http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/dml-of-carbondata.html ---------------------------------------------------------------------- diff --git a/content/dml-of-carbondata.html b/content/dml-of-carbondata.html new file mode 100644 index 0000000..2048c9e --- /dev/null +++ b/content/dml-of-carbondata.html @@ -0,0 +1,588 @@ +<!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> + <script defer src="https://use.fontawesome.com/releases/v5.0.8/js/all.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://dist.apache.org/repos/dist/release/carbondata/1.4.1/"; + target="_blank">Apache CarbonData 1.4.1</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.4.0/"; + target="_blank">Apache CarbonData 1.4.0</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.3.1/"; + target="_blank">Apache CarbonData 1.3.1</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.3.0/"; + target="_blank">Apache CarbonData 1.3.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="documentation.html" class="active">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/carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://github.com/apache/carbondata/blob/master/docs/release-guide.md"; + target="_blank">Release Guide</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PMC+and+Committers+member+list"; + target="_blank">Project PMC 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"; target="_blank"> + <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" placeholder="Search...." required/> + </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/> + <span style=" position: relative; top: -3px;"> Only search for CarbonData</span> + </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="verticalnavbar"> + <nav class="b-sticky-nav"> + <div class="nav-scroller"> + <div class="nav__inner"> + <a class="b-nav__intro nav__item" href="./introduction.html">introduction</a> + <a class="b-nav__quickstart nav__item" href="./quick-start-guide.html">quick start</a> + <a class="b-nav__uses nav__item" href="./usescases.html">use cases</a> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__docs nav__item nav__sub__anchor" href="./language-manual.html">Language Reference</a> + <a class="nav__item nav__sub__item" href="./ddl-of-carbondata.html">DDL</a> + <a class="nav__item nav__sub__item" href="./dml-of-carbondata.html">DML</a> + <a class="nav__item nav__sub__item" href="./streaming-guide.html">Streaming</a> + <a class="nav__item nav__sub__item" href="./configuration-parameters.html">Configuration</a> + <a class="nav__item nav__sub__item" href="./datamap-developer-guide.html">Datamaps</a> + <a class="nav__item nav__sub__item" href="./supported-data-types-in-carbondata.html">Data Types</a> + </div> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__datamap nav__item nav__sub__anchor" href="./datamap-management.html">DataMaps</a> + <a class="nav__item nav__sub__item" href="./bloomfilter-datamap-guide.html">Bloom Filter</a> + <a class="nav__item nav__sub__item" href="./lucene-datamap-guide.html">Lucene</a> + <a class="nav__item nav__sub__item" href="./preaggregate-datamap-guide.html">Pre-Aggregate</a> + <a class="nav__item nav__sub__item" href="./timeseries-datamap-guide.html">Time Series</a> + </div> + + <a class="b-nav__s3 nav__item" href="./s3-guide.html">S3 Support</a> + <a class="b-nav__api nav__item" href="./sdk-guide.html">API</a> + <a class="b-nav__perf nav__item" href="./performance-tuning.html">Performance Tuning</a> + <a class="b-nav__faq nav__item" href="./faq.html">FAQ</a> + <a class="b-nav__contri nav__item" href="./how-to-contribute-to-apache-carbondata.html">Contribute</a> + <a class="b-nav__security nav__item" href="./security.html">Security</a> + <a class="b-nav__release nav__item" href="./release-guide.html">Release Guide</a> + </div> + </div> + <div class="navindicator"> + <div class="b-nav__intro navindicator__item"></div> + <div class="b-nav__quickstart navindicator__item"></div> + <div class="b-nav__uses navindicator__item"></div> + <div class="b-nav__docs navindicator__item"></div> + <div class="b-nav__datamap navindicator__item"></div> + <div class="b-nav__s3 navindicator__item"></div> + <div class="b-nav__api navindicator__item"></div> + <div class="b-nav__perf navindicator__item"></div> + <div class="b-nav__faq navindicator__item"></div> + <div class="b-nav__contri navindicator__item"></div> + <div class="b-nav__security navindicator__item"></div> + </div> + </nav> + </div> + <div class="mdcontent"> + <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-data-manipulation-language" class="anchor" href="#carbondata-data-manipulation-language" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>CarbonData Data Manipulation Language</h1> +<p>CarbonData DML statements are documented here,which includes:</p> +<ul> +<li><a href="#load-data">LOAD DATA</a></li> +<li><a href="#insert-data-into-carbondata-table">INSERT DATA</a></li> +<li><a href="#load-data-using-static-partition">Load Data Using Static Partition</a></li> +<li><a href="#load-data-using-dynamic-partition">Load Data Using Dynamic Partition</a></li> +<li><a href="#update-and-delete">UPDATE AND DELETE</a></li> +<li><a href="#compaction">COMPACTION</a></li> +<li><a href="./segment-management-on-carbondata.html">SEGMENT MANAGEMENT</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> +<h3> +<a id="load-files-to-carbondata-table" class="anchor" href="#load-files-to-carbondata-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>LOAD FILES TO CARBONDATA TABLE</h3> +<p>This command is used to load csv files to carbondata, OPTIONS are not mandatory for data loading process.</p> +<pre><code>LOAD DATA [LOCAL] INPATH 'folder_path' +INTO TABLE [db_name.]table_name +OPTIONS(property_name=property_value, ...) +</code></pre> +<p><strong>Supported Properties:</strong> <a href="#delimiter">DELIMITER</a>, <a href="#quotechar">QUOTECHAR</a>, <a href="#commentchar">COMMENTCHAR</a>, <a href="#header">HEADER</a>, <a href="#fileheader">FILEHEADER</a>, <a href="#multiline">MULTILINE</a>, <a href="#escapechar">ESCAPECHAR</a>, <a href="#skip_empty_line">SKIP_EMPTY_LINE</a>, <a href="#complex_delimiter_level_1">COMPLEX_DELIMITER_LEVEL_1</a>, <a href="#complex_delimiter_level_2">COMPLEX_DELIMITER_LEVEL_2</a>, <a href="#all_dictionary_path">ALL_DICTIONARY_PATH</a>, <a href="#columndict">COLUMNDICT</a>, <a href="#dateformat">DATEFORMAT</a>,<a href="#timestampformat"> TIMESTAMPFORMAT</a>, <a href="#sort-column-bounds">SORT_COLUMN_BOUNDS</a>, <a href="#single_pass">SINGLE_PASS</a>, <a href="#bad-records-handling">BAD_RECORDS_LOGGER_ENABLE</a>, <a href="#bad-records-handling">BAD_RECORD_PATH</a>, <a href="#bad-records-handling">BAD_RECORDS_ACTION</a>, <a href="#bad-records-handling">IS_EMPTY_DATA_BAD_RECORD</a>, <a href=" #global_sort_partitions">GLOBAL_SORT_PARTITIONS</a></p> +<p>You can use the following options to load data:</p> +<ul> +<li> +<h5> +<a id="delimiter" class="anchor" href="#delimiter" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DELIMITER:</h5> +<p>Delimiters can be provided in the load command.