity index 86%
copy from content/admin_guide.html
copy to content/cn/admin_guide.html
index 20323a4..fc64ae6 100644
--- a/content/admin_guide.html
+++ b/content/cn/admin_guide.html
@@ -6,25 +6,25 @@
<meta name="description" content="This section offers an overview of tools available to operate an ecosystem of Hudi datasets">
<meta name="keywords" content="hudi, administration, operation, devops">
<title>Administering Hudi Pipelines | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/admin_guide.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Administering Hudi Pipelines">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li class="active"><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -351,7 +358,7 @@ Hudi library effectively manages this dataset internally, using .hoodie subfolde
<p>To initialize a hudi table, use the following command.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>18/09/06 15:56:52 INFO annotation.AutowiredAnnotationBeanPostProcessor: JSR-330 'javax.inject.Inject' annotation found and supported for autowiring
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>18/09/06 15:56:52 INFO annotation.AutowiredAnnotationBeanPostProcessor: JSR-330 'javax.inject.Inject' annotation found and supported for autowiring
============================================
* *
* _ _ _ _ *
@@ -367,12 +374,11 @@ Welcome to Hoodie CLI. Please type help if you are looking for help.
hudi->create --path /user/hive/warehouse/table1 --tableName hoodie_table_1 --tableType COPY_ON_WRITE
.....
18/09/06 15:57:15 INFO table.HoodieTableMetaClient: Finished Loading Table of type COPY_ON_WRITE from ...
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To see the description of hudi table, use the command:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:hoodie_table_1->desc
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:hoodie_table_1->desc
18/09/06 15:57:19 INFO timeline.HoodieActiveTimeline: Loaded instants []
_________________________________________________________
| Property | Value |
@@ -383,25 +389,23 @@ hudi->create --path /user/hive/warehouse/table1 --tableName hoodie_table_1 --
| hoodie.table.name | hoodie_table_1 |
| hoodie.table.type | COPY_ON_WRITE |
| hoodie.archivelog.folder| |
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Following is a sample command to connect to a Hudi dataset contains uber trips.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->connect --path /app/uber/trips
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->connect --path /app/uber/trips
16/10/05 23:20:37 INFO model.HoodieTableMetadata: Attempting to load the commits under /app/uber/trips/.hoodie with suffix .commit
16/10/05 23:20:37 INFO model.HoodieTableMetadata: Attempting to load the commits under /app/uber/trips/.hoodie with suffix .inflight
16/10/05 23:20:37 INFO model.HoodieTableMetadata: All commits :HoodieCommits{commitList=[20161002045850, 20161002052915, 20161002055918, 20161002065317, 20161002075932, 20161002082904, 20161002085949, 20161002092936, 20161002105903, 20161002112938, 20161002123005, 20161002133002, 20161002155940, 20161002165924, 20161002172907, 20161002175905, 20161002190016, 20161002192954, 20161002195925, 20161002205935, 20161002215928, 20161002222938, 20161002225915, 20161002232906, 20161003003028, 201 [...]
Metadata for table trips loaded
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Once connected to the dataset, a lot of other commands become available. The shell has contextual autocomplete help (press TAB) and below is a list of all commands, few of which are reviewed in this section
are reviewed</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help
* ! - Allows execution of operating system (OS) commands
* // - Inline comment markers (start of line only)
* ; - Inline comment markers (start of line only)
@@ -430,8 +434,7 @@ are reviewed</p>
* version - Displays shell version
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="inspecting-commits">Inspecting Commits</h4>
@@ -440,7 +443,7 @@ Each commit has a monotonically increasing string/number called the <strong>comm
<p>To view some basic information about the last 10 commits,</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commits show --sortBy "Total Bytes Written" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commits show --sortBy "Total Bytes Written" --desc true --limit 10
________________________________________________________________________________________________________________________________________________________________________
| CommitTime | Total Bytes Written| Total Files Added| Total Files Updated| Total Partitions Written| Total Records Written| Total Update Records Written| Total Errors|
|=======================================================================================================================================================================|
@@ -448,46 +451,42 @@ Each commit has a monotonically increasing string/number called the <strong>comm
....
....
hoodie:trips->
-</code></pre>
-</div>
+</code></pre></div></div>
<p>At the start of each write, Hudi also writes a .inflight commit to the .hoodie folder. You can use the timestamp there to estimate how long the commit has been inflight</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>$ hdfs dfs -ls /app/uber/trips/.hoodie/*.inflight
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ hdfs dfs -ls /app/uber/trips/.hoodie/*.inflight
-rw-r--r-- 3 vinoth supergroup 321984 2016-10-05 23:18 /app/uber/trips/.hoodie/20161005225920.inflight
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="drilling-down-to-a-specific-commit">Drilling Down to a specific Commit</h4>
<p>To understand how the writes spread across specific partiions,</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commit showpartitions --commit 20161005165855 --sortBy "Total Bytes Written" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commit showpartitions --commit 20161005165855 --sortBy "Total Bytes Written" --desc true --limit 10
__________________________________________________________________________________________________________________________________________
| Partition Path| Total Files Added| Total Files Updated| Total Records Inserted| Total Records Updated| Total Bytes Written| Total Errors|
|=========================================================================================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<p>If you need file level granularity , we can do the following</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->commit showfiles --commit 20161005165855 --sortBy "Partition Path"
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->commit showfiles --commit 20161005165855 --sortBy "Partition Path"
________________________________________________________________________________________________________________________________________________________
| Partition Path| File ID | Previous Commit| Total Records Updated| Total Records Written| Total Bytes Written| Total Errors|
|=======================================================================================================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="filesystem-view">FileSystem View</h4>
<p>Hudi views each partition as a collection of file-groups with each file-group containing a list of file-slices in commit
order (See Concepts). The below commands allow users to view the file-slices for a data-set.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code> hoodie:stock_ticks_mor->show fsview all
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> hoodie:stock_ticks_mor->show fsview all
....
_______________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________
| Partition | FileId | Base-Instant | Data-File | Data-File Size| Num Delta Files| Total Delta File Size| Delta Files |
@@ -504,33 +503,30 @@ order (See Concepts). The below commands allow users to view the file-slices for
| 2018/08/31| 111415c3-f26d-4639-86c8-f9956f245ac3| 20181002180759| hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/111415c3-f26d-4639-86c8-f9956f245ac3_0_20181002180759.parquet| 432.5 KB | 1 | 20.8 KB | 20.8 KB | 0.0 B | 0.0 B | 0.0 B | [HoodieLogFile {hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/.111415c3-f26d-4639-86c8-f9956f245ac3_20181002180759.log.1}]| [] |
hoodie:stock_ticks_mor->
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="statistics">Statistics</h4>
<p>Since Hudi directly manages file sizes for DFS dataset, it might be good to get an overall picture</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->stats filesizes --partitionPath 2016/09/01 --sortBy "95th" --desc true --limit 10
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->stats filesizes --partitionPath 2016/09/01 --sortBy "95th" --desc true --limit 10
________________________________________________________________________________________________
| CommitTime | Min | 10th | 50th | avg | 95th | Max | NumFiles| StdDev |
|===============================================================================================|
| <COMMIT_ID> | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 93.9 MB | 2 | 2.3 KB |
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<p>In case of Hudi write taking much longer, it might be good to see the write amplification for any sudden increases</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->stats wa
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->stats wa
__________________________________________________________________________
| CommitTime | Total Upserted| Total Written| Write Amplifiation Factor|
|=========================================================================|
....
....
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="archived-commits">Archived Commits</h4>
@@ -542,30 +538,28 @@ This is a sequence file that contains a mapping from commitNumber => json wit
<p>To get an idea of the lag between compaction and writer applications, use the below command to list down all
pending compactions.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compactions show all
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compactions show all
___________________________________________________________________
| Compaction Instant Time| State | Total FileIds to be Compacted|
|==================================================================|
| <INSTANT_1> | REQUESTED| 35 |
| <INSTANT_2> | INFLIGHT | 27 |
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To inspect a specific compaction plan, use</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction show --instant <INSTANT_1>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction show --instant <INSTANT_1>
_________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________
| Partition Path| File Id | Base Instant | Data File Path | Total Delta Files| getMetrics |
|================================================================================================================================================================================================================================================
| 2018/07/17 | <UUID> | <INSTANT_1> | viewfs://ns-default/.../../UUID_<INSTANT>.parquet | 1 | {TOTAL_LOG_FILES=1.0, TOTAL_IO_READ_MB=1230.0, TOTAL_LOG_FILES_SIZE=2.51255751E8, TOTAL_IO_WRITE_MB=991.0, TOTAL_IO_MB=2221.0}|
-</code></pre>
-</div>
+</code></pre></div></div>
<p>To manually schedule or run a compaction, use the below command. This command uses spark launcher to perform compaction
operations. NOTE : Make sure no other application is scheduling compaction for this dataset concurrently</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help compaction schedule
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help compaction schedule
Keyword: compaction schedule
Description: Schedule Compaction
Keyword: sparkMemory
@@ -575,10 +569,9 @@ Description: Schedule Compaction
Default if unspecified: '1G'
* compaction schedule - Schedule Compaction
-</code></pre>
-</div>
+</code></pre></div></div>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->help compaction run
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->help compaction run
Keyword: compaction run
Description: Run Compaction for given instant time
Keyword: tableName
@@ -618,14 +611,13 @@ Description: Run Compaction for given instant time
Default if unspecified: '__NULL__'
* compaction run - Run Compaction for given instant time
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="validate-compaction">Validate Compaction</h5>
<p>Validating a compaction plan : Check if all the files necessary for compactions are present and are valid</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction validate --instant 20181005222611
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction validate --instant 20181005222611
...
COMPACTION PLAN VALID
@@ -645,8 +637,7 @@ hoodie:stock_ticks_mor->compaction validate --instant 20181005222601
| File Id | Base Instant Time| Base Data File | Num Delta Files| Valid| Error |
|=====================================================================================================================================================================================================================================================================================================|
| 05320e98-9a57-4c38-b809-a6beaaeb36bd| 20181005222445 | hdfs://namenode:8020/user/hive/warehouse/stock_ticks_mor/2018/08/31/05320e98-9a57-4c38-b809-a6beaaeb36bd_0_20181005222445.parquet| 1 | false| All log files specified in compaction operation is not present. Missing .... |
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="note">NOTE</h5>
@@ -658,19 +649,17 @@ so that are preserved. Hudi provides the following CLI to support it</p>
<h5 id="unscheduling-compaction">UnScheduling Compaction</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction unscheduleFileId --fileId <FileUUID>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction unscheduleFileId --fileId <FileUUID>
....
No File renames needed to unschedule file from pending compaction. Operation successful.
-</code></pre>
-</div>
+</code></pre></div></div>
<p>In other cases, an entire compaction plan needs to be reverted. This is supported by the following CLI</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:trips->compaction unschedule --compactionInstant <compactionInstant>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:trips->compaction unschedule --compactionInstant <compactionInstant>
.....
No File renames needed to unschedule pending compaction. Operation successful.
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="repair-compaction">Repair Compaction</h5>
@@ -680,12 +669,11 @@ partial failures, the compaction operation could become inconsistent with the st
command comes to the rescue, it will rearrange the file-slices so that there is no loss and the file-slices are
consistent with the compaction plan</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction repair --instant 20181005222611
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hoodie:stock_ticks_mor->compaction repair --instant 20181005222611
......
Compaction successfully repaired
.....
-</code></pre>
-</div>
+</code></pre></div></div>
<h2 id="metrics">Metrics</h2>
@@ -701,7 +689,9 @@ Compaction successfully repaired
<p>These metrics can then be plotted on a standard tool like grafana. Below is a sample commit duration chart.</p>
-<figure><img class="docimage" src="images/hudi_commit_duration.png" alt="hudi_commit_duration.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_commit_duration.png" alt="hudi_commit_duration.png" style="max-width: 1000px" />
+</figure>
<h2 id="troubleshooting">Troubleshooting Failures</h2>
@@ -714,7 +704,7 @@ Compaction successfully repaired
<li><strong>_hoodie_partition_path</strong> - Path from basePath that identifies the partition containing this record</li>
</ul>
-<div class="bs-callout bs-callout-warning">Note that as of now, Hudi assumes the application passes in the same deterministic partitionpath for a given recordKey. i.e the uniqueness of record key is only enforced within each partition</div>
+<p>Note that as of now, Hudi assumes the application passes in the same deterministic partitionpath for a given recordKey. i.e the uniqueness of record key is only enforced within each partition</p>
<h4 id="missing-records">Missing records</h4>
@@ -736,7 +726,9 @@ If you do find errors, then the record was not actually written by Hudi, but han
<p>Typical upsert() DAG looks like below. Note that Hudi client also caches intermediate RDDs to intelligently profile workload and size files and spark parallelism.
Also Spark UI shows sortByKey twice due to the probe job also being shown, nonetheless its just a single sort.</p>
-<figure><img class="docimage" src="images/hudi_upsert_dag.png" alt="hudi_upsert_dag.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_upsert_dag.png" alt="hudi_upsert_dag.png" style="max-width: 1000px" />
+</figure>
<p>At a high level, there are two steps</p>
@@ -778,7 +770,7 @@ In the future, a more sophisticated debug/management UI would be added to the pr
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/community.html b/content/cn/community.html
similarity index 81%
copy from content/community.html
copy to content/cn/community.html
index 89eb6c7..1c4e21c 100644
--- a/content/community.html
+++ b/content/cn/community.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, use cases, big data, apache">
<title>Community | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li class="active"><a href="community.html">Community</a></li>
+ <li class="active"><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/community.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Community">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -345,7 +352,7 @@
<tbody>
<tr>
<td>For any general questions, user support, development discussions</td>
- <td>Dev Mailing list (<a href="mailto:dev-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:dev-unsubscribe@hudi.apache.or& [...]
+ <td>Dev Mailing list (<a href="mailto:dev-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:dev-unsubscribe@hudi.apache.org">Unsubscribe</a>, <a href="https://lists.apache.org/list.html?dev@hudi.apache.org">Archives</a>). Empty email works for subscribe/unsubscribe. Please use <a href="https://gist.github.com">gists</a> to share code/stacktraces on the email.</td>
</tr>
<tr>
<td>For reporting bugs or issues or discover known issues</td>
@@ -365,12 +372,12 @@
</tr>
<tr>
<td>For stream of commits, pull requests etc</td>
- <td>Commits Mailing list (<a href="mailto:commits-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:commits-unsubscribe@hudi.� [...]
+ <td>Commits Mailing list (<a href="mailto:commits-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:commits-unsubscribe@hudi.apache.org">Unsubscribe</a>, <a href="https://lists.apache.org/list.html?commits@hudi.apache.org">Archives</a>)</td>
</tr>
</tbody>
</table>
-<p>If you wish to report a security vulnerability, please contact <a href="mailto:security@apache.org">security@apache.org</a>.
+<p>If you wish to report a security vulnerability, please contact <a href="mailto:security@apache.org">security@apache.org</a>.
Apache Hudi follows the typical Apache vulnerability handling <a href="https://apache.org/security/committers.html#vulnerability-handling">process</a>.</p>
<h2 id="contributing">Contributing</h2>
@@ -438,7 +445,7 @@ Specifically, please refer to the detailed <a href="contributing.html">contribut
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/comparison.html b/content/cn/comparison.html
similarity index 89%
copy from content/comparison.html
copy to content/cn/comparison.html
index a308acd..a1d3d4a 100644
--- a/content/comparison.html
+++ b/content/cn/comparison.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="apache, hudi, kafka, kudu, hive, hbase, stream processing">
<title>Comparison | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/comparison.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Comparison">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li class="active"><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -399,7 +406,7 @@ and will eventually happen as a <a href="https://issues.apache.org/jira/browse/H
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/concepts.html b/content/cn/concepts.html
similarity index 91%
copy from content/concepts.html
copy to content/cn/concepts.html
index 67d1e5e..77a3ec5 100644
--- a/content/concepts.html
+++ b/content/cn/concepts.html
@@ -6,25 +6,25 @@
<meta name="description" content="Here we introduce some basic concepts & give a broad technical overview of Hudi">
<meta name="keywords" content="hudi, design, storage, views, timeline">
<title>Concepts | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/concepts.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Concepts">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li class="active"><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -374,7 +381,9 @@ in one of the following states</p>
<li><code class="highlighter-rouge">COMPLETED</code> - Denotes completion of an action on the timeline</li>
</ul>
-<figure><img class="docimage" src="images/hudi_timeline.png" alt="hudi_timeline.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_timeline.png" alt="hudi_timeline.png" />
+</figure>
<p>Example above shows upserts happenings between 10:00 and 10:20 on a Hudi dataset, roughly every 5 mins, leaving commit metadata on the Hudi timeline, along
with other background cleaning/compactions. One key observation to make is that the commit time indicates the <code class="highlighter-rouge">arrival time</code> of the data (10:20AM), while the actual data
@@ -507,7 +516,9 @@ This is a much desired property for analytical workloads, which is predominantly
<p>Following illustrates how this works conceptually, when data written into copy-on-write storage and two queries running on top of it.</p>
-<figure><img class="docimage" src="images/hudi_cow.png" alt="hudi_cow.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_cow.png" alt="hudi_cow.png" />
+</figure>
<p>As data gets written, updates to existing file groups produce a new slice for that file group stamped with the commit instant time,
while inserts allocate a new file group and write its first slice for that file group. These file slices and their commit instant times are color coded above.
