http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/ddl-operation-on-carbondata.html ---------------------------------------------------------------------- diff --git a/content/ddl-operation-on-carbondata.html b/content/ddl-operation-on-carbondata.html new file mode 100644 index 0000000..24346a0 --- /dev/null +++ b/content/ddl-operation-on-carbondata.html @@ -0,0 +1,580 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + <link href='images/favicon.ico' rel='shortcut icon' type='image/x-icon'> + <!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags --> + <title>CarbonData</title> + <style> + + </style> + <!-- Bootstrap --> + + <link rel="stylesheet" href="css/bootstrap.min.css"> + <link href="css/style.css" rel="stylesheet"> + <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> + <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js";></script> + <script src="https://oss.maxcdn.scom/respond/1.4.2/respond.min.js";></script> + <![endif]--> + <script src="js/jquery.min.js"></script> + <script src="js/bootstrap.min.js"></script> + + +</head> +<body> +<header> + <nav class="navbar navbar-default navbar-custom cd-navbar-wrapper"> + <div class="container"> + <div class="navbar-header"> + <button aria-controls="navbar" aria-expanded="false" data-target="#navbar" data-toggle="collapse" + class="navbar-toggle collapsed" type="button"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> + <a href="index.html" class="logo"> + <img src="images/CarbonDataLogo.png" alt="CarbonData logo" title="CarbocnData logo"/> + </a> + </div> + <div class="navbar-collapse collapse cd_navcontnt" id="navbar"> + <ul class="nav navbar-nav navbar-right navlist-custom"> + <li><a href="index.html" class="hidden-xs"><i class="fa fa-home" aria-hidden="true"></i> </a> + </li> + <li><a href="index.html" class="hidden-lg hidden-md hidden-sm">Home</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle " data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false"> Download <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/1.0.0-incubating"; + target="_blank">Apache CarbonData 1.0.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.2.0-incubating"; + target="_blank">Apache CarbonData 0.2.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.1-incubating"; + target="_blank">Apache CarbonData 0.1.1</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.0-incubating"; + target="_blank">Apache CarbonData 0.1.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="mainpage.html" class="">Documentation</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false">Community <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://github.com/apache/incubator-carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PPMC+and+Committers+member+list"; + target="_blank">Project PPMC and Committers</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=66850609"; + target="_blank">CarbonData Meetups</a></li> + <li><a href="security.html">Apache CarbonData Security</a></li> + <li><a href="https://issues.apache.org/jira/browse/CARBONDATA"; target="_blank">Apache + Jira</a></li> + <li><a href="videogallery.html">CarbonData Videos </a></li> + </ul> + </li> + <li class="dropdown"> + <a href="http://www.apache.org/"; class="apache_link hidden-xs dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="http://www.apache.org/"; class="hidden-lg hidden-md hidden-sm dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li> + <a href="#" id="search-icon"><i class="fa fa-search" aria-hidden="true"></i></a> + + </li> + + </ul> + </div><!--/.nav-collapse --> + <div id="search-box"> + <form method="get" action="http://www.google.com/search";> + <div class="search-block"> + <table border="0" cellpadding="0" width="100%"> + <tr> + <td style="width:80%"> + <input type="text" name="q" size=" 5" maxlength="255" value="" + class="search-input"/> + </td> + <td style="width:20%"> + <input type="submit" value="Search"/></td> + </tr> + <tr> + <td align="left" style="font-size:75%" colspan="2"> + <input type="checkbox" name="sitesearch" value="carbondata.apache.org" checked/> + Only search for CarbonData + </td> + </tr> + </table> + </div> + </form> + </div> + </div> + </nav> +</header> <!-- end Header part --> + +<div class="fixed-padding"></div> <!-- top padding with fixde header --> + +<section><!-- Dashboard nav --> + <div class="container-fluid q"> + <div class="col-sm-12 col-md-12 maindashboard"> + <div class="row"> + <section> + <div style="padding:10px 15px;"> + <div id="viewpage" name="viewpage"> + <div class="row"> + <div class="col-sm-12 col-md-12"> + <div> + +<h1> +<a id="ddl-operations-on-carbondata" class="anchor" href="#ddl-operations-on-carbondata" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DDL Operations on CarbonData</h1> + +<p>This tutorial guides you through the data definition language support provided by CarbonData.</p> + +<h2> +<a id="overview" class="anchor" href="#overview" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Overview</h2> + +<p>The following DDL operations are supported in CarbonData :</p> + +<ul> +<li><a href="#create-table">CREATE TABLE</a></li> +<li><a href="#show-table">SHOW TABLE</a></li> +<li><a href="#drop-table">DROP TABLE</a></li> +<li><a href="#compaction">COMPACTION</a></li> +<li><a href="#bucketing">BUCKETING</a></li> +<li><a href="#table-rename">TABLE RENAME</a></li> +</ul> + +<h2> +<a id="create-table" class="anchor" href="#create-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>CREATE TABLE</h2> + +<p>This command can be used to create a CarbonData table by specifying the list of fields along with the table properties.</p> + +<pre><code> CREATE TABLE [IF NOT EXISTS] [db_name.]table_name + [(col_name data_type , ...)] + STORED BY 'carbondata' + [TBLPROPERTIES (property_name=property_value, ...)] + // All Carbon's additional table options will go into properties +</code></pre> + +<h3> +<a id="parameter-description" class="anchor" href="#parameter-description" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>db_name</td> +<td>Name of the database. Database name should consist of alphanumeric characters and underscore(_) special character.</td> +<td>Yes</td> +</tr> +<tr> +<td>field_list</td> +<td>Comma separated List of fields with data type. The field names should consist of alphanumeric characters and underscore(_) special character.</td> +<td>No</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in Database. Table Name should consist of alphanumeric characters and underscore(_) special character.</td> +<td>No</td> +</tr> +<tr> +<td>STORED BY</td> +<td>"org.apache.carbondata.format", identifies and creates a CarbonData table.</td> +<td>No</td> +</tr> +<tr> +<td>TBLPROPERTIES</td> +<td>List of CarbonData table properties.</td> +<td></td> +</tr> +</tbody> +</table> + +<h3> +<a id="usage-guidelines" class="anchor" href="#usage-guidelines" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h3> + +<p>Following are the guidelines for using table properties.</p> + +<ul> +<li> +<p><strong>Dictionary Encoding Configuration</strong></p> + +<p>Dictionary encoding is enabled by default for all String columns, and disabled for non-String columns. You can include and exclude columns for dictionary encoding.</p> +</li> +</ul> + +<pre><code> TBLPROPERTIES ('DICTIONARY_EXCLUDE'='column1, column2') + TBLPROPERTIES ('DICTIONARY_INCLUDE'='column1, column2') +</code></pre> + +<p>Here, DICTIONARY_EXCLUDE will exclude dictionary creation. This is applicable for high-cardinality columns and is an optional parameter. DICTIONARY_INCLUDE will generate dictionary for the columns specified in the list.