</p> +<pre><code>OPTIONS('DELIMITER'=',') +</code></pre> +</li> +<li> +<h5> +<a id="quotechar" class="anchor" href="#quotechar" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>QUOTECHAR:</h5> +<p>Quote Characters can be provided in the load command.</p> +<pre><code>OPTIONS('QUOTECHAR'='"') +</code></pre> +</li> +<li> +<h5> +<a id="commentchar" class="anchor" href="#commentchar" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>COMMENTCHAR:</h5> +<p>Comment Characters can be provided in the load command if user want to comment lines.</p> +<pre><code>OPTIONS('COMMENTCHAR'='#') +</code></pre> +</li> +<li> +<h5> +<a id="header" class="anchor" href="#header" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>HEADER:</h5> +<p>When you load the CSV file without the file header and the file header is the same with the table schema, then add 'HEADER'='false' to load data SQL as user need not provide the file header. By default the value is 'true'. +false: CSV file is without file header. +true: CSV file is with file header.</p> +<pre><code>OPTIONS('HEADER'='false') +</code></pre> +<p><strong>NOTE:</strong> If the HEADER option exist and is set to 'true', then the FILEHEADER option is not required.</p> +</li> +<li> +<h5> +<a id="fileheader" class="anchor" href="#fileheader" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>FILEHEADER:</h5> +<p>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> +<h5> +<a id="multiline" class="anchor" href="#multiline" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>MULTILINE:</h5> +<p>CSV with new line character in quotes.</p> +<pre><code>OPTIONS('MULTILINE'='true') +</code></pre> +</li> +<li> +<h5> +<a id="escapechar" class="anchor" href="#escapechar" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>ESCAPECHAR:</h5> +<p>Escape char can be provided if user want strict validation of escape character in CSV files.</p> +<pre><code>OPTIONS('ESCAPECHAR'='\') +</code></pre> +</li> +<li> +<h5> +<a id="skip_empty_line" class="anchor" href="#skip_empty_line" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>SKIP_EMPTY_LINE:</h5> +<p>This option will ignore the empty line in the CSV file during the data load.</p> +<pre><code>OPTIONS('SKIP_EMPTY_LINE'='TRUE/FALSE') +</code></pre> +</li> +<li> +<h5> +<a id="complex_delimiter_level_1" class="anchor" href="#complex_delimiter_level_1" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>COMPLEX_DELIMITER_LEVEL_1:</h5> +<p>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'='$') +</code></pre> +</li> +<li> +<h5> +<a id="complex_delimiter_level_2" class="anchor" href="#complex_delimiter_level_2" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>COMPLEX_DELIMITER_LEVEL_2:</h5> +<p>Split the complex type nested data column in a row. Applies level_1 delimiter & applies level_2 based on complex data type (eg., a:b$c:d --> Array> = {{a,b},{c,d}}).</p> +<pre><code>OPTIONS('COMPLEX_DELIMITER_LEVEL_2'=':') +</code></pre> +</li> +<li> +<h5> +<a id="all_dictionary_path" class="anchor" href="#all_dictionary_path" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>ALL_DICTIONARY_PATH:</h5> +<p>All dictionary files path.</p> +<pre><code>OPTIONS('ALL_DICTIONARY_PATH'='/opt/alldictionary/data.dictionary') +</code></pre> +</li> +<li> +<h5> +<a id="columndict" class="anchor" href="#columndict" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>COLUMNDICT:</h5> +<p>Dictionary file path for specified column.</p> +<pre><code>OPTIONS('COLUMNDICT'='column1:dictionaryFilePath1,column2:dictionaryFilePath2') +</code></pre> +<p><strong>NOTE:</strong> ALL_DICTIONARY_PATH and COLUMNDICT can't be used together.</p> +</li> +<li> +<h5> +<a id="dateformattimestampformat" class="anchor" href="#dateformattimestampformat" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DATEFORMAT/TIMESTAMPFORMAT:</h5> +<p>Date and Timestamp format for specified column.</p> +<pre><code>OPTIONS('DATEFORMAT' = 'yyyy-MM-dd','TIMESTAMPFORMAT'='yyyy-MM-dd HH:mm:ss') +</code></pre> +<p><strong>NOTE:</strong> 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 rel="nofollow">SimpleDateFormat</a>.</p> +</li> +<li> +<h5> +<a id="sort-column-bounds" class="anchor" href="#sort-column-bounds" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>SORT COLUMN BOUNDS:</h5> +<p>Range bounds for sort columns.</p> +<p>Suppose the table is created with 'SORT_COLUMNS'='name,id' and the range for name is aaa<del>zzz, the value range for id is 0</del>1000. Then during data loading, we can specify the following option to enhance data loading performance.</p> +<pre><code>OPTIONS('SORT_COLUMN_BOUNDS'='f,250;l,500;r,750') +</code></pre> +<p>Each bound is separated by ';' and each field value in bound is separated by ','. In the example above, we provide 3 bounds to distribute records to 4 partitions. The values 'f','l','r' can evenly distribute the records. Inside carbondata, for a record we compare the value of sort columns with that of the bounds and decide which partition the record will be forwarded to.</p> +<p><strong>NOTE:</strong></p> +<ul> +<li>SORT_COLUMN_BOUNDS will be used only when the SORT_SCOPE is 'local_sort'.</li> +<li>Carbondata will use these bounds as ranges to process data concurrently during the final sort percedure. The records will be sorted and written out inside each partition. Since the partition is sorted, all records will be sorted.</li> +<li>Since the actual order and literal order of the dictionary column are not necessarily the same, we do not recommend you to use this feature if the first sort column is 'dictionary_include'.</li> +<li>The option works better if your CPU usage during loading is low. If your system is already CPU tense, better not to use this option. Besides, it depends on the user to specify the bounds. If user does not know the exactly bounds to make the data distributed evenly among the bounds, loading performance will still be better than before or at least the same as before.</li> +<li>Users can find more information about this option in the description of PR1953.</li> +</ul> +</li> +<li> +<h5> +<a id="single_pass" class="anchor" href="#single_pass" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>SINGLE_PASS:</h5> +<p>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> +</li> +</ul> +<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><strong>NOTE:</strong></p> +<ul> +<li>If this option is set to TRUE then data loading will take less time.</li> +<li>If this option is set to some invalid value other than TRUE or FALSE then it uses the default value.</li> +</ul> +<p>Example:</p> +<pre><code>LOAD DATA local inpath '/opt/rawdata/data.csv' INTO table carbontable +options('DELIMITER'=',', 'QUOTECHAR'='"','COMMENTCHAR'='#', +'HEADER'='false', +'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> +<ul> +<li> +<h5> +<a id="bad-records-handling" class="anchor" href="#bad-records-handling" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>BAD RECORDS HANDLING:</h5> +<p>Methods of handling bad records are as follows:</p> +<ul> +<li>Load all of the data before dealing with the errors.