Elgato_dark/zeppelin
1
0
Fork 0
mirror of https://github.com/apache/zeppelin synced 2026-05-24 09:38:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge from master

Browse source
This commit is contained in:
Rajat Venkatesh 2016-01-20 18:01:22 +05:30
commit 0fdcfe63cb
123 changed files with 2762 additions and 891 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

77
.travis.yml
View file

@ -14,61 +14,46 @@
# limitations under the License.
language: java
jdk:
- oraclejdk7
matrix:
include:
# Test all modules
- jdk: "oraclejdk7"
env: SPARK_VER="1.6.0" HADOOP_VER="2.3" PROFILE="-Pspark-1.6 -Phadoop-2.3 -Ppyspark -Pscalding" BUILD_FLAG="package -Pbuild-distr" TEST_FLAG="verify -Pusing-packaged-distr"
# Test spark module for 1.5.2
- jdk: "oraclejdk7"
env: SPARK_VER="1.5.2" HADOOP_VER="2.3" PROFILE="-Pspark-1.5 -Phadoop-2.3 -Ppyspark" BUILD_FLAG="package -DskipTests" TEST_FLAG="verify"
# Test spark module for 1.4.1
- jdk: "oraclejdk7"
env: SPARK_VER="1.4.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.4 -Phadoop-2.3 -Ppyspark" BUILD_FLAG="package -DskipTests" TEST_FLAG="verify"
# Test spark module for 1.3.1
- jdk: "oraclejdk7"
env: SPARK_VER="1.3.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.3 -Phadoop-2.3 -Ppyspark" BUILD_FLAG="package -DskipTests" TEST_FLAG="verify"
# Test spark module for 1.2.1
- jdk: "oraclejdk7"
env: SPARK_VER="1.2.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.2 -Phadoop-2.3 -Ppyspark" BUILD_FLAG="package -DskipTests" TEST_FLAG="verify"
# Test spark module for 1.1.1
- jdk: "oraclejdk7"
env: SPARK_VER="1.1.1" HADOOP_VER="2.3" PROFILE="-Pspark-1.1 -Phadoop-2.3 -Ppyspark" BUILD_FLAG="package -DskipTests" TEST_FLAG="verify"
before_install:
- "export DISPLAY=:99.0"
- "sh -e /etc/init.d/xvfb start"
install:
- mvn package -DskipTests -Pspark-1.6 -Phadoop-2.3 -Ppyspark -Pscalding -B
- mvn $BUILD_FLAG $PROFILE -B
before_script:
-
- ./testing/startSparkCluster.sh $SPARK_VER $HADOOP_VER
- echo "export SPARK_HOME=`pwd`/spark-$SPARK_VER-bin-hadoop$HADOOP_VER" > conf/zeppelin-env.sh
script:
# spark 1.6
- mvn package -Pbuild-distr -Pspark-1.6 -Phadoop-2.3 -Ppyspark -Pscalding -B
- ./testing/startSparkCluster.sh 1.6.0 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.6.0-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn verify -Pusing-packaged-distr -Pspark-1.6 -Phadoop-2.3 -Ppyspark -Pscalding -B
- ./testing/stopSparkCluster.sh 1.6.0 2.3
# spark 1.5
- rm -rf `pwd`/interpreter/spark
- mvn package -DskipTests -Pspark-1.5 -Phadoop-2.3 -Ppyspark -B -pl 'zeppelin-interpreter,spark-dependencies,spark'
- ./testing/startSparkCluster.sh 1.5.2 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.5.2-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn package -Pspark-1.5 -Phadoop-2.3 -B -pl 'zeppelin-interpreter,zeppelin-zengine,zeppelin-server' -Dtest=org.apache.zeppelin.rest.*Test -DfailIfNoTests=false
- ./testing/stopSparkCluster.sh 1.5.2 2.3
# spark 1.4
- rm -rf `pwd`/interpreter/spark
- mvn package -DskipTests -Pspark-1.4 -Phadoop-2.3 -Ppyspark -B -pl 'zeppelin-interpreter,spark-dependencies,spark'
- ./testing/startSparkCluster.sh 1.4.1 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.4.1-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn package -Pspark-1.4 -Phadoop-2.3 -B -pl 'zeppelin-interpreter,zeppelin-zengine,zeppelin-server' -Dtest=org.apache.zeppelin.rest.*Test -DfailIfNoTests=false
- ./testing/stopSparkCluster.sh 1.4.1 2.3
# spark 1.3
- rm -rf `pwd`/interpreter/spark
- mvn package -DskipTests -Pspark-1.3 -Phadoop-2.3 -Ppyspark -B -pl 'zeppelin-interpreter,spark-dependencies,spark'
- ./testing/startSparkCluster.sh 1.3.1 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.3.1-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn package -Pspark-1.3 -Phadoop-2.3 -B -pl 'zeppelin-interpreter,zeppelin-zengine,zeppelin-server' -Dtest=org.apache.zeppelin.rest.*Test -DfailIfNoTests=false
- ./testing/stopSparkCluster.sh 1.3.1 2.3
# spark 1.2
- rm -rf `pwd`/interpreter/spark
- mvn package -Pspark-1.2 -Phadoop-2.3 -Ppyspark -B -pl 'zeppelin-interpreter,spark-dependencies,spark'
- ./testing/startSparkCluster.sh 1.2.1 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.2.1-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn package -Pspark-1.2 -Phadoop-2.3 -B -pl 'zeppelin-interpreter,zeppelin-zengine,zeppelin-server' -Dtest=org.apache.zeppelin.rest.*Test -DfailIfNoTests=false
- ./testing/stopSparkCluster.sh 1.2.1 2.3
# spark 1.1
- rm -rf `pwd`/interpreter/spark
- mvn package -Pspark-1.1 -Phadoop-2.3 -Ppyspark -B -pl 'zeppelin-interpreter,spark-dependencies,spark'
- ./testing/startSparkCluster.sh 1.1.1 2.3
- echo "export SPARK_HOME=`pwd`/spark-1.1.1-bin-hadoop2.3" > conf/zeppelin-env.sh
- mvn package -Pspark-1.1 -Phadoop-2.3 -B -pl 'zeppelin-interpreter,zeppelin-zengine,zeppelin-server' -Dtest=org.apache.zeppelin.rest.*Test -DfailIfNoTests=false
- ./testing/stopSparkCluster.sh 1.1.1 2.3
- mvn $TEST_FLAG $PROFILE -B
after_failure:
- cat target/rat.txt
@ -77,7 +62,7 @@ after_failure:
- cat zeppelin-distribution/target/zeppelin-*-SNAPSHOT/zeppelin-*-SNAPSHOT/logs/zeppelin*.out
after_script:
-
- ./testing/stopSparkCluster.sh $SPARK_VER $HADOOP_VER
notifications:
slack:

16
CONTRIBUTING.md
View file

@ -68,7 +68,8 @@ Here are some things you will need to build and test Zeppelin.
### Software Configuration Management (SCM)
Zeppelin uses Git for its SCM system. Hosted by github.com. `https://github.com/apache/incubator-zeppelin` you'll need git client installed in your development machine.
Zeppelin uses Git for its SCM system. `http://git.apache.org/incubator-zeppelin.git` you'll need git client installed in your development machine.
For write access, `https://git-wip-us.apache.org/repos/asf/incubator-zeppelin.git`
### Integrated Development Environment (IDE)
@ -114,26 +115,31 @@ To build the code, install
* Apache Maven
## Getting the source code
First of all, you need the Zeppelin source code. The official location for Zeppelin is [https://github.com/apache/incubator-zeppelin](https://github.com/apache/incubator-zeppelin)
First of all, you need the Zeppelin source code. The official location for Zeppelin is [http://git.apache.org/incubator-zeppelin.git](http://git.apache.org/incubator-zeppelin.git).
### git access
Get the source code on your development machine using git.
```
git clone git@github.com:apache/incubator-zeppelin.git zeppelin
git clone http://git.apache.org/incubator-zeppelin.git zeppelin
```
You may also want to develop against a specific release. For example, for branch-0.1
```
git clone -b branch-0.1 git@github.com:apache/incubator-zeppelin.git zeppelin
git clone -b branch-0.1 http://git.apache.org/incubator-zeppelin.git zeppelin
```
or with write access
```
git clone https://git-wip-us.apache.org/repos/asf/incubator-zeppelin.git
```
### Fork repository
If you want not only build Zeppelin but also make change, then you need fork Zeppelin repository and make pull request.
If you want not only build Zeppelin but also make change, then you need fork Zeppelin github mirror repository (https://github.com/apache/incubator-zeppelin) and make pull request.
## Build

3
README.md
View file

@ -1,6 +1,6 @@
#Zeppelin
**Documentation:** [User Guide](http://zeppelin.incubator.apache.org/docs/index.html)<br/>
**Documentation:** [User Guide](http://zeppelin.incubator.apache.org/docs/latest/index.html)<br/>
**Mailing Lists:** [User and Dev mailing list](http://zeppelin.incubator.apache.org/community.html)<br/>
**Continuous Integration:** [![Build Status](https://secure.travis-ci.org/apache/incubator-zeppelin.png?branch=master)](https://travis-ci.org/apache/incubator-zeppelin) <br/>
**Contributing:** [Contribution Guide](https://github.com/apache/incubator-zeppelin/blob/master/CONTRIBUTING.md)<br/>
@ -45,6 +45,7 @@ sudo ln -s /usr/local/apache-maven-3.3.3/bin/mvn /usr/local/bin/mvn
_Notes:_
- Ensure node is installed by running `node --version`
- Ensure maven is running version 3.1.x or higher with `mvn -version`
- Configure maven to use more memory than usual by ```export MAVEN_OPTS="-Xmx2g -XX:MaxPermSize=1024m"```
### Build
If you want to build Zeppelin from the source, please first clone this repository, then:

43
SECURITY-README.md Normal file
View file

@ -0,0 +1,43 @@
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
# Shiro Authentication
To connect to Zeppelin, users will be asked to enter their credentials. Once logged, a user has access to all notes including other users notes.
This a a first step toward full security as implemented by this pull request (https://github.com/apache/incubator-zeppelin/pull/53).
# Security setup
1. Secure the HTTP channel: Comment the line "/** = anon" and uncomment the line "/** = authcBasic" in the file conf/shiro.ini. Read more about he shiro.ini file format at the following URL http://shiro.apache.org/configuration.html#Configuration-INISections.
2. Secure the Websocket channel : Set to property "zeppelin.anonymous.allowed" to "false" in the file conf/zeppelin-site.xml. You can start by renaming conf/zeppelin-site.xml.template to conf/zeppelin-site.xml
3. Start Zeppelin : bin/zeppelin.sh
4. point your browser to http://localhost:8080
5. Login using one of the user/password combinations defined in the conf/shiro.ini file.
# Implementation notes
## Vocabulary
username, owner and principal are used interchangeably to designate the currently authenticated user
## What are we securing ?
Zeppelin is basically a web application that spawn remote interpreters to run commands and return HTML fragments to be displayed on the user browser.
The scope of this PR is to require credentials to access Zeppelin. To achieve this, we use Apache Shiro.
## HTTP Endpoint security
Apache Shiro sits as a servlet filter between the browser and the exposed services and handles the required authentication without any programming required. (See Apache Shiro for more info).
## Websocket security
Securing the HTTP endpoints is not enough, since Zeppelin also communicates with the browser through websockets. To secure this channel, we take the following approach:
1. The browser on startup requests a ticket through HTTP
2. The Apache Shiro Servlet filter handles the user auth
3. Once the user is authenticated, a ticket is assigned to this user and the ticket is returned to the browser
All websockets communications require the username and ticket to be submitted by the browser. Upon receiving a websocket message, the server checks that the ticket received is the one assigned to the username through the HTTP request (step 3 above).

3
bin/zeppelin-daemon.sh
View file

@ -67,6 +67,9 @@ if [[ -d "${ZEPPELIN_HOME}/zeppelin-server/target/classes" ]]; then
ZEPPELIN_CLASSPATH+=":${ZEPPELIN_HOME}/zeppelin-server/target/classes"
fi
# Add jdbc connector jar
# ZEPPELIN_CLASSPATH+=":${ZEPPELIN_HOME}/jdbc/jars/jdbc-connector-jar"
addJarInDir "${ZEPPELIN_HOME}"
addJarInDir "${ZEPPELIN_HOME}/lib"
addJarInDir "${ZEPPELIN_HOME}/zeppelin-interpreter/target/lib"

38
conf/shiro.ini Normal file
View file

@ -0,0 +1,38 @@
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
[users]
# List of users with their password allowed to access Zeppelin.
# To use a different strategy (LDAP / Database / ...) check the shiro doc at http://shiro.apache.org/configuration.html#Configuration-INISections
admin = password1
user1 = password2
user2 = password3
# Sample LDAP configuration, for user Authentication, currently tested for single Realm
[main]
#ldapRealm = org.apache.shiro.realm.ldap.JndiLdapRealm
#ldapRealm.userDnTemplate = cn={0},cn=engg,ou=testdomain,dc=testdomain,dc=com
#ldapRealm.contextFactory.url = ldap://ldaphost:389
#ldapRealm.contextFactory.authenticationMechanism = SIMPLE
[urls]
# anon means the access is anonymous.
# authcBasic means Basic Auth Security
# To enfore security, comment the line below and uncomment the next one
/** = anon
#/** = authcBasic

8
conf/zeppelin-site.xml.template
View file

@ -105,7 +105,7 @@
<property>
<name>zeppelin.interpreters</name>
<value>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.angular.AngularInterpreter,org.apache.zeppelin.shell.ShellInterpreter,org.apache.zeppelin.hive.HiveInterpreter,org.apache.zeppelin.tajo.TajoInterpreter,org.apache.zeppelin.flink.FlinkInterpreter,org.apache.zeppelin.lens.LensInterpreter,org.apache.zeppelin.ignite.IgniteInterpreter,org.apache.zeppelin.ignite.IgniteSqlInterpreter,org.apache.zeppelin.cassandra.CassandraInterpreter,org.apache.zeppelin.geode.GeodeOqlInterpreter,org.apache.zeppelin.postgresql.PostgreSqlInterpreter,org.apache.zeppelin.phoenix.PhoenixInterpreter,org.apache.zeppelin.kylin.KylinInterpreter,org.apache.zeppelin.elasticsearch.ElasticsearchInterpreter,org.apache.zeppelin.scalding.ScaldingInterpreter,org.apache.zeppelin.hbase.HbaseInterpreter</value>
<value>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.angular.AngularInterpreter,org.apache.zeppelin.shell.ShellInterpreter,org.apache.zeppelin.hive.HiveInterpreter,org.apache.zeppelin.tajo.TajoInterpreter,org.apache.zeppelin.flink.FlinkInterpreter,org.apache.zeppelin.lens.LensInterpreter,org.apache.zeppelin.ignite.IgniteInterpreter,org.apache.zeppelin.ignite.IgniteSqlInterpreter,org.apache.zeppelin.cassandra.CassandraInterpreter,org.apache.zeppelin.geode.GeodeOqlInterpreter,org.apache.zeppelin.postgresql.PostgreSqlInterpreter,org.apache.zeppelin.jdbc.JDBCInterpreter,org.apache.zeppelin.phoenix.PhoenixInterpreter,org.apache.zeppelin.kylin.KylinInterpreter,org.apache.zeppelin.elasticsearch.ElasticsearchInterpreter,org.apache.zeppelin.scalding.ScaldingInterpreter,org.apache.zeppelin.hbase.HbaseInterpreter</value>
<description>Comma separated interpreter configurations. First interpreter become a default</description>
</property>
@ -180,5 +180,11 @@
<description>Allowed sources for REST and WebSocket requests (i.e. http://onehost:8080,http://otherhost.com). If you leave * you are vulnerable to https://issues.apache.org/jira/browse/ZEPPELIN-173</description>
</property>
<property>
<name>zeppelin.anonymous.allowed</name>
<value>true</value>
<description>Anonymous user allowed by default</description>
</property>
</configuration>

2
dev/create_release.sh
View file

@ -125,7 +125,7 @@ function make_binary_release() {
rm -rf ${WORKING_DIR}/zeppelin-${RELEASE_NAME}-bin-${BIN_RELEASE_NAME}
}
make_binary_release all "-Pspark-1.5 -Phadoop-2.4 -Pyarn -Ppyspark"
make_binary_release all "-Pspark-1.6 -Phadoop-2.4 -Pyarn -Ppyspark"
# remove non release files and dirs
rm -rf ${WORKING_DIR}/zeppelin

1
docs/_includes/themes/zeppelin/_navigation.html
View file

@ -37,6 +37,7 @@
<a href="#" data-toggle="dropdown" class="dropdown-toggle">Interpreter <b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="{{BASE_PATH}}/manual/interpreters.html">Overview</a></li>
<li><a href="{{BASE_PATH}}/manual/dynamicinterpreterload.html">Dynamic Interpreter Loading</a></li>
<li role="separator" class="divider"></li>
<li><a href="{{BASE_PATH}}/interpreter/cassandra.html">Cassandra</a></li>
<li><a href="{{BASE_PATH}}/interpreter/elasticsearch.html">Elasticsearch</a></li>

BIN
docs/assets/themes/zeppelin/img/docs-img/interpreter_binding_1.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 322 KiB

BIN
docs/assets/themes/zeppelin/img/docs-img/interpreter_binding_2.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 298 KiB

BIN
docs/assets/themes/zeppelin/img/docs-img/interpreter_setting_1.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 396 KiB

BIN
docs/assets/themes/zeppelin/img/docs-img/interpreter_setting_2.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 146 KiB

BIN
docs/assets/themes/zeppelin/img/docs-img/interpreter_setting_3.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 257 KiB

BIN
docs/assets/themes/zeppelin/img/docs-img/zeppelin_user.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 325 KiB

46
docs/development/writingzeppelininterpreter.md
View file

@ -32,10 +32,8 @@ All Interpreters in the same interpreter group are launched in a single, separat
### Make your own Interpreter
Creating a new interpreter is quite simple. Just extend [org.apache.zeppelin.interpreter](https://github.com/apache/incubator-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.
Your interpreter name is derived from the static register method
You can include `org.apache.zeppelin:zeppelin-interpreter:[VERSION]` artifact in your build system.
Your interpreter name is derived from the static register method.
```
static {
@ -44,16 +42,15 @@ static {
```
The name will appear later in the interpreter name option box during the interpreter configuration process.
The name of the interpreter is what you later write to identify a paragraph which should be interpreted using this interpreter.
```
%MyInterpreterName
some interpreter spesific code...
some interpreter specific code...
```
### Install your interpreter binary
Once you have build your interpreter, you can place your interpreter under directory with all the dependencies.
Once you have built your interpreter, you can place it under the interpreter directory with all its dependencies.
```
[ZEPPELIN_HOME]/interpreter/[INTERPRETER_NAME]/
@ -63,33 +60,34 @@ Once you have build your interpreter, you can place your interpreter under direc
To configure your interpreter you need to follow these steps:
1. create conf/zeppelin-site.xml by copying conf/zeppelin-site.xml.template to conf/zeppelin-site.xml
1. Add your interpreter class name to the zeppelin.interpreters property in `conf/zeppelin-site.xml`.
2. Add your interpreter class name to the zeppelin.interpreters property in conf/zeppelin-site.xml
Property value is comma separated [INTERPRETER_CLASS_NAME]
for example,
Property value is comma separated [INTERPRETER\_CLASS\_NAME].
For example,
```
```
<property>
<name>zeppelin.interpreters</name>
<value>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</value>
</property>
```
3. start zeppelin by running ```./bin/zeppelin-deamon start```
4. in the interpreter page, click the +Create button and configure your interpreter properties.
2. Add your interpreter to the [default configuration](https://github.com/apache/incubator-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`.
3. Start Zeppelin by running `./bin/zeppelin-daemon.sh start`.
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 shipped with zeppelin have a [default configuration](https://github.com/apache/incubator-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.
Note that the interpreters shipped with zeppelin have a [default configuration](https://github.com/apache/incubator-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
#### 0.5.0
Inside of a notebook, %[INTERPRETER_NAME] directive will call your interpreter.
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.
for example
For example,
```
%myintp
@ -100,16 +98,14 @@ println(a)
<br />
#### 0.6.0 and later
Inside of a notebook, %[INTERPRETER\_GROUP].[INTERPRETER\_NAME] directive will call your interpreter.
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.
You can omit either [INTERPRETER\_GROUP] or [INTERPRETER\_NAME]. Omit [INTERPRETER\_NAME] selects first available interpreter in the [INTERPRETER\_GROUP].
Omit '[INTERPRETER\_GROUP]' will selects [INTERPRETER\_NAME] from default interpreter group.
You can omit either [INTERPRETER\_GROUP] or [INTERPRETER\_NAME]. If you omit [INTERPRETER\_NAME], then first available interpreter will be selected in the [INTERPRETER\_GROUP].
Likewise, if you skip [INTERPRETER\_GROUP], then [INTERPRETER\_NAME] will be chosen from default interpreter group.
For example, if you have two interpreter myintp1 and myintp2 in group mygrp,
you can call myintp1 like
For example, if you have two interpreter myintp1 and myintp2 in group mygrp, you can call myintp1 like
```
%mygrp.myintp1
@ -125,7 +121,7 @@ and you can call myintp2 like
codes for myintp2
```
If you omit your interpreter name, it'll selects first available interpreter in the group (myintp1)
If you omit your interpreter name, it'll select first available interpreter in the group ( myintp1 ).
```
%mygrp

2
docs/index.md
View file

@ -117,7 +117,7 @@ This way, you can easily embed it as an iframe inside of your website.</p>
<br />
### 100% Opensource
Apache Zeppelin (incubating) is Apache2 Licensed software. Please check out the [source repository](https://github.com/apache/incubator-zeppelin) and [How to contribute](./development/howtocontribute.html)
Apache Zeppelin (incubating) is Apache2 Licensed software. Please check out the [source repository](http://git.apache.org/incubator-zeppelin.git) and [How to contribute](./development/howtocontribute.html)
Zeppelin has a very active development community.
Join the [Mailing list](./community.html) and report issues on our [Issue tracker](https://issues.apache.org/jira/browse/ZEPPELIN).