</p> + +<ul> +<li> +<p><strong>Row/Column Format Configuration</strong></p> + +<p>Column groups with more than one column are stored in row format, instead of columnar format. By default, each column is a separate column group.</p> +</li> +</ul> + +<pre><code>TBLPROPERTIES ('COLUMN_GROUPS'='(column1, column3), +(Column4,Column5,Column6)') +</code></pre> + +<ul> +<li> +<p><strong>Table Block Size Configuration</strong></p> + +<p>The block size of table files can be defined using the property TABLE_BLOCKSIZE. It accepts only integer values. The default value is 1024 MB and supports a range of 1 MB to 2048 MB. + If you do not specify this value in the DDL command, default value is used.</p> +</li> +</ul> + +<pre><code> TBLPROPERTIES ('TABLE_BLOCKSIZE'='512') +</code></pre> + +<p>Here 512 MB means the block size of this table is 512 MB, you can also set it as 512M or 512.</p> + +<ul> +<li> +<p><strong>Inverted Index Configuration</strong></p> + +<p>Inverted index is very useful to improve compression ratio and query speed, especially for those low-cardinality columns who are in reward position. + By default inverted index is enabled. The user can disable the inverted index creation for some columns.</p> +</li> +</ul> + +<pre><code> TBLPROPERTIES ('NO_INVERTED_INDEX'='column1, column3') +</code></pre> + +<p>No inverted index shall be generated for the columns specified in NO_INVERTED_INDEX. This property is applicable on columns with high-cardinality and is an optional parameter.</p> + +<p>NOTE:</p> + +<ul> +<li><p>By default all columns other than numeric datatype are treated as dimensions and all columns of numeric datatype are treated as measures.</p></li> +<li><p>All dimensions except complex datatype columns are part of multi dimensional key(MDK). This behavior can be overridden by using TBLPROPERTIES. If the user wants to keep any column (except columns of complex datatype) in multi dimensional key then he can keep the columns either in DICTIONARY_EXCLUDE or DICTIONARY_INCLUDE.</p></li> +</ul> + +<h3> +<a id="example" class="anchor" href="#example" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code> CREATE TABLE IF NOT EXISTS productSchema.productSalesTable ( + productNumber Int, + productName String, + storeCity String, + storeProvince String, + productCategory String, + productBatch String, + saleQuantity Int, + revenue Int) + STORED BY 'carbondata' + TBLPROPERTIES ('COLUMN_GROUPS'='(productNumber,productName)', + 'DICTIONARY_EXCLUDE'='storeCity', + 'DICTIONARY_INCLUDE'='productNumber', + 'NO_INVERTED_INDEX'='productBatch') +</code></pre> + +<h2> +<a id="show-table" class="anchor" href="#show-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>SHOW TABLE</h2> + +<p>This command can be used to list all the tables in current database or all the tables of a specific database.</p> + +<pre><code> SHOW TABLES [IN db_Name]; +</code></pre> + +<h3> +<a id="parameter-description-1" class="anchor" href="#parameter-description-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>IN db_Name</td> +<td>Name of the database. Required only if tables of this specific database are to be listed.</td> +<td>Yes</td> +</tr> +</tbody> +</table> + +<h3> +<a id="example-1" class="anchor" href="#example-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code> SHOW TABLES IN ProductSchema; +</code></pre> + +<h2> +<a id="drop-table" class="anchor" href="#drop-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DROP TABLE</h2> + +<p>This command is used to delete an existing table.</p> + +<pre><code> DROP TABLE [IF EXISTS] [db_name.]table_name; +</code></pre> + +<h3> +<a id="parameter-description-2" class="anchor" href="#parameter-description-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>db_Name</td> +<td>Name of the database. If not specified, current database will be selected.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>Name of the table to be deleted.</td> +<td>NO</td> +</tr> +</tbody> +</table> + +<h3> +<a id="example-2" class="anchor" href="#example-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code> DROP TABLE IF EXISTS productSchema.productSalesTable; +</code></pre> + +<h2> +<a id="compaction" class="anchor" href="#compaction" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>COMPACTION</h2> + +<p>This command merges the specified number of segments into one segment. This enhances the query performance of the table.</p> + +<pre><code> ALTER TABLE [db_name.]table_name COMPACT 'MINOR/MAJOR'; +</code></pre> + +<p>To get details about Compaction refer to <a href="data-management.html">Data Management</a></p> + +<h3> +<a id="parameter-description-3" class="anchor" href="#parameter-description-3" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>db_name</td> +<td>Database name, if it is not specified then it uses current database.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in provided database.</td> +<td>NO</td> +</tr> +</tbody> +</table> + +<h3> +<a id="syntax" class="anchor" href="#syntax" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<ul> +<li><strong>Minor Compaction</strong></li> +</ul> + +<pre><code>ALTER TABLE table_name COMPACT 'MINOR'; +</code></pre> + +<ul> +<li><strong>Major Compaction</strong></li> +</ul> + +<pre><code>ALTER TABLE table_name COMPACT 'MAJOR'; +</code></pre> + +<h2> +<a id="bucketing" class="anchor" href="#bucketing" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>BUCKETING</h2> + +<p>Bucketing feature can be used to distribute/organize the table/partition data into multiple files such +that similar records are present in the same file. While creating a table, a user needs to specify the +columns to be used for bucketing and the number of buckets. For the selction of bucket the Hash value +of columns is used.</p> + +<pre><code> CREATE TABLE [IF NOT EXISTS] [db_name.]table_name + [(col_name data_type, ...)] + STORED BY 'carbondata' + TBLPROPERTIES('BUCKETNUMBER'='noOfBuckets', + 'BUCKETCOLUMNS'='columnname') +</code></pre> + +<h2> +<a id="parameter-description-4" class="anchor" href="#parameter-description-4" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h2> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>BUCKETNUMBER</td> +<td>Specifies the number of Buckets to be created.</td> +<td>No</td> +</tr> +<tr> +<td>BUCKETCOLUMNS</td> +<td>Specify the columns to be considered for Bucketing</td> +<td>No</td> +</tr> +</tbody> +</table> + +<h2> +<a id="usage-guidelines-1" class="anchor" href="#usage-guidelines-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h2> + +<ul> +<li><p>The feature is supported for Spark 1.6.2 onwards, but the performance optimization is evident from Spark 2.1 onwards.</p></li> +<li><p>Bucketing can not be performed for columns of Complex Data Types.</p></li> +<li><p>Columns in the BUCKETCOLUMN parameter must be only dimension. The BUCKETCOLUMN parameter can not be a measure or a combination of measures and dimensions.</p></li> +</ul> + +<h2> +<a id="example-" class="anchor" href="#example-" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example :</h2> + +<pre><code> CREATE TABLE IF NOT EXISTS productSchema.productSalesTable ( + productNumber Int, + productName String, + storeCity String, + storeProvince String, + productCategory String, + productBatch String, + saleQuantity Int, + revenue Int) + STORED BY 'carbondata' + TBLPROPERTIES ('COLUMN_GROUPS'='(productName,productNumber)', + 'DICTIONARY_EXCLUDE'='productName', + 'DICTIONARY_INCLUDE'='productNumber', + 'NO_INVERTED_INDEX'='productBatch', + 'BUCKETNUMBER'='4', + 'BUCKETCOLUMNS'='productName') +</code></pre> + +<h2> +<a id="table-rename" class="anchor" href="#table-rename" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>TABLE RENAME</h2> + +<p>This command is used to rename the existing table.