</li> +<li>Clean or delete bad records before loading data or stop the loading when bad records are found.</li> +</ul> +<pre><code>OPTIONS('BAD_RECORDS_LOGGER_ENABLE'='true', 'BAD_RECORD_PATH'='hdfs://hacluster/tmp/carbon', 'BAD_RECORDS_ACTION'='REDIRECT', 'IS_EMPTY_DATA_BAD_RECORD'='false') +</code></pre> +</li> +</ul> +<p><strong>NOTE:</strong></p> +<ul> +<li>BAD_RECORDS_ACTION property can have four type of actions for bad records FORCE, REDIRECT, IGNORE and FAIL.</li> +<li>FAIL option is its Default value. If the FAIL option is used, then data loading fails if any bad records are found.</li> +<li>If the REDIRECT option is used, CarbonData will add all bad records in to a separate CSV file. However, this file must not be used for subsequent data loading because the content may not exactly match the source record. You are advised to cleanse the original source record for further data ingestion. This option is used to remind you which records are bad records.</li> +<li>If the FORCE option is used, then it auto-converts the data by storing the bad records as NULL before Loading data.</li> +<li>If the IGNORE option is used, then bad records are neither loaded nor written to the separate CSV file.</li> +<li>In loaded data, if all records are bad records, the BAD_RECORDS_ACTION is invalid and the load operation fails.</li> +<li>The default maximum number of characters per column is 32000. If there are more than 32000 characters in a column, please refer to <em>String longer than 32000 characters</em> section.</li> +<li>Since Bad Records Path can be specified in create, load and carbon properties. +Therefore, value specified in load will have the highest priority, and value specified in carbon properties will have the least priority.</li> +</ul> +<p><strong>Bad Records Path:</strong> +This property is used to specify the location where bad records would be written.</p> +<pre><code>TBLPROPERTIES('BAD_RECORDS_PATH'='/opt/badrecords'') +</code></pre> +<p>Example:</p> +<pre><code>LOAD DATA INPATH 'filepath.csv' INTO TABLE tablename +OPTIONS('BAD_RECORDS_LOGGER_ENABLE'='true','BAD_RECORD_PATH'='hdfs://hacluster/tmp/carbon', +'BAD_RECORDS_ACTION'='REDIRECT','IS_EMPTY_DATA_BAD_RECORD'='false') +</code></pre> +<ul> +<li> +<h5> +<a id="global_sort_partitions" class="anchor" href="#global_sort_partitions" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>GLOBAL_SORT_PARTITIONS:</h5> +<p>If the SORT_SCOPE is defined as GLOBAL_SORT, then user can specify the number of partitions to use while shuffling data for sort using GLOBAL_SORT_PARTITIONS. If it is not configured, or configured less than 1, then it uses the number of map task as reduce task. It is recommended that each reduce task deal with 512MB-1GB data.</p> +</li> +</ul> +<pre><code>OPTIONS('GLOBAL_SORT_PARTITIONS'='2') +</code></pre> +<p>NOTE:</p> +<ul> +<li>GLOBAL_SORT_PARTITIONS should be Integer type, the range is [1,Integer.MaxValue].</li> +<li>It is only used when the SORT_SCOPE is GLOBAL_SORT.</li> +</ul> +<h3> +<a id="insert-data-into-carbondata-table" class="anchor" href="#insert-data-into-carbondata-table" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>INSERT DATA INTO CARBONDATA TABLE</h3> +<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> +<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> +<p>Overwrite insert data:</p> +<pre><code>INSERT OVERWRITE TABLE <CARBONDATA TABLE> SELECT * FROM sourceTableName +[ WHERE { <filter_condition> } ] +</code></pre> +<p><strong>NOTE:</strong></p> +<ul> +<li>The source table and the CarbonData table must have the same table schema.</li> +<li>The data type of source and destination table columns should be same</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>Examples</p> +<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 OVERWRITE TABLE table1 SELECT * FROM TABLE2 +</code></pre> +<h3> +<a id="load-data-using-static-partition" class="anchor" href="#load-data-using-static-partition" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Load Data Using Static Partition</h3> +<p>This command allows you to load data using static partition.</p> +<pre><code>LOAD DATA [LOCAL] INPATH 'folder_path' +INTO TABLE [db_name.]table_name PARTITION (partition_spec) +OPTIONS(property_name=property_value, ...) +INSERT INTO INTO TABLE [db_name.]table_name PARTITION (partition_spec) <SELECT STATEMENT> +</code></pre> +<p>Example:</p> +<pre><code>LOAD DATA LOCAL INPATH '${env:HOME}/staticinput.csv' +INTO TABLE locationTable +PARTITION (country = 'US', state = 'CA') +INSERT INTO TABLE locationTable +PARTITION (country = 'US', state = 'AL') +SELECT <columns list excluding partition columns> FROM another_user +</code></pre> +<h3> +<a id="load-data-using-dynamic-partition" class="anchor" href="#load-data-using-dynamic-partition" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Load Data Using Dynamic Partition</h3> +<p>This command allows you to load data using dynamic partition. If partition spec is not specified, then the partition is considered as dynamic.</p> +<p>Example:</p> +<pre><code>LOAD DATA LOCAL INPATH '${env:HOME}/staticinput.csv' +INTO TABLE locationTable +INSERT INTO TABLE locationTable +SELECT <columns list excluding partition columns> FROM another_user +</code></pre> +<h2> +<a id="update-and-delete" class="anchor" href="#update-and-delete" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>UPDATE AND DELETE</h2> +<h3> +<a id="update" class="anchor" href="#update" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>UPDATE</h3> +<p>This command will allow to update the CarbonData table based on the column expression and optional filter conditions.</p> +<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 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> +<p><strong>NOTE:</strong> The update command fails if multiple input rows in source table are matched with single row in destination table.</p> +<p>Examples:</p> +<pre><code>UPDATE t3 SET (t3_salary) = (t3_salary + 9) WHERE t3_name = 'aaa1' +</code></pre> +<pre><code>UPDATE t3 SET (t3_date, t3_country) = ('2017-11-18', 'india') WHERE t3_salary < 15003 +</code></pre> +<pre><code>UPDATE t3 SET (t3_country, t3_name) = (SELECT t5_country, t5_name FROM t5 WHERE t5_id = 5) WHERE t3_id < 5 +</code></pre> +<pre><code>UPDATE t3 SET (t3_date, t3_serialname, t3_salary) = (SELECT '2099-09-09', t5_serialname, '9999' FROM t5 WHERE t5_id = 5) WHERE t3_id < 5 +</code></pre> +<pre><code>UPDATE t3 SET (t3_country, t3_salary) = (SELECT t5_country, t5_salary FROM t5 FULL JOIN t3 u WHERE u.t3_id = t5_id and t5_id=6) WHERE t3_id >6 +</code></pre> +<p>NOTE: Update Complex datatype columns is not supported.