From 78dca9ef0a9765154ecce67597c35e59ede8a50f Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 18:10:06 -0700 Subject: [PATCH 01/24] Add toc.js for auto generating TOC --- docs/_includes/themes/zeppelin/default.html | 1 + docs/assets/themes/zeppelin/js/docs.js | 4 + docs/assets/themes/zeppelin/js/toc.js | 98 +++++++++++++++++++++ 3 files changed, 103 insertions(+) create mode 100755 docs/assets/themes/zeppelin/js/toc.js diff --git a/docs/_includes/themes/zeppelin/default.html b/docs/_includes/themes/zeppelin/default.html index eb99b9bd0fd..cd07602ec90 100644 --- a/docs/_includes/themes/zeppelin/default.html +++ b/docs/_includes/themes/zeppelin/default.html @@ -33,6 +33,7 @@ + diff --git a/docs/assets/themes/zeppelin/js/docs.js b/docs/assets/themes/zeppelin/js/docs.js index 1d2d002344c..343f6e85d57 100644 --- a/docs/assets/themes/zeppelin/js/docs.js +++ b/docs/assets/themes/zeppelin/js/docs.js @@ -118,6 +118,10 @@ $(function() { maybeScrollToHash(); }); + $(document).ready(function() { + $('#toc').toc(); + }); + // Scroll now too in case we had opened the page on a hash, but wait a bit because some browsers // will try to do *their* initial scroll after running the onReady handler. $(window).load(function() { setTimeout(function() { maybeScrollToHash(); }, 25); }); diff --git a/docs/assets/themes/zeppelin/js/toc.js b/docs/assets/themes/zeppelin/js/toc.js new file mode 100755 index 00000000000..9fb6b562323 --- /dev/null +++ b/docs/assets/themes/zeppelin/js/toc.js @@ -0,0 +1,98 @@ +// https://github.com/ghiculescu/jekyll-table-of-contents +(function($){ + $.fn.toc = function(options) { + var defaults = { + noBackToTopLinks: false, + title: 'Jump to...', + minimumHeaders: 3, + headers: 'h1, h2, h3, h4, h5, h6', + listType: 'ol', // values: [ol|ul] + showEffect: 'show', // values: [show|slideDown|fadeIn|none] + showSpeed: 'slow', // set to 0 to deactivate effect + classes: { list: '', + item: '' + } + }, + settings = $.extend(defaults, options); + + function fixedEncodeURIComponent (str) { + return encodeURIComponent(str).replace(/[!'()*]/g, function(c) { + return '%' + c.charCodeAt(0).toString(16); + }); + } + + function createLink (header) { + var innerText = (header.textContent === undefined) ? header.innerText : header.textContent; + return "" + innerText + ""; + } + + var headers = $(settings.headers).filter(function() { + // get all headers with an ID + var previousSiblingName = $(this).prev().attr( "name" ); + if (!this.id && previousSiblingName) { + this.id = $(this).attr( "id", previousSiblingName.replace(/\./g, "-") ); + } + return this.id; + }), output = $(this); + if (!headers.length || headers.length < settings.minimumHeaders || !output.length) { + $(this).hide(); + return; + } + + if (0 === settings.showSpeed) { + settings.showEffect = 'none'; + } + + var render = { + show: function() { output.hide().html(html).show(settings.showSpeed); }, + slideDown: function() { output.hide().html(html).slideDown(settings.showSpeed); }, + fadeIn: function() { output.hide().html(html).fadeIn(settings.showSpeed); }, + none: function() { output.html(html); } + }; + + var get_level = function(ele) { return parseInt(ele.nodeName.replace("H", ""), 10); }; + var highest_level = headers.map(function(_, ele) { return get_level(ele); }).get().sort()[0]; + var return_to_top = ' '; + + var level = get_level(headers[0]), + this_level, + html = settings.title + " <" +settings.listType + " class=\"" + settings.classes.list +"\">"; + headers.on('click', function() { + if (!settings.noBackToTopLinks) { + window.location.hash = this.id; + } + }) + .addClass('clickable-header') + .each(function(_, header) { + this_level = get_level(header); + if (!settings.noBackToTopLinks && this_level === highest_level) { + $(header).addClass('top-level-header').after(return_to_top); + } + if (this_level === level) // same level as before; same indenting + html += "
  • " + createLink(header); + else if (this_level <= level){ // higher level than before; end parent ol + for(i = this_level; i < level; i++) { + html += "
    • " + } + html += "
  • " + createLink(header); + } + else if (this_level > level) { // lower level than before; expand the previous to contain a ol + for(i = this_level; i > level; i--) { + html += "<" + settings.listType + " class=\"" + settings.classes.list +"\">" + + "
  • " + } + html += createLink(header); + } + level = this_level; // update for the next one + }); + html += ""; + if (!settings.noBackToTopLinks) { + $(document).on('click', '.back-to-top', function() { + $(window).scrollTop(0); + window.location.hash = ''; + }); + } + + render[settings.showEffect](); + }; +})(jQuery); From 1f10b97945cbe4373843003ad311e780a3e2dd14 Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 19:40:17 -0700 Subject: [PATCH 02/24] Change toc configuration --- docs/assets/themes/zeppelin/js/toc.js | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/assets/themes/zeppelin/js/toc.js b/docs/assets/themes/zeppelin/js/toc.js index 9fb6b562323..8977fff2137 100755 --- a/docs/assets/themes/zeppelin/js/toc.js +++ b/docs/assets/themes/zeppelin/js/toc.js @@ -3,12 +3,12 @@ $.fn.toc = function(options) { var defaults = { noBackToTopLinks: false, - title: 'Jump to...', - minimumHeaders: 3, - headers: 'h1, h2, h3, h4, h5, h6', - listType: 'ol', // values: [ol|ul] - showEffect: 'show', // values: [show|slideDown|fadeIn|none] - showSpeed: 'slow', // set to 0 to deactivate effect + title: '', + minimumHeaders: 2, + headers: 'h2, h3', + listType: 'ul', // values: [ol|ul] + showEffect: 'none', // values: [show|slideDown|fadeIn|none] + showSpeed: '0', // set to 0 to deactivate effect classes: { list: '', item: '' } From 587d4baea064de393b05266093967f6b9657318b Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 19:41:49 -0700 Subject: [PATCH 03/24] Apply auto TOC to all of docs under docs/security/ --- docs/security/authentication.md | 15 +++++++------ docs/security/interpreter_authorization.md | 2 ++ docs/security/notebook_authorization.md | 7 ++++-- docs/security/shiroauthentication.md | 26 ++++++++++++---------- 4 files changed, 29 insertions(+), 21 deletions(-) diff --git a/docs/security/authentication.md b/docs/security/authentication.md index e7a793d542f..7ce160aa2b5 100644 --- a/docs/security/authentication.md +++ b/docs/security/authentication.md @@ -19,11 +19,12 @@ limitations under the License. --> # Authentication for NGINX -Authentication is company-specific. +
    -One option is to use [Basic Access Authentication](https://en.wikipedia.org/wiki/Basic_access_authentication) +Authentication is company-specific. +One option is to use [Basic Access Authentication](https://en.wikipedia.org/wiki/Basic_access_authentication). -### HTTP Basic Authentication using NGINX +## HTTP Basic Authentication using NGINX > **Quote from Wikipedia:** NGINX is a web server. It can act as a reverse proxy server for HTTP, HTTPS, SMTP, POP3, and IMAP protocols, as well as a load balancer and an HTTP cache. @@ -39,7 +40,7 @@ This instruction based on Ubuntu 14.04 LTS but may work with other OS with few c ``` $ apt-get install nginx ``` - *Important: On pre 1.3.13 version of NGINX, Proxy for Websocket may not fully works. Please use latest version of NGINX. See: [NGINX documentation](https://www.nginx.com/blog/websocket-nginx/)* + > **NOTE :** On pre 1.3.13 version of NGINX, Proxy for Websocket may not fully works. Please use latest version of NGINX. See: [NGINX documentation](https://www.nginx.com/blog/websocket-nginx/). 1. Setup init script in NGINX @@ -119,12 +120,12 @@ This instruction based on Ubuntu 14.04 LTS but may work with other OS with few c 1. More security consideration * Using HTTPS connection with Basic Authentication is highly recommended since basic auth without encryption may expose your important credential information over the network. -* Using [Shiro Security feature built-into Zeppelin](https://github.com/apache/zeppelin/blob/master/SECURITY-README.md) is recommended if you prefer all-in-one solution for authentication but NGINX may provides ad-hoc solution for re-use authentication served by your system's NGINX server or in case of you need to separate authentication from zeppelin server. +* Using [Shiro Security feature built-into Zeppelin](./shiroauthentication.html) is recommended if you prefer all-in-one solution for authentication but NGINX may provides ad-hoc solution for re-use authentication served by your system's NGINX server or in case of you need to separate authentication from zeppelin server. * It is recommended to isolate direct connection to Zeppelin server from public internet or external services to secure your zeppelin instance from unexpected attack or problems caused by public zone. -### Another option +## Another option Another option is to have an authentication server that can verify user credentials in an LDAP server. If an incoming request to the Zeppelin server does not have a cookie with user information encrypted with the authentication server public key, the user is redirected to the authentication server. Once the user is verified, the authentication server redirects the browser to a specific URL in the Zeppelin server which sets the authentication cookie in the browser. -The end result is that all requests to the Zeppelin web server have the authentication cookie which contains user and groups information. +The end result is that all requests to the Zeppelin web server have the authentication cookie which contains user and groups information. \ No newline at end of file diff --git a/docs/security/interpreter_authorization.md b/docs/security/interpreter_authorization.md index 3809cd4bd6c..6e59e0718a9 100644 --- a/docs/security/interpreter_authorization.md +++ b/docs/security/interpreter_authorization.md @@ -19,6 +19,8 @@ limitations under the License. --> # Interpreter and Data Source Authorization +
    + ## Interpreter Authorization Interpreter authorization involves permissions like creating an interpreter and execution queries using it. diff --git a/docs/security/notebook_authorization.md b/docs/security/notebook_authorization.md index 7793d4f2235..87885676ef3 100644 --- a/docs/security/notebook_authorization.md +++ b/docs/security/notebook_authorization.md @@ -19,6 +19,9 @@ limitations under the License. --> # Zeppelin Notebook Authorization +
