You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@knox.apache.org by su...@apache.org on 2015/05/26 18:07:09 UTC
svn commit: r1681785 [4/8] - in /knox: site/ site/books/knox-0-7-0/ trunk/
trunk/books/0.7.0/ trunk/books/0.7.0/dev-guide/
Added: knox/site/books/knox-0-7-0/warning.png
URL: http://svn.apache.org/viewvc/knox/site/books/knox-0-7-0/warning.png?rev=1681785&view=auto
==============================================================================
Binary file - no diff available.
Propchange: knox/site/books/knox-0-7-0/warning.png
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
Added: knox/site/books/knox-0-7-0/workflow-configuration.xml
URL: http://svn.apache.org/viewvc/knox/site/books/knox-0-7-0/workflow-configuration.xml?rev=1681785&view=auto
==============================================================================
--- knox/site/books/knox-0-7-0/workflow-configuration.xml (added)
+++ knox/site/books/knox-0-7-0/workflow-configuration.xml Tue May 26 16:07:07 2015
@@ -0,0 +1,47 @@
+<?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.
+-->
+<configuration>
+ <property>
+ <name>jobTracker</name>
+ <value>REPLACE.JOBTRACKER.RPCHOSTPORT</value>
+ <!-- Example: <value>localhost:50300</value> -->
+ </property>
+ <property>
+ <name>nameNode</name>
+ <value>hdfs://REPLACE.NAMENODE.RPCHOSTPORT</value>
+ <!-- Example: <value>hdfs://localhost:8020</value> -->
+ </property>
+ <property>
+ <name>oozie.wf.application.path</name>
+ <value>hdfs://REPLACE.NAMENODE.RPCHOSTPORT/tmp/test</value>
+ <!-- Example: <value>hdfs://localhost:8020/tmp/test</value> -->
+ </property>
+ <property>
+ <name>user.name</name>
+ <value>mapred</value>
+ </property>
+ <property>
+ <name>inputDir</name>
+ <value>/tmp/test/input</value>
+ </property>
+ <property>
+ <name>outputDir</name>
+ <value>/tmp/test/output</value>
+ </property>
+</configuration>
Added: knox/site/books/knox-0-7-0/workflow-definition.xml
URL: http://svn.apache.org/viewvc/knox/site/books/knox-0-7-0/workflow-definition.xml?rev=1681785&view=auto
==============================================================================
--- knox/site/books/knox-0-7-0/workflow-definition.xml (added)
+++ knox/site/books/knox-0-7-0/workflow-definition.xml Tue May 26 16:07:07 2015
@@ -0,0 +1,36 @@
+<?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.
+-->
+<workflow-app xmlns="uri:oozie:workflow:0.2" name="wordcount-workflow">
+ <start to="root"/>
+ <action name="root">
+ <java>
+ <job-tracker>${jobTracker}</job-tracker>
+ <name-node>${nameNode}</name-node>
+ <main-class>org.apache.hadoop.examples.WordCount</main-class>
+ <arg>${inputDir}</arg>
+ <arg>${outputDir}</arg>
+ </java>
+ <ok to="end"/>
+ <error to="fail"/>
+ </action>
+ <kill name="fail">
+ <message>Java failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+ </kill>
+ <end name="end"/>
+</workflow-app>
\ No newline at end of file
Modified: knox/site/index.html
URL: http://svn.apache.org/viewvc/knox/site/index.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/index.html (original)
+++ knox/site/index.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Modified: knox/site/issue-tracking.html
URL: http://svn.apache.org/viewvc/knox/site/issue-tracking.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/issue-tracking.html (original)
+++ knox/site/issue-tracking.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Modified: knox/site/license.html
URL: http://svn.apache.org/viewvc/knox/site/license.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/license.html (original)
+++ knox/site/license.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Modified: knox/site/mail-lists.html
URL: http://svn.apache.org/viewvc/knox/site/mail-lists.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/mail-lists.html (original)
+++ knox/site/mail-lists.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Modified: knox/site/project-info.html
URL: http://svn.apache.org/viewvc/knox/site/project-info.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/project-info.html (original)
+++ knox/site/project-info.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Modified: knox/site/team-list.html
URL: http://svn.apache.org/viewvc/knox/site/team-list.html?rev=1681785&r1=1681784&r2=1681785&view=diff
==============================================================================
--- knox/site/team-list.html (original)
+++ knox/site/team-list.html Tue May 26 16:07:07 2015
@@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-11 -->
+<!-- Generated by Apache Maven Doxia Site Renderer 1.6 at 2015-05-26 -->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
@@ -10,7 +10,7 @@
@import url("./css/site.css");
</style>
<link rel="stylesheet" href="./css/print.css" type="text/css" media="print" />
- <meta name="Date-Revision-yyyymmdd" content="20150511" />
+ <meta name="Date-Revision-yyyymmdd" content="20150526" />
<meta http-equiv="Content-Language" content="en" />
<script type="text/javascript">var _gaq = _gaq || [];
@@ -57,7 +57,7 @@
<a href="https://cwiki.apache.org/confluence/display/KNOX/Index" class="externalLink" title="Wiki">Wiki</a>
- | <span id="publishDate">Last Published: 2015-05-11</span>
+ | <span id="publishDate">Last Published: 2015-05-26</span>
| <span id="projectVersion">Version: 0.0.0-SNAPSHOT</span>
</div>
<div class="clear">
Added: knox/trunk/books/0.7.0/admin_api.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/admin_api.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/admin_api.md (added)
+++ knox/trunk/books/0.7.0/admin_api.md Tue May 26 16:07:07 2015
@@ -0,0 +1,159 @@
+<!---
+ 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.
+--->
+
+### Admin API ###
+
+Access to the administrator functions of Knox are provided by the Admin REST API.
+
+#### Admin API URL ####
+
+The URL mapping for the Knox Admin API is simple:
+
+| ------- | ----------------------------------------------------------------------------- |
+| Gateway | `https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1` |
+
+Please note that to access that admin API, the user attempting to connect must have admin credentials inside of the LDAP Server
+
+
+##### API Documentation
+
+###### Operations
+
+ * ###### HTTP GET
+ 1. #[Server Version]
+ 2. #[Topology Collection]
+ 3. #[Topology]
+ * ###### HTTP PUT
+ * ###### HTTP DELETE
+
+##### Server Version
+
+###### Description
+
+Calls to Knox and returns the gateway's current version and the version hash inside of a JSON object.
+
+###### Example Request URL
+
+`https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1/version`
+
+###### Example cURL Request
+
+`curl -u admin:admin-password -i -k https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1/version`
+
+###### Response
+
+ <ServerVersion>
+ <version>0.6.0</version>
+ <hash>{version-hash}</hash>
+ </ServerVersion>
+
+##### Topology Collection
+
+###### Description
+
+Calls to Knox and return an array of JSON objects that represent the list of deployed topologies currently inside of the gateway.
