| <!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 (1.8.0_181-google-v7) on Mon Jan 27 16:42:32 PST 2020 --> |
| <title>BoundedSource.BoundedReader (Apache Beam 2.20.0-SNAPSHOT)</title> |
| <meta name="date" content="2020-01-27"> |
| <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="BoundedSource.BoundedReader (Apache Beam 2.20.0-SNAPSHOT)"; |
| } |
| } |
| catch(err) { |
| } |
| //--> |
| var methods = {"i0":6,"i1":10,"i2":10,"i3":10,"i4":10,"i5":10}; |
| var tabs = {65535:["t0","All 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/BoundedSource.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/CompressedSource.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/BoundedSource.BoundedReader.html" target="_top">Frames</a></li> |
| <li><a href="BoundedSource.BoundedReader.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><a href="#field.summary">Field</a> | </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><a href="#field.detail">Field</a> | </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 BoundedSource.BoundedReader" class="title">Class BoundedSource.BoundedReader<T></h2> |
| </div> |
| <div class="contentContainer"> |
| <ul class="inheritance"> |
| <li>java.lang.Object</li> |
| <li> |
| <ul class="inheritance"> |
| <li><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html" title="class in org.apache.beam.sdk.io">org.apache.beam.sdk.io.Source.Reader</a><T></li> |
| <li> |
| <ul class="inheritance"> |
| <li>org.apache.beam.sdk.io.BoundedSource.BoundedReader<T></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <div class="description"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <dl> |
| <dt>All Implemented Interfaces:</dt> |
| <dd>java.lang.AutoCloseable</dd> |
| </dl> |
| <dl> |
| <dt>Direct Known Subclasses:</dt> |
| <dd><a href="../../../../../org/apache/beam/sdk/io/gcp/bigquery/BigQueryStorageStreamSource.BigQueryStorageStreamReader.html" title="class in org.apache.beam.sdk.io.gcp.bigquery">BigQueryStorageStreamSource.BigQueryStorageStreamReader</a>, <a href="../../../../../org/apache/beam/sdk/io/OffsetBasedSource.OffsetBasedReader.html" title="class in org.apache.beam.sdk.io">OffsetBasedSource.OffsetBasedReader</a></dd> |
| </dl> |
| <dl> |
| <dt>Enclosing class:</dt> |
| <dd><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io">BoundedSource</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="type parameter in BoundedSource">T</a>></dd> |
| </dl> |
| <hr> |
| <br> |
| <pre><a href="../../../../../org/apache/beam/sdk/annotations/Experimental.html" title="annotation in org.apache.beam.sdk.annotations">@Experimental</a>(<a href="../../../../../org/apache/beam/sdk/annotations/Experimental.html#value--">value</a>=<a href="../../../../../org/apache/beam/sdk/annotations/Experimental.Kind.html#SOURCE_SINK">SOURCE_SINK</a>) |
| public abstract static class <span class="typeNameLabel">BoundedSource.BoundedReader<T></span> |
| extends <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html" title="class in org.apache.beam.sdk.io">Source.Reader</a><T></pre> |
| <div class="block">A <code>Reader</code> that reads a bounded amount of input and supports some additional operations, |
| such as progress estimation and dynamic work rebalancing. |
| |
| <h3>Boundedness</h3> |
| |
| <p>Once <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> has returned false, neither will be called again on |
| this object. |
| |
| <h3>Thread safety</h3> |
| |
| <p>All methods will be run from the same thread except <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getFractionConsumed--"><code>getFractionConsumed()</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a>, and <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--"><code>getSplitPointsRemaining()</code></a>, all of which can be called concurrently from a different thread. |
| There will not be multiple concurrent calls to <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a>. |
| |
| <p>It must be safe to call <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getFractionConsumed--"><code>getFractionConsumed()</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>, <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a>, and <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--"><code>getSplitPointsRemaining()</code></a> |
| concurrently with other methods. |
| |
| <p>Additionally, a successful <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a> call must, by definition, cause <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a> to start returning a different value. Callers of <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a> |
| need to be aware of the possibility that the returned value can change at any time, and must |
| only access the properties of the source returned by <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a> which do not |
| change between <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a> calls. |
| |
| <h3>Implementing <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a></h3> |
| |
| <p>In the course of dynamic work rebalancing, the method <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a> may be called |