@@ -533,7 +544,9 @@ their columnar base file, to keep the query performance in check (larger delta l
<p>Following illustrates how the storage works, and shows queries on both near-real time table and read optimized table.</p>
-<figure><img class="docimage" src="images/hudi_mor.png" alt="hudi_mor.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_mor.png" alt="hudi_mor.png" style="max-width: 1000px" />
+</figure>
<p>There are lot of interesting things happening in this example, which bring out the subtleties in the approach.</p>
@@ -575,7 +588,7 @@ this storage such as reduced write amplification by avoiding synchronous merge o
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/configurations.html b/content/cn/configurations.html
similarity index 95%
copy from content/configurations.html
copy to content/cn/configurations.html
index 09c4f8e..c917115 100644
--- a/content/configurations.html
+++ b/content/cn/configurations.html
@@ -6,25 +6,25 @@
<meta name="description" content="Here we list all possible configurations and what they mean">
<meta name="keywords" content="garbage collection, hudi, jvm, configs, tuning">
<title>Configurations | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/configurations.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Configurations">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li class="active"><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -389,7 +396,7 @@ The actual datasource level configs are listed below.</p>
<p>Additionally, you can pass down any of the WriteClient level configs directly using <code class="highlighter-rouge">options()</code> or <code class="highlighter-rouge">option(k,v)</code> methods.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>inputDF.write()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>inputDF.write()
.format("org.apache.hudi")
.options(clientOpts) // any of the Hudi client opts can be passed in as well
.option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY(), "_row_key")
@@ -398,8 +405,7 @@ The actual datasource level configs are listed below.</p>
.option(HoodieWriteConfig.TABLE_NAME, tableName)
.mode(SaveMode.Append)
.save(basePath);
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Options useful for writing datasets via <code class="highlighter-rouge">write.format.option(...)</code></p>
@@ -513,7 +519,7 @@ necessarily correspond to an instant on the timeline. New data written with an
<p>Jobs programming directly against the RDD level apis can build a <code class="highlighter-rouge">HoodieWriteConfig</code> object and pass it in to the <code class="highlighter-rouge">HoodieWriteClient</code> constructor.
HoodieWriteConfig can be built using a builder pattern as below.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>HoodieWriteConfig cfg = HoodieWriteConfig.newBuilder()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>HoodieWriteConfig cfg = HoodieWriteConfig.newBuilder()
.withPath(basePath)
.forTable(tableName)
.withSchema(schemaStr)
@@ -522,8 +528,7 @@ HoodieWriteConfig can be built using a builder pattern as below.</p>
.withIndexConfig(HoodieIndexConfig.newBuilder().withXXX(...).build())
...
.build();
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Following subsections go over different aspects of write configs, explaining most important configs with their property names, default values.</p>
@@ -799,7 +804,7 @@ HoodieWriteConfig can be built using a builder pattern as below.</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/contributing.html b/content/cn/contributing.html
similarity index 90%
copy from content/contributing.html
copy to content/cn/contributing.html
index 6a5090c..a56da22 100644
--- a/content/contributing.html
+++ b/content/cn/contributing.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, ide, developer, setup">
<title>Developer Setup | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li class="dropdownActive"><a href="contributing.html">Contributing</a></li>
+ <li class="dropdownActive"><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/contributing.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Developer Setup">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -461,7 +468,7 @@ instructions on making changes to the website.</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/docker_demo.html b/content/cn/docker_demo.html
similarity index 92%
copy from content/docker_demo.html
copy to content/cn/docker_demo.html
index b904d84..2810b07 100644
--- a/content/docker_demo.html
+++ b/content/cn/docker_demo.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, docker, demo">
<title>Docker Demo | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/docker_demo.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Docker Demo">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -346,7 +353,7 @@ data infrastructure is brought up in a local docker cluster within your computer
<li>/etc/hosts : The demo references many services running in container by the hostname. Add the following settings to /etc/hosts</li>
</ul>
-<div class="highlighter-rouge"><pre class="highlight"><code> 127.0.0.1 adhoc-1
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> 127.0.0.1 adhoc-1
127.0.0.1 adhoc-2
127.0.0.1 namenode
127.0.0.1 datanode1
@@ -355,8 +362,7 @@ data infrastructure is brought up in a local docker cluster within your computer
127.0.0.1 kafkabroker
127.0.0.1 sparkmaster
127.0.0.1 zookeeper
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Also, this has not been tested on some environments like Docker on Windows.</p>
@@ -364,18 +370,17 @@ data infrastructure is brought up in a local docker cluster within your computer
<h4 id="build-hudi">Build Hudi</h4>
-<p>The first step is to build hudi
-<code class="highlighter-rouge">
-cd <HUDI_WORKSPACE>
+<p>The first step is to build hudi</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd <HUDI_WORKSPACE>
mvn package -DskipTests
-</code></p>
+</code></pre></div></div>
<h4 id="bringing-up-demo-cluster">Bringing up Demo Cluster</h4>
<p>The next step is to run the docker compose script and setup configs for bringing up the cluster.
This should pull the docker images from docker hub and setup docker cluster.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cd docker
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd docker
./setup_demo.sh
....
....
@@ -403,8 +408,7 @@ Copying spark default config and setting up configs
Copying spark default config and setting up configs
Copying spark default config and setting up configs
varadarb-C02SG7Q3G8WP:docker varadarb$ docker ps
-</code></pre>
-</div>
+</code></pre></div></div>
<p>At this point, the docker cluster will be up and running. The demo cluster brings up the following services</p>
@@ -430,7 +434,7 @@ The batches are windowed intentionally so that the second batch contains updates
<p>Upload the first batch to Kafka topic ‘stock ticks’</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cat docker/demo/data/batch_1.json | kafkacat -b kafkabroker -t stock_ticks -P
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cat docker/demo/data/batch_1.json | kafkacat -b kafkabroker -t stock_ticks -P
To check if the new topic shows up, use
kafkacat -b kafkabroker -L -J | jq .
@@ -471,8 +475,7 @@ kafkacat -b kafkabroker -L -J | jq .
]
}
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-2-incrementally-ingest-data-from-kafka-topic">Step 2: Incrementally ingest data from Kafka topic</h4>
@@ -481,7 +484,7 @@ pull changes and apply to Hudi dataset using upsert/insert primitives. Here, we
json data from kafka topic and ingest to both COW and MOR tables we initialized in the previous step. This tool
automatically initializes the datasets in the file-system if they do not exist yet.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
# Run the following spark-submit command to execute the delta-streamer and ingest to stock_ticks_cow dataset in HDFS
spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer $HUDI_UTILITIES_BUNDLE --storage-type COPY_ON_WRITE --source-class org.apache.hudi.utilities.sources.JsonKafkaSource --source-ordering-field ts --target-base-path /user/hive/warehouse/stock_ticks_cow --target-table stock_ticks_cow --props /var/demo/config/kafka-source.properties --schemaprovider-class org.apache.hudi.utilities.schema.FilebasedSchemaProvider
@@ -503,8 +506,7 @@ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer
# contain mostly Kafa connectivity settings, the avro-schema to be used for ingesting along with key and partitioning fields.
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>You can use HDFS web-browser to look at the datasets
<code class="highlighter-rouge">http://namenode:50070/explorer.html#/user/hive/warehouse/stock_ticks_cow</code>.</p>
@@ -520,7 +522,7 @@ file under .hoodie which signals a successful commit.</p>
<p>At this step, the datasets are available in HDFS. We need to sync with Hive to create new Hive tables and add partitions
inorder to run Hive queries against those datasets.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
# THis command takes in HIveServer URL and COW Hudi Dataset location in HDFS and sync the HDFS state to Hive
/var/hoodie/ws/hudi-hive/run_sync_tool.sh --jdbc-url jdbc:hive2://hiveserver:10000 --user hive --pass hive --partitioned-by dt --base-path /user/hive/warehouse/stock_ticks_cow --database default --table stock_ticks_cow
@@ -536,8 +538,7 @@ inorder to run Hive queries against those datasets.</p>
2018-09-24 22:23:09,559 INFO [main] hive.HiveSyncTool (HiveSyncTool.java:syncHoodieTable(112)) - Sync complete for stock_ticks_mor_rt
....
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>After executing the above command, you will notice</p>
<ol>
@@ -552,7 +553,7 @@ provides the ReadOptimized view for the Hudi dataset and the later provides the
(for both COW and MOR dataset)and realtime views (for MOR dataset)give the same value “10:29 a.m” as Hudi create a
parquet file for the first batch of data.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# List Tables
0: jdbc:hive2://hiveserver:10000> show tables;
@@ -648,14 +649,13 @@ WARNING: Hive-on-MR is deprecated in Hive 2 and may not be available in the futu
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-4-b-run-spark-sql-queries">Step 4 (b): Run Spark-SQL Queries</h4>
<p>Hudi support Spark as query processor just like Hive. Here are the same hive queries
running in spark-sql</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
$SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --master local[2] --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
...
@@ -746,15 +746,14 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
|20180924222155 |GOOG |2018-08-31 10:29:00|3391 |1230.1899|1230.085|
+-------------------+------+-------------------+------+---------+--------+
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-5-upload-second-batch-to-kafka-and-run-deltastreamer-to-ingest">Step 5: Upload second batch to Kafka and run DeltaStreamer to ingest</h4>
<p>Upload the second batch of data and ingest this batch using delta-streamer. As this batch does not bring in any new
partitions, there is no need to run hive-sync</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cat docker/demo/data/batch_2.json | kafkacat -b kafkabroker -t stock_ticks -P
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cat docker/demo/data/batch_2.json | kafkacat -b kafkabroker -t stock_ticks -P
# Within Docker container, run the ingestion command
docker exec -it adhoc-2 /bin/bash
@@ -767,8 +766,7 @@ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer
spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer $HUDI_UTILITIES_BUNDLE --storage-type MERGE_ON_READ --source-class org.apache.hudi.utilities.sources.JsonKafkaSource --source-ordering-field ts --target-base-path /user/hive/warehouse/stock_ticks_mor --target-table stock_ticks_mor --props /var/demo/config/kafka-source.properties --schemaprovider-class org.apache.hudi.utilities.schema.FilebasedSchemaProvider --disable-compaction
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>With Copy-On-Write table, the second ingestion by DeltaStreamer resulted in a new version of Parquet file getting created.
See <code class="highlighter-rouge">http://namenode:50070/explorer.html#/user/hive/warehouse/stock_ticks_cow/2018/08/31</code></p>
@@ -786,7 +784,7 @@ This is the time, when ReadOptimized and Realtime views will provide different r
return “10:29 am” as it will only read from the Parquet file. Realtime View will do on-the-fly merge and return
latest committed data which is “10:59 a.m”.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# Copy On Write Table:
@@ -850,14 +848,13 @@ WARNING: Hive-on-MR is deprecated in Hive 2 and may not be available in the futu
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-6b-run-spark-sql-queries">Step 6(b): Run Spark SQL Queries</h4>
<p>Running the same queries in Spark-SQL:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
# Copy On Write Table:
@@ -918,8 +915,7 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-7--incremental-query-for-copy-on-write-table">Step 7 : Incremental Query for COPY-ON-WRITE Table</h4>
@@ -927,7 +923,7 @@ exit
<p>Lets take the same projection query example</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
0: jdbc:hive2://hiveserver:10000> select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG';
@@ -937,8 +933,7 @@ beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache
| 20180924064621 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02 |
| 20180924065039 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
<p>As you notice from the above queries, there are 2 commits - 20180924064621 and 20180924065039 in timeline order.
When you follow the steps, you will be getting different timestamps for commits. Substitute them
@@ -951,20 +946,19 @@ the commit time of the first batch (20180924064621) and run incremental query</p
<p>Hudi incremental mode provides efficient scanning for incremental queries by filtering out files that do not have any
candidate rows using hudi-managed metadata.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.mode=INCREMENTAL;
No rows affected (0.009 seconds)
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.max.commits=3;
No rows affected (0.009 seconds)
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.start.timestamp=20180924064621;
-</code></pre>
-</div>
+</code></pre></div></div>
<p>With the above setting, file-ids that do not have any updates from the commit 20180924065039 is filtered out without scanning.
Here is the incremental query :</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>0: jdbc:hive2://hiveserver:10000>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>0: jdbc:hive2://hiveserver:10000>
0: jdbc:hive2://hiveserver:10000> select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG' and `_hoodie_commit_time` > '20180924064621';
+----------------------+---------+----------------------+---------+------------+-----------+--+
| _hoodie_commit_time | symbol | ts | volume | open | close |
@@ -973,11 +967,10 @@ Here is the incremental query :</p>
+----------------------+---------+----------------------+---------+------------+-----------+--+
1 row selected (0.83 seconds)
0: jdbc:hive2://hiveserver:10000>
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="incremental-query-with-spark-sql">Incremental Query with Spark SQL:</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
Welcome to
____ __
@@ -1010,15 +1003,14 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
| 20180924065039 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-8-schedule-and-run-compaction-for-merge-on-read-dataset">Step 8: Schedule and Run Compaction for Merge-On-Read dataset</h4>
<p>Lets schedule and run a compaction to create a new version of columnar file so that read-optimized readers will see fresher data.
Again, You can use Hudi CLI to manually schedule and run compaction</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
root@adhoc-1:/opt# /var/hoodie/ws/hudi-cli/hudi-cli.sh
============================================
* *
@@ -1101,8 +1093,7 @@ hoodie:stock_ticks->compactions show all
|==================================================================|
| 20180924070031 | COMPLETED| 1 |
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-9-run-hive-queries-including-incremental-queries">Step 9: Run Hive Queries including incremental queries</h4>
@@ -1111,7 +1102,7 @@ Lets also run the incremental query for MOR table.
From looking at the below query output, it will be clear that the fist commit time for the MOR table is 20180924064636
and the second commit time is 20180924070031</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# Read Optimized View
@@ -1167,12 +1158,11 @@ No rows affected (0.013 seconds)
+----------------------+---------+----------------------+---------+------------+-----------+--+
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="read-optimized-and-realtime-views-for-mor-with-spark-sql-after-compaction">Read Optimized and Realtime Views for MOR with Spark-SQL after compaction</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
# Read Optimized View
@@ -1207,32 +1197,28 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
| 20180924064636 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02 |
| 20180924070031 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
<p>This brings the demo to an end.</p>
<h2 id="testing-hudi-in-local-docker-environment">Testing Hudi in Local Docker environment</h2>
-<p>You can bring up a hadoop docker environment containing Hadoop, Hive and Spark services with support for hudi.
-<code class="highlighter-rouge">
-$ mvn pre-integration-test -DskipTests
-</code>
-The above command builds docker images for all the services with
+<p>You can bring up a hadoop docker environment containing Hadoop, Hive and Spark services with support for hudi.</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ mvn pre-integration-test -DskipTests
+</code></pre></div></div>
+<p>The above command builds docker images for all the services with
current Hudi source installed at /var/hoodie/ws and also brings up the services using a compose file. We
currently use Hadoop (v2.8.4), Hive (v2.3.3) and Spark (v2.3.1) in docker images.</p>
-<p>To bring down the containers
-<code class="highlighter-rouge">
-$ cd hudi-integ-test
+<p>To bring down the containers</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ cd hudi-integ-test
$ mvn docker-compose:down
-</code></p>
+</code></pre></div></div>
-<p>If you want to bring up the docker containers, use
-<code class="highlighter-rouge">
-$ cd hudi-integ-test
+<p>If you want to bring up the docker containers, use</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ cd hudi-integ-test
$ mvn docker-compose:up -DdetachedMode=true
-</code></p>
+</code></pre></div></div>
<p>Hudi is a library that is operated in a broader data analytics/ingestion environment
involving Hadoop, Hive and Spark. Interoperability with all these systems is a key objective for us. We are
@@ -1258,7 +1244,7 @@ run the script
<p>Here are the commands:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cd docker
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd docker
./build_local_docker_images.sh
.....
@@ -1293,8 +1279,7 @@ run the script
[INFO] Finished at: 2018-09-10T17:47:37-07:00
[INFO] Final Memory: 236M/1848M
[INFO] ------------------------------------------------------------------------
-</code></pre>
-</div>
+</code></pre></div></div>
<div class="tags">
@@ -1323,7 +1308,7 @@ run the script
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/404.html b/content/cn/events/2016-12-30-strata-talk-2017.html
similarity index 80%
copy from content/404.html
copy to content/cn/events/2016-12-30-strata-talk-2017.html
index acf9628..6dfd25c 100644
--- a/content/404.html
+++ b/content/cn/events/2016-12-30-strata-talk-2017.html
@@ -5,26 +5,26 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="">
<meta name="keywords" content="">
-<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<title>Connect with us at Strata San Jose March 2017 | Hudi</title>
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -162,11 +164,16 @@
- <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Page Not Found page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
+ <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Connect with us at Strata San Jose March 2017 page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
<li>
+ <li>
+
+ <a href="/events/2016-12-30-strata-talk-2017.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,13 +181,13 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
- searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
+ dataSource: '/search.json',
+ searchResultTemplate: '<li><a href="{url}" title="Connect with us at Strata San Jose March 2017">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
fuzzy: true,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -317,7 +324,7 @@
<!-- Content Column -->
<div class="col-md-9">
<div class="post-header">
- <h1 class="post-title-main">Page Not Found</h1>
+ <h1 class="post-title-main">Connect with us at Strata San Jose March 2017</h1>
</div>
@@ -354,11 +361,21 @@ $('#toc').on('click', 'a', function() {
- <p>Sorry, but the page you were trying to view does not exist. Try searching for it or looking at the URL to see if it looks correct.</p>
+ <p>We will be presenting Hudi & general concepts around how incremental processing works at Uber.