193
docs/interpreter/cassandra.md
View file

@ -6,10 +6,8 @@ group: manual
---
{% include JB/setup %}
<hr/>
## 1. Cassandra CQL Interpreter for Apache Zeppelin
<br/>
<table class="table-configuration">
<tr>
<th>Name</th>
@ -23,35 +21,32 @@ group: manual
</tr>
</table>
<hr/>
## 2. Enabling Cassandra Interpreter
In a notebook, to enable the **Cassandra** interpreter, click on the **Gear** icon and select **Cassandra**
In a notebook, to enable the **Cassandra** interpreter, click on the **Gear** icon and select **Cassandra**.
<center>
![Interpreter Binding](../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterBinding.png)
![Interpreter Selection](../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterSelection.png)
<center>
<img src="../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterBinding.png" width="25%" height="25%">
<br>
<img src="../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterSelection.png" width="25%" height="25%">
</center>
<hr/>
## 3. Using the Cassandra Interpreter
In a paragraph, use **_%cassandra_** to select the **Cassandra** interpreter and then input all commands.
To access the interactive help, type **HELP;**
To access the interactive help, type `HELP;`
<center>
![Interactive Help](../assets/themes/zeppelin/img/docs-img/cassandra-InteractiveHelp.png)
<center>
<img src="../assets/themes/zeppelin/img/docs-img/cassandra-InteractiveHelp.png" width="50%" height="50%">
</center>
<hr/>
## 4. Interpreter Commands
The **Cassandra** interpreter accepts the following commands
The **Cassandra** interpreter accepts the following commands.
<center>
<table class="table-configuration">
@ -85,10 +80,9 @@ group: manual
<td>All CQL-compatible statements (SELECT, INSERT, CREATE ...)</td>
<td>All CQL statements are executed directly against the Cassandra server</td>
</tr>
</table>
</table>
</center>
<hr/>
## 5. CQL statements
This interpreter is compatible with any CQL statement supported by Cassandra. Ex:
@ -97,7 +91,7 @@ This interpreter is compatible with any CQL statement supported by Cassandra. Ex
INSERT INTO users(login,name) VALUES('jdoe','John DOE');
SELECT * FROM users WHERE login='jdoe';
```
```
Each statement should be separated by a semi-colon ( **;** ) except the special commands below:
@ -149,7 +143,7 @@ This means that the following statements are equivalent and valid:
```
The complete list of all CQL statements and versions can be found below:
<center>
<center>
<table class="table-configuration">
<tr>
<th>Cassandra Version</th>
@ -163,7 +157,7 @@ The complete list of all CQL statements and versions can be found below:
http://docs.datastax.com/en/cql/3.3/cql/cqlIntro.html
</a>
</td>
</tr>
</tr>
<tr>
<td><strong>2.1 & 2.0</strong></td>
<td>
@ -172,7 +166,7 @@ The complete list of all CQL statements and versions can be found below:
http://docs.datastax.com/en/cql/3.1/cql/cql_intro_c.html
</a>
</td>
</tr>
</tr>
<tr>
<td><strong>1.2</strong></td>
<td>
@ -181,11 +175,10 @@ The complete list of all CQL statements and versions can be found below:
http://docs.datastax.com/en/cql/3.0/cql/aboutCQL.html
</a>
</td>
</tr>
</tr>
</table>
</center>
<hr/>
## 6. Comments in statements
@ -203,21 +196,19 @@ It is possible to add comments between statements. Single line comments start wi
Insert into users(login,name) vAlues('hsue','Helen SUE');
```
<hr/>
## 7. Syntax Validation
The interpreters is shipped with a built-in syntax validator. This validator only checks for basic syntax errors.
All CQL-related syntax validation is delegated directly to **Cassandra**
All CQL-related syntax validation is delegated directly to **Cassandra**.
Most of the time, syntax errors are due to **missing semi-colons** between statements or **typo errors**.
<hr/>
## 8. Schema commands
To make schema discovery easier and more interactive, the following commands are supported:
<center>
<center>
<table class="table-configuration">
<tr>
<th>Command</th>
@ -226,67 +217,65 @@ To make schema discovery easier and more interactive, the following commands are
<tr>
<td><strong>DESCRIBE CLUSTER;</strong></td>
<td>Show the current cluster name and its partitioner</td>
</tr>
</tr>
<tr>
<td><strong>DESCRIBE KEYSPACES;</strong></td>
<td>List all existing keyspaces in the cluster and their configuration (replication factor, durable write ...)</td>
</tr>
</tr>
<tr>
<td><strong>DESCRIBE TABLES;</strong></td>
<td>List all existing keyspaces in the cluster and for each, all the tables name</td>
</tr>
</tr>
<tr>
<td><strong>DESCRIBE TYPES;</strong></td>
<td>List all existing user defined types in the <strong>current (logged) keyspace</strong></td>
</tr>
</tr>
<tr>
<td nowrap><strong>DESCRIBE FUNCTIONS &lt;keyspace_name&gt;;</strong></td>
<td>List all existing user defined functions in the given keyspace</td>
</tr>
</tr>
<tr>
<td nowrap><strong>DESCRIBE AGGREGATES &lt;keyspace_name&gt;;</strong></td>
<td>List all existing user defined aggregates in the given keyspace</td>
</tr>
</tr>
<tr>
<td nowrap><strong>DESCRIBE KEYSPACE &lt;keyspace_name&gt;;</strong></td>
<td>Describe the given keyspace configuration and all its table details (name, columns, ...)</td>
</tr>
<td>Describe the given keyspace configuration and all its table details (name, columns, ...)</td>
</tr>
<tr>
<td nowrap><strong>DESCRIBE TABLE (&lt;keyspace_name&gt;).&lt;table_name&gt;;</strong></td>
<td>
Describe the given table. If the keyspace is not provided, the current logged in keyspace is used.
If there is no logged in keyspace, the default system keyspace is used.
If no table is found, an error message is raised
If no table is found, an error message is raised.
</td>
</tr>
</tr>
<tr>
<td nowrap><strong>DESCRIBE TYPE (&lt;keyspace_name&gt;).&lt;type_name&gt;;</strong></td>
<td>
Describe the given type(UDT). If the keyspace is not provided, the current logged in keyspace is used.
If there is no logged in keyspace, the default system keyspace is used.
If no type is found, an error message is raised
If no type is found, an error message is raised.
</td>
</tr>
</tr>
<tr>
<td nowrap><strong>DESCRIBE FUNCTION (&lt;keyspace_name&gt;).&lt;function_name&gt;;</strong></td>
<td>Describe the given user defined function. The keyspace is optional</td>
</tr>
<td>Describe the given user defined function. The keyspace is optional.</td>
</tr>
<tr>
<td nowrap><strong>DESCRIBE AGGREGATE (&lt;keyspace_name&gt;).&lt;aggregate_name&gt;;</strong></td>
<td>Describe the given user defined aggregate. The keyspace is optional</td>
</tr>
<td>Describe the given user defined aggregate. The keyspace is optional.</td>
</tr>
</table>
</center>
</center>
The schema objects (cluster, keyspace, table, type, function and aggregate) are displayed in a tabular format.
There is a drop-down menu on the top left corner to expand objects details. On the top right menu is shown the Icon legend.
<br/>
<center>
![Describe Schema](../assets/themes/zeppelin/img/docs-img/cassandra-DescribeSchema.png)
</center>
<hr/>
## 9. Runtime Parameters
@ -294,8 +283,7 @@ Sometimes you want to be able to pass runtime query parameters to your statement
Those parameters are not part of the CQL specs and are specific to the interpreter.
Below is the list of all parameters:
<br/>
<center>
<center>
<table class="table-configuration">
<tr>
<th>Parameter</th>
@ -305,38 +293,37 @@ Below is the list of all parameters:
<tr>
<td nowrap>Consistency Level</td>
<td><strong>@consistency=<em>value</em></strong></td>
<td>Apply the given consistency level to all queries in the paragraph</td>
<td>Apply the given consistency level to all queries in the paragraph.</td>
</tr>
<tr>
<td nowrap>Serial Consistency Level</td>
<td><strong>@serialConsistency=<em>value</em></strong></td>
<td>Apply the given serial consistency level to all queries in the paragraph</td>
<td>Apply the given serial consistency level to all queries in the paragraph.</td>
</tr>
<tr>
<td nowrap>Timestamp</td>
<td><strong>@timestamp=<em>long value</em></strong></td>
<td>
Apply the given timestamp to all queries in the paragraph.
Please note that timestamp value passed directly in CQL statement will override this value
Please note that timestamp value passed directly in CQL statement will override this value.
</td>
</tr>
<tr>
<td nowrap>Retry Policy</td>
<td><strong>@retryPolicy=<em>value</em></strong></td>
<td>Apply the given retry policy to all queries in the paragraph</td>
<td>Apply the given retry policy to all queries in the paragraph.</td>
</tr>
<tr>
<td nowrap>Fetch Size</td>
<td><strong>@fetchSize=<em>integer value</em></strong></td>
<td>Apply the given fetch size to all queries in the paragraph</td>
<td>Apply the given fetch size to all queries in the paragraph.</td>
</tr>
</table>
</center>
Some parameters only accept restricted values:
<br/>
<center>
<center>
<table class="table-configuration">
<tr>
<th>Parameter</th>
@ -344,11 +331,11 @@ Below is the list of all parameters:
</tr>
<tr>
<td nowrap>Consistency Level</td>
<td><strong>ALL, ANY, ONE, TWO, THREE, QUORUM, LOCAL_ONE, LOCAL_QUORUM, EACH_QUORUM</strong></td>
<td><strong>ALL, ANY, ONE, TWO, THREE, QUORUM, LOCAL\_ONE, LOCAL\_QUORUM, EACH\_QUORUM</strong></td>
</tr>
<tr>
<td nowrap>Serial Consistency Level</td>
<td><strong>SERIAL, LOCAL_SERIAL</strong></td>
<td><strong>SERIAL, LOCAL\_SERIAL</strong></td>
</tr>
<tr>
<td nowrap>Timestamp</td>
@ -356,7 +343,7 @@ Below is the list of all parameters:
</tr>
<tr>
<td nowrap>Retry Policy</td>
<td><strong>DEFAULT, DOWNGRADING_CONSISTENCY, FALLTHROUGH, LOGGING_DEFAULT, LOGGING_DOWNGRADING, LOGGING_FALLTHROUGH</strong></td>
<td><strong>DEFAULT, DOWNGRADING\_CONSISTENCY, FALLTHROUGH, LOGGING\_DEFAULT, LOGGING\_DOWNGRADING, LOGGING\_FALLTHROUGH</strong></td>
</tr>
<tr>
<td nowrap>Fetch Size</td>
@ -365,7 +352,7 @@ Below is the list of all parameters:
</table>
</center>
>Please note that you should **not** add semi-colon ( **;** ) at the end of each parameter statement
>Please note that you should **not** add semi-colon ( **;** ) at the end of each parameter statement.
Some examples:
@ -395,12 +382,11 @@ Some examples:
Some remarks about query parameters:
> 1. **many** query parameters can be set in the same paragraph
> 2. if the **same** query parameter is set many time with different values, the interpreter only take into account the first value
> 3. each query parameter applies to **all CQL statements** in the same paragraph, unless you override the option using plain CQL text (like forcing timestamp with the USING clause)
> 4. the order of each query parameter with regard to CQL statement does not matter
> 1. **Many** query parameters can be set in the same paragraph.
> 2. If the **same** query parameter is set many time with different values, the interpreter only take into account the first value.
> 3. Each query parameter applies to **all CQL statements** in the same paragraph, unless you override the option using plain CQL text. ( Like forcing timestamp with the USING clause )
> 4. The order of each query parameter with regard to CQL statement does not matter.
<hr/>
## 10. Support for Prepared Statements
@ -424,17 +410,15 @@ Example:
@remove_prepare[statement_name]
```
<br/>
#### a. @prepare
<br/>
You can use the syntax _"@prepare[statement_name]=SELECT ..."_ to create a prepared statement.
The _statement_name_ is **mandatory** because the interpreter prepares the given statement with the Java driver and
saves the generated prepared statement in an **internal hash map**, using the provided _statement_name_ as search key.
You can use the syntax `@prepare[statement_name]=SELECT ...` to create a prepared statement.
The `statement_name` is **mandatory** because the interpreter prepares the given statement with the Java driver and
saves the generated prepared statement in an **internal hash map**, using the provided `statement_name` as search key.
> Please note that this internal prepared statement map is shared with **all notebooks** and **all paragraphs** because
there is only one instance of the interpreter for Cassandra
there is only one instance of the interpreter for Cassandra.
> If the interpreter encounters **many** @prepare for the **same _statement_name_ (key)**, only the **first** statement will be taken into account.
> If the interpreter encounters **many** @prepare for the **same statement_name (key)**, only the **first** statement will be taken into account.
Example:
@ -443,37 +427,36 @@ Example:
@prepare[select]=SELECT * FROM spark_demo.albums LIMIT ?
@prepare[select]=SELECT * FROM spark_demo.artists LIMIT ?
```
```
For the above example, the prepared statement is _SELECT * FROM spark_demo.albums LIMIT ?_.
_SELECT * FROM spark_demo.artists LIMIT ?_ is ignored because an entry already exists in the prepared statements map with the key select.
For the above example, the prepared statement is `SELECT * FROM spark_demo.albums LIMIT ?`.
`SELECT * FROM spark_demo.artists LIMIT ?` is ignored because an entry already exists in the prepared statements map with the key select.
In the context of **Zeppelin**, a notebook can be scheduled to be executed at regular interval,
thus it is necessary to **avoid re-preparing many time the same statement (considered an anti-pattern)**.
<br/>
<br/>
#### b. @bind
<br/>
Once the statement is prepared (possibly in a separated notebook/paragraph). You can bind values to it:
Once the statement is prepared ( possibly in a separated notebook/paragraph ). You can bind values to it:
```
@bind[select_first]=10
```
```
Bound values are not mandatory for the **@bind** statement. However if you provide bound values, they need to comply to some syntax:
Bound values are not mandatory for the `@bind` statement. However if you provide bound values, they need to comply to some syntax:
* String values should be enclosed between simple quotes ( ‘ )
* Date values should be enclosed between simple quotes ( ‘ ) and respect the formats:
1. yyyy-MM-dd HH:MM:ss
2. yyyy-MM-dd HH:MM:ss.SSS
* **null** is parsed as-is
* **boolean** (true|false) are parsed as-is
* **null** is parsed as-is.
* **boolean** (true|false) is parsed as-is.
* collection values must follow the **[standard CQL syntax]**:
* list: [‘list_item1’, ’list_item2’, ...]
* set: {‘set_item1’, ‘set_item2’, …}
* map: {‘key1’: ‘val1’, ‘key2’: ‘val2’, …}
* **tuple** values should be enclosed between parenthesis (see **[Tuple CQL syntax]**): (‘text’, 123, true)
* **udt** values should be enclosed between brackets (see **[UDT CQL syntax]**): {stree_name: ‘Beverly Hills’, number: 104, zip_code: 90020, state: ‘California’, …}
* **tuple** values should be enclosed between parenthesis ( see **[Tuple CQL syntax]** ): (‘text’, 123, true)
* **udt** values should be enclosed between brackets ( see **[UDT CQL syntax]** ): {stree_name: ‘Beverly Hills’, number: 104, zip_code: 90020, state: ‘California’, …}
> It is possible to use the @bind statement inside a batch:
>
@ -485,14 +468,12 @@ Bound values are not mandatory for the **@bind** statement. However if you provi
> APPLY BATCH;
> ```
<br/>
#### c. @remove_prepare
<br/>
To avoid for a prepared statement to stay forever in the prepared statement map, you can use the
**@remove_prepare[statement_name]** syntax to remove it.
`@remove_prepare[statement_name]` syntax to remove it.
Removing a non-existing prepared statement yields no error.
<hr/>
## 11. Using Dynamic Forms
@ -529,7 +510,6 @@ It is also possible to use dynamic forms for **prepared statements**:
{% endraw %}
<hr/>
## 12. Execution parallelism and shared states
@ -543,44 +523,34 @@ Consequently, if you use the **USE _keyspace name_;** statement to log into a ke
per instance of **Cassandra** interpreter.
The same remark does apply to the **prepared statement hash map**, it is shared by **all users** using the same instance of **Cassandra** interpreter.
Until **Zeppelin** offers a real multi-users separation, there is a work-around to segregate user environment and states:
_create different **Cassandra** interpreter instances_
create different **Cassandra** interpreter instances.
For this, first go to the **Interpreter** menu and click on the **Create** button
<br/>
<br/>
For this, first go to the **Interpreter** menu and click on the **Create** button.
<center>
![Create Interpreter](../assets/themes/zeppelin/img/docs-img/cassandra-NewInterpreterInstance.png)
</center>
In the interpreter creation form, put **cass-instance2** as **Name** and select the **cassandra**
in the interpreter drop-down list
<br/>
<br/>
in the interpreter drop-down list
<center>
![Interpreter Name](../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterName.png)
</center>
</center>
Click on **Save** to create the new interpreter instance. Now you should be able to see it in the interpreter list.
<br/>
<br/>
<center>
![Interpreter In List](../assets/themes/zeppelin/img/docs-img/cassandra-NewInterpreterInList.png)
</center>
</center>
Go back to your notebook and click on the **Gear** icon to configure interpreter bindings.
You should be able to see and select the **cass-instance2** interpreter instance in the available
interpreter list instead of the standard **cassandra** instance.
<br/>
<br/>
<center>
![Interpreter Instance Selection](../assets/themes/zeppelin/img/docs-img/cassandra-InterpreterInstanceSelection.png)
</center>
<hr/>
## 13. Interpreter Configuration
@ -638,7 +608,7 @@ Below are the configuration parameters and their default value.
<strong>
It is strongly recommended to let the default value
and prefix the table name with the actual keyspace
in all of your queries
in all of your queries.
</strong>
</td>
<td>system</td>
@ -649,7 +619,7 @@ Below are the configuration parameters and their default value.
Load balancing policy. Default = <em>new TokenAwarePolicy(new DCAwareRoundRobinPolicy())</em>
To Specify your own policy, provide the <strong>fully qualify class name (FQCN)</strong> of your policy.
At runtime the interpreter will instantiate the policy using
<strong>Class.forName(FQCN)</strong>
<strong>Class.forName(FQCN).</strong>
</td>
<td>DEFAULT</td>
</tr>
@ -723,7 +693,7 @@ Below are the configuration parameters and their default value.
<td>
Cassandra query default consistency level
<br/>
Available values: ONE, TWO, THREE, QUORUM, LOCAL_ONE, LOCAL_QUORUM, EACH_QUORUM, ALL
Available values: ONE, TWO, THREE, QUORUM, LOCAL\_ONE, LOCAL\_QUORUM, EACH\_QUORUM, ALL
</td>
<td>ONE</td>
</tr>
@ -748,7 +718,7 @@ Below are the configuration parameters and their default value.
Default = new ExponentialReconnectionPolicy(1000, 10 * 60 * 1000)
To Specify your own policy, provide the <strong>fully qualify class name (FQCN)</strong> of your policy.
At runtime the interpreter will instantiate the policy using
<strong>Class.forName(FQCN)</strong>
<strong>Class.forName(FQCN).</strong>
</td>
<td>DEFAULT</td>
</tr>
@ -759,7 +729,7 @@ Below are the configuration parameters and their default value.
Default = DefaultRetryPolicy.INSTANCE
To Specify your own policy, provide the <strong>fully qualify class name (FQCN)</strong> of your policy.
At runtime the interpreter will instantiate the policy using
<strong>Class.forName(FQCN)</strong>
<strong>Class.forName(FQCN).</strong>
</td>
<td>DEFAULT</td>
</tr>
@ -785,18 +755,17 @@ Below are the configuration parameters and their default value.
Default = NoSpeculativeExecutionPolicy.INSTANCE
To Specify your own policy, provide the <strong>fully qualify class name (FQCN)</strong> of your policy.
At runtime the interpreter will instantiate the policy using
<strong>Class.forName(FQCN)</strong>
<strong>Class.forName(FQCN).</strong>
</td>
<td>DEFAULT</td>
</tr>
</table>
<hr/>
## 14. Bugs & Contacts
If you encounter a bug for this interpreter, please create a **[JIRA]** ticket and ping me on Twitter
at **[@doanduyhai]**
at **[@doanduyhai]**.
[Cassandra Java Driver]: https://github.com/datastax/java-driver