</p> +<h3> +<a id="delete" class="anchor" href="#delete" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>DELETE</h3> +<p>This command allows us to delete records from CarbonData table.</p> +<pre><code>DELETE FROM table_name [WHERE expression] +</code></pre> +<p>Examples:</p> +<pre><code>DELETE FROM carbontable WHERE column1 = 'china' +</code></pre> +<pre><code>DELETE FROM carbontable WHERE column1 IN ('china', 'USA') +</code></pre> +<pre><code>DELETE FROM carbontable WHERE column1 IN (SELECT column11 FROM sourceTable2) +</code></pre> +<pre><code>DELETE FROM carbontable WHERE column1 IN (SELECT column11 FROM sourceTable2 WHERE column1 = 'USA') +</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>Compaction improves the query performance significantly.</p> +<p>There are several types of compaction.</p> +<pre><code>ALTER TABLE [db_name.]table_name COMPACT 'MINOR/MAJOR/CUSTOM' +</code></pre> +<ul> +<li><strong>Minor Compaction</strong></li> +</ul> +<p>In Minor compaction, user can specify the number of loads to be merged. +Minor compaction triggers for every data load if the parameter carbon.enable.auto.load.merge is set to true. +If any segments are available to be merged, then compaction will run parallel with data load, there are 2 levels in minor compaction:</p> +<ul> +<li>Level 1: Merging of the segments which are not yet compacted.</li> +<li>Level 2: Merging of the compacted segments again to form a larger segment.</li> +</ul> +<pre><code>ALTER TABLE table_name COMPACT 'MINOR' +</code></pre> +<ul> +<li><strong>Major Compaction</strong></li> +</ul> +<p>In Major compaction, multiple segments can be merged into one large segment. +User will specify the compaction size until which segments can be merged, Major compaction is usually done during the off-peak time. +Configure the property carbon.major.compaction.size with appropriate value in MB.</p> +<p>This command merges the specified number of segments into one segment:</p> +<pre><code>ALTER TABLE table_name COMPACT 'MAJOR' +</code></pre> +<ul> +<li><strong>Custom Compaction</strong></li> +</ul> +<p>In Custom compaction, user can directly specify segment ids to be merged into one large segment. +All specified segment ids should exist and be valid, otherwise compaction will fail. +Custom compaction is usually done during the off-peak time.</p> +<pre><code>ALTER TABLE table_name COMPACT 'CUSTOM' WHERE SEGMENT.ID IN (2,3,4) +</code></pre> +<p>NOTE: Compaction is unsupported for table containing Complex columns.</p> +<ul> +<li><strong>CLEAN SEGMENTS AFTER Compaction</strong></li> +</ul> +<p>Clean the segments which are compacted:</p> +<pre><code>CLEAN FILES FOR TABLE carbon_table +</code></pre> +<script> +$(function() { + // Show selected style on nav item + $('.b-nav__docs').addClass('selected'); + + // Display docs subnav items + if (!$('.b-nav__docs').parent().hasClass('nav__item__with__subs--expanded')) { + $('.b-nav__docs').parent().toggleClass('nav__item__with__subs--expanded'); + } +}); +</script> +</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>
http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/dml-operation-on-carbondata.html ---------------------------------------------------------------------- diff --git a/content/dml-operation-on-carbondata.html b/content/dml-operation-on-carbondata.html index b6a5642..655a61c 100644 --- a/content/dml-operation-on-carbondata.html +++ b/content/dml-operation-on-carbondata.html @@ -713,4 +713,4 @@ column1 = 'USA'); </section><!-- End systemblock part --> <script src="js/custom.js"></script> </body> -</html> \ No newline at end of file +</html> http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/documentation.html ---------------------------------------------------------------------- diff --git a/content/documentation.html b/content/documentation.html new file mode 100644 index 0000000..634da94 --- /dev/null +++ b/content/documentation.html @@ -0,0 +1,256 @@ +<!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> + <script defer src="https://use.fontawesome.com/releases/v5.0.8/js/all.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://dist.apache.org/repos/dist/release/carbondata/1.4.1/"; + target="_blank">Apache CarbonData 1.4.1</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.4.0/"; + target="_blank">Apache CarbonData 1.4.0</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.3.1/"; + target="_blank">Apache CarbonData 1.3.1</a></li> + <li> + <a href="https://dist.apache.org/repos/dist/release/carbondata/1.3.0/"; + target="_blank">Apache CarbonData 1.3.0</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Releases"; + target="_blank">Release Archive</a></li> + </ul> + </li> + <li><a href="documentation.html" class="active">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/carbondata/blob/master/docs/How-to-contribute-to-Apache-CarbonData.md"; + target="_blank">Contributing to CarbonData</a></li> + <li> + <a href="https://github.com/apache/carbondata/blob/master/docs/release-guide.md"; + target="_blank">Release Guide</a></li> + <li> + <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/PMC+and+Committers+member+list"; + target="_blank">Project PMC 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"; target="_blank"> + <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" placeholder="Search...." required/> + </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/> + <span style=" position: relative; top: -3px;"> Only search for CarbonData</span> + </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="verticalnavbar"> + <nav class="b-sticky-nav"> + <div class="nav-scroller"> + <div class="nav__inner"> + <a class="b-nav__intro nav__item" href="./introduction.html">introduction</a> + <a class="b-nav__quickstart nav__item" href="./quick-start-guide.html">quick start</a> + <a class="b-nav__uses nav__item" href="./usescases.html">use cases</a> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__docs nav__item nav__sub__anchor" href="./language-manual.html">Language Reference</a> + <a class="nav__item nav__sub__item" href="./ddl-of-carbondata.html">DDL</a> + <a class="nav__item nav__sub__item" href="./dml-of-carbondata.html">DML</a> + <a class="nav__item nav__sub__item" href="./streaming-guide.html">Streaming</a> + <a class="nav__item nav__sub__item" href="./configuration-parameters.html">Configuration</a> + <a class="nav__item nav__sub__item" href="./datamap-developer-guide.html">Datamaps</a> + <a class="nav__item nav__sub__item" href="./supported-data-types-in-carbondata.html">Data Types</a> + </div> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__datamap nav__item nav__sub__anchor" href="./datamap-management.html">DataMaps</a> + <a class="nav__item nav__sub__item" href="./bloomfilter-datamap-guide.html">Bloom Filter</a> + <a class="nav__item nav__sub__item" href="./lucene-datamap-guide.html">Lucene</a> + <a class="nav__item nav__sub__item" href="./preaggregate-datamap-guide.html">Pre-Aggregate</a> + <a class="nav__item