+Catch our talk <strong>“Incremental Processing on Hadoop At Uber”</strong></p>
+
<div class="tags">
+ <b>Tags: </b>
+
+
+
+ <a href="tag_news.html" class="btn btn-default navbar-btn cursorNorm" role="button">news</a>
+
+
+
</div>
@@ -375,7 +392,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/404.html b/content/cn/events/2019-01-18-asf-incubation.html
similarity index 81%
copy from content/404.html
copy to content/cn/events/2019-01-18-asf-incubation.html
index acf9628..f146611 100644
--- a/content/404.html
+++ b/content/cn/events/2019-01-18-asf-incubation.html
@@ -5,26 +5,26 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="">
<meta name="keywords" content="">
-<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<title>Hudi entered Apache Incubator | Hudi</title>
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -162,11 +164,16 @@
- <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Page Not Found page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
+ <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Hudi entered Apache Incubator page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
<li>
+ <li>
+
+ <a href="/events/2019-01-18-asf-incubation.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,13 +181,13 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
- searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
+ dataSource: '/search.json',
+ searchResultTemplate: '<li><a href="{url}" title="Hudi entered Apache Incubator">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
fuzzy: true,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -317,7 +324,7 @@
<!-- Content Column -->
<div class="col-md-9">
<div class="post-header">
- <h1 class="post-title-main">Page Not Found</h1>
+ <h1 class="post-title-main">Hudi entered Apache Incubator</h1>
</div>
@@ -354,11 +361,20 @@ $('#toc').on('click', 'a', function() {
- <p>Sorry, but the page you were trying to view does not exist. Try searching for it or looking at the URL to see if it looks correct.</p>
+ <p>In the coming weeks, we will be moving in our new home on the Apache Incubator.</p>
+
<div class="tags">
+ <b>Tags: </b>
+
+
+
+ <a href="tag_news.html" class="btn btn-default navbar-btn cursorNorm" role="button">news</a>
+
+
+
</div>
@@ -375,7 +391,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/gcs_hoodie.html b/content/cn/gcs_hoodie.html
similarity index 87%
copy from content/gcs_hoodie.html
copy to content/cn/gcs_hoodie.html
index 0902ab1..333eec8 100644
--- a/content/gcs_hoodie.html
+++ b/content/cn/gcs_hoodie.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we go over how to configure hudi with Google Cloud Storage.">
<meta name="keywords" content="hudi, hive, google cloud, storage, spark, presto">
<title>GCS Filesystem | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/gcs_hoodie.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="GCS Filesystem">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -348,7 +355,7 @@
<p>Add the required configs in your core-site.xml from where Hudi can fetch them. Replace the <code class="highlighter-rouge">fs.defaultFS</code> with your GCS bucket name and Hudi should be able to read/write from the bucket.</p>
-<div class="language-xml highlighter-rouge"><pre class="highlight"><code> <span class="nt"><property></span>
+<div class="language-xml highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="nt"><property></span>
<span class="nt"><name></span>fs.defaultFS<span class="nt"></name></span>
<span class="nt"><value></span>gs://hudi-bucket<span class="nt"></value></span>
<span class="nt"></property></span>
@@ -381,8 +388,7 @@
<span class="nt"><name></span>google.cloud.auth.service.account.keyfile<span class="nt"></name></span>
<span class="nt"><value></span>GCS_SERVICE_ACCOUNT_KEYFILE<span class="nt"></value></span>
<span class="nt"></property></span>
-</code></pre>
-</div>
+</code></pre></div></div>
<h3 id="gcs-libs">GCS Libs</h3>
@@ -411,7 +417,7 @@
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/index.html b/content/cn/index.html
similarity index 87%
copy from content/index.html
copy to content/cn/index.html
index bf041bc..9d2f976 100644
--- a/content/index.html
+++ b/content/cn/index.html
@@ -6,25 +6,25 @@
<meta name="description" content="Hudi brings stream processing to big data, providing fresh data while being an order of magnitude efficient over traditional batch processing.">
<meta name="keywords" content="big data, stream processing, cloud, hdfs, storage, upserts, change capture">
<title>What is Hudi? | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/index.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="What is Hudi?">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -364,7 +371,9 @@ $('#toc').on('click', 'a', function() {
<li><strong>Near-Real time Table</strong> - Provides queries on real-time data, using a combination of columnar & row based storage (e.g Parquet + <a href="http://avro.apache.org/docs/current/mr.html">Avro</a>)</li>
</ul>
-<figure><img class="docimage" src="images/hudi_intro_1.png" alt="hudi_intro_1.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_intro_1.png" alt="hudi_intro_1.png" />
+</figure>
<p>By carefully managing how data is laid out in storage & how it’s exposed to queries, Hudi is able to power a rich data ecosystem where external sources can be ingested in near real-time and made available for interactive SQL Engines like <a href="https://prestodb.io">Presto</a> & <a href="https://spark.apache.org/sql/">Spark</a>, while at the same time capable of being consumed incrementally from processing/ETL frameworks like <a href="https://hive.apache.org/">Hive</a> & [...]
@@ -397,7 +406,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/migration_guide.html b/content/cn/migration_guide.html
similarity index 87%
copy from content/migration_guide.html
copy to content/cn/migration_guide.html
index 7cb85db..148f430 100644
--- a/content/migration_guide.html
+++ b/content/cn/migration_guide.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we will discuss some available tools for migrating your existing dataset into a Hudi dataset">
<meta name="keywords" content="hudi, migration, use case">
<title>Migration Guide | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/migration_guide.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Migration Guide">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -374,7 +381,7 @@ This tool essentially starts a Spark Job to read the existing parquet dataset an
<p>Write your own custom logic of how to load an existing dataset into a Hudi managed one. Please read about the RDD API
<a href="quickstart.html">here</a>.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>Using the HDFSParquetImporter Tool. Once hudi has been built via `mvn clean install -DskipTests`, the shell can be
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Using the HDFSParquetImporter Tool. Once hudi has been built via `mvn clean install -DskipTests`, the shell can be
fired by via `cd hudi-cli && ./hudi-cli.sh`.
hudi->hdfsparquetimport
@@ -391,8 +398,7 @@ hudi->hdfsparquetimport
--format parquet
--sparkMemory 6g
--retry 2
-</code></pre>
-</div>
+</code></pre></div></div>
<div class="tags">
@@ -413,7 +419,7 @@ hudi->hdfsparquetimport
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/news.html b/content/cn/news.html
similarity index 83%
copy from content/news.html
copy to content/cn/news.html
index fcdc17f..c875913 100644
--- a/content/news.html
+++ b/content/cn/news.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="apache, hudi, news, blog, updates, release notes, announcements">
<title>News | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li class="active"><a href="news">News</a></li>
+ <li class="active"><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/news.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="News">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -245,45 +252,76 @@
<div class="home">
- <div class="post-list">
+ <div class="post-list">
+
+
-
-
- <h2><a class="post-link" href="strata-talk.html">Hudi entered Apache Incubator</a></h2>
- <span class="post-meta">Jan 18, 2019 /
+
+
+
+ <h2><a class="post-link" href="/cn/events/2016-12-30-strata-talk-2017.html">Connect with us at Strata San Jose March 2017</a></h2>
+ <span class="post-meta">Dec 30, 2016 /
<a href="tag_news.html">news</a>
</span>
- <p> In the coming weeks, we will be moving in our new home on the Apache Incubator.
+ <p> We will be presenting Hudi & general concepts around how incremental processing works at Uber.
+Catch our talk “Incremental Processing on Hadoop At Uber”
</p>
+
-
-
- <h2><a class="post-link" href="strata-talk.html">Connect with us at Strata San Jose March 2017</a></h2>
- <span class="post-meta">Dec 30, 2016 /
+
+
+
+
+
+
+ <h2><a class="post-link" href="/cn/events/2019-01-18-asf-incubation.html">Hudi entered Apache Incubator</a></h2>
+ <span class="post-meta">Jan 18, 2019 /
<a href="tag_news.html">news</a>
</span>
- <p> We will be presenting Hudi & general concepts around how incremental processing works at Uber.
-Catch our talk “Incremental Processing on Hadoop At Uber”
+ <p> In the coming weeks, we will be moving in our new home on the Apache Incubator.
</p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
- <p><a href="feed.xml"" class="btn btn-primary navbar-btn cursorNorm" role="button">RSS Subscribe</a></p>
+ <p><a href="feed.xml" class="btn btn-primary navbar-btn cursorNorm" role="button">RSS Subscribe</a></p>
<hr />
<p>See more posts from the <a href="news_archive.html">News Archive</a>. </p>
</div>
+</div>
<div class="tags">
@@ -304,7 +342,7 @@ Catch our talk “Incremental Processing on Hadoop At Uber”
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/news_archive.html b/content/cn/news_archive.html
similarity index 83%
copy from content/news_archive.html
copy to content/cn/news_archive.html
index 4d74956..6ca01bc 100644
--- a/content/news_archive.html
+++ b/content/cn/news_archive.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="news, blog, updates, release notes, announcements">
<title>News | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li class="active"><a href="news">News</a></li>
+ <li class="active"><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/news_archive.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="News">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -339,33 +346,18 @@
<section id="archive">
<h3>This year's posts</h3>
-
- <ul class="this">
-
- <li><time>18 Jan</time><a href="strata-talk.html">Hudi entered Apache Incubator</a></li>
-
-
-
-
-
- </ul>
- <h3>2016</h3>
- <ul class="past">
-
-
- <li><time>30 Dec</time><a href="strata-talk.html">Connect with us at Strata San Jose March 2017</a></li>
-
- </ul>
+ </ul>
</section>
- <hr/>
+ <hr />
</div>
+</div>
<div class="tags">
@@ -386,7 +378,7 @@
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/performance.html b/content/cn/performance.html
similarity index 83%
copy from content/performance.html
copy to content/cn/performance.html
index 85e1057..e01045c 100644
--- a/content/performance.html
+++ b/content/cn/performance.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, index, storage, compaction, cleaning, implementation">
<title>Performance | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/performance.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Performance">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li class="active"><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -339,12 +346,16 @@ the conventional alternatives for achieving these tasks.</p>
<p>Following shows the speed up obtained for NoSQL database ingestion, from incrementally upserting on a Hudi dataset on the copy-on-write storage,
on 5 tables ranging from small to huge (as opposed to bulk loading the tables)</p>
-<figure><img class="docimage" src="images/hudi_upsert_perf1.png" alt="hudi_upsert_perf1.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_upsert_perf1.png" alt="hudi_upsert_perf1.png" style="max-width: 1000px" />
+</figure>
<p>Given Hudi can build the dataset incrementally, it opens doors for also scheduling ingesting more frequently thus reducing latency, with
significant savings on the overall compute cost.</p>
-<figure><img class="docimage" src="images/hudi_upsert_perf2.png" alt="hudi_upsert_perf2.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_upsert_perf2.png" alt="hudi_upsert_perf2.png" style="max-width: 1000px" />
+</figure>
<p>Hudi upserts have been stress tested upto 4TB in a single commit across the t1 table.
See <a href="https://cwiki.apache.org/confluence/display/HUDI/Tuning+Guide">here</a> for some tuning tips.</p>
@@ -369,16 +380,21 @@ with no impact on queries. Following charts compare the Hudi vs non-Hudi dataset
<p><strong>Hive</strong></p>
-<figure><img class="docimage" src="images/hudi_query_perf_hive.png" alt="hudi_query_perf_hive.png" style="max-width: 800px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_query_perf_hive.png" alt="hudi_query_perf_hive.png" style="max-width: 800px" />
+</figure>
<p><strong>Spark</strong></p>
-<figure><img class="docimage" src="images/hudi_query_perf_spark.png" alt="hudi_query_perf_spark.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_query_perf_spark.png" alt="hudi_query_perf_spark.png" style="max-width: 1000px" />
+</figure>
<p><strong>Presto</strong></p>
-<figure><img class="docimage" src="images/hudi_query_perf_presto.png" alt="hudi_query_perf_presto.png" style="max-width: 1000px" /></figure>
-
+<figure>
+ <img class="docimage" src="/images/hudi_query_perf_presto.png" alt="hudi_query_perf_presto.png" style="max-width: 1000px" />
+</figure>
<div class="tags">
@@ -399,7 +415,7 @@ with no impact on queries. Following charts compare the Hudi vs non-Hudi dataset
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/powered_by.html b/content/cn/powered_by.html
similarity index 89%
copy from content/powered_by.html
copy to content/cn/powered_by.html
index 27a7d31..33d086c 100644
--- a/content/powered_by.html
+++ b/content/cn/powered_by.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, talks, presentation">
<title>Talks & Powered By | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -115,15 +115,15 @@
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -132,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -171,8 +171,7 @@
<li>
- <!-- link to the Chinese home page when current is blog page -->
- <a href="/cn/powered_by.html">中文版</a>
+ <a href="/powered_by.html">English</a>
</li>
<!--comment out this block if you want to hide search-->
@@ -182,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Talks & Powered By">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -237,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li class="active"><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -261,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -421,7 +420,7 @@ September 2019, ApacheCon NA 19, Las Vegas, NV, USA</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
@@ -453,4 +452,4 @@ September 2019, ApacheCon NA 19, Las Vegas, NV, USA</p>
</body>
-</html>
+</html>
\ No newline at end of file
diff --git a/content/privacy.html b/content/cn/privacy.html
similarity index 87%
copy from content/privacy.html
copy to content/cn/privacy.html
index e96aaad..8c43aad 100644
--- a/content/privacy.html
+++ b/content/cn/privacy.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, privacy">
<title>Privacy Policy | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/privacy.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Privacy Policy">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -392,7 +399,7 @@ The collected information consists of the following:</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/querying_data.html b/content/cn/querying_data.html
similarity index 88%
copy from content/querying_data.html
copy to content/cn/querying_data.html
index 0e1b9f1..2018b01 100644
--- a/content/querying_data.html
+++ b/content/cn/querying_data.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we go over how to enable SQL queries on Hudi built tables.">
<meta name="keywords" content="hudi, hive, spark, sql, presto">
<title>Querying Hudi Datasets | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/querying_data.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Querying Hudi Datasets">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li class="active"><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -373,7 +380,7 @@ queries can pick up the custom RecordReader as well.</p>
<p><code class="highlighter-rouge">HiveIncrementalPuller</code> allows incrementally extracting changes from large fact/dimension tables via HiveQL, combining the benefits of Hive (reliably process complex SQL queries) and
incremental primitives (speed up query by pulling tables incrementally instead of scanning fully). The tool uses Hive JDBC to run the hive query and saves its results in a temp table.
that can later be upserted. Upsert utility (<code class="highlighter-rouge">HoodieDeltaStreamer</code>) has all the state it needs from the directory structure to know what should be the commit time on the target table.
-e.g: <code class="highlighter-rouge">/app/incremental-hql/intermediate/{source_table_name}_temp/{last_commit_included}</code>.The Delta Hive table registered will be of the form <code class="highlighter-rouge"><span class="p">{</span><span class="err">tmpdb</span><span class="p">}</span><span class="err">.</span><span class="p">{</span><span class="err">source_table</span><span class="p">}</span><span class="err">_</span><span class="p">{</span><span class="err">last_commit_included</spa [...]
+e.g: <code class="highlighter-rouge">/app/incremental-hql/intermediate/{source_table_name}_temp/{last_commit_included}</code>.The Delta Hive table registered will be of the form <code class="highlighter-rouge">{tmpdb}.{source_table}_{last_commit_included}</code>.</p>
<p>The following are the configuration options for HiveIncrementalPuller</p>
@@ -485,41 +492,37 @@ separated) and calls InputFormat.listStatus() only once with all those partition
<p>To read RO table as a Hive table using SparkSQL, simply push a path filter into sparkContext as follows.
