You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hcatalog-commits@incubator.apache.org by ha...@apache.org on 2011/07/08 01:17:53 UTC
svn commit: r1144117 - in /incubator/hcatalog/branches/branch-0.1: ./
src/docs/ src/docs/src/documentation/content/xdocs/
src/java/org/apache/hcatalog/mapreduce/ src/java/org/apache/hcatalog/pig/
Author: hashutosh
Date: Fri Jul 8 01:17:52 2011
New Revision: 1144117
URL: http://svn.apache.org/viewvc?rev=1144117&view=rev
Log:
HCATALOG-54 Javadoc is not being built as part of HCatalog docs
Added:
incubator/hcatalog/branches/branch-0.1/src/docs/overview.html
Modified:
incubator/hcatalog/branches/branch-0.1/CHANGES.txt
incubator/hcatalog/branches/branch-0.1/build.xml
incubator/hcatalog/branches/branch-0.1/src/docs/src/documentation/content/xdocs/site.xml
incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatInputStorageDriver.java
incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatTableInfo.java
incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/JobInfo.java
incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/pig/PigHCatUtil.java
Modified: incubator/hcatalog/branches/branch-0.1/CHANGES.txt
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/CHANGES.txt?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/CHANGES.txt (original)
+++ incubator/hcatalog/branches/branch-0.1/CHANGES.txt Fri Jul 8 01:17:52 2011
@@ -15,6 +15,8 @@ Release 0.1.0
(Krishna Kumar via macyang)
IMPROVEMENTS
+ HCAT-54. Javadoc is not being built as part of HCatalog docs (hashutosh)
+
HCAT-44. Add a releaseaudit target to build.xml (gates)
HCAT-40. Remove dependencies from the HCatalog client jar (macyang)
Modified: incubator/hcatalog/branches/branch-0.1/build.xml
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/build.xml?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/build.xml (original)
+++ incubator/hcatalog/branches/branch-0.1/build.xml Fri Jul 8 01:17:52 2011
@@ -317,7 +317,7 @@
Docs Section
================================================================================
-->
- <target name="docs" depends="forrest.check" description="Generate forrest-based documentation. To use, specify -Dforrest.home=<base of Apache Forrest installation> on the command line." if="forrest.home">
+ <target name="docs" depends="javadoc, forrest.check" description="Generate forrest-based documentation. To use, specify -Dforrest.home=<base of Apache Forrest installation> on the command line." if="forrest.home">
<exec dir="${docs.src}" executable="${forrest.home}/bin/forrest"
failonerror="true">
</exec>
@@ -330,6 +330,18 @@
<fail message="'forrest.home' is not defined. Please pass -Dforrest.home=<base of Apache Forrest installation> to Ant on the command-line." />
</target>
+ <target name="javadoc" depends="clientjar" description="Create documentation">
+ <mkdir dir="${build.javadoc}" />
+ <javadoc overview="${src.dir}/../docs/overview.html" packagenames="org.apache.hcatalog.*" destdir="${build.javadoc}" author="true" version="true" use="true" windowtitle="HCatalog ${hcatalog.version} API" doctitle="HCatalog ${hcatalog.version} API" bottom="Copyright &copy; ${year} The Apache Software Foundation">
+ <packageset dir="${src.dir}" />
+ <classpath>
+ <path refid="classpath" />
+ </classpath>
+ <group title="hcatalog" packages="org.apache.hcatalog.*" />
+ </javadoc>
+ </target>
+
+
<!--
===============================================================================
Distribution Section
Added: incubator/hcatalog/branches/branch-0.1/src/docs/overview.html
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/docs/overview.html?rev=1144117&view=auto
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/docs/overview.html (added)
+++ incubator/hcatalog/branches/branch-0.1/src/docs/overview.html Fri Jul 8 01:17:52 2011
@@ -0,0 +1,116 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<title>Overview </title>
+</head>
+<body>
+<h1>Overview </h1>
+<div id="front-matter">
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#HCatalog">HCatalog </a>
+</li>
+<li>
+<a href="#HCatalog+Architecture">HCatalog Architecture</a>
+<ul class="minitoc">
+<li>
+<a href="#Interfaces">Interfaces</a>
+</li>
+<li>
+<a href="#Data+Model">Data Model</a>
+</li>
+</ul>
+</li>
+<li>
+<a href="#Data+Flow+Example">Data Flow Example</a>
+</li>
+</ul>
+</div>
+</div>
+
+<a name="HCatalog"></a>
+<h2 class="h3">HCatalog </h2>