nav__sub__item" href="./timeseries-datamap-guide.html">Time Series</a> + </div> + + <a class="b-nav__s3 nav__item" href="./s3-guide.html">S3 Support</a> + <a class="b-nav__api nav__item" href="./sdk-guide.html">API</a> + <a class="b-nav__perf nav__item" href="./performance-tuning.html">Performance Tuning</a> + <a class="b-nav__faq nav__item" href="./faq.html">FAQ</a> + <a class="b-nav__contri nav__item" href="./how-to-contribute-to-apache-carbondata.html">Contribute</a> + <a class="b-nav__security nav__item" href="./security.html">Security</a> + <a class="b-nav__release nav__item" href="./release-guide.html">Release Guide</a> + </div> + </div> + <div class="navindicator"> + <div class="b-nav__intro navindicator__item"></div> + <div class="b-nav__quickstart navindicator__item"></div> + <div class="b-nav__uses navindicator__item"></div> + <div class="b-nav__docs navindicator__item"></div> + <div class="b-nav__datamap navindicator__item"></div> + <div class="b-nav__s3 navindicator__item"></div> + <div class="b-nav__api navindicator__item"></div> + <div class="b-nav__perf navindicator__item"></div> + <div class="b-nav__faq navindicator__item"></div> + <div class="b-nav__contri navindicator__item"></div> + <div class="b-nav__security navindicator__item"></div> + </div> + </nav> + </div> + <div class="mdcontent"> + <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="apache-carbondata-documentation" class="anchor" href="#apache-carbondata-documentation" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Apache CarbonData Documentation</h1> +<p>Apache CarbonData is a new big data file format for faster interactive query using advanced columnar storage, index, compression and encoding techniques to improve computing efficiency, which helps in speeding up queries by an order of magnitude faster over PetaBytes of data.</p> +<h2> +<a id="getting-started" class="anchor" href="#getting-started" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Getting Started</h2> +<p><strong>File Format Concepts:</strong> Start with the basics of understanding the <a href="./file-structure-of-carbondata.html#carbondata-file-structure">CarbonData file format</a> and its storage structure.This will help to understand other parts of the documentation, incuding deployment, programming and usage guides.</p> +<p><strong>Quick Start:</strong> <a href="./quick-start-guide.html#installing-and-configuring-carbondata-to-run-locally-with-spark-shell">Run an example program</a> on your local machine or <a href="https://github.com/apache/carbondata/tree/master/examples/spark2/src/main/scala/org/apache/carbondata/examples"; target=_blank>study some examples</a>.</p> +<p><strong>CarbonData SQL Language Reference:</strong> CarbonData extends the Spark SQL language and adds several <a href="./ddl-of-carbondata.html">DDL</a> and <a href="./dml-of-carbondata.html">DML</a> statements to support operations on it.Refer to the <a href="./language-manual.html">Reference Manual</a> to understand the supported features and functions.</p> +<p><strong>Programming Guides:</strong> You can read our guides about <a href="./sdk-guide.html">APIs supported</a> to learn how to integrate CarbonData with your applications.</p> +<h2> +<a id="deployment" class="anchor" href="#deployment" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Deployment</h2> +<p>CarbonData can be integrated with popular Execution engines like <a href="./quick-start-guide.html#spark">Spark</a> and <a href="./quick-start-guide.html#presto">Presto</a>.Refer to the <a href="./quick-start-guide.html##deployment-modes">Installation and Configuration</a> section to understand all modes of Integrating CarbonData.</p> +<h2> +<a id="contributing-to-carbondata" class="anchor" href="#contributing-to-carbondata" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Contributing to CarbonData</h2> +<p>The Apache CarbonData community welcomes all kinds of contributions from anyone with a passion for +faster data format.Contributing to CarbonData doesn?t just mean writing code. Helping new users on the mailing list, testing releases, and improving documentation are also welcome.Please follow the <a href="./how-to-contribute-to-apache-carbondata.html">Contributing to CarbonData guidelines</a> before proposing a design or code change.</p> +<p><strong>Compiling CarbonData:</strong> This <a href="https://github.com/apache/carbondata/tree/master/build"; target=_blank>guide</a> will help you to compile and generate the jars for test.</p> +<h2> +<a id="external-resources" class="anchor" href="#external-resources" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>External Resources</h2> +<p><strong>Wiki:</strong> You can read the <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/CarbonData+Home"; rel="nofollow">Apache CarbonData wiki</a> page for upcoming release plan, blogs and training materials.</p> +<p><strong>Summit:</strong> Presentations from past summits and conferences can be found <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=66850609"; rel="nofollow">here</a>.</p> +<p><strong>Blogs:</strong> Blogs by external users can be found <a href="https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=67635497"; rel="nofollow">here</a>.</p> +<p><strong>Performance reports:</strong> TPC-H performance reports can be found <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/Performance+-+TPCH+Report+of+CarbonData+%281.2+version%29+and+Parquet+on+Spark+Execution+Engine"; rel="nofollow">here</a>.</p> +<p><strong>Trainings:</strong> Training records on design and code flows can be found <a href="https://cwiki.apache.org/confluence/display/CARBONDATA/CarbonData+Training+Materials"; rel="nofollow">here</a>.</p> +<script> +// Show selected style on nav item +$(function() { $('.b-nav__intro').addClass('selected'); }); +</script> +</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> http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/errorpage.html ---------------------------------------------------------------------- diff --git a/content/errorpage.html b/content/errorpage.html index 090dce5..35cc01a 100644 --- a/content/errorpage.html +++ b/content/errorpage.html @@ -89,4 +89,4 @@ </body> -</html> \ No newline at end of file +</html> http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/faq.html ---------------------------------------------------------------------- diff --git a/content/faq.html b/content/faq.html index cf84d34..52112b7 100644 --- a/content/faq.html +++ b/content/faq.html @@ -22,6 +22,7 @@ <![endif]--> <script src="js/jquery.min.js"></script> <script src="js/bootstrap.min.js"></script> + <script defer src="https://use.fontawesome.com/releases/v5.0.8/js/all.js";></script> </head> @@ -67,7 +68,7 @@ target="_blank">Release Archive</a></li> </ul> </li> - <li><a href="mainpage.html" class="active">Documentation</a></li> + <li><a href="documentation.html" class="active">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> @@ -152,7 +153,57 @@ <section><!