| <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> |
| <!-- NewPage --> |
| <html lang="en"> |
| <head> |
| <!-- Generated by javadoc --> |
| <title>ChangelogIterator</title> |
| <link rel="stylesheet" type="text/css" href="../../../../stylesheet.css" title="Style"> |
| <script type="text/javascript" src="../../../../script.js"></script> |
| </head> |
| <body> |
| <script type="text/javascript"><!-- |
| try { |
| if (location.href.indexOf('is-external=true') == -1) { |
| parent.document.title="ChangelogIterator"; |
| } |
| } |
| catch(err) { |
| } |
| //--> |
| var methods = {"i0":9,"i1":10,"i2":10}; |
| var tabs = {65535:["t0","All Methods"],1:["t1","Static Methods"],2:["t2","Instance Methods"],8:["t4","Concrete Methods"]}; |
| var altColor = "altColor"; |
| var rowColor = "rowColor"; |
| var tableTab = "tableTab"; |
| var activeTableTab = "activeTableTab"; |
| </script> |
| <noscript> |
| <div>JavaScript is disabled on your browser.</div> |
| </noscript> |
| <!-- ========= START OF TOP NAVBAR ======= --> |
| <div class="topNav"><a name="navbar.top"> |
| <!-- --> |
| </a> |
| <div class="skipNav"><a href="#skip.navbar.top" title="Skip navigation links">Skip navigation links</a></div> |
| <a name="navbar.top.firstrow"> |
| <!-- --> |
| </a> |
| <ul class="navList" title="Navigation"> |
| <li><a href="../../../../overview-summary.html">Overview</a></li> |
| <li><a href="package-summary.html">Package</a></li> |
| <li class="navBarCell1Rev">Class</li> |
| <li><a href="package-tree.html">Tree</a></li> |
| <li><a href="../../../../deprecated-list.html">Deprecated</a></li> |
| <li><a href="../../../../index-all.html">Index</a></li> |
| <li><a href="../../../../help-doc.html">Help</a></li> |
| </ul> |
| </div> |
| <div class="subNav"> |
| <ul class="navList"> |
| <li>Prev Class</li> |
| <li><a href="../../../../org/apache/iceberg/spark/CommitMetadata.html" title="class in org.apache.iceberg.spark"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../index.html?org/apache/iceberg/spark/ChangelogIterator.html" target="_top">Frames</a></li> |
| <li><a href="ChangelogIterator.html" target="_top">No Frames</a></li> |
| </ul> |
| <ul class="navList" id="allclasses_navbar_top"> |
| <li><a href="../../../../allclasses-noframe.html">All Classes</a></li> |
| </ul> |
| <div> |
| <script type="text/javascript"><!-- |
| allClassesLink = document.getElementById("allclasses_navbar_top"); |
| if(window==top) { |
| allClassesLink.style.display = "block"; |
| } |
| else { |
| allClassesLink.style.display = "none"; |
| } |
| //--> |
| </script> |
| </div> |
| <div> |
| <ul class="subNavList"> |
| <li>Summary: </li> |
| <li>Nested | </li> |
| <li>Field | </li> |
| <li>Constr | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li>Field | </li> |
| <li>Constr | </li> |
| <li><a href="#method.detail">Method</a></li> |
| </ul> |
| </div> |
| <a name="skip.navbar.top"> |
| <!-- --> |
| </a></div> |
| <!-- ========= END OF TOP NAVBAR ========= --> |
| <!-- ======== START OF CLASS DATA ======== --> |
| <div class="header"> |
| <div class="subTitle">org.apache.iceberg.spark</div> |
| <h2 title="Class ChangelogIterator" class="title">Class ChangelogIterator</h2> |
| </div> |
| <div class="contentContainer"> |
| <ul class="inheritance"> |
| <li>java.lang.Object</li> |
| <li> |
| <ul class="inheritance"> |
| <li>org.apache.iceberg.spark.ChangelogIterator</li> |
| </ul> |
| </li> |
| </ul> |
| <div class="description"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <dl> |
| <dt>All Implemented Interfaces:</dt> |
| <dd>java.util.Iterator<org.apache.spark.sql.Row></dd> |
| </dl> |
| <hr> |
| <br> |
| <pre>public class <span class="typeNameLabel">ChangelogIterator</span> |
| extends java.lang.Object |
| implements java.util.Iterator<org.apache.spark.sql.Row></pre> |
| <div class="block">An iterator that transforms rows from changelog tables within a single Spark task. It assumes |