53
docs/interpreter/elasticsearch.md
View file

@ -8,10 +8,11 @@ group: manual
## Elasticsearch Interpreter for Apache Zeppelin
[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.
### 1. Configuration
<br />
## 1. Configuration
<br/>
<table class="table-configuration">
<tr>
<th>Property</th>
@ -31,7 +32,7 @@ group: manual
<tr>
<td>elasticsearch.port</td>
<td>9300</td>
<td>Connection port <b>(important: this is not the HTTP port, but the transport port)</b></td>
<td>Connection port <b>( Important: this is not the HTTP port, but the transport port )</b></td>
</tr>
<tr>
<td>elasticsearch.result.size</td>
@ -45,22 +46,17 @@ group: manual
</center>
> Note #1: you can add more properties to configure the Elasticsearch client.
> **Note #1 :** You can add more properties to configure the Elasticsearch client.
> Note #2: if you use Shield, you can add a property named `shield.user` with a value containing the name and the password (format: `username:password`). For more details about Shield configuration, consult the [Shield reference guide](https://www.elastic.co/guide/en/shield/current/_using_elasticsearch_java_clients_with_shield.html). Do not forget, to copy the shield client jar in the interpreter directory (`ZEPPELIN_HOME/interpreters/elasticsearch`).
> **Note #2 :** If you use Shield, you can add a property named `shield.user` with a value containing the name and the password ( format: `username:password` ). For more details about Shield configuration, consult the [Shield reference guide](https://www.elastic.co/guide/en/shield/current/_using_elasticsearch_java_clients_with_shield.html). Do not forget, to copy the shield client jar in the interpreter directory (`ZEPPELIN_HOME/interpreters/elasticsearch`).
<hr/>
### 2. Enabling the Elasticsearch Interpreter
<br />
## 2. Enabling the Elasticsearch Interpreter
In a notebook, to enable the **Elasticsearch** interpreter, click the **Gear** icon and select **Elasticsearch**.
<hr/>
### 3. Using the Elasticsearch Interpreter
<br />
## 3. Using the Elasticsearch Interpreter
In a paragraph, use `%elasticsearch` to select the Elasticsearch interpreter and then input all commands. To get the list of available commands, use `help`.
@ -82,14 +78,14 @@ Commands:
. same comments as for the search
- get /index/type/id
- delete /index/type/id
- index /ndex/type/id <json-formatted document>
- index /index/type/id <json-formatted document>
. the id can be omitted, elasticsearch will generate one
```
> Tip: use (CTRL + .) for completion
> **Tip :** Use ( Ctrl + . ) for autocompletion.
#### get
### Get
With the `get` command, you can find a document by id. The result is a JSON document.
```bash
@ -101,12 +97,12 @@ Example:
![Elasticsearch - Get](../assets/themes/zeppelin/img/docs-img/elasticsearch-get.png)
#### search
### Search
With the `search` command, you can send a search query to Elasticsearch. There are two formats of query:
* You can provide a JSON-formatted query, that is exactly what you provide when you use the REST API of Elasticsearch.
* See [Elasticsearch search API reference document](https://www.elastic.co/guide/en/elasticsearch/reference/current/search.html) for more details about the content of the search queries.
* You can also provide the content of a `query_string`
* You can also provide the content of a `query_string`.
* This is a shortcut to a query like that: `{ "query": { "query_string": { "query": "__HERE YOUR QUERY__", "analyze_wildcard": true } } }`
* See [Elasticsearch query string syntax](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax) for more details about the content of such a query.
@ -134,7 +130,7 @@ Examples:
```bash
| %elasticsearch
| search / { "query": { "match_all": {} } }
| search / { "query": { "match_all": { } } }
|
| %elasticsearch
| search /logs { "query": { "query_string": { "query": "request.method:GET AND status:200" } } }
@ -159,7 +155,7 @@ Examples:
| search /logs (404 AND (POST OR DELETE))
```
> **Important**: a document in Elasticsearch is a JSON document, so it is hierarchical, not flat as a row in a SQL table.
> **Important** : a document in Elasticsearch is a JSON document, so it is hierarchical, not flat as a row in a SQL table.
For the Elastic interpreter, the result of a search query is flattened.
Suppose we have a JSON document:
@ -179,12 +175,10 @@ Suppose we have a JSON document:
The data will be flattened like this:
content_length | date | request.headers[0] | request.headers[1] | request.method | request.url | status
---------------|------|--------------------|--------------------|----------------|-------------|-------
1234 | 2015-12-08T21:03:13.588Z | Accept: \*.\* | Host: apache.org | GET | /zeppelin/4cd001cd-c517-4fa9-b8e5-a06b8f4056c4 | 403
Examples:
* With a table containing the results:
@ -206,7 +200,7 @@ Examples:
![Elasticsearch - Search with aggregation (multi-bucket)](../assets/themes/zeppelin/img/docs-img/elasticsearch-agg-multi-bucket-pie.png)
#### count
### Count
With the `count` command, you can count documents available in some indices and types. You can also provide a query.
```bash
@ -223,7 +217,7 @@ Examples:
![Elasticsearch - Count with query](../assets/themes/zeppelin/img/docs-img/elasticsearch-count-with-query.png)
#### index
### Index
With the `index` command, you can insert/update a document in Elasticsearch.
```bash
@ -234,7 +228,7 @@ With the `index` command, you can insert/update a document in Elasticsearch.
| index /index/type <JSON document>
```
#### delete
### Delete
With the `delete` command, you can delete a document.
```bash
@ -243,14 +237,13 @@ With the `delete` command, you can delete a document.
```
### Apply Zeppelin Dynamic Forms
#### Apply Zeppelin Dynamic Forms
You can leverage [Zeppelin Dynamic Form]({{BASE_PATH}}/manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parameterization features
You can leverage [Zeppelin Dynamic Form]({{BASE_PATH}}/manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parameterization features.
```bash
| %elasticsearch
| size ${limit=10}
| search /index/type { "query": { "match_all": {} } }
| search /index/type { "query": { "match_all": { } } }
```

23
docs/interpreter/flink.md
View file

@ -8,13 +8,13 @@ group: manual
## Flink interpreter for Apache Zeppelin
[Apache Flink](https://flink.apache.org) is an open source platform for distributed stream and batch data processing.
[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
<br>
## How to start local Flink cluster, to test the interpreter
Zeppelin comes with pre-configured flink-local interpreter, which starts Flink in a local mode on your machine, so you do not need to install anything.
### How to configure interpreter to point to Flink cluster
## How to configure interpreter to point to Flink cluster
At the "Interpreters" menu, you have to create a new Flink interpreter and provide next properties:
<table class="table-configuration">
@ -33,18 +33,13 @@ At the "Interpreters" menu, you have to create a new Flink interpreter and provi
<td>6123</td>
<td>port of running JobManager</td>
</tr>
<tr>
<td>xxx</td>
<td>yyy</td>
<td>anything else from [Flink Configuration](https://ci.apache.org/projects/flink/flink-docs-release-0.9/setup/config.html)</td>
</tr>
</table>
<br />
For more information about Flink configuration, you can find it [here](https://ci.apache.org/projects/flink/flink-docs-release-0.10/setup/config.html).
### How to test it's working
## How to test it's working
In example, by using the [Zeppelin notebook](https://www.zeppelinhub.com/viewer/notebooks/aHR0cHM6Ly9yYXcuZ2l0aHVidXNlcmNvbnRlbnQuY29tL05GTGFicy96ZXBwZWxpbi1ub3RlYm9va3MvbWFzdGVyL25vdGVib29rcy8yQVFFREs1UEMvbm90ZS5qc29u) is from [Till Rohrmann's presentation](http://www.slideshare.net/tillrohrmann/data-analysis-49806564) "Interactive data analysis with Apache Flink" for Apache Flink Meetup.
In example, by using the [Zeppelin notebook](https://www.zeppelinhub.com/viewer/notebooks/aHR0cHM6Ly9yYXcuZ2l0aHVidXNlcmNvbnRlbnQuY29tL05GTGFicy96ZXBwZWxpbi1ub3RlYm9va3MvbWFzdGVyL25vdGVib29rcy8yQVFFREs1UEMvbm90ZS5qc29u) is from Till Rohrmann's presentation [Interactive data analysis with Apache Flink](http://www.slideshare.net/tillrohrmann/data-analysis-49806564) for Apache Flink Meetup.
```
@ -52,7 +47,7 @@ In example, by using the [Zeppelin notebook](https://www.zeppelinhub.com/viewer/
rm 10.txt.utf-8
wget http://www.gutenberg.org/ebooks/10.txt.utf-8
```
```
{% highlight scala %}
%flink
case class WordCount(word: String, frequency: Int)
val bible:DataSet[String] = env.readTextFile("10.txt.utf-8")
@ -65,4 +60,4 @@ val wordCounts = partialCounts.groupBy("word").reduce{
(left, right) => WordCount(left.word, left.frequency + right.frequency)
}
val result10 = wordCounts.first(10).collect()
```
{% endhighlight %}

28
docs/interpreter/hive.md
View file

@ -8,10 +8,10 @@ group: manual
## 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.
### Configuration
<br/>
## 1. Configuration
<table class="table-configuration">
<tr>
<th>Property</th>
@ -31,48 +31,48 @@ group: manual
<tr>
<td>default.user</td>
<td></td>
<td><b>(Optional)</b>Username of the connection</td>
<td><b>( Optional ) </b>Username of the connection</td>
</tr>
<tr>
<td>default.password</td>
<td></td>
<td><b>(Optional)</b>Password of the connection</td>
<td><b>( Optional ) </b>Password of the connection</td>
</tr>
<tr>
<td>default.xxx</td>
<td></td>
<td><b>(Optional)</b>Other properties used by the driver</td>
<td><b>( Optional ) </b>Other properties used by the driver</td>
</tr>
<tr>
<td>${prefix}.driver</td>
<td></td>
<td>Driver class path of `%hive(${prefix})`</td>
<td>Driver class path of <code>%hive(${prefix})</code> </td>
</tr>
<tr>
<td>${prefix}.url</td>
<td></td>
<td>Url of `%hive(${prefix})`</td>
<td>Url of <code>%hive(${prefix})</code> </td>
</tr>
<tr>
<td>${prefix}.user</td>
<td></td>
<td><b>(Optional)</b>Username of the connection of `%hive(${prefix})`</td>
<td><b>( Optional ) </b>Username of the connection of <code>%hive(${prefix})</code> </td>
</tr>
<tr>
<td>${prefix}.password</td>
<td></td>
<td><b>(Optional)</b>Password of the connection of `%hive(${prefix})`</td>
<td><b>( Optional ) </b>Password of the connection of <code>%hive(${prefix})</code> </td>
</tr>
<tr>
<td>${prefix}.xxx</td>
<td></td>
<td><b>(Optional)</b>Other properties used by the driver of `%hive(${prefix})`</td>
<td><b>( Optional ) </b>Other properties used by the driver of <code>%hive(${prefix})</code> </td>
</tr>
</table>
This interpreter provides multiple configuration with ${prefix}. User can set a multiple connection properties by this prefix. It can be used like `%hive(${prefix})`.
This interpreter provides multiple configuration with `${prefix}`. User can set a multiple connection properties by this prefix. It can be used like `%hive(${prefix})`.
### How to use
## 2. How to use
Basically, you can use
@ -91,9 +91,9 @@ select * from my_table;
You can also run multiple queries up to 10 by default. Changing these settings is not implemented yet.
#### Apply Zeppelin Dynamic Forms
### Apply Zeppelin Dynamic Forms
You can leverage [Zeppelin Dynamic Form]({{BASE_PATH}}/manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parameterization features
You can leverage [Zeppelin Dynamic Form]({{BASE_PATH}}/manual/dynamicform.html) inside your queries. You can use both the `text input` and `select form` parameterization features.
```sql
%hive

2
docs/interpreter/lens.md
View file

@ -25,7 +25,7 @@ In order to use Lens interpreters, you may install Apache Lens in some simple st
```
### Configuring Lens Interpreter
At the "Interpreters" menu, you can to edit Lens interpreter or create new one. Zeppelin provides these properties for Lens.
At the "Interpreters" menu, you can edit Lens interpreter or create new one. Zeppelin provides these properties for Lens.
<table class="table-configuration">
<tr>

9
docs/interpreter/markdown.md
View file

@ -10,13 +10,14 @@ group: manual
### 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 checkout [markdown4j](https://code.google.com/p/markdown4j/)
In Zeppelin notebook you can use ``` %md ``` in the beginning of a paragraph to invoke the Markdown interpreter to generate static html from Markdown plain text.
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.
In Zeppelin, Markdown interpreter is enabled by default.
<img src="{{BASE_PATH}}/assets/themes/zeppelin/img/docs-img/markdown-interpreter-setting.png" width="600px" />
<img src="{{BASE_PATH}}/assets/themes/zeppelin/img/docs-img/markdown-interpreter-setting.png" width="60%" />
### Example
The following example demonstrates the basic usage of Markdown in a Zeppelin notebook.
<img src="{{BASE_PATH}}/assets/themes/zeppelin/img/docs-img/markdown-example.png" width="800px" />
<img src="{{BASE_PATH}}/assets/themes/zeppelin/img/docs-img/markdown-example.png" width="70%" />

118
docs/interpreter/spark.md
View file

@ -7,7 +7,7 @@ group: manual
{% include JB/setup %}
## Spark Interpreter
## Spark Interpreter for Apache Zeppelin
[Apache Spark](http://spark.apache.org) is supported in Zeppelin with
Spark Interpreter group, which consisted of 4 interpreters.
@ -40,18 +40,15 @@ Spark Interpreter group, which consisted of 4 interpreters.
</tr>
</table>
<br />
## Configuration
<br /><br />
### Configuration
<hr />
Without any configuration, Spark interpreter works out of box in local mode. But if you want to connect to your Spark cluster, you'll need following two simple steps.
Without any configuration, Spark interpreter works out of box in local mode. But if you want to connect to your Spark cluster, you'll need to follow below two simple steps.
#### 1. export SPARK_HOME
### 1. Export SPARK_HOME
In **conf/zeppelin-env.sh**, export SPARK_HOME environment variable with your Spark installation path.
In **conf/zeppelin-env.sh**, export `SPARK_HOME` environment variable with your Spark installation path.
for example
@ -66,9 +63,7 @@ export HADOOP_CONF_DIR=/usr/lib/hadoop
export SPARK_SUBMIT_OPTIONS="--packages com.databricks:spark-csv_2.10:1.2.0"
```
<br />
#### 2. set master in Interpreter menu.
### 2. Set master in Interpreter menu
After start Zeppelin, go to **Interpreter** menu and edit **master** property in your Spark interpreter setting. The value may vary depending on your Spark cluster deployment type.
@ -81,30 +76,24 @@ for example,
That's it. Zeppelin will work with any version of Spark and any deployment type without rebuilding Zeppelin in this way. ( Zeppelin 0.5.5-incubating release works up to Spark 1.5.2 )
> Note that without exporting `SPARK_HOME`, it's running in local mode with included version of Spark. The included version may vary depending on the build profile.
<br />
That's it. Zeppelin will work with any version of Spark and any deployment type without rebuild Zeppelin in this way. (Zeppelin 0.5.5-incubating release works up to Spark 1.5.1)
Note that without exporting SPARK_HOME, it's running in local mode with included version of Spark. The included version may vary depending on the build profile.
<br /> <br />
### SparkContext, SQLContext, ZeppelinContext
<hr />
## SparkContext, SQLContext, ZeppelinContext
SparkContext, SQLContext, ZeppelinContext are automatically created and exposed as variable names 'sc', 'sqlContext' and 'z', respectively, both in scala and python environments.
Note that scala / python environment shares the same SparkContext, SQLContext, ZeppelinContext instance.
> Note that scala / python environment shares the same SparkContext, SQLContext, ZeppelinContext instance.
<br />
<a name="dependencyloading"> </a>
<br />
<br />
### Dependency Management
<hr />
There are two ways to load external library in spark interpreter. First is using Zeppelin's %dep interpreter and second is loading Spark properties.
## Dependency Management
There are two ways to load external library in spark interpreter. First is using Zeppelin's `%dep` interpreter and second is loading Spark properties.
#### 1. Dynamic Dependency Loading via %dep interpreter
### 1. Dynamic Dependency Loading via %dep interpreter
When your code requires external library, instead of doing download/copy/restart Zeppelin, you can easily do following jobs using %dep interpreter.
When your code requires external library, instead of doing download/copy/restart Zeppelin, you can easily do following jobs using `%dep` interpreter.
* Load libraries recursively from Maven repository
* Load libraries from local filesystem
@ -112,7 +101,7 @@ When your code requires external library, instead of doing download/copy/restart
* Automatically add libraries to SparkCluster (You can turn off)
Dep interpreter leverages scala environment. So you can write any Scala code here.
Note that %dep interpreter should be used before %spark, %pyspark, %sql.
Note that `%dep` interpreter should be used before `%spark`, `%pyspark`, `%sql`.
Here's usages.
@ -150,9 +139,7 @@ z.load("groupId:artifactId:version").exclude("groupId:*")
z.load("groupId:artifactId:version").local()
```
<br />
#### 2. Loading Spark Properties
### 2. Loading Spark Properties
Once `SPARK_HOME` is set in `conf/zeppelin-env.sh`, Zeppelin uses `spark-submit` as spark interpreter runner. `spark-submit` supports two ways to load configurations. The first is command line options such as --master and Zeppelin can pass these options to `spark-submit` by exporting `SPARK_SUBMIT_OPTIONS` in conf/zeppelin-env.sh. Second is reading configuration options from `SPARK_HOME/conf/spark-defaults.conf`. Spark properites that user can set to distribute libraries are:
<table class="table-configuration">
@ -181,9 +168,8 @@ Once `SPARK_HOME` is set in `conf/zeppelin-env.sh`, Zeppelin uses `spark-submit`
<td>Comma-separated list of files to be placed in the working directory of each executor.</td>
</tr>
</table>
Note that adding jar to pyspark is only availabe via %dep interpreter at the moment
> Note that adding jar to pyspark is only availabe via `%dep` interpreter at the moment.
<br/>
Here are few examples:
* SPARK\_SUBMIT\_OPTIONS in conf/zeppelin-env.sh
@ -197,40 +183,43 @@ Here are few examples:
spark.files /path/mylib1.py,/path/mylib2.egg,/path/mylib3.zip
<br />
<br />
### ZeppelinContext
<hr />
## ZeppelinContext
Zeppelin automatically injects ZeppelinContext as variable 'z' in your scala/python environment. ZeppelinContext provides some additional functions and utility.
<br />
#### Object exchange
### Object Exchange
ZeppelinContext extends map and it's shared between scala, python environment.
So you can put some object from scala and read it from python, vise versa.
<div class="codetabs">
<div data-lang="scala" markdown="1">
Put object from scala
```scala
{% highlight scala %}
// Put object from scala
%spark
val myObject = ...
z.put("objName", myObject)
```
{% endhighlight %}
Get object from python
</div>
<div data-lang="python" markdown="1">
```python
%python
{% highlight python %}
# Get object from python
%pyspark
myObject = z.get("objName")
```
<br />
#### Form creation
{% endhighlight %}
</div>
</div>
### Form Creation
ZeppelinContext provides functions for creating forms.
In scala and python environments, you can create forms programmatically.
<div class="codetabs">
<div data-lang="scala" markdown="1">
```scala
{% highlight scala %}
%spark
/* Create text input form */
z.input("formName")
@ -245,7 +234,30 @@ z.select("formName", Seq(("option1", "option1DisplayName"),
/* Create select form with default value*/
z.select("formName", "option1", Seq(("option1", "option1DisplayName"),
("option2", "option2DisplayName")))
```
{% endhighlight %}
</div>
<div data-lang="python" markdown="1">
{% highlight python %}
%pyspark
# Create text input form
z.input("formName")
# Create text input form with default value
z.input("formName", "defaultValue")
# Create select form
z.select("formName", [("option1", "option1DisplayName"),
("option2", "option2DisplayName")])
# Create select form with default value
z.select("formName", [("option1", "option1DisplayName"),
("option2", "option2DisplayName")], "option1")
{% endhighlight %}
</div>
</div>
In sql environment, you can create form in simple template.

124
docs/manual/dynamicinterpreterload.md Normal file
View file

@ -0,0 +1,124 @@
---
layout: page
title: "Dynamic Interpreter Loading"
description: ""
group: manual
---
<!--
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
{% include JB/setup %}
## 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.
<br/>
## 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.
<center><img src="../assets/themes/zeppelin/img/docs-img/zeppelin_user.png" height="85%" width="85%"></center>
## Load & Unload Interpreters Using REST API
### 1. 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. )
```
http://[zeppelin-server]:[zeppelin-port]/api/interpreter/load/[interpreter_group_name]/[interpreter_name]
```
The Restful method will be <code>**POST**</code>. And the parameters you need are:
1. **Artifact:** Maven artifact ( groupId:artifactId:version )
2. **Class Name:** Package name + Interpreter class name
3. **Repository ( optional ):** Additional maven repository address
For example, if you want to load `markdown` interpreter to your Zeppelin, the parameters and URL you need may look like:
```
http://127.0.0.1:8080/api/interpreter/load/md/markdown
```
```
{
"artifact": "org.apache.zeppelin:zeppelin-markdown:0.6.0-incubating-SNAPSHOT",
"className": "org.apache.zeppelin.markdown.Markdown",
"repository": {
"url": "http://dl.bintray.com/spark-packages/maven",
"snapshot": false
}
}
```
The meaning of each parameters is:
1. **Artifact**
- groupId: org.apache.zeppelin
- artifactId: zeppelin-markdown
- version: 0.6.0-incubating-SNAPSHOT
2. **Class Name**
- Package Name: org.apache.zeppelin
- Interpreter Class Name: markdown.Markdown
3. **Repository ( optional )**
- Url: http://dl.bintray.com/spark-packages/maven
- Snapshot: false
> <b>Please note: </b>The interpreters you downloaded need to be **reload**, when your Zeppelin server is down.
### 2. Unload
If you want to **unload** the interpreters using REST API,
```
http://[zeppelin-server]:[zeppelin-port]/api/interpreter/unload/[interpreter_group_name]/[interpreter_name]
```
In this case, the Restful method will be <code>**DELETE**</code>.
<br/>
## 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 ?
After loading an interpreter, you can use it by creating and configuring it in Zeppelin's **Interpreter tab**.
Oh, you don't need to restart your Zeppelin server. Because it is **Dynamic Loading**, you can configure and load it **at runtime** !
1. After Zeppelin server up, browse Zeppelin home and click **Interpreter tab**.
<center><img src="../assets/themes/zeppelin/img/docs-img/interpreter_setting_1.png" height="85%" width="85%"></center>
2. At the **Interpreter** section, click **+Create** button.
<center><img src="../assets/themes/zeppelin/img/docs-img/interpreter_setting_2.png" height="85%" width="85%"></center>
3. Then, you can verify the interpreter list that you loaded.
<center><img src="../assets/themes/zeppelin/img/docs-img/interpreter_setting_3.png" height="85%" width="85%"></center>
4. After choosing an interpreter, you can configure and use it. Don't forget to save it.
5. Create a new notebook in the **Notebook** section, then you can bind the interpreters from your interpreter list. Just drag and drop !
<center><img src="../assets/themes/zeppelin/img/docs-img/interpreter_binding_1.png" height="85%" width="85%"></center>
<center><img src="../assets/themes/zeppelin/img/docs-img/interpreter_binding_2.png" height="85%" width="85%"></center>
6. At last, you can use your interpreter !
If you want to get the specific information about respective interpreters, please checkout each interpreter documentation.

49
docs/manual/interpreters.md
View file

@ -20,45 +20,50 @@ limitations under the License.
{% include JB/setup %}
## Interpreters in zeppelin
## Interpreters in Zeppelin
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, Hive, Markdown, Shell and so on.
This section explain the role of Interpreters, interpreters group and interpreters settings in Zeppelin.
Zeppelin interpreter concept 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, Hive, Markdown and Shell.
<br/>
## What is Zeppelin interpreter?
### What is zeppelin interpreter?
Zeppelin Interpreter is a plug-in which enables Zeppelin users to use a specific language/data-processing-backend. For example, to use scala code in Zeppelin, you need `%spark` interpreter.
Zeppelin Interpreter is the plug-in which enable zeppelin user to use a specific language/data-processing-backend. For example to use scala code in Zeppelin, you need ```spark``` interpreter.
When you click on the ```+Create``` button in the interpreter page the interpreter drop-down list box will present all the available interpreters on your server.
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.
<img src="/assets/themes/zeppelin/img/screenshots/interpreter_create.png">
### What is zeppelin interpreter setting?
<br/>
## What is Zeppelin Interpreter Setting?
Zeppelin interpreter setting is the configuration of a given interpreter on zeppelin server. For example, the properties requried for hive JDBC interpreter to connect to the Hive server.
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.
<img src="/assets/themes/zeppelin/img/screenshots/interpreter_setting.png">
### What is zeppelin interpreter group?
Every Interpreter belongs to an InterpreterGroup. InterpreterGroup is a unit of start/stop interpreter.
By default, every interpreter belong to a single group but the group might contain more interpreters. For example, spark interpreter group include spark support, pySpark,
<br/>
## What is Zeppelin 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.
Technically, Zeppelin interpreters from the same group are running in the same JVM. For more information about this, please checkout [here](../development/writingzeppelininterpreter.html).
Interpreters belong to a single group a registered together and all of their properties are listed in the interpreter setting.
Each interpreters is belonged to a single group and registered together. All of their properties are listed in the interpreter setting like below image.
<img src="/assets/themes/zeppelin/img/screenshots/interpreter_setting_spark.png">
### Programming langages for interpreter
<br/>
## Programming Languages for Interpreter
If the interpreter uses a specific programming language (like Scala, Python, SQL), it is generally a good idea to add syntax highlighting support for that to the notebook paragraph editor.
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 https://github.com/ajaxorg/ace-builds/tree/master/src-noconflict
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).
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` in zeppelin-web/src/app/notebook/paragraph/paragraph.controller.js
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`.

73
docs/rest-api/rest-interpreter.md
View file

@ -22,28 +22,29 @@ limitations under the License.
## Zeppelin REST API
Zeppelin provides several REST API's for interaction and remote activation of zeppelin functionality.
All REST API are available starting with the following endpoint ```http://[zeppelin-server]:[zeppelin-port]/api```
All REST API are available starting with the following endpoint `http://[zeppelin-server]:[zeppelin-port]/api`.
Note that zeppein REST API receive or return JSON objects, it it recommended you install some JSON view such as
[JSONView](https://chrome.google.com/webstore/detail/jsonview/chklaanhfefbnpoihckbnefhakgolnmc)
[JSON View](https://chrome.google.com/webstore/detail/jsonview/chklaanhfefbnpoihckbnefhakgolnmc).
If you work with zeppelin and find a need for an additional REST API please [file an issue or send us mail](../../community.html)
If you work with zeppelin and find a need for an additional REST API, please [file an issue or send us mail](http://zeppelin.incubator.apache.org/community.html).
<br />
### Interpreter REST API list
## Interpreter REST API List
The role of registered interpreters, settings and interpreters group is described [here](../manual/interpreters.html)
The role of registered interpreters, settings and interpreters group are described in [here](../manual/interpreters.html).
### 1. List of Registered Interpreters & Interpreter Settings
<table class="table-configuration">
<col width="200">
<tr>
<th>List registered interpreters</th>
<th>List of registered interpreters</th>
<th></th>
</tr>
<tr>
<td>Description</td>
<td>This ```GET``` method return all the registered interpreters available on the server.</td>
<td>This ```GET``` method returns all the registered interpreters available on the server.</td>
</tr>
<tr>
<td>URL</td>
@ -54,12 +55,11 @@ limitations under the License.
<td>200</td>
</tr>
<tr>
<td> Fail code</td>
<td>Fail code</td>
<td> 500 </td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>
{
@ -113,12 +113,12 @@ limitations under the License.
<table class="table-configuration">
<col width="200">
<tr>
<th>List interpreters settings</th>
<th>List of interpreters settings</th>
<th></th>
</tr>
<tr>
<td>Description</td>
<td>This ```GET``` method return all the interpreters settings registered on the server.</td>
<td>This ```GET``` method returns all the interpreters settings registered on the server.</td>
</tr>
<tr>
<td>URL</td>
@ -129,12 +129,11 @@ limitations under the License.
<td>200</td>
</tr>
<tr>
<td> Fail code</td>
<td>Fail code</td>
<td> 500 </td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>
{
@ -182,7 +181,8 @@ limitations under the License.
</table>
<br/>
### 2. Create an Interpreter Setting
<table class="table-configuration">
<col width="200">
<tr>
@ -202,12 +202,11 @@ limitations under the License.
<td>201</td>
</tr>
<tr>
<td> Fail code</td>
<td>Fail code</td>
<td> 500 </td>
</tr>
<tr>
<td> sample JSON input
</td>
<td>Sample JSON input</td>
<td>
<pre>
{
@ -227,8 +226,7 @@ limitations under the License.
</td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>
{
@ -256,7 +254,8 @@ limitations under the License.
<br/>
### 3. Update an Interpreter Setting
<table class="table-configuration">
<col width="200">
<tr>
@ -276,12 +275,11 @@ limitations under the License.
<td>200</td>
</tr>
<tr>
<td> Fail code</td>
<td>Fail code</td>
<td> 500 </td>
</tr>
<tr>
<td> sample JSON input
</td>
<td>Sample JSON input</td>
<td>
<pre>
{
@ -301,8 +299,7 @@ limitations under the License.
</td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>
{
@ -330,7 +327,8 @@ limitations under the License.
<br/>
### 4. Delete an Interpreter Setting
<table class="table-configuration">
<col width="200">
<tr>
@ -354,17 +352,17 @@ limitations under the License.
<td> 500 </td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>{"status":"OK"}</pre>
<code>{"status":"OK"}</code>
</td>
</tr>
</table>
<br/>
### 5. Restart an Interpreter
<table class="table-configuration">
<col width="200">
<tr>
@ -373,7 +371,7 @@ limitations under the License.
</tr>
<tr>
<td>Description</td>
<td>This ```PUT``` method restart the given interpreter id.</td>
<td>This ```PUT``` method restarts the given interpreter id.</td>
</tr>
<tr>
<td>URL</td>
@ -384,14 +382,13 @@ limitations under the License.
<td>200</td>
</tr>
<tr>
<td> Fail code</td>
<td>Fail code</td>
<td> 500 </td>
</tr>
<tr>
<td> sample JSON response
</td>
<td>Sample JSON response</td>
<td>
<pre>{"status":"OK"}</pre>
<code>{"status":"OK"}</code>
</td>
</tr>
</table>

28
docs/tutorial/tutorial.md
View file

@ -17,20 +17,20 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
### Zeppelin Tutorial
## Zeppelin Tutorial
We will assume you have Zeppelin installed already. If that's not the case, see [Install](../install/install.html).
This tutorial walks you through some of the fundamental Zeppelin concepts. We will assume you have already installed Zeppelin. If not, please see [here](../install/install.html) first.
Zeppelin's current main backend processing engine is [Apache Spark](https://spark.apache.org). If you're new to the system, you might want to start by getting an idea of how it processes data to get the most out of Zeppelin.
Current main backend processing engine of Zeppelin is [Apache Spark](https://spark.apache.org). If you're new to this system, you might want to start by getting an idea of how it processes data to get the most out of Zeppelin.
<br />
### Tutorial with Local File
## Tutorial with Local File
#### Data Refine
### 1. Data Refine
Before you start Zeppelin tutorial, you will need to download [bank.zip](http://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip).
First, to transform data from csv format into RDD of `Bank` objects, run following script. This will also remove header using `filter` function.
First, to transform csv format data into RDD of `Bank` objects, run following script. This will also remove header using `filter` function.
```scala
@ -38,7 +38,7 @@ val bankText = sc.textFile("yourPath/bank/bank-full.csv")
case class Bank(age:Integer, job:String, marital : String, education : String, balance : Integer)
// split each line, filter out header (starts with "age"), and map it into Bank case class
// split each line, filter out header (starts with "age"), and map it into Bank case class
val bank = bankText.map(s=>s.split(";")).filter(s=>s(0)!="\"age\"").map(
s=>Bank(s(0).toInt,
s(1).replaceAll("\"", ""),
@ -52,8 +52,7 @@ val bank = bankText.map(s=>s.split(";")).filter(s=>s(0)!="\"age\"").map(
bank.toDF().registerTempTable("bank")
```
<br />
#### Data Retrieval
### 2. Data Retrieval
Suppose we want to see age distribution from `bank`. To do this, run:
@ -74,9 +73,9 @@ Now we want to see age distribution with certain marital status and add combo bo
```
<br />
### Tutorial with Streaming Data
## Tutorial with Streaming Data
#### Data Refine
### 1. Data Refine
Since this tutorial is based on Twitter's sample tweet stream, you must configure authentication with a Twitter account. To do this, take a look at [Twitter Credential Setup](https://databricks-training.s3.amazonaws.com/realtime-processing-with-spark-streaming.html#twitter-credential-setup). After you get API keys, you should fill out credential related values(`apiKey`, `apiSecret`, `accessToken`, `accessTokenSecret`) with your API keys on following script.
@ -136,12 +135,11 @@ twt.print
ssc.start()
```
<br />
#### Data Retrieval
### 2. Data Retrieval
For each following script, every time you click run button you will see different result since it is based on real-time data.
Let's begin by extracting maximum 10 tweets which contain the word "girl".
Let's begin by extracting maximum 10 tweets which contain the word **girl**.
```sql
%sql select * from tweets where text like '%girl%' limit 10
@ -154,7 +152,7 @@ This time suppose we want to see how many tweets have been created per sec durin
```
You can make user-defined function and use it in Spark SQL. Let's try it by making function named `sentiment`. This function will return one of the three attitudes(positive, negative, neutral) towards the parameter.
You can make user-defined function and use it in Spark SQL. Let's try it by making function named `sentiment`. This function will return one of the three attitudes( positive, negative, neutral ) towards the parameter.
```scala
def sentiment(s:String) : String = {