+<div class="section">
+<p>HCatalog is a table management and storage management layer for Hadoop that enables users with different data processing tools – Pig, MapReduce, Hive, Streaming – to more easily read and write data on the grid. HCatalog’s table abstraction presents users with a relational view of data in the Hadoop distributed file system (HDFS) and ensures that users need not worry about where or in what format their data is stored – RCFile format, text files, sequence files. </p>
+<p>(Note: In this release, Streaming is not supported. Also, HCatalog supports only writing RCFile formatted files and only reading PigStorage formated text files.)</p>
+<p></p>
+
+
+
+<a name="HCatalog+Architecture"></a>
+<h2 class="h3">HCatalog Architecture</h2>
+<div class="section">
+<p>HCatalog is built on top of the Hive metastore and incorporates components from the Hive DDL. HCatalog provides read and write interfaces for Pig and MapReduce and a command line interface for data definitions.</p>
+<p>(Note: HCatalog notification is not available in this release.)</p>
+<p></p>
+<a name="Interfaces"></a>
+<h3 class="h4">Interfaces</h3>
+<p>The HCatalog interface for Pig – HCatLoader and HCatStorer – is an implementation of the Pig load and store interfaces. HCatLoader accepts a table to read data from; you can indicate which partitions to scan by immediately following the load statement with a partition filter statement. HCatStorer accepts a table to write to and a specification of partition keys to create a new partition. Currently HCatStorer only supports writing to one partition. HCatLoader and HCatStorer are implemented on top of HCatInputFormat and HCatOutputFormat respectively </p>
+<p>The HCatalog interface for MapReduce – HCatInputFormat and HCatOutputFormat – is an implementation of Hadoop InputFormat and OutputFormat. HCatInputFormat accepts a table to read data from and a selection predicate to indicate which partitions to scan. HCatOutputFormat accepts a table to write to and a specification of partition keys to create a new partition. Currently HCatOutputFormat only supports writing to one partition.</p>
+<p>
+<strong>Note:</strong> Currently there is no Hive-specific interface. Since HCatalog uses Hive's metastore, Hive can read data in HCatalog directly as long as a SerDe for that data already exists. In the future we plan to write a HCatalogSerDe so that users won't need storage-specific SerDes and so that Hive users can write data to HCatalog. Currently, this is supported - if a Hive user writes data in the RCFile format, it is possible to read the data through HCatalog. </p>
+<p>Data is defined using HCatalog's command line interface (CLI). The HCatalog CLI supports most of the DDL portion of Hive's query language, allowing users to create, alter, drop tables, etc. The CLI also supports the data exploration part of the Hive command line, such as SHOW TABLES, DESCRIBE TABLE, etc.</p>
+<a name="Data+Model"></a>
+<h3 class="h4">Data Model</h3>
+<p>HCatalog presents a relational view of data in HDFS. Data is stored in tables and these tables can be placed in databases. Tables can also be hash partitioned on one or more keys; that is, for a given value of a key (or set of keys) there will be one partition that contains all rows with that value (or set of values). For example, if a table is partitioned on date and there are three days of data in the table, there will be three partitions in the table. New partitions can be added to a table, and partitions can be dropped from a table. Partitioned tables have no partitions at create time. Unpartitioned tables effectively have one default partition that must be created at table creation time. There is no guaranteed read consistency when a partition is dropped.</p>
+<p>Partitions contain records. Once a partition is created records cannot be added to it, removed from it, or updated in it. (In the future some ability to integrate changes to a partition will be added.) Partitions are multi-dimensional and not hierarchical. Records are divided into columns. Columns have a name and a datatype. HCatalog supports the same datatypes as Hive. </p>
+</div>
+
+
+<a name="Data+Flow+Example"></a>
+<h2 class="h3">Data Flow Example</h2>
+<div class="section">
+<p>This simple data flow example shows how HCatalog is used to move data from the grid into a database.