    + +## Overview We assume that there is an **Shiro Authentication** component that associates a user string and a set of group strings with every NotebookSocket. If you don't set the authentication components yet, please check [Shiro authentication for Apache Zeppelin](./shiroauthentication.html) first. @@ -44,12 +47,12 @@ If someone who doesn't have **read** permission is trying to access the notebook ## How it works In this section, we will explain the detail about how the notebook authorization works in backend side. -#### NotebookServer +### NotebookServer The [NotebookServer](https://github.com/apache/zeppelin/blob/master/zeppelin-server/src/main/java/org/apache/zeppelin/socket/NotebookServer.java) classifies every notebook operations into three categories: **Read**, **Write**, **Manage**. Before executing a notebook operation, it checks if the user and the groups associated with the `NotebookSocket` have permissions. For example, before executing a **Read** operation, it checks if the user and the groups have at least one entity that belongs to the **Reader** entities. -#### Notebook REST API call +### Notebook REST API call Zeppelin executes a [REST API call](https://github.com/apache/zeppelin/blob/master/zeppelin-server/src/main/java/org/apache/zeppelin/rest/NotebookRestApi.java) for the notebook permission information. In the backend side, Zeppelin gets the user information for the connection and allows the operation if the users and groups associated with the current user have at least one entity that belongs to owner entities for the notebook. diff --git a/docs/security/shiroauthentication.md b/docs/security/shiroauthentication.md index 969e2f44aaf..733ff11b673 100644 --- a/docs/security/shiroauthentication.md +++ b/docs/security/shiroauthentication.md @@ -20,6 +20,10 @@ limitations under the License. {% include JB/setup %} # Shiro authentication for Apache Zeppelin + +
    + +## Overview [Apache Shiro](http://shiro.apache.org/) is a powerful and easy-to-use Java security framework that performs authentication, authorization, cryptography, and session management. In this documentation, we will explain step by step how Shiro works for Zeppelin notebook authentication. When you connect to Apache Zeppelin, you will be asked to enter your credentials. Once you logged in, then you have access to all notes including other user's notes. @@ -27,28 +31,28 @@ When you connect to Apache Zeppelin, you will be asked to enter your credentials ## Security Setup You can setup **Zeppelin notebook authentication** in some simple steps. -####1. Secure the HTTP channel -To secure the HTTP channel, you have to change both **anon** and **authcBasic** settings in `conf/shiro.ini`. In here, **anon** means "the access is anonymous" and **authcBasic** means "basic auth security". +### 1. Secure the HTTP channel +To secure the HTTP channel, you have to change both **anon** and **authc** settings in `conf/shiro.ini`. In here, **anon** means "the access is anonymous" and **authc** means "formed auth security". The default status of them is ``` /** = anon -#/** = authcBasic +#/** = authc ``` -Deactivate the line "/** = anon" and activate the line "/** = authcBasic" in `conf/shiro.ini` file. +Deactivate the line "/** = anon" and activate the line "/** = authc" in `conf/shiro.ini` file. ``` #/** = anon -/** = authcBasic +/** = authc ``` For the further information about `shiro.ini` file format, please refer to [Shiro Configuration](http://shiro.apache.org/configuration.html#Configuration-INISections). -####2. Secure the Websocket channel +### 2. Secure the Websocket channel Set to property **zeppelin.anonymous.allowed** to **false** in `conf/zeppelin-site.xml`. If you don't have this file yet, just copy `conf/zeppelin-site.xml.template` to `conf/zeppelin-site.xml`. -####3. Start Zeppelin +### 3. Start Zeppelin ``` bin/zeppelin-daemon.sh start (or restart) @@ -56,7 +60,7 @@ bin/zeppelin-daemon.sh start (or restart) Then you can browse Zeppelin at [http://localhost:8080](http://localhost:8080). -####4. Login +### 4. Login Finally, you can login using one of the below **username/password** combinations.
    @@ -67,10 +71,8 @@ user1 = password2 user2 = password3 ``` -Those combinations are defined in the `conf/shiro.ini` file. - -####5. Groups and permissions (optional) -In case you want to leverage user groups and permissions, use one of the following configuration for LDAP or AD under `[main]` segment of shiro.ini +### 5. Groups and permissions (optional) +In case you want to leverage user groups and permissions, use one of the following configuration for LDAP or AD under `[main]` segment in `shiro.ini` ``` activeDirectoryRealm = org.apache.zeppelin.server.ActiveDirectoryGroupRealm From 9c5f76bbb1302c8d093c4da9044aa39eb5b93224 Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 19:42:17 -0700 Subject: [PATCH 04/24] Apply auto TOC to all of docs under docs/interpreter/ --- docs/interpreter/alluxio.md | 6 +++- docs/interpreter/cassandra.md | 4 ++- docs/interpreter/elasticsearch.md | 6 +++- docs/interpreter/flink.md | 6 +++- docs/interpreter/geode.md | 30 +++++++++------- docs/interpreter/hbase.md | 12 +++++-- docs/interpreter/hdfs.md | 13 +++++-- docs/interpreter/hive.md | 10 ++++-- docs/interpreter/ignite.md | 14 ++++---- docs/interpreter/jdbc.md | 57 ++++++++++++++++++------------- docs/interpreter/lens.md | 12 ++++--- docs/interpreter/livy.md | 21 ++++++------ docs/interpreter/markdown.md | 8 +++-- docs/interpreter/postgresql.md | 46 +++++++++++++------------ docs/interpreter/python.md | 9 +++-- docs/interpreter/scalding.md | 19 ++++++----- docs/interpreter/spark.md | 22 +++++++----- 17 files changed, 179 insertions(+), 116 deletions(-) diff --git a/docs/interpreter/alluxio.md b/docs/interpreter/alluxio.md index 332dd0d24b2..c8ecf93d281 100644 --- a/docs/interpreter/alluxio.md +++ b/docs/interpreter/alluxio.md @@ -6,7 +6,11 @@ group: manual --- {% include JB/setup %} -## Alluxio Interpreter for Apache Zeppelin +# Alluxio Interpreter for Apache Zeppelin + +
    + +## Overview [Alluxio](http://alluxio.org/) is a memory-centric distributed storage system enabling reliable data sharing at memory-speed across cluster frameworks. ## Configuration diff --git a/docs/interpreter/cassandra.md b/docs/interpreter/cassandra.md index 2091666761c..33cff199b05 100644 --- a/docs/interpreter/cassandra.md +++ b/docs/interpreter/cassandra.md @@ -6,7 +6,9 @@ group: manual --- {% include JB/setup %} -## Cassandra CQL Interpreter for Apache Zeppelin +# Cassandra CQL Interpreter for Apache Zeppelin + +
    diff --git a/docs/interpreter/elasticsearch.md b/docs/interpreter/elasticsearch.md index 70af3c09846..4721bcda3f2 100644 --- a/docs/interpreter/elasticsearch.md +++ b/docs/interpreter/elasticsearch.md @@ -6,7 +6,11 @@ group: manual --- {% include JB/setup %} -## Elasticsearch Interpreter for Apache Zeppelin +# Elasticsearch Interpreter for Apache Zeppelin + +
    + +## Overview [Elasticsearch](https://www.elastic.co/products/elasticsearch) is a highly scalable open-source full-text search and analytics engine. It allows you to store, search, and analyze big volumes of data quickly and in near real time. It is generally used as the underlying engine/technology that powers applications that have complex search features and requirements. ## Configuration diff --git a/docs/interpreter/flink.md b/docs/interpreter/flink.md index 9d2f0b05a9f..a678480b59f 100644 --- a/docs/interpreter/flink.md +++ b/docs/interpreter/flink.md @@ -6,7 +6,11 @@ group: manual --- {% include JB/setup %} -## Flink interpreter for Apache Zeppelin +# Flink interpreter for Apache Zeppelin + +
    + +## Overview [Apache Flink](https://flink.apache.org) is an open source platform for distributed stream and batch data processing. Flink’s core is a streaming dataflow engine that provides data distribution, communication, and fault tolerance for distributed computations over data streams. Flink also builds batch processing on top of the streaming engine, overlaying native iteration support, managed memory, and program optimization. ## How to start local Flink cluster, to test the interpreter diff --git a/docs/interpreter/geode.md b/docs/interpreter/geode.md index 53a912e3ac6..84a026efff5 100644 --- a/docs/interpreter/geode.md +++ b/docs/interpreter/geode.md @@ -6,7 +6,11 @@ group: manual --- {% include JB/setup %} -## Geode/Gemfire OQL Interpreter for Apache Zeppelin +# Geode/Gemfire OQL Interpreter for Apache Zeppelin + +
    + +## Overview
    @@ -33,7 +37,7 @@ This interpreter supports the [Geode](http://geode.incubator.apache.org/) [Objec This [Video Tutorial](https://www.youtube.com/watch?v=zvzzA9GXu3Q) illustrates some of the features provided by the `Geode Interpreter`. -### Create Interpreter +## Create Interpreter By default Zeppelin creates one `Geode/OQL` instance. You can remove it or create more instances. Multiple Geode instances can be created, each configured to the same or different backend Geode cluster. But over time a `Notebook` can have only one Geode interpreter instance `bound`. That means you _cannot_ connect to different Geode clusters in the same `Notebook`. This is a known Zeppelin limitation. @@ -42,10 +46,10 @@ To create new Geode instance open the `Interpreter` section and click the `+Crea > Note: The `Name` of the instance is used only to distinguish the instances while binding them to the `Notebook`. The `Name` is irrelevant inside the `Notebook`. In the `Notebook` you must use `%geode.oql` tag. -### Bind to Notebook +## Bind to Notebook In the `Notebook` click on the `settings` icon in the top right corner. The select/deselect the interpreters to be bound with the `Notebook`. -### Configuration +## Configuration You can modify the configuration of the Geode from the `Interpreter` section. The Geode interpreter expresses the following properties:
    Name
    @@ -71,12 +75,12 @@ You can modify the configuration of the Geode from the `Interpreter` section. T