4
elasticsearch/src/main/java/org/apache/zeppelin/elasticsearch/ElasticsearchInterpreter.java
View file

@ -141,6 +141,10 @@ public class ElasticsearchInterpreter extends Interpreter {
@Override
public InterpreterResult interpret(String cmd, InterpreterContext interpreterContext) {
logger.info("Run Elasticsearch command '" + cmd + "'");
if (StringUtils.isEmpty(cmd) || StringUtils.isEmpty(cmd.trim())) {
return new InterpreterResult(InterpreterResult.Code.SUCCESS);
}
int currentResultSize = resultSize;

10
elasticsearch/src/test/java/org/apache/zeppelin/elasticsearch/ElasticsearchInterpreterTest.java
View file

@ -198,4 +198,14 @@ public class ElasticsearchInterpreterTest {
assertEquals("11", res.message());
}
@Test
public void testMisc() {
InterpreterResult res = interpreter.interpret(null, null);
assertEquals(Code.SUCCESS, res.code());
res = interpreter.interpret(" \n \n ", null);
assertEquals(Code.SUCCESS, res.code());
}
}

1
ignite/src/main/java/org/apache/zeppelin/ignite/IgniteInterpreter.java
View file

@ -211,6 +211,7 @@ public class IgniteInterpreter extends Interpreter {
initEx = null;
} catch (Exception e) {
logger.error("Error in IgniteInterpreter while getIgnite: " , e);
initEx = e;
}
}

2
ignite/src/main/java/org/apache/zeppelin/ignite/IgniteSqlInterpreter.java
View file

@ -154,6 +154,7 @@ public class IgniteSqlInterpreter extends Interpreter {
}
}
} catch (Exception e) {
logger.error("Exception in IgniteSqlInterpreter while InterpreterResult interpret: ", e);
return IgniteInterpreterUtils.buildErrorResult(e);
} finally {
curStmt = null;
@ -169,6 +170,7 @@ public class IgniteSqlInterpreter extends Interpreter {
curStmt.cancel();
} catch (SQLException e) {
// No-op.
logger.info("No-op while cancel in IgniteSqlInterpreter", e);
} finally {
curStmt = null;
}

7
ignite/src/main/resources/default-ignite-jdbc.xml
View file

@ -33,13 +33,6 @@
<property name="peerClassLoadingEnabled" value="true"/>
<property name="marshaller">
<bean class="org.apache.ignite.marshaller.optimized.OptimizedMarshaller">
<!-- Set to false to allow non-serializable objects in examples, default is true. -->
<property name="requireSerializable" value="false"/>
</bean>
</property>
<!-- Explicitly configure TCP discovery SPI to provide list of initial nodes. -->
<property name="discoverySpi">
<bean class="org.apache.ignite.spi.discovery.tcp.TcpDiscoverySpi">

1
ignite/src/test/java/org/apache/zeppelin/ignite/IgniteSqlInterpreterTest.java
View file

@ -60,7 +60,6 @@ public class IgniteSqlInterpreterTest {
IgniteConfiguration cfg = new IgniteConfiguration();
cfg.setDiscoverySpi(discoSpi);
cfg.setPeerClassLoadingEnabled(true);
cfg.setMarshaller(new OptimizedMarshaller());
cfg.setGridName("test");

169
jdbc/pom.xml Normal file
View file

@ -0,0 +1,169 @@
<?xml version="1.0" encoding="UTF-8"?>
<!--
~ Licensed to the Apache Software Foundation (ASF) under one or more
~ contributor license agreements. See the NOTICE file distributed with
~ this work for additional information regarding copyright ownership.
~ The ASF licenses this file to You under the Apache License, Version 2.0
~ (the "License"); you may not use this file except in compliance with
~ the License. You may obtain a copy of the License at
~
~ http://www.apache.org/licenses/LICENSE-2.0
~
~ Unless required by applicable law or agreed to in writing, software
~ distributed under the License is distributed on an "AS IS" BASIS,
~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
~ See the License for the specific language governing permissions and
~ limitations under the License.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>zeppelin</artifactId>
<groupId>org.apache.zeppelin</groupId>
<version>0.6.0-incubating-SNAPSHOT</version>
</parent>
<groupId>org.apache.zeppelin</groupId>
<artifactId>zeppelin-jdbc</artifactId>
<packaging>jar</packaging>
<version>0.6.0-incubating-SNAPSHOT</version>
<name>Zeppelin: JDBC interpreter</name>
<url>http://www.apache.org</url>
<properties>
<postgresql.version>9.4-1201-jdbc41</postgresql.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.zeppelin</groupId>
<artifactId>zeppelin-interpreter</artifactId>
<version>${project.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.postgresql</groupId>
<artifactId>postgresql</artifactId>
<version>${postgresql.version}</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>jline</groupId>
<artifactId>jline</artifactId>
<version>2.12.1</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.h2database</groupId>
<artifactId>h2</artifactId>
<version>1.4.190</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-all</artifactId>
<version>1.9.5</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.mockrunner</groupId>
<artifactId>mockrunner-jdbc</artifactId>
<version>1.0.8</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-deploy-plugin</artifactId>
<version>2.7</version>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
<plugin>
<artifactId>maven-enforcer-plugin</artifactId>
<version>1.3.1</version>
<executions>
<execution>
<id>enforce</id>
<phase>none</phase>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-dependency-plugin</artifactId>
<version>2.8</version>
<executions>
<execution>
<id>copy-dependencies</id>
<phase>package</phase>
<goals>
<goal>copy-dependencies</goal>
</goals>
<configuration>
<outputDirectory>${project.build.directory}/../../interpreter/jdbc</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>false</overWriteSnapshots>
<overWriteIfNewer>true</overWriteIfNewer>
<includeScope>runtime</includeScope>
</configuration>
</execution>
<execution>
<id>copy-artifact</id>
<phase>package</phase>
<goals>
<goal>copy</goal>
</goals>
<configuration>
<outputDirectory>${project.build.directory}/../../interpreter/jdbc</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>false</overWriteSnapshots>
<overWriteIfNewer>true</overWriteIfNewer>
<includeScope>runtime</includeScope>
<artifactItems>
<artifactItem>
<groupId>${project.groupId}</groupId>
<artifactId>${project.artifactId}</artifactId>
<version>${project.version}</version>
<type>${project.packaging}</type>
</artifactItem>
</artifactItems>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>

413
jdbc/src/main/java/org/apache/zeppelin/jdbc/JDBCInterpreter.java Normal file
View file

@ -0,0 +1,413 @@
/**
* Licensed to the Apache Software Foundation (ASF) under one or more contributor license
* agreements. See the NOTICE file distributed with this work for additional information regarding
* copyright ownership. The ASF licenses this file to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance with the License. You may obtain a
* copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software distributed under the License
* is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
* or implied. See the License for the specific language governing permissions and limitations under
* the License.
*/
package org.apache.zeppelin.jdbc;
import static org.apache.commons.lang.StringUtils.containsIgnoreCase;
import java.io.IOException;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.ResultSetMetaData;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.Set;
import org.apache.zeppelin.interpreter.Interpreter;
import org.apache.zeppelin.interpreter.InterpreterContext;
import org.apache.zeppelin.interpreter.InterpreterPropertyBuilder;
import org.apache.zeppelin.interpreter.InterpreterResult;
import org.apache.zeppelin.interpreter.InterpreterResult.Code;
import org.apache.zeppelin.scheduler.Scheduler;
import org.apache.zeppelin.scheduler.SchedulerFactory;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.common.base.Function;
import com.google.common.collect.Lists;
import com.google.common.collect.Sets;
import com.google.common.collect.Sets.SetView;
/**
* JDBC interpreter for Zeppelin. This interpreter can also be used for accessing HAWQ,
* GreenplumDB, MariaDB, MySQL, Postgres and Redshit.
*
* <ul>
* <li>{@code default.url} - JDBC URL to connect to.</li>
* <li>{@code default.user} - JDBC user name..</li>
* <li>{@code default.password} - JDBC password..</li>
* <li>{@code default.driver.name} - JDBC driver name.</li>
* <li>{@code common.max.result} - Max number of SQL result to display.</li>
* </ul>
*
* <p>
* How to use: <br/>
* {@code %jdbc.sql} <br/>
* {@code
* SELECT store_id, count(*)
* FROM retail_demo.order_lineitems_pxf
* GROUP BY store_id;
* }
* </p>
*
*/
public class JDBCInterpreter extends Interpreter {
private Logger logger = LoggerFactory.getLogger(JDBCInterpreter.class);
static final String COMMON_KEY = "common";
static final String MAX_LINE_KEY = "max_count";
static final String MAX_LINE_DEFAULT = "1000";
static final String DEFAULT_KEY = "default";
static final String DRIVER_KEY = "driver";
static final String URL_KEY = "url";
static final String USER_KEY = "user";
static final String PASSWORD_KEY = "password";
static final String DOT = ".";
private static final char WHITESPACE = ' ';
private static final char NEWLINE = '\n';
private static final char TAB = '\t';
private static final String TABLE_MAGIC_TAG = "%table ";
private static final String EXPLAIN_PREDICATE = "EXPLAIN ";
private static final String UPDATE_COUNT_HEADER = "Update Count";
static final String COMMON_MAX_LINE = COMMON_KEY + DOT + MAX_LINE_KEY;
static final String DEFAULT_DRIVER = DEFAULT_KEY + DOT + DRIVER_KEY;
static final String DEFAULT_URL = DEFAULT_KEY + DOT + URL_KEY;
static final String DEFAULT_USER = DEFAULT_KEY + DOT + USER_KEY;
static final String DEFAULT_PASSWORD = DEFAULT_KEY + DOT + PASSWORD_KEY;
static final String EMPTY_COLUMN_VALUE = "";
private final HashMap<String, Properties> propertiesMap;
private final Map<String, Statement> paragraphIdStatementMap;
private final Map<String, ArrayList<Connection>> propertyKeyUnusedConnectionListMap;
private final Map<String, Connection> paragraphIdConnectionMap;
static {
Interpreter.register(
"sql",
"jdbc",
JDBCInterpreter.class.getName(),
new InterpreterPropertyBuilder()
.add(DEFAULT_URL, "jdbc:postgresql://localhost:5432/", "The URL for JDBC.")
.add(DEFAULT_USER, "gpadmin", "The JDBC user name")
.add(DEFAULT_PASSWORD, "",
"The JDBC user password")
.add(DEFAULT_DRIVER, "org.postgresql.Driver", "JDBC Driver Name")
.add(COMMON_MAX_LINE, MAX_LINE_DEFAULT,
"Max number of SQL result to display.").build());
}
public JDBCInterpreter(Properties property) {
super(property);
propertiesMap = new HashMap<>();
propertyKeyUnusedConnectionListMap = new HashMap<>();
paragraphIdStatementMap = new HashMap<>();
paragraphIdConnectionMap = new HashMap<>();
}
public HashMap<String, Properties> getPropertiesMap() {
return propertiesMap;
}
@Override
public void open() {
for (String propertyKey : property.stringPropertyNames()) {
logger.debug("propertyKey: {}", propertyKey);
String[] keyValue = propertyKey.split("\\.", 2);
if (2 == keyValue.length) {
logger.info("key: {}, value: {}", keyValue[0], keyValue[1]);
Properties prefixProperties;
if (propertiesMap.containsKey(keyValue[0])) {
prefixProperties = propertiesMap.get(keyValue[0]);
} else {
prefixProperties = new Properties();
propertiesMap.put(keyValue[0], prefixProperties);
}
prefixProperties.put(keyValue[1], property.getProperty(propertyKey));
}
}
Set<String> removeKeySet = new HashSet<>();
for (String key : propertiesMap.keySet()) {
if (!COMMON_KEY.equals(key)) {
Properties properties = propertiesMap.get(key);
if (!properties.containsKey(DRIVER_KEY) || !properties.containsKey(URL_KEY)) {
logger.error("{} will be ignored. {}.{} and {}.{} is mandatory.",
key, DRIVER_KEY, key, key, URL_KEY);
removeKeySet.add(key);
}
}
}
for (String key : removeKeySet) {
propertiesMap.remove(key);
}
logger.debug("propertiesMap: {}", propertiesMap);
}
public Connection getConnection(String propertyKey) throws ClassNotFoundException, SQLException {
Connection connection = null;
if (propertyKeyUnusedConnectionListMap.containsKey(propertyKey)) {
ArrayList<Connection> connectionList = propertyKeyUnusedConnectionListMap.get(propertyKey);
if (0 != connectionList.size()) {
connection = propertyKeyUnusedConnectionListMap.get(propertyKey).remove(0);
if (null != connection && connection.isClosed()) {
connection.close();
connection = null;
}
}
}
if (null == connection) {
Properties properties = propertiesMap.get(propertyKey);
logger.info(properties.getProperty(DRIVER_KEY));
Class.forName(properties.getProperty(DRIVER_KEY));
String url = properties.getProperty(URL_KEY);
String user = properties.getProperty(USER_KEY);
String password = properties.getProperty(PASSWORD_KEY);
if (null != user && null != password) {
connection = DriverManager.getConnection(url, user, password);
} else {
connection = DriverManager.getConnection(url, properties);
}
}
return connection;
}
public Statement getStatement(String propertyKey, String paragraphId)
throws SQLException, ClassNotFoundException {
Connection connection;
if (paragraphIdConnectionMap.containsKey(paragraphId)) {
connection = paragraphIdConnectionMap.get(paragraphId);
} else {
connection = getConnection(propertyKey);
}
Statement statement = connection.createStatement();
if (isStatementClosed(statement)) {
connection = getConnection(propertyKey);
statement = connection.createStatement();
}
paragraphIdConnectionMap.put(paragraphId, connection);
paragraphIdStatementMap.put(paragraphId, statement);
return statement;
}
private boolean isStatementClosed(Statement statement) {
try {
return statement.isClosed();
} catch (Throwable t) {
logger.debug("{} doesn't support isClosed method", statement);
return false;
}
}
@Override
public void close() {
try {
for (List<Connection> connectionList : propertyKeyUnusedConnectionListMap.values()) {
for (Connection c : connectionList) {
c.close();
}
}
for (Statement statement : paragraphIdStatementMap.values()) {
statement.close();
}
paragraphIdStatementMap.clear();
for (Connection connection : paragraphIdConnectionMap.values()) {
connection.close();
}
paragraphIdConnectionMap.clear();
} catch (SQLException e) {
logger.error("Error while closing...", e);
}
}
private InterpreterResult executeSql(String propertyKey, String sql,
InterpreterContext interpreterContext) {
String paragraphId = interpreterContext.getParagraphId();
try {
Statement statement = getStatement(propertyKey, paragraphId);
statement.setMaxRows(getMaxResult());
StringBuilder msg = null;
boolean isTableType = false;
if (containsIgnoreCase(sql, EXPLAIN_PREDICATE)) {
msg = new StringBuilder();
} else {
msg = new StringBuilder(TABLE_MAGIC_TAG);
isTableType = true;
}
ResultSet resultSet = null;
try {
boolean isResultSetAvailable = statement.execute(sql);
if (isResultSetAvailable) {
resultSet = statement.getResultSet();
ResultSetMetaData md = resultSet.getMetaData();
for (int i = 1; i < md.getColumnCount() + 1; i++) {
if (i > 1) {
msg.append(TAB);
}
msg.append(replaceReservedChars(isTableType, md.getColumnName(i)));
}
msg.append(NEWLINE);
int displayRowCount = 0;
while (resultSet.next() && displayRowCount < getMaxResult()) {
for (int i = 1; i < md.getColumnCount() + 1; i++) {
msg.append(replaceReservedChars(isTableType, resultSet.getString(i)));
if (i != md.getColumnCount()) {
msg.append(TAB);
}
}
msg.append(NEWLINE);
displayRowCount++;
}
} else {
// Response contains either an update count or there are no results.
int updateCount = statement.getUpdateCount();
msg.append(UPDATE_COUNT_HEADER).append(NEWLINE);
msg.append(updateCount).append(NEWLINE);
}
} finally {
try {
if (resultSet != null) {
resultSet.close();
}
statement.close();
} finally {
statement = null;
}
}
return new InterpreterResult(Code.SUCCESS, msg.toString());
} catch (SQLException ex) {
logger.error("Cannot run " + sql, ex);
return new InterpreterResult(Code.ERROR, ex.getMessage());
} catch (ClassNotFoundException e) {
logger.error("Cannot run " + sql, e);
return new InterpreterResult(Code.ERROR, e.getMessage());
}
}
/**
* For %table response replace Tab and Newline characters from the content.
*/
private String replaceReservedChars(boolean isTableResponseType, String str) {
if (str == null) {
return EMPTY_COLUMN_VALUE;
}
return (!isTableResponseType) ? str : str.replace(TAB, WHITESPACE).replace(NEWLINE, WHITESPACE);
}
@Override
public InterpreterResult interpret(String cmd, InterpreterContext contextInterpreter) {
logger.info("Run SQL command '{}'", cmd);
String propertyKey = getPropertyKey(cmd);
if (null != propertyKey) {
cmd = cmd.substring(propertyKey.length() + 2);
} else {
propertyKey = DEFAULT_KEY;
}
cmd = cmd.trim();
logger.info("PropertyKey: {}, SQL command: '{}'", propertyKey, cmd);
return executeSql(propertyKey, cmd, contextInterpreter);
}
@Override
public void cancel(InterpreterContext context) {
logger.info("Cancel current query statement.");
String paragraphId = context.getParagraphId();
try {
paragraphIdStatementMap.get(paragraphId).cancel();
} catch (SQLException e) {
logger.error("Error while cancelling...", e);
}
}
public String getPropertyKey(String cmd) {
int firstLineIndex = cmd.indexOf("\n");
if (-1 == firstLineIndex) {
firstLineIndex = cmd.length();
}
int configStartIndex = cmd.indexOf("(");
int configLastIndex = cmd.indexOf(")");
if (configStartIndex != -1 && configLastIndex != -1
&& configLastIndex < firstLineIndex && configLastIndex < firstLineIndex) {
return cmd.substring(configStartIndex + 1, configLastIndex);
}
return null;
}
@Override
public FormType getFormType() {
return FormType.SIMPLE;
}
@Override
public int getProgress(InterpreterContext context) {
return 0;
}
@Override
public Scheduler getScheduler() {
return SchedulerFactory.singleton().createOrGetFIFOScheduler(
JDBCInterpreter.class.getName() + this.hashCode());
}
@Override
public List<String> completion(String buf, int cursor) {
return null;
}
public int getMaxResult() {
return Integer.valueOf(
propertiesMap.get(COMMON_KEY).getProperty(MAX_LINE_KEY, MAX_LINE_DEFAULT));
}
}