+
+###### Example Request URL
+
+`https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/{api-version}/topologies`
+
+###### Example cURL Request
+
+`curl -u admin:admin-password -i -k -H Accept:application/json https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1/topologies`
+
+###### Response
+
+ [
+ {
+ "href":"https://localhost:8443/gateway/admin/api/v1/topologies/_default",
+ "name":"_default",
+ "timestamp":"1405633120000",
+ "uri":"https://localhost:8443/gateway/_default"
+ },
+ {
+ "href":"https://localhost:8443/gateway/admin/api/v1/topologies/admin",
+ "name":"admin",
+ "timestamp":"1406672646000",
+ "uri":"https://localhost:8443/gateway/admin"
+ }
+ ]
+
+
+##### Topology
+
+###### Description
+
+Calls to Knox and return a JSON object that represents the requested topology
+
+###### Example Request URL
+
+`https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1/topologies/{topology-name}`
+
+###### Example cURL Request
+
+`curl -u admin:admin-password -i -k -H Accept:application/json https://{gateway-host}:{gateway-port}/{gateway-path}/admin/api/v1/topologies/{topology-name}`
+
+###### Response
+
+ {
+ "name": "admin",
+ "providers": [{
+ "enabled": true,
+ "name": "ShiroProvider",
+ "params": {
+ "sessionTimeout": "30",
+ "main.ldapRealm": "org.apache.hadoop.gateway.shirorealm.KnoxLdapRealm",
+ "main.ldapRealm.userDnTemplate": "uid={0},ou=people,dc=hadoop,dc=apache,dc=org",
+ "main.ldapRealm.contextFactory.url": "ldap://localhost:33389",
+ "main.ldapRealm.contextFactory.authenticationMechanism": "simple",
+ "urls./**": "authcBasic"
+ },
+ "role": "authentication"
+ }, {
+ "enabled": true,
+ "name": "AclsAuthz",
+ "params": {
+ "knox.acl": "admin;*;*"
+ },
+ "role": "authorization"
+ }, {
+ "enabled": true,
+ "name": "Default",
+ "params": {},
+ "role": "identity-assertion"
+ }, {
+ "enabled": true,
+ "name": "static",
+ "params": {
+ "localhost": "sandbox,sandbox.hortonworks.com"
+ },
+ "role": "hostmap"
+ }],
+ "services": [{
+ "name": null,
+ "params": {},
+ "role": "KNOX",
+ "url": null
+ }],
+ "timestamp": 1406672646000,
+ "uri": "https://localhost:8443/gateway/admin"
+ }
+
+
+
+
+
Added: knox/trunk/books/0.7.0/book.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book.md (added)
+++ knox/trunk/books/0.7.0/book.md Tue May 26 16:07:07 2015
@@ -0,0 +1,113 @@
+<!--
+ 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.
+-->
+
+<<../common/header.md>>
+
+<img src="knox-logo.gif" alt="Knox"/>
+<!-- <img src="apache-logo.gif" alt="Apache"/> -->
+<img src="apache-logo.gif" align="right" alt="Apache"/>
+
+# Apache Knox Gateway 0.6.x User's Guide #
+
+## Table Of Contents ##
+
+* #[Introduction]
+* #[Quick Start]
+* #[Gateway Samples]
+* #[Apache Knox Details]
+ * #[Apache Knox Directory Layout]
+ * #[Supported Services]
+* #[Gateway Details]
+ * #[URL Mapping]
+ * #[Configuration]
+ * #[Knox CLI]
+ * #[Admin API]
+ * #[Authentication]
+ * #[Advanced LDAP Authentication]
+ * #[LDAP Authentication Caching]
+ * #[LDAPGroupLookup]
+ * #[Identity Assertion]
+ * #[Authorization]
+ * #[Secure Clusters]
+ * #[High Availability]
+ * #[Web App Security Provider]
+ * #[Preauthenticated SSO Provider]
+ * #[Audit]
+* #[Client Details]
+* #[Service Details]
+ * #[WebHDFS]
+ * #[WebHCat]
+ * #[Oozie]
+ * #[HBase]
+ * #[Hive]
+ * #[Yarn]
+ * #[Storm]
+* #[Limitations]
+* #[Troubleshooting]
+* #[Export Controls]
+
+
+## Introduction ##
+
+The Apache Knox Gateway is a system that provides a single point of authentication and access for Apache Hadoop services in a cluster.
+The goal is to simplify Hadoop security for both users (i.e. who access the cluster data and execute jobs) and operators (i.e. who control access and manage the cluster).
+The gateway runs as a server (or cluster of servers) that provide centralized access to one or more Hadoop clusters.
+In general the goals of the gateway are as follows:
+
+* Provide perimeter security for Hadoop REST APIs to make Hadoop security easier to setup and use
+ * Provide authentication and token verification at the perimeter
+ * Enable authentication integration with enterprise and cloud identity management systems
+ * Provide service level authorization at the perimeter
+* Expose a single URL hierarchy that aggregates REST APIs of a Hadoop cluster
+ * Limit the network endpoints (and therefore firewall holes) required to access a Hadoop cluster
+ * Hide the internal Hadoop cluster topology from potential attackers
+
+<<quick_start.md>>
+<<book_getting-started.md>>
+<<book_knox-samples.md>>
+<<book_gateway-details.md>>
+<<book_client-details.md>>
+<<book_service-details.md>>
+<<book_limitations.md>>
+<<book_troubleshooting.md>>
+
+
+## Export Controls ##
+
+Apache Knox Gateway includes cryptographic software.
+The country in which you currently reside may have restrictions on the import, possession, use, and/or
+re-export to another country, of encryption software.
+BEFORE using any encryption software, please check your country's laws, regulations and policies concerning the
+import, possession, or use, and re-export of encryption software, to see if this is permitted.
+See http://www.wassenaar.org for more information.
+
+The U.S. Government Department of Commerce, Bureau of Industry and Security (BIS),
+has classified this software as Export Commodity Control Number (ECCN) 5D002.C.1,
+which includes information security software using or performing cryptographic functions with asymmetric algorithms.
+The form and manner of this Apache Software Foundation distribution makes it eligible for export under the
+License Exception ENC Technology Software Unrestricted (TSU) exception
+(see the BIS Export Administration Regulations, Section 740.13) for both object code and source code.
+
+The following provides more details on the included cryptographic software:
+
+* Apache Knox Gateway uses the ApacheDS which in turn uses Bouncy Castle generic encryption libraries.
+* See http://www.bouncycastle.org for more details on Bouncy Castle.
+* See http://directory.apache.org/apacheds for more details on ApacheDS.