    -### How to use +## How to use > *Tip 1: Use (CTRL + .) for OQL auto-completion.* > *Tip 2: Always start the paragraphs with the full `%geode.oql` prefix tag! The short notation: `%geode` would still be able run the OQL queries but the syntax highlighting and the auto-completions will be disabled.* -#### Create / Destroy Regions +### Create / Destroy Regions The OQL specification does not support [Geode Regions](https://cwiki.apache.org/confluence/display/GEODE/Index#Index-MainConceptsandComponents) mutation operations. To `create`/`destroy` regions one should use the [GFSH](http://geode-docs.cfapps.io/docs/tools_modules/gfsh/chapter_overview.html) shell tool instead. In the following it is assumed that the GFSH is colocated with Zeppelin server. ```bash @@ -97,7 +101,7 @@ EOF Above snippet re-creates two regions: `regionEmployee` and `regionCompany`. Note that you have to explicitly specify the locator host and port. The values should match those you have used in the Geode Interpreter configuration. Comprehensive list of [GFSH Commands by Functional Area](http://geode-docs.cfapps.io/docs/tools_modules/gfsh/gfsh_quick_reference.html). -#### Basic OQL +### Basic OQL ```sql %geode.oql SELECT count(*) FROM /regionEmployee @@ -136,7 +140,7 @@ SELECT e.key, e.value FROM /regionEmployee.entrySet e > Note: You can have multiple queries in the same paragraph but only the result from the first is displayed. [[1](https://issues.apache.org/jira/browse/ZEPPELIN-178)], [[2](https://issues.apache.org/jira/browse/ZEPPELIN-212)]. -#### GFSH Commands From The Shell +### GFSH Commands From The Shell Use the Shell Interpreter (`%sh`) to run OQL commands form the command line: ```bash @@ -145,7 +149,7 @@ source /etc/geode/conf/geode-env.sh gfsh -e "connect" -e "list members" ``` -#### Apply Zeppelin Dynamic Forms +### Apply Zeppelin Dynamic Forms You can leverage [Zeppelin Dynamic Form](../manual/dynamicform.html) inside your OQL queries. You can use both the `text input` and `select form` parameterization features ```sql @@ -153,7 +157,10 @@ You can leverage [Zeppelin Dynamic Form](../manual/dynamicform.html) inside your SELECT * FROM /regionEmployee e WHERE e.employeeId > ${Id} ``` -#### Geode REST API +### Auto-completion +The Geode Interpreter provides a basic auto-completion functionality. On `(Ctrl+.)` it list the most relevant suggestions in a pop-up window. + +## Geode REST API To list the defined regions you can use the [Geode REST API](http://geode-docs.cfapps.io/docs/geode_rest/chapter_overview.html): ``` @@ -182,6 +189,3 @@ http://phd1.localdomain:8484/gemfire-api/v1/ http-service-port=8484 start-dev-rest-api=true ``` - -### Auto-completion -The Geode Interpreter provides a basic auto-completion functionality. On `(Ctrl+.)` it list the most relevant suggestions in a pop-up window. diff --git a/docs/interpreter/hbase.md b/docs/interpreter/hbase.md index 2eaa91578f7..1aeb77bcade 100644 --- a/docs/interpreter/hbase.md +++ b/docs/interpreter/hbase.md @@ -6,16 +6,22 @@ group: manual --- {% include JB/setup %} -## HBase Shell Interpreter for Apache Zeppelin +# HBase Shell Interpreter for Apache Zeppelin + +
    + +## Overview [HBase Shell](http://hbase.apache.org/book.html#shell) is a JRuby IRB client for Apache HBase. This interpreter provides all capabilities of Apache HBase shell within Apache Zeppelin. The interpreter assumes that Apache HBase client software has been installed and it can connect to the Apache HBase cluster from the machine on where Apache Zeppelin is installed. -To get start with HBase, please see [HBase Quickstart](https://hbase.apache.org/book.html#quickstart) +To get start with HBase, please see [HBase Quickstart](https://hbase.apache.org/book.html#quickstart). ## HBase release supported By default, Zeppelin is built against HBase 1.0.x releases. To work with HBase 1.1.x releases, use the following build command: + ```bash # HBase 1.1.4 mvn clean package -DskipTests -Phadoop-2.6 -Dhadoop.version=2.6.0 -P build-distr -Dhbase.hbase.version=1.1.4 -Dhbase.hadoop.version=2.6.0 ``` + To work with HBase 1.2.0+, use the following build command: ```bash @@ -94,4 +100,4 @@ And then to put data into that table put 'test', 'row1', 'cf:a', 'value1' ``` -For more information on all commands available, refer to [HBase shell commands](https://learnhbase.wordpress.com/2013/03/02/hbase-shell-commands/) +For more information on all commands available, refer to [HBase shell commands](https://learnhbase.wordpress.com/2013/03/02/hbase-shell-commands/). diff --git a/docs/interpreter/hdfs.md b/docs/interpreter/hdfs.md index 58d825dddb3..7cde31a6960 100644 --- a/docs/interpreter/hdfs.md +++ b/docs/interpreter/hdfs.md @@ -6,8 +6,11 @@ group: manual --- {% include JB/setup %} -## HDFS File System Interpreter for Apache Zeppelin +# HDFS File System Interpreter for Apache Zeppelin +
    + +## Overview [Hadoop File System](http://hadoop.apache.org/) is a distributed, fault tolerant file system part of the hadoop project and is often used as storage for distributed processing engines like [Hadoop MapReduce](http://hadoop.apache.org/) and [Apache Spark](http://spark.apache.org/) or underlying file systems like [Alluxio](http://www.alluxio.org/). ## Configuration @@ -44,13 +47,17 @@ It supports the basic shell file commands applied to HDFS, it currently only sup > **Tip :** Use ( Ctrl + . ) for autocompletion. -### Create Interpreter +## Create Interpreter In a notebook, to enable the **HDFS** interpreter, click the **Gear** icon and select **HDFS**. -#### WebHDFS REST API +## WebHDFS REST API You can confirm that you're able to access the WebHDFS API by running a curl command against the WebHDFS end point provided to the interpreter. Here is an example: + +```bash $> curl "http://localhost:50070/webhdfs/v1/?op=LISTSTATUS" +``` + diff --git a/docs/interpreter/hive.md b/docs/interpreter/hive.md index 2fc365c3502..a1fc4e1e618 100644 --- a/docs/interpreter/hive.md +++ b/docs/interpreter/hive.md @@ -6,8 +6,9 @@ group: manual --- {% include JB/setup %} -## Hive Interpreter for Apache Zeppelin -The [Apache Hive](https://hive.apache.org/) ™ data warehouse software facilitates querying and managing large datasets residing in distributed storage. Hive provides a mechanism to project structure onto this data and query the data using a SQL-like language called HiveQL. At the same time this language also allows traditional map/reduce programmers to plug in their custom mappers and reducers when it is inconvenient or inefficient to express this logic in HiveQL. +# Hive Interpreter for Apache Zeppelin + +
    ## Important Notice Hive Interpreter will be deprecated and merged into JDBC Interpreter. You can use Hive Interpreter by using JDBC Interpreter with same functionality. See the example below of settings and dependencies. @@ -52,7 +53,6 @@ Hive Interpreter will be deprecated and merged into JDBC Interpreter. You can us ----- ### Configuration @@ -115,6 +115,10 @@ Hive Interpreter will be deprecated and merged into JDBC Interpreter. You can us This interpreter provides multiple configuration with `${prefix}`. User can set a multiple connection properties by this prefix. It can be used like `%hive(${prefix})`. +## Overview + +The [Apache Hive](https://hive.apache.org/) ™ data warehouse software facilitates querying and managing large datasets residing in distributed storage. Hive provides a mechanism to project structure onto this data and query the data using a SQL-like language called HiveQL. At the same time this language also allows traditional map/reduce programmers to plug in their custom mappers and reducers when it is inconvenient or inefficient to express this logic in HiveQL. + ## How to use Basically, you can use diff --git a/docs/interpreter/ignite.md b/docs/interpreter/ignite.md index 6bc20abb5ed..8a25fd7ca79 100644 --- a/docs/interpreter/ignite.md +++ b/docs/interpreter/ignite.md @@ -6,16 +6,18 @@ group: manual --- {% include JB/setup %} -## Ignite Interpreter for Apache Zeppelin +# Ignite Interpreter for Apache Zeppelin -### Overview +
    + +## Overview [Apache Ignite](https://ignite.apache.org/) In-Memory Data Fabric is a high-performance, integrated and distributed in-memory platform for computing and transacting on large-scale data sets in real-time, orders of magnitude faster than possible with traditional disk-based or flash technologies. ![Apache Ignite](../assets/themes/zeppelin/img/docs-img/ignite-logo.png) You can use Zeppelin to retrieve distributed data from cache using Ignite SQL interpreter. Moreover, Ignite interpreter allows you to execute any Scala code in cases when SQL doesn't fit to your requirements. For example, you can populate data into your caches or execute distributed computations. -### Installing and Running Ignite example +## Installing and Running Ignite example In order to use Ignite interpreters, you may install Apache Ignite in some simple steps: 1. Download Ignite [source release](https://ignite.apache.org/download.html#sources) or [binary release](https://ignite.apache.org/download.html#binaries) whatever you want. But you must download Ignite as the same version of Zeppelin's. If it is not, you can't use scala code on Zeppelin. You can find ignite version in Zeppelin at the pom.xml which is placed under `path/to/your-Zeppelin/ignite/pom.xml` ( Of course, in Zeppelin source release ). Please check `ignite.version` .
    Currently, Zeppelin provides ignite only in Zeppelin source release. So, if you download Zeppelin binary release( `zeppelin-0.5.0-incubating-bin-spark-xxx-hadoop-xx` ), you can not use ignite interpreter on Zeppelin. We are planning to include ignite in a future binary release. @@ -31,7 +33,7 @@ In order to use Ignite interpreters, you may install Apache Ignite in some simpl $ nohup java -jar ``` -### Configuring Ignite Interpreter +## Configuring Ignite Interpreter At the "Interpreters" menu, you may edit Ignite interpreter or create new one. Zeppelin provides these properties for Ignite.
    @@ -69,14 +71,14 @@ At the "Interpreters" menu, you may edit Ignite interpreter or create new one. Z ![Configuration of Ignite Interpreter](../assets/themes/zeppelin/img/docs-img/ignite-interpreter-setting.png) -### Interpreter Binding for Zeppelin Notebook +## How to use After configuring Ignite interpreter, create your own notebook. Then you can bind interpreters like below image. ![Binding Interpreters](../assets/themes/zeppelin/img/docs-img/ignite-interpreter-binding.png) For more interpreter binding information see [here](http://zeppelin.apache.org/docs/manual/interpreters.html). -### How to use Ignite SQL interpreter +### Ignite SQL interpreter In order to execute SQL query, use ` %ignite.ignitesql ` prefix.
