| <!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>TextRowCountEstimator (Apache Beam 2.38.0-SNAPSHOT)</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="TextRowCountEstimator (Apache Beam 2.38.0-SNAPSHOT)"; |
| } |
| } |
| catch(err) { |
| } |
| //--> |
| var methods = {"i0":9,"i1":10,"i2":6,"i3":6,"i4":6,"i5":6,"i6":6,"i7":6,"i8":6}; |
| var tabs = {65535:["t0","All Methods"],1:["t1","Static Methods"],2:["t2","Instance Methods"],4:["t3","Abstract 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><a href="../../../../../org/apache/beam/sdk/io/TextIO.Write.html" title="class in org.apache.beam.sdk.io"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.Builder.html" title="class in org.apache.beam.sdk.io"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../../index.html?org/apache/beam/sdk/io/TextRowCountEstimator.html" target="_top">Frames</a></li> |
| <li><a href="TextRowCountEstimator.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><a href="#nested.class.summary">Nested</a> | </li> |
| <li>Field | </li> |
| <li><a href="#constructor.summary">Constr</a> | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li>Field | </li> |
| <li><a href="#constructor.detail">Constr</a> | </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.beam.sdk.io</div> |
| <h2 title="Class TextRowCountEstimator" class="title">Class TextRowCountEstimator</h2> |
| </div> |
| <div class="contentContainer"> |
| <ul class="inheritance"> |
| <li>java.lang.Object</li> |
| <li> |
| <ul class="inheritance"> |
| <li>org.apache.beam.sdk.io.TextRowCountEstimator</li> |
| </ul> |
| </li> |
| </ul> |
| <div class="description"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <hr> |
| <br> |
| <pre>public abstract class <span class="typeNameLabel">TextRowCountEstimator</span> |
| extends java.lang.Object</pre> |
| <div class="block">This returns a row count estimation for files associated with a file pattern.</div> |
| </li> |
| </ul> |
| </div> |
| <div class="summary"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <!-- ======== NESTED CLASS SUMMARY ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="nested.class.summary"> |
| <!-- --> |
| </a> |
| <h3>Nested Class Summary</h3> |
| <table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Nested Class Summary table, listing nested classes, and an explanation"> |
| <caption><span>Nested Classes</span><span class="tabEnd"> </span></caption> |
| <tr> |
| <th class="colFirst" scope="col">Modifier and Type</th> |
| <th class="colLast" scope="col">Class and Description</th> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.Builder.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.Builder</a></span></code> |
| <div class="block">Builder for <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html" title="class in org.apache.beam.sdk.io"><code>TextRowCountEstimator</code></a>.</div> |
| </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.LimitNumberOfFiles.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.LimitNumberOfFiles</a></span></code> |
| <div class="block">This strategy stops sampling if we sample enough number of bytes.</div> |
| </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.LimitNumberOfTotalBytes.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.LimitNumberOfTotalBytes</a></span></code> |
| <div class="block">This strategy stops sampling when total number of sampled bytes are more than some threshold.</div> |
| </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.NoEstimationException.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.NoEstimationException</a></span></code> |
| <div class="block">An exception that will be thrown if the estimator cannot get an estimation of the number of |
| lines.</div> |
| </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.SampleAllFiles.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.SampleAllFiles</a></span></code> |
| <div class="block">This strategy samples all the files.</div> |
| </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static interface </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.SamplingStrategy.html" title="interface in org.apache.beam.sdk.io">TextRowCountEstimator.SamplingStrategy</a></span></code> |
| <div class="block">Sampling Strategy shows us when should we stop reading further files.</div> |
| </td> |
| </tr> |
| </table> |
| </li> |
| </ul> |