</p> + +<h3> +<a id="syntax-1" class="anchor" href="#syntax-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<pre><code> ALTER TABLE [db_name.]table_name RENAME TO new_table_name; +</code></pre> + +<h3> +<a id="parameter-description-5" class="anchor" href="#parameter-description-5" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +</tr> +</thead> +<tbody> +<tr> +<td>db_name</td> +<td>Name of the database. If this parameter is left unspecified, the current database is selected.</td> +</tr> +<tr> +<td>table_name</td> +<td>Name of the existing table.</td> +</tr> +<tr> +<td>new_table_name</td> +<td>New table name for the existing table.</td> +</tr> +</tbody> +</table> + +<h3> +<a id="usage-guidelines-2" class="anchor" href="#usage-guidelines-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h3> + +<p>Following conditions must be met for successful rename operation:</p> + +<ul> +<li>Queries running in parallel which requires the formation of path using the table name for reading carbon store files might fail during this operation.</li> +<li>Secondary index table rename is not permitted.</li> +</ul> + +<h3> +<a id="example-3" class="anchor" href="#example-3" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code> ALTER TABLE carbon RENAME TO carbondata; + + ALTER TABLE test_db.carbon RENAME TO test_db.carbondata; +</code></pre> +</div> +</div> +</div> +</div> +<div class="doc-footer"> + <a href="#top" class="scroll-top">Top</a> +</div> +</div> +</section> +</div> +</div> +</div> +</section><!-- End systemblock part --> +<script src="js/custom.js"></script> +</body> +</html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/dml-operation-on-carbondata.html ---------------------------------------------------------------------- diff --git a/content/dml-operation-on-carbondata.html b/content/dml-operation-on-carbondata.html new file mode 100644 index 0000000..c05e461 --- /dev/null +++ b/content/dml-operation-on-carbondata.html @@ -0,0 +1,745 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + <link href='images/favicon.ico' rel='shortcut icon' type='image/x-icon'> + <!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags --> + <title>CarbonData</title> + <style> + + </style> + <!-- Bootstrap --> + + <link rel="stylesheet" href="css/bootstrap.min.css"> + <link href="css/style.css" rel="stylesheet"> + <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> + <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js";></script> + <script src="https://oss.maxcdn.scom/respond/1.4.2/respond.min.js";></script> + <![endif]--> + <script src="js/jquery.min.js"></script> + <script src="js/bootstrap.min.js"></script> + + +</head> +<body> +<header> + <nav class="navbar navbar-default navbar-custom cd-navbar-wrapper"> + <div class="container"> + <div class="navbar-header"> + <button aria-controls="navbar" aria-expanded="false" data-target="#navbar" data-toggle="collapse" + class="navbar-toggle collapsed" type="button"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> + <a href="index.html" class="logo"> + <img src="images/CarbonDataLogo.png" alt="CarbonData logo" title="CarbocnData logo"/> + </a> + </div> + <div class="navbar-collapse collapse cd_navcontnt" id="navbar"> + <ul class="nav navbar-nav navbar-right navlist-custom"> + <li><a href="index.html" class="hidden-xs"><i class="fa fa-home" aria-hidden="true"></i> </a> + </li> + <li><a href="index.html" class="hidden-lg hidden-md hidden-sm">Home</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle " data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false"> Download <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/1.0.0-incubating"; + target="_blank">Apache CarbonData 1.0.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.2.0-incubating"; + target="_blank">Apache CarbonData 0.2.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.1-incubating"; + target="_blank">Apache CarbonData 0.1.1</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.0-incubating"; + target="_blank">Apache CarbonData 0.1.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="mainpage.html" class="">Documentation</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false">Community <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://github.com/apache/incubator-carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PPMC+and+Committers+member+list"; + target="_blank">Project PPMC and Committers</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=66850609"; + target="_blank">CarbonData Meetups</a></li> + <li><a href="security.html">Apache CarbonData Security</a></li> + <li><a href="https://issues.apache.org/jira/browse/CARBONDATA"; target="_blank">Apache + Jira</a></li> + <li><a href="videogallery.html">CarbonData Videos </a></li> + </ul> + </li> + <li class="dropdown"> + <a href="http://www.apache.org/"; class="apache_link hidden-xs dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="http://www.apache.org/"; class="hidden-lg hidden-md hidden-sm dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li> + <a href="#" id="search-icon"><i class="fa fa-search" aria-hidden="true"></i></a> + + </li> + + </ul> + </div><!--/.nav-collapse --> + <div id="search-box"> + <form method="get" action="http://www.google.com/search";> + <div class="search-block"> + <table border="0" cellpadding="0" width="100%"> + <tr> + <td style="width:80%"> + <input type="text" name="q" size=" 5" maxlength="255" value="" + class="search-input"/> + </td> + <td style="width:20%"> + <input type="submit" value="Search"/></td> + </tr> + <tr> + <td align="left" style="font-size:75%" colspan="2"> + <input type="checkbox" name="sitesearch" value="carbondata.apache.org" checked/> + Only search for CarbonData + </td> + </tr> + </table> + </div> + </form> + </div> + </div> + </nav> +</header> <!-- end Header part --> + +<div class="fixed-padding"></div> <!-- top padding with fixde header --> + +<section><!-- Dashboard nav --> + <div class="container-fluid q"> + <div class="col-sm-12 col-md-12 maindashboard"> + <div class="row"> + <section> + <div style="padding:10px 15px;"> + <div id="viewpage" name="viewpage"> + <div class="row"> + <div class="col-sm-12 col-md-12"> + <div> + +<h1> +<a id="dml-operations-on-carbondata" class="anchor" href="#dml-operations-on-carbondata" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DML Operations on CarbonData</h1> + +<p>This tutorial guides you through the data manipulation language support provided by CarbonData.</p> + +<h2> +<a id="overview" class="anchor" href="#overview" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Overview</h2> + +<p>The following DML operations are supported in CarbonData :</p> + +<ul> +<li><a href="#load-data">LOAD DATA</a></li> +<li><a href="#insert-data-into-a-carbondata-table">INSERT DATA INTO A CARBONDATA TABLE</a></li> +<li><a href="#show-segments">SHOW SEGMENTS</a></li> +<li><a href="#delete-segment-by-id">DELETE SEGMENT BY ID</a></li> +<li><a href="#delete-segment-by-date">DELETE SEGMENT BY DATE</a></li> +<li><a href="#update-carbondata-table">UPDATE CARBONDATA TABLE</a></li> +<li><a href="#delete-records-from-carbondata-table">DELETE RECORDS FROM CARBONDATA TABLE</a></li> +</ul> + +<h2> +<a id="load-data" class="anchor" href="#load-data" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>LOAD DATA</h2> + +<p>This command loads the user data in raw format to the CarbonData specific data format store, this allows CarbonData to provide good performance while querying the data. +Please visit <a href="data-management.html">Data Management</a> for more details on LOAD.