| concurrently with <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a>. It is critical that their interaction is |
| implemented in a thread-safe way, otherwise data loss is possible. |
| |
| <p>Sources which support dynamic work rebalancing should use <a href="../../../../../org/apache/beam/sdk/io/range/RangeTracker.html" title="interface in org.apache.beam.sdk.io.range"><code>RangeTracker</code></a> to manage the (source-specific) range of positions |
| that is being split.</div> |
| </li> |
| </ul> |
| </div> |
| <div class="summary"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <!-- =========== FIELD SUMMARY =========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="field.summary"> |
| <!-- --> |
| </a> |
| <h3>Field Summary</h3> |
| <table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Field Summary table, listing fields, and an explanation"> |
| <caption><span>Fields</span><span class="tabEnd"> </span></caption> |
| <tr> |
| <th class="colFirst" scope="col">Modifier and Type</th> |
| <th class="colLast" scope="col">Field and Description</th> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#SPLIT_POINTS_UNKNOWN">SPLIT_POINTS_UNKNOWN</a></span></code> |
| <div class="block">A constant to use as the return value for <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--"><code>getSplitPointsRemaining()</code></a> when the exact value is unknown.</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/BoundedSource.BoundedReader.html#BoundedReader--">BoundedReader</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="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>abstract <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io">BoundedSource</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--">getCurrentSource</a></span>()</code> |
| <div class="block">Returns a <code>Source</code> describing the same input that this <code>Reader</code> currently reads |
| (including items already read).</div> |
| </td> |
| </tr> |
| <tr id="i1" class="rowColor"> |
| <td class="colFirst"><code><a href="https://static.javadoc.io/joda-time/joda-time/2.10.3/org/joda/time/Instant.html?is-external=true" title="class or interface in org.joda.time">Instant</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentTimestamp--">getCurrentTimestamp</a></span>()</code> |
| <div class="block">By default, returns the minimum possible timestamp.</div> |
| </td> |
| </tr> |
| <tr id="i2" class="altColor"> |
| <td class="colFirst"><code>java.lang.Double</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getFractionConsumed--">getFractionConsumed</a></span>()</code> |
| <div class="block">Returns a value in [0, 1] representing approximately what fraction of the <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>current source</code></a> this reader has read so far, or <code>null</code> if such an |
| estimate is not available.</div> |
| </td> |
| </tr> |
| <tr id="i3" class="rowColor"> |
| <td class="colFirst"><code>long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--">getSplitPointsConsumed</a></span>()</code> |
| <div class="block">Returns the total amount of parallelism in the consumed (returned and processed) range of |
| this reader's current <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource</code></a> (as would be returned by <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>).</div> |
| </td> |
| </tr> |
| <tr id="i4" class="altColor"> |
| <td class="colFirst"><code>long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--">getSplitPointsRemaining</a></span>()</code> |
| <div class="block">Returns the total amount of parallelism in the unprocessed part of this reader's current |
| <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource</code></a> (as would be returned by <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>).</div> |
| </td> |
| </tr> |
| <tr id="i5" class="rowColor"> |
| <td class="colFirst"><code><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io">BoundedSource</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-">splitAtFraction</a></span>(double fraction)</code> |
| <div class="block">Tells the reader to narrow the range of the input it's going to read and give up the |
| remainder, so that the new range would contain approximately the given fraction of the amount |
| of data in the current range.</div> |
| </td> |
| </tr> |
| </table> |
| <ul class="blockList"> |
| <li class="blockList"><a name="methods.inherited.from.class.org.apache.beam.sdk.io.Source.Reader"> |
| <!-- --> |
| </a> |
| <h3>Methods inherited from class org.apache.beam.sdk.io.<a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html" title="class in org.apache.beam.sdk.io">Source.Reader</a></h3> |
| <code><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--">advance</a>, <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#close--">close</a>, <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#getCurrent--">getCurrent</a>, <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--">start</a></code></li> |
| </ul> |
| <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"> |
| <!-- ============ FIELD DETAIL =========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="field.detail"> |
| <!-- --> |