+
+
+<<../common/footer.md>>
+
Added: knox/trunk/books/0.7.0/book_client-details.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_client-details.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_client-details.md (added)
+++ knox/trunk/books/0.7.0/book_client-details.md Tue May 26 16:07:07 2015
@@ -0,0 +1,516 @@
+<!---
+ 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.
+--->
+
+## Client Details ##
+
+Hadoop requires a client that can be used to interact remotely with the services provided by Hadoop cluster.
+This will also be true when using the Apache Knox Gateway to provide perimeter security and centralized access for these services.
+The two primary existing clients for Hadoop are the CLI (i.e. Command Line Interface, hadoop) and HUE (i.e. Hadoop User Environment).
+For several reasons however, neither of these clients can _currently_ be used to access Hadoop services via the Apache Knox Gateway.
+
+This led to thinking about a very simple client that could help people use and evaluate the gateway.
+The list below outlines the general requirements for such a client.
+
+* Promote the evaluation and adoption of the Apache Knox Gateway
+* Simple to deploy and use on data worker desktops to access to remote Hadoop clusters
+* Simple to extend with new commands both by other Hadoop projects and by the end user
+* Support the notion of a SSO session for multiple Hadoop interactions
+* Support the multiple authentication and federation token capabilities of the Apache Knox Gateway
+* Promote the use of REST APIs as the dominant remote client mechanism for Hadoop services
+* Promote the the sense of Hadoop as a single unified product
+* Aligned with the Apache Knox Gateway's overall goals for security
+
+The result is a very simple DSL ([Domain Specific Language](http://en.wikipedia.org/wiki/Domain-specific_language)) of sorts that is used via [Groovy](http://groovy.codehaus.org) scripts.
+Here is an example of a command that copies a file from the local file system to HDFS.
+
+_Note: The variables session, localFile and remoteFile are assumed to be defined._
+
+ Hdfs.put( session ).file( localFile ).to( remoteFile ).now()
+
+*This work is very early in development but is also very useful in its current state.*
+*We are very interested in receiving feedback about how to improve this feature and the DSL in particular.*
+
+A note of thanks to [REST-assured](https://code.google.com/p/rest-assured/) which provides a [Fluent interface](http://en.wikipedia.org/wiki/Fluent_interface) style DSL for testing REST services.
+It served as the initial inspiration for the creation of this DSL.
+
+
+### Assumptions ###
+
+This document assumes a few things about your environment in order to simplify the examples.
+
+* The JVM is executable as simply java.
+* The Apache Knox Gateway is installed and functional.
+* The example commands are executed within the context of the GATEWAY_HOME current directory.
+The GATEWAY_HOME directory is the directory within the Apache Knox Gateway installation that contains the README file and the bin, conf and deployments directories.
+* A few examples require the use of commands from a standard Groovy installation. These examples are optional but to try them you will need Groovy [installed](http://groovy.codehaus.org/Installing+Groovy).
+
+
+### Basics ###
+
+The DSL requires a shell to interpret the Groovy script.
+The shell can either be used interactively or to execute a script file.
+To simplify use, the distribution contains an embedded version of the Groovy shell.
+
+The shell can be run interactively. Use the command `exit` to exit.
+
+ java -jar bin/shell.jar
+
+When running interactively it may be helpful to reduce some of the output generated by the shell console.
+Use the following command in the interactive shell to reduce that output.
+This only needs to be done once as these preferences are persisted.
+
+ set verbosity QUIET
+ set show-last-result false
+
+Also when running interactively use the `exit` command to terminate the shell.
+Using `^C` to exit can sometimes leaves the parent shell in a problematic state.
+
+The shell can also be used to execute a script by passing a single filename argument.
+
+ java -jar bin/shell.jar samples/ExampleWebHdfsPutGet.groovy
+
+
+### Examples ###
+
+Once the shell can be launched the DSL can be used to interact with the gateway and Hadoop.
+Below is a very simple example of an interactive shell session to upload a file to HDFS.
+
+ java -jar bin/shell.jar
+ knox:000> session = Hadoop.login( "https://localhost:8443/gateway/sandbox", "guest", "guest-password" )
+ knox:000> Hdfs.put( session ).file( "README" ).to( "/tmp/example/README" ).now()
+
+The `knox:000>` in the example above is the prompt from the embedded Groovy console.
+If you output doesn't look like this you may need to set the verbosity and show-last-result preferences as described above in the Usage section.
+
+If you relieve an error `HTTP/1.1 403 Forbidden` it may be because that file already exists.
+Try deleting it with the following command and then try again.
+
+ knox:000> Hdfs.rm(session).file("/tmp/example/README").now()
+
+Without using some other tool to browse HDFS it is hard to tell that that this command did anything.
+Execute this to get a bit more feedback.
+
+ knox:000> println "Status=" + Hdfs.put( session ).file( "README" ).to( "/tmp/example/README2" ).now().statusCode
+ Status=201
+
+Notice that a different filename is used for the destination.
+Without this an error would have resulted.
+Of course the DSL also provides a command to list the contents of a directory.
+
+ knox:000> println Hdfs.ls( session ).dir( "/tmp/example" ).now().string
+ {"FileStatuses":{"FileStatus":[{"accessTime":1363711366977,"blockSize":134217728,"group":"hdfs","length":19395,"modificationTime":1363711366977,"owner":"guest","pathSuffix":"README","permission":"644","replication":1,"type":"FILE"},{"accessTime":1363711375617,"blockSize":134217728,"group":"hdfs","length":19395,"modificationTime":1363711375617,"owner":"guest","pathSuffix":"README2","permission":"644","replication":1,"type":"FILE"}]}}
+
+It is a design decision of the DSL to not provide type safe classes for various request and response payloads.
+Doing so would provide an undesirable coupling between the DSL and the service implementation.
+It also would make adding new commands much more difficult.
+See the Groovy section below for a variety capabilities and tools for working with JSON and XML to make this easy.
+The example below shows the use of JsonSlurper and GPath to extract content from a JSON response.
+
+ knox:000> import groovy.json.JsonSlurper
+ knox:000> text = Hdfs.ls( session ).dir( "/tmp/example" ).now().string
+ knox:000> json = (new JsonSlurper()).parseText( text )
+ knox:000> println json.FileStatuses.FileStatus.pathSuffix
+ [README, README2]
+
+*In the future, "built-in" methods to slurp JSON and XML may be added to make this a bit easier.*
+*This would allow for this type if single line interaction.*
+
+ println Hdfs.ls(session).dir("/tmp").now().json().FileStatuses.FileStatus.pathSuffix
+
+Shell session should always be ended with shutting down the session.
+The examples above do not touch on it but the DSL supports the simple execution of commands asynchronously.
+The shutdown command attempts to ensures that all asynchronous commands have completed before existing the shell.