</p> + +<h3> +<a id="syntax" class="anchor" href="#syntax" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<pre><code>LOAD DATA [LOCAL] INPATH 'folder_path' +INTO TABLE [db_name.]table_name +OPTIONS(property_name=property_value, ...) +</code></pre> + +<p>OPTIONS are not mandatory for data loading process. Inside OPTIONS user can provide either of any options like DELIMITER, QUOTECHAR, ESCAPECHAR, MULTILINE as per requirement.</p> + +<p>NOTE: The path shall be canonical path.</p> + +<h3> +<a id="parameter-description" class="anchor" href="#parameter-description" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>folder_path</td> +<td>Path of raw csv data folder or file.</td> +<td>NO</td> +</tr> +<tr> +<td>db_name</td> +<td>Database name, if it is not specified then it uses the current database.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in provided database.</td> +<td>NO</td> +</tr> +<tr> +<td>OPTIONS</td> +<td>Extra options provided to Load</td> +<td>YES</td> +</tr> +</tbody> +</table> + +<h3> +<a id="usage-guidelines" class="anchor" href="#usage-guidelines" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h3> + +<p>You can use the following options to load data:</p> + +<ul> +<li> +<p><strong>DELIMITER:</strong> Delimiters can be provided in the load command.</p> + +<pre><code>OPTIONS('DELIMITER'=',') +</code></pre> +</li> +<li> +<p><strong>QUOTECHAR:</strong> Quote Characters can be provided in the load command.</p> + +<pre><code>OPTIONS('QUOTECHAR'='"') +</code></pre> +</li> +<li> +<p><strong>COMMENTCHAR:</strong> Comment Characters can be provided in the load command if user want to comment lines.</p> + +<pre><code>OPTIONS('COMMENTCHAR'='#') +</code></pre> +</li> +<li> +<p><strong>FILEHEADER:</strong> Headers can be provided in the LOAD DATA command if headers are missing in the source files.</p> + +<pre><code>OPTIONS('FILEHEADER'='column1,column2') +</code></pre> +</li> +<li> +<p><strong>MULTILINE:</strong> CSV with new line character in quotes.</p> + +<pre><code>OPTIONS('MULTILINE'='true') +</code></pre> +</li> +<li> +<p><strong>ESCAPECHAR:</strong> Escape char can be provided if user want strict validation of escape character on CSV.</p> + +<pre><code>OPTIONS('ESCAPECHAR'='\') +</code></pre> +</li> +<li> +<p><strong>COMPLEX_DELIMITER_LEVEL_1:</strong> Split the complex type data column in a row (eg., a$b$c --> Array = {a,b,c}).</p> + +<pre><code>OPTIONS('COMPLEX_DELIMITER_LEVEL_1'='$') +</code></pre> +</li> +<li> +<p><strong>COMPLEX_DELIMITER_LEVEL_2:</strong> Split the complex type nested data column in a row. Applies level_1 delimiter & applies level_2 based on complex data type (eg., a:b$c:d --> Array> = {{a,b},{c,d}}).</p> + +<pre><code>OPTIONS('COMPLEX_DELIMITER_LEVEL_2'=':') +</code></pre> +</li> +<li> +<p><strong>ALL_DICTIONARY_PATH:</strong> All dictionary files path.</p> + +<pre><code>OPTIONS('ALL_DICTIONARY_PATH'='/opt/alldictionary/data.dictionary') +</code></pre> +</li> +<li> +<p><strong>COLUMNDICT:</strong> Dictionary file path for specified column.</p> + +<pre><code>OPTIONS('COLUMNDICT'='column1:dictionaryFilePath1, +column2:dictionaryFilePath2') +</code></pre> + +<p>NOTE: ALL_DICTIONARY_PATH and COLUMNDICT can't be used together.</p> +</li> +<li> +<p><strong>DATEFORMAT:</strong> Date format for specified column.</p> + +<pre><code>OPTIONS('DATEFORMAT'='column1:dateFormat1, column2:dateFormat2') +</code></pre> + +<p>NOTE: Date formats are specified by date pattern strings. The date pattern letters in CarbonData are same as in JAVA. Refer to <a href="http://docs.oracle.com/javase/7/docs/api/java/text/SimpleDateFormat.html"; target=_blank>SimpleDateFormat</a>.</p> +</li> +<li> +<p><strong>SINGLE_PASS:</strong> Single Pass Loading enables single job to finish data loading with dictionary generation on the fly. It enhances performance in the scenarios where the subsequent data loading after initial load involves fewer incremental updates on the dictionary.</p> + +<p>This option specifies whether to use single pass for loading data or not. By default this option is set to FALSE.</p> + +<pre><code>OPTIONS('SINGLE_PASS'='TRUE') +</code></pre> + +<p>Note :</p> + +<ul> +<li><p>If this option is set to TRUE then data loading will take less time.</p></li> +<li> +<p>If this option is set to some invalid value other than TRUE or FALSE then it uses the default value.</p> + +<h3> +<a id="example" class="anchor" href="#example" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> +</li> +</ul> +</li> +</ul> + +<pre><code>LOAD DATA local inpath '/opt/rawdata/data.csv' INTO table carbontable +options('DELIMITER'=',', 'QUOTECHAR'='"','COMMENTCHAR'='#', +'FILEHEADER'='empno,empname,designation,doj,workgroupcategory, + workgroupcategoryname,deptno,deptname,projectcode, + projectjoindate,projectenddate,attendance,utilization,salary', +'MULTILINE'='true','ESCAPECHAR'='\','COMPLEX_DELIMITER_LEVEL_1'='$', +'COMPLEX_DELIMITER_LEVEL_2'=':', +'ALL_DICTIONARY_PATH'='/opt/alldictionary/data.dictionary', +'SINGLE_PASS'='TRUE' +) +</code></pre> + +<h2> +<a id="insert-data-into-a-carbondata-table" class="anchor" href="#insert-data-into-a-carbondata-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>INSERT DATA INTO A CARBONDATA TABLE</h2> + +<p>This command inserts data into a CarbonData table. It is defined as a combination of two queries Insert and Select query respectively. It inserts records from a source table into a target CarbonData table. The source table can be a Hive table, Parquet table or a CarbonData table itself. It comes with the functionality to aggregate the records of a table by performing Select query on source table and load its corresponding resultant records into a CarbonData table.</p> + +<p><strong>NOTE</strong> : The client node where the INSERT command is executing, must be part of the cluster.</p> + +<h3> +<a id="syntax-1" class="anchor" href="#syntax-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<pre><code>INSERT INTO TABLE <CARBONDATA TABLE> SELECT * FROM sourceTableName +[ WHERE { <filter_condition> } ]; +</code></pre> + +<p>You can also omit the <code>table</code> keyword and write your query as:</p> + +<pre><code>INSERT INTO <CARBONDATA TABLE> SELECT * FROM sourceTableName +[ WHERE { <filter_condition> } ]; +</code></pre> + +<h3> +<a id="parameter-description-1" class="anchor" href="#parameter-description-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +</tr> +</thead> +<tbody> +<tr> +<td>CARBON TABLE</td> +<td>The name of the Carbon table in which you want to perform the insert operation.</td> +</tr> +<tr> +<td>sourceTableName</td> +<td>The table from which the records are read and inserted into destination CarbonData table.</td> +</tr> +</tbody> +</table> + +<h3> +<a id="usage-guidelines-1" class="anchor" href="#usage-guidelines-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h3> + +<p>The following condition must be met for successful insert operation :</p> + +<ul> +<li>The source table and the CarbonData table must have the same table schema.