| <!-- ======== CONSTRUCTOR SUMMARY ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="constructor.summary"> |
| <!-- --> |
| </a> |
| <h3>Constructor Summary</h3> |
| <table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Constructor Summary table, listing constructors, and an explanation"> |
| <caption><span>Constructors</span><span class="tabEnd"> </span></caption> |
| <tr> |
| <th class="colOne" scope="col">Constructor and Description</th> |
| </tr> |
| <tr class="altColor"> |
| <td class="colOne"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#TextRowCountEstimator--">TextRowCountEstimator</a></span>()</code> </td> |
| </tr> |
| </table> |
| </li> |
| </ul> |
| <!-- ========== 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="t3" class="tableTab"><span><a href="javascript:show(4);">Abstract 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 <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.Builder.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.Builder</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#builder--">builder</a></span>()</code> </td> |
| </tr> |
| <tr id="i1" class="rowColor"> |
| <td class="colFirst"><code>java.lang.Double</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#estimateRowCount-org.apache.beam.sdk.options.PipelineOptions-">estimateRowCount</a></span>(<a href="../../../../../org/apache/beam/sdk/options/PipelineOptions.html" title="interface in org.apache.beam.sdk.options">PipelineOptions</a> pipelineOptions)</code> |
| <div class="block">Estimates the number of non empty rows.</div> |
| </td> |
| </tr> |
| <tr id="i2" class="altColor"> |
| <td class="colFirst"><code>abstract <a href="../../../../../org/apache/beam/sdk/io/Compression.html" title="enum in org.apache.beam.sdk.io">Compression</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getCompression--">getCompression</a></span>()</code> </td> |
| </tr> |
| <tr id="i3" class="rowColor"> |
| <td class="colFirst"><code>abstract byte[]</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getDelimiters--">getDelimiters</a></span>()</code> </td> |
| </tr> |
| <tr id="i4" class="altColor"> |
| <td class="colFirst"><code>abstract <a href="../../../../../org/apache/beam/sdk/io/FileIO.ReadMatches.DirectoryTreatment.html" title="enum in org.apache.beam.sdk.io">FileIO.ReadMatches.DirectoryTreatment</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getDirectoryTreatment--">getDirectoryTreatment</a></span>()</code> </td> |
| </tr> |
| <tr id="i5" class="rowColor"> |
| <td class="colFirst"><code>abstract <a href="../../../../../org/apache/beam/sdk/io/fs/EmptyMatchTreatment.html" title="enum in org.apache.beam.sdk.io.fs">EmptyMatchTreatment</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getEmptyMatchTreatment--">getEmptyMatchTreatment</a></span>()</code> </td> |
| </tr> |
| <tr id="i6" class="altColor"> |
| <td class="colFirst"><code>abstract java.lang.String</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getFilePattern--">getFilePattern</a></span>()</code> </td> |
| </tr> |
| <tr id="i7" class="rowColor"> |
| <td class="colFirst"><code>abstract long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getNumSampledBytesPerFile--">getNumSampledBytesPerFile</a></span>()</code> </td> |
| </tr> |
| <tr id="i8" class="altColor"> |
| <td class="colFirst"><code>abstract <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.SamplingStrategy.html" title="interface in org.apache.beam.sdk.io">TextRowCountEstimator.SamplingStrategy</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.html#getSamplingStrategy--">getSamplingStrategy</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> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| <div class="details"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <!-- ========= CONSTRUCTOR DETAIL ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="constructor.detail"> |
| <!-- --> |
| </a> |
| <h3>Constructor Detail</h3> |
| <a name="TextRowCountEstimator--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>TextRowCountEstimator</h4> |
| <pre>public TextRowCountEstimator()</pre> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ============ METHOD DETAIL ========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.detail"> |
| <!-- --> |
| </a> |
| <h3>Method Detail</h3> |
| <a name="getNumSampledBytesPerFile--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getNumSampledBytesPerFile</h4> |