+
+ knox:000> session.shutdown()
+ knox:000> exit
+
+All of the commands above could have been combined into a script file and executed as a single line.
+
+ java -jar bin/shell.jar samples/ExampleWebHdfsPutGet.groovy
+
+This would be the content of that script.
+
+ import org.apache.hadoop.gateway.shell.Hadoop
+ import org.apache.hadoop.gateway.shell.hdfs.Hdfs
+ import groovy.json.JsonSlurper
+
+ gateway = "https://localhost:8443/gateway/sandbox"
+ username = "guest"
+ password = "guest-password"
+ dataFile = "README"
+
+ session = Hadoop.login( gateway, username, password )
+ Hdfs.rm( session ).file( "/tmp/example" ).recursive().now()
+ Hdfs.put( session ).file( dataFile ).to( "/tmp/example/README" ).now()
+ text = Hdfs.ls( session ).dir( "/tmp/example" ).now().string
+ json = (new JsonSlurper()).parseText( text )
+ println json.FileStatuses.FileStatus.pathSuffix
+ session.shutdown()
+ exit
+
+Notice the `Hdfs.rm` command. This is included simply to ensure that the script can be rerun.
+Without this an error would result the second time it is run.
+
+
+### Futures ###
+
+The DSL supports the ability to invoke commands asynchronously via the later() invocation method.
+The object returned from the later() method is a java.util.concurrent.Future parametrized with the response type of the command.
+This is an example of how to asynchronously put a file to HDFS.
+
+ future = Hdfs.put(session).file("README").to("/tmp/example/README").later()
+ println future.get().statusCode
+
+The future.get() method will block until the asynchronous command is complete.
+To illustrate the usefulness of this however multiple concurrent commands are required.
+
+ readmeFuture = Hdfs.put(session).file("README").to("/tmp/example/README").later()
+ licenseFuture = Hdfs.put(session).file("LICENSE").to("/tmp/example/LICENSE").later()
+ session.waitFor( readmeFuture, licenseFuture )
+ println readmeFuture.get().statusCode
+ println licenseFuture.get().statusCode
+
+The session.waitFor() method will wait for one or more asynchronous commands to complete.
+
+
+### Closures ###
+
+Futures alone only provide asynchronous invocation of the command.
+What if some processing should also occur asynchronously once the command is complete.
+Support for this is provided by closures.
+Closures are blocks of code that are passed into the later() invocation method.
+In Groovy these are contained within {} immediately after a method.
+These blocks of code are executed once the asynchronous command is complete.
+
+ Hdfs.put(session).file("README").to("/tmp/example/README").later(){ println it.statusCode }
+
+In this example the put() command is executed on a separate thread and once complete the `println it.statusCode` block is executed on that thread.
+The it variable is automatically populated by Groovy and is a reference to the result that is returned from the future or now() method.
+The future example above can be rewritten to illustrate the use of closures.
+
+ readmeFuture = Hdfs.put(session).file("README").to("/tmp/example/README").later() { println it.statusCode }
+ licenseFuture = Hdfs.put(session).file("LICENSE").to("/tmp/example/LICENSE").later() { println it.statusCode }
+ session.waitFor( readmeFuture, licenseFuture )
+
+Again, the session.waitFor() method will wait for one or more asynchronous commands to complete.
+
+
+### Constructs ###
+
+In order to understand the DSL there are three primary constructs that need to be understood.
+
+
+#### Session ####
+
+This construct encapsulates the client side session state that will be shared between all command invocations.
+In particular it will simplify the management of any tokens that need to be presented with each command invocation.
+It also manages a thread pool that is used by all asynchronous commands which is why it is important to call one of the shutdown methods.
+
+The syntax associated with this is expected to change we expect that credentials will not need to be provided to the gateway.
+Rather it is expected that some form of access token will be used to initialize the session.
+
+
+#### Services ####
+
+Services are the primary extension point for adding new suites of commands.
+The current built in examples are: Hdfs, Job and Workflow.
+The desire for extensibility is the reason for the slightly awkward Hdfs.ls(session) syntax.
+Certainly something more like `session.hdfs().ls()` would have been preferred but this would prevent adding new commands easily.
+At a minimum it would result in extension commands with a different syntax from the "built-in" commands.
+
+The service objects essentially function as a factory for a suite of commands.
+
+
+#### Commands ####
+
+Commands provide the behavior of the DSL.
+They typically follow a Fluent interface style in order to allow for single line commands.
+There are really three parts to each command: Request, Invocation, Response
+
+
+#### Request ####
+
+The request is populated by all of the methods following the "verb" method and the "invoke" method.
+For example in `Hdfs.rm(session).ls(dir).now()` the request is populated between the "verb" method `rm()` and the "invoke" method `now()`.
+
+
+#### Invocation ####
+
+The invocation method controls how the request is invoked.
+Currently supported synchronous and asynchronous invocation.
+The now() method executes the request and returns the result immediately.
+The later() method submits the request to be executed later and returns a future from which the result can be retrieved.
+In addition later() invocation method can optionally be provided a closure to execute when the request is complete.
+See the Futures and Closures sections below for additional detail and examples.
+
+
+#### Response ####
+
+The response contains the results of the invocation of the request.
+In most cases the response is a thin wrapper over the HTTP response.
+In fact many commands will share a single BasicResponse type that only provides a few simple methods.
+
+ public int getStatusCode()
+ public long getContentLength()
+ public String getContentType()
+ public String getContentEncoding()
+ public InputStream getStream()
+ public String getString()
+ public byte[] getBytes()
+ public void close();
+
+Thanks to Groovy these methods can be accessed as attributes.
+In the some of the examples the staticCode was retrieved for example.
+
+ println Hdfs.put(session).rm(dir).now().statusCode
+
+Groovy will invoke the getStatusCode method to retrieve the statusCode attribute.
+
+The three methods getStream(), getBytes() and getString deserve special attention.
+Care must be taken that the HTTP body is fully read once and only once.
+Therefore one of these methods (and only one) must be called once and only once.
+Calling one of these more than once will cause an error.
+Failing to call one of these methods once will result in lingering open HTTP connections.
+The close() method may be used if the caller is not interested in reading the result body.
+Most commands that do not expect a response body will call close implicitly.
+If the body is retrieved via getBytes() or getString(), the close() method need not be called.
+When using getStream(), care must be taken to consume the entire body otherwise lingering open HTTP connections will result.
+The close() method may be called after reading the body partially to discard the remainder of the body.
+
+
+### Services ###
+
+The built-in supported client DLS for each Hadoop service can be found in the #[Service Details] section.
+
+
+### Extension ###
+
+Extensibility is a key design goal of the KnoxShell and client DSL.
+There are two ways to provide extended functionality for use with the shell.
+The first is to simply create Groovy scripts that use the DSL to perform a useful task.
+The second is to add new services and commands.