125
jdbc/src/test/java/org/apache/zeppelin/jdbc/JDBCInterpreterTest.java Normal file
View file

@ -0,0 +1,125 @@
/**
* Licensed to the Apache Software Foundation (ASF) under one or more contributor license
* agreements. See the NOTICE file distributed with this work for additional information regarding
* copyright ownership. The ASF licenses this file to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance with the License. You may obtain a
* copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software distributed under the License
* is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
* or implied. See the License for the specific language governing permissions and limitations under
* the License.
*/
package org.apache.zeppelin.jdbc;
import static java.lang.String.format;
import static org.junit.Assert.assertEquals;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.DEFAULT_KEY;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.DEFAULT_DRIVER;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.DEFAULT_PASSWORD;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.DEFAULT_USER;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.DEFAULT_URL;
import static org.apache.zeppelin.jdbc.JDBCInterpreter.COMMON_MAX_LINE;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.Properties;
import org.apache.zeppelin.interpreter.InterpreterContext;
import org.apache.zeppelin.interpreter.InterpreterResult;
import org.apache.zeppelin.jdbc.JDBCInterpreter;
import org.junit.Before;
import org.junit.Test;
import com.mockrunner.jdbc.BasicJDBCTestCaseAdapter;
/**
* JDBC interpreter unit tests
*/
public class JDBCInterpreterTest extends BasicJDBCTestCaseAdapter {
static String jdbcConnection;
private static String getJdbcConnection() throws IOException {
if(null == jdbcConnection) {
Path tmpDir = Files.createTempDirectory("h2-test-");
tmpDir.toFile().deleteOnExit();
jdbcConnection = format("jdbc:h2:%s", tmpDir);
}
return jdbcConnection;
}
@Before
public void setUp() throws Exception {
Class.forName("org.h2.Driver");
Connection connection = DriverManager.getConnection(getJdbcConnection());
Statement statement = connection.createStatement();
statement.execute(
"DROP TABLE IF EXISTS test_table; " +
"CREATE TABLE test_table(id varchar(255), name varchar(255));");
statement.execute(
"insert into test_table(id, name) values ('a', 'a_name'),('b', 'b_name');"
);
}
@Test
public void testDefaultProperties() throws SQLException {
JDBCInterpreter jdbcInterpreter = new JDBCInterpreter(new Properties());
assertEquals("org.postgresql.Driver", jdbcInterpreter.getProperty(DEFAULT_DRIVER));
assertEquals("jdbc:postgresql://localhost:5432/", jdbcInterpreter.getProperty(DEFAULT_URL));
assertEquals("gpadmin", jdbcInterpreter.getProperty(DEFAULT_USER));
assertEquals("", jdbcInterpreter.getProperty(DEFAULT_PASSWORD));
assertEquals("1000", jdbcInterpreter.getProperty(COMMON_MAX_LINE));
}
@Test
public void testSelectQuery() throws SQLException, IOException {
Properties properties = new Properties();
properties.setProperty("common.max_count", "1000");
properties.setProperty("common.max_retry", "3");
properties.setProperty("default.driver", "org.h2.Driver");
properties.setProperty("default.url", getJdbcConnection());
properties.setProperty("default.user", "");
properties.setProperty("default.password", "");
JDBCInterpreter t = new JDBCInterpreter(properties);
t.open();
String sqlQuery = "select * from test_table";
InterpreterResult interpreterResult = t.interpret(sqlQuery, new InterpreterContext("", "1", "","", null,null,null,null));
assertEquals(InterpreterResult.Code.SUCCESS, interpreterResult.code());
assertEquals(InterpreterResult.Type.TABLE, interpreterResult.type());
assertEquals("ID\tNAME\na\ta_name\nb\tb_name\n", interpreterResult.message());
}
@Test
public void testSelectQueryMaxResult() throws SQLException, IOException {
Properties properties = new Properties();
properties.setProperty("common.max_count", "1");
properties.setProperty("common.max_retry", "3");
properties.setProperty("default.driver", "org.h2.Driver");
properties.setProperty("default.url", getJdbcConnection());
properties.setProperty("default.user", "");
properties.setProperty("default.password", "");
JDBCInterpreter t = new JDBCInterpreter(properties);
t.open();
String sqlQuery = "select * from test_table";
InterpreterResult interpreterResult = t.interpret(sqlQuery, new InterpreterContext("", "1", "","", null,null,null,null));
assertEquals(InterpreterResult.Code.SUCCESS, interpreterResult.code());
assertEquals(InterpreterResult.Type.TABLE, interpreterResult.type());
assertEquals("ID\tNAME\na\ta_name\n", interpreterResult.message());
}
}

3
lens/src/main/java/org/apache/zeppelin/lens/LensInterpreter.java
View file

@ -128,7 +128,7 @@ public class LensInterpreter extends Interpreter {
s_logger.info("LensInterpreter created");
}
catch (Exception e) {
e.printStackTrace();
s_logger.error(e.toString(), e);
s_logger.error("unable to create lens interpreter", e);
}
}
@ -375,6 +375,7 @@ public class LensInterpreter extends Interpreter {
closeShell(s_paraToQH.get(context.getParagraphId()).getShell());
} catch (Exception e) {
// ignore
s_logger.info("Exception in LensInterpreter while cancel finally, ignore", e);
}
s_paraToQH.remove(context.getParagraphId());
closeShell(shell);

7
lens/src/main/java/org/apache/zeppelin/lens/LensJLineShellComponent.java
View file

@ -17,6 +17,9 @@ package org.apache.zeppelin.lens;
import java.util.Map;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.BeansException;
import org.springframework.beans.factory.BeanFactoryUtils;
import org.springframework.beans.factory.InitializingBean;
@ -56,6 +59,8 @@ public class LensJLineShellComponent extends JLineShell
private ExecutionStrategy executionStrategy = new LensSimpleExecutionStrategy();
private SimpleParser parser = new SimpleParser();
private static final Logger LOGGER = LoggerFactory.getLogger(LensJLineShellComponent.class);
public SimpleParser getSimpleParser() {
return parser;
}
@ -123,7 +128,7 @@ public class LensJLineShellComponent extends JLineShell
try {
shellThread.join();
} catch (InterruptedException e) {
e.printStackTrace();
LOGGER.error(e.toString(), e);
}
}

4
markdown/src/main/java/org/apache/zeppelin/markdown/Markdown.java
View file

@ -29,12 +29,15 @@ import org.apache.zeppelin.interpreter.InterpreterUtils;
import org.apache.zeppelin.scheduler.Scheduler;
import org.apache.zeppelin.scheduler.SchedulerFactory;
import org.markdown4j.Markdown4jProcessor;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* Markdown interpreter for Zeppelin.
*/
public class Markdown extends Interpreter {
private Markdown4jProcessor md;
static final Logger LOGGER = LoggerFactory.getLogger(Markdown.class);
static {
Interpreter.register("md", Markdown.class.getName());
@ -58,6 +61,7 @@ public class Markdown extends Interpreter {
try {
html = md.process(st);
} catch (IOException | java.lang.RuntimeException e) {
LOGGER.error("Exception in Markdown while interpret ", e);
return new InterpreterResult(Code.ERROR, InterpreterUtils.getMostRelevantMessage(e));
}
return new InterpreterResult(Code.SUCCESS, "%html " + html);

6
phoenix/pom.xml
View file

@ -45,6 +45,12 @@
<scope>provided</scope>
</dependency>
<dependency>
<groupId>sqlline</groupId>
<artifactId>sqlline</artifactId>
<version>1.1.9</version>
</dependency>
<dependency>
<groupId>org.apache.phoenix</groupId>
<artifactId>phoenix-core</artifactId>

13
pom.xml
View file

@ -95,6 +95,7 @@
<module>hbase</module>
<module>phoenix</module>
<module>postgresql</module>
<module>jdbc</module>
<module>tajo</module>
<module>flink</module>
<module>ignite</module>
@ -209,6 +210,18 @@
<version>4.11</version>
<scope>test</scope>
</dependency>
<!-- Apache Shiro -->
<dependency>
<groupId>org.apache.shiro</groupId>
<artifactId>shiro-core</artifactId>
<version>1.2.3</version>
</dependency>
<dependency>
<groupId>org.apache.shiro</groupId>
<artifactId>shiro-web</artifactId>
<version>1.2.3</version>
</dependency>
</dependencies>
</dependencyManagement>

1
postgresql/src/main/java/org/apache/zeppelin/postgresql/PostgreSqlInterpreter.java
View file

@ -297,6 +297,7 @@ public class PostgreSqlInterpreter extends Interpreter {
try {
currentStatement.cancel();
} catch (SQLException ex) {
logger.error("SQLException in PostgreSqlInterpreter while cancel ", ex);
} finally {
currentStatement = null;
}

3
spark-dependencies/pom.xml
View file

@ -272,14 +272,12 @@
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.10</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-twitter_2.10</artifactId>
@ -292,7 +290,6 @@
<version>${spark.version}</version>
</dependency>
<!-- hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>

129
spark/pom.xml
View file

@ -38,64 +38,8 @@
<spark.version>1.4.1</spark.version>
<scala.version>2.10.4</scala.version>
<scala.binary.version>2.10</scala.binary.version>
<hadoop.version>2.3.0</hadoop.version>
<py4j.version>0.8.2.1</py4j.version>
</properties>
<profiles>
<profile>
<id>vendor-repo</id>
<repositories>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
</profile>
<profile>
<id>spark-1.1</id>
<properties>
<spark.version>1.1.1</spark.version>
</properties>
</profile>
<profile>
<id>spark-1.2</id>
<properties>
<spark.version>1.2.1</spark.version>
</properties>
</profile>
<profile>
<id>spark-1.3</id>
<properties>
<spark.version>1.3.1</spark.version>
</properties>
</profile>
<profile>
<id>spark-1.4</id>
<properties>
<spark.version>1.4.1</spark.version>
</properties>
</profile>
<profile>
<id>spark-1.5</id>
<properties>
<spark.version>1.5.2</spark.version>
</properties>
</profile>
<profile>
<id>spark-1.6</id>
<properties>
<spark.version>1.6.0</spark.version>
<py4j.version>0.9</py4j.version>
</properties>
</profile>
</profiles>
<dependencies>
<dependency>
@ -247,51 +191,6 @@
<version>1.3</version>
</dependency>
<!-- to compile and test code.
Runtime dependency is provided by either spark-dependencies submodule or SPARK_HOME
-->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-repl_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-catalyst_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
@ -326,12 +225,6 @@
<scope>provided</scope>
</dependency>
<dependency>
<groupId>net.sf.py4j</groupId>
<artifactId>py4j</artifactId>
<version>${py4j.version}</version>
</dependency>
<!--TEST-->
<dependency>
@ -346,6 +239,28 @@
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.datanucleus</groupId>
<artifactId>datanucleus-core</artifactId>
<version>3.2.10</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.datanucleus</groupId>
<artifactId>datanucleus-api-jdo</artifactId>
<version>3.2.6</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.datanucleus</groupId>
<artifactId>datanucleus-rdbms</artifactId>
<version>3.2.9</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>

40
spark/src/main/java/org/apache/zeppelin/spark/DepInterpreter.java
View file

@ -40,7 +40,9 @@ import org.apache.zeppelin.interpreter.InterpreterResult;
import org.apache.zeppelin.interpreter.InterpreterResult.Code;
import org.apache.zeppelin.interpreter.WrappedInterpreter;
import org.apache.zeppelin.scheduler.Scheduler;
import org.apache.zeppelin.spark.dep.DependencyContext;
import org.apache.zeppelin.spark.dep.SparkDependencyContext;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.sonatype.aether.resolution.ArtifactResolutionException;
import org.sonatype.aether.resolution.DependencyResolutionException;
@ -67,7 +69,9 @@ public class DepInterpreter extends Interpreter {
"spark",
DepInterpreter.class.getName(),
new InterpreterPropertyBuilder()
.add("zeppelin.dep.localrepo", "local-repo", "local repository for dependency loader")
.add("zeppelin.dep.localrepo",
getSystemDefault("ZEPPELIN_DEP_LOCALREPO", null, "local-repo"),
"local repository for dependency loader")
.add("zeppelin.dep.additionalRemoteRepository",
"spark-packages,http://dl.bintray.com/spark-packages/maven,false;",
"A list of 'id,remote-repository-URL,is-snapshot;' for each remote repository.")
@ -77,18 +81,39 @@ public class DepInterpreter extends Interpreter {
private SparkIMain intp;
private ByteArrayOutputStream out;
private DependencyContext depc;
private SparkDependencyContext depc;
private SparkJLineCompletion completor;
private SparkILoop interpreter;
static final Logger LOGGER = LoggerFactory.getLogger(DepInterpreter.class);
public DepInterpreter(Properties property) {
super(property);
}
public DependencyContext getDependencyContext() {
public SparkDependencyContext getDependencyContext() {
return depc;
}
public static String getSystemDefault(
String envName,
String propertyName,
String defaultValue) {
if (envName != null && !envName.isEmpty()) {
String envValue = System.getenv().get(envName);
if (envValue != null) {
return envValue;
}
}
if (propertyName != null && !propertyName.isEmpty()) {
String propValue = System.getProperty(propertyName);
if (propValue != null) {
return propValue;
}
}
return defaultValue;
}
@Override
public void close() {
@ -149,16 +174,16 @@ public class DepInterpreter extends Interpreter {
intp.setContextClassLoader();
intp.initializeSynchronous();
depc = new DependencyContext(getProperty("zeppelin.dep.localrepo"),
depc = new SparkDependencyContext(getProperty("zeppelin.dep.localrepo"),
getProperty("zeppelin.dep.additionalRemoteRepository"));
completor = new SparkJLineCompletion(intp);
intp.interpret("@transient var _binder = new java.util.HashMap[String, Object]()");
Map<String, Object> binder = (Map<String, Object>) getValue("_binder");
binder.put("depc", depc);
intp.interpret("@transient val z = "
+ "_binder.get(\"depc\").asInstanceOf[org.apache.zeppelin.spark.dep.DependencyContext]");
+ "_binder.get(\"depc\")"
+ ".asInstanceOf[org.apache.zeppelin.spark.dep.SparkDependencyContext]");
}
@ -195,6 +220,7 @@ public class DepInterpreter extends Interpreter {
depc.fetch();
} catch (MalformedURLException | DependencyResolutionException
| ArtifactResolutionException e) {
LOGGER.error("Exception in DepInterpreter while interpret ", e);
return new InterpreterResult(Code.ERROR, e.toString());
}

4
spark/src/main/java/org/apache/zeppelin/spark/PySparkInterpreter.java
View file

@ -54,7 +54,7 @@ import org.apache.zeppelin.interpreter.InterpreterResult;
import org.apache.zeppelin.interpreter.InterpreterResult.Code;
import org.apache.zeppelin.interpreter.LazyOpenInterpreter;
import org.apache.zeppelin.interpreter.WrappedInterpreter;
import org.apache.zeppelin.spark.dep.DependencyContext;
import org.apache.zeppelin.spark.dep.SparkDependencyContext;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -127,7 +127,7 @@ public class PySparkInterpreter extends Interpreter implements ExecuteResultHand
URL [] urls = new URL[0];
if (depInterpreter != null) {
DependencyContext depc = depInterpreter.getDependencyContext();
SparkDependencyContext depc = depInterpreter.getDependencyContext();
if (depc != null) {
List<File> files = depc.getFiles();
List<URL> urlList = new LinkedList<URL>();

22
spark/src/main/java/org/apache/zeppelin/spark/SparkInterpreter.java
View file

@ -55,8 +55,8 @@ import org.apache.zeppelin.interpreter.InterpreterUtils;
import org.apache.zeppelin.interpreter.WrappedInterpreter;
import org.apache.zeppelin.scheduler.Scheduler;
import org.apache.zeppelin.scheduler.SchedulerFactory;
import org.apache.zeppelin.spark.dep.DependencyContext;
import org.apache.zeppelin.spark.dep.DependencyResolver;
import org.apache.zeppelin.spark.dep.SparkDependencyContext;
import org.apache.zeppelin.spark.dep.SparkDependencyResolver;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -82,7 +82,7 @@ import scala.tools.nsc.settings.MutableSettings.PathSetting;
*
*/
public class SparkInterpreter extends Interpreter {
Logger logger = LoggerFactory.getLogger(SparkInterpreter.class);
public static Logger logger = LoggerFactory.getLogger(SparkInterpreter.class);
static {
Interpreter.register(
@ -117,7 +117,7 @@ public class SparkInterpreter extends Interpreter {
private SparkContext sc;
private ByteArrayOutputStream out;
private SQLContext sqlc;
private DependencyResolver dep;
private SparkDependencyResolver dep;
private SparkJLineCompletion completor;
private JobProgressListener sparkListener;
@ -186,7 +186,7 @@ public class SparkInterpreter extends Interpreter {
}
} catch (NoSuchMethodException | SecurityException | IllegalAccessException
| IllegalArgumentException | InvocationTargetException e) {
e.printStackTrace();
logger.error(e.toString(), e);
return null;
}
return pl;
@ -222,9 +222,9 @@ public class SparkInterpreter extends Interpreter {
return sqlc;
}
public DependencyResolver getDependencyResolver() {
public SparkDependencyResolver getDependencyResolver() {
if (dep == null) {
dep = new DependencyResolver(intp,
dep = new SparkDependencyResolver(intp,
sc,
getProperty("zeppelin.dep.localrepo"),
getProperty("zeppelin.dep.additionalRemoteRepository"));
@ -335,6 +335,10 @@ public class SparkInterpreter extends Interpreter {
conf.set("spark.submit.pyArchives", Joiner.on(":").join(pythonLibs));
}
// Distributes needed libraries to workers.
if (getProperty("master").equals("yarn-client")) {
conf.set("spark.yarn.isPython", "true");
}
SparkContext sparkContext = new SparkContext(conf);
return sparkContext;
@ -423,7 +427,7 @@ public class SparkInterpreter extends Interpreter {
// add dependency from DepInterpreter
DepInterpreter depInterpreter = getDepInterpreter();
if (depInterpreter != null) {
DependencyContext depc = depInterpreter.getDependencyContext();
SparkDependencyContext depc = depInterpreter.getDependencyContext();
if (depc != null) {
List<File> files = depc.getFiles();
if (files != null) {
@ -532,7 +536,7 @@ public class SparkInterpreter extends Interpreter {
// add jar
if (depInterpreter != null) {
DependencyContext depc = depInterpreter.getDependencyContext();
SparkDependencyContext depc = depInterpreter.getDependencyContext();
if (depc != null) {
List<File> files = depc.getFilesDist();
if (files != null) {