| <pre>public abstract long getNumSampledBytesPerFile()</pre> |
| </li> |
| </ul> |
| <a name="getDelimiters--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getDelimiters</h4> |
| <pre>public abstract byte[] getDelimiters()</pre> |
| </li> |
| </ul> |
| <a name="getFilePattern--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getFilePattern</h4> |
| <pre>public abstract java.lang.String getFilePattern()</pre> |
| </li> |
| </ul> |
| <a name="getCompression--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getCompression</h4> |
| <pre>public abstract <a href="../../../../../org/apache/beam/sdk/io/Compression.html" title="enum in org.apache.beam.sdk.io">Compression</a> getCompression()</pre> |
| </li> |
| </ul> |
| <a name="getSamplingStrategy--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getSamplingStrategy</h4> |
| <pre>public abstract <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.SamplingStrategy.html" title="interface in org.apache.beam.sdk.io">TextRowCountEstimator.SamplingStrategy</a> getSamplingStrategy()</pre> |
| </li> |
| </ul> |
| <a name="getEmptyMatchTreatment--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getEmptyMatchTreatment</h4> |
| <pre>public abstract <a href="../../../../../org/apache/beam/sdk/io/fs/EmptyMatchTreatment.html" title="enum in org.apache.beam.sdk.io.fs">EmptyMatchTreatment</a> getEmptyMatchTreatment()</pre> |
| </li> |
| </ul> |
| <a name="getDirectoryTreatment--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getDirectoryTreatment</h4> |
| <pre>public abstract <a href="../../../../../org/apache/beam/sdk/io/FileIO.ReadMatches.DirectoryTreatment.html" title="enum in org.apache.beam.sdk.io">FileIO.ReadMatches.DirectoryTreatment</a> getDirectoryTreatment()</pre> |
| </li> |
| </ul> |
| <a name="builder--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>builder</h4> |
| <pre>public static <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.Builder.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.Builder</a> builder()</pre> |
| </li> |
| </ul> |
| <a name="estimateRowCount-org.apache.beam.sdk.options.PipelineOptions-"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>estimateRowCount</h4> |
| <pre>public java.lang.Double estimateRowCount(<a href="../../../../../org/apache/beam/sdk/options/PipelineOptions.html" title="interface in org.apache.beam.sdk.options">PipelineOptions</a> pipelineOptions) |
| throws java.io.IOException, |
| <a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.NoEstimationException.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.NoEstimationException</a></pre> |
| <div class="block">Estimates the number of non empty rows. It samples NumSampledBytesPerFile bytes from every file |
| until the condition in sampling strategy is met. Then it takes the average line size of the |
| rows and divides the total file sizes by that number. If all the sampled rows are empty, and it |
| has not sampled all the lines (due to sampling strategy) it throws Exception.</div> |
| <dl> |
| <dt><span class="returnLabel">Returns:</span></dt> |
| <dd>Number of estimated rows.</dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.NoEstimationException.html" title="class in org.apache.beam.sdk.io">TextRowCountEstimator.NoEstimationException</a></code> - if all the sampled |
| lines are empty and we have not read all the lines in the matched files.</dd> |
| <dd><code>java.io.IOException</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><a href="../../../../../org/apache/beam/sdk/io/TextIO.Write.html" title="class in org.apache.beam.sdk.io"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../../org/apache/beam/sdk/io/TextRowCountEstimator.Builder.html" title="class in org.apache.beam.sdk.io"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../../index.html?org/apache/beam/sdk/io/TextRowCountEstimator.html" target="_top">Frames</a></li> |
| <li><a href="TextRowCountEstimator.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><a href="#nested.class.summary">Nested</a> | </li> |
| <li>Field | </li> |
| <li><a href="#constructor.summary">Constr</a> | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li>Field | </li> |
| <li><a href="#constructor.detail">Constr</a> | </li> |
| <li><a href="#method.detail">Method</a></li> |
| </ul> |
| </div> |
| <a name="skip.navbar.bottom"> |
| <!-- --> |
| </a></div> |
| <!-- ======== END OF BOTTOM NAVBAR ======= --> |
| </body> |
| </html> |