+ From the database, the data can then be analyzed using Hive.</p>
+<p>
+<strong>First</strong> Joe in data acquisition uses distcp to get data onto the grid.</p>
+<pre class="code">
+hadoop distcp file:///file.dat hdfs://data/rawevents/20100819/data
+
+hcat "alter table rawevents add partition 20100819 hdfs://data/rawevents/20100819/data"
+</pre>
+<p>
+<strong>Second</strong> Sally in data processing uses Pig to cleanse and prepare the data.</p>
+<p>Without HCatalog, Sally must be manually informed by Joe that data is available, or use Oozie and poll on HDFS.</p>
+<pre class="code">
+A = load '/data/rawevents/20100819/data' as (alpha:int, beta:chararray, …);
+B = filter A by bot_finder(zeta) = 0;
+…
+store Z into 'data/processedevents/20100819/data';
+</pre>
+<p>With HCatalog, Oozie will be notified by HCatalog data is available and can then start the Pig job</p>
+<pre class="code">
+A = load 'rawevents' using HCatLoader;
+B = filter A by date = '20100819' and by bot_finder(zeta) = 0;
+…
+store Z into 'processedevents' using HCatStorer("date=20100819");
+</pre>
+<p>
+<strong>Third</strong> Robert in client management uses Hive to analyze his clients' results.</p>
+<p>Without HCatalog, Robert must alter the table to add the required partition. </p>
+<pre class="code">
+alter table processedevents add partition 20100819 hdfs://data/processedevents/20100819/data
+
+select advertiser_id, count(clicks)
+from processedevents
+where date = '20100819'
+group by adverstiser_id;
+</pre>
+<p>With HCatalog, Robert does not need to modify the table structure.</p>
+<pre class="code">
+select advertiser_id, count(clicks)
+from processedevents
+where date = ‘20100819’
+group by adverstiser_id;
+</pre>
+</div>
+
+<div class="copyright">
+ Copyright ©
+ 2011 <a href="http://www.apache.org/licenses/">The Apache Software Foundation</a>
+</div>
+</div>
+</body>
+</html>
Modified: incubator/hcatalog/branches/branch-0.1/src/docs/src/documentation/content/xdocs/site.xml
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/docs/src/documentation/content/xdocs/site.xml?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/docs/src/documentation/content/xdocs/site.xml (original)
+++ incubator/hcatalog/branches/branch-0.1/src/docs/src/documentation/content/xdocs/site.xml Fri Jul 8 01:17:52 2011
@@ -45,6 +45,7 @@ See http://forrest.apache.org/docs/linki
<index label="Cmd Line Interface " href="cli.html" />
<index label="Supported data formats" href="supportedformats.html" />
<index label="Installation" href="install.html" />
- </docs>
+ <api label="API Docs" href="api/index.html"/>
+ </docs>
</site>
Modified: incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatInputStorageDriver.java
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatInputStorageDriver.java?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatInputStorageDriver.java (original)
+++ incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatInputStorageDriver.java Fri Jul 8 01:17:52 2011
@@ -45,7 +45,7 @@ public abstract class HCatInputStorageDr
/**
* Returns the InputFormat to use with this Storage Driver.
- * @param properties the properties containing parameters required for initialization of InputFormat
+ * @param howlProperties the properties containing parameters required for initialization of InputFormat
* @return the InputFormat instance
*/
public abstract InputFormat<? extends WritableComparable, ? extends Writable> getInputFormat(Properties howlProperties);
@@ -56,7 +56,8 @@ public abstract class HCatInputStorageDr
* Implementers of StorageDriver should look to overwriting this function so as to convert their
* value type to HowlRecord. Default implementation is provided for StorageDriver implementations
* on top of an underlying InputFormat that already uses HowlRecord as a tuple
- * @param value the underlying value to convert to HowlRecord
+ * @param baseKey
+ * @param baseValue the underlying value to convert to HowlRecord
*/
public abstract HCatRecord convertToHCatRecord(WritableComparable baseKey, Writable baseValue) throws IOException;
@@ -130,7 +131,6 @@ public abstract class HCatInputStorageDr
* the schema it has (like Zebra) or it will use this to create a HowlRecord matching the output schema.