    Supposing you are running `org.apache.ignite.examples.streaming.wordcount.StreamWords`, then you can use "words" cache( Of course you have to specify this cache name to the Ignite interpreter setting section `ignite.jdbc.url` of Zeppelin ). For example, you can select top 10 words in the words cache using the following query diff --git a/docs/interpreter/jdbc.md b/docs/interpreter/jdbc.md index c4eef986d2f..830dd9789e4 100644 --- a/docs/interpreter/jdbc.md +++ b/docs/interpreter/jdbc.md @@ -7,7 +7,11 @@ group: manual {% include JB/setup %} -## Generic JDBC Interpreter for Apache Zeppelin +# Generic JDBC Interpreter for Apache Zeppelin + +
    + +## Overview This interpreter lets you create a JDBC connection to any data source, by now it has been tested with: @@ -16,16 +20,14 @@ This interpreter lets you create a JDBC connection to any data source, by now it * MariaDB * Redshift * Apache Hive -* Apache Drill - * Details on using [Drill JDBC Driver](https://drill.apache.org/docs/using-the-jdbc-driver) * Apache Phoenix -* Apache Tajo +* Apache Drill (Details on using [Drill JDBC Driver](https://drill.apache.org/docs/using-the-jdbc-driverde* Apache Tajo If someone else used another database please report how it works to improve functionality. -### Create Interpreter +## Create Interpreter -When create a interpreter by default use PostgreSQL with the next properties: +When you create a interpreter by default use PostgreSQL with the next properties:
    @@ -56,7 +58,7 @@ When create a interpreter by default use PostgreSQL with the next properties: It is not necessary to add driver jar to the classpath for PostgreSQL as it is included in Zeppelin. -#### Simple connection +### Simple connection Prior to creating the interpreter it is necessary to add maven coordinate or path of the JDBC driver to the Zeppelin classpath. To do this you must edit dependencies artifact(ex. `mysql:mysql-connector-java:5.1.38`) in interpreter menu as shown: @@ -95,7 +97,7 @@ To create the interpreter you need to specify connection parameters as shown in
    -#### Multiple connections +### Multiple connections JDBC interpreter also allows connections to multiple data sources. It is necessary to set a prefix for each connection to reference it in the paragraph in the form of `%jdbc(prefix)`. Before you create the interpreter it is necessary to add each driver's maven coordinates or JDBC driver's jar file path to the Zeppelin classpath. To do this you must edit the dependencies of JDBC interpreter in interpreter menu as following: @@ -151,10 +153,10 @@ You can add all the jars you need to make multiple connections into the same JDB -### Bind to Notebook +## Bind to Notebook In the `Notebook` click on the `settings` icon at the top-right corner. Use select/deselect to specify the interpreters to be used in the `Notebook`. -### More Properties +## More Properties You can modify the interpreter configuration in the `Interpreter` section. The most common properties are as follows, but you can specify other properties that need to be connected. @@ -197,9 +199,11 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    -### Examples -#### Hive -##### Properties +## Examples + +### Hive + +#### Properties @@ -222,7 +226,8 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Namehive_password
    -##### Dependencies + +#### Dependencies @@ -237,8 +242,9 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Artifact
    -#### Phoenix -##### Properties + +### Phoenix +#### Properties @@ -261,7 +267,7 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Namephoenix_password
    -##### Dependencies +#### Dependencies @@ -272,8 +278,9 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Artifact
    -#### Tajo -##### Properties + +### Tajo +#### Properties @@ -288,7 +295,8 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Namejdbc:tajo://localhost:26002/default
    -##### Dependencies + +#### Dependencies @@ -300,9 +308,9 @@ To develop this functionality use this [method](http://docs.oracle.com/javase/7/
    Artifact
    -### How to use +## How to use -#### Reference in paragraph +### Reference in paragraph Start the paragraphs with the `%jdbc`, this will use the `default` prefix for connection. If you want to use other connection you should specify the prefix of it as follows `%jdbc(prefix)`: @@ -311,6 +319,7 @@ Start the paragraphs with the `%jdbc`, this will use the `default` prefix for co SELECT * FROM db_name; ``` + or ```sql @@ -319,7 +328,7 @@ SELECT * FROM db_name; ``` -#### Apply Zeppelin Dynamic Forms +### Apply Zeppelin Dynamic Forms You can leverage [Zeppelin Dynamic Form](../manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parametrization features @@ -330,5 +339,5 @@ FROM demo.performers WHERE name='{{performer=Sheryl Crow|Doof|Fanfarlo|Los Paranoia}}' ``` -### Bugs & Contacts +## Bugs & Reporting If you find a bug for this interpreter, please create a [JIRA]( https://issues.apache.org/jira/browse/ZEPPELIN-382?jql=project%20%3D%20ZEPPELIN) ticket. diff --git a/docs/interpreter/lens.md b/docs/interpreter/lens.md index 0b4711bace5..b4bcda49bd7 100644 --- a/docs/interpreter/lens.md +++ b/docs/interpreter/lens.md @@ -6,14 +6,16 @@ group: manual --- {% include JB/setup %} -## Lens Interpreter for Apache Zeppelin +# Lens Interpreter for Apache Zeppelin -### Overview +
    + +## Overview [Apache Lens](https://lens.apache.org/) provides an Unified Analytics interface. Lens aims to cut the Data Analytics silos by providing a single view of data across multiple tiered data stores and optimal execution environment for the analytical query. It seamlessly integrates Hadoop with traditional data warehouses to appear like one. ![Apache Lens](../assets/themes/zeppelin/img/docs-img/lens-logo.png) -### Installing and Running Lens +## Installing and Running Lens In order to use Lens interpreters, you may install Apache Lens in some simple steps: 1. Download Lens for latest version from [the ASF](http://www.apache.org/dyn/closer.lua/lens/2.3-beta). Or the older release can be found [in the Archives](http://archive.apache.org/dist/lens/). @@ -24,7 +26,7 @@ In order to use Lens interpreters, you may install Apache Lens in some simple st ./bin/lens-ctl start (or stop) ``` -### Configuring Lens Interpreter +## Configuring Lens Interpreter At the "Interpreters" menu, you can edit Lens interpreter or create new one. Zeppelin provides these properties for Lens. @@ -163,7 +165,7 @@ query execute cube select customer_city_name, product_details.description, produ These are just examples that provided in advance by Lens. If you want to explore whole tutorials of Lens, see the [tutorial video](https://cwiki.apache.org/confluence/display/LENS/2015/07/13/20+Minute+video+demo+of+Apache+Lens+through+examples). -### Lens UI Service +## Lens UI Service Lens also provides web UI service. Once the server starts up, you can open the service on http://serverhost:19999/index.html and browse. You may also check the structure that you made and use query easily here. ![Lens UI Service](../assets/themes/zeppelin/img/docs-img/lens-ui-service.png) diff --git a/docs/interpreter/livy.md b/docs/interpreter/livy.md index 225cd817bee..ef7c8ce6876 100644 --- a/docs/interpreter/livy.md +++ b/docs/interpreter/livy.md @@ -6,8 +6,12 @@ group: manual --- {% include JB/setup %} -## Livy Interpreter for Apache Zeppelin -Livy is an open source REST interface for interacting with Spark from anywhere. It supports executing snippets of code or programs in a Spark context that runs locally or in YARN. +# Livy Interpreter for Apache Zeppelin + +
    + +## Overview +[Livy](http://livy.io/) is an open source REST interface for interacting with Spark from anywhere. It supports executing snippets of code or programs in a Spark context that runs locally or in YARN. * Interactive Scala, Python and R shells * Batch submissions in Scala, Java, Python @@ -16,13 +20,12 @@ Livy is an open source REST interface for interacting with Spark from anywhere. * Does not require any code change to your programs ### Requirements - Additional requirements for the Livy interpreter are: * Spark 1.3 or above. * Livy server. -### Configuration +## Configuration We added some common configurations for spark, and you can set any configuration you want. This link contains all spark configurations: http://spark.apache.org/docs/latest/configuration.html#available-properties. And instead of starting property with `spark.` it should be replaced with `livy.spark.`. @@ -101,8 +104,6 @@ Example: `spark.master` to `livy.spark.master`
    - - ## How to use Basically, you can use @@ -136,7 +137,7 @@ hello("livy") When Zeppelin server is running with authentication enabled, then this interpreter utilizes Livy’s user impersonation feature i.e. sends extra parameter for creating and running a session ("proxyUser": "${loggedInUser}"). This is particularly useful when multi users are sharing a Notebook server. -### Apply Zeppelin Dynamic Forms +## Apply Zeppelin Dynamic Forms You can leverage [Zeppelin Dynamic Form]({{BASE_PATH}}/manual/dynamicform.html). You can use both the `text input` and `select form` parameterization features. ``` @@ -159,7 +160,7 @@ The session would have timed out, you may need to restart the interpreter. > Blacklisted configuration values in session config: spark.master -edit `conf/spark-blacklist.conf` file in livy server and comment out `#spark.master` line. +Edit `conf/spark-blacklist.conf` file in livy server and comment out `#spark.master` line. -if you choose to work on livy in `apps/spark/java` directory in https://github.com/cloudera/hue , -copy `spark-user-configurable-options.template` to `spark-user-configurable-options.conf` file in livy server and comment out `#spark.master` +If you choose to work on livy in `apps/spark/java` directory in [https://github.com/cloudera/hue](https://github.com/cloudera/hue), +copy `spark-user-configurable-options.template` to `spark-user-configurable-options.conf` file in livy server and comment out `#spark.master`. diff --git a/docs/interpreter/markdown.md b/docs/interpreter/markdown.md index 08b44f84f20..21184dcf762 100644 --- a/docs/interpreter/markdown.md +++ b/docs/interpreter/markdown.md @@ -6,9 +6,11 @@ group: manual --- {% include JB/setup %} -## Markdown Interpreter for Apache Zeppelin +# Markdown Interpreter for Apache Zeppelin -### Overview +
