| <!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 --> |
| <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> |
| <title>WARCFileWriter (Apache HBase 3.0.0-alpha-2-SNAPSHOT Test API)</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="WARCFileWriter (Apache HBase 3.0.0-alpha-2-SNAPSHOT Test API)"; |
| } |
| } |
| catch(err) { |
| } |
| //--> |
| var methods = {"i0":10,"i1":10,"i2":9,"i3":10,"i4":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="class-use/WARCFileWriter.html">Use</a></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/hadoop/hbase/test/util/warc/WARCFileReader.CountingInputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.CountingOutputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../../../../index.html?org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html" target="_top">Frames</a></li> |
| <li><a href="WARCFileWriter.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><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.hadoop.hbase.test.util.warc</div> |
| <h2 title="Class WARCFileWriter" class="title">Class WARCFileWriter</h2> |
| </div> |
| <div class="contentContainer"> |
| <ul class="inheritance"> |
| <li><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true" title="class or interface in java.lang">java.lang.Object</a></li> |
| <li> |
| <ul class="inheritance"> |
| <li>org.apache.hadoop.hbase.test.util.warc.WARCFileWriter</li> |
| </ul> |
| </li> |
| </ul> |
| <div class="description"> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <hr> |
| <br> |
| <pre>public class <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.74">WARCFileWriter</a> |
| extends <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true" title="class or interface in java.lang">Object</a></pre> |
| <div class="block">Writes <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCRecord</code></a>s to a WARC file, using Hadoop's filesystem APIs. (This means you |
| can write to HDFS, S3 or any other filesystem supported by Hadoop). This implementation is |
| not tied to the MapReduce APIs -- that link is provided by the mapred |
| <code>com.martinkl.warc.mapred.WARCOutputFormat</code> and the mapreduce |
| <code>com.martinkl.warc.mapreduce.WARCOutputFormat</code>. |
| |
| WARCFileWriter keeps track of how much data it has written (optionally gzip-compressed); |
| when the file becomes larger than some threshold, it is automatically closed and a |
| new segment is started. A segment number is appended to the filename for that purpose. |
| The segment number always starts at 00000, and by default a new segment is started when |
| the file size exceeds 1GB. To change the target size for a segment, you can set the |
| `warc.output.segment.size` key in the Hadoop configuration to the number of bytes. |
| (Files may actually be a bit larger than this threshold, since we finish writing the |
| current record before opening a new file.)</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>private class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.CountingOutputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCFileWriter.CountingOutputStream</a></span></code> </td> |
| </tr> |
| </table> |
| </li> |
| </ul> |
| <!-- =========== 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>private <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.CountingOutputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCFileWriter.CountingOutputStream</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#byteStream">byteStream</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>private long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#bytesWritten">bytesWritten</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private org.apache.hadoop.io.compress.CompressionCodec</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#codec">codec</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>private org.apache.hadoop.conf.Configuration</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#conf">conf</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private <a href="https://docs.oracle.com/javase/8/docs/api/java/io/DataOutputStream.html?is-external=true" title="class or interface in java.io">DataOutputStream</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#dataStream">dataStream</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#DEFAULT_MAX_SEGMENT_SIZE">DEFAULT_MAX_SEGMENT_SIZE</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#extensionFormat">extensionFormat</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>private static org.slf4j.Logger</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#logger">logger</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#maxSegmentSize">maxSegmentSize</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>private org.apache.hadoop.util.Progressable</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#progress">progress</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#segmentsAttempted">segmentsAttempted</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>private long</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#segmentsCreated">segmentsCreated</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>private org.apache.hadoop.fs.Path</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#workOutputPath">workOutputPath</a></span></code> </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/hadoop/hbase/test/util/warc/WARCFileWriter.html#WARCFileWriter-org.apache.hadoop.conf.Configuration-org.apache.hadoop.io.compress.CompressionCodec-org.apache.hadoop.fs.Path-">WARCFileWriter</a></span>(org.apache.hadoop.conf.Configuration conf, |
| org.apache.hadoop.io.compress.CompressionCodec codec, |