This method retains Spark built-in optimizations for reading Parquet files like vectorized reading on Hudi tables.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>spark.sparkContext.hadoopConfiguration.setClass("mapreduce.input.pathFilter.class", classOf[org.apache.hudi.hadoop.HoodieROTablePathFilter], classOf[org.apache.hadoop.fs.PathFilter]);
-</code></pre>
-</div>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>spark.sparkContext.hadoopConfiguration.setClass("mapreduce.input.pathFilter.class", classOf[org.apache.hudi.hadoop.HoodieROTablePathFilter], classOf[org.apache.hadoop.fs.PathFilter]);
+</code></pre></div></div>
<p>If you prefer to glob paths on DFS via the datasource, you can simply do something like below to get a Spark dataframe to work with.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>Dataset<Row> hoodieROViewDF = spark.read().format("org.apache.hudi")
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Dataset<Row> hoodieROViewDF = spark.read().format("org.apache.hudi")
// pass any path glob, can include hudi & non-hudi datasets
.load("/glob/path/pattern");
-</code></pre>
-</div>
+</code></pre></div></div>
<h3 id="spark-rt-view">Real time table</h3>
<p>Currently, real time table can only be queried as a Hive table in Spark. In order to do this, set <code class="highlighter-rouge">spark.sql.hive.convertMetastoreParquet=false</code>, forcing Spark to fallback
to using the Hive Serde to read the data (planning/executions is still Spark).</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>$ spark-shell --jars hudi-spark-bundle-x.y.z-SNAPSHOT.jar --driver-class-path /etc/hive/conf --packages com.databricks:spark-avro_2.11:4.0.0 --conf spark.sql.hive.convertMetastoreParquet=false --num-executors 10 --driver-memory 7g --executor-memory 2g --master yarn-client
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ spark-shell --jars hudi-spark-bundle-x.y.z-SNAPSHOT.jar --driver-class-path /etc/hive/conf --packages com.databricks:spark-avro_2.11:4.0.0 --conf spark.sql.hive.convertMetastoreParquet=false --num-executors 10 --driver-memory 7g --executor-memory 2g --master yarn-client
scala> sqlContext.sql("select count(*) from hudi_rt where datestr = '2016-10-02'").show()
-</code></pre>
-</div>
+</code></pre></div></div>
<h3 id="spark-incr-pull">Incremental Pulling</h3>
<p>The <code class="highlighter-rouge">hudi-spark</code> module offers the DataSource API, a more elegant way to pull data from Hudi dataset and process it via Spark.
A sample incremental pull, that will obtain all records written since <code class="highlighter-rouge">beginInstantTime</code>, looks like below.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code> Dataset<Row> hoodieIncViewDF = spark.read()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> Dataset<Row> hoodieIncViewDF = spark.read()
.format("org.apache.hudi")
.option(DataSourceReadOptions.VIEW_TYPE_OPT_KEY(),
DataSourceReadOptions.VIEW_TYPE_INCREMENTAL_OPT_VAL())
.option(DataSourceReadOptions.BEGIN_INSTANTTIME_OPT_KEY(),
<beginInstantTime>)
.load(tablePath); // For incremental view, pass in the root/base path of dataset
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Please refer to <a href="configurations.html#spark-datasource">configurations</a> section, to view all datasource options.</p>
@@ -570,7 +573,7 @@ This requires the <code class="highlighter-rouge">hudi-presto-bundle</code> jar
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/quickstart.html b/content/cn/quickstart.html
similarity index 73%
copy from content/quickstart.html
copy to content/cn/quickstart.html
index 21d49ab..951999a 100644
--- a/content/quickstart.html
+++ b/content/cn/quickstart.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, quickstart">
<title>Quickstart | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -115,15 +115,15 @@
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -132,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -171,8 +171,7 @@
<li>
- <!-- link to the Chinese home page when current is blog page -->
- <a href="/cn/quickstart.html">中文版</a>
+ <a href="/quickstart.html">English</a>
</li>
<!--comment out this block if you want to hide search-->
@@ -182,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Quickstart">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -230,28 +229,28 @@
- <li class="active"><a href="quickstart.html">Quickstart</a></li>
+ <li><a href="quickstart.html">Quickstart</a></li>
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -261,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -340,31 +339,32 @@
<p><br />
-To get a quick peek at Hudi’s capabilities, we have put together a <a href="https://www.youtube.com/watch?v=VhNgUsxdrD0">demo video</a>
-that showcases this on a docker based setup with all dependent systems running locally. We recommend you replicate the same setup
-and run the demo yourself, by following steps <a href="docker_demo.html">here</a>. Also, if you are looking for ways to migrate your existing data to Hudi,
-refer to <a href="migration_guide.html">migration guide</a>.</p>
+为快速了解Hudi的功能，我们制作了一个基于Docker设置、所有依赖系统都在本地运行的<a href="https://www.youtube.com/watch？V=vhngusxdrd0">演示视频</a>。
+我们建议您复制相同的设置然后按照<a href="docker_demo.html">这里</a>的步骤自己运行这个演示。另外，如果您正在寻找将现有数据迁移到Hudi的方法，请参阅<a href="migration_guide.html">迁移指南</a>。</p>
-<p>If you have Hive, Hadoop, Spark installed already & prefer to do it on your own setup, read on.</p>
+<p>如果您已经安装了hive、hadoop和spark，那么请继续阅读。</p>
-<h2 id="download-hudi">Download Hudi</h2>
+<h2 id="下载hudi">下载Hudi</h2>
-<p>Check out <a href="https://github.com/apache/incubator-hudi">code</a> and normally build the maven project, from command line</p>
+<p>Git检出<a href="https://github.com/apache/incubator-hudi">代码</a>或下载<a href="https://github.com/apache/incubator-hudi/archive/hudi-0.4.5.zip">最新版本</a></p>
+
+<p>并通过命令行构建maven项目</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ mvn clean install -DskipTests -DskipITs
</code></pre></div></div>
-<p>To work with older version of Hive (pre Hive-1.2.1), use</p>
+<p>如果使用旧版本的Hive(Hive-1.2.1以前)，使用</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ mvn clean install -DskipTests -DskipITs -Dhive11
</code></pre></div></div>
-<p>For IDE, you can pull in the code into IntelliJ as a normal maven project.
-You might want to add your spark jars folder to project dependencies under ‘Module Setttings’, to be able to run from IDE.</p>
+<blockquote>
+ <p>对于IDE，您可以将代码作为普通的maven项目导入IntelliJ。
+您可能需要将spark jars文件夹添加到 ‘Module Settings’ 下的项目依赖中，以便能够在IDE运行。</p>
+</blockquote>
-<h3 id="version-compatibility">Version Compatibility</h3>
+<h3 id="版本兼容性">版本兼容性</h3>
-<p>Hudi requires Java 8 to be installed on a *nix system. Hudi works with Spark-2.x versions.
-Further, we have verified that Hudi works with the following combination of Hadoop/Hive/Spark.</p>
+<p>Hudi要求在*nix系统上安装Java 8。 Hudi使用Spark-2.x版本。此外，我们已经验证Hudi可使用以下Hadoop/Hive/Spark组合。</p>
<table>
<thead>
@@ -372,7 +372,7 @@ Further, we have verified that Hudi works with the following combination of Hado
<th>Hadoop</th>
<th>Hive</th>
<th>Spark</th>
- <th>Instructions to Build Hudi</th>
+ <th>构建Hudi说明</th>
</tr>
</thead>
<tbody>
@@ -397,14 +397,15 @@ Further, we have verified that Hudi works with the following combination of Hado
</tbody>
</table>
-<p>If your environment has other versions of hadoop/hive/spark, please try out Hudi
-and let us know if there are any issues.</p>
+<blockquote>
+ <p>如果你的环境有其他版本的hadoop/hive/spark，请使用Hudi并告诉我们是否存在任何问题。</p>
+</blockquote>
-<h2 id="generate-sample-dataset">Generate Sample Dataset</h2>
+<h2 id="生成样本数据集">生成样本数据集</h2>
-<h3 id="environment-variables">Environment Variables</h3>
+<h3 id="环境变量">环境变量</h3>
-<p>Please set the following environment variables according to your setup. We have given an example setup with CDH version</p>
+<p>请根据您的设置配置以下环境变量。我们给出了一个CDH版本的示例设置</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd incubator-hudi
export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/jre/
@@ -418,10 +419,9 @@ export SPARK_CONF_DIR=$SPARK_HOME/conf
export PATH=$JAVA_HOME/bin:$HIVE_HOME/bin:$HADOOP_HOME/bin:$SPARK_INSTALL/bin:$PATH
</code></pre></div></div>
-<h3 id="run-hoodiejavaapp">Run HoodieJavaApp</h3>
+<h3 id="运行hoodiejavaapp">运行HoodieJavaApp</h3>
-<p>Run <strong>hudi-spark/src/test/java/HoodieJavaApp.java</strong> class, to place a two commits (commit 1 => 100 inserts, commit 2 => 100 updates to previously inserted 100 records) onto your DFS/local filesystem. Use the wrapper script
-to run from command-line</p>
+<p>运行 <strong>hudi-spark/src/test/java/HoodieJavaApp.java</strong> 类，将两个提交(提交1 => 100个插入，提交2 => 100个更新到先前插入的100个记录)放到DFS/本地文件系统上。从命令行运行脚本</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd hudi-spark
./run_hoodie_app.sh --help
@@ -440,14 +440,13 @@ Usage: <main class> [options]
Default: COPY_ON_WRITE
</code></pre></div></div>
-<p>The class lets you choose table names, output paths and one of the storage types. In your own applications, be sure to include the <code class="highlighter-rouge">hudi-spark</code> module as dependency
-and follow a similar pattern to write/read datasets via the datasource.</p>
+<p>这个类允许您选择表名、输出路径和存储类型。在您自己的应用程序中，请确保包含<code class="highlighter-rouge">hudi-spark</code>模块依赖并遵循类似模式通过数据源写入/读取数据集。</p>
-<h2 id="query-a-hudi-dataset">Query a Hudi dataset</h2>
+<h2 id="查询hudi数据集">查询Hudi数据集</h2>
-<p>Next, we will register the sample dataset into Hive metastore and try to query using <a href="#hive">Hive</a>, <a href="#spark">Spark</a> & <a href="#presto">Presto</a></p>
+<p>接下来，我们将样本数据集注册到Hive Metastore并尝试使用<a href="#hive">Hive</a>、<a href="#spark">Spark</a>和<a href="#presto">Presto</a>进行查询</p>
-<h3 id="start-hive-server-locally">Start Hive Server locally</h3>
+<h3 id="本地启动hive-server">本地启动Hive Server</h3>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hdfs namenode # start name node
hdfs datanode # start data node
@@ -461,10 +460,9 @@ bin/hiveserver2 \
</code></pre></div></div>
-<h3 id="run-hive-sync-tool">Run Hive Sync Tool</h3>
-<p>Hive Sync Tool will update/create the necessary metadata(schema and partitions) in hive metastore. This allows for schema evolution and incremental addition of new partitions written to.
-It uses an incremental approach by storing the last commit time synced in the TBLPROPERTIES and only syncing the commits from the last sync commit time stored.
-Both <a href="writing_data.html#datasource-writer">Spark Datasource</a> & <a href="writing_data.html#deltastreamer">DeltaStreamer</a> have capability to do this, after each write.</p>
+<h3 id="运行hive同步工具">运行Hive同步工具</h3>
+<p>Hive同步工具将在hive Metastore中更新/创建必要的元数据(模式和分区)，这允许模式演变和新分区的增量添加。它使用一种增量方法，将最后一次的同步提交时间存储在TBLPROPERTIES中，并且只同步上次存储的同步提交时间后的提交。
+每次写入后， <a href="writing_data.html #datasource-writer">Spark Datasource</a>和<a href="writing_data.html＃deltastreamer">DeltaStreamer</a>都可执行此操作。</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd hudi-hive
./run_sync_tool.sh
@@ -477,12 +475,14 @@ Both <a href="writing_data.html#datasource-writer">Spark Datasource</a> & <a
--partitioned-by field1,field2
</code></pre></div></div>
-<p>For some reason, if you want to do this by hand. Please
-follow <a href="https://cwiki.apache.org/confluence/display/HUDI/Registering+sample+dataset+to+Hive+via+beeline">this</a>.</p>
+
+<blockquote>
+ <p>若你想亲手运行。请参考<a href="https://cwiki.apache.org/confluence/display/HUDI/Registering+sample+dataset+to+Hive+via+beeline">这个</a>.</p>
+</blockquote>
<h3 id="hive">HiveQL</h3>
-<p>Let’s first perform a query on the latest committed snapshot of the table</p>
+<p>我们首先对表的最新提交的快照进行查询</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hive> set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
hive> set hive.stats.autogather=false;
@@ -497,7 +497,7 @@ hive>
<h3 id="spark">SparkSQL</h3>
-<p>Spark is super easy, once you get Hive working as above. Just spin up a Spark Shell as below</p>
+<p>只要你按上述方式让Hive工作起来，使用Spark将非常容易。只需启动Spark Shell，如下所示</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ cd $SPARK_INSTALL
$ spark-shell --jars $HUDI_SRC/packaging/hudi-spark-bundle/target/hudi-spark-bundle-0.4.6-SNAPSHOT.jar --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --packages com.databricks:spark-avro_2.11:4.0.0
@@ -511,20 +511,20 @@ scala> sqlContext.sql("select count(*) from hoodie_test").show(10000)
<h3 id="presto">Presto</h3>
-<p>Checkout the ‘master’ branch on OSS Presto, build it, and place your installation somewhere.</p>
+<p>Git检出OSS Presto上的 ‘master’ 分支，构建并安装。</p>
<ul>
- <li>Copy the hudi/packaging/hudi-presto-bundle/target/hudi-presto-bundle-*.jar into $PRESTO_INSTALL/plugin/hive-hadoop2/</li>
- <li>Startup your server and you should be able to query the same Hive table via Presto</li>
+ <li>将hudi/packaging/hudi-presto-bundle/target/hudi-presto-bundle-*.jar 复制到 $PRESTO_INSTALL/plugin/hive-hadoop2/</li>
+ <li>启动服务器，您应该能够通过Presto查询到相同的Hive表</li>
</ul>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>show columns from hive.default.hoodie_test;
select count(*) from hive.default.hoodie_test
</code></pre></div></div>
-<h3 id="incremental-hiveql">Incremental HiveQL</h3>
+<h3 id="增量-hiveql">增量 HiveQL</h3>
-<p>Let’s now perform a query, to obtain the <strong>ONLY</strong> changed rows since a commit in the past.</p>
+<p>现在我们执行一个查询，以获取自上次提交以来已更改的行。</p>
<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>hive> set hoodie.hoodie_test.consume.mode=INCREMENTAL;
hive> set hoodie.hoodie_test.consume.start.timestamp=001;
@@ -547,7 +547,9 @@ hive>
hive>
</code></pre></div></div>
-<p>This is only supported for Read-optimized view for now.”</p>
+<blockquote>
+ <p>注意：当前只有读优化视图支持。</p>
+</blockquote>
<div class="tags">
@@ -576,7 +578,7 @@ hive>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
@@ -608,4 +610,4 @@ hive>
</body>
-</html>
+</html>
\ No newline at end of file
diff --git a/content/s3_hoodie.html b/content/cn/s3_hoodie.html
similarity index 85%
copy from content/s3_hoodie.html
copy to content/cn/s3_hoodie.html
index 1a36a0c..b58fe8b 100644
--- a/content/s3_hoodie.html
+++ b/content/cn/s3_hoodie.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we go over how to configure Hudi with S3 filesystem.">
<meta name="keywords" content="hudi, hive, aws, s3, spark, presto">
<title>S3 Filesystem | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/s3_hoodie.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="S3 Filesystem">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -350,7 +357,7 @@
<p>Alternatively, add the required configs in your core-site.xml from where Hudi can fetch them. Replace the <code class="highlighter-rouge">fs.defaultFS</code> with your S3 bucket name and Hudi should be able to read/write from the bucket.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code> <property>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <property>
<name>fs.defaultFS</name>
<value>s3://ysharma</value>
</property>
@@ -379,21 +386,19 @@
<name>fs.s3n.awsSecretAccessKey</name>
<value>AWS_SECRET</value>
</property>
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Utilities such as hudi-cli or deltastreamer tool, can pick up s3 creds via environmental variable prefixed with <code class="highlighter-rouge">HOODIE_ENV_</code>. For e.g below is a bash snippet to setup
such variables and then have cli be able to work on datasets stored in s3</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>export HOODIE_ENV_fs_DOT_s3a_DOT_access_DOT_key=$accessKey
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>export HOODIE_ENV_fs_DOT_s3a_DOT_access_DOT_key=$accessKey
export HOODIE_ENV_fs_DOT_s3a_DOT_secret_DOT_key=$secretKey
export HOODIE_ENV_fs_DOT_s3_DOT_awsAccessKeyId=$accessKey
export HOODIE_ENV_fs_DOT_s3_DOT_awsSecretAccessKey=$secretKey
export HOODIE_ENV_fs_DOT_s3n_DOT_awsAccessKeyId=$accessKey
export HOODIE_ENV_fs_DOT_s3n_DOT_awsSecretAccessKey=$secretKey
export HOODIE_ENV_fs_DOT_s3n_DOT_impl=org.apache.hadoop.fs.s3a.S3AFileSystem
-</code></pre>
-</div>
+</code></pre></div></div>
<h3 id="aws-libs">AWS Libs</h3>
@@ -423,7 +428,7 @@ export HOODIE_ENV_fs_DOT_s3n_DOT_impl=org.apache.hadoop.fs.s3a.S3AFileSystem
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/powered_by.html b/content/cn/use_cases.html
similarity index 53%
copy from content/powered_by.html
copy to content/cn/use_cases.html
index 27a7d31..f0c8472 100644
--- a/content/powered_by.html
+++ b/content/cn/use_cases.html
@@ -3,28 +3,28 @@
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1">
-<meta name="description" content="">
-<meta name="keywords" content="hudi, talks, presentation">
-<title>Talks & Powered By | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<meta name="description" content="以下是一些使用Hudi的示例，说明了加快处理速度和提高效率的好处">
+<meta name="keywords" content="hudi, data ingestion, etl, real time, use cases">
+<title>Use Cases | Hudi</title>
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -115,15 +115,15 @@
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -132,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -164,15 +164,14 @@
- <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Talks & Powered By page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
+ <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Use Cases page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
<li>
<li>
- <!-- link to the Chinese home page when current is blog page -->
- <a href="/cn/powered_by.html">中文版</a>
+ <a href="/use_cases.html">English</a>
</li>
<!--comment out this block if you want to hide search-->
@@ -182,13 +181,13 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
- searchResultTemplate: '<li><a href="{url}" title="Talks & Powered By">{title}</a></li>',
+ dataSource: '/search.json',
+ searchResultTemplate: '<li><a href="{url}" title="Use Cases">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
fuzzy: true,
@@ -237,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li class="active"><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -261,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -325,7 +324,7 @@
<!-- Content Column -->
<div class="col-md-9">
<div class="post-header">
- <h1 class="post-title-main">Talks & Powered By</h1>
+ <h1 class="post-title-main">Use Cases</h1>
</div>
@@ -333,74 +332,66 @@
<div class="post-content">
+ <div class="summary">以下是一些使用Hudi的示例，说明了加快处理速度和提高效率的好处</div>
+
- <h2 id="adoption">Adoption</h2>
-
-<h4 id="uber">Uber</h4>
-
-<p>Hudi was originally developed at <a href="https://uber.com">Uber</a>, to achieve <a href="http://www.slideshare.net/vinothchandar/hadoop-strata-talk-uber-your-hadoop-has-arrived/32">low latency database ingestion, with high efficiency</a>.