8
spark/src/main/java/org/apache/zeppelin/spark/ZeppelinContext.java
View file

@ -43,7 +43,7 @@ import org.apache.zeppelin.display.Input.ParamOption;
import org.apache.zeppelin.interpreter.InterpreterContext;
import org.apache.zeppelin.interpreter.InterpreterContextRunner;
import org.apache.zeppelin.interpreter.InterpreterException;
import org.apache.zeppelin.spark.dep.DependencyResolver;
import org.apache.zeppelin.spark.dep.SparkDependencyResolver;
import scala.Tuple2;
import scala.Unit;
@ -53,14 +53,14 @@ import scala.collection.Iterable;
* Spark context for zeppelin.
*/
public class ZeppelinContext extends HashMap<String, Object> {
private DependencyResolver dep;
private SparkDependencyResolver dep;
private PrintStream out;
private InterpreterContext interpreterContext;
private int maxResult;
public ZeppelinContext(SparkContext sc, SQLContext sql,
InterpreterContext interpreterContext,
DependencyResolver dep, PrintStream printStream,
SparkDependencyResolver dep, PrintStream printStream,
int maxResult) {
this.sc = sc;
this.sqlContext = sql;
@ -220,7 +220,7 @@ public class ZeppelinContext extends HashMap<String, Object> {
paramOptions[i++] = new ParamOption(valueAndDisplayValue._1(), valueAndDisplayValue._2());
}
return gui.select(name, "", paramOptions);
return gui.select(name, defaultValue, paramOptions);
}
public void setGui(GUI o) {

181
spark/src/main/java/org/apache/zeppelin/spark/dep/SparkDependencyContext.java Normal file
View file

@ -0,0 +1,181 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
import java.io.File;
import java.net.MalformedURLException;
import java.util.LinkedList;
import java.util.List;
import org.apache.zeppelin.dep.Booter;
import org.apache.zeppelin.dep.Dependency;
import org.apache.zeppelin.dep.Repository;
import org.sonatype.aether.RepositorySystem;
import org.sonatype.aether.RepositorySystemSession;
import org.sonatype.aether.artifact.Artifact;
import org.sonatype.aether.collection.CollectRequest;
import org.sonatype.aether.graph.DependencyFilter;
import org.sonatype.aether.repository.RemoteRepository;
import org.sonatype.aether.repository.Authentication;
import org.sonatype.aether.resolution.ArtifactResolutionException;
import org.sonatype.aether.resolution.ArtifactResult;
import org.sonatype.aether.resolution.DependencyRequest;
import org.sonatype.aether.resolution.DependencyResolutionException;
import org.sonatype.aether.util.artifact.DefaultArtifact;
import org.sonatype.aether.util.artifact.JavaScopes;
import org.sonatype.aether.util.filter.DependencyFilterUtils;
import org.sonatype.aether.util.filter.PatternExclusionsDependencyFilter;
/**
*
*/
public class SparkDependencyContext {
List<Dependency> dependencies = new LinkedList<Dependency>();
List<Repository> repositories = new LinkedList<Repository>();
List<File> files = new LinkedList<File>();
List<File> filesDist = new LinkedList<File>();
private RepositorySystem system = Booter.newRepositorySystem();
private RepositorySystemSession session;
private RemoteRepository mavenCentral = Booter.newCentralRepository();
private RemoteRepository mavenLocal = Booter.newLocalRepository();
private List<RemoteRepository> additionalRepos = new LinkedList<RemoteRepository>();
public SparkDependencyContext(String localRepoPath, String additionalRemoteRepository) {
session = Booter.newRepositorySystemSession(system, localRepoPath);
addRepoFromProperty(additionalRemoteRepository);
}
public Dependency load(String lib) {
Dependency dep = new Dependency(lib);
if (dependencies.contains(dep)) {
dependencies.remove(dep);
}
dependencies.add(dep);
return dep;
}
public Repository addRepo(String name) {
Repository rep = new Repository(name);
repositories.add(rep);
return rep;
}
public void reset() {
dependencies = new LinkedList<Dependency>();
repositories = new LinkedList<Repository>();
files = new LinkedList<File>();
filesDist = new LinkedList<File>();
}
private void addRepoFromProperty(String listOfRepo) {
if (listOfRepo != null) {
String[] repos = listOfRepo.split(";");
for (String repo : repos) {
String[] parts = repo.split(",");
if (parts.length == 3) {
String id = parts[0].trim();
String url = parts[1].trim();
boolean isSnapshot = Boolean.parseBoolean(parts[2].trim());
if (id.length() > 1 && url.length() > 1) {
RemoteRepository rr = new RemoteRepository(id, "default", url);
rr.setPolicy(isSnapshot, null);
additionalRepos.add(rr);
}
}
}
}
}
/**
* fetch all artifacts
* @return
* @throws MalformedURLException
* @throws ArtifactResolutionException
* @throws DependencyResolutionException
*/
public List<File> fetch() throws MalformedURLException,
DependencyResolutionException, ArtifactResolutionException {
for (Dependency dep : dependencies) {
if (!dep.isLocalFsArtifact()) {
List<ArtifactResult> artifacts = fetchArtifactWithDep(dep);
for (ArtifactResult artifact : artifacts) {
if (dep.isDist()) {
filesDist.add(artifact.getArtifact().getFile());
}
files.add(artifact.getArtifact().getFile());
}
} else {
if (dep.isDist()) {
filesDist.add(new File(dep.getGroupArtifactVersion()));
}
files.add(new File(dep.getGroupArtifactVersion()));
}
}
return files;
}
private List<ArtifactResult> fetchArtifactWithDep(Dependency dep)
throws DependencyResolutionException, ArtifactResolutionException {
Artifact artifact = new DefaultArtifact(
SparkDependencyResolver.inferScalaVersion(dep.getGroupArtifactVersion()));
DependencyFilter classpathFlter = DependencyFilterUtils
.classpathFilter(JavaScopes.COMPILE);
PatternExclusionsDependencyFilter exclusionFilter = new PatternExclusionsDependencyFilter(
SparkDependencyResolver.inferScalaVersion(dep.getExclusions()));
CollectRequest collectRequest = new CollectRequest();
collectRequest.setRoot(new org.sonatype.aether.graph.Dependency(artifact,
JavaScopes.COMPILE));
collectRequest.addRepository(mavenCentral);
collectRequest.addRepository(mavenLocal);
for (RemoteRepository repo : additionalRepos) {
collectRequest.addRepository(repo);
}
for (Repository repo : repositories) {
RemoteRepository rr = new RemoteRepository(repo.getName(), "default", repo.getUrl());
rr.setPolicy(repo.isSnapshot(), null);
Authentication auth = repo.getAuthentication();
if (auth != null) {
rr.setAuthentication(auth);
}
collectRequest.addRepository(rr);
}
DependencyRequest dependencyRequest = new DependencyRequest(collectRequest,
DependencyFilterUtils.andFilter(exclusionFilter, classpathFlter));
return system.resolveDependencies(session, dependencyRequest).getArtifactResults();
}
public List<File> getFiles() {
return files;
}
public List<File> getFilesDist() {
return filesDist;
}
}

52
spark/src/main/java/org/apache/zeppelin/spark/dep/DependencyResolver.java → spark/src/main/java/org/apache/zeppelin/spark/dep/SparkDependencyResolver.java
View file

@ -30,10 +30,9 @@ import java.util.List;
import org.apache.commons.lang.StringUtils;
import org.apache.spark.SparkContext;
import org.apache.spark.repl.SparkIMain;
import org.apache.zeppelin.dep.AbstractDependencyResolver;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.sonatype.aether.RepositorySystem;
import org.sonatype.aether.RepositorySystemSession;
import org.sonatype.aether.artifact.Artifact;
import org.sonatype.aether.collection.CollectRequest;
import org.sonatype.aether.graph.Dependency;
@ -56,21 +55,13 @@ import scala.tools.nsc.util.MergedClassPath;
/**
* Deps resolver.
* Add new dependencies from mvn repo (at runetime) to Zeppelin.
* Add new dependencies from mvn repo (at runtime) to Spark interpreter group.
*/
public class DependencyResolver {
Logger logger = LoggerFactory.getLogger(DependencyResolver.class);
public class SparkDependencyResolver extends AbstractDependencyResolver {
Logger logger = LoggerFactory.getLogger(SparkDependencyResolver.class);
private Global global;
private SparkIMain intp;
private SparkContext sc;
private RepositorySystem system = Booter.newRepositorySystem();
private List<RemoteRepository> repos = new LinkedList<RemoteRepository>();
private RepositorySystemSession session;
private DependencyFilter classpathFlter = DependencyFilterUtils.classpathFilter(
JavaScopes.COMPILE,
JavaScopes.PROVIDED,
JavaScopes.RUNTIME,
JavaScopes.SYSTEM);
private final String[] exclusions = new String[] {"org.scala-lang:scala-library",
"org.scala-lang:scala-compiler",
@ -80,40 +71,15 @@ public class DependencyResolver {
"org.apache.zeppelin:zeppelin-spark",
"org.apache.zeppelin:zeppelin-server"};
public DependencyResolver(SparkIMain intp, SparkContext sc, String localRepoPath,
public SparkDependencyResolver(SparkIMain intp, SparkContext sc, String localRepoPath,
String additionalRemoteRepository) {
super(localRepoPath);
this.intp = intp;
this.global = intp.global();
this.sc = sc;
session = Booter.newRepositorySystemSession(system, localRepoPath);
repos.add(Booter.newCentralRepository()); // add maven central
repos.add(Booter.newLocalRepository());
addRepoFromProperty(additionalRemoteRepository);
}
public void addRepo(String id, String url, boolean snapshot) {
synchronized (repos) {
delRepo(id);
RemoteRepository rr = new RemoteRepository(id, "default", url);
rr.setPolicy(snapshot, null);
repos.add(rr);
}
}
public RemoteRepository delRepo(String id) {
synchronized (repos) {
Iterator<RemoteRepository> it = repos.iterator();
if (it.hasNext()) {
RemoteRepository repo = it.next();
if (repo.getId().equals(id)) {
it.remove();
return repo;
}
}
}
return null;
}
private void addRepoFromProperty(String listOfRepo) {
if (listOfRepo != null) {
String[] repos = listOfRepo.split(";");
@ -309,16 +275,16 @@ public class DependencyResolver {
}
/**
*
* @param dependency
* @param excludes list of pattern can either be of the form groupId:artifactId
* @return
* @throws Exception
*/
@Override
public List<ArtifactResult> getArtifactsWithDep(String dependency,
Collection<String> excludes) throws Exception {
Artifact artifact = new DefaultArtifact(inferScalaVersion(dependency));
DependencyFilter classpathFlter = DependencyFilterUtils.classpathFilter( JavaScopes.COMPILE );
DependencyFilter classpathFilter = DependencyFilterUtils.classpathFilter(JavaScopes.COMPILE);
PatternExclusionsDependencyFilter exclusionFilter =
new PatternExclusionsDependencyFilter(inferScalaVersion(excludes));
@ -331,7 +297,7 @@ public class DependencyResolver {
}
}
DependencyRequest dependencyRequest = new DependencyRequest(collectRequest,
DependencyFilterUtils.andFilter(exclusionFilter, classpathFlter));
DependencyFilterUtils.andFilter(exclusionFilter, classpathFilter));
return system.resolveDependencies(session, dependencyRequest).getArtifactResults();
}

5
spark/src/test/java/org/apache/zeppelin/spark/SparkInterpreterTest.java
View file

@ -38,12 +38,15 @@ import org.junit.Before;
import org.junit.FixMethodOrder;
import org.junit.Test;
import org.junit.runners.MethodSorters;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@FixMethodOrder(MethodSorters.NAME_ASCENDING)
public class SparkInterpreterTest {
public static SparkInterpreter repl;
private InterpreterContext context;
private File tmpDir;
public static Logger LOGGER = LoggerFactory.getLogger(SparkInterpreterTest.class);
/**
@ -177,7 +180,7 @@ public class SparkInterpreterTest {
for (Object oKey : intpProperty.keySet()) {
String key = (String) oKey;
String value = (String) intpProperty.get(key);
repl.logger.debug(String.format("[%s]: [%s]", key, value));
LOGGER.debug(String.format("[%s]: [%s]", key, value));
if (key.startsWith("spark.") && value.isEmpty()) {
assertTrue(String.format("configuration starting from 'spark.' should not be empty. [%s]", key), !sparkConf.contains(key) || !sparkConf.get(key).isEmpty());
}

5
spark/src/test/java/org/apache/zeppelin/spark/SparkSqlInterpreterTest.java
View file

@ -33,6 +33,8 @@ import org.apache.zeppelin.interpreter.InterpreterResult.Type;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class SparkSqlInterpreterTest {
@ -41,6 +43,8 @@ public class SparkSqlInterpreterTest {
private InterpreterContext context;
private InterpreterGroup intpGroup;
Logger LOGGER = LoggerFactory.getLogger(SparkSqlInterpreterTest.class);
@Before
public void setUp() throws Exception {
Properties p = new Properties();
@ -96,6 +100,7 @@ public class SparkSqlInterpreterTest {
fail("Exception not catched");
} catch (Exception e) {
// okay
LOGGER.info("Exception in SparkSqlInterpreterTest while test ", e);
}
assertEquals(InterpreterResult.Code.SUCCESS, sql.interpret("select case when name==\"aa\" then name else name end from test", context).code());
}

22
spark/src/test/java/org/apache/zeppelin/spark/dep/DependencyResolverTest.java → spark/src/test/java/org/apache/zeppelin/spark/dep/SparkDependencyResolverTest.java
View file

@ -19,10 +19,10 @@ package org.apache.zeppelin.spark.dep;
import static org.junit.Assert.assertEquals;
import org.apache.zeppelin.spark.dep.DependencyResolver;
import org.apache.zeppelin.spark.dep.SparkDependencyResolver;
import org.junit.Test;
public class DependencyResolverTest {
public class SparkDependencyResolverTest {
@Test
public void testInferScalaVersion() {
@ -30,23 +30,23 @@ public class DependencyResolverTest {
String scalaVersion = version[0] + "." + version[1];
assertEquals("groupId:artifactId:version",
DependencyResolver.inferScalaVersion("groupId:artifactId:version"));
SparkDependencyResolver.inferScalaVersion("groupId:artifactId:version"));
assertEquals("groupId:artifactId_" + scalaVersion + ":version",
DependencyResolver.inferScalaVersion("groupId::artifactId:version"));
SparkDependencyResolver.inferScalaVersion("groupId::artifactId:version"));
assertEquals("groupId:artifactId:version::test",
DependencyResolver.inferScalaVersion("groupId:artifactId:version::test"));
SparkDependencyResolver.inferScalaVersion("groupId:artifactId:version::test"));
assertEquals("*",
DependencyResolver.inferScalaVersion("*"));
SparkDependencyResolver.inferScalaVersion("*"));
assertEquals("groupId:*",
DependencyResolver.inferScalaVersion("groupId:*"));
SparkDependencyResolver.inferScalaVersion("groupId:*"));
assertEquals("groupId:artifactId*",
DependencyResolver.inferScalaVersion("groupId:artifactId*"));
SparkDependencyResolver.inferScalaVersion("groupId:artifactId*"));
assertEquals("groupId:artifactId_" + scalaVersion,
DependencyResolver.inferScalaVersion("groupId::artifactId"));
SparkDependencyResolver.inferScalaVersion("groupId::artifactId"));
assertEquals("groupId:artifactId_" + scalaVersion + "*",
DependencyResolver.inferScalaVersion("groupId::artifactId*"));
SparkDependencyResolver.inferScalaVersion("groupId::artifactId*"));
assertEquals("groupId:artifactId_" + scalaVersion + ":*",
DependencyResolver.inferScalaVersion("groupId::artifactId:*"));
SparkDependencyResolver.inferScalaVersion("groupId::artifactId:*"));
}
}

14
tajo/src/test/java/org/apache/zeppelin/tajo/TesterResultSet.java
View file

@ -17,13 +17,16 @@
*/
package org.apache.zeppelin.tajo;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.InputStream;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
import java.math.BigDecimal;
import java.sql.*;
import java.util.Calendar;
import java.util.Map;
import java.io.InputStream;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
/**
* This is borrowed from Apache Commons DBCP2.
@ -31,6 +34,9 @@ import java.io.UnsupportedEncodingException;
* A dummy {@link java.sql.ResultSet}, for testing purposes.
*/
public class TesterResultSet implements ResultSet {
Logger LOGGER = LoggerFactory.getLogger(TesterResultSet.class);
public TesterResultSet(Statement stmt) {
_statement = stmt;
}
@ -262,6 +268,8 @@ public class TesterResultSet implements ResultSet {
return columnName.getBytes("UTF-8");
} catch (UnsupportedEncodingException e) {
// Impossible. JVMs are required to support UTF-8
LOGGER.error("Exception in TesterResultSet while getBytes, Impossible. JVMs are required to" +
" support UTF-8", e);
return null;
}
}

2
zeppelin-distribution/src/bin_license/LICENSE
View file

@ -91,6 +91,8 @@ The following components are provided under Apache License.
(Apache 2.0) Lucene Suggest (org.apache.lucene:lucene-suggest:5.3.1 - http://lucene.apache.org/lucene-parent/lucene-suggest)
(Apache 2.0) Elasticsearch: Core (org.elasticsearch:elasticsearch:2.1.0 - http://nexus.sonatype.org/oss-repository-hosting.html/parent/elasticsearch)
(Apache 2.0) Joda convert (org.joda:joda-convert:1.2 - http://joda-convert.sourceforge.net)
(Apache 2.0) Shiro Core (org.apache.shiro:shiro-core:1.2.3 - https://shiro.apache.org)
(Apache 2.0) Shiro Web (org.apache.shiro:shiro-web:1.2.3 - https://shiro.apache.org)
(Apache 2.0) SnakeYAML (org.yaml:snakeyaml:1.15 - http://www.snakeyaml.org)

117
zeppelin-interpreter/pom.xml
View file

@ -97,6 +97,123 @@
<artifactId>commons-lang3</artifactId>
<version>${commons-lang.version}</version>
</dependency>
<!-- Aether :: maven dependency resolution -->
<dependency>
<groupId>org.apache.maven</groupId>
<artifactId>maven-plugin-api</artifactId>
<version>3.0</version>
<exclusions>
<exclusion>
<groupId>org.codehaus.plexus</groupId>
<artifactId>plexus-utils</artifactId>
</exclusion>
<exclusion>
<groupId>org.sonatype.sisu</groupId>
<artifactId>sisu-inject-plexus</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.maven</groupId>
<artifactId>maven-model</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-api</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-util</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-impl</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.apache.maven</groupId>
<artifactId>maven-aether-provider</artifactId>
<version>3.0.3</version>
<exclusions>
<exclusion>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-api</artifactId>
</exclusion>
<exclusion>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-spi</artifactId>
</exclusion>
<exclusion>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-util</artifactId>
</exclusion>
<exclusion>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-impl</artifactId>
</exclusion>
<exclusion>
<groupId>org.codehaus.plexus</groupId>
<artifactId>plexus-utils</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-connector-file</artifactId>
<version>1.12</version>
</dependency>
<dependency>
<groupId>org.sonatype.aether</groupId>
<artifactId>aether-connector-wagon</artifactId>
<version>1.12</version>
<exclusions>
<exclusion>
<groupId>org.apache.maven.wagon</groupId>
<artifactId>wagon-provider-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.maven.wagon</groupId>
<artifactId>wagon-provider-api</artifactId>
<version>1.0</version>
<exclusions>
<exclusion>
<groupId>org.codehaus.plexus</groupId>
<artifactId>plexus-utils</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.maven.wagon</groupId>
<artifactId>wagon-http-lightweight</artifactId>
<version>1.0</version>
<exclusions>
<exclusion>
<groupId>org.apache.maven.wagon</groupId>
<artifactId>wagon-http-shared</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.maven.wagon</groupId>
<artifactId>wagon-http</artifactId>
<version>1.0</version>
<exclusions>
</exclusions>
</dependency>
</dependencies>
<build>

70
zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/AbstractDependencyResolver.java Normal file
View file

@ -0,0 +1,70 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.dep;
import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import org.sonatype.aether.RepositorySystem;
import org.sonatype.aether.RepositorySystemSession;
import org.sonatype.aether.repository.RemoteRepository;
import org.sonatype.aether.resolution.ArtifactResult;
/**
* Abstract dependency resolver.
* Add new dependencies from mvn repo (at runtime) Zeppelin.
*/
public abstract class AbstractDependencyResolver {
protected RepositorySystem system = Booter.newRepositorySystem();
protected List<RemoteRepository> repos = new LinkedList<RemoteRepository>();
protected RepositorySystemSession session;
public AbstractDependencyResolver(String localRepoPath) {
session = Booter.newRepositorySystemSession(system, localRepoPath);
repos.add(Booter.newCentralRepository()); // add maven central
repos.add(Booter.newLocalRepository());
}
public void addRepo(String id, String url, boolean snapshot) {
synchronized (repos) {
delRepo(id);
RemoteRepository rr = new RemoteRepository(id, "default", url);
rr.setPolicy(snapshot, null);
repos.add(rr);
}
}
public RemoteRepository delRepo(String id) {
synchronized (repos) {
Iterator<RemoteRepository> it = repos.iterator();
if (it.hasNext()) {
RemoteRepository repo = it.next();
if (repo.getId().equals(id)) {
it.remove();
return repo;
}
}
}
return null;
}
public abstract List<ArtifactResult> getArtifactsWithDep(String dependency,
Collection<String> excludes) throws Exception;
}

4
spark/src/main/java/org/apache/zeppelin/spark/dep/Booter.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/Booter.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import java.io.File;
@ -64,7 +64,7 @@ public class Booter {
public static RemoteRepository newCentralRepository() {
return new RemoteRepository("central", "default", "http://repo1.maven.org/maven2/");
}
public static RemoteRepository newLocalRepository() {
return new RemoteRepository("local",
"default", "file://" + System.getProperty("user.home") + "/.m2/repository");

2
spark/src/main/java/org/apache/zeppelin/spark/dep/Dependency.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/Dependency.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import java.util.LinkedList;
import java.util.List;

41
spark/src/main/java/org/apache/zeppelin/spark/dep/DependencyContext.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/DependencyContext.java
View file