+In order to add new service and commands new classes must be written in either Groovy or Java and added to the classpath of the shell.
+Fortunately there is a very simple way to add classes and JARs to the shell classpath.
+The first time the shell is executed it will create a configuration file in the same directory as the JAR with the same base name and a `.cfg` extension.
+
+ bin/shell.jar
+ bin/shell.cfg
+
+That file contains both the main class for the shell as well as a definition of the classpath.
+Currently that file will by default contain the following.
+
+ main.class=org.apache.hadoop.gateway.shell.Shell
+ class.path=../lib; ../lib/*.jar; ../ext; ../ext/*.jar
+
+Therefore to extend the shell you should copy any new service and command class either to the `ext` directory or if they are packaged within a JAR copy the JAR to the `ext` directory.
+The `lib` directory is reserved for JARs that may be delivered with the product.
+
+Below are samples for the service and command classes that would need to be written to add new commands to the shell.
+These happen to be Groovy source files but could with very minor changes be Java files.
+The easiest way to add these to the shell is to compile them directory into the `ext` directory.
+*Note: This command depends upon having the Groovy compiler installed and available on the execution path.*
+
+ groovy -d ext -cp bin/shell.jar samples/SampleService.groovy \
+ samples/SampleSimpleCommand.groovy samples/SampleComplexCommand.groovy
+
+These source files are available in the samples directory of the distribution but these are included here for convenience.
+
+
+#### Sample Service (Groovy)
+
+ import org.apache.hadoop.gateway.shell.Hadoop
+
+ class SampleService {
+
+ static String PATH = "/webhdfs/v1"
+
+ static SimpleCommand simple( Hadoop session ) {
+ return new SimpleCommand( session )
+ }
+
+ static ComplexCommand.Request complex( Hadoop session ) {
+ return new ComplexCommand.Request( session )
+ }
+
+ }
+
+#### Sample Simple Command (Groovy)
+
+ import org.apache.hadoop.gateway.shell.AbstractRequest
+ import org.apache.hadoop.gateway.shell.BasicResponse
+ import org.apache.hadoop.gateway.shell.Hadoop
+ import org.apache.http.client.methods.HttpGet
+ import org.apache.http.client.utils.URIBuilder
+
+ import java.util.concurrent.Callable
+
+ class SimpleCommand extends AbstractRequest<BasicResponse> {
+
+ SimpleCommand( Hadoop session ) {
+ super( session )
+ }
+
+ private String param
+ SimpleCommand param( String param ) {
+ this.param = param
+ return this
+ }
+
+ @Override
+ protected Callable<BasicResponse> callable() {
+ return new Callable<BasicResponse>() {
+ @Override
+ BasicResponse call() {
+ URIBuilder uri = uri( SampleService.PATH, param )
+ addQueryParam( uri, "op", "LISTSTATUS" )
+ HttpGet get = new HttpGet( uri.build() )
+ return new BasicResponse( execute( get ) )
+ }
+ }
+ }
+
+ }
+
+
+#### Sample Complex Command (Groovy)
+
+ import com.jayway.jsonpath.JsonPath
+ import org.apache.hadoop.gateway.shell.AbstractRequest
+ import org.apache.hadoop.gateway.shell.BasicResponse
+ import org.apache.hadoop.gateway.shell.Hadoop
+ import org.apache.http.HttpResponse
+ import org.apache.http.client.methods.HttpGet
+ import org.apache.http.client.utils.URIBuilder
+
+ import java.util.concurrent.Callable
+
+ class ComplexCommand {
+
+ static class Request extends AbstractRequest<Response> {
+
+ Request( Hadoop session ) {
+ super( session )
+ }
+
+ private String param;
+ Request param( String param ) {
+ this.param = param;
+ return this;
+ }
+
+ @Override
+ protected Callable<Response> callable() {
+ return new Callable<Response>() {
+ @Override
+ Response call() {
+ URIBuilder uri = uri( SampleService.PATH, param )
+ addQueryParam( uri, "op", "LISTSTATUS" )
+ HttpGet get = new HttpGet( uri.build() )
+ return new Response( execute( get ) )
+ }
+ }
+ }
+
+ }
+
+ static class Response extends BasicResponse {
+
+ Response(HttpResponse response) {
+ super(response)
+ }
+
+ public List<String> getNames() {
+ return JsonPath.read( string, "\$.FileStatuses.FileStatus[*].pathSuffix" )
+ }
+
+ }
+
+ }
+
+
+### Groovy
+
+The shell included in the distribution is basically an unmodified packaging of the Groovy shell.
+The distribution does however provide a wrapper that makes it very easy to setup the class path for the shell.
+In fact the JARs required to execute the DSL are included on the class path by default.
+Therefore these command are functionally equivalent if you have Groovy [installed][15].
+See below for a description of what is required for JARs required by the DSL from `lib` and `dep` directories.
+
+ java -jar bin/shell.jar samples/ExampleWebHdfsPutGet.groovy
+ groovy -classpath {JARs required by the DSL from lib and dep} samples/ExampleWebHdfsPutGet.groovy
+
+The interactive shell isn't exactly equivalent.
+However the only difference is that the shell.jar automatically executes some additional imports that are useful for the KnoxShell client DSL.
+So these two sets of commands should be functionality equivalent.
+*However there is currently a class loading issue that prevents the groovysh command from working properly.*
+
+ java -jar bin/shell.jar
+
+ groovysh -classpath {JARs required by the DSL from lib and dep}
+ import org.apache.hadoop.gateway.shell.Hadoop
+ import org.apache.hadoop.gateway.shell.hdfs.Hdfs
+ import org.apache.hadoop.gateway.shell.job.Job
+ import org.apache.hadoop.gateway.shell.workflow.Workflow
+ import java.util.concurrent.TimeUnit
+
+Alternatively, you can use the Groovy Console which does not appear to have the same class loading issue.
+
+ groovyConsole -classpath {JARs required by the DSL from lib and dep}
+
+ import org.apache.hadoop.gateway.shell.Hadoop
+ import org.apache.hadoop.gateway.shell.hdfs.Hdfs
+ import org.apache.hadoop.gateway.shell.job.Job
+ import org.apache.hadoop.gateway.shell.workflow.Workflow
+ import java.util.concurrent.TimeUnit
+
+The JARs currently required by the client DSL are
+
+ lib/gateway-shell-${gateway-version}.jar
+ dep/httpclient-4.2.3.jar
+ dep/httpcore-4.2.2.jar
+ dep/commons-lang3-3.1.jar
+ dep/commons-codec-1.7.jar
+
+So on Linux/MacOS you would need this command
+
+ groovy -cp lib/gateway-shell-0.4.0.jar:dep/httpclient-4.2.5.jar:dep/httpcore-4.2.4.jar:dep/commons-lang3-3.1.jar:dep/commons-codec-1.7.jar samples/ExampleWebHdfsPutGet.groovy
+
+and on Windows you would need this command
+
+ groovy -cp lib/gateway-shell-0.4.0.jar;dep/httpclient-4.2.5.jar;dep/httpcore-4.2.4.jar;dep/commons-lang3-3.1.jar;dep/commons-codec-1.7.jar samples/ExampleWebHdfsPutGet.groovy
+
+The exact list of required JARs is likely to change from release to release so it is recommended that you utilize the wrapper `bin/shell.jar`.