</li> +<li>The table must be created.</li> +<li>Overwrite is not supported for CarbonData table.</li> +<li>The data type of source and destination table columns should be same, else the data from source table will be treated as bad records and the INSERT command fails.</li> +<li>INSERT INTO command does not support partial success if bad records are found, it will fail.</li> +<li>Data cannot be loaded or updated in source table while insert from source table to target table is in progress.</li> +</ul> + +<p>To enable data load or update during insert operation, configure the following property to true.</p> + +<pre><code>carbon.insert.persist.enable=true +</code></pre> + +<p>By default the above configuration will be false.</p> + +<p><strong>NOTE</strong>: Enabling this property will reduce the performance.</p> + +<h3> +<a id="examples" class="anchor" href="#examples" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Examples</h3> + +<pre><code>INSERT INTO table1 SELECT item1 ,sum(item2 + 1000) as result FROM +table2 group by item1; +</code></pre> + +<pre><code>INSERT INTO table1 SELECT item1, item2, item3 FROM table2 +where item2='xyz'; +</code></pre> + +<pre><code>INSERT INTO table1 SELECT * FROM table2 +where exists (select * from table3 +where table2.item1 = table3.item1); +</code></pre> + +<p><strong>The Status Success/Failure shall be captured in the driver log.</strong></p> + +<h2> +<a id="show-segments" class="anchor" href="#show-segments" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>SHOW SEGMENTS</h2> + +<p>This command is used to get the segments of CarbonData table.</p> + +<pre><code>SHOW SEGMENTS FOR TABLE [db_name.]table_name +LIMIT number_of_segments; +</code></pre> + +<h3> +<a id="parameter-description-2" class="anchor" href="#parameter-description-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>db_name</td> +<td>Database name, if it is not specified then it uses the current database.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in provided database.</td> +<td>NO</td> +</tr> +<tr> +<td>number_of_segments</td> +<td>Limit the output to this number.</td> +<td>YES</td> +</tr> +</tbody> +</table> + +<h3> +<a id="example-1" class="anchor" href="#example-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code>SHOW SEGMENTS FOR TABLE CarbonDatabase.CarbonTable LIMIT 4; +</code></pre> + +<h2> +<a id="delete-segment-by-id" class="anchor" href="#delete-segment-by-id" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DELETE SEGMENT BY ID</h2> + +<p>This command is used to delete segment by using the segment ID. Each segment has a unique segment ID associated with it. +Using this segment ID, you can remove the segment.</p> + +<p>The following command will get the segmentID.</p> + +<pre><code>SHOW SEGMENTS FOR Table dbname.tablename LIMIT number_of_segments +</code></pre> + +<p>After you retrieve the segment ID of the segment that you want to delete, execute the following command to delete the selected segment.</p> + +<pre><code>DELETE SEGMENT segment_sequence_id1, segments_sequence_id2, .... +FROM TABLE tableName +</code></pre> + +<h3> +<a id="parameter-description-3" class="anchor" href="#parameter-description-3" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>segment_id</td> +<td>Segment Id of the load.</td> +<td>NO</td> +</tr> +<tr> +<td>db_name</td> +<td>Database name, if it is not specified then it uses the current database.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in provided database.</td> +<td>NO</td> +</tr> +</tbody> +</table> + +<h3> +<a id="example-2" class="anchor" href="#example-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code>DELETE SEGMENT 0 FROM TABLE CarbonDatabase.CarbonTable; +DELETE SEGMENT 0.1,5,8 FROM TABLE CarbonDatabase.CarbonTable; +</code></pre> + +<p>NOTE: Here 0.1 is compacted segment sequence id. </p> + +<h2> +<a id="delete-segment-by-date" class="anchor" href="#delete-segment-by-date" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DELETE SEGMENT BY DATE</h2> + +<p>This command will allow to delete the CarbonData segment(s) from the store based on the date provided by the user in the DML command. +The segment created before the particular date will be removed from the specific stores.</p> + +<pre><code>DELETE FROM TABLE [schema_name.]table_name +WHERE[DATE_FIELD]BEFORE [DATE_VALUE] +</code></pre> + +<h3> +<a id="parameter-description-4" class="anchor" href="#parameter-description-4" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +<th>Optional</th> +</tr> +</thead> +<tbody> +<tr> +<td>DATE_VALUE</td> +<td>Valid segment load start time value. All the segments before this specified date will be deleted.</td> +<td>NO</td> +</tr> +<tr> +<td>db_name</td> +<td>Database name, if it is not specified then it uses the current database.</td> +<td>YES</td> +</tr> +<tr> +<td>table_name</td> +<td>The name of the table in provided database.</td> +<td>NO</td> +</tr> +</tbody> +</table> + +<h3> +<a id="example-3" class="anchor" href="#example-3" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Example:</h3> + +<pre><code> DELETE SEGMENTS FROM TABLE CarbonDatabase.CarbonTable + WHERE STARTTIME BEFORE '2017-06-01 12:05:06'; +</code></pre> + +<h2> +<a id="update-carbondata-table" class="anchor" href="#update-carbondata-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Update CarbonData Table</h2> + +<p>This command will allow to update the carbon table based on the column expression and optional filter conditions.</p> + +<h3> +<a id="syntax-2" class="anchor" href="#syntax-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<pre><code> UPDATE <table_name> + SET (column_name1, column_name2, ... column_name n) = + (column1_expression , column2_expression . .. column n_expression ) + [ WHERE { <filter_condition> } ]; +</code></pre> + +<p>alternatively the following the command can also be used for updating the CarbonData Table :</p> + +<pre><code>UPDATE <table_name> +SET (column_name1, column_name2,) = +(select sourceColumn1, sourceColumn2 from sourceTable +[ WHERE { <filter_condition> } ] ) +[ WHERE { <filter_condition> } ]; +</code></pre> + +<h3> +<a id="parameter-description-5" class="anchor" href="#parameter-description-5" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +</tr> +</thead> +<tbody> +<tr> +<td>table_name</td> +<td>The name of the Carbon table in which you want to perform the update operation.</td> +</tr> +<tr> +<td>column_name</td> +<td>The destination columns to be updated.</td> +</tr> +<tr> +<td>sourceColumn</td> +<td>The source table column values to be updated in destination table.</td> +</tr> +<tr> +<td>sourceTable</td> +<td>The table from which the records are updated into destination Carbon table.</td> +</tr> +</tbody> +</table> + +<h3> +<a id="usage-guidelines-2" class="anchor" href="#usage-guidelines-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Usage Guidelines</h3> + +<p>The following conditions must be met for successful updation :</p> + +<ul> +<li>The update command fails if multiple input rows in source table are matched with single row in destination table.</li> +<li>If the source table generates empty records, the update operation will complete successfully without updating the table.</li> +<li>If a source table row does not correspond to any of the existing rows in a destination table, the update operation will complete successfully without updating the table.</li> +<li>In sub-query, if the source table and the target table are same, then the update operation fails.