@ -15,14 +15,12 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import java.io.File;
import java.net.MalformedURLException;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.HashMap;
import org.sonatype.aether.RepositorySystem;
import org.sonatype.aether.RepositorySystemSession;
@ -30,7 +28,6 @@ import org.sonatype.aether.artifact.Artifact;
import org.sonatype.aether.collection.CollectRequest;
import org.sonatype.aether.graph.DependencyFilter;
import org.sonatype.aether.repository.RemoteRepository;
import org.sonatype.aether.repository.Authentication;
import org.sonatype.aether.resolution.ArtifactResolutionException;
import org.sonatype.aether.resolution.ArtifactResult;
import org.sonatype.aether.resolution.DependencyRequest;
@ -54,11 +51,9 @@ public class DependencyContext {
private RepositorySystemSession session;
private RemoteRepository mavenCentral = Booter.newCentralRepository();
private RemoteRepository mavenLocal = Booter.newLocalRepository();
private List<RemoteRepository> additionalRepos = new LinkedList<RemoteRepository>();
public DependencyContext(String localRepoPath, String additionalRemoteRepository) {
session = Booter.newRepositorySystemSession(system, localRepoPath);
addRepoFromProperty(additionalRemoteRepository);
public DependencyContext(String localRepoPath) {
session = Booter.newRepositorySystemSession(system, localRepoPath);
}
public Dependency load(String lib) {
@ -85,24 +80,6 @@ public class DependencyContext {
filesDist = new LinkedList<File>();
}
private void addRepoFromProperty(String listOfRepo) {
if (listOfRepo != null) {
String[] repos = listOfRepo.split(";");
for (String repo : repos) {
String[] parts = repo.split(",");
if (parts.length == 3) {
String id = parts[0].trim();
String url = parts[1].trim();
boolean isSnapshot = Boolean.parseBoolean(parts[2].trim());
if (id.length() > 1 && url.length() > 1) {
RemoteRepository rr = new RemoteRepository(id, "default", url);
rr.setPolicy(isSnapshot, null);
additionalRepos.add(rr);
}
}
}
}
}
/**
* fetch all artifacts
@ -136,13 +113,12 @@ public class DependencyContext {
private List<ArtifactResult> fetchArtifactWithDep(Dependency dep)
throws DependencyResolutionException, ArtifactResolutionException {
Artifact artifact = new DefaultArtifact(
DependencyResolver.inferScalaVersion(dep.getGroupArtifactVersion()));
Artifact artifact = new DefaultArtifact(dep.getGroupArtifactVersion());
DependencyFilter classpathFlter = DependencyFilterUtils
.classpathFilter(JavaScopes.COMPILE);
PatternExclusionsDependencyFilter exclusionFilter = new PatternExclusionsDependencyFilter(
DependencyResolver.inferScalaVersion(dep.getExclusions()));
dep.getExclusions());
CollectRequest collectRequest = new CollectRequest();
collectRequest.setRoot(new org.sonatype.aether.graph.Dependency(artifact,
@ -150,16 +126,9 @@ public class DependencyContext {
collectRequest.addRepository(mavenCentral);
collectRequest.addRepository(mavenLocal);
for (RemoteRepository repo : additionalRepos) {
collectRequest.addRepository(repo);
}
for (Repository repo : repositories) {
RemoteRepository rr = new RemoteRepository(repo.getName(), "default", repo.getUrl());
rr.setPolicy(repo.isSnapshot(), null);
Authentication auth = repo.getAuthentication();
if (auth != null) {
rr.setAuthentication(auth);
}
collectRequest.addRepository(rr);
}

163
zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/DependencyResolver.java Normal file
View file

@ -0,0 +1,163 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.dep;
import java.io.File;
import java.util.Arrays;
import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import org.apache.commons.io.FileUtils;
import org.apache.commons.lang.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.sonatype.aether.artifact.Artifact;
import org.sonatype.aether.collection.CollectRequest;
import org.sonatype.aether.graph.Dependency;
import org.sonatype.aether.graph.DependencyFilter;
import org.sonatype.aether.repository.RemoteRepository;
import org.sonatype.aether.resolution.ArtifactResult;
import org.sonatype.aether.resolution.DependencyRequest;
import org.sonatype.aether.util.artifact.DefaultArtifact;
import org.sonatype.aether.util.artifact.JavaScopes;
import org.sonatype.aether.util.filter.DependencyFilterUtils;
import org.sonatype.aether.util.filter.PatternExclusionsDependencyFilter;
/**
* Deps resolver.
* Add new dependencies from mvn repo (at runtime) to Zeppelin.
*/
public class DependencyResolver extends AbstractDependencyResolver {
Logger logger = LoggerFactory.getLogger(DependencyResolver.class);
private final String[] exclusions = new String[] {"org.apache.zeppelin:zeppelin-zengine",
"org.apache.zeppelin:zeppelin-interpreter",
"org.apache.zeppelin:zeppelin-server"};
public DependencyResolver(String localRepoPath) {
super(localRepoPath);
}
public List<File> load(String artifact) throws Exception {
return load(artifact, new LinkedList<String>());
}
public List<File> load(String artifact, String destPath) throws Exception {
return load(artifact, new LinkedList<String>(), destPath);
}
public synchronized List<File> load(String artifact, Collection<String> excludes)
throws Exception {
if (StringUtils.isBlank(artifact)) {
// Should throw here
throw new RuntimeException("Invalid artifact to load");
}
// <groupId>:<artifactId>[:<extension>[:<classifier>]]:<version>
int numSplits = artifact.split(":").length;
if (numSplits >= 3 && numSplits <= 6) {
return loadFromMvn(artifact, excludes);
} else {
LinkedList<File> libs = new LinkedList<File>();
libs.add(new File(artifact));
return libs;
}
}
public List<File> load(String artifact, Collection<String> excludes, String destPath)
throws Exception {
List<File> libs = load(artifact, excludes);
// find home dir
String home = System.getenv("ZEPPELIN_HOME");
if (home == null) {
home = System.getProperty("zeppelin.home");
}
if (home == null) {
home = "..";
}
for (File srcFile: libs) {
File destFile = new File(home + "/" + destPath, srcFile.getName());
if (!destFile.exists() || !FileUtils.contentEquals(srcFile, destFile)) {
FileUtils.copyFile(srcFile, destFile);
logger.info("copy {} to {}", srcFile.getAbsolutePath(), destPath);
}
}
return libs;
}
private List<File> loadFromMvn(String artifact, Collection<String> excludes) throws Exception {
Collection<String> allExclusions = new LinkedList<String>();
allExclusions.addAll(excludes);
allExclusions.addAll(Arrays.asList(exclusions));
List<ArtifactResult> listOfArtifact;
listOfArtifact = getArtifactsWithDep(artifact, allExclusions);
Iterator<ArtifactResult> it = listOfArtifact.iterator();
while (it.hasNext()) {
Artifact a = it.next().getArtifact();
String gav = a.getGroupId() + ":" + a.getArtifactId() + ":" + a.getVersion();
for (String exclude : allExclusions) {
if (gav.startsWith(exclude)) {
it.remove();
break;
}
}
}
List<File> files = new LinkedList<File>();
for (ArtifactResult artifactResult : listOfArtifact) {
files.add(artifactResult.getArtifact().getFile());
logger.info("load {}", artifactResult.getArtifact().getFile().getAbsolutePath());
}
return files;
}
/**
* @param dependency
* @param excludes list of pattern can either be of the form groupId:artifactId
* @return
* @throws Exception
*/
@Override
public List<ArtifactResult> getArtifactsWithDep(String dependency,
Collection<String> excludes) throws Exception {
Artifact artifact = new DefaultArtifact(dependency);
DependencyFilter classpathFilter = DependencyFilterUtils.classpathFilter(JavaScopes.COMPILE);
PatternExclusionsDependencyFilter exclusionFilter =
new PatternExclusionsDependencyFilter(excludes);
CollectRequest collectRequest = new CollectRequest();
collectRequest.setRoot(new Dependency(artifact, JavaScopes.COMPILE));
synchronized (repos) {
for (RemoteRepository repo : repos) {
collectRequest.addRepository(repo);
}
}
DependencyRequest dependencyRequest = new DependencyRequest(collectRequest,
DependencyFilterUtils.andFilter(exclusionFilter, classpathFilter));
return system.resolveDependencies(session, dependencyRequest).getArtifactResults();
}
}

4
spark/src/main/java/org/apache/zeppelin/spark/dep/Repository.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/Repository.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import org.sonatype.aether.repository.Authentication;
/**
*
@ -70,7 +70,7 @@ public class Repository {
return this;
}
protected Authentication getAuthentication() {
public Authentication getAuthentication() {
Authentication auth = null;
if (this.username != null && this.password != null) {
auth = new Authentication(this.username, this.password);

2
spark/src/main/java/org/apache/zeppelin/spark/dep/RepositoryListener.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/RepositoryListener.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

2
spark/src/main/java/org/apache/zeppelin/spark/dep/RepositorySystemFactory.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/RepositorySystemFactory.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import org.apache.maven.repository.internal.DefaultServiceLocator;
import org.apache.maven.wagon.Wagon;

2
spark/src/main/java/org/apache/zeppelin/spark/dep/TransferListener.java → zeppelin-interpreter/src/main/java/org/apache/zeppelin/dep/TransferListener.java
View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
package org.apache.zeppelin.spark.dep;
package org.apache.zeppelin.dep;
import java.io.PrintStream;
import java.text.DecimalFormat;

2
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/Interpreter.java
View file

@ -131,7 +131,7 @@ public abstract class Interpreter {
static Logger logger = LoggerFactory.getLogger(Interpreter.class);
public static Logger logger = LoggerFactory.getLogger(Interpreter.class);
private InterpreterGroup interpreterGroup;
private URL [] classloaderUrls;
protected Properties property;

8
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/InterpreterGroup.java
View file

@ -33,6 +33,8 @@ import org.apache.zeppelin.interpreter.remote.RemoteInterpreterProcess;
public class InterpreterGroup extends LinkedList<Interpreter>{
String id;
Logger LOGGER = Logger.getLogger(InterpreterGroup.class);
AngularObjectRegistry angularObjectRegistry;
RemoteInterpreterProcess remoteInterpreterProcess; // attached remote interpreter process
@ -100,8 +102,7 @@ public class InterpreterGroup extends LinkedList<Interpreter>{
try {
t.join();
} catch (InterruptedException e) {
Logger logger = Logger.getLogger(InterpreterGroup.class);
logger.error("Can't close interpreter", e);
LOGGER.error("Can't close interpreter", e);
}
}
}
@ -124,8 +125,7 @@ public class InterpreterGroup extends LinkedList<Interpreter>{
try {
t.join();
} catch (InterruptedException e) {
Logger logger = Logger.getLogger(InterpreterGroup.class);
logger.error("Can't close interpreter", e);
LOGGER.error("Can't close interpreter", e);
}
}

1
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/remote/RemoteAngularObjectRegistry.java
View file

@ -101,7 +101,6 @@ public class RemoteAngularObjectRegistry extends AngularObjectRegistry {
* this method should be used instead of remove()
* @param name
* @param noteId
* @param emit
* @return
*/
public AngularObject removeAndNotifyRemoteProcess(String name, String noteId) {

1
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/remote/RemoteInterpreterEventPoller.java
View file

@ -124,6 +124,7 @@ public class RemoteInterpreterEventPoller extends Thread {
wait(1000);
}
} catch (InterruptedException ignored) {
logger.info("Error in RemoteInterpreterEventPoller while waitQuietly : ", ignored);
}
}

8
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/remote/RemoteInterpreterProcess.java
View file

@ -121,6 +121,8 @@ public class RemoteInterpreterProcess implements ExecuteResultHandler {
try {
Thread.sleep(500);
} catch (InterruptedException e) {
logger.error("Exception in RemoteInterpreterProcess while synchronized reference " +
"Thread.sleep", e);
}
}
}
@ -177,6 +179,8 @@ public class RemoteInterpreterProcess implements ExecuteResultHandler {
client.shutdown();
} catch (Exception e) {
// safely ignore exception while client.shutdown() may terminates remote process
logger.info("Exception in RemoteInterpreterProcess while synchronized dereference, can " +
"safely ignore exception while client.shutdown() may terminates remote process", e);
} finally {
if (client != null) {
// no longer used
@ -195,6 +199,8 @@ public class RemoteInterpreterProcess implements ExecuteResultHandler {
try {
Thread.sleep(500);
} catch (InterruptedException e) {
logger.error("Exception in RemoteInterpreterProcess while synchronized dereference " +
"Thread.sleep", e);
}
} else {
break;
@ -266,6 +272,8 @@ public class RemoteInterpreterProcess implements ExecuteResultHandler {
client = getClient();
} catch (NullPointerException e) {
// remote process not started
logger.info("NullPointerException in RemoteInterpreterProcess while " +
"updateRemoteAngularObject getClient, remote process not started", e);
return;
} catch (Exception e) {
logger.error("Can't update angular object", e);

9
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/remote/RemoteInterpreterServer.java
View file

@ -114,6 +114,7 @@ public class RemoteInterpreterServer
try {
Thread.sleep(300);
} catch (InterruptedException e) {
logger.info("Exception in RemoteInterpreterServer while shutdown, Thread.sleep", e);
}
}
@ -170,7 +171,7 @@ public class RemoteInterpreterServer
} catch (ClassNotFoundException | NoSuchMethodException | SecurityException
| InstantiationException | IllegalAccessException
| IllegalArgumentException | InvocationTargetException e) {
e.printStackTrace();
logger.error(e.toString(), e);
throw new TException(e);
}
}
@ -225,6 +226,7 @@ public class RemoteInterpreterServer
try {
jobListener.wait(1000);
} catch (InterruptedException e) {
logger.info("Exception in RemoteInterpreterServer while interpret, jobListener.wait", e);
}
}
}
@ -455,6 +457,7 @@ public class RemoteInterpreterServer
try {
eventQueue.wait(1000);
} catch (InterruptedException e) {
logger.info("Exception in RemoteInterpreterServer while getEvent, eventQueue.wait", e);
}
}
@ -468,7 +471,6 @@ public class RemoteInterpreterServer
/**
* called when object is updated in client (web) side.
* @param className
* @param name
* @param noteId noteId where the update issues
* @param object
@ -499,6 +501,7 @@ public class RemoteInterpreterServer
return;
} catch (Exception e) {
// no luck
logger.info("Exception in RemoteInterpreterServer while angularObjectUpdate, no luck", e);
}
}
@ -510,6 +513,7 @@ public class RemoteInterpreterServer
}.getType());
} catch (Exception e) {
// no lock
logger.info("Exception in RemoteInterpreterServer while angularObjectUpdate, no lock", e);
}
}
@ -544,6 +548,7 @@ public class RemoteInterpreterServer
}.getType());
} catch (Exception e) {
// nolock
logger.info("Exception in RemoteInterpreterServer while angularObjectAdd, nolock", e);
}
// try string object type at last

5
zeppelin-interpreter/src/main/java/org/apache/zeppelin/interpreter/remote/RemoteInterpreterUtils.java
View file

@ -17,6 +17,9 @@
package org.apache.zeppelin.interpreter.remote;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.net.InetSocketAddress;
import java.net.ServerSocket;
@ -26,6 +29,7 @@ import java.net.Socket;
*
*/
public class RemoteInterpreterUtils {
static Logger LOGGER = LoggerFactory.getLogger(RemoteInterpreterUtils.class);
public static int findRandomAvailablePortOnAllLocalInterfaces() throws IOException {
int port;
try (ServerSocket socket = new ServerSocket(0);) {
@ -43,6 +47,7 @@ public class RemoteInterpreterUtils {
discover.close();
return true;
} catch (IOException e) {
LOGGER.info("Exception in RemoteInterpreterUtils while checkIfRemoteEndpointAccessible", e);
return false;
}
}

5
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/FIFOScheduler.java
View file

@ -24,6 +24,8 @@ import java.util.List;
import java.util.concurrent.ExecutorService;
import org.apache.zeppelin.scheduler.Job.Status;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* FIFOScheduler runs submitted job sequentially
@ -36,6 +38,8 @@ public class FIFOScheduler implements Scheduler {
Job runningJob = null;
private String name;
static Logger LOGGER = LoggerFactory.getLogger(FIFOScheduler.class);
public FIFOScheduler(String name, ExecutorService executor, SchedulerListener listener) {
this.name = name;
this.executor = executor;
@ -107,6 +111,7 @@ public class FIFOScheduler implements Scheduler {
try {
queue.wait(500);
} catch (InterruptedException e) {
LOGGER.error("Exception in FIFOScheduler while run queue.wait", e);
}
continue;
}

10
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/Job.java
View file

@ -78,6 +78,8 @@ public abstract class Job {
Date dateFinished;
Status status;
static Logger LOGGER = LoggerFactory.getLogger(Job.class);
transient boolean aborted = false;
String errorMessage;
@ -172,14 +174,14 @@ public abstract class Job {
dateFinished = new Date();
progressUpdator.terminate();
} catch (NullPointerException e) {
logger().error("Job failed", e);
LOGGER.error("Job failed", e);
progressUpdator.terminate();
this.exception = e;
result = e.getMessage();
errorMessage = getStack(e);
dateFinished = new Date();
} catch (Throwable e) {
logger().error("Job failed", e);
LOGGER.error("Job failed", e);
progressUpdator.terminate();
this.exception = e;
result = e.getMessage();
@ -248,10 +250,6 @@ public abstract class Job {
return dateFinished;
}
private Logger logger() {
return LoggerFactory.getLogger(Job.class);
}
protected void setResult(Object result) {
this.result = result;
}

1
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/JobProgressPoller.java
View file

@ -57,6 +57,7 @@ public class JobProgressPoller extends Thread {
try {
Thread.sleep(intervalMs);
} catch (InterruptedException e) {
logger.error("Exception in JobProgressPoller while run Thread.sleep", e);
}
}
}

5
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/ParallelScheduler.java
View file

@ -24,6 +24,8 @@ import java.util.List;
import java.util.concurrent.ExecutorService;
import org.apache.zeppelin.scheduler.Job.Status;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* Parallel scheduler runs submitted job concurrently.
@ -37,6 +39,8 @@ public class ParallelScheduler implements Scheduler {
private String name;
private int maxConcurrency;
static Logger LOGGER = LoggerFactory.getLogger(ParallelScheduler.class);
public ParallelScheduler(String name, ExecutorService executor, SchedulerListener listener,
int maxConcurrency) {
this.name = name;
@ -107,6 +111,7 @@ public class ParallelScheduler implements Scheduler {
try {
queue.wait(500);
} catch (InterruptedException e) {
LOGGER.error("Exception in MockInterpreterAngular while interpret queue.wait", e);
}
continue;
}

16
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/RemoteScheduler.java
View file

@ -17,12 +17,6 @@
package org.apache.zeppelin.scheduler;
import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import java.util.concurrent.ExecutorService;
import org.apache.thrift.TException;
import org.apache.zeppelin.interpreter.InterpreterResult;
import org.apache.zeppelin.interpreter.InterpreterResult.Code;
@ -32,6 +26,12 @@ import org.apache.zeppelin.scheduler.Job.Status;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import java.util.concurrent.ExecutorService;
/**
* RemoteScheduler runs in ZeppelinServer and proxies Scheduler running on RemoteInterpreter
*/
@ -67,6 +67,7 @@ public class RemoteScheduler implements Scheduler {
try {
queue.wait(500);
} catch (InterruptedException e) {
logger.error("Exception in RemoteScheduler while run queue.wait", e);
}
continue;
}
@ -86,6 +87,8 @@ public class RemoteScheduler implements Scheduler {
try {
queue.wait(500);
} catch (InterruptedException e) {
logger.error("Exception in RemoteScheduler while jobRunner.isJobSubmittedInRemote " +
"queue.wait", e);
}
}
}
@ -194,6 +197,7 @@ public class RemoteScheduler implements Scheduler {
try {
this.wait(interval);
} catch (InterruptedException e) {
logger.error("Exception in RemoteScheduler while run this.wait", e);
}
}

4
zeppelin-interpreter/src/main/java/org/apache/zeppelin/scheduler/SchedulerFactory.java
View file

@ -32,7 +32,7 @@ import org.slf4j.LoggerFactory;
* TODO(moon) : add description.
*/
public class SchedulerFactory implements SchedulerListener {
private final Logger logger = LoggerFactory.getLogger(SchedulerFactory.class);
private static final Logger logger = LoggerFactory.getLogger(SchedulerFactory.class);
ExecutorService executor;
Map<String, Scheduler> schedulers = new LinkedHashMap<String, Scheduler>();
@ -46,7 +46,7 @@ public class SchedulerFactory implements SchedulerListener {
try {
singleton = new SchedulerFactory();
} catch (Exception e) {
e.printStackTrace();
logger.error(e.toString(), e);
}
}
}

62
zeppelin-interpreter/src/test/java/org/apache/zeppelin/dep/DependencyResolverTest.java Normal file
View file

@ -0,0 +1,62 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.dep;
import static org.junit.Assert.assertTrue;
import java.io.File;
import org.apache.commons.io.FileUtils;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Test;
public class DependencyResolverTest {
private static DependencyResolver resolver;
private static String testPath;
private static String testCopyPath;
private static String home;
@BeforeClass
public static void setUp() throws Exception {
testPath = "test-repo";
testCopyPath = "test-copy-repo";
resolver = new DependencyResolver(testPath);
home = System.getenv("ZEPPELIN_HOME");
if (home == null) {
home = System.getProperty("zeppelin.home");
}
if (home == null) {
home = "..";
}
}
@AfterClass
public static void tearDown() throws Exception {
FileUtils.deleteDirectory(new File(home + "/" + testPath));
FileUtils.deleteDirectory(new File(home + "/" + testCopyPath));
}
@Test
public void testLoad() throws Exception {
resolver.load("org.apache.commons:commons-lang3:3.4", testCopyPath);
assertTrue(new File(home + "/" + testPath + "/org/apache/commons/commons-lang3/3.4/").exists());
assertTrue(new File(home + "/" + testCopyPath + "/commons-lang3-3.4.jar").exists());
}
}

1
zeppelin-interpreter/src/test/java/org/apache/zeppelin/interpreter/remote/mock/MockInterpreterAngular.java
View file

@ -90,6 +90,7 @@ public class MockInterpreterAngular extends Interpreter {
try {
Thread.sleep(500); // wait for watcher executed
} catch (InterruptedException e) {
logger.error("Exception in MockInterpreterAngular while interpret Thread.sleep", e);
}
String msg = registry.getAll(context.getNoteId()).size() + " " + Integer.toString(numWatch.get());

5
zeppelin-interpreter/src/test/java/org/apache/zeppelin/scheduler/SleepingJob.java
View file

@ -22,6 +22,8 @@ import java.util.Map;
import org.apache.zeppelin.scheduler.Job;
import org.apache.zeppelin.scheduler.JobListener;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class SleepingJob extends Job{
@ -30,6 +32,8 @@ public class SleepingJob extends Job{
private long start;
private int count;
static Logger LOGGER = LoggerFactory.getLogger(SleepingJob.class);
public SleepingJob(String jobName, JobListener listener, int time){
super(jobName, listener);
@ -44,6 +48,7 @@ public class SleepingJob extends Job{
try {
Thread.sleep(10);
} catch (InterruptedException e) {
LOGGER.error("Exception in MockInterpreterAngular while interpret Thread.sleep", e);
}
if(System.currentTimeMillis() - start>time) break;
}