+
+In addition because the DSL can be used via standard Groovy, the Groovy integrations in many popular IDEs (e.g. IntelliJ , Eclipse) can also be used.
+This makes it particularly nice to develop and execute scripts to interact with Hadoop.
+The code-completion features in modern IDEs in particular provides immense value.
+All that is required is to add the gateway-shell-0.4.0.jar to the projects class path.
+
+There are a variety of Groovy tools that make it very easy to work with the standard interchange formats (i.e. JSON and XML).
+In Groovy the creation of XML or JSON is typically done via a "builder" and parsing done via a "slurper".
+In addition once JSON or XML is "slurped" the GPath, an XPath like feature build into Groovy can be used to access data.
+
+* XML
+ * Markup Builder [Overview](http://groovy.codehaus.org/Creating+XML+using+Groovy's+MarkupBuilder), [API](http://groovy.codehaus.org/api/groovy/xml/MarkupBuilder.html)
+ * XML Slurper [Overview](http://groovy.codehaus.org/Reading+XML+using+Groovy's+XmlSlurper), [API](http://groovy.codehaus.org/api/groovy/util/XmlSlurper.html)
+ * XPath [Overview](http://groovy.codehaus.org/GPath), [API](http://docs.oracle.com/javase/1.5.0/docs/api/javax/xml/xpath/XPath.html)
+* JSON
+ * JSON Builder [API](http://groovy.codehaus.org/gapi/groovy/json/JsonBuilder.html)
+ * JSON Slurper [API](http://groovy.codehaus.org/gapi/groovy/json/JsonSlurper.html)
+ * JSON Path [API](https://code.google.com/p/json-path/)
+ * GPath [Overview](http://groovy.codehaus.org/GPath)
+
Added: knox/trunk/books/0.7.0/book_gateway-details.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_gateway-details.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_gateway-details.md (added)
+++ knox/trunk/books/0.7.0/book_gateway-details.md Tue May 26 16:07:07 2015
@@ -0,0 +1,93 @@
+<!---
+ 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.
+--->
+
+## Gateway Details ##
+
+This section describes the details of the Knox Gateway itself. Including:
+
+* How URLs are mapped between a gateway that services multiple Hadoop clusters and the clusters themselves
+* How the gateway is configured through gateway-site.xml and cluster specific topology files
+* How to configure the various policy enfocement provider features such as authentication, authorization, auditing, hostmapping, etc.
+
+### URL Mapping ###
+
+The gateway functions much like a reverse proxy.
+As such, it maintains a mapping of URLs that are exposed externally by the gateway to URLs that are provided by the Hadoop cluster.
+
+#### Default Topology URLs #####
+In order to provide compatibility with the Hadoop java client and existing CLI tools, the Knox Gateway has provided a feature called the Default Topology. This refers to a topology deployment that will be able to route URLs without the additional context that the gateway uses for differentiating from one Hadoop cluster to another. This allows the URLs to match those used by existing clients for that may access webhdfs through the Hadoop file system abstraction.
+
+When a topology file is deployed with a file name that matches the configured default topology name, a specialized mapping for URLs is installed for that particular topology. This allows the URLs that are expected by the existing Hadoop CLIs for webhdfs to be used in interacting with the specific Hadoop cluster that is represented by the default topology file.
+
+The configuration for the default topology name is found in gateway-site.xml as a property called: "default.app.topology.name".
+
+The default value for this property is "sandbox".
+
+Therefore, when deploying the sandbox.xml topology, both of the following example URLs work for the same underlying Hadoop cluster:
+
+ https://{gateway-host}:{gateway-port}/webhdfs
+ https://{gateway-host}:{gateway-port}/{gateway-path}/{cluster-name}/webhdfs
+
+These default topology URLs exist for all of the services in the topology.
+
+#### Fully Qualified URLs #####
+Examples of mappings for the WebHDFS, WebHCat, Oozie and Stargate/HBase are shown below.
+These mapping are generated from the combination of the gateway configuration file (i.e. `{GATEWAY_HOME}/conf/gateway-site.xml`) and the cluster topology descriptors (e.g. `{GATEWAY_HOME}/conf/topologies/{cluster-name}.xml`).
+The port numbers show for the Cluster URLs represent the default ports for these services.
+The actual port number may be different for a given cluster.
+
+* WebHDFS
+ * Gateway: `https://{gateway-host}:{gateway-port}/{gateway-path}/{cluster-name}/webhdfs`
+ * Cluster: `http://{webhdfs-host}:50070/webhdfs`
+* WebHCat (Templeton)
+ * Gateway: `https://{gateway-host}:{gateway-port}/{gateway-path}/{cluster-name}/templeton`
+ * Cluster: `http://{webhcat-host}:50111/templeton}`
+* Oozie
+ * Gateway: `https://{gateway-host}:{gateway-port}/{gateway-path}/{cluster-name}/oozie`
+ * Cluster: `http://{oozie-host}:11000/oozie}`
+* Stargate (HBase)
+ * Gateway: `https://{gateway-host}:{gateway-port}/{gateway-path}/{cluster-name}/hbase`
+ * Cluster: `http://{hbase-host}:60080`
+* Hive JDBC
+ * Gateway: jdbc:hive2://{gateway-host}:{gateway-port}/;ssl=true;sslTrustStore={gateway-trust-store-path};trustStorePassword={gateway-trust-store-password}?hive.server2.transport.mode=http;hive.server2.thrift.http.path={gateway-path}/{cluster-name}/hive
+ * Cluster: `http://{hive-host}:10001/cliservice`
+
+The values for `{gateway-host}`, `{gateway-port}`, `{gateway-path}` are provided via the gateway configuration file (i.e. `{GATEWAY_HOME}/conf/gateway-site.xml`).
+
+The value for `{cluster-name}` is derived from the file name of the cluster topology descriptor (e.g. `{GATEWAY_HOME}/deployments/{cluster-name}.xml`).
+
+The value for `{webhdfs-host}`, `{webhcat-host}`, `{oozie-host}`, `{hbase-host}` and `{hive-host}` are provided via the cluster topology descriptor (e.g. `{GATEWAY_HOME}/conf/topologies/{cluster-name}.xml`).