    + +## Overview [Markdown](http://daringfireball.net/projects/markdown/) is a plain text formatting syntax designed so that it can be converted to HTML. Zeppelin uses markdown4j. For more examples and extension support, please checkout [here](https://code.google.com/p/markdown4j/). In Zeppelin notebook, you can use ` %md ` in the beginning of a paragraph to invoke the Markdown interpreter and generate static html from Markdown plain text. @@ -17,7 +19,7 @@ In Zeppelin, Markdown interpreter is enabled by default. -### Example +## Example The following example demonstrates the basic usage of Markdown in a Zeppelin notebook. diff --git a/docs/interpreter/postgresql.md b/docs/interpreter/postgresql.md index 5985b188791..be3c165fe74 100644 --- a/docs/interpreter/postgresql.md +++ b/docs/interpreter/postgresql.md @@ -6,7 +6,12 @@ group: manual --- {% include JB/setup %} +# PostgreSQL, HAWQ Interpreter for Apache Zeppelin + +
    + ## Important Notice + Postgresql Interpreter will be deprecated and merged into JDBC Interpreter. You can use Postgresql by using JDBC Interpreter with same functionality. See the example below of settings and dependencies. ### Properties @@ -44,10 +49,19 @@ Postgresql Interpreter will be deprecated and merged into JDBC Interpreter. You +--- + +## Overview + +[zeppelin-view](https://www.youtube.com/watch?v=wqXXQhJ5Uk8) ----- +This interpreter seamlessly supports the following SQL data processing engines: -## PostgreSQL, HAWQ Interpreter for Apache Zeppelin +* [PostgreSQL](http://www.postgresql.org/) - OSS, Object-relational database management system (ORDBMS) +* [Apache HAWQ](http://pivotal.io/big-data/pivotal-hawq) - Powerful [Open Source](https://wiki.apache.org/incubator/HAWQProposal) SQL-On-Hadoop engine. +* [Greenplum](http://pivotal.io/big-data/pivotal-greenplum-database) - MPP database built on open source PostgreSQL. + +This [Video Tutorial](https://www.youtube.com/watch?v=wqXXQhJ5Uk8) illustrates some of the features provided by the `Postgresql Interpreter`. @@ -62,17 +76,7 @@ Postgresql Interpreter will be deprecated and merged into JDBC Interpreter. You
    -[zeppelin-view](https://www.youtube.com/watch?v=wqXXQhJ5Uk8) - -This interpreter seamlessly supports the following SQL data processing engines: - -* [PostgreSQL](http://www.postgresql.org/) - OSS, Object-relational database management system (ORDBMS) -* [Apache HAWQ](http://pivotal.io/big-data/pivotal-hawq) - Powerful [Open Source](https://wiki.apache.org/incubator/HAWQProposal) SQL-On-Hadoop engine. -* [Greenplum](http://pivotal.io/big-data/pivotal-greenplum-database) - MPP database built on open source PostgreSQL. - -This [Video Tutorial](https://www.youtube.com/watch?v=wqXXQhJ5Uk8) illustrates some of the features provided by the `Postgresql Interpreter`. - -### Create Interpreter +## Create Interpreter By default Zeppelin creates one `PSQL` instance. You can remove it or create new instances. Multiple PSQL instances can be created, each configured to the same or different backend databases. But over time a `Notebook` can have only one PSQL interpreter instance `bound`. That means you _cannot_ connect to different databases in the same `Notebook`. This is a known Zeppelin limitation. @@ -81,10 +85,10 @@ To create new PSQL instance open the `Interpreter` section and click the `+Creat > Note: The `Name` of the instance is used only to distinct the instances while binding them to the `Notebook`. The `Name` is irrelevant inside the `Notebook`. In the `Notebook` you must use `%psql.sql` tag. -### Bind to Notebook +## Bind to Notebook In the `Notebook` click on the `settings` icon in the top right corner. The select/deselect the interpreters to be bound with the `Notebook`. -### Configuration +## Configuration You can modify the configuration of the PSQL from the `Interpreter` section. The PSQL interpreter expenses the following properties: @@ -120,12 +124,12 @@ You can modify the configuration of the PSQL from the `Interpreter` section. Th
    -### How to use +## How to use ``` Tip: Use (CTRL + .) for SQL auto-completion. ``` -#### DDL and SQL commands +### DDL and SQL commands Start the paragraphs with the full `%psql.sql` prefix tag! The short notation: `%psql` would still be able run the queries but the syntax highlighting and the auto-completions will be disabled. You can use the standard CREATE / DROP / INSERT commands to create or modify the data model: @@ -154,7 +158,7 @@ select count(*) from mytable; select * from mytable; ``` -#### PSQL command line tools +### PSQL command line tools Use the Shell Interpreter (`%sh`) to access the command line [PSQL](http://www.postgresql.org/docs/9.4/static/app-psql.html) interactively: ```bash @@ -179,7 +183,7 @@ This will produce output like this: retail_demo | gpadmin ``` -#### Apply Zeppelin Dynamic Forms +### Apply Zeppelin Dynamic Forms You can leverage [Zeppelin Dynamic Form](../manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parametrization features ```sql @@ -191,7 +195,7 @@ ORDER BY count ${order=DESC,DESC|ASC} LIMIT ${limit=10}; ``` -#### Example HAWQ PXF/HDFS Tables +### Example HAWQ PXF/HDFS Tables Create HAWQ external table that read data from tab-separated-value data in HDFS. ```sql @@ -209,5 +213,5 @@ And retrieve content select * from retail_demo.payment_methods_pxf ``` -### Auto-completion +## Auto-completion The PSQL Interpreter provides a basic auto-completion functionality. On `(Ctrl+.)` it list the most relevant suggestions in a pop-up window. In addition to the SQL keyword the interpreter provides suggestions for the Schema, Table, Column names as well. diff --git a/docs/interpreter/python.md b/docs/interpreter/python.md index b34b0898ffc..34f6f45b6db 100644 --- a/docs/interpreter/python.md +++ b/docs/interpreter/python.md @@ -6,7 +6,9 @@ group: manual --- {% include JB/setup %} -## Python 2 & 3 Interpreter for Apache Zeppelin +# Python 2 & 3 Interpreter for Apache Zeppelin + +
    ## Configuration @@ -63,8 +65,6 @@ print (z.select("f1",[("o1","1"),("o2","2")],"2")) print("".join(z.checkbox("f3", [("o1","1"), ("o2","2")],["1"]))) ``` - - ## Zeppelin features not fully supported by the Python Interpreter * Interrupt a paragraph execution (`cancel()` method) is currently only supported in Linux and MacOs. If interpreter runs in another operating system (for instance MS Windows) , interrupt a paragraph will close the whole interpreter. A JIRA ticket ([ZEPPELIN-893](https://issues.apache.org/jira/browse/ZEPPELIN-893)) is opened to implement this feature in a next release of the interpreter. @@ -105,7 +105,6 @@ rates = pd.read_csv("bank.csv", sep=";") z.show(rates) ``` - ## Technical description -For in-depth technical details on current implementation plese reffer [python/README.md](https://github.com/apache/zeppelin/blob/master/python/README.md) +For in-depth technical details on current implementation plese reffer [python/README.md](https://github.com/apache/zeppelin/blob/master/python/README.md). diff --git a/docs/interpreter/scalding.md b/docs/interpreter/scalding.md index ec5608bf3b3..e8774df67fa 100644 --- a/docs/interpreter/scalding.md +++ b/docs/interpreter/scalding.md @@ -6,17 +6,20 @@ group: manual --- {% include JB/setup %} -## Scalding Interpreter for Apache Zeppelin +# Scalding Interpreter for Apache Zeppelin + +
    + [Scalding](https://github.com/twitter/scalding) is an open source Scala library for writing MapReduce jobs. -### Building the Scalding Interpreter +## Building the Scalding Interpreter You have to first build the Scalding interpreter by enable the **scalding** profile as follows: ``` mvn clean package -Pscalding -DskipTests ``` -### Enabling the Scalding Interpreter +## Enabling the Scalding Interpreter In a notebook, to enable the **Scalding** interpreter, click on the **Gear** icon,select **Scalding**, and hit **Save**.
    @@ -27,7 +30,7 @@ In a notebook, to enable the **Scalding** interpreter, click on the **Gear** ico
    -### Configuring the Interpreter +## Configuring the Interpreter Scalding interpreter runs in two modes: @@ -65,9 +68,9 @@ For reducer estimation, you need to add something like: If you want to control the maximum number of open interpreters, you have to select "scoped" interpreter for note option and set max.open.instances argument. -### Testing the Interpreter +## Testing the Interpreter -#### Local mode +### Local mode In example, by using the [Alice in Wonderland](https://gist.github.com/johnynek/a47699caa62f4f38a3e2) tutorial, we will count words (of course!), and plot a graph of the top 10 words in the book. @@ -111,7 +114,7 @@ If you click on the icon for the pie chart, you should be able to see a chart li ![Scalding - Pie - Chart](../assets/themes/zeppelin/img/docs-img/scalding-pie.png) -#### HDFS mode +### HDFS mode **Test mode** @@ -146,7 +149,7 @@ a.toList This command should create a map reduce job. -### Future Work +## Future Work * Better user feedback (hadoop url, progress updates) * Ability to cancel jobs * Ability to dynamically load jars without restarting the interpreter diff --git a/docs/interpreter/spark.md b/docs/interpreter/spark.md index df5e83176f2..4425b788fd4 100644 --- a/docs/interpreter/spark.md +++ b/docs/interpreter/spark.md @@ -7,8 +7,14 @@ group: manual {% include JB/setup %} -## Spark Interpreter for Apache Zeppelin -[Apache Spark](http://spark.apache.org) is supported in Zeppelin with +# Spark Interpreter for Apache Zeppelin + +
    + +## Overview +[Apache Spark](http://spark.apache.org) is a fast and general-purpose cluster computing system. +It provides high-level APIs in Java, Scala, Python and R, and an optimized engine that supports general execution graphs +Apache Spark is supported in Zeppelin with Spark Interpreter group, which consists of five interpreters.