10
zeppelin-server/pom.xml
View file

@ -269,6 +269,16 @@
<version>1.9.0</version>
<scope>test</scope>
</dependency>
<!-- Apache Shiro -->
<dependency>
<groupId>org.apache.shiro</groupId>
<artifactId>shiro-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.shiro</groupId>
<artifactId>shiro-web</artifactId>
</dependency>
</dependencies>
<build>

3
zeppelin-server/src/main/java/org/apache/zeppelin/rest/InterpreterRestApi.java
View file

@ -110,9 +110,11 @@ public class InterpreterRestApi {
interpreterFactory.setPropertyAndRestart(settingId,
new InterpreterOption(true), p.getProperties());
} catch (InterpreterException e) {
logger.error("Exception in InterpreterRestApi while updateSetting ", e);
return new JsonResponse(
Status.NOT_FOUND, e.getMessage(), ExceptionUtils.getStackTrace(e)).build();
} catch (IOException e) {
logger.error("Exception in InterpreterRestApi while updateSetting ", e);
return new JsonResponse(
Status.INTERNAL_SERVER_ERROR, e.getMessage(), ExceptionUtils.getStackTrace(e)).build();
}
@ -144,6 +146,7 @@ public class InterpreterRestApi {
try {
interpreterFactory.restart(settingId);
} catch (InterpreterException e) {
logger.error("Exception in InterpreterRestApi while restartSetting ", e);
return new JsonResponse(
Status.NOT_FOUND, e.getMessage(), ExceptionUtils.getStackTrace(e)).build();
}

1
zeppelin-server/src/main/java/org/apache/zeppelin/rest/NotebookRestApi.java
View file

@ -308,6 +308,7 @@ public class NotebookRestApi {
notebookServer.broadcastNote(note);
return new JsonResponse(Status.OK, "").build();
} catch (IndexOutOfBoundsException e) {
LOG.error("Exception in NotebookRestApi while moveParagraph ", e);
return new JsonResponse(Status.BAD_REQUEST, "paragraph's new index is out of bound").build();
}
}

74
zeppelin-server/src/main/java/org/apache/zeppelin/rest/SecurityRestApi.java Normal file
View file

@ -0,0 +1,74 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.rest;
import org.apache.zeppelin.conf.ZeppelinConfiguration;
import org.apache.zeppelin.server.JsonResponse;
import org.apache.zeppelin.ticket.TicketContainer;
import org.apache.zeppelin.utils.SecurityUtils;
import javax.ws.rs.GET;
import javax.ws.rs.Path;
import javax.ws.rs.Produces;
import javax.ws.rs.core.Response;
import java.util.HashMap;
import java.util.Map;
/**
* Zeppelin security rest api endpoint.
*
*/
@Path("/security")
@Produces("application/json")
public class SecurityRestApi {
/**
* Required by Swagger.
*/
public SecurityRestApi() {
super();
}
/**
* Get ticket
* Returns username & ticket
* for anonymous access, username is always anonymous.
* After getting this ticket, access through websockets become safe
*
* @return 200 response
*/
@GET
@Path("ticket")
public Response ticket() {
ZeppelinConfiguration conf = ZeppelinConfiguration.create();
String principal = SecurityUtils.getPrincipal();
JsonResponse response;
// ticket set to anonymous for anonymous user. Simplify testing.
String ticket;
if ("anonymous".equals(principal))
ticket = "anonymous";
else
ticket = TicketContainer.instance.getTicket(principal);
Map<String, String> data = new HashMap<>();
data.put("principal", principal);
data.put("ticket", ticket);
response = new JsonResponse(Response.Status.OK, "", data);
return response.build();
}
}

8
zeppelin-server/src/main/java/org/apache/zeppelin/server/CorsFilter.java
View file

@ -19,12 +19,12 @@ package org.apache.zeppelin.server;
import org.apache.zeppelin.conf.ZeppelinConfiguration;
import org.apache.zeppelin.utils.SecurityUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.text.DateFormat;
import java.util.Arrays;
import java.util.Date;
import java.util.Locale;
@ -43,6 +43,8 @@ import javax.servlet.http.HttpServletResponse;
*/
public class CorsFilter implements Filter {
private static final Logger LOGGER = LoggerFactory.getLogger(CorsFilter.class);
@Override
public void doFilter(ServletRequest request, ServletResponse response, FilterChain filterChain)
throws IOException, ServletException {
@ -54,7 +56,7 @@ public class CorsFilter implements Filter {
origin = sourceHost;
}
} catch (URISyntaxException e) {
e.printStackTrace();
LOGGER.error("Exception in WebDriverManager while getWebDriver ", e);
}
if (((HttpServletRequest) request).getMethod().equals("OPTIONS")) {

16
zeppelin-server/src/main/java/org/apache/zeppelin/server/ZeppelinServer.java
View file

@ -30,12 +30,14 @@ import javax.ws.rs.core.Application;
import org.apache.cxf.jaxrs.servlet.CXFNonSpringJaxrsServlet;
import org.apache.zeppelin.conf.ZeppelinConfiguration;
import org.apache.zeppelin.conf.ZeppelinConfiguration.ConfVars;
import org.apache.zeppelin.dep.DependencyResolver;
import org.apache.zeppelin.interpreter.InterpreterFactory;
import org.apache.zeppelin.notebook.Notebook;
import org.apache.zeppelin.notebook.repo.NotebookRepo;
import org.apache.zeppelin.notebook.repo.NotebookRepoSync;
import org.apache.zeppelin.rest.InterpreterRestApi;
import org.apache.zeppelin.rest.NotebookRestApi;
import org.apache.zeppelin.rest.SecurityRestApi;
import org.apache.zeppelin.rest.ZeppelinRestApi;
import org.apache.zeppelin.scheduler.SchedulerFactory;
import org.apache.zeppelin.search.SearchService;
@ -72,12 +74,14 @@ public class ZeppelinServer extends Application {
private InterpreterFactory replFactory;
private NotebookRepo notebookRepo;
private SearchService notebookIndex;
private DependencyResolver depResolver;
public ZeppelinServer() throws Exception {
ZeppelinConfiguration conf = ZeppelinConfiguration.create();
this.depResolver = new DependencyResolver(conf.getString(ConfVars.ZEPPELIN_DEP_LOCALREPO));
this.schedulerFactory = new SchedulerFactory();
this.replFactory = new InterpreterFactory(conf, notebookWsServer);
this.replFactory = new InterpreterFactory(conf, notebookWsServer, depResolver);
this.notebookRepo = new NotebookRepoSync(conf);
this.notebookIndex = new LuceneSearch();
@ -135,6 +139,7 @@ public class ZeppelinServer extends Application {
try {
System.in.read();
} catch (IOException e) {
LOG.error("Exception in ZeppelinServer while main ", e);
}
System.exit(0);
}
@ -226,6 +231,12 @@ public class ZeppelinServer extends Application {
cxfContext.addFilter(new FilterHolder(CorsFilter.class), "/*",
EnumSet.allOf(DispatcherType.class));
cxfContext.addFilter(org.apache.shiro.web.servlet.ShiroFilter.class, "/*",
EnumSet.allOf(DispatcherType.class));
cxfContext.addEventListener(new org.apache.shiro.web.env.EnvironmentLoaderListener());
return cxfContext;
}
@ -273,6 +284,9 @@ public class ZeppelinServer extends Application {
InterpreterRestApi interpreterApi = new InterpreterRestApi(replFactory);
singletons.add(interpreterApi);
SecurityRestApi securityApi = new SecurityRestApi();
singletons.add(securityApi);
return singletons;
}
}

2
zeppelin-server/src/main/java/org/apache/zeppelin/socket/Message.java
View file

@ -103,6 +103,8 @@ public class Message {
public OP op;
public Map<String, Object> data = new HashMap<String, Object>();
public String ticket = "anonymous";
public String principal = "anonymous";
public Message(OP op) {
this.op = op;

20
zeppelin-server/src/main/java/org/apache/zeppelin/socket/NotebookServer.java
View file

@ -41,6 +41,7 @@ import org.apache.zeppelin.scheduler.Job.Status;
import org.apache.zeppelin.scheduler.JobListener;
import org.apache.zeppelin.server.ZeppelinServer;
import org.apache.zeppelin.socket.Message.OP;
import org.apache.zeppelin.ticket.TicketContainer;
import org.apache.zeppelin.utils.SecurityUtils;
import org.eclipse.jetty.websocket.WebSocket;
import org.eclipse.jetty.websocket.WebSocketServlet;
@ -71,9 +72,9 @@ public class NotebookServer extends WebSocketServlet implements
try {
return SecurityUtils.isValidOrigin(origin, ZeppelinConfiguration.create());
} catch (UnknownHostException e) {
e.printStackTrace();
LOG.error(e.toString(), e);
} catch (URISyntaxException e) {
e.printStackTrace();
LOG.error(e.toString(), e);
}
return false;
}
@ -96,6 +97,19 @@ public class NotebookServer extends WebSocketServlet implements
try {
Message messagereceived = deserializeMessage(msg);
LOG.debug("RECEIVE << " + messagereceived.op);
LOG.debug("RECEIVE PRINCIPAL << " + messagereceived.principal);
LOG.debug("RECEIVE TICKET << " + messagereceived.ticket);
String ticket = TicketContainer.instance.getTicket(messagereceived.principal);
if (ticket != null && !ticket.equals(messagereceived.ticket))
throw new Exception("Invalid ticket " + messagereceived.ticket + " != " + ticket);
ZeppelinConfiguration conf = ZeppelinConfiguration.create();
boolean allowAnonymous = conf.
getBoolean(ZeppelinConfiguration.ConfVars.ZEPPELIN_ANONYMOUS_ALLOWED);
if (!allowAnonymous && messagereceived.principal.equals("anonymous")) {
throw new Exception("Anonymous access not allowed ");
}
/** Lets be elegant here */
switch (messagereceived.op) {
case LIST_NOTES:
@ -772,7 +786,7 @@ public class NotebookServer extends WebSocketServlet implements
try {
note.persist();
} catch (IOException e) {
e.printStackTrace();
LOG.error(e.toString(), e);
}
}
notebookServer.broadcastNote(note);

82
zeppelin-server/src/main/java/org/apache/zeppelin/ticket/TicketContainer.java Normal file
View file

@ -0,0 +1,82 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.ticket;
import java.util.Calendar;
import java.util.Map;
import java.util.UUID;
import java.util.concurrent.ConcurrentHashMap;
/**
* Very simple ticket container
* No cleanup is done, since the same user accross different devices share the same ticket
* The Map size is at most the number of different user names having access to a Zeppelin instance
*/
public class TicketContainer {
private static class Entry {
public final String ticket;
// lastAccessTime still unused
public final long lastAccessTime;
Entry(String ticket) {
this.ticket = ticket;
this.lastAccessTime = Calendar.getInstance().getTimeInMillis();
}
}
private Map<String, Entry> sessions = new ConcurrentHashMap<>();
public static final TicketContainer instance = new TicketContainer();
/**
* For test use
* @param principal
* @param ticket
* @return true if ticket assigned to principal.
*/
public boolean isValid(String principal, String ticket) {
if ("anonymous".equals(principal) && "anonymous".equals(ticket))
return true;
Entry entry = sessions.get(principal);
return entry != null && entry.ticket.equals(ticket);
}
/**
* get or create ticket for Websocket authentication assigned to authenticated shiro user
* For unathenticated user (anonymous), always return ticket value "anonymous"
* @param principal
* @return
*/
public synchronized String getTicket(String principal) {
Entry entry = sessions.get(principal);
String ticket;
if (entry == null) {
if (principal.equals("anonymous"))
ticket = "anonymous";
else
ticket = UUID.randomUUID().toString();
} else {
ticket = entry.ticket;
}
entry = new Entry(ticket);
sessions.put(principal, entry);
return ticket;
}
}

17
zeppelin-server/src/main/java/org/apache/zeppelin/utils/SecurityUtils.java
View file

@ -16,6 +16,7 @@
*/
package org.apache.zeppelin.utils;
import org.apache.shiro.subject.Subject;
import org.apache.zeppelin.conf.ZeppelinConfiguration;
import java.net.InetAddress;
@ -44,4 +45,20 @@ public class SecurityUtils {
"localhost".equals(sourceUriHost) ||
conf.getAllowedOrigins().contains(sourceHost);
}
/**
* Return the authenticated user if any otherwise returns "anonymous"
* @return shiro principal
*/
public static String getPrincipal() {
Subject subject = org.apache.shiro.SecurityUtils.getSubject();
String principal;
if (subject.isAuthenticated()) {
principal = subject.getPrincipal().toString();
}
else {
principal = "anonymous";
}
return principal;
}
}

31
zeppelin-server/src/main/resources/shiro.ini Normal file
View file

@ -0,0 +1,31 @@
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
[users]
# List of users with their password allowed to access Zeppelin.
# To use a different strategy (LDAP / Database / ...) check the shiro doc at http://shiro.apache.org/configuration.html#Configuration-INISections
admin = password
[urls]
# anon means the access is anonymous.
# authcBasic means Basic Auth Security
# To enfore security, comment the line below and uncomment the next one
/** = anon
#/** = authcBasic

7
zeppelin-server/src/test/java/com/webautomation/ScreenCaptureHtmlUnitDriver.java
View file

@ -50,6 +50,8 @@ import com.gargoylesoftware.htmlunit.WebRequest;
import com.gargoylesoftware.htmlunit.WebWindow;
import com.gargoylesoftware.htmlunit.html.HtmlElement;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* from https://code.google.com/p/selenium/issues/detail?id=1361
@ -63,6 +65,8 @@ public class ScreenCaptureHtmlUnitDriver extends HtmlUnitDriver implements Takes
// http://stackoverflow.com/questions/4652777/java-regex-to-get-the-urls-from-css
private final static Pattern cssUrlPattern = Pattern.compile("background(-image)?[\\s]*:[^url]*url[\\s]*\\([\\s]*([^\\)]*)[\\s]*\\)[\\s]*");// ?<url>
static Logger LOGGER = LoggerFactory.getLogger(ScreenCaptureHtmlUnitDriver.class);
public ScreenCaptureHtmlUnitDriver() {
super();
}
@ -88,6 +92,7 @@ public class ScreenCaptureHtmlUnitDriver extends HtmlUnitDriver implements Takes
try {
archive = downloadCssAndImages(getWebClient(), (HtmlPage) getCurrentWindow().getEnclosedPage());
} catch (Exception e) {
LOGGER.error("Exception in ScreenCaptureHtmlUnitDriver while getScreenshotAs ", e);
}
if(target.equals(OutputType.BASE64)){
return target.convertFromBase64Png(new Base64Encoder().encode(archive));
@ -116,6 +121,7 @@ public class ScreenCaptureHtmlUnitDriver extends HtmlUnitDriver implements Takes
window = webClient.getWebWindowByName(page.getUrl().toString()+"_screenshot");
webClient.getPage(window, new WebRequest(page.getUrl()));
} catch (Exception e) {
LOGGER.error("Exception in ScreenCaptureHtmlUnitDriver while downloadCssAndImages ", e);
window = webClient.openWindow(page.getUrl(), page.getUrl().toString()+"_screenshot");
}
@ -148,6 +154,7 @@ public class ScreenCaptureHtmlUnitDriver extends HtmlUnitDriver implements Takes
.replace("resources/", "./").getBytes());
}
} catch (Exception e) {
LOGGER.error("Exception in ScreenCaptureHtmlUnitDriver while resultList.iterator ", e);
}
}
String pagesrc = replaceRemoteUrlsWithLocal(page.getWebResponse().getContentAsString(), urlMapping);

1
zeppelin-server/src/test/java/org/apache/zeppelin/ProcessData.java
View file

@ -233,6 +233,7 @@ public class ProcessData {
String exceptionAsString = sw.toString();
LOG.error(exceptionAsString);
} catch (Exception ignore) {
LOG.info("Exception in ProcessData while buildOutputAndErrorStreamData ", ignore);
}
break;
}

7
zeppelin-server/src/test/java/org/apache/zeppelin/WebDriverManager.java
View file

@ -85,6 +85,7 @@ public class WebDriverManager {
driver = new FirefoxDriver(ffox, profile);
} catch (Exception e) {
LOG.error("Exception in WebDriverManager while FireFox Driver ", e);
}
}
@ -92,6 +93,7 @@ public class WebDriverManager {
try {
driver = new ChromeDriver();
} catch (Exception e) {
LOG.error("Exception in WebDriverManager while ChromeDriver ", e);
}
}
@ -99,6 +101,7 @@ public class WebDriverManager {
try {
driver = new SafariDriver();
} catch (Exception e) {
LOG.error("Exception in WebDriverManager while SafariDriver ", e);
}
}
@ -126,6 +129,7 @@ public class WebDriverManager {
loaded = true;
break;
} catch (TimeoutException e) {
LOG.info("Exception in WebDriverManager while WebDriverWait ", e);
driver.navigate().to(url);
}
}
@ -164,7 +168,6 @@ public class WebDriverManager {
} catch (IOException e) {
LOG.error("Download of firebug version: " + firefoxVersion + ", falied in path " + tempPath);
LOG.error(e.toString());
}
LOG.info("Download of firebug version: " + firefoxVersion + ", successful");
}
@ -178,7 +181,7 @@ public class WebDriverManager {
String versionString = (String) CommandExecutor.executeCommandLocalHost(firefoxVersionCmd, false, ProcessData.Types_Of_Data.OUTPUT);
return Integer.valueOf(versionString.replaceAll("Mozilla Firefox", "").trim().substring(0, 2));
} catch (Exception e) {
e.printStackTrace();
LOG.error("Exception in WebDriverManager while getWebDriver ", e);
return -1;
}
}

3
zeppelin-server/src/test/java/org/apache/zeppelin/ZeppelinIT.java
View file

@ -101,6 +101,7 @@ public class ZeppelinIT {
WebElement element = pollingWait(locator, MAX_BROWSER_TIMEOUT_SEC);
return txt.equals(element.getText());
} catch (TimeoutException e) {
LOG.error("Exception in ZeppelinIT while waitForText ", e);
return false;
}
}
@ -255,6 +256,7 @@ public class ZeppelinIT {
System.out.println("testCreateNotebook Test executed");
} catch (ElementNotVisibleException e) {
LOG.error("Exception in ZeppelinIT while testAngularDisplay ", e);
File scrFile = ((TakesScreenshot)driver).getScreenshotAs(OutputType.FILE);
}
@ -279,6 +281,7 @@ public class ZeppelinIT {
try {
Thread.sleep(500); // wait for notebook list updated
} catch (InterruptedException e) {
LOG.error("Exception in ZeppelinIT while createNewNote Thread.sleep", e);
}
}
}

2
zeppelin-server/src/test/java/org/apache/zeppelin/ZeppelinITUtils.java
View file

@ -33,7 +33,7 @@ public class ZeppelinITUtils {
try {
Thread.sleep(millis);
} catch (InterruptedException e) {
e.printStackTrace();
LOG.error("Exception in WebDriverManager while getWebDriver ", e);
}
if (logOutput) {
LOG.info("Finished.");

14
zeppelin-server/src/test/java/org/apache/zeppelin/rest/AbstractTestRestApi.java
View file

@ -55,7 +55,7 @@ public abstract class AbstractTestRestApi {
static final String restApiUrl = "/api";
static final String url = getUrlToTest();
protected static final boolean wasRunning = checkIfServerIsRuning();
protected static final boolean wasRunning = checkIfServerIsRunning();
static boolean pySpark = false;
private String getUrl(String path) {
@ -86,7 +86,7 @@ public abstract class AbstractTestRestApi {
try {
ZeppelinServer.main(new String[] {""});
} catch (Exception e) {
e.printStackTrace();
LOG.error("Exception in WebDriverManager while getWebDriver ", e);
throw new RuntimeException(e);
}
}
@ -101,7 +101,7 @@ public abstract class AbstractTestRestApi {
boolean started = false;
while (System.currentTimeMillis() - s < 1000 * 60 * 3) { // 3 minutes
Thread.sleep(2000);
started = checkIfServerIsRuning();
started = checkIfServerIsRunning();
if (started == true) {
break;
}
@ -156,7 +156,7 @@ public abstract class AbstractTestRestApi {
try {
return InetAddress.getLocalHost().getHostName();
} catch (UnknownHostException e) {
e.printStackTrace();
LOG.error("Exception in WebDriverManager while getWebDriver ", e);
return "localhost";
}
}
@ -218,7 +218,7 @@ public abstract class AbstractTestRestApi {
boolean started = true;
while (System.currentTimeMillis() - s < 1000 * 60 * 3) { // 3 minutes
Thread.sleep(2000);
started = checkIfServerIsRuning();
started = checkIfServerIsRunning();
if (started == false) {
break;
}
@ -231,13 +231,14 @@ public abstract class AbstractTestRestApi {
}
}
protected static boolean checkIfServerIsRuning() {
protected static boolean checkIfServerIsRunning() {
GetMethod request = null;
boolean isRunning = true;
try {
request = httpGet("/");
isRunning = request.getStatusCode() == 200;
} catch (IOException e) {
LOG.error("Exception in AbstractTestRestApi while checkIfServerIsRunning ", e);
isRunning = false;
} finally {
if (request != null) {
@ -343,6 +344,7 @@ public abstract class AbstractTestRestApi {
try {
new JsonParser().parse(body);
} catch (JsonParseException e) {
LOG.error("Exception in AbstractTestRestApi while matchesSafely ", e);
isValid = false;
}
return isValid;

58
zeppelin-server/src/test/java/org/apache/zeppelin/rest/SecurityRestApiTest.java Normal file
View file

@ -0,0 +1,58 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.zeppelin.rest;
import com.google.gson.Gson;
import com.google.gson.reflect.TypeToken;
import org.apache.commons.httpclient.methods.GetMethod;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Test;
import java.io.IOException;
import java.util.Map;
import static org.junit.Assert.*;
public class SecurityRestApiTest extends AbstractTestRestApi {
Gson gson = new Gson();
@BeforeClass
public static void init() throws Exception {
AbstractTestRestApi.startUp();
}
@AfterClass
public static void destroy() throws Exception {
AbstractTestRestApi.shutDown();
}
@Test
public void testTicket() throws IOException {
GetMethod get = httpGet("/security/ticket");
get.addRequestHeader("Origin", "http://localhost");
Map<String, Object> resp = gson.fromJson(get.getResponseBodyAsString(),
new TypeToken<Map<String, Object>>(){}.getType());
Map<String, String> body = (Map<String, String>) resp.get("body");
assertEquals("anonymous", body.get("principal"));
assertEquals("anonymous", body.get("ticket"));
get.releaseConnection();
}
}

Some files were not shown because too many files have changed in this diff Show more