| that rows are sorted by identifier columns and change type. |
| |
| <p>It removes the carry-over rows. Carry-over rows are the result of a removal and insertion of |
| the same row within an operation because of the copy-on-write mechanism. For example, given a |
| file which contains row1 (id=1, data='a') and row2 (id=2, data='b'). A copy-on-write delete of |
| row2 would require erasing this file and preserving row1 in a new file. The change-log table |
| would report this as (id=1, data='a', op='DELETE') and (id=1, data='a', op='INSERT'), despite it |
| not being an actual change to the table. The iterator finds the carry-over rows and removes them |
| from the result. |
| |
| <p>This iterator also finds delete/insert rows which represent an update, and converts them into |
| update records. For example, these two rows |
| |
| <ul> |
| <li>(id=1, data='a', op='DELETE') |
| <li>(id=1, data='b', op='INSERT') |
| </ul> |
| |
| <p>will be marked as update-rows: |
| |
| <ul> |
| <li>(id=1, data='a', op='UPDATE_BEFORE') |
| <li>(id=1, data='b', op='UPDATE_AFTER') |
| </ul></div> |
| </li> |
| </ul> |
| </div> |
| <div class="summary"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <!-- ========== METHOD SUMMARY =========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.summary"> |
| <!-- --> |
| </a> |
| <h3>Method Summary</h3> |
| <table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation"> |
| <caption><span id="t0" class="activeTableTab"><span>All Methods</span><span class="tabEnd"> </span></span><span id="t1" class="tableTab"><span><a href="javascript:show(1);">Static Methods</a></span><span class="tabEnd"> </span></span><span id="t2" class="tableTab"><span><a href="javascript:show(2);">Instance Methods</a></span><span class="tabEnd"> </span></span><span id="t4" class="tableTab"><span><a href="javascript:show(8);">Concrete Methods</a></span><span class="tabEnd"> </span></span></caption> |
| <tr> |
| <th class="colFirst" scope="col">Modifier and Type</th> |
| <th class="colLast" scope="col">Method and Description</th> |
| </tr> |
| <tr id="i0" class="altColor"> |
| <td class="colFirst"><code>static java.util.Iterator<org.apache.spark.sql.Row></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/iceberg/spark/ChangelogIterator.html#create-java.util.Iterator-org.apache.spark.sql.types.StructType-java.lang.String:A-">create</a></span>(java.util.Iterator<org.apache.spark.sql.Row> rowIterator, |
| org.apache.spark.sql.types.StructType rowType, |
| java.lang.String[] identifierFields)</code> |
| <div class="block">Creates an iterator for records of a changelog table.</div> |
| </td> |
| </tr> |
| <tr id="i1" class="rowColor"> |
| <td class="colFirst"><code>boolean</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/iceberg/spark/ChangelogIterator.html#hasNext--">hasNext</a></span>()</code> </td> |
| </tr> |
| <tr id="i2" class="altColor"> |
| <td class="colFirst"><code>org.apache.spark.sql.Row</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/iceberg/spark/ChangelogIterator.html#next--">next</a></span>()</code> </td> |
| </tr> |
| </table> |
| <ul class="blockList"> |
| <li class="blockList"><a name="methods.inherited.from.class.java.lang.Object"> |
| <!-- --> |
| </a> |
| <h3>Methods inherited from class java.lang.Object</h3> |
| <code>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</code></li> |
| </ul> |
| <ul class="blockList"> |
| <li class="blockList"><a name="methods.inherited.from.class.java.util.Iterator"> |
| <!-- --> |
| </a> |
| <h3>Methods inherited from interface java.util.Iterator</h3> |
| <code>forEachRemaining, remove</code></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| <div class="details"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <!-- ============ METHOD DETAIL ========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.detail"> |
| <!-- --> |
| </a> |
| <h3>Method Detail</h3> |