-- Dashboard nav --> <div class="container-fluid q"> <div class="col-sm-12 col-md-12 maindashboard"> - <div class="row"> + <div class="verticalnavbar"> + <nav class="b-sticky-nav"> + <div class="nav-scroller"> + <div class="nav__inner"> + <a class="b-nav__intro nav__item" href="./introduction.html">introduction</a> + <a class="b-nav__quickstart nav__item" href="./quick-start-guide.html">quick start</a> + <a class="b-nav__uses nav__item" href="./usescases.html">use cases</a> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__docs nav__item nav__sub__anchor" href="./language-manual.html">Language Reference</a> + <a class="nav__item nav__sub__item" href="./ddl-of-carbondata.html">DDL</a> + <a class="nav__item nav__sub__item" href="./dml-of-carbondata.html">DML</a> + <a class="nav__item nav__sub__item" href="./streaming-guide.html">Streaming</a> + <a class="nav__item nav__sub__item" href="./configuration-parameters.html">Configuration</a> + <a class="nav__item nav__sub__item" href="./datamap-developer-guide.html">Datamaps</a> + <a class="nav__item nav__sub__item" href="./supported-data-types-in-carbondata.html">Data Types</a> + </div> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__datamap nav__item nav__sub__anchor" href="./datamap-management.html">DataMaps</a> + <a class="nav__item nav__sub__item" href="./bloomfilter-datamap-guide.html">Bloom Filter</a> + <a class="nav__item nav__sub__item" href="./lucene-datamap-guide.html">Lucene</a> + <a class="nav__item nav__sub__item" href="./preaggregate-datamap-guide.html">Pre-Aggregate</a> + <a class="nav__item nav__sub__item" href="./timeseries-datamap-guide.html">Time Series</a> + </div> + + <a class="b-nav__s3 nav__item" href="./s3-guide.html">S3 Support</a> + <a class="b-nav__api nav__item" href="./sdk-guide.html">API</a> + <a class="b-nav__perf nav__item" href="./performance-tuning.html">Performance Tuning</a> + <a class="b-nav__faq nav__item" href="./faq.html">FAQ</a> + <a class="b-nav__contri nav__item" href="./how-to-contribute-to-apache-carbondata.html">Contribute</a> + <a class="b-nav__security nav__item" href="./security.html">Security</a> + <a class="b-nav__release nav__item" href="./release-guide.html">Release Guide</a> + </div> + </div> + <div class="navindicator"> + <div class="b-nav__intro navindicator__item"></div> + <div class="b-nav__quickstart navindicator__item"></div> + <div class="b-nav__uses navindicator__item"></div> + <div class="b-nav__docs navindicator__item"></div> + <div class="b-nav__datamap navindicator__item"></div> + <div class="b-nav__s3 navindicator__item"></div> + <div class="b-nav__api navindicator__item"></div> + <div class="b-nav__perf navindicator__item"></div> + <div class="b-nav__faq navindicator__item"></div> + <div class="b-nav__contri navindicator__item"></div> + <div class="b-nav__security navindicator__item"></div> + </div> + </nav> + </div> + <div class="mdcontent"> <section> <div style="padding:10px 15px;"> <div id="viewpage" name="viewpage"> @@ -174,6 +225,22 @@ <li><a href="#Why-all-executors-are-showing-success-in-Spark-UI-even-after-Dataload-command-failed-at-driver-side">Why all executors are showing success in Spark UI even after Dataload command failed at Driver side?</a></li> <li><a href="#Why-different-time-zone-result-for-select-query-output-when-query-SDK-writer-output">Why different time zone result for select query output when query SDK writer output?</a></li> </ul> +<h1> +<a id="troubleshooting" class="anchor" href="#troubleshooting" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>TroubleShooting</h1> +<ul> +<li><a href="#Getting-tablestatus.lock-issues-When-loading-data">Getting tablestatus.lock issues When loading data</a></li> +<li><a href="#failed-to-load-thrift-libraries">Failed to load thrift libraries</a></li> +<li><a href="#failed-to-launch-the-spark-shell">Failed to launch the Spark Shell</a></li> +<li><a href="#failed-to-execute-load-query-on-cluster">Failed to execute load query on cluster</a></li> +<li><a href="#failed-to-execute-insert-query-on-cluster">Failed to execute insert query on cluster</a></li> +<li><a href="#failed-to-connect-to-hiveuser-with-thrift">Failed to connect to hiveuser with thrift</a></li> +<li><a href="#failed-to-read-the-metastore-db-during-table">Failed to read the metastore db during table</a></li> +<li><a href="#failed-to-load-data-on-the-cluster">Failed to load data on the cluster</a></li> +<li><a href="#failed-to-insert-data-on-the-cluster">Failed to insert data on the cluster</a></li> +<li><a href="#failed-to-execute-concurrent-operations-on-table-by-multiple-workers">Failed to execute Concurrent Operations(Load,Insert,Update) on table by multiple workers</a></li> +<li><a href="#failed-to-create-a-table-with-a-single-numeric-column">Failed to create a table with a single numeric column</a></li> +</ul> +<h2></h2> <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> @@ -311,6 +378,195 @@ If wanted to control timezone of data while writing, then set cluster's time-zon <pre><code>cluster timezone is Asia/Shanghai TimeZone.setDefault(TimeZone.getTimeZone("Asia/Shanghai")) </code></pre> +<h2> +<a id="getting-tablestatuslock-issues-when-loading-data" class="anchor" href="#getting-tablestatuslock-issues-when-loading-data" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Getting tablestatus.lock issues When loading data</h2> +<p><strong>Symptom</strong></p> +<pre><code>17/11/11 16:48:13 ERROR LocalFileLock: main hdfs:/localhost:9000/carbon/store/default/hdfstable/tablestatus.lock (No such file or directory) +java.io.FileNotFoundException: hdfs:/localhost:9000/carbon/store/default/hdfstable/tablestatus.lock (No such file or directory) + at java.io.FileOutputStream.open0(Native Method) + at java.io.FileOutputStream.open(FileOutputStream.java:270) + at java.io.FileOutputStream.<init>(FileOutputStream.java:213) + at java.io.FileOutputStream.<init>(FileOutputStream.java:101) +</code></pre> +<p><strong>Possible Cause</strong> +If you use <code><hdfs path></code> as store path when creating carbonsession, may get the errors,because the default is LOCALLOCK.</p> +<p><strong>Procedure</strong> +Before creating carbonsession, sets as below:</p> +<pre><code>import org.apache.carbondata.core.util.CarbonProperties +import org.apache.carbondata.core.constants.CarbonCommonConstants +CarbonProperties.getInstance().addProperty(CarbonCommonConstants.LOCK_TYPE, "HDFSLOCK") +</code></pre> +<h2> +<a id="failed-to-load-thrift-libraries" class="anchor" href="#failed-to-load-thrift-libraries" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to load thrift libraries</h2> +<p><strong>Symptom</strong></p> +<p>Thrift throws following exception :</p> +<pre><code>thrift: error while loading shared libraries: +libthriftc.so.0: cannot open shared object file: No such file or directory +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The complete path to the directory containing the libraries is not configured correctly.