-It has been in production since Aug 2016, powering ~100 highly business critical tables on Hadoop, worth 100s of TBs(including top 10 including trips,riders,partners).
-It also powers several incremental Hive ETL pipelines and being currently integrated into Uber’s data dispersal system.</p>
-
-<h4 id="emis-health">EMIS Health</h4>
-
-<p>[EMIS Health][https://www.emishealth.com/] is the largest provider of Primary Care IT software in the UK with datasets including more than 500Bn healthcare records. HUDI is used to manage their analytics dataset in production and keeping them up-to-date with their upstream source. Presto is being used to query the data written in HUDI format.</p>
-
-<h4 id="yieldsio">Yields.io</h4>
-
-<p>Yields.io is the first FinTech platform that uses AI for automated model validation and real-time monitoring on an enterprise-wide scale. Their data lake is managed by Hudi. They are also actively building their infrastructure for incremental, cross language/platform machine learning using Hudi.</p>
-
-<h4 id="yotpo">Yotpo</h4>
-
-<p>Using Hudi at Yotpo for several usages. Firstly, integrated Hudi as a writer in their open source ETL framework https://github.com/YotpoLtd/metorikku and using as an output writer for a CDC pipeline, with events that are being generated from a database binlog streams to Kafka and then are written to S3.</p>
-
-<h2 id="talks--presentations">Talks & Presentations</h2>
-
-<ol>
- <li>
- <p><a href="https://conferences.oreilly.com/strata/strata-ca/public/schedule/detail/56511">“Hoodie: Incremental processing on Hadoop at Uber”</a> - By Vinoth Chandar & Prasanna Rajaperumal
-Mar 2017, Strata + Hadoop World, San Jose, CA</p>
- </li>
- <li>
- <p><a href="http://www.dataengconf.com/hoodie-an-open-source-incremental-processing-framework-from-uber">“Hoodie: An Open Source Incremental Processing Framework From Uber”</a> - By Vinoth Chandar.
-Apr 2017, DataEngConf, San Francisco, CA <a href="https://www.slideshare.net/vinothchandar/hoodie-dataengconf-2017">Slides</a> <a href="https://www.youtube.com/watch?v=7Wudjc-v7CA">Video</a></p>
- </li>
- <li>
- <p><a href="https://spark-summit.org/2017/events/incremental-processing-on-large-analytical-datasets/">“Incremental Processing on Large Analytical Datasets”</a> - By Prasanna Rajaperumal
-June 2017, Spark Summit 2017, San Francisco, CA. <a href="https://www.slideshare.net/databricks/incremental-processing-on-large-analytical-datasets-with-prasanna-rajaperumal-and-vinoth-chandar">Slides</a> <a href="https://www.youtube.com/watch?v=3HS0lQX-cgo&feature=youtu.be">Video</a></p>
- </li>
- <li>
- <p><a href="https://conferences.oreilly.com/strata/strata-ny/public/schedule/detail/70937">“Hudi: Unifying storage and serving for batch and near-real-time analytics”</a> - By Nishith Agarwal & Balaji Vardarajan
-September 2018, Strata Data Conference, New York, NY</p>
- </li>
- <li>
- <p><a href="https://databricks.com/session/hudi-near-real-time-spark-pipelines-at-petabyte-scale">“Hudi: Large-Scale, Near Real-Time Pipelines at Uber”</a> - By Vinoth Chandar & Nishith Agarwal
-October 2018, Spark+AI Summit Europe, London, UK</p>
- </li>
- <li>
- <p><a href="https://www.youtube.com/watch?v=1w3IpavhSWA">“Powering Uber’s global network analytics pipelines in real-time with Apache Hudi”</a> - By Ethan Guo & Nishith Agarwal, April 2019, Data Council SF19, San Francisco, CA.</p>
- </li>
- <li>
- <p><a href="https://www.slideshare.net/ChesterChen/sf-big-analytics-20190612-building-highly-efficient-data-lakes-using-apache-hudi">“Building highly efficient data lakes using Apache Hudi (Incubating)”</a> - By Vinoth Chandar
-June 2019, SF Big Analytics Meetup, San Mateo, CA</p>
- </li>
- <li>
- <p><a href="https://docs.google.com/presentation/d/1FHhsvh70ZP6xXlHdVsAI0g__B_6Mpto5KQFlZ0b8-mM">“Apache Hudi (Incubating) - The Past, Present and Future Of Efficient Data Lake Architectures”</a> - By Vinoth Chandar & Balaji Varadarajan
-September 2019, ApacheCon NA 19, Las Vegas, NV, USA</p>
- </li>
-</ol>
-
-<h2 id="articles">Articles</h2>
-
-<ol>
- <li><a href="https://www.oreilly.com/ideas/ubers-case-for-incremental-processing-on-hadoop">“The Case for incremental processing on Hadoop”</a> - O’reilly Ideas article by Vinoth Chandar</li>
- <li><a href="https://eng.uber.com/hoodie/">“Hoodie: Uber Engineering’s Incremental Processing Framework on Hadoop”</a> - Engineering Blog By Prasanna Rajaperumal</li>
-</ol>
+ <h2 id="近实时摄取">近实时摄取</h2>
+
+<p>将外部源(如事件日志、数据库、外部源)的数据摄取到<a href="http://martinfowler.com/bliki/DataLake.html">Hadoop数据湖</a>是一个众所周知的问题。
+尽管这些数据对整个组织来说是最有价值的，但不幸的是，在大多数(如果不是全部)Hadoop部署中都使用零散的方式解决，即使用多个不同的摄取工具。</p>
+
+<p>对于RDBMS摄取，Hudi提供__通过更新插入达到更快加载__，而不是昂贵且低效的批量加载。例如，您可以读取MySQL BIN日志或<a href="https://sqoop.apache.org/docs/1.4.2/SqoopUserGuide.html#_incremental_imports">Sqoop增量导入</a>并将其应用于
+DFS上的等效Hudi表。这比<a href="https://sqoop.apache.org/docs/1.4.0-incubating/SqoopUserGuide.html#id1770457">批量合并任务</a>及<a href="http://hortonworks.com/blog/four-step-strategy-incremental-updates-hive/">复杂的手工合并工作流</a>更快/更有效率。</p>
+
+<p>对于NoSQL数据存储，如<a href="http://cassandra.apache.org/">Cassandra</a> / <a href="http://www.project-voldemort.com/voldemort/">Voldemort</a> / <a href="https://hbase.apache.org/">HBase</a>，即使是中等规模大小也会存储数十亿行。
+毫无疑问， <strong>全量加载不可行</strong>，如果摄取需要跟上较高的更新量，那么则需要更有效的方法。</p>
+
+<p>即使对于像<a href="kafka.apache.org">Kafka</a>这样的不可变数据源，Hudi也可以 <strong>强制在HDFS上使用最小文件大小</strong>, 这采取了综合方式解决<a href="https://blog.cloudera.com/blog/2009/02/the-small-files-problem/">Hadoop中的一个老问题</a>来改善NameNode的健康状况。这对事件流来说更为重要，因为它通常具有较高容量(例如：点击流)，如果管理不当，可能会对Hadoop群集造成严重损害。</p>
+
+<p>在所有源中，通过<code class="highlighter-rouge">提交</code>这一概念，Hudi增加了以原子方式向消费者发布新数据的功能，这种功能十分必要。</p>
+
+<h2 id="近实时分析">近实时分析</h2>
+
+<p>通常，实时<a href="https://en.wikipedia.org/wiki/Data_mart">数据集市</a>由专业(实时)数据分析存储提供支持，例如<a href="http://druid.io/">Druid</a>或<a href="http://www.memsql.com/">Memsql</a>或<a href="http://opentsdb.net/">OpenTSDB</a>。
+这对于较小规模的数据量来说绝对是完美的(<a href="https://blog.twitter.com/2015/hadoop-filesystem-at-twitter">相比于这样安装Hadoop</a>)，这种情况需要在亚秒级响应查询，例如系统监控或交互式实时分析。
+但是，由于Hadoop上的数据太陈旧了，通常这些系统会被滥用于非交互式查询，这导致利用率不足和硬件/许可证成本的浪费。</p>
+
+<p>另一方面，Hadoop上的交互式SQL解决方案(如Presto和SparkSQL)表现出色，在__几秒钟内完成查询__。
+通过将__数据新鲜度提高到几分钟__，Hudi可以提供一个更有效的替代方案，并支持存储在DFS中的__数量级更大的数据集__的实时分析。
+此外，Hudi没有外部依赖(如专用于实时分析的HBase集群)，因此可以在更新的分析上实现更快的分析，而不会增加操作开销。</p>
+
+<h2 id="增量处理管道">增量处理管道</h2>
+
+<p>Hadoop提供的一个基本能力是构建一系列数据集，这些数据集通过表示为工作流的DAG相互派生。
+工作流通常取决于多个上游工作流输出的新数据，新数据的可用性传统上由新的DFS文件夹/Hive分区指示。
+让我们举一个具体的例子来说明这点。上游工作流<code class="highlighter-rouge">U</code>可以每小时创建一个Hive分区，在每小时结束时(processing_time)使用该小时的数据(event_time)，提供1小时的有效新鲜度。
+然后，下游工作流<code class="highlighter-rouge">D</code>在<code class="highlighter-rouge">U</code>结束后立即启动，并在下一个小时内自行处理，将有效延迟时间增加到2小时。</p>
+
+<p>上面的示例忽略了迟到的数据，即<code class="highlighter-rouge">processing_time</code>和<code class="highlighter-rouge">event_time</code>分开时。
+不幸的是，在今天的后移动和前物联网世界中，<strong>来自间歇性连接的移动设备和传感器的延迟数据是常态，而不是异常</strong>。
+在这种情况下，保证正确性的唯一补救措施是<a href="https://falcon.apache.org/FalconDocumentation.html#Handling_late_input_data">重新处理最后几个小时</a>的数据，
+每小时一遍又一遍，这可能会严重影响整个生态系统的效率。例如; 试想一下，在数百个工作流中每小时重新处理TB数据。</p>
+
+<p>Hudi通过以单个记录为粒度的方式(而不是文件夹/分区)从上游 Hudi数据集<code class="highlighter-rouge">HU</code>消费新数据(包括迟到数据)，来解决上面的问题。
+应用处理逻辑，并使用下游Hudi数据集<code class="highlighter-rouge">HD</code>高效更新/协调迟到数据。在这里，<code class="highlighter-rouge">HU</code>和<code class="highlighter-rouge">HD</code>可以以更频繁的时间被连续调度
+比如15分钟，并且<code class="highlighter-rouge">HD</code>提供端到端30分钟的延迟。</p>
+
+<p>为实现这一目标，Hudi采用了类似于<a href="https://spark.apache.org/docs/latest/streaming-programming-guide.html#join-operations">Spark Streaming</a>、发布/订阅系统等流处理框架，以及像<a href="http://kafka.apache.org/documentation/#theconsumer">Kafka</a>
+或<a href="https://docs.oracle.com/cd/E11882_01/server.112/e16545/xstrm_cncpt.htm#XSTRM187">Oracle XStream</a>等数据库复制技术的类似概念。
+如果感兴趣，可以在<a href="https://www.oreilly.com/ideas/ubers-case-for-incremental-processing-on-hadoop">这里</a>找到有关增量处理(相比于流处理和批处理)好处的更详细解释。</p>
+
+<h2 id="dfs的数据分发">DFS的数据分发</h2>
+
+<p>Hadoop的一个流行用例是压缩数据，然后将其分发回在线服务存储层，以供应用程序使用。
+例如，一个Spark管道可以<a href="https://eng.uber.com/telematics/">确定Hadoop上的紧急制动事件</a>并将它们加载到服务存储层(如ElasticSearch)中，供Uber应用程序使用以增加安全驾驶。这种用例中，通常架构会在Hadoop和服务存储之间引入<code class="highlighter-rouge">队列</code>，以防止目标服务存储被压垮。
+对于队列的选择，一种流行的选择是Kafka，这个模型经常导致__在DFS上存储相同数据的冗余(用于计算结果的离线分析)和Kafka(用于分发)__</p>
+
+<p>通过将每次运行的Spark管道更新插入的输出转换为Hudi数据集，Hudi可以再次有效地解决这个问题，然后可以以增量方式获取尾部数据(就像Kafka主题一样)然后写入服务存储层。</p>
<div class="tags">
@@ -421,7 +412,7 @@ September 2019, ApacheCon NA 19, Las Vegas, NV, USA</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
@@ -453,4 +444,4 @@ September 2019, ApacheCon NA 19, Las Vegas, NV, USA</p>
</body>
-</html>
+</html>
\ No newline at end of file
diff --git a/content/writing_data.html b/content/cn/writing_data.html
similarity index 88%
copy from content/writing_data.html
copy to content/cn/writing_data.html
index 70c8ac9..ca21699 100644
--- a/content/writing_data.html
+++ b/content/cn/writing_data.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we will discuss some available tools for incrementally ingesting & storing data.">
<meta name="keywords" content="hudi, incremental, batch, stream, processing, Hive, ETL, Spark SQL">
<title>Writing Hudi Datasets | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,17 +111,19 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
- <li><a href="news">News</a></li>
+ <li><a href="news">新闻</a></li>
- <li><a href="community.html">Community</a></li>
+ <li><a href="community.html">社区</a></li>
- <li><a href="https://github.com/apache/incubator-hudi" target="_blank">Code</a></li>
+ <li><a href="https://github.com/apache/incubator-hudi" target="_blank">代码</a></li>
@@ -130,27 +132,27 @@
<li class="dropdown">
- <a href="#" class="dropdown-toggle" data-toggle="dropdown">Developers<b class="caret"></b></a>
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">开发者<b class="caret"></b></a>
<ul class="dropdown-menu">
- <li><a href="contributing.html">Contributing</a></li>
+ <li><a href="contributing.html">贡献</a></li>
- <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">Wiki/Designs</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank">维基/设计</a></li>
- <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">Issues</a></li>
+ <li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank">问题</a></li>
- <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">Blog</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/pages/viewrecentblogposts.action?key=HUDI" target="_blank">博客</a></li>
- <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">Team</a></li>
+ <li><a href="https://projects.apache.org/project.html?incubator-hudi" target="_blank">团队</a></li>
</ul>
@@ -167,6 +169,11 @@
<li>
+ <li>
+
+ <a href="/writing_data.html">English</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +181,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Writing Hudi Datasets">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -229,21 +236,21 @@
- <li><a href="use_cases.html">Use Cases</a></li>
+ <li><a href="use_cases.html">用户案例</a></li>
- <li><a href="powered_by.html">Talks & Powered By</a></li>
+ <li><a href="powered_by.html">演讲 & Powered By</a></li>
- <li><a href="comparison.html">Comparison</a></li>
+ <li><a href="comparison.html">对比</a></li>
@@ -253,47 +260,47 @@
<li>
- <a href="#">Documentation</a>
+ <a href="#">文档</a>
<ul>
- <li><a href="concepts.html">Concepts</a></li>
+ <li><a href="concepts.html">概念</a></li>
- <li class="active"><a href="writing_data.html">Writing Data</a></li>
+ <li><a href="writing_data.html">写入数据</a></li>
- <li><a href="querying_data.html">Querying Data</a></li>
+ <li><a href="querying_data.html">查询数据</a></li>
- <li><a href="configurations.html">Configuration</a></li>
+ <li><a href="configurations.html">配置</a></li>
- <li><a href="performance.html">Performance</a></li>
+ <li><a href="performance.html">性能</a></li>
- <li><a href="admin_guide.html">Administering</a></li>
+ <li><a href="admin_guide.html">管理</a></li>
@@ -367,7 +374,7 @@ can be chosen/changed across each commit/deltacommit issued against the dataset.