    @@ -200,13 +206,13 @@ Here are few examples: * SPARK\_SUBMIT\_OPTIONS in conf/zeppelin-env.sh - export SPARK_SUBMIT_OPTIONS="--packages com.databricks:spark-csv_2.10:1.2.0 --jars /path/mylib1.jar,/path/mylib2.jar --files /path/mylib1.py,/path/mylib2.zip,/path/mylib3.egg" + export SPARK_SUBMIT_OPTIONS="--packages com.databricks:spark-csv_2.10:1.2.0 --jars /path/mylib1.jar,/path/mylib2.jar --files /path/mylib1.py,/path/mylib2.zip,/path/mylib3.egg" * SPARK_HOME/conf/spark-defaults.conf - spark.jars /path/mylib1.jar,/path/mylib2.jar - spark.jars.packages com.databricks:spark-csv_2.10:1.2.0 - spark.files /path/mylib1.py,/path/mylib2.egg,/path/mylib3.zip + spark.jars /path/mylib1.jar,/path/mylib2.jar + spark.jars.packages com.databricks:spark-csv_2.10:1.2.0 + spark.files /path/mylib1.py,/path/mylib2.egg,/path/mylib3.zip ### 3. Dynamic Dependency Loading via %dep interpreter > Note: `%dep` interpreter is deprecated since v0.6.0. @@ -344,7 +350,7 @@ select * from ${table=defaultTableName} where text like '%${search}%' To learn more about dynamic form, checkout [Dynamic Form](../manual/dynamicform.html). -### Interpreter setting option. +## Interpreter setting option Interpreter setting can choose one of 'shared', 'scoped', 'isolated' option. Spark interpreter creates separate scala compiler per each notebook but share a single SparkContext in 'scoped' mode (experimental). It creates separate SparkContext per each notebook in 'isolated' mode. @@ -354,7 +360,7 @@ Logical setup with Zeppelin, Kerberos Key Distribution Center (KDC), and Spark o -####Configuration Setup +### Configuration Setup 1. On the server that Zeppelin is installed, install Kerberos client modules and configuration, krb5.conf. This is to make the server communicate with KDC. From bef398e2255348e3178c4415ab9c04aaabeba5e3 Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 19:42:32 -0700 Subject: [PATCH 05/24] Apply auto TOC to all of docs under docs/development/ --- docs/development/howtocontribute.md | 26 ++++---- docs/development/howtocontributewebsite.md | 41 ++++++------ .../development/writingzeppelininterpreter.md | 66 ++++++++++--------- 3 files changed, 69 insertions(+), 64 deletions(-) diff --git a/docs/development/howtocontribute.md b/docs/development/howtocontribute.md index 7b3ee0cfe6b..a859a91e2da 100644 --- a/docs/development/howtocontribute.md +++ b/docs/development/howtocontribute.md @@ -7,8 +7,9 @@ group: development # Contributing to Apache Zeppelin ( Code ) -## IMPORTANT -Apache Zeppelin is an [Apache2 License](http://www.apache.org/licenses/LICENSE-2.0.html) Software. +
    + +> **NOTE :** Apache Zeppelin is an [Apache2 License](http://www.apache.org/licenses/LICENSE-2.0.html) Software. Any contributions to Zeppelin (Source code, Documents, Image, Website) means you agree with license all your contributions as Apache2 License. ## Setting up @@ -22,7 +23,7 @@ Since Zeppelin uses Git for it's SCM system, you need git client installed in yo You are free to use whatever IDE you prefer, or your favorite command line editor. -### Build Tools +#### Build Tools To build the code, install @@ -46,10 +47,10 @@ You may also want to develop against a specific branch. For example, for branch- git clone -b branch-0.5.6 git://git.apache.org/zeppelin.git zeppelin ``` -#### Fork repository -If you want not only build Zeppelin but also make any changes, then you need fork [Zeppelin github mirror repository](https://github.com/apache/zeppelin) and make a pull request. +Apache Zeppelin follows [Fork & Pull](https://github.com/sevntu-checkstyle/sevntu.checkstyle/wiki/Development-workflow-with-Git:-Fork,-Branching,-Commits,-and-Pull-Request) as a source control workflow. +If you want to not only build Zeppelin but also make any changes, then you need to fork [Zeppelin github mirror repository](https://github.com/apache/zeppelin) and make a pull request. -###Build +### Build ``` mvn install @@ -67,6 +68,8 @@ To build with specific spark / hadoop version mvn install -Dspark.version=x.x.x -Dhadoop.version=x.x.x ``` +For the further + ### Run Zeppelin server in development mode ``` @@ -88,21 +91,16 @@ Server will be run on [http://localhost:8080](http://localhost:8080). Some portions of the Zeppelin code are generated by [Thrift](http://thrift.apache.org). For most Zeppelin changes, you don't need to worry about this. But if you modify any of the Thrift IDL files (e.g. zeppelin-interpreter/src/main/thrift/*.thrift), then you also need to regenerate these files and submit their updated version as part of your patch. -To regenerate the code, install **thrift-0.9.0** and change directory into Zeppelin source directory. and then run following command +To regenerate the code, install **thrift-0.9.2** and change directory into Zeppelin source directory. and then run following command ``` thrift -out zeppelin-interpreter/src/main/java/ --gen java zeppelin-interpreter/src/main/thrift/RemoteInterpreterService.thrift ``` - -## JIRA -Zeppelin manages its issues in Jira. [https://issues.apache.org/jira/browse/ZEPPELIN](https://issues.apache.org/jira/browse/ZEPPELIN) - -## Where to Start -You can find issues for [beginner](https://issues.apache.org/jira/browse/ZEPPELIN-924?jql=project%20%3D%20ZEPPELIN%20and%20status%20%3D%20Open%20and%20labels%20in%20\(beginner%2C%20newbie\)). - ## Stay involved Contributors should join the Zeppelin mailing lists. * [dev@zeppelin.apache.org](http://mail-archives.apache.org/mod_mbox/zeppelin-dev/) is for people who want to contribute code to Zeppelin. [subscribe](mailto:dev-subscribe@zeppelin.apache.org?subject=send this email to subscribe), [unsubscribe](mailto:dev-unsubscribe@zeppelin.apache.org?subject=send this email to unsubscribe), [archives](http://mail-archives.apache.org/mod_mbox/zeppelin-dev/) + +If you have any issues, create a ticket in [JIRA](https://issues.apache.org/jira/browse/ZEPPELIN). diff --git a/docs/development/howtocontributewebsite.md b/docs/development/howtocontributewebsite.md index f56b8e3ee1f..0db15551585 100644 --- a/docs/development/howtocontributewebsite.md +++ b/docs/development/howtocontributewebsite.md @@ -7,49 +7,52 @@ group: development # Contributing to Apache Zeppelin ( Website ) -## IMPORTANT -Apache Zeppelin is an [Apache2 License](http://www.apache.org/licenses/LICENSE-2.0.html) Software. -Any contribution to Zeppelin (Source code, Documents, Image, Website) means you agree license all your contributions as Apache2 License. +
    -## Modifying the website +This page will give you an overview of how to build and contribute to the documentation of Apache Zeppelin. +The online documentation at [zeppelin.apache.org](https://zeppelin.apache.org/docs/latest/) is also generated from the files found here. -#### Getting the source code -Website is hosted in 'master' branch under `/docs/` dir. +> **NOTE :** Apache Zeppelin is an [Apache2 License](http://www.apache.org/licenses/LICENSE-2.0.html) Software. +Any contributions to Zeppelin (Source code, Documents, Image, Website) means you agree with license all your contributions as Apache2 License. -First of all, you need the website source code. The official location of mirror for Zeppelin is [http://git.apache.org/zeppelin.git](http://git.apache.org/zeppelin.git). +## Getting the source code +First of all, you need Zeppelin source code. The official location of Zeppelin is [http://git.apache.org/zeppelin.git](http://git.apache.org/zeppelin.git). +Documentation website is hosted in 'master' branch under `/docs/` dir. + +### git access +First of all, you need the website source code. The official location of mirror for Zeppelin is [http://git.apache.org/zeppelin.git](http://git.apache.org/zeppelin.git). Get the source code on your development machine using git. ``` git clone git://git.apache.org/zeppelin.git cd docs ``` +Apache Zeppelin follows [Fork & Pull](https://github.com/sevntu-checkstyle/sevntu.checkstyle/wiki/Development-workflow-with-Git:-Fork,-Branching,-Commits,-and-Pull-Request) as a source control workflow. +If you want to not only build Zeppelin but also make any changes, then you need to fork [Zeppelin github mirror repository](https://github.com/apache/zeppelin) and make a pull request. -#### Build - -To build, you'll need to install some prerequisites. Please check 'Build documentation' section in [docs/README.md](https://github.com/apache/zeppelin/blob/master/docs/README.md#build-documentation). +### Build -#### Run website in development mode +You'll need to install some prerequisites to build the code. Please check [Build documentation](https://github.com/apache/zeppelin/blob/master/docs/README.md#build-documentation) section in [docs/README.md](https://github.com/apache/zeppelin/blob/master/docs/README.md). -While you're modifying website, you'll want to see preview of it. Please check 'Run website' section in [docs/README.md](https://github.com/apache/zeppelin/blob/master/docs/README.md#run-website). +### Run website in development mode -You'll be able to access it on [http://localhost:4000](http://localhost:4000) with your web browser. +While you're modifying website, you might want to see preview of it. Please check [Run website](https://github.com/apache/zeppelin/blob/master/docs/README.md#run-website) section in [docs/README.md](https://github.com/apache/zeppelin/blob/master/docs/README.md). +Then you'll be able to access it on [http://localhost:4000](http://localhost:4000) with your web browser. -#### Making a Pull Request +### Making a Pull Request When you are ready, just make a pull-request. ## Alternative way -You can directly edit .md files in `/docs/` dir at github's web interface and make pull-request immediatly. - - -## JIRA -Zeppelin manages its issues in Jira. [https://issues.apache.org/jira/browse/ZEPPELIN](https://issues.apache.org/jira/browse/ZEPPELIN) +You can directly edit `.md` files in `/docs/` directory at the web interface of github and make pull-request immediatly. ## Stay involved Contributors should join the Zeppelin mailing lists. * [dev@zeppelin.apache.org](http://mail-archives.apache.org/mod_mbox/zeppelin-dev/) is for people who want to contribute code to Zeppelin. [subscribe](mailto:dev-subscribe@zeppelin.apache.org?subject=send this email to subscribe), [unsubscribe](mailto:dev-unsubscribe@zeppelin.apache.org?subject=send this email to unsubscribe), [archives](http://mail-archives.apache.org/mod_mbox/zeppelin-dev/) + +If you have any issues, create a ticket in [JIRA](https://issues.apache.org/jira/browse/ZEPPELIN). diff --git a/docs/development/writingzeppelininterpreter.md b/docs/development/writingzeppelininterpreter.md index f3412116527..7e7f4ef2653 100644 --- a/docs/development/writingzeppelininterpreter.md +++ b/docs/development/writingzeppelininterpreter.md @@ -19,21 +19,25 @@ limitations under the License. --> {% include JB/setup %} -### What is Zeppelin Interpreter +# Writing a New Interpreter -Zeppelin Interpreter is a language backend. For example to use scala code in Zeppelin, you need scala interpreter. -Every Interpreter belongs to an InterpreterGroup. +