| </a> |
| <h3>Field Detail</h3> |
| <a name="SPLIT_POINTS_UNKNOWN"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>SPLIT_POINTS_UNKNOWN</h4> |
| <pre>public static final long SPLIT_POINTS_UNKNOWN</pre> |
| <div class="block">A constant to use as the return value for <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--"><code>getSplitPointsRemaining()</code></a> when the exact value is unknown.</div> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../../constant-values.html#org.apache.beam.sdk.io.BoundedSource.BoundedReader.SPLIT_POINTS_UNKNOWN">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ========= CONSTRUCTOR DETAIL ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="constructor.detail"> |
| <!-- --> |
| </a> |
| <h3>Constructor Detail</h3> |
| <a name="BoundedReader--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>BoundedReader</h4> |
| <pre>public BoundedReader()</pre> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ============ METHOD DETAIL ========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.detail"> |
| <!-- --> |
| </a> |
| <h3>Method Detail</h3> |
| <a name="getFractionConsumed--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getFractionConsumed</h4> |
| <pre><a href="https://static.javadoc.io/com.google.code.findbugs/jsr305/3.0.2/javax/annotation/Nullable.html?is-external=true" title="class or interface in javax.annotation">@Nullable</a> |
| public java.lang.Double getFractionConsumed()</pre> |
| <div class="block">Returns a value in [0, 1] representing approximately what fraction of the <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>current source</code></a> this reader has read so far, or <code>null</code> if such an |
| estimate is not available. |
| |
| <p>It is recommended that this method should satisfy the following properties: |
| |
| <ul> |
| <li>Should return 0 before the <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> call. |
| <li>Should return 1 after a <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> call that returns false. |
| <li>The returned values should be non-decreasing (though they don't have to be unique). |
| </ul> |
| |
| <p>By default, returns null to indicate that this cannot be estimated. |
| |
| <h3>Thread safety</h3> |
| |
| If <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a> is implemented, this method can be called concurrently to other |
| methods (including itself), and it is therefore critical for it to be implemented in a |
| thread-safe way.</div> |
| </li> |
| </ul> |
| <a name="getSplitPointsConsumed--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getSplitPointsConsumed</h4> |
| <pre>public long getSplitPointsConsumed()</pre> |
| <div class="block">Returns the total amount of parallelism in the consumed (returned and processed) range of |
| this reader's current <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource</code></a> (as would be returned by <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>). This corresponds to all split point records (see <a href="../../../../../org/apache/beam/sdk/io/range/RangeTracker.html" title="interface in org.apache.beam.sdk.io.range"><code>RangeTracker</code></a>) |
| returned by this reader, <em>excluding</em> the last split point returned if the reader is |
| not finished. |
| |
| <p>Consider the following examples: (1) An input that can be read in parallel down to the |
| individual records, such as <a href="../../../../../org/apache/beam/sdk/io/CountingSource.html#upTo-long-"><code>CountingSource.upTo(long)</code></a>, is called "perfectly splittable". |
| (2) a "block-compressed" file format such as <a href="../../../../../org/apache/beam/sdk/io/AvroIO.html" title="class in org.apache.beam.sdk.io"><code>AvroIO</code></a>, in which a block of records has |
| to be read as a whole, but different blocks can be read in parallel. (3) An "unsplittable" |
| input such as a cursor in a database. |
| |
| <ul> |
| <li>Any <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>reader</code></a> that is unstarted (aka, has never had a call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a>) has a consumed parallelism of 0. This condition holds independent of whether |
| the input is splittable. |
| <li>Any <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>reader</code></a> that has only returned its first element (aka, has |
| never had a call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a>) has a consumed parallelism of 0: the first |
| element is the current element and is still being processed. This condition holds |
| independent of whether the input is splittable. |
| <li>For an empty reader (in which the call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> returned false), the consumed |
| parallelism is 0. This condition holds independent of whether the input is splittable. |
| <li>For a non-empty, finished reader (in which the call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> returned true and |
| a call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> has returned false), the value returned must be at least 1 |
| and should equal the total parallelism in the source. |