<p>Command line options describe capabilities in more detail</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>[hoodie]$ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer `ls packaging/hudi-utilities-bundle/target/hudi-utilities-bundle-*.jar` --help
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>[hoodie]$ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer `ls packaging/hudi-utilities-bundle/target/hudi-utilities-bundle-*.jar` --help
Usage: <main class> [options]
Options:
--commit-on-errors
@@ -436,29 +443,26 @@ Usage: <main class> [options]
schema) before writing. Default : Not set. E:g -
org.apache.hudi.utilities.transform.SqlQueryBasedTransformer (which
allows a SQL query template to be passed as a transformation function)
-</code></pre>
-</div>
+</code></pre></div></div>
<p>The tool takes a hierarchically composed property file and has pluggable interfaces for extracting data, key generation and providing schema. Sample configs for ingesting from kafka and dfs are
provided under <code class="highlighter-rouge">hudi-utilities/src/test/resources/delta-streamer-config</code>.</p>
<p>For e.g: once you have Confluent Kafka, Schema registry up & running, produce some test data using (<a href="https://docs.confluent.io/current/ksql/docs/tutorials/generate-custom-test-data.html">impressions.avro</a> provided by schema-registry repo)</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>[confluent-5.0.0]$ bin/ksql-datagen schema=../impressions.avro format=avro topic=impressions key=impressionid
-</code></pre>
-</div>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>[confluent-5.0.0]$ bin/ksql-datagen schema=../impressions.avro format=avro topic=impressions key=impressionid
+</code></pre></div></div>
<p>and then ingest it as follows.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>[hoodie]$ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer `ls packaging/hudi-utilities-bundle/target/hudi-utilities-bundle-*.jar` \
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>[hoodie]$ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer `ls packaging/hudi-utilities-bundle/target/hudi-utilities-bundle-*.jar` \
--props file://${PWD}/hudi-utilities/src/test/resources/delta-streamer-config/kafka-source.properties \
--schemaprovider-class org.apache.hudi.utilities.schema.SchemaRegistryProvider \
--source-class org.apache.hudi.utilities.sources.AvroKafkaSource \
--source-ordering-field impresssiontime \
--target-base-path file:///tmp/hudi-deltastreamer-op --target-table uber.impressions \
--op BULK_INSERT
-</code></pre>
-</div>
+</code></pre></div></div>
<p>In some cases, you may want to migrate your existing dataset into Hudi beforehand. Please refer to <a href="migration_guide.html">migration guide</a>.</p>
@@ -468,7 +472,7 @@ provided under <code class="highlighter-rouge">hudi-utilities/src/test/resources
Following is how we can upsert a dataframe, while specifying the field names that need to be used
for <code class="highlighter-rouge">recordKey => _row_key</code>, <code class="highlighter-rouge">partitionPath => partition</code> and <code class="highlighter-rouge">precombineKey => timestamp</code></p>
-<div class="highlighter-rouge"><pre class="highlight"><code>inputDF.write()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>inputDF.write()
.format("org.apache.hudi")
.options(clientOpts) // any of the Hudi client opts can be passed in as well
.option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY(), "_row_key")
@@ -477,8 +481,7 @@ for <code class="highlighter-rouge">recordKey => _row_key</code>, <code class
.option(HoodieWriteConfig.TABLE_NAME, tableName)
.mode(SaveMode.Append)
.save(basePath);
-</code></pre>
-</div>
+</code></pre></div></div>
<h2 id="syncing-to-hive">Syncing to Hive</h2>
@@ -486,7 +489,7 @@ for <code class="highlighter-rouge">recordKey => _row_key</code>, <code class
In case, its preferable to run this from commandline or in an independent jvm, Hudi provides a <code class="highlighter-rouge">HiveSyncTool</code>, which can be invoked as below,
once you have built the hudi-hive module.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cd hudi-hive
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd hudi-hive
./run_sync_tool.sh
[hudi-hive]$ ./run_sync_tool.sh --help
Usage: <main class> [options]
@@ -505,8 +508,7 @@ Usage: <main class> [options]
name of the target table in Hive
* --user
Hive username
-</code></pre>
-</div>
+</code></pre></div></div>
<h2 id="deletes">Deletes</h2>
@@ -519,14 +521,13 @@ Usage: <main class> [options]
via either DataSource or DeltaStreamer which always returns Optional.Empty as the combined value. Hudi ships with a built-in <code class="highlighter-rouge">org.apache.hudi.EmptyHoodieRecordPayload</code> class that does exactly this.</li>
</ul>
-<div class="highlighter-rouge"><pre class="highlight"><code> deleteDF // dataframe containing just records to be deleted
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> deleteDF // dataframe containing just records to be deleted
.write().format("org.apache.hudi")
.option(...) // Add HUDI options like record-key, partition-path and others as needed for your setup
// specify record_key, partition_key, precombine_fieldkey & usual params
.option(DataSourceWriteOptions.PAYLOAD_CLASS_OPT_KEY, "org.apache.hudi.EmptyHoodieRecordPayload")
-</code></pre>
-</div>
+</code></pre></div></div>
<h2 id="storage-management">Storage Management</h2>
@@ -567,7 +568,7 @@ once created cannot be deleted, but simply expanded as explained before.</li>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/community.html b/content/community.html
index 89eb6c7..0e9abb9 100644
--- a/content/community.html
+++ b/content/community.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, use cases, big data, apache">
<title>Community | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/community.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Community">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -345,7 +353,7 @@
<tbody>
<tr>
<td>For any general questions, user support, development discussions</td>
- <td>Dev Mailing list (<a href="mailto:dev-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:dev-unsubscribe@hudi.apache.or& [...]
+ <td>Dev Mailing list (<a href="mailto:dev-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:dev-unsubscribe@hudi.apache.org">Unsubscribe</a>, <a href="https://lists.apache.org/list.html?dev@hudi.apache.org">Archives</a>). Empty email works for subscribe/unsubscribe. Please use <a href="https://gist.github.com">gists</a> to share code/stacktraces on the email.</td>
</tr>
<tr>
<td>For reporting bugs or issues or discover known issues</td>
@@ -353,7 +361,7 @@
</tr>
<tr>
<td>For quick pings & 1-1 chats</td>
- <td>Join our <a href="https://join.slack.com/t/apache-hudi/signup">slack group</a></td>
+ <td>Join our <a href="https://join.slack.com/t/apache-hudi/signup">slack group</a>. In case your mail domain is not there in pre-approved list for joining slack group, please check out the <a href="https://github.com/apache/incubator-hudi/issues/143">github issue</a></td>
</tr>
<tr>
<td>For proposing large features, changes</td>
@@ -365,12 +373,12 @@
</tr>
<tr>
<td>For stream of commits, pull requests etc</td>
- <td>Commits Mailing list (<a href="mailto:commits-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:commits-unsubscribe@hudi.� [...]
+ <td>Commits Mailing list (<a href="mailto:commits-subscribe@hudi.apache.org">Subscribe</a>, <a href="mailto:commits-unsubscribe@hudi.apache.org">Unsubscribe</a>, <a href="https://lists.apache.org/list.html?commits@hudi.apache.org">Archives</a>)</td>
</tr>
</tbody>
</table>
-<p>If you wish to report a security vulnerability, please contact <a href="mailto:security@apache.org">security@apache.org</a>.
+<p>If you wish to report a security vulnerability, please contact <a href="mailto:security@apache.org">security@apache.org</a>.
Apache Hudi follows the typical Apache vulnerability handling <a href="https://apache.org/security/committers.html#vulnerability-handling">process</a>.</p>
<h2 id="contributing">Contributing</h2>
@@ -438,7 +446,7 @@ Specifically, please refer to the detailed <a href="contributing.html">contribut
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/comparison.html b/content/comparison.html
index a308acd..644ff8b 100644
--- a/content/comparison.html
+++ b/content/comparison.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="apache, hudi, kafka, kudu, hive, hbase, stream processing">
<title>Comparison | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/comparison.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Comparison">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -399,7 +407,7 @@ and will eventually happen as a <a href="https://issues.apache.org/jira/browse/H
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/concepts.html b/content/concepts.html
index 67d1e5e..ac506d7 100644
--- a/content/concepts.html
+++ b/content/concepts.html
@@ -6,25 +6,25 @@
<meta name="description" content="Here we introduce some basic concepts & give a broad technical overview of Hudi">
<meta name="keywords" content="hudi, design, storage, views, timeline">
<title>Concepts | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/concepts.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Concepts">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -374,7 +382,9 @@ in one of the following states</p>
<li><code class="highlighter-rouge">COMPLETED</code> - Denotes completion of an action on the timeline</li>
</ul>
-<figure><img class="docimage" src="images/hudi_timeline.png" alt="hudi_timeline.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_timeline.png" alt="hudi_timeline.png" />
+</figure>
<p>Example above shows upserts happenings between 10:00 and 10:20 on a Hudi dataset, roughly every 5 mins, leaving commit metadata on the Hudi timeline, along
with other background cleaning/compactions. One key observation to make is that the commit time indicates the <code class="highlighter-rouge">arrival time</code> of the data (10:20AM), while the actual data
@@ -507,7 +517,9 @@ This is a much desired property for analytical workloads, which is predominantly
<p>Following illustrates how this works conceptually, when data written into copy-on-write storage and two queries running on top of it.</p>
-<figure><img class="docimage" src="images/hudi_cow.png" alt="hudi_cow.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_cow.png" alt="hudi_cow.png" />
+</figure>
<p>As data gets written, updates to existing file groups produce a new slice for that file group stamped with the commit instant time,
while inserts allocate a new file group and write its first slice for that file group. These file slices and their commit instant times are color coded above.
@@ -533,7 +545,9 @@ their columnar base file, to keep the query performance in check (larger delta l
<p>Following illustrates how the storage works, and shows queries on both near-real time table and read optimized table.</p>
-<figure><img class="docimage" src="images/hudi_mor.png" alt="hudi_mor.png" style="max-width: 1000px" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_mor.png" alt="hudi_mor.png" style="max-width: 1000px" />
+</figure>
<p>There are lot of interesting things happening in this example, which bring out the subtleties in the approach.</p>
@@ -575,7 +589,7 @@ this storage such as reduced write amplification by avoiding synchronous merge o
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/configurations.html b/content/configurations.html
index 09c4f8e..a0d1bf9 100644
--- a/content/configurations.html
+++ b/content/configurations.html
@@ -6,25 +6,25 @@
<meta name="description" content="Here we list all possible configurations and what they mean">
<meta name="keywords" content="garbage collection, hudi, jvm, configs, tuning">
<title>Configurations | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/configurations.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Configurations">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -389,7 +397,7 @@ The actual datasource level configs are listed below.</p>
<p>Additionally, you can pass down any of the WriteClient level configs directly using <code class="highlighter-rouge">options()</code> or <code class="highlighter-rouge">option(k,v)</code> methods.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>inputDF.write()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>inputDF.write()
.format("org.apache.hudi")
.options(clientOpts) // any of the Hudi client opts can be passed in as well
.option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY(), "_row_key")
@@ -398,8 +406,7 @@ The actual datasource level configs are listed below.</p>
.option(HoodieWriteConfig.TABLE_NAME, tableName)
.mode(SaveMode.Append)
.save(basePath);
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Options useful for writing datasets via <code class="highlighter-rouge">write.format.option(...)</code></p>
@@ -513,7 +520,7 @@ necessarily correspond to an instant on the timeline. New data written with an
<p>Jobs programming directly against the RDD level apis can build a <code class="highlighter-rouge">HoodieWriteConfig</code> object and pass it in to the <code class="highlighter-rouge">HoodieWriteClient</code> constructor.
HoodieWriteConfig can be built using a builder pattern as below.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>HoodieWriteConfig cfg = HoodieWriteConfig.newBuilder()
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>HoodieWriteConfig cfg = HoodieWriteConfig.newBuilder()
.withPath(basePath)
.forTable(tableName)
.withSchema(schemaStr)
@@ -522,8 +529,7 @@ HoodieWriteConfig can be built using a builder pattern as below.</p>
.withIndexConfig(HoodieIndexConfig.newBuilder().withXXX(...).build())
...
.build();
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Following subsections go over different aspects of write configs, explaining most important configs with their property names, default values.</p>
@@ -799,7 +805,7 @@ HoodieWriteConfig can be built using a builder pattern as below.</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/contributing.html b/content/contributing.html
index 6a5090c..5dc2f6e 100644
--- a/content/contributing.html
+++ b/content/contributing.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, ide, developer, setup">
<title>Developer Setup | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/contributing.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Developer Setup">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -461,7 +469,7 @@ instructions on making changes to the website.</p>
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/docker-compose.yml b/content/docker-compose.yml
new file mode 100644
index 0000000..7c454e3
--- /dev/null
+++ b/content/docker-compose.yml
@@ -0,0 +1,13 @@
+version: '3.3'
+services:
+ server:
+ build:
+ context: .
+ dockerfile: Dockerfile
+ image: hudi_docs/latest
+ ports:
+ - '4000:4000'
+ volumes:
+ - ".:/src"
+networks:
+ default:
diff --git a/content/docker_demo.html b/content/docker_demo.html
index b904d84..97c76c6 100644
--- a/content/docker_demo.html
+++ b/content/docker_demo.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="hudi, docker, demo">
<title>Docker Demo | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/docker_demo.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Docker Demo">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -346,7 +354,7 @@ data infrastructure is brought up in a local docker cluster within your computer
<li>/etc/hosts : The demo references many services running in container by the hostname. Add the following settings to /etc/hosts</li>
</ul>
-<div class="highlighter-rouge"><pre class="highlight"><code> 127.0.0.1 adhoc-1
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> 127.0.0.1 adhoc-1
127.0.0.1 adhoc-2
127.0.0.1 namenode
127.0.0.1 datanode1
@@ -355,8 +363,7 @@ data infrastructure is brought up in a local docker cluster within your computer
127.0.0.1 kafkabroker
127.0.0.1 sparkmaster
127.0.0.1 zookeeper
-</code></pre>
-</div>
+</code></pre></div></div>
<p>Also, this has not been tested on some environments like Docker on Windows.</p>
@@ -364,18 +371,17 @@ data infrastructure is brought up in a local docker cluster within your computer
<h4 id="build-hudi">Build Hudi</h4>
-<p>The first step is to build hudi
-<code class="highlighter-rouge">
-cd <HUDI_WORKSPACE>
+<p>The first step is to build hudi</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd <HUDI_WORKSPACE>
mvn package -DskipTests
-</code></p>
+</code></pre></div></div>
<h4 id="bringing-up-demo-cluster">Bringing up Demo Cluster</h4>
<p>The next step is to run the docker compose script and setup configs for bringing up the cluster.
This should pull the docker images from docker hub and setup docker cluster.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cd docker
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd docker
./setup_demo.sh
....
....
@@ -395,7 +401,9 @@ Creating hivemetastore ... done
Creating historyserver ... done
Creating hiveserver ... done
Creating datanode1 ... done
+Creating presto-coordinator-1 ... done
Creating sparkmaster ... done
+Creating presto-worker-1 ... done
Creating adhoc-1 ... done
Creating adhoc-2 ... done
Creating spark-worker-1 ... done
@@ -403,8 +411,7 @@ Copying spark default config and setting up configs
Copying spark default config and setting up configs
Copying spark default config and setting up configs
varadarb-C02SG7Q3G8WP:docker varadarb$ docker ps
-</code></pre>
-</div>
+</code></pre></div></div>
<p>At this point, the docker cluster will be up and running. The demo cluster brings up the following services</p>
@@ -430,7 +437,7 @@ The batches are windowed intentionally so that the second batch contains updates
<p>Upload the first batch to Kafka topic ‘stock ticks’</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cat docker/demo/data/batch_1.json | kafkacat -b kafkabroker -t stock_ticks -P
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cat docker/demo/data/batch_1.json | kafkacat -b kafkabroker -t stock_ticks -P
To check if the new topic shows up, use
kafkacat -b kafkabroker -L -J | jq .
@@ -471,8 +478,7 @@ kafkacat -b kafkabroker -L -J | jq .
]
}
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-2-incrementally-ingest-data-from-kafka-topic">Step 2: Incrementally ingest data from Kafka topic</h4>
@@ -481,7 +487,7 @@ pull changes and apply to Hudi dataset using upsert/insert primitives. Here, we
json data from kafka topic and ingest to both COW and MOR tables we initialized in the previous step. This tool
automatically initializes the datasets in the file-system if they do not exist yet.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
# Run the following spark-submit command to execute the delta-streamer and ingest to stock_ticks_cow dataset in HDFS
spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer $HUDI_UTILITIES_BUNDLE --storage-type COPY_ON_WRITE --source-class org.apache.hudi.utilities.sources.JsonKafkaSource --source-ordering-field ts --target-base-path /user/hive/warehouse/stock_ticks_cow --target-table stock_ticks_cow --props /var/demo/config/kafka-source.properties --schemaprovider-class org.apache.hudi.utilities.schema.FilebasedSchemaProvider
@@ -503,8 +509,7 @@ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer
# contain mostly Kafa connectivity settings, the avro-schema to be used for ingesting along with key and partitioning fields.