    + +## What is Apache Zeppelin Interpreter + +Apache Zeppelin Interpreter is a language backend. For example to use scala code in Zeppelin, you need a scala interpreter. +Every Interpreters belongs to an **InterpreterGroup**. Interpreters in the same InterpreterGroup can reference each other. For example, SparkSqlInterpreter can reference SparkInterpreter to get SparkContext from it while they're in the same group. -InterpreterSetting is configuration of a given InterpreterGroup and a unit of start/stop interpreter. -All Interpreters in the same InterpreterSetting are launched in a single, separate JVM process. The Interpreter communicates with Zeppelin engine via thrift. +[InterpreterSetting](https://github.com/apache/zeppelin/blob/master/zeppelin-zengine/src/main/java/org/apache/zeppelin/interpreter/InterpreterSetting.java) is configuration of a given [InterpreterGroup](https://github.com/apache/zeppelin/blob/master/zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/InterpreterGroup.java) and a unit of start/stop interpreter. +All Interpreters in the same InterpreterSetting are launched in a single, separate JVM process. The Interpreter communicates with Zeppelin engine via **[Thrift](https://github.com/apache/zeppelin/blob/master/zeppelin-interpreter/src/main/thrift/RemoteInterpreterService.thrift)**. -In 'Separate Interpreter for each note' mode, new Interpreter instance will be created per notebook. But it still runs on the same JVM while they're in the same InterpreterSettings. +In 'Separate Interpreter(scoped / isolated) for each note' mode which you can see at the **Interpreter Setting** menu when you create a new interpreter, new interpreter instance will be created per notebook. But it still runs on the same JVM while they're in the same InterpreterSettings. -### Make your own Interpreter +## Make your own Interpreter Creating a new interpreter is quite simple. Just extend [org.apache.zeppelin.interpreter](https://github.com/apache/zeppelin/blob/master/zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/Interpreter.java) abstract class and implement some methods. You can include `org.apache.zeppelin:zeppelin-interpreter:[VERSION]` artifact in your build system. And you should your jars under your interpreter directory with specific directory name. Zeppelin server reads interpreter directories recursively and initializes interpreters including your own interpreter. @@ -91,18 +95,18 @@ The name of the interpreter is what you later write to identify a paragraph whic some interpreter specific code... ``` -### Programming Languages for Interpreter +## Programming Languages for Interpreter If the interpreter uses a specific programming language ( like Scala, Python, SQL ), it is generally recommended to add a syntax highlighting supported for that to the notebook paragraph editor. To check out the list of languages supported, see the `mode-*.js` files under `zeppelin-web/bower_components/ace-builds/src-noconflict` or from [github.com/ajaxorg/ace-builds](https://github.com/ajaxorg/ace-builds/tree/master/src-noconflict). If you want to add a new set of syntax highlighting, -1. Add the `mode-*.js` file to `zeppelin-web/bower.json` ( when built, `zeppelin-web/src/index.html` will be changed automatically. ). -2. Add to the list of `editorMode` in `zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js` - it follows the pattern 'ace/mode/x' where x is the name. -3. Add to the code that checks for `%` prefix and calls `session.setMode(editorMode.x)` in `setParagraphMode` located in `zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js`. +1. Add the `mode-*.js` file to [zeppelin-web/bower.json](https://github.com/apache/zeppelin/blob/master/zeppelin-web/bower.json) ( when built, [zeppelin-web/src/index.html](https://github.com/apache/zeppelin/blob/master/zeppelin-web/src/index.html) will be changed automatically. ). +2. Add to the list of `editorMode` in [zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js](https://github.com/apache/zeppelin/blob/master/zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js) - it follows the pattern 'ace/mode/x' where x is the name. +3. Add to the code that checks for `%` prefix and calls `session.setMode(editorMode.x)` in `setParagraphMode` located in [zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js](https://github.com/apache/zeppelin/blob/master/zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js). -### Install your interpreter binary +## Install your interpreter binary Once you have built your interpreter, you can place it under the interpreter directory with all its dependencies. @@ -110,7 +114,7 @@ Once you have built your interpreter, you can place it under the interpreter dir [ZEPPELIN_HOME]/interpreter/[INTERPRETER_NAME]/ ``` -### Configure your interpreter +## Configure your interpreter To configure your interpreter you need to follow these steps: @@ -119,12 +123,12 @@ To configure your interpreter you need to follow these steps: Property value is comma separated [INTERPRETER\_CLASS\_NAME]. For example, -``` - - zeppelin.interpreters - org.apache.zeppelin.spark.SparkInterpreter,org.apache.zeppelin.spark.PySparkInterpreter,org.apache.zeppelin.spark.SparkSqlInterpreter,org.apache.zeppelin.spark.DepInterpreter,org.apache.zeppelin.markdown.Markdown,org.apache.zeppelin.shell.ShellInterpreter,org.apache.zeppelin.hive.HiveInterpreter,com.me.MyNewInterpreter - -``` + ``` + + zeppelin.interpreters + org.apache.zeppelin.spark.SparkInterpreter,org.apache.zeppelin.spark.PySparkInterpreter,org.apache.zeppelin.spark.SparkSqlInterpreter,org.apache.zeppelin.spark.DepInterpreter,org.apache.zeppelin.markdown.Markdown,org.apache.zeppelin.shell.ShellInterpreter,org.apache.zeppelin.hive.HiveInterpreter,com.me.MyNewInterpreter + + ``` 2. Add your interpreter to the [default configuration](https://github.com/apache/zeppelin/blob/master/zeppelin-zengine/src/main/java/org/apache/zeppelin/conf/ZeppelinConfiguration.java#L397) which is used when there is no `zeppelin-site.xml`. @@ -133,11 +137,11 @@ To configure your interpreter you need to follow these steps: 4. In the interpreter page, click the `+Create` button and configure your interpreter properties. Now you are done and ready to use your interpreter. -Note that the interpreters released with zeppelin have a [default configuration](https://github.com/apache/zeppelin/blob/master/zeppelin-zengine/src/main/java/org/apache/zeppelin/conf/ZeppelinConfiguration.java#L397) which is used when there is no `conf/zeppelin-site.xml`. +> **Note :** Interpreters released with zeppelin have a [default configuration](https://github.com/apache/zeppelin/blob/master/zeppelin-zengine/src/main/java/org/apache/zeppelin/conf/ZeppelinConfiguration.java#L397) which is used when there is no `conf/zeppelin-site.xml`. -### Use your interpreter +## Use your interpreter -#### 0.5.0 +### 0.5.0 Inside of a notebook, `%[INTERPRETER_NAME]` directive will call your interpreter. Note that the first interpreter configuration in zeppelin.interpreters will be the default one. @@ -150,8 +154,7 @@ val a = "My interpreter" println(a) ``` -
    -#### 0.6.0 and later +### 0.6.0 and later Inside of a notebook, `%[INTERPRETER_GROUP].[INTERPRETER_NAME]` directive will call your interpreter. Note that the first interpreter configuration in zeppelin.interpreters will be the default one. @@ -192,7 +195,7 @@ You can only omit your interpreter group when your interpreter group is selected codes for myintp2 ``` -### Examples +## Examples Checkout some interpreters released with Zeppelin by default. @@ -201,15 +204,16 @@ Checkout some interpreters released with Zeppelin by default. - [shell](https://github.com/apache/zeppelin/tree/master/shell) - [jdbc](https://github.com/apache/zeppelin/tree/master/jdbc) -### Contributing a new Interpreter to Zeppelin releases +## Contributing a new Interpreter to Zeppelin releases We welcome contribution to a new interpreter. Please follow these few steps: - - First, check out the general contribution guide [here](./howtocontributewebsite.html). - - Follow the steps in "Make your own Interpreter" section above. - - Add your interpreter as in the "Configure your interpreter" section above; also add it to the example template [zeppelin-site.xml.template](https://github.com/apache/zeppelin/blob/master/conf/zeppelin-site.xml.template). - - Add tests! They are run by Travis for all changes and it is important that they are self-contained. + - First, check out the general contribution guide [here](https://github.com/apache/zeppelin/blob/master/CONTRIBUTING.md). + - Follow the steps in [Make your own Interpreter](#make-your-own-interpreter) section above. + - Add your interpreter as in the [Configure your interpreter](#configure-your-interpreter) section above; also add it to the example template [zeppelin-site.xml.template](https://github.com/apache/zeppelin/blob/master/conf/zeppelin-site.xml.template). + - Add tests! They are run by [Travis](https://travis-ci.org/apache/zeppelin) for all changes and it is important that they are self-contained. - Include your interpreter as a module in [`pom.xml`](https://github.com/apache/zeppelin/blob/master/pom.xml). - Add documentation on how to use your interpreter under `docs/interpreter/`. Follow the Markdown style as this [example](https://github.com/apache/zeppelin/blob/master/docs/interpreter/elasticsearch.md). Make sure you list config settings and provide working examples on using your interpreter in code boxes in Markdown. Link to images as appropriate (images should go to `docs/assets/themes/zeppelin/img/docs-img/`). And add a link to your documentation in the navigation menu (`docs/_includes/themes/zeppelin/_navigation.html`). - Most importantly, ensure licenses of the transitive closure of all dependencies are list in [license file](https://github.com/apache/zeppelin/blob/master/zeppelin-distribution/src/bin_license/LICENSE). - - Commit your changes and open a Pull Request on the project [Mirror on GitHub](https://github.com/apache/zeppelin); check to make sure Travis CI build is passing. + - Commit your changes and open a [Pull Request](https://github.com/apache/zeppelin/pulls) on the project [Mirror on GitHub](https://github.com/apache/zeppelin); check to make sure Travis CI build is passing. + \ No newline at end of file From 163691ce51296efb645aa8a295a5c9dda502e780 Mon Sep 17 00:00:00 2001 From: AhyoungRyu Date: Thu, 16 Jun 2016 19:42:46 -0700 Subject: [PATCH 06/24] Apply auto TOC to all of docs under docs/manual/ --- docs/manual/dynamicform.md | 22 ++--- docs/manual/dynamicinterpreterload.md | 25 +++--- docs/manual/interpreters.md | 22 +++-- docs/manual/notebookashomepage.md | 125 ++++++++++++-------------- docs/manual/publish.md | 15 ++-- 5 files changed, 106 insertions(+), 103 deletions(-) diff --git a/docs/manual/dynamicform.md b/docs/manual/dynamicform.md index 6594767efec..b554fec1127 100644 --- a/docs/manual/dynamicform.md +++ b/docs/manual/dynamicform.md @@ -19,16 +19,18 @@ limitations under the License. --> {% include JB/setup %} -## Dynamic Form +# Dynamic Form -Zeppelin dynamically creates input forms. Depending on language backend, there're two different ways to create dynamic form. +
    + +Apache Zeppelin dynamically creates input forms. Depending on language backend, there're two different ways to create dynamic form. Custom language backend can select which type of form creation it wants to use. -### Using form Templates +## Using form Templates This mode creates form using simple template language. It's simple and easy to use. For example Markdown, Shell, SparkSql language backend uses it. -#### Text input form +### Text input form To create text input form, use `${formName}` templates. @@ -42,7 +44,7 @@ Also you can provide default value, using `${formName=defaultValue}`. -#### Select form +### Select form To create select form, use `${formName=defaultValue,option1|option2...}` @@ -54,7 +56,7 @@ Also you can separate option's display name and value, using `${formName=default -#### Checkbox form +### Checkbox form For multi-selection, you can create a checkbox form using `${checkbox:formName=defaultValue1|defaultValue2...,option1|option2...}`. The variable will be substituted by a comma-separated string based on the selected items. For example: @@ -64,13 +66,13 @@ Besides, you can specify the delimiter using `${checkbox(delimiter):formName=... -### Creates Programmatically +## Creates Programmatically Some language backend uses programmatic way to create form. For example [ZeppelinContext](../interpreter/spark.html#zeppelincontext) provides form creation API Here're some examples. -####Text input form +### Text input form
    @@ -91,7 +93,7 @@ print("Hello "+z.input("name"))
    -####Text input form with default value +### Text input form with default value
    @@ -112,7 +114,7 @@ print("Hello "+z.input("name", "sun"))
    -####Select form +### Select form