| <li>For example (1): After returning record #30 (starting at 1) out of 50 in a perfectly |
| splittable 50-record input, this value should be 29. When finished, the consumed |
| parallelism should be 50. |
| <li>For example (2): In a block-compressed value consisting of 5 blocks, the value should |
| stay at 0 until the first record of the second block is returned; stay at 1 until the |
| first record of the third block is returned, etc. Only once the end-of-file is reached |
| then the fifth block has been consumed and the value should stay at 5. |
| <li>For example (3): For any non-empty unsplittable input, the consumed parallelism is 0 |
| until the reader is finished (because the last call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> returned false, |
| at which point it becomes 1. |
| </ul> |
| |
| <p>A reader that is implemented using a <a href="../../../../../org/apache/beam/sdk/io/range/RangeTracker.html" title="interface in org.apache.beam.sdk.io.range"><code>RangeTracker</code></a> is encouraged to use the range |
| tracker's ability to count split points to implement this method. See <a href="../../../../../org/apache/beam/sdk/io/OffsetBasedSource.OffsetBasedReader.html" title="class in org.apache.beam.sdk.io"><code>OffsetBasedSource.OffsetBasedReader</code></a> and <a href="../../../../../org/apache/beam/sdk/io/range/OffsetRangeTracker.html" title="class in org.apache.beam.sdk.io.range"><code>OffsetRangeTracker</code></a> for an example. |
| |
| <p>Defaults to <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#SPLIT_POINTS_UNKNOWN"><code>SPLIT_POINTS_UNKNOWN</code></a>. Any value less than 0 will be interpreted as |
| unknown. |
| |
| <h3>Thread safety</h3> |
| |
| See the javadoc on <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource.BoundedReader</code></a> for information about thread safety.</div> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsRemaining--"><code>getSplitPointsRemaining()</code></a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="getSplitPointsRemaining--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getSplitPointsRemaining</h4> |
| <pre>public long getSplitPointsRemaining()</pre> |
| <div class="block">Returns the total amount of parallelism in the unprocessed part of this reader's current |
| <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource</code></a> (as would be returned by <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>). This corresponds |
| to all unprocessed split point records (see <a href="../../../../../org/apache/beam/sdk/io/range/RangeTracker.html" title="interface in org.apache.beam.sdk.io.range"><code>RangeTracker</code></a>), including the last split |
| point returned, in the remainder part of the source. |
| |
| <p>This function should be implemented only <strong>in addition to <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a></strong> and only if <em>an exact value can be returned</em>. |
| |
| <p>Consider the following examples: (1) An input that can be read in parallel down to the |
| individual records, such as <a href="../../../../../org/apache/beam/sdk/io/CountingSource.html#upTo-long-"><code>CountingSource.upTo(long)</code></a>, is called "perfectly splittable". |
| (2) a "block-compressed" file format such as <a href="../../../../../org/apache/beam/sdk/io/AvroIO.html" title="class in org.apache.beam.sdk.io"><code>AvroIO</code></a>, in which a block of records has |
| to be read as a whole, but different blocks can be read in parallel. (3) An "unsplittable" |
| input such as a cursor in a database. |
| |
| <p>Assume for examples (1) and (2) that the number of records or blocks remaining is known: |
| |
| <ul> |
| <li>Any <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>reader</code></a> for which the last call to <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> has returned true should should not return 0, because this reader itself |
| represents parallelism at least 1. This condition holds independent of whether the |
| input is splittable. |
| <li>A finished reader (for which <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a>) has returned false |
| should return a value of 0. This condition holds independent of whether the input is |
| splittable. |
| <li>For example 1: After returning record #30 (starting at 1) out of 50 in a perfectly |
| splittable 50-record input, this value should be 21 (20 remaining + 1 current) if the |
| total number of records is known. |
| <li>For example 2: After returning a record in block 3 in a block-compressed file |
| consisting of 5 blocks, this value should be 3 (since blocks 4 and 5 can be processed |
| in parallel by new readers produced via dynamic work rebalancing, while the current |
| reader continues processing block 3) if the total number of blocks is known. |
| <li>For example (3): a reader for any non-empty unsplittable input, should return 1 until |
| it is finished, at which point it should return 0. |
| <li>For any reader: After returning the last split point in a file (e.g., the last record |
| in example (1), the first record in the last block for example (2), or the first record |
| in the file for example (3), this value should be 1: apart from the current task, no |