* @param jobContext the job context object
* @param howlSchema the schema published in Howl for this data
- * @param instantiationState
* @throws IOException Signals that an I/O exception has occurred.
*/
public abstract void setOriginalSchema(JobContext jobContext, HCatSchema howlSchema) throws IOException;
@@ -149,7 +149,6 @@ public abstract class HCatInputStorageDr
* driver can add the partition key values to the output HowlRecord if the partition key values are not present on disk.
* @param jobContext the job context object
* @param partitionValues the partition values having a map with partition key name as key and the HowlKeyValue as value
- * @param instantiationState
* @throws IOException Signals that an I/O exception has occurred.
*/
public abstract void setPartitionValues(JobContext jobContext, Map<String,String> partitionValues) throws IOException;
Modified: incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatTableInfo.java
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatTableInfo.java?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatTableInfo.java (original)
+++ incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/HCatTableInfo.java Fri Jul 8 01:17:52 2011
@@ -25,8 +25,8 @@ import org.apache.hadoop.hive.metastore.
/**
*
- * HCatTableInfo - class to communicate table information to {@link HowlInputFormat}
- * and {@link HowlOutputFormat}
+ * HCatTableInfo - class to communicate table information to {@link HCatInputFormat}
+ * and {@link HCatOutputFormat}
*
*/
public class HCatTableInfo implements Serializable {
@@ -67,7 +67,7 @@ public class HCatTableInfo implements Se
private Map<String, String> partitionValues;
/**
- * Initializes a new HCatTableInfo instance to be used with {@link HowlInputFormat}
+ * Initializes a new HCatTableInfo instance to be used with {@link HCatInputFormat}
* for reading data from a table.
* @param serverUri the Metadata server uri
* @param serverKerberosPrincipal If the howl server is configured to
@@ -86,7 +86,7 @@ public class HCatTableInfo implements Se
}
/**
- * Initializes a new HCatTableInfo instance to be used with {@link HowlInputFormat}
+ * Initializes a new HCatTableInfo instance to be used with {@link HCatInputFormat}
* for reading data from a table.
* @param serverUri the Metadata server uri
* @param serverKerberosPrincipal If the howl server is configured to
@@ -115,7 +115,7 @@ public class HCatTableInfo implements Se
this.filter = filter;
}
/**
- * Initializes a new HCatTableInfo instance to be used with {@link HowlOutputFormat}
+ * Initializes a new HCatTableInfo instance to be used with {@link HCatOutputFormat}
* for writing data from a table.
* @param serverUri the Metadata server uri
* @param serverKerberosPrincipal If the howl server is configured to
Modified: incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/JobInfo.java
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/JobInfo.java?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/JobInfo.java (original)
+++ incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/mapreduce/JobInfo.java Fri Jul 8 01:17:52 2011
@@ -40,7 +40,7 @@ public class JobInfo implements Serializ
/**
* Instantiates a new howl job info.
- * @param tableName the table name
+ * @param howlTableInfo
* @param tableSchema the table schema
* @param partitions the partitions
*/
Modified: incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/pig/PigHCatUtil.java
URL: http://svn.apache.org/viewvc/incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/pig/PigHCatUtil.java?rev=1144117&r1=1144116&r2=1144117&view=diff
==============================================================================
--- incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/pig/PigHCatUtil.java (original)
+++ incubator/hcatalog/branches/branch-0.1/src/java/org/apache/hcatalog/pig/PigHCatUtil.java Fri Jul 8 01:17:52 2011
@@ -229,7 +229,7 @@ public class PigHCatUtil {
}
/**
- * @param type owl column type
+ * @param hfs schema of the column
* @return corresponding pig type
* @throws IOException
*/