</li> +<li>If the sub-query used in UPDATE statement contains aggregate method or group by query, then the UPDATE operation fails.</li> +</ul> + +<h3> +<a id="examples-1" class="anchor" href="#examples-1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Examples</h3> + +<p>Update is not supported for queries that contain aggregate or group by.</p> + +<pre><code> UPDATE t_carbn01 a + SET (a.item_type_code, a.profit) = ( SELECT b.item_type_cd, + sum(b.profit) from t_carbn01b b + WHERE item_type_cd =2 group by item_type_code); +</code></pre> + +<p>Here the Update Operation fails as the query contains aggregate function sum(b.profit) and group by clause in the sub-query.</p> + +<pre><code>UPDATE carbonTable1 d +SET(d.column3,d.column5 ) = (SELECT s.c33 ,s.c55 +FROM sourceTable1 s WHERE d.column1 = s.c11) +WHERE d.column1 = 'china' EXISTS( SELECT * from table3 o where o.c2 > 1); +</code></pre> + +<pre><code>UPDATE carbonTable1 d SET (c3) = (SELECT s.c33 from sourceTable1 s +WHERE d.column1 = s.c11) +WHERE exists( select * from iud.other o where o.c2 > 1); +</code></pre> + +<pre><code>UPDATE carbonTable1 SET (c2, c5 ) = (c2 + 1, concat(c5 , "y" )); +</code></pre> + +<pre><code>UPDATE carbonTable1 d SET (c2, c5 ) = (c2 + 1, "xyx") +WHERE d.column1 = 'india'; +</code></pre> + +<pre><code>UPDATE carbonTable1 d SET (c2, c5 ) = (c2 + 1, "xyx") +WHERE d.column1 = 'india' +and EXISTS( SELECT * FROM table3 o WHERE o.column2 > 1); +</code></pre> + +<p><strong>The Status Success/Failure shall be captured in the driver log and the client.</strong></p> + +<h2> +<a id="delete-records-from-carbondata-table" class="anchor" href="#delete-records-from-carbondata-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Delete Records from CarbonData Table</h2> + +<p>This command allows us to delete records from CarbonData table.</p> + +<h3> +<a id="syntax-3" class="anchor" href="#syntax-3" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Syntax</h3> + +<pre><code>DELETE FROM table_name [WHERE expression]; +</code></pre> + +<h3> +<a id="parameter-description-6" class="anchor" href="#parameter-description-6" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Parameter Description</h3> + +<table> +<thead> +<tr> +<th>Parameter</th> +<th>Description</th> +</tr> +</thead> +<tbody> +<tr> +<td>table_name</td> +<td>The name of the Carbon table in which you want to perform the delete.</td> +</tr> +</tbody> +</table> + +<h3> +<a id="examples-2" class="anchor" href="#examples-2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Examples</h3> + +<pre><code>DELETE FROM columncarbonTable1 d WHERE d.column1 = 'china'; +</code></pre> + +<pre><code>DELETE FROM dest WHERE column1 IN ('china', 'USA'); +</code></pre> + +<pre><code>DELETE FROM columncarbonTable1 +WHERE column1 IN (SELECT column11 FROM sourceTable2); +</code></pre> + +<pre><code>DELETE FROM columncarbonTable1 +WHERE column1 IN (SELECT column11 FROM sourceTable2 WHERE +column1 = 'USA'); +</code></pre> + +<pre><code>DELETE FROM columncarbonTable1 WHERE column2 >= 4 +</code></pre> + +<p><strong>The Status Success/Failure shall be captured in the driver log and the client.</strong></p> +</div> +</div> +</div> +</div> +<div class="doc-footer"> + <a href="#top" class="scroll-top">Top</a> +</div> +</div> +</section> +</div> +</div> +</div> +</section><!-- End systemblock part --> +<script src="js/custom.js"></script> +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/faq.html ---------------------------------------------------------------------- diff --git a/content/faq.html b/content/faq.html new file mode 100644 index 0000000..fe58fe6 --- /dev/null +++ b/content/faq.html @@ -0,0 +1,258 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + <link href='images/favicon.ico' rel='shortcut icon' type='image/x-icon'> + <!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags --> + <title>CarbonData</title> + <style> + + </style> + <!-- Bootstrap --> + + <link rel="stylesheet" href="css/bootstrap.min.css"> + <link href="css/style.css" rel="stylesheet"> + <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> + <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js";></script> + <script src="https://oss.maxcdn.scom/respond/1.4.2/respond.min.js";></script> + <![endif]--> + <script src="js/jquery.min.js"></script> + <script src="js/bootstrap.min.js"></script> + + +</head> +<body> +<header> + <nav class="navbar navbar-default navbar-custom cd-navbar-wrapper"> + <div class="container"> + <div class="navbar-header"> + <button aria-controls="navbar" aria-expanded="false" data-target="#navbar" data-toggle="collapse" + class="navbar-toggle collapsed" type="button"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> + <a href="index.html" class="logo"> + <img src="images/CarbonDataLogo.png" alt="CarbonData logo" title="CarbocnData logo"/> + </a> + </div> + <div class="navbar-collapse collapse cd_navcontnt" id="navbar"> + <ul class="nav navbar-nav navbar-right navlist-custom"> + <li><a href="index.html" class="hidden-xs"><i class="fa fa-home" aria-hidden="true"></i> </a> + </li> + <li><a href="index.html" class="hidden-lg hidden-md hidden-sm">Home</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle " data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false"> Download <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/1.0.0-incubating"; + target="_blank">Apache CarbonData 1.0.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.2.0-incubating"; + target="_blank">Apache CarbonData 0.2.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.1-incubating"; + target="_blank">Apache CarbonData 0.1.1</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.0-incubating"; + target="_blank">Apache CarbonData 0.1.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="mainpage.html" class="">Documentation</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false">Community <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://github.com/apache/incubator-carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PPMC+and+Committers+member+list"; + target="_blank">Project PPMC and Committers</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=66850609"; + target="_blank">CarbonData Meetups</a></li> + <li><a href="security.html">Apache CarbonData Security</a></li> + <li><a href="https://issues.apache.org/jira/browse/CARBONDATA"; target="_blank">Apache + Jira</a></li> + <li><a href="videogallery.html">CarbonData Videos </a></li> + </ul> + </li> + <li class="dropdown"> + <a href="http://www.apache.org/"; class="apache_link hidden-xs dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="http://www.apache.org/"; class="hidden-lg hidden-md hidden-sm dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li> + <a href="#" id="search-icon"><i class="fa fa-search" aria-hidden="true"></i></a> + + </li> + + </ul> + </div><!--/.nav-collapse --> + <div id="search-box"> + <form method="get" action="http://www.google.com/search";> + <div class="search-block"> + <table border="0" cellpadding="0" width="100%"> + <tr> + <td style="width:80%"> + <input type="text" name="q" size=" 5" maxlength="255" value="" + class="search-input"/> + </td> + <td style="width:20%"> + <input type="submit" value="Search"/></td> + </tr> + <tr> + <td align="left" style="font-size:75%" colspan="2"> + <input type="checkbox" name="sitesearch" value="carbondata.apache.org" checked/> + Only search for CarbonData + </td> + </tr> + </table> + </div> + </form> + </div> + </div> + </nav> +</header> <!