| additional remainder can be split off. |
| </ul> |
| |
| <p>Defaults to <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#SPLIT_POINTS_UNKNOWN"><code>SPLIT_POINTS_UNKNOWN</code></a>. Any value less than 0 will be interpreted as |
| unknown. |
| |
| <h3>Thread safety</h3> |
| |
| See the javadoc on <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource.BoundedReader</code></a> for information about thread safety.</div> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getSplitPointsConsumed--"><code>getSplitPointsConsumed()</code></a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="getCurrentSource--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getCurrentSource</h4> |
| <pre>public abstract <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io">BoundedSource</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>> getCurrentSource()</pre> |
| <div class="block">Returns a <code>Source</code> describing the same input that this <code>Reader</code> currently reads |
| (including items already read). |
| |
| <h3>Usage</h3> |
| |
| <p>Reader subclasses can use this method for convenience to access unchanging properties of |
| the source being read. Alternatively, they can cache these properties in the constructor. |
| |
| <p>The framework will call this method in the course of dynamic work rebalancing, e.g. after |
| a successful <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a> call. |
| |
| <h3>Mutability and thread safety</h3> |
| |
| <p>Remember that <a href="../../../../../org/apache/beam/sdk/io/Source.html" title="class in org.apache.beam.sdk.io"><code>Source</code></a> objects must always be immutable. However, the return value |
| of this function may be affected by dynamic work rebalancing, happening asynchronously via |
| <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#splitAtFraction-double-"><code>splitAtFraction(double)</code></a>, meaning it can return a different <a href="../../../../../org/apache/beam/sdk/io/Source.html" title="class in org.apache.beam.sdk.io"><code>Source</code></a> object. However, the returned object itself will still itself be immutable. Callers |
| must take care not to rely on properties of the returned source that may be asynchronously |
| changed as a result of this process (e.g. do not cache an end offset when reading a file). |
| |
| <h3>Implementation</h3> |
| |
| <p>For convenience, subclasses should usually return the most concrete subclass of <a href="../../../../../org/apache/beam/sdk/io/Source.html" title="class in org.apache.beam.sdk.io"><code>Source</code></a> possible. In practice, the implementation of this method should nearly always be one |
| of the following: |
| |
| <ul> |
| <li>Source that inherits from a base class that already implements <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html#getCurrentSource--"><code>getCurrentSource()</code></a>: delegate to base class. In this case, it is almost always an error |
| for the subclass to maintain its own copy of the source. |
| <pre><code> |
| public FooReader(FooSource<T> source) { |
| super(source); |
| } |
| |
| public FooSource<T> getCurrentSource() { |
| return (FooSource<T>)super.getCurrentSource(); |
| } |
| </code></pre> |
| <li>Source that does not support dynamic work rebalancing: return a private final variable. |
| <pre><code> |
| private final FooSource<T> source; |
| |
| public FooReader(FooSource<T> source) { |
| this.source = source; |
| } |
| |
| public FooSource<T> getCurrentSource() { |
| return source; |
| } |
| </code></pre> |
| <li><a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="class in org.apache.beam.sdk.io"><code>BoundedSource.BoundedReader</code></a> that explicitly supports dynamic work rebalancing: |
| maintain a variable pointing to an immutable source object, and protect it with |
| synchronization. |
| <pre><code> |
| private FooSource<T> source; |
| |
| public FooReader(FooSource<T> source) { |
| this.source = source; |
| } |
| |
| public synchronized FooSource<T> getCurrentSource() { |
| return source; |
| } |
| |
| public synchronized FooSource<T> splitAtFraction(double fraction) { |
| ... |
| FooSource<T> primary = ...; |
| FooSource<T> residual = ...; |
| this.source = primary; |
| return residual; |
| } |
| </code></pre> |
| </ul></div> |
| <dl> |
| <dt><span class="overrideSpecifyLabel">Specified by:</span></dt> |
| <dd><code><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#getCurrentSource--">getCurrentSource</a></code> in class <code><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html" title="class in org.apache.beam.sdk.io">Source.Reader</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="splitAtFraction-double-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>splitAtFraction</h4> |
| <pre><a href="https://static.javadoc.io/com.google.code.findbugs/jsr305/3.0.2/javax/annotation/Nullable.html?is-external=true" title="class or interface in javax.annotation">@Nullable</a> |
| public <a href="../../../../../org/apache/beam/sdk/io/BoundedSource.html" title="class in org.apache.beam.sdk.io">BoundedSource</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>> splitAtFraction(double fraction)</pre> |