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>You can use HDFS web-browser to look at the datasets
<code class="highlighter-rouge">http://namenode:50070/explorer.html#/user/hive/warehouse/stock_ticks_cow</code>.</p>
@@ -520,7 +525,7 @@ file under .hoodie which signals a successful commit.</p>
<p>At this step, the datasets are available in HDFS. We need to sync with Hive to create new Hive tables and add partitions
inorder to run Hive queries against those datasets.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
# THis command takes in HIveServer URL and COW Hudi Dataset location in HDFS and sync the HDFS state to Hive
/var/hoodie/ws/hudi-hive/run_sync_tool.sh --jdbc-url jdbc:hive2://hiveserver:10000 --user hive --pass hive --partitioned-by dt --base-path /user/hive/warehouse/stock_ticks_cow --database default --table stock_ticks_cow
@@ -536,8 +541,7 @@ inorder to run Hive queries against those datasets.</p>
2018-09-24 22:23:09,559 INFO [main] hive.HiveSyncTool (HiveSyncTool.java:syncHoodieTable(112)) - Sync complete for stock_ticks_mor_rt
....
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>After executing the above command, you will notice</p>
<ol>
@@ -552,7 +556,7 @@ provides the ReadOptimized view for the Hudi dataset and the later provides the
(for both COW and MOR dataset)and realtime views (for MOR dataset)give the same value “10:29 a.m” as Hudi create a
parquet file for the first batch of data.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# List Tables
0: jdbc:hive2://hiveserver:10000> show tables;
@@ -648,14 +652,13 @@ WARNING: Hive-on-MR is deprecated in Hive 2 and may not be available in the futu
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-4-b-run-spark-sql-queries">Step 4 (b): Run Spark-SQL Queries</h4>
<p>Hudi support Spark as query processor just like Hive. Here are the same hive queries
running in spark-sql</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
$SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --master local[2] --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
...
@@ -746,15 +749,104 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
|20180924222155 |GOOG |2018-08-31 10:29:00|3391 |1230.1899|1230.085|
+-------------------+------+-------------------+------+---------+--------+
-</code></pre>
-</div>
+</code></pre></div></div>
+
+<h4 id="step-4-c-run-presto-queries">Step 4 (c): Run Presto Queries</h4>
+
+<p>Here are the Presto queries for similar Hive and Spark queries. Currently, Hudi does not support Presto queries on realtime views.</p>
+
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it presto-worker-1 presto --server presto-coordinator-1:8090
+presto> show catalogs;
+ Catalog
+-----------
+ hive
+ jmx
+ localfile
+ system
+(4 rows)
+
+Query 20190817_134851_00000_j8rcz, FINISHED, 1 node
+Splits: 19 total, 19 done (100.00%)
+0:04 [0 rows, 0B] [0 rows/s, 0B/s]
+
+presto> use hive.default;
+USE
+presto:default> show tables;
+ Table
+--------------------
+ stock_ticks_cow
+ stock_ticks_mor
+ stock_ticks_mor_rt
+(3 rows)
+
+Query 20190822_181000_00001_segyw, FINISHED, 2 nodes
+Splits: 19 total, 19 done (100.00%)
+0:05 [3 rows, 99B] [0 rows/s, 18B/s]
+
+
+# COPY-ON-WRITE Queries:
+=========================
+
+
+presto:default> select symbol, max(ts) from stock_ticks_cow group by symbol HAVING symbol = 'GOOG';
+ symbol | _col1
+--------+---------------------
+ GOOG | 2018-08-31 10:29:00
+(1 row)
+
+Query 20190822_181011_00002_segyw, FINISHED, 1 node
+Splits: 49 total, 49 done (100.00%)
+0:12 [197 rows, 613B] [16 rows/s, 50B/s]
+
+presto:default> select "_hoodie_commit_time", symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG';
+ _hoodie_commit_time | symbol | ts | volume | open | close
+---------------------+--------+---------------------+--------+-----------+----------
+ 20190822180221 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02
+ 20190822180221 | GOOG | 2018-08-31 10:29:00 | 3391 | 1230.1899 | 1230.085
+(2 rows)
+
+Query 20190822_181141_00003_segyw, FINISHED, 1 node
+Splits: 17 total, 17 done (100.00%)
+0:02 [197 rows, 613B] [109 rows/s, 341B/s]
+
+
+# Merge-On-Read Queries:
+==========================
+
+Lets run similar queries against M-O-R dataset.
+
+# Run against ReadOptimized View. Notice that the latest timestamp is 10:29
+presto:default> select symbol, max(ts) from stock_ticks_mor group by symbol HAVING symbol = 'GOOG';
+ symbol | _col1
+--------+---------------------
+ GOOG | 2018-08-31 10:29:00
+(1 row)
+
+Query 20190822_181158_00004_segyw, FINISHED, 1 node
+Splits: 49 total, 49 done (100.00%)
+0:02 [197 rows, 613B] [110 rows/s, 343B/s]
+
+
+presto:default> select "_hoodie_commit_time", symbol, ts, volume, open, close from stock_ticks_mor where symbol = 'GOOG';
+ _hoodie_commit_time | symbol | ts | volume | open | close
+---------------------+--------+---------------------+--------+-----------+----------
+ 20190822180250 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02
+ 20190822180250 | GOOG | 2018-08-31 10:29:00 | 3391 | 1230.1899 | 1230.085
+(2 rows)
+
+Query 20190822_181256_00006_segyw, FINISHED, 1 node
+Splits: 17 total, 17 done (100.00%)
+0:02 [197 rows, 613B] [92 rows/s, 286B/s]
+
+presto:default> exit
+</code></pre></div></div>
<h4 id="step-5-upload-second-batch-to-kafka-and-run-deltastreamer-to-ingest">Step 5: Upload second batch to Kafka and run DeltaStreamer to ingest</h4>
<p>Upload the second batch of data and ingest this batch using delta-streamer. As this batch does not bring in any new
partitions, there is no need to run hive-sync</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cat docker/demo/data/batch_2.json | kafkacat -b kafkabroker -t stock_ticks -P
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cat docker/demo/data/batch_2.json | kafkacat -b kafkabroker -t stock_ticks -P
# Within Docker container, run the ingestion command
docker exec -it adhoc-2 /bin/bash
@@ -767,8 +859,7 @@ spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer
spark-submit --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer $HUDI_UTILITIES_BUNDLE --storage-type MERGE_ON_READ --source-class org.apache.hudi.utilities.sources.JsonKafkaSource --source-ordering-field ts --target-base-path /user/hive/warehouse/stock_ticks_mor --target-table stock_ticks_mor --props /var/demo/config/kafka-source.properties --schemaprovider-class org.apache.hudi.utilities.schema.FilebasedSchemaProvider --disable-compaction
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<p>With Copy-On-Write table, the second ingestion by DeltaStreamer resulted in a new version of Parquet file getting created.
See <code class="highlighter-rouge">http://namenode:50070/explorer.html#/user/hive/warehouse/stock_ticks_cow/2018/08/31</code></p>
@@ -786,7 +877,7 @@ This is the time, when ReadOptimized and Realtime views will provide different r
return “10:29 am” as it will only read from the Parquet file. Realtime View will do on-the-fly merge and return
latest committed data which is “10:59 a.m”.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# Copy On Write Table:
@@ -850,14 +941,13 @@ WARNING: Hive-on-MR is deprecated in Hive 2 and may not be available in the futu
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-6b-run-spark-sql-queries">Step 6(b): Run Spark SQL Queries</h4>
<p>Running the same queries in Spark-SQL:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
# Copy On Write Table:
@@ -918,8 +1008,68 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
+
+<h4 id="step-6c-run-presto-queries">Step 6(c): Run Presto Queries</h4>
+
+<p>Running the same queries on Presto for ReadOptimized views.</p>
+
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it presto-worker-1 presto --server presto-coordinator-1:8090
+presto> use hive.default;
+USE
+
+# Copy On Write Table:
+
+presto:default>select symbol, max(ts) from stock_ticks_cow group by symbol HAVING symbol = 'GOOG';
+ symbol | _col1
+--------+---------------------
+ GOOG | 2018-08-31 10:59:00
+(1 row)
+
+Query 20190822_181530_00007_segyw, FINISHED, 1 node
+Splits: 49 total, 49 done (100.00%)
+0:02 [197 rows, 613B] [125 rows/s, 389B/s]
+
+presto:default>select "_hoodie_commit_time", symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG';
+ _hoodie_commit_time | symbol | ts | volume | open | close
+---------------------+--------+---------------------+--------+-----------+----------
+ 20190822180221 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02
+ 20190822181433 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215
+(2 rows)
+
+Query 20190822_181545_00008_segyw, FINISHED, 1 node
+Splits: 17 total, 17 done (100.00%)
+0:02 [197 rows, 613B] [106 rows/s, 332B/s]
+
+As you can notice, the above queries now reflect the changes that came as part of ingesting second batch.
+
+
+# Merge On Read Table:
+
+# Read Optimized View
+presto:default> select symbol, max(ts) from stock_ticks_mor group by symbol HAVING symbol = 'GOOG';
+ symbol | _col1
+--------+---------------------
+ GOOG | 2018-08-31 10:29:00
+(1 row)
+
+Query 20190822_181602_00009_segyw, FINISHED, 1 node
+Splits: 49 total, 49 done (100.00%)
+0:01 [197 rows, 613B] [139 rows/s, 435B/s]
+
+presto:default>select "_hoodie_commit_time", symbol, ts, volume, open, close from stock_ticks_mor where symbol = 'GOOG';
+ _hoodie_commit_time | symbol | ts | volume | open | close
+---------------------+--------+---------------------+--------+-----------+----------
+ 20190822180250 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02
+ 20190822180250 | GOOG | 2018-08-31 10:29:00 | 3391 | 1230.1899 | 1230.085
+(2 rows)
+
+Query 20190822_181615_00010_segyw, FINISHED, 1 node
+Splits: 17 total, 17 done (100.00%)
+0:01 [197 rows, 613B] [154 rows/s, 480B/s]
+
+presto:default> exit
+</code></pre></div></div>
<h4 id="step-7--incremental-query-for-copy-on-write-table">Step 7 : Incremental Query for COPY-ON-WRITE Table</h4>
@@ -927,7 +1077,7 @@ exit
<p>Lets take the same projection query example</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
0: jdbc:hive2://hiveserver:10000> select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG';
@@ -937,8 +1087,7 @@ beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache
| 20180924064621 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02 |
| 20180924065039 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
<p>As you notice from the above queries, there are 2 commits - 20180924064621 and 20180924065039 in timeline order.
When you follow the steps, you will be getting different timestamps for commits. Substitute them
@@ -951,20 +1100,19 @@ the commit time of the first batch (20180924064621) and run incremental query</p
<p>Hudi incremental mode provides efficient scanning for incremental queries by filtering out files that do not have any
candidate rows using hudi-managed metadata.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.mode=INCREMENTAL;
No rows affected (0.009 seconds)
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.max.commits=3;
No rows affected (0.009 seconds)
0: jdbc:hive2://hiveserver:10000> set hoodie.stock_ticks_cow.consume.start.timestamp=20180924064621;
-</code></pre>
-</div>
+</code></pre></div></div>
<p>With the above setting, file-ids that do not have any updates from the commit 20180924065039 is filtered out without scanning.
Here is the incremental query :</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>0: jdbc:hive2://hiveserver:10000>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>0: jdbc:hive2://hiveserver:10000>
0: jdbc:hive2://hiveserver:10000> select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG' and `_hoodie_commit_time` > '20180924064621';
+----------------------+---------+----------------------+---------+------------+-----------+--+
| _hoodie_commit_time | symbol | ts | volume | open | close |
@@ -973,11 +1121,10 @@ Here is the incremental query :</p>
+----------------------+---------+----------------------+---------+------------+-----------+--+
1 row selected (0.83 seconds)
0: jdbc:hive2://hiveserver:10000>
-</code></pre>
-</div>
+</code></pre></div></div>
<h5 id="incremental-query-with-spark-sql">Incremental Query with Spark SQL:</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
Welcome to
____ __
@@ -1010,15 +1157,14 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
| 20180924065039 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-8-schedule-and-run-compaction-for-merge-on-read-dataset">Step 8: Schedule and Run Compaction for Merge-On-Read dataset</h4>
<p>Lets schedule and run a compaction to create a new version of columnar file so that read-optimized readers will see fresher data.
Again, You can use Hudi CLI to manually schedule and run compaction</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
root@adhoc-1:/opt# /var/hoodie/ws/hudi-cli/hudi-cli.sh
============================================
* *
@@ -1101,8 +1247,7 @@ hoodie:stock_ticks->compactions show all
|==================================================================|
| 20180924070031 | COMPLETED| 1 |
-</code></pre>
-</div>
+</code></pre></div></div>
<h4 id="step-9-run-hive-queries-including-incremental-queries">Step 9: Run Hive Queries including incremental queries</h4>
@@ -1111,7 +1256,7 @@ Lets also run the incremental query for MOR table.
From looking at the below query output, it will be clear that the fist commit time for the MOR table is 20180924064636
and the second commit time is 20180924070031</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-2 /bin/bash
beeline -u jdbc:hive2://hiveserver:10000 --hiveconf hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat --hiveconf hive.stats.autogather=false
# Read Optimized View
@@ -1167,12 +1312,11 @@ No rows affected (0.013 seconds)
+----------------------+---------+----------------------+---------+------------+-----------+--+
exit
exit
-</code></pre>
-</div>
+</code></pre></div></div>
-<h5 id="read-optimized-and-realtime-views-for-mor-with-spark-sql-after-compaction">Read Optimized and Realtime Views for MOR with Spark-SQL after compaction</h5>
+<h5 id="step-10-read-optimized-and-realtime-views-for-mor-with-spark-sql-after-compaction">Step 10: Read Optimized and Realtime Views for MOR with Spark-SQL after compaction</h5>
-<div class="highlighter-rouge"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it adhoc-1 /bin/bash
bash-4.4# $SPARK_INSTALL/bin/spark-shell --jars $HUDI_SPARK_BUNDLE --driver-class-path $HADOOP_CONF_DIR --conf spark.sql.hive.convertMetastoreParquet=false --deploy-mode client --driver-memory 1G --master local[2] --executor-memory 3G --num-executors 1 --packages com.databricks:spark-avro_2.11:4.0.0
# Read Optimized View
@@ -1207,32 +1351,60 @@ scala> spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, clo
| 20180924064636 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02 |
| 20180924070031 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215 |
+----------------------+---------+----------------------+---------+------------+-----------+--+
-</code></pre>
-</div>
+</code></pre></div></div>
+
+<h5 id="step-11--presto-queries-over-read-optimized-view-on-mor-dataset-after-compaction">Step 11: Presto queries over Read Optimized View on MOR dataset after compaction</h5>
+
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>docker exec -it presto-worker-1 presto --server presto-coordinator-1:8090
+presto> use hive.default;
+USE
+
+# Read Optimized View
+resto:default> select symbol, max(ts) from stock_ticks_mor group by symbol HAVING symbol = 'GOOG';
+ symbol | _col1
+--------+---------------------
+ GOOG | 2018-08-31 10:59:00
+(1 row)
+
+Query 20190822_182319_00011_segyw, FINISHED, 1 node
+Splits: 49 total, 49 done (100.00%)
+0:01 [197 rows, 613B] [133 rows/s, 414B/s]
+
+presto:default> select "_hoodie_commit_time", symbol, ts, volume, open, close from stock_ticks_mor where symbol = 'GOOG';
+ _hoodie_commit_time | symbol | ts | volume | open | close
+---------------------+--------+---------------------+--------+-----------+----------
+ 20190822180250 | GOOG | 2018-08-31 09:59:00 | 6330 | 1230.5 | 1230.02
+ 20190822181944 | GOOG | 2018-08-31 10:59:00 | 9021 | 1227.1993 | 1227.215
+(2 rows)
+
+Query 20190822_182333_00012_segyw, FINISHED, 1 node
+Splits: 17 total, 17 done (100.00%)
+0:02 [197 rows, 613B] [98 rows/s, 307B/s]
+
+presto:default>
+
+</code></pre></div></div>
<p>This brings the demo to an end.</p>
<h2 id="testing-hudi-in-local-docker-environment">Testing Hudi in Local Docker environment</h2>
-<p>You can bring up a hadoop docker environment containing Hadoop, Hive and Spark services with support for hudi.
-<code class="highlighter-rouge">
-$ mvn pre-integration-test -DskipTests
-</code>
-The above command builds docker images for all the services with
+<p>You can bring up a hadoop docker environment containing Hadoop, Hive and Spark services with support for hudi.</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ mvn pre-integration-test -DskipTests
+</code></pre></div></div>
+<p>The above command builds docker images for all the services with
current Hudi source installed at /var/hoodie/ws and also brings up the services using a compose file. We
currently use Hadoop (v2.8.4), Hive (v2.3.3) and Spark (v2.3.1) in docker images.</p>
-<p>To bring down the containers
-<code class="highlighter-rouge">
-$ cd hudi-integ-test
+<p>To bring down the containers</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ cd hudi-integ-test
$ mvn docker-compose:down
-</code></p>
+</code></pre></div></div>
-<p>If you want to bring up the docker containers, use
-<code class="highlighter-rouge">
-$ cd hudi-integ-test
+<p>If you want to bring up the docker containers, use</p>
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>$ cd hudi-integ-test
$ mvn docker-compose:up -DdetachedMode=true
-</code></p>
+</code></pre></div></div>
<p>Hudi is a library that is operated in a broader data analytics/ingestion environment
involving Hadoop, Hive and Spark. Interoperability with all these systems is a key objective for us. We are
@@ -1258,7 +1430,7 @@ run the script
<p>Here are the commands:</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>cd docker
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>cd docker
./build_local_docker_images.sh
.....