+
+Note: The ports 50070, 50111, 11000, 60080 (default 8080) and 10001 are the defaults for WebHDFS, WebHCat, Oozie, Stargate/HBase and Hive respectively.
+Their values can also be provided via the cluster topology descriptor if your Hadoop cluster uses different ports.
+
+<<config.md>>
+<<knox_cli.md>>
+<<admin_api.md>>
+<<x-forwarded-headers.md>>
+<<config_authn.md>>
+<<config_advanced_ldap.md>>
+<<config_ldap_authc_cache.md>>
+<<config_ldap_group_lookup.md>>
+<<config_id_assertion.md>>
+<<config_authz.md>>
+<<config_kerberos.md>>
+<<config_ha.md>>
+<<config_webappsec_provider.md>>
+<<config_preauth_sso_provider.md>>
+<<config_mutual_authentication_ssl.md>>
+<<config_audit.md>>
Added: knox/trunk/books/0.7.0/book_getting-started.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_getting-started.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_getting-started.md (added)
+++ knox/trunk/books/0.7.0/book_getting-started.md Tue May 26 16:07:07 2015
@@ -0,0 +1,96 @@
+<!---
+ 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.
+--->
+
+## Apache Knox Details ##
+
+This section provides everything you need to know to get the Knox gateway up and running against a Hadoop cluster.
+
+#### Hadoop ####
+
+An existing Hadoop 2.x cluster is required for Knox 0.6.0 to sit in front of and protect.
+It is possible to use a Hadoop cluster deployed on EC2 but this will require additional configuration not covered here.
+It is also possible to protect access to a services of a Hadoop cluster that is secured with kerberos.
+This too requires additional configuration that is described in other sections of this guide.
+See #[Supported Services] for details on what is supported for this release.
+
+The Hadoop cluster should be ensured to have at least WebHDFS, WebHCat (i.e. Templeton) and Oozie configured, deployed and running.
+HBase/Stargate and Hive can also be accessed via the Knox Gateway given the proper versions and configuration.
+
+The instructions that follow assume a few things:
+
+1. The gateway is *not* collocated with the Hadoop clusters themselves.
+2. The host names and IP addresses of the cluster services are accessible by the gateway where ever it happens to be running.
+
+All of the instructions and samples provided here are tailored and tested to work "out of the box" against a [Hortonworks Sandbox 2.x VM][sandbox].
+
+
+#### Apache Knox Directory Layout ####
+
+Knox can be installed by expanding the zip/archive file.
+
+The table below provides a brief explanation of the important files and directories within `{GATEWWAY_HOME}`
+
+| Directory | Purpose |
+| ------------------------ | ------- |
+| conf/ | Contains configuration files that apply to the gateway globally (i.e. not cluster specific ). |
+| data/ | Contains security and topology specific artifacts that require read/write access at runtime |
+| conf/topologies/ | Contains topology files that represent Hadoop clusters which the gateway uses to deploy cluster proxies |
+| data/security/ | Contains the persisted master secret and keystore dir |
+| data/security/keystores/ | Contains the gateway identity keystore and credential stores for the gateway and each deployed cluster topology |
+| data/services | Contains service behavior definitions for the services currently supported. |
+| bin/ | Contains the executable shell scripts, batch files and JARs for clients and servers. |
+| data/deployments/ | Contains deployed cluster topologies used to protect access to specific Hadoop clusters. |
+| lib/ | Contains the JARs for all the components that make up the gateway. |
+| dep/ | Contains the JARs for all of the components upon which the gateway depends. |
+| ext/ | A directory where user supplied extension JARs can be placed to extends the gateways functionality. |
+| pids/ | Contains the process ids for running ldap and gateway servers |
+| samples/ | Contains a number of samples that can be used to explore the functionality of the gateway. |
+| templates/ | Contains default configuration files that can be copied and customized. |
+| README | Provides basic information about the Apache Knox Gateway. |
+| ISSUES | Describes significant know issues. |
+| CHANGES | Enumerates the changes between releases. |
+| LICENSE | Documents the license under which this software is provided. |
+| NOTICE | Documents required attribution notices for included dependencies. |
+
+
+### Supported Services ###
+
+This table enumerates the versions of various Hadoop services that have been tested to work with the Knox Gateway.
+
+| Service | Version | Non-Secure | Secure |
+| -------------------- | ---------- | ----------- | ------ |
+| WebHDFS | 2.4.0 | ![y] | ![y] |
+| WebHCat/Templeton | 0.13.0 | ![y] | ![y] |
+| Oozie | 4.0.0 | ![y] | ![y] |
+| HBase/Stargate | 0.98.0 | ![y] | ![y] |
+| Hive (via WebHCat) | 0.13.0 | ![y] | ![y] |
+| Hive (via JDBC/ODBC) | 0.13.0 | ![y] | ![y] |
+| Yarn ResourceManager | 2.5.0 | ![y] | ![y] |
+| Storm | 0.9.3 | ![y] | ![n] |
+
+
+### More Examples ###
+
+These examples provide more detail about how to access various Apache Hadoop services via the Apache Knox Gateway.
+
+* #[WebHDFS Examples]
+* #[WebHCat Examples]
+* #[Oozie Examples]
+* #[HBase Examples]
+* #[Hive Examples]
+* #[Yarn Examples]
+* #[Storm Examples]
Added: knox/trunk/books/0.7.0/book_knox-samples.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_knox-samples.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_knox-samples.md (added)
+++ knox/trunk/books/0.7.0/book_knox-samples.md Tue May 26 16:07:07 2015
@@ -0,0 +1,69 @@
+<!---
+ 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.
+--->
+
+### Gateway Samples ###
+
+The purpose of the samples within the {GATEWAY_HOME}/samples directory is to demonstrate the capabilities of the Apache Knox Gateway to provide access to the numerous APIs that are available from the service components of a Hadoop cluster.
+
+Depending on exactly how your Knox installation was done, there will be some number of steps required in order fully install and configure the samples for use.
+
+This section will help describe the assumptions of the samples and the steps to get them to work in a couple of different deployment scenarios.
+
+#### Assumptions of the Samples ####
+
+The samples were initially written with the intent of working out of the box for the various Hadoop demo environments that are deployed as a single node cluster inside of a VM. The following assumptions were made from that context and should be understood in order to get the samples to work in other deployment scenarios:
+
+* That there is a valid java JDK on the PATH for executing the samples
+* The Knox Demo LDAP server is running on localhost and port 33389 which is the default port for the ApacheDS LDAP server.
+* That the LDAP directory in use has a set of demo users provisioned with the convention of username and username"-password" as the password. Most of the samples have some variation of this pattern with "guest" and "guest-password".
+* That the Knox Gateway instance is running on the same machine which you will be running the samples from - therefore "localhost" and that the default port of "8443" is being used.