| <div class="block">Tells the reader to narrow the range of the input it's going to read and give up the |
| remainder, so that the new range would contain approximately the given fraction of the amount |
| of data in the current range. |
| |
| <p>Returns a <code>BoundedSource</code> representing the remainder. |
| |
| <h3>Detailed description</h3> |
| |
| Assuming the following sequence of calls: |
| |
| <pre><code> |
| BoundedSource<T> initial = reader.getCurrentSource(); |
| BoundedSource<T> residual = reader.splitAtFraction(fraction); |
| BoundedSource<T> primary = reader.getCurrentSource(); |
| </code></pre> |
| |
| <ul> |
| <li>The "primary" and "residual" sources, when read, should together cover the same set of |
| records as "initial". |
| <li>The current reader should continue to be in a valid state, and continuing to read from |
| it should, together with the records it already read, yield the same records as would |
| have been read by "primary". |
| <li>The amount of data read by "primary" should ideally represent approximately the given |
| fraction of the amount of data read by "initial". |
| </ul> |
| |
| For example, a reader that reads a range of offsets <i>[A, B)</i> in a file might implement |
| this method by truncating the current range to <i>[A, A + fraction*(B-A))</i> and returning a |
| Source representing the range <i>[A + fraction*(B-A), B)</i>. |
| |
| <p>This method should return <code>null</code> if the split cannot be performed for this fraction |
| while satisfying the semantics above. E.g., a reader that reads a range of offsets in a file |
| should return <code>null</code> if it is already past the position in its range corresponding to |
| the given fraction. In this case, the method MUST have no effect (the reader must behave as |
| if the method hadn't been called at all). |
| |
| <h3>Statefulness</h3> |
| |
| Since this method (if successful) affects the reader's source, in subsequent invocations |
| "fraction" should be interpreted relative to the new current source. |
| |
| <h3>Thread safety and blocking</h3> |
| |
| This method will be called concurrently to other methods (however there will not be multiple |
| concurrent invocations of this method itself), and it is critical for it to be implemented in |
| a thread-safe way (otherwise data loss is possible). |
| |
| <p>It is also very important that this method always completes quickly. In particular, it |
| should not perform or wait on any blocking operations such as I/O, RPCs etc. Violating this |
| requirement may stall completion of the work item or even cause it to fail. |
| |
| <p>It is incorrect to make both this method and <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a>/<a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> <code>synchronized</code>, because those methods can perform blocking operations, and then this method |
| would have to wait for those calls to complete. |
| |
| <p><a href="../../../../../org/apache/beam/sdk/io/range/RangeTracker.html" title="interface in org.apache.beam.sdk.io.range"><code>RangeTracker</code></a> makes it easy to implement this method |
| safely and correctly. |
| |
| <p>By default, returns null to indicate that splitting is not possible.</div> |
| </li> |
| </ul> |
| <a name="getCurrentTimestamp--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>getCurrentTimestamp</h4> |
| <pre>public <a href="https://static.javadoc.io/joda-time/joda-time/2.10.3/org/joda/time/Instant.html?is-external=true" title="class or interface in org.joda.time">Instant</a> getCurrentTimestamp() |
| throws java.util.NoSuchElementException</pre> |
| <div class="block">By default, returns the minimum possible timestamp.</div> |
| <dl> |
| <dt><span class="overrideSpecifyLabel">Specified by:</span></dt> |
| <dd><code><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#getCurrentTimestamp--">getCurrentTimestamp</a></code> in class <code><a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html" title="class in org.apache.beam.sdk.io">Source.Reader</a><<a href="../../../../../org/apache/beam/sdk/io/BoundedSource.BoundedReader.html" title="type parameter in BoundedSource.BoundedReader">T</a>></code></dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code>java.util.NoSuchElementException</code> - if the reader is at the beginning of the input and <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> wasn't called, or if the last <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#start--"><code>Source.Reader.start()</code></a> or <a href="../../../../../org/apache/beam/sdk/io/Source.Reader.html#advance--"><code>Source.Reader.advance()</code></a> returned <code>false</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/BoundedSource.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/CompressedSource.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/BoundedSource.BoundedReader.html" target="_top">Frames</a></li> |
| <li><a href="BoundedSource.BoundedReader.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><a href="#field.summary">Field</a> | </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><a href="#field.detail">Field</a> | </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> |