</p> +<p><strong>Procedure</strong></p> +<p>Follow the Apache thrift docs at <a href="https://thrift.apache.org/docs/install"; target=_blank rel="nofollow">https://thrift.apache.org/docs/install</a> to install thrift correctly.</p> +<h2> +<a id="failed-to-launch-the-spark-shell" class="anchor" href="#failed-to-launch-the-spark-shell" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to launch the Spark Shell</h2> +<p><strong>Symptom</strong></p> +<p>The shell prompts the following error :</p> +<pre><code>org.apache.spark.sql.CarbonContext$$anon$$apache$spark$sql$catalyst$analysis +$OverrideCatalog$_setter_$org$apache$spark$sql$catalyst$analysis +$OverrideCatalog$$overrides_$e +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The Spark Version and the selected Spark Profile do not match.</p> +<p><strong>Procedure</strong></p> +<ol> +<li> +<p>Ensure your spark version and selected profile for spark are correct.</p> +</li> +<li> +<p>Use the following command :</p> +</li> +</ol> +<pre><code>"mvn -Pspark-2.1 -Dspark.version {yourSparkVersion} clean package" +</code></pre> +<p>Note : Refrain from using "mvn clean package" without specifying the profile.</p> +<h2> +<a id="failed-to-execute-load-query-on-cluster" class="anchor" href="#failed-to-execute-load-query-on-cluster" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to execute load query on cluster</h2> +<p><strong>Symptom</strong></p> +<p>Load query failed with the following exception:</p> +<pre><code>Dictionary file is locked for updation. +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The carbon.properties file is not identical in all the nodes of the cluster.</p> +<p><strong>Procedure</strong></p> +<p>Follow the steps to ensure the carbon.properties file is consistent across all the nodes:</p> +<ol> +<li> +<p>Copy the carbon.properties file from the master node to all the other nodes in the cluster. +For example, you can use ssh to copy this file to all the nodes.</p> +</li> +<li> +<p>For the changes to take effect, restart the Spark cluster.</p> +</li> +</ol> +<h2> +<a id="failed-to-execute-insert-query-on-cluster" class="anchor" href="#failed-to-execute-insert-query-on-cluster" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to execute insert query on cluster</h2> +<p><strong>Symptom</strong></p> +<p>Load query failed with the following exception:</p> +<pre><code>Dictionary file is locked for updation. +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The carbon.properties file is not identical in all the nodes of the cluster.</p> +<p><strong>Procedure</strong></p> +<p>Follow the steps to ensure the carbon.properties file is consistent across all the nodes:</p> +<ol> +<li> +<p>Copy the carbon.properties file from the master node to all the other nodes in the cluster. +For example, you can use scp to copy this file to all the nodes.</p> +</li> +<li> +<p>For the changes to take effect, restart the Spark cluster.</p> +</li> +</ol> +<h2> +<a id="failed-to-connect-to-hiveuser-with-thrift" class="anchor" href="#failed-to-connect-to-hiveuser-with-thrift" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to connect to hiveuser with thrift</h2> +<p><strong>Symptom</strong></p> +<p>We get the following exception :</p> +<pre><code>Cannot connect to hiveuser. +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The external process does not have permission to access.</p> +<p><strong>Procedure</strong></p> +<p>Ensure that the Hiveuser in mysql must allow its access to the external processes.</p> +<h2> +<a id="failed-to-read-the-metastore-db-during-table-creation" class="anchor" href="#failed-to-read-the-metastore-db-during-table-creation" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to read the metastore db during table creation</h2> +<p><strong>Symptom</strong></p> +<p>We get the following exception on trying to connect :</p> +<pre><code>Cannot read the metastore db +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The metastore db is dysfunctional.</p> +<p><strong>Procedure</strong></p> +<p>Remove the metastore db from the carbon.metastore in the Spark Directory.</p> +<h2> +<a id="failed-to-load-data-on-the-cluster" class="anchor" href="#failed-to-load-data-on-the-cluster" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to load data on the cluster</h2> +<p><strong>Symptom</strong></p> +<p>Data loading fails with the following exception :</p> +<pre><code>Data Load failure exception +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The following issue can cause the failure :</p> +<ol> +<li> +<p>The core-site.xml, hive-site.xml, yarn-site and carbon.properties are not consistent across all nodes of the cluster.</p> +</li> +<li> +<p>Path to hdfs ddl is not configured correctly in the carbon.properties.</p> +</li> +</ol> +<p><strong>Procedure</strong></p> +<p>Follow the steps to ensure the following configuration files are consistent across all the nodes:</p> +<ol> +<li> +<p>Copy the core-site.xml, hive-site.xml, yarn-site,carbon.properties files from the master node to all the other nodes in the cluster. +For example, you can use scp to copy this file to all the nodes.</p> +<p>Note : Set the path to hdfs ddl in carbon.properties in the master node.</p> +</li> +<li> +<p>For the changes to take effect, restart the Spark cluster.</p> +</li> +</ol> +<h2> +<a id="failed-to-insert-data-on-the-cluster" class="anchor" href="#failed-to-insert-data-on-the-cluster" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to insert data on the cluster</h2> +<p><strong>Symptom</strong></p> +<p>Insertion fails with the following exception :</p> +<pre><code>Data Load failure exception +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>The following issue can cause the failure :</p> +<ol> +<li> +<p>The core-site.xml, hive-site.xml, yarn-site and carbon.properties are not consistent across all nodes of the cluster.</p> +</li> +<li> +<p>Path to hdfs ddl is not configured correctly in the carbon.properties.</p> +</li> +</ol> +<p><strong>Procedure</strong></p> +<p>Follow the steps to ensure the following configuration files are consistent across all the nodes:</p> +<ol> +<li> +<p>Copy the core-site.xml, hive-site.xml, yarn-site,carbon.properties files from the master node to all the other nodes in the cluster. +For example, you can use scp to copy this file to all the nodes.</p> +<p>Note : Set the path to hdfs ddl in carbon.properties in the master node.</p> +</li> +<li> +<p>For the changes to take effect, restart the Spark cluster.</p> +</li> +</ol> +<h2> +<a id="failed-to-execute-concurrent-operations-on-table-by-multiple-workers" class="anchor" href="#failed-to-execute-concurrent-operations-on-table-by-multiple-workers" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to execute Concurrent Operations on table by multiple workers</h2> +<p><strong>Symptom</strong></p> +<p>Execution fails with the following exception :</p> +<pre><code>Table is locked for updation. +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>Concurrency not supported.