-- end Header part --> + +<div class="fixed-padding"></div> <!-- top padding with fixde header --> + +<section><!-- Dashboard nav --> + <div class="container-fluid q"> + <div class="col-sm-12 col-md-12 maindashboard"> + <div class="row"> + <section> + <div style="padding:10px 15px;"> + <div id="viewpage" name="viewpage"> + <div class="row"> + <div class="col-sm-12 col-md-12"> + <div> + +<h1> +<a id="faqs" class="anchor" href="#faqs" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>FAQs</h1> + +<ul> +<li><a href="#what-are-bad-records">What are Bad Records?</a></li> +<li><a href="#where-are-bad-records-stored-in-carbondata">Where are Bad Records Stored in CarbonData?</a></li> +<li><a href="#how-to-enable-bad-record-logging">How to enable Bad Record Logging?</a></li> +<li><a href="#how-to-ignore-the-bad-records">How to ignore the Bad Records?</a></li> +<li><a href="#how-to-specify-store-location-while-creating-carbon-session">How to specify store location while creating carbon session?</a></li> +<li><a href="#what-is-carbon-lock-type">What is Carbon Lock Type?</a></li> +<li><a href="#how-to-resolve-abstract-method-error">How to resolve Abstract Method Error?</a></li> +</ul> + +<h2> +<a id="what-are-bad-records" class="anchor" href="#what-are-bad-records" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>What are Bad Records?</h2> + +<p>Records that fail to get loaded into the CarbonData due to data type incompatibility or are empty or have incompatible format are classified as Bad Records.</p> + +<h2> +<a id="where-are-bad-records-stored-in-carbondata" class="anchor" href="#where-are-bad-records-stored-in-carbondata" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Where are Bad Records Stored in CarbonData?</h2> + +<p>The bad records are stored at the location set in carbon.badRecords.location in carbon.properties file. +By default <strong>carbon.badRecords.location</strong> specifies the following location <code>/opt/Carbon/Spark/badrecords</code>.</p> + +<h2> +<a id="how-to-enable-bad-record-logging" class="anchor" href="#how-to-enable-bad-record-logging" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>How to enable Bad Record Logging?</h2> + +<p>While loading data we can specify the approach to handle Bad Records. In order to analyse the cause of the Bad Records the parameter <code>BAD_RECORDS_LOGGER_ENABLE</code> must be set to value <code>TRUE</code>. There are multiple approaches to handle Bad Records which can be specified by the parameter <code>BAD_RECORDS_ACTION</code>.</p> + +<ul> +<li>To pad the incorrect values of the csv rows with NULL value and load the data in CarbonData, set the following in the query :</li> +</ul> + +<pre><code>'BAD_RECORDS_ACTION'='FORCE' +</code></pre> + +<ul> +<li>To write the Bad Records without padding incorrect values with NULL in the raw csv (set in the parameter <strong>carbon.badRecords.location</strong>), set the following in the query :</li> +</ul> + +<pre><code>'BAD_RECORDS_ACTION'='REDIRECT' +</code></pre> + +<h2> +<a id="how-to-ignore-the-bad-records" class="anchor" href="#how-to-ignore-the-bad-records" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>How to ignore the Bad Records?</h2> + +<p>To ignore the Bad Records from getting stored in the raw csv, we need to set the following in the query :</p> + +<pre><code>'BAD_RECORDS_ACTION'='IGNORE' +</code></pre> + +<h2> +<a id="how-to-specify-store-location-while-creating-carbon-session" class="anchor" href="#how-to-specify-store-location-while-creating-carbon-session" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>How to specify store location while creating carbon session?</h2> + +<p>The store location specified while creating carbon session is used by the CarbonData to store the meta data like the schema, dictionary files, dictionary meta data and sort indexes.</p> + +<p>Try creating <code>carbonsession</code> with <code>storepath</code> specified in the following manner :</p> + +<pre><code>val carbon = SparkSession.builder().config(sc.getConf).getOrCreateCarbonSession(<store_path>) +</code></pre> + +<p>Example:</p> + +<pre><code>val carbon = SparkSession.builder().config(sc.getConf).getOrCreateCarbonSession("hdfs://localhost:9000/carbon/store ") +</code></pre> + +<h2> +<a id="what-is-carbon-lock-type" class="anchor" href="#what-is-carbon-lock-type" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>What is Carbon Lock Type?</h2> + +<p>The Apache CarbonData acquires lock on the files to prevent concurrent operation from modifying the same files. The lock can be of the following types depending on the storage location, for HDFS we specify it to be of type HDFSLOCK. By default it is set to type LOCALLOCK. +The property carbon.lock.type configuration specifies the type of lock to be acquired during concurrent operations on table. This property can be set with the following values :</p> + +<ul> +<li> +<strong>LOCALLOCK</strong> : This Lock is created on local file system as file. This lock is useful when only one spark driver (thrift server) runs on a machine and no other CarbonData spark application is launched concurrently.</li> +<li> +<strong>HDFSLOCK</strong> : This Lock is created on HDFS file system as file. This lock is useful when multiple CarbonData spark applications are launched and no ZooKeeper is running on cluster and the HDFS supports, file based locking.</li> +</ul> + +<h2> +<a id="how-to-resolve-abstract-method-error" class="anchor" href="#how-to-resolve-abstract-method-error" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>How to resolve Abstract Method Error?</h2> + +<p>In order to build CarbonData project it is necessary to specify the spark profile. The spark profile sets the Spark Version. You need to specify the <code>spark version</code> while using Maven to build project.</p> +</div> +</div> +</div> +</div> +<div class="doc-footer"> + <a href="#top" class="scroll-top">Top</a> +</div> +</div> +</section> +</div> +</div> +</div> +</section><!-- End systemblock part --> +<script src="js/custom.js"></script> +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/file-structure-of-carbondata.html ---------------------------------------------------------------------- diff --git a/content/file-structure-of-carbondata.html b/content/file-structure-of-carbondata.html new file mode 100644 index 0000000..aa0040c --- /dev/null +++ b/content/file-structure-of-carbondata.html @@ -0,0 +1,209 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + <link href='images/favicon.ico' rel='shortcut icon' type='image/x-icon'> + <!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags --> + <title>CarbonData</title> + <style> + + </style> + <!-- Bootstrap --> + + <link rel="stylesheet" href="css/bootstrap.min.css"> + <link href="css/style.css" rel="stylesheet"> + <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> + <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js";></script> + <script src="https://oss.maxcdn.scom/respond/1.4.2/respond.min.js";></script> + <![endif]--> + <script src="js/jquery.min.js"></script> + <script src="js/bootstrap.min.js"></script> + + +</head> +<body> +<header> + <nav class="navbar navbar-default navbar-custom cd-navbar-wrapper"> + <div class="container"> + <div class="navbar-header"> + <button aria-controls="navbar" aria-expanded="false" data-target="#navbar" data-toggle="collapse" + class="navbar-toggle collapsed" type="button"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> + <a href="index.html" class="logo"> + <img src="images/CarbonDataLogo.png" alt="CarbonData logo" title="CarbocnData logo"/> + </a> + </div> + <div class="navbar-collapse collapse cd_navcontnt" id="navbar"> + <ul class="nav navbar-nav navbar-right navlist-custom"> + <li><a href="index.html" class="hidden-xs"><i class="fa fa-home" aria-hidden="true"></i> </a> + </li> + <li><a href="index.html" class="hidden-lg hidden-md hidden-sm">Home</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle " data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false"> Download <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/1.0.0-incubating"; + target="_blank">Apache CarbonData 1.0.