| <a name="create-java.util.Iterator-org.apache.spark.sql.types.StructType-java.lang.String:A-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>create</h4> |
| <pre>public static java.util.Iterator<org.apache.spark.sql.Row> create(java.util.Iterator<org.apache.spark.sql.Row> rowIterator, |
| org.apache.spark.sql.types.StructType rowType, |
| java.lang.String[] identifierFields)</pre> |
| <div class="block">Creates an iterator for records of a changelog table.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>rowIterator</code> - the iterator of rows from a changelog table</dd> |
| <dd><code>rowType</code> - the schema of the rows</dd> |
| <dd><code>identifierFields</code> - the names of the identifier columns, which determine if rows are the |
| same</dd> |
| <dt><span class="returnLabel">Returns:</span></dt> |
| <dd>a new <a href="../../../../org/apache/iceberg/spark/ChangelogIterator.html" title="class in org.apache.iceberg.spark"><code>ChangelogIterator</code></a> instance concatenated with the null-removal iterator</dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="hasNext--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>hasNext</h4> |
| <pre>public boolean hasNext()</pre> |
| <dl> |
| <dt><span class="overrideSpecifyLabel">Specified by:</span></dt> |
| <dd><code>hasNext</code> in interface <code>java.util.Iterator<org.apache.spark.sql.Row></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="next--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>next</h4> |
| <pre>public org.apache.spark.sql.Row next()</pre> |
| <dl> |
| <dt><span class="overrideSpecifyLabel">Specified by:</span></dt> |
| <dd><code>next</code> in interface <code>java.util.Iterator<org.apache.spark.sql.Row></code></dd> |
| </dl> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| </div> |
| <!-- ========= END OF CLASS DATA ========= --> |
| <!-- ======= START OF BOTTOM NAVBAR ====== --> |
| <div class="bottomNav"><a name="navbar.bottom"> |
| <!-- --> |
| </a> |
| <div class="skipNav"><a href="#skip.navbar.bottom" title="Skip navigation links">Skip navigation links</a></div> |
| <a name="navbar.bottom.firstrow"> |
| <!-- --> |
| </a> |
| <ul class="navList" title="Navigation"> |
| <li><a href="../../../../overview-summary.html">Overview</a></li> |
| <li><a href="package-summary.html">Package</a></li> |
| <li class="navBarCell1Rev">Class</li> |
| <li><a href="package-tree.html">Tree</a></li> |
| <li><a href="../../../../deprecated-list.html">Deprecated</a></li> |
| <li><a href="../../../../index-all.html">Index</a></li> |
| <li><a href="../../../../help-doc.html">Help</a></li> |
| </ul> |
| </div> |
| <div class="subNav"> |
| <ul class="navList"> |
| <li>Prev Class</li> |
| <li><a href="../../../../org/apache/iceberg/spark/CommitMetadata.html" title="class in org.apache.iceberg.spark"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../index.html?org/apache/iceberg/spark/ChangelogIterator.html" target="_top">Frames</a></li> |
| <li><a href="ChangelogIterator.html" target="_top">No Frames</a></li> |
| </ul> |
| <ul class="navList" id="allclasses_navbar_bottom"> |
| <li><a href="../../../../allclasses-noframe.html">All Classes</a></li> |
| </ul> |
| <div> |
| <script type="text/javascript"><!-- |
| allClassesLink = document.getElementById("allclasses_navbar_bottom"); |
| if(window==top) { |
| allClassesLink.style.display = "block"; |
| } |
| else { |
| allClassesLink.style.display = "none"; |
| } |
| //--> |
| </script> |
| </div> |
| <div> |
| <ul class="subNavList"> |
| <li>Summary: </li> |
| <li>Nested | </li> |
| <li>Field | </li> |
| <li>Constr | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li>Field | </li> |
| <li>Constr | </li> |
| <li><a href="#method.detail">Method</a></li> |
| </ul> |
| </div> |
| <a name="skip.navbar.bottom"> |
| <!-- --> |
| </a></div> |
| <!-- ======== END OF BOTTOM NAVBAR ======= --> |
| </body> |
| </html> |