@@ -1293,8 +1465,7 @@ run the script
[INFO] Finished at: 2018-09-10T17:47:37-07:00
[INFO] Final Memory: 236M/1848M
[INFO] ------------------------------------------------------------------------
-</code></pre>
-</div>
+</code></pre></div></div>
<div class="tags">
@@ -1323,7 +1494,7 @@ run the script
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/404.html b/content/events/2016-12-30-strata-talk-2017.html
similarity index 87%
copy from content/404.html
copy to content/events/2016-12-30-strata-talk-2017.html
index acf9628..ba7908a 100644
--- a/content/404.html
+++ b/content/events/2016-12-30-strata-talk-2017.html
@@ -5,26 +5,26 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="">
<meta name="keywords" content="">
-<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<title>Connect with us at Strata San Jose March 2017 | Hudi</title>
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -162,11 +164,17 @@
- <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Page Not Found page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
+ <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Connect with us at Strata San Jose March 2017 page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/events/2016-12-30-strata-talk-2017.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,13 +182,13 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
- searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
+ dataSource: '/search.json',
+ searchResultTemplate: '<li><a href="{url}" title="Connect with us at Strata San Jose March 2017">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
fuzzy: true,
@@ -317,7 +325,7 @@
<!-- Content Column -->
<div class="col-md-9">
<div class="post-header">
- <h1 class="post-title-main">Page Not Found</h1>
+ <h1 class="post-title-main">Connect with us at Strata San Jose March 2017</h1>
</div>
@@ -354,11 +362,21 @@ $('#toc').on('click', 'a', function() {
- <p>Sorry, but the page you were trying to view does not exist. Try searching for it or looking at the URL to see if it looks correct.</p>
+ <p>We will be presenting Hudi & general concepts around how incremental processing works at Uber.
+Catch our talk <strong>“Incremental Processing on Hadoop At Uber”</strong></p>
+
<div class="tags">
+ <b>Tags: </b>
+
+
+
+ <a href="tag_news.html" class="btn btn-default navbar-btn cursorNorm" role="button">news</a>
+
+
+
</div>
@@ -375,7 +393,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/404.html b/content/events/2019-01-18-asf-incubation.html
similarity index 88%
copy from content/404.html
copy to content/events/2019-01-18-asf-incubation.html
index acf9628..16d2203 100644
--- a/content/404.html
+++ b/content/events/2019-01-18-asf-incubation.html
@@ -5,26 +5,26 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="">
<meta name="keywords" content="">
-<title>Page Not Found | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<title>Hudi entered Apache Incubator | Hudi</title>
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -162,11 +164,17 @@
- <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Page Not Found page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
+ <a class="email" title="Submit feedback" href="#" onclick="javascript:window.location='mailto:dev@hudi.apache.org?subject=Hudi Documentation feedback&body=I have some feedback about the Hudi entered Apache Incubator page: ' + window.location.href;"><i class="fa fa-envelope-o"></i> Feedback</a>
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/events/2019-01-18-asf-incubation.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,13 +182,13 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
- searchResultTemplate: '<li><a href="{url}" title="Page Not Found">{title}</a></li>',
+ dataSource: '/search.json',
+ searchResultTemplate: '<li><a href="{url}" title="Hudi entered Apache Incubator">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
fuzzy: true,
@@ -317,7 +325,7 @@
<!-- Content Column -->
<div class="col-md-9">
<div class="post-header">
- <h1 class="post-title-main">Page Not Found</h1>
+ <h1 class="post-title-main">Hudi entered Apache Incubator</h1>
</div>
@@ -354,11 +362,20 @@ $('#toc').on('click', 'a', function() {
- <p>Sorry, but the page you were trying to view does not exist. Try searching for it or looking at the URL to see if it looks correct.</p>
+ <p>In the coming weeks, we will be moving in our new home on the Apache Incubator.</p>
+
<div class="tags">
+ <b>Tags: </b>
+
+
+
+ <a href="tag_news.html" class="btn btn-default navbar-btn cursorNorm" role="button">news</a>
+
+
+
</div>
@@ -375,7 +392,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/feed.xml b/content/feed.xml
index 3ff5547..ec6ded0 100644
--- a/content/feed.xml
+++ b/content/feed.xml
@@ -3,40 +3,11 @@
<channel>
<title></title>
<description>Apache Hudi (pronounced “Hoodie”) provides upserts and incremental processing capaibilities on Big Data</description>
- <link>http://localhost:4000/</link>
- <atom:link href="http://localhost:4000/feed.xml" rel="self" type="application/rss+xml"/>
- <pubDate>Sun, 11 Aug 2019 17:25:16 -0700</pubDate>
- <lastBuildDate>Sun, 11 Aug 2019 17:25:16 -0700</lastBuildDate>
- <generator>Jekyll v3.3.1</generator>
-
- <item>
- <title>Hudi entered Apache Incubator</title>
- <description><p>In the coming weeks, we will be moving in our new home on the Apache Incubator.</p>
-
-</description>
- <pubDate>Fri, 18 Jan 2019 00:00:00 -0800</pubDate>
- <link>http://localhost:4000/strata-talk.html</link>
- <guid isPermaLink="true">http://localhost:4000/strata-talk.html</guid>
-
- <category>news</category>
-
-
- </item>
-
- <item>
- <title>Connect with us at Strata San Jose March 2017</title>
- <description><p>We will be presenting Hudi &amp; general concepts around how incremental processing works at Uber.
-Catch our talk <strong>“Incremental Processing on Hadoop At Uber”</strong></p>
-
-</description>
- <pubDate>Fri, 30 Dec 2016 00:00:00 -0800</pubDate>
- <link>http://localhost:4000/strata-talk.html</link>
- <guid isPermaLink="true">http://localhost:4000/strata-talk.html</guid>
-
- <category>news</category>
-
-
- </item>
+ <link>http://0.0.0.0:4000/</link>
+ <atom:link href="http://0.0.0.0:4000/feed.xml" rel="self" type="application/rss+xml"/>
+ <pubDate>Mon, 16 Sep 2019 19:19:14 +0000</pubDate>
+ <lastBuildDate>Mon, 16 Sep 2019 19:19:14 +0000</lastBuildDate>
+ <generator>Jekyll v3.7.2</generator>
</channel>
</rss>
diff --git a/content/gcs_hoodie.html b/content/gcs_hoodie.html
index 0902ab1..79aace2 100644
--- a/content/gcs_hoodie.html
+++ b/content/gcs_hoodie.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we go over how to configure hudi with Google Cloud Storage.">
<meta name="keywords" content="hudi, hive, google cloud, storage, spark, presto">
<title>GCS Filesystem | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/gcs_hoodie.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="GCS Filesystem">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -348,7 +356,7 @@
<p>Add the required configs in your core-site.xml from where Hudi can fetch them. Replace the <code class="highlighter-rouge">fs.defaultFS</code> with your GCS bucket name and Hudi should be able to read/write from the bucket.</p>
-<div class="language-xml highlighter-rouge"><pre class="highlight"><code> <span class="nt"><property></span>
+<div class="language-xml highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="nt"><property></span>
<span class="nt"><name></span>fs.defaultFS<span class="nt"></name></span>
<span class="nt"><value></span>gs://hudi-bucket<span class="nt"></value></span>
<span class="nt"></property></span>
@@ -381,8 +389,7 @@
<span class="nt"><name></span>google.cloud.auth.service.account.keyfile<span class="nt"></name></span>
<span class="nt"><value></span>GCS_SERVICE_ACCOUNT_KEYFILE<span class="nt"></value></span>
<span class="nt"></property></span>
-</code></pre>
-</div>
+</code></pre></div></div>
<h3 id="gcs-libs">GCS Libs</h3>
@@ -411,7 +418,7 @@
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/index.html b/content/index.html
index bf041bc..d99d670 100644
--- a/content/index.html
+++ b/content/index.html
@@ -6,25 +6,25 @@
<meta name="description" content="Hudi brings stream processing to big data, providing fresh data while being an order of magnitude efficient over traditional batch processing.">
<meta name="keywords" content="big data, stream processing, cloud, hdfs, storage, upserts, change capture">
<title>What is Hudi? | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/index.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="What is Hudi?">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -364,7 +372,9 @@ $('#toc').on('click', 'a', function() {
<li><strong>Near-Real time Table</strong> - Provides queries on real-time data, using a combination of columnar & row based storage (e.g Parquet + <a href="http://avro.apache.org/docs/current/mr.html">Avro</a>)</li>
</ul>
-<figure><img class="docimage" src="images/hudi_intro_1.png" alt="hudi_intro_1.png" /></figure>
+<figure>
+ <img class="docimage" src="/images/hudi_intro_1.png" alt="hudi_intro_1.png" />
+</figure>
<p>By carefully managing how data is laid out in storage & how it’s exposed to queries, Hudi is able to power a rich data ecosystem where external sources can be ingested in near real-time and made available for interactive SQL Engines like <a href="https://prestodb.io">Presto</a> & <a href="https://spark.apache.org/sql/">Spark</a>, while at the same time capable of being consumed incrementally from processing/ETL frameworks like <a href="https://hive.apache.org/">Hive</a> & [...]
@@ -397,7 +407,7 @@ $('#toc').on('click', 'a', function() {
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/js/mydoc_scroll.html b/content/js/mydoc_scroll.html
index e5a1578..576c693 100644
--- a/content/js/mydoc_scroll.html
+++ b/content/js/mydoc_scroll.html
@@ -6,25 +6,25 @@
<meta name="description" content="This page demonstrates how you the integration of a script called ScrollTo, which is used here to link definitions of a JSON code sample to a list of definit...">
<meta name="keywords" content="json, scrolling, scrollto, jquery plugin">
<title>Scroll layout | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/js/mydoc_scroll.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Scroll layout">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -611,7 +619,7 @@ $('#small-box-links').localScroll({
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/migration_guide.html b/content/migration_guide.html
index 7cb85db..3749f1e 100644
--- a/content/migration_guide.html
+++ b/content/migration_guide.html
@@ -6,25 +6,25 @@
<meta name="description" content="In this page, we will discuss some available tools for migrating your existing dataset into a Hudi dataset">
<meta name="keywords" content="hudi, migration, use case">
<title>Migration Guide | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/migration_guide.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="Migration Guide">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -374,7 +382,7 @@ This tool essentially starts a Spark Job to read the existing parquet dataset an
<p>Write your own custom logic of how to load an existing dataset into a Hudi managed one. Please read about the RDD API
<a href="quickstart.html">here</a>.</p>
-<div class="highlighter-rouge"><pre class="highlight"><code>Using the HDFSParquetImporter Tool. Once hudi has been built via `mvn clean install -DskipTests`, the shell can be
+<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Using the HDFSParquetImporter Tool. Once hudi has been built via `mvn clean install -DskipTests`, the shell can be
fired by via `cd hudi-cli && ./hudi-cli.sh`.
hudi->hdfsparquetimport
@@ -391,8 +399,7 @@ hudi->hdfsparquetimport
--format parquet
--sparkMemory 6g
--retry 2
-</code></pre>
-</div>
+</code></pre></div></div>
<div class="tags">
@@ -413,7 +420,7 @@ hudi->hdfsparquetimport
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/news.html b/content/news.html
index fcdc17f..767dde1 100644
--- a/content/news.html
+++ b/content/news.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="apache, hudi, news, blog, updates, release notes, announcements">
<title>News | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li class="active"><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/news.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
SimpleJekyllSearch.init({
searchInput: document.getElementById('search-input'),
resultsContainer: document.getElementById('results-container'),
- dataSource: 'search.json',
+ dataSource: '/search.json',
searchResultTemplate: '<li><a href="{url}" title="News">{title}</a></li>',
noResultsText: 'No results found.',
limit: 10,
@@ -245,45 +253,76 @@
<div class="home">
- <div class="post-list">
+ <div class="post-list">
+
+
-
-
- <h2><a class="post-link" href="strata-talk.html">Hudi entered Apache Incubator</a></h2>
- <span class="post-meta">Jan 18, 2019 /
+
+
+
+
+
+
+ <h2><a class="post-link" href="/events/2016-12-30-strata-talk-2017.html">Connect with us at Strata San Jose March 2017</a></h2>
+ <span class="post-meta">Dec 30, 2016 /
<a href="tag_news.html">news</a>
</span>
- <p> In the coming weeks, we will be moving in our new home on the Apache Incubator.
+ <p> We will be presenting Hudi & general concepts around how incremental processing works at Uber.
+Catch our talk “Incremental Processing on Hadoop At Uber”
</p>
+
-
-
- <h2><a class="post-link" href="strata-talk.html">Connect with us at Strata San Jose March 2017</a></h2>
- <span class="post-meta">Dec 30, 2016 /
+
+
+
+
+
+
+ <h2><a class="post-link" href="/events/2019-01-18-asf-incubation.html">Hudi entered Apache Incubator</a></h2>
+ <span class="post-meta">Jan 18, 2019 /
<a href="tag_news.html">news</a>
</span>
- <p> We will be presenting Hudi & general concepts around how incremental processing works at Uber.
-Catch our talk “Incremental Processing on Hadoop At Uber”
+ <p> In the coming weeks, we will be moving in our new home on the Apache Incubator.
</p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
- <p><a href="feed.xml"" class="btn btn-primary navbar-btn cursorNorm" role="button">RSS Subscribe</a></p>
+ <p><a href="feed.xml" class="btn btn-primary navbar-btn cursorNorm" role="button">RSS Subscribe</a></p>
<hr />
<p>See more posts from the <a href="news_archive.html">News Archive</a>. </p>
</div>
+</div>
<div class="tags">
@@ -304,7 +343,7 @@ Catch our talk “Incremental Processing on Hadoop At Uber”
Licensed under the Apache License, Version 2.0<br>
Apache and the Apache feather logo are trademarks of The Apache Software Foundation.| <a href="/privacy">Privacy Policy</a><br>
<a class="footer-link-img" href="https://apache.org">
- <img src="images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
+ <img src="/images/asf_logo.svg" alt="The Apache Software Foundation" height="100px" widh="50px"></a>
</p>
<p>
Apache Hudi is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the <a href="http://incubator.apache.org/">Apache Incubator</a>.
diff --git a/content/news_archive.html b/content/news_archive.html
index 4d74956..9099217 100644
--- a/content/news_archive.html
+++ b/content/news_archive.html
@@ -6,25 +6,25 @@
<meta name="description" content="">
<meta name="keywords" content="news, blog, updates, release notes, announcements">
<title>News | Hudi</title>
-<link rel="stylesheet" href="css/syntax.css">
+<link rel="stylesheet" href="/css/syntax.css">
<link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
<!--<link rel="stylesheet" type="text/css" href="css/bootstrap.min.css">-->
-<link rel="stylesheet" href="css/modern-business.css">
-<link rel="stylesheet" href="css/lavish-bootstrap.css">
-<link rel="stylesheet" href="css/customstyles.css">
-<link rel="stylesheet" href="css/theme-blue.css">
+<link rel="stylesheet" href="/css/modern-business.css">
+<link rel="stylesheet" href="/css/lavish-bootstrap.css">
+<link rel="stylesheet" href="/css/customstyles.css">
+<link rel="stylesheet" href="/css/theme-blue.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script>
-<script src="js/jquery.navgoco.min.js"></script>
+<script src="/js/jquery.navgoco.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/2.0.0/anchor.min.js"></script>
-<script src="js/toc.js"></script>
-<script src="js/customscripts.js"></script>
+<script src="/js/toc.js"></script>
+<script src="/js/customscripts.js"></script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
@@ -37,7 +37,7 @@
</script>
-<link rel="shortcut icon" href="images/favicon.ico">
+<link rel="shortcut icon" href="/images/favicon.ico">
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
@@ -46,7 +46,7 @@
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
-<link rel="alternate" type="application/rss+xml" title="" href="http://localhost:4000feed.xml">
+<link rel="alternate" type="application/rss+xml" title="" href="http://0.0.0.0:4000feed.xml">
<script>
$(document).ready(function() {
@@ -111,6 +111,8 @@
<ul class="nav navbar-nav navbar-right">
<!-- entries without drop-downs appear here -->
+
+
<li class="active"><a href="news">News</a></li>
@@ -167,6 +169,12 @@
<li>
+ <li>
+
+ <!-- link to the Chinese home page when current is blog page -->
+ <a href="/cn/news_archive.html">中文版</a>
+
+ </li>
<!--comment out this block if you want to hide search-->
<li>
<!--start search-->
@@ -174,12 +182,12 @@
<input type="text" id="search-input" placeholder="search...">
<ul id="results-container"></ul>
</div>
- <script src="js/jekyll-search.js" type="text/javascript"></script>
+ <script src="/js/jekyll-search.js" type="text/javascript"></script>
<script type="text/javascript">
... 1833 lines suppressed ...