+* Finally, that there is a properly provisioned sandbox.xml topology in the {GATEWAY_HOME}/conf/topologies directory that is configured to point to the actual host and ports of running service components.
+
+#### Steps for Demo Single Node Clusters ####
+
+There should be little to do if anything in a demo environment that has been provisioned with illustrating the use of Apache Knox.
+
+However, the following items will be worth ensuring before you start:
+
+1. The sandbox.xml topology is configured properly for the deployed services
+2. That there is an LDAP server running with guest/guest-password user available in the directory
+
+#### Steps for Ambari Deployed Knox Gateway ####
+
+Apache Knox instances that are under the management of Ambari are generally assumed not to be demo instances. These instances are in place to facilitate development, testing or production Hadoop clusters.
+
+The Knox samples can however be made to work with Ambari managed Knox instances with a few steps:
+
+1. You need to have ssh access to the environment in order for the localhost assumption within the samples to be valid.
+2. The Knox Demo LDAP Server is started - you can start it from Ambari
+3. The default.xml topology file can be copied to sandbox.xml in order to satisfy the topology name assumption in the samples.
+4. Be sure to use an actual Java JRE to run the sample with something like:
+
+ /usr/jdk64/jdk1.7.0_67/bin/java -jar bin/shell.jar samples/ExampleWebHdfsLs.groovy
+
+#### Steps for a Manually Installed Knox Gateway ####
+
+For manually installed Knox instances, there is really no way for the installer to know how to configure the topology file for you.
+
+Essentially, these steps are identical to the Amabari deployed instance except that #3 should be replaced with the configuration of the ootb sandbox.xml to point the configuration at the proper hosts and ports.
+
+1. You need to have ssh access to the environment in order for the localhost assumption within the samples to be valid.
+2. The Knox Demo LDAP Server is started - you can start it from Ambari
+3. Change the hosts and ports within the {GATEWAY_HOME}/conf/topologies/sandbox.xml to reflect your actual cluster service locations.
+4. Be sure to use an actual Java JRE to run the sample with something like:
+
+ /usr/jdk64/jdk1.7.0_67/bin/java -jar bin/shell.jar samples/ExampleWebHdfsLs.groovy
\ No newline at end of file
Added: knox/trunk/books/0.7.0/book_limitations.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_limitations.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_limitations.md (added)
+++ knox/trunk/books/0.7.0/book_limitations.md Tue May 26 16:07:07 2015
@@ -0,0 +1,34 @@
+<!---
+ 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.
+--->
+
+## Limitations ##
+
+
+### Secure Oozie POST/PUT Request Payload Size Restriction ###
+
+With one exception there are no known size limits for requests or responses payloads that pass through the gateway.
+The exception involves POST or PUT request payload sizes for Oozie in a Kerberos secured Hadoop cluster.
+In this one case there is currently a 4Kb payload size limit for the first request made to the Hadoop cluster.
+This is a result of how the gateway negotiates a trust relationship between itself and the cluster via SPNego.
+There is an undocumented configuration setting to modify this limit's value if required.
+In the future this will be made more easily configuration and at that time it will be documented.
+
+### Group Membership Propagation ###
+
+Groups that are acquired via Shiro Group Lookup and/or Identity Assertion Group Principal Mapping are not propagated to the Hadoop services.
+Therefore, groups used for Service Level Authorization policy may not match those acquired within the cluster via GroupMappingServiceProvider plugins.
+
Added: knox/trunk/books/0.7.0/book_service-details.md
URL: http://svn.apache.org/viewvc/knox/trunk/books/0.7.0/book_service-details.md?rev=1681785&view=auto
==============================================================================
--- knox/trunk/books/0.7.0/book_service-details.md (added)
+++ knox/trunk/books/0.7.0/book_service-details.md Tue May 26 16:07:07 2015
@@ -0,0 +1,86 @@
+<!---
+ 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.
+--->
+
+## Service Details ##
+
+In the sections that follow the integrations currently available out of the box with the gateway will be described.
+In general these sections will include examples that demonstrate how to access each of these services via the gateway.
+In many cases this will include both the use of [cURL][curl] as a REST API client as well as the use of the Knox Client DSL.
+You may notice that there are some minor differences between using the REST API of a given service via the gateway.
+In general this is necessary in order to achieve the goal of leaking internal Hadoop cluster details to the client.
+
+Keep in mind that the gateway uses a plugin model for supporting Hadoop services.
+Check back with the [Apache Knox][site] site for the latest news on plugin availability.
+You can also create your own custom plugin to extend the capabilities of the gateway.
+
+These are the current Hadoop services with built-in support.
+
+* #[WebHDFS]
+* #[WebHCat]
+* #[Oozie]
+* #[HBase]
+* #[Hive]
+* #[Yarn]
+* #[Storm]
+
+### Assumptions
+
+This document assumes a few things about your environment in order to simplify the examples.
+
+* The JVM is executable as simply java.
+* The Apache Knox Gateway is installed and functional.
+* The example commands are executed within the context of the GATEWAY_HOME current directory.
+The GATEWAY_HOME directory is the directory within the Apache Knox Gateway installation that contains the README file and the bin, conf and deployments directories.
+* The [cURL][curl] command line HTTP client utility is installed and functional.
+* A few examples optionally require the use of commands from a standard Groovy installation.
+These examples are optional but to try them you will need Groovy [installed](http://groovy.codehaus.org/Installing+Groovy).
+* The default configuration for all of the samples is setup for use with Hortonworks' [Sandbox][sandbox] version 2.
+
+### Customization
+
+Using these samples with other Hadoop installations will require changes to the steps describe here as well as changes to referenced sample scripts.
+This will also likely require changes to the gateway's default configuration.
+In particular host names, ports user names and password may need to be changes to match your environment.
+These changes may need to be made to gateway configuration and also the Groovy sample script files in the distribution.
+All of the values that may need to be customized in the sample scripts can be found together at the top of each of these files.
+
+### cURL
+
+The cURL HTTP client command line utility is used extensively in the examples for each service.
+In particular this form of the cURL command line is used repeatedly.
+
+ curl -i -k -u guest:guest-password ...
+
+The option -i (aka --include) is used to output HTTP response header information.
+This will be important when the content of the HTTP Location header is required for subsequent requests.
+
+The option -k (aka --insecure) is used to avoid any issues resulting the use of demonstration SSL certificates.
+
+The option -u (aka --user) is used to provide the credentials to be used when the client is challenged by the gateway.
+
+Keep in mind that the samples do not use the cookie features of cURL for the sake of simplicity.
+Therefore each request via cURL will result in an authentication.
+
+<<service_webhdfs.md>>
+<<service_webhcat.md>>
+<<service_oozie.md>>
+<<service_hbase.md>>
+<<service_hive.md>>
+<<service_yarn.md>>
+<<service_storm.md>>
+
+