</p> +<p><strong>Procedure</strong></p> +<p>Worker must wait for the query execution to complete and the table to release the lock for another query execution to succeed.</p> +<h2> +<a id="failed-to-create-a-table-with-a-single-numeric-column" class="anchor" href="#failed-to-create-a-table-with-a-single-numeric-column" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Failed to create a table with a single numeric column</h2> +<p><strong>Symptom</strong></p> +<p>Execution fails with the following exception :</p> +<pre><code>Table creation fails. +</code></pre> +<p><strong>Possible Cause</strong></p> +<p>Behaviour not supported.</p> +<p><strong>Procedure</strong></p> +<p>A single column that can be considered as dimension is mandatory for table creation.</p> +<script> +// Show selected style on nav item +$(function() { $('.b-nav__faq').addClass('selected'); }); +</script> </div> </div> </div> @@ -326,4 +582,4 @@ TimeZone.setDefault(TimeZone.getTimeZone("Asia/Shanghai")) </section><!-- End systemblock part --> <script src="js/custom.js"></script> </body> -</html> \ No newline at end of file +</html> http://git-wip-us.apache.org/repos/asf/carbondata-site/blob/44eed099/content/file-structure-of-carbondata.html ---------------------------------------------------------------------- diff --git a/content/file-structure-of-carbondata.html b/content/file-structure-of-carbondata.html index edebccf..b96d622 100644 --- a/content/file-structure-of-carbondata.html +++ b/content/file-structure-of-carbondata.html @@ -22,6 +22,7 @@ <![endif]--> <script src="js/jquery.min.js"></script> <script src="js/bootstrap.min.js"></script> + <script defer src="https://use.fontawesome.com/releases/v5.0.8/js/all.js";></script> </head> @@ -67,7 +68,7 @@ target="_blank">Release Archive</a></li> </ul> </li> - <li><a href="mainpage.html" class="active">Documentation</a></li> + <li><a href="documentation.html" class="active">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> @@ -152,7 +153,57 @@ <section><!-- Dashboard nav --> <div class="container-fluid q"> <div class="col-sm-12 col-md-12 maindashboard"> - <div class="row"> + <div class="verticalnavbar"> + <nav class="b-sticky-nav"> + <div class="nav-scroller"> + <div class="nav__inner"> + <a class="b-nav__intro nav__item" href="./introduction.html">introduction</a> + <a class="b-nav__quickstart nav__item" href="./quick-start-guide.html">quick start</a> + <a class="b-nav__uses nav__item" href="./usescases.html">use cases</a> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__docs nav__item nav__sub__anchor" href="./language-manual.html">Language Reference</a> + <a class="nav__item nav__sub__item" href="./ddl-of-carbondata.html">DDL</a> + <a class="nav__item nav__sub__item" href="./dml-of-carbondata.html">DML</a> + <a class="nav__item nav__sub__item" href="./streaming-guide.html">Streaming</a> + <a class="nav__item nav__sub__item" href="./configuration-parameters.html">Configuration</a> + <a class="nav__item nav__sub__item" href="./datamap-developer-guide.html">Datamaps</a> + <a class="nav__item nav__sub__item" href="./supported-data-types-in-carbondata.html">Data Types</a> + </div> + + <div class="nav__item nav__item__with__subs"> + <a class="b-nav__datamap nav__item nav__sub__anchor" href="./datamap-management.html">DataMaps</a> + <a class="nav__item nav__sub__item" href="./bloomfilter-datamap-guide.html">Bloom Filter</a> + <a class="nav__item nav__sub__item" href="./lucene-datamap-guide.html">Lucene</a> + <a class="nav__item nav__sub__item" href="./preaggregate-datamap-guide.html">Pre-Aggregate</a> + <a class="nav__item nav__sub__item" href="./timeseries-datamap-guide.html">Time Series</a> + </div> + + <a class="b-nav__s3 nav__item" href="./s3-guide.html">S3 Support</a> + <a class="b-nav__api nav__item" href="./sdk-guide.html">API</a> + <a class="b-nav__perf nav__item" href="./performance-tuning.html">Performance Tuning</a> + <a class="b-nav__faq nav__item" href="./faq.html">FAQ</a> + <a class="b-nav__contri nav__item" href="./how-to-contribute-to-apache-carbondata.html">Contribute</a> + <a class="b-nav__security nav__item" href="./security.html">Security</a> + <a class="b-nav__release nav__item" href="./release-guide.html">Release Guide</a> + </div> + </div> + <div class="navindicator"> + <div class="b-nav__intro navindicator__item"></div> + <div class="b-nav__quickstart navindicator__item"></div> + <div class="b-nav__uses navindicator__item"></div> + <div class="b-nav__docs navindicator__item"></div> + <div class="b-nav__datamap navindicator__item"></div> + <div class="b-nav__s3 navindicator__item"></div> + <div class="b-nav__api navindicator__item"></div> + <div class="b-nav__perf navindicator__item"></div> + <div class="b-nav__faq navindicator__item"></div> + <div class="b-nav__contri navindicator__item"></div> + <div class="b-nav__security navindicator__item"></div> + </div> + </nav> + </div> + <div class="mdcontent"> <section> <div style="padding:10px 15px;"> <div id="viewpage" name="viewpage"> @@ -168,7 +219,7 @@ <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/carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"; alt="CarbonData File Structure" style="max-width:100%;"></a></p> +<p><a href="../docs/images/carbon_data_file_structure_new.png?raw=true" target="_blank" rel="noopener noreferrer"><img src="https://github.com/apache/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> @@ -176,7 +227,7 @@ <li>Column Page Group : Data of one column and it is further divided into 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/carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"; alt="CarbonData File Format" style="max-width:100%;"></a></p> +<p><a href="../docs/images/carbon_data_format_new.png?raw=true" target="_blank" rel="noopener noreferrer"><img src="https://github.com/apache/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> @@ -184,6 +235,17 @@ <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> +<script> +$(function() { + // Show selected style on nav item + $('.b-nav__docs').addClass('selected'); + + // Display docs subnav items + if (!$('.b-nav__docs').parent().hasClass('nav__item__with__subs--expanded')) { + $('.b-nav__docs').parent().toggleClass('nav__item__with__subs--expanded'); + } +}); +</script> </div> </div> </div> @@ -199,4 +261,4 @@ </section><!-- End systemblock part --> <script src="js/custom.js"></script> </body> -</html> \ No newline at end of file +</html>
![https://github.com/apache/carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"](https://github.com/apache/carbondata/blob/master/docs/images/carbon_data_file_structure_new.png?raw=true"){kind=link}
![https://github.com/apache/carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"](https://github.com/apache/carbondata/blob/master/docs/images/carbon_data_format_new.png?raw=true"){kind=link}