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.2.0-incubating"; + target="_blank">Apache CarbonData 0.2.0</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.1-incubating"; + target="_blank">Apache CarbonData 0.1.1</a></li> + <li> + <a href="https://www.apache.org/dyn/closer.lua/incubator/carbondata/0.1.0-incubating"; + target="_blank">Apache CarbonData 0.1.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="mainpage.html" class="">Documentation</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" + aria-expanded="false">Community <span class="caret"></span></a> + <ul class="dropdown-menu"> + <li> + <a href="https://github.com/apache/incubator-carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PPMC+and+Committers+member+list"; + target="_blank">Project PPMC and Committers</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=66850609"; + target="_blank">CarbonData Meetups</a></li> + <li><a href="security.html">Apache CarbonData Security</a></li> + <li><a href="https://issues.apache.org/jira/browse/CARBONDATA"; target="_blank">Apache + Jira</a></li> + <li><a href="videogallery.html">CarbonData Videos </a></li> + </ul> + </li> + <li class="dropdown"> + <a href="http://www.apache.org/"; class="apache_link hidden-xs dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="http://www.apache.org/"; class="hidden-lg hidden-md hidden-sm dropdown-toggle" + data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache</a> + <ul class="dropdown-menu"> + <li><a href="http://www.apache.org/"; target="_blank">Apache Homepage</a></li> + <li><a href="http://www.apache.org/licenses/"; target="_blank">License</a></li> + <li><a href="http://www.apache.org/foundation/sponsorship.html"; + target="_blank">Sponsorship</a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; target="_blank">Thanks</a></li> + </ul> + </li> + + <li> + <a href="#" id="search-icon"><i class="fa fa-search" aria-hidden="true"></i></a> + + </li> + + </ul> + </div><!--/.nav-collapse --> + <div id="search-box"> + <form method="get" action="http://www.google.com/search";> + <div class="search-block"> + <table border="0" cellpadding="0" width="100%"> + <tr> + <td style="width:80%"> + <input type="text" name="q" size=" 5" maxlength="255" value="" + class="search-input"/> + </td> + <td style="width:20%"> + <input type="submit" value="Search"/></td> + </tr> + <tr> + <td align="left" style="font-size:75%" colspan="2"> + <input type="checkbox" name="sitesearch" value="carbondata.apache.org" checked/> + Only search for CarbonData + </td> + </tr> + </table> + </div> + </form> + </div> + </div> + </nav> +</header> <!-- end Header part --> + +<div class="fixed-padding"></div> <!-- top padding with fixde header --> + +<section><!-- Dashboard nav --> + <div class="container-fluid q"> + <div class="col-sm-12 col-md-12 maindashboard"> + <div class="row"> + <section> + <div style="padding:10px 15px;"> + <div id="viewpage" name="viewpage"> + <div class="row"> + <div class="col-sm-12 col-md-12"> + <div> + +<h1> +<a id="carbondata-file-structure" class="anchor" href="#carbondata-file-structure" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>CarbonData File Structure</h1> + +<p>CarbonData files contain groups of data called blocklets, along with all required information like schema, offsets and indices etc, in a file header and footer, co-located in HDFS.</p> + +<p>The file footer can be read once to build the indices in memory, which can be utilized for optimizing the scans and processing for all subsequent queries.</p> + +<h3> +<a id="understanding-carbondata-file-structure" class="anchor" href="#understanding-carbondata-file-structure" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Understanding CarbonData File Structure</h3> + +<ul> +<li>Block : It would be as same as HDFS block, CarbonData creates one file for each data block, user can specify TABLE_BLOCKSIZE during creation table. Each file contains File Header, Blocklets and File Footer. </li> +</ul> + +<p><a href="../docs/images/carbon_data_file_structure_new.png?raw=true" target="_blank"><img src="https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"; alt="CarbonData File Structure" style="max-width:100%;"></a></p> + +<ul> +<li>File Header : It contains CarbonData file version number, list of column schema and schema updation timestamp.</li> +<li>File Footer : it contains Number of rows, segmentinfo ,all blocklets? info and index, you can find the detail from the below diagram.</li> +<li>Blocklet : Rows are grouped to form a blocklet, the size of the blocklet is configurable and default size is 64MB, Blocklet contains Column Page groups for each column.</li> +<li>Column Page Group : Data of one column and it is further divided to pages, it is guaranteed to be contiguous in file.</li> +<li>Page : It has the data of one column and the number of row is fixed to 32000 size. </li> +</ul> + +<p><a href="../docs/images/carbon_data_format_new.png?raw=true" target="_blank"><img src="https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"; alt="CarbonData File Format" style="max-width:100%;"></a></p> + +<h3> +<a id="each-page-contains-three-types-of-data" class="anchor" href="#each-page-contains-three-types-of-data" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Each page contains three types of data</h3> + +<ul> +<li>Data Page: Contains the encoded data of a column of columns.</li> +<li>Row ID Page (optional): Contains the row ID mappings used when the data page is stored as an inverted index.</li> +<li>RLE Page (optional): Contains additional metadata used when the data page is RLE coded.</li> +</ul> +</div> +</div> +</div> +</div> +<div class="doc-footer"> + <a href="#top" class="scroll-top">Top</a> +</div> +</div> +</section> +</div> +</div> +</div> +</section><!-- End systemblock part --> +<script src="js/custom.js"></script> +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/fonts/FontAwesome.otf ---------------------------------------------------------------------- diff --git a/content/fonts/FontAwesome.otf b/content/fonts/FontAwesome.otf new file mode 100644 index 0000000..401ec0f Binary files /dev/null and b/content/fonts/FontAwesome.otf differ http://git-wip-us.apache.org/repos/asf/incubator-carbondata-site/blob/b96a419a/content/fonts/OpenSans-Bold.eot ---------------------------------------------------------------------- diff --git a/content/fonts/OpenSans-Bold.eot b/content/fonts/OpenSans-Bold.eot new file mode 100644 index 0000000..016123b Binary files /dev/null and b/content/fonts/OpenSans-Bold.eot differ
![https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"](https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"){kind=link}
![https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"](https://github.com/apache/incubator-carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"){kind=link}