    diff --git a/docs/manual/dynamicinterpreterload.md b/docs/manual/dynamicinterpreterload.md index 0794314b53d..42dd74df61f 100644 --- a/docs/manual/dynamicinterpreterload.md +++ b/docs/manual/dynamicinterpreterload.md @@ -19,12 +19,13 @@ limitations under the License. --> {% include JB/setup %} -## Dynamic Interpreter Loading using REST API +# Dynamic Interpreter Loading using REST API + +
    Zeppelin provides pluggable interpreter architecture which results in a wide and variety of the supported backend system. In this section, we will introduce **Dynamic interpreter loading** using **REST API**. This concept actually comes from [Zeppelin Helium Proposal](https://cwiki.apache.org/confluence/display/ZEPPELIN/Helium+proposal). Before we start, if you are not familiar with the concept of **Zeppelin interpreter**, you can check out [Overview of Zeppelin interpreter](../manual/interpreters.html) first. -
    ## Overview In the past, Zeppelin was loading interpreter binaries from `/interpreter/[interpreter_name]` directory. They were configured by `zeppelin.interpreters` property in `conf/zeppelin-site.xml` or `ZEPPELIN_INTERPRETERS` env variables in `conf/zeppelin-env.sh`. They were loaded on Zeppelin server startup and stayed alive until the server was stopped. In order to simplify using 3rd party interpreters, we changed this way to **dynamically** load interpreters from **Maven Repository** using **REST API**. Hopefully, the picture below will help you to understand the process. @@ -32,7 +33,7 @@ In order to simplify using 3rd party interpreters, we changed this way to **dyna ## Load & Unload Interpreters Using REST API -### 1. Load +### Load You can **load** interpreters located in Maven repository using REST API, like this: ( Maybe, you are unfamiliar with `[interpreter_group_name]` or `[interpreter_name]`. If so, please checkout [Interpreters in Zeppelin](../manual/interpreter.html) again. ) @@ -69,21 +70,21 @@ http://127.0.0.1:8080/api/interpreter/load/md/markdown The meaning of each parameters is: 1. **Artifact** - - groupId: org.apache.zeppelin - - artifactId: zeppelin-markdown - - version: 0.6.0-SNAPSHOT + - groupId: org.apache.zeppelin + - artifactId: zeppelin-markdown + - version: 0.6.0-SNAPSHOT 2. **Class Name** - - Package Name: org.apache.zeppelin - - Interpreter Class Name: markdown.Markdown + - Package Name: org.apache.zeppelin + - Interpreter Class Name: markdown.Markdown 3. **Repository ( optional )** - - Url: http://dl.bintray.com/spark-packages/maven - - Snapshot: false + - Url: http://dl.bintray.com/spark-packages/maven + - Snapshot: false > Please note: The interpreters you downloaded need to be **reload**, when your Zeppelin server is down. -### 2. Unload +### Unload If you want to **unload** the interpreters using REST API, ``` @@ -95,7 +96,7 @@ In this case, the Restful method will be **DELETE**. ## What is the next step after Loading ? ### Q1. Where is the location of interpreters you downloaded ? - + Actually, the answer about this question is in the above picture. Once the REST API is called, the `.jar` files of interpreters you get are saved under `ZEPPELIN_HOME/local-repo` first. Then, they will be copied to `ZEPPELIN_HOME/interpreter` directory. So, please checkout your `ZEPPELIN_HOME/interpreter`. ### Q2. Then, how can I use this interpreter ? diff --git a/docs/manual/interpreters.md b/docs/manual/interpreters.md index 488d5e9f28c..a21d34e81a7 100644 --- a/docs/manual/interpreters.md +++ b/docs/manual/interpreters.md @@ -19,7 +19,12 @@ limitations under the License. --> {% include JB/setup %} -## Interpreters in Zeppelin +# Interpreters in Apache Zeppelin + +
    + +## Overview + In this section, we will explain about the role of interpreters, interpreters group and interpreter settings in Zeppelin. The concept of Zeppelin interpreter allows any language/data-processing-backend to be plugged into Zeppelin. Currently, Zeppelin supports many interpreters such as Scala ( with Apache Spark ), Python ( with Apache Spark ), SparkSQL, JDBC, Markdown, Shell and so on. @@ -29,12 +34,12 @@ Zeppelin Interpreter is a plug-in which enables Zeppelin users to use a specific When you click the ```+Create``` button in the interpreter page, the interpreter drop-down list box will show all the available interpreters on your server. - + -## What is Zeppelin Interpreter Setting? +## What is interpreter setting? Zeppelin interpreter setting is the configuration of a given interpreter on Zeppelin server. For example, the properties are required for hive JDBC interpreter to connect to the Hive server. - + Properties are exported as environment variable when property name is consisted of upper characters, numbers and underscore ([A-Z_0-9]). Otherwise set properties as JVM property. @@ -44,14 +49,15 @@ Each notebook can be bound to multiple Interpreter Settings using setting icon o -## What is Zeppelin Interpreter Group? +## What is interpreter group? Every Interpreter is belonged to an **Interpreter Group**. Interpreter Group is a unit of start/stop interpreter. By default, every interpreter is belonged to a single group, but the group might contain more interpreters. For example, Spark interpreter group is including Spark support, pySpark, SparkSQL and the dependency loader. Technically, Zeppelin interpreters from the same group are running in the same JVM. For more information about this, please checkout [here](../development/writingzeppelininterpreter.html). Each interpreters is belonged to a single group and registered together. All of their properties are listed in the interpreter setting like below image. - + + ## Interpreter binding mode @@ -62,7 +68,7 @@ In 'shared' mode, every notebook bound to the Interpreter Setting will share the -## Connecting to the Existing Remote Interpreter +## Connecting to the existing remote interpreter Zeppelin users can start interpreter thread embedded in their service. This will provide flexibility to user to start interpreter on remote host. To start interpreter along with your service you have to create an instance of ``RemoteInterpreterServer`` and start it as follows: @@ -75,4 +81,4 @@ interpreter.start() The above code will start interpreter thread inside your process. Once the interpreter is started you can configure zeppelin to connect to RemoteInterpreter by checking **Connect to existing process** checkbox and then provide **Host** and **Port** on which interpreter porocess is listening as shown in the image below: - + diff --git a/docs/manual/notebookashomepage.md b/docs/manual/notebookashomepage.md index 48f06a6df45..f784263bfd7 100644 --- a/docs/manual/notebookashomepage.md +++ b/docs/manual/notebookashomepage.md @@ -19,91 +19,84 @@ limitations under the License. --> {% include JB/setup %} -## Customize your zeppelin homepage - Zeppelin allows you to use one of the notebooks you create as your zeppelin Homepage. - With that you can brand your zeppelin installation, - adjust the instruction to your users needs and even translate to other languages. +# Customize Apache Zeppelin homepage -
    -### How to set a notebook as your zeppelin homepage +
    -The process for creating your homepage is very simple as shown below: - - 1. Create a notebook using zeppelin - 2. Set the notebook id in the config file - 3. Restart zeppelin +Apache Zeppelin allows you to use one of the notebooks you create as your Zeppelin Homepage. +With that you can brand your Zeppelin installation, adjust the instruction to your users needs and even translate to other languages. -
    -#### Create a notebook using zeppelin - Create a new notebook using zeppelin, - you can use ```%md``` interpreter for markdown content or any other interpreter you like. +## How to set a notebook as your Zeppelin homepage - You can also use the display system to generate [text](../displaysystem/display.html), - [html](../displaysystem/display.html#html),[table](../displaysystem/table.html) or - [angular](../displaysystem/angular.html) +The process for creating your homepage is very simple as shown below: - Run (shift+Enter) the notebook and see the output. Optionally, change the notebook view to report to hide - the code sections. +1. Create a notebook using Zeppelin +2. Set the notebook id in the config file +3. Restart Zeppelin -
    -#### Set the notebook id in the config file - To set the notebook id in the config file you should copy it from the last word in the notebook url +### Create a notebook using Zeppelin +Create a new notebook using Zeppelin, +you can use ```%md``` interpreter for markdown content or any other interpreter you like. +You can also use the display system to generate [text](../displaysystem/basicdisplaysystem.html#text), [html](../displaysystem/basicdisplaysystem.html#html), [table](../displaysystem/basicdisplaysystem.html#table) or +Angular ([backend API](../displaysystem/back-end-angular.html), [frontend API](../displaysystem/front-end-angular.html)). - for example +Run (shift+Enter) the notebook and see the output. Optionally, change the notebook view to report to hide +the code sections. - +### Set the notebook id in the config file +To set the notebook id in the config file, you should copy it from the last word in the notebook url. +For example, - Set the notebook id to the ```ZEPPELIN_NOTEBOOK_HOMESCREEN``` environment variable - or ```zeppelin.notebook.homescreen``` property. + - You can also set the ```ZEPPELIN_NOTEBOOK_HOMESCREEN_HIDE``` environment variable - or ```zeppelin.notebook.homescreen.hide``` property to hide the new notebook from the notebook list. +Set the notebook id to the ```ZEPPELIN_NOTEBOOK_HOMESCREEN``` environment variable +or ```zeppelin.notebook.homescreen``` property. -
    -#### Restart zeppelin - Restart your zeppelin server +You can also set the ```ZEPPELIN_NOTEBOOK_HOMESCREEN_HIDE``` environment variable +or ```zeppelin.notebook.homescreen.hide``` property to hide the new notebook from the notebook list. - ``` - ./bin/zeppelin-deamon stop - ./bin/zeppelin-deamon start - ``` - ####That's it! Open your browser and navigate to zeppelin and see your customized homepage... +### Restart Zeppelin +Restart your Zeppelin server +``` +./bin/zeppelin-deamon stop +./bin/zeppelin-deamon start +``` +That's it! Open your browser and navigate to Zeppelin and see your customized homepage.
    -### Show notebooks list in your custom homepage -If you want to display the list of notebooks on your custom zeppelin homepage all +## Show notebooks list in your custom homepage +If you want to display the list of notebooks on your custom Zeppelin homepage all you need to do is use our %angular support. -
    - Add the following code to a paragraph in you home page and run it... walla! you have your notebooks list. - - ```javascript - println( - """%angular -
    -

    Notebooks

    - +Add the following code to a paragraph in you home page and run it... walla! you have your notebooks list. + +```javascript +println( +"""%angular +
    +

    Notebooks

    + - """) - ``` +
    +""") +``` - After running the notebook you will see output similar to this one: - +After running the notebook you will see output similar to this one: + - The main trick here relays in linking the ```
    ``` to the controller: +The main trick here relays in linking the ```
    ``` to the controller: - ```javascript -
    - ``` +```javascript +
    +``` - Once we have ```home``` as our controller variable in our ```
    ``` - we can use ```home.notes.list``` to get access to the notebook list. +Once we have ```home``` as our controller variable in our ```
    ``` +we can use ```home.notes.list``` to get access to the notebook list. diff --git a/docs/manual/publish.md b/docs/manual/publish.md index 1559fba2f8e..ca4d7cc18f4 100644 --- a/docs/manual/publish.md +++ b/docs/manual/publish.md @@ -19,13 +19,14 @@ limitations under the License. --> {% include JB/setup %} -## How can you publish your paragraph ? -Zeppelin provides a feature for publishing your notebook paragraph results. Using this feature, you can show Zeppelin notebook paragraph results in your own website. -It's very straightforward. Just use `