| org.apache.hadoop.fs.Path workOutputPath)</code> |
| <div class="block">Creates a WARC file, and opens it for writing.</div> |
| </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colOne"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#WARCFileWriter-org.apache.hadoop.conf.Configuration-org.apache.hadoop.io.compress.CompressionCodec-org.apache.hadoop.fs.Path-org.apache.hadoop.util.Progressable-">WARCFileWriter</a></span>(org.apache.hadoop.conf.Configuration conf, |
| org.apache.hadoop.io.compress.CompressionCodec codec, |
| org.apache.hadoop.fs.Path workOutputPath, |
| org.apache.hadoop.util.Progressable progress)</code> |
| <div class="block">Creates a WARC file, and opens it for writing.</div> |
| </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="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>void</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#close--">close</a></span>()</code> |
| <div class="block">Flushes any buffered data and closes the file.</div> |
| </td> |
| </tr> |
| <tr id="i1" class="rowColor"> |
| <td class="colFirst"><code>private void</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#createSegment--">createSegment</a></span>()</code> |
| <div class="block">Creates an output segment file and sets up the output streams to point at it.</div> |
| </td> |
| </tr> |
| <tr id="i2" class="altColor"> |
| <td class="colFirst"><code>static org.apache.hadoop.io.compress.CompressionCodec</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#getGzipCodec-org.apache.hadoop.conf.Configuration-">getGzipCodec</a></span>(org.apache.hadoop.conf.Configuration conf)</code> |
| <div class="block">Instantiates a Hadoop codec for compressing and decompressing Gzip files.</div> |
| </td> |
| </tr> |
| <tr id="i3" class="rowColor"> |
| <td class="colFirst"><code>void</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#write-org.apache.hadoop.hbase.test.util.warc.WARCRecord-">write</a></span>(<a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCRecord</a> record)</code> |
| <div class="block">Appends a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCRecord</code></a> to the file, in WARC/1.0 format.</div> |
| </td> |
| </tr> |
| <tr id="i4" class="altColor"> |
| <td class="colFirst"><code>void</code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#write-org.apache.hadoop.hbase.test.util.warc.WARCWritable-">write</a></span>(<a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCWritable.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCWritable</a> record)</code> |
| <div class="block">Appends a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCRecord</code></a> wrapped in a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCWritable.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCWritable</code></a> to the file.</div> |
| </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.<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true" title="class or interface in java.lang">Object</a></h3> |
| <code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#clone--" title="class or interface in java.lang">clone</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#equals-java.lang.Object-" title="class or interface in java.lang">equals</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#finalize--" title="class or interface in java.lang">finalize</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#getClass--" title="class or interface in java.lang">getClass</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#hashCode--" title="class or interface in java.lang">hashCode</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#notify--" title="class or interface in java.lang">notify</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#notifyAll--" title="class or interface in java.lang">notifyAll</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#toString--" title="class or interface in java.lang">toString</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait--" title="class or interface in java.lang">wait</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait-long-" title="class or interface in java.lang">wait</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait-long-int-" title="class or interface in java.lang">wait</a></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="logger"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>logger</h4> |
| <pre>private static final org.slf4j.Logger <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.75">logger</a></pre> |
| </li> |
| </ul> |
| <a name="DEFAULT_MAX_SEGMENT_SIZE"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>DEFAULT_MAX_SEGMENT_SIZE</h4> |
| <pre>public static final long <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.76">DEFAULT_MAX_SEGMENT_SIZE</a></pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../../../../constant-values.html#org.apache.hadoop.hbase.test.util.warc.WARCFileWriter.DEFAULT_MAX_SEGMENT_SIZE">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="conf"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>conf</h4> |
| <pre>private final org.apache.hadoop.conf.Configuration <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.78">conf</a></pre> |
| </li> |
| </ul> |
| <a name="codec"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>codec</h4> |
| <pre>private final org.apache.hadoop.io.compress.CompressionCodec <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.79">codec</a></pre> |
| </li> |
| </ul> |
| <a name="workOutputPath"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>workOutputPath</h4> |
| <pre>private final org.apache.hadoop.fs.Path <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.80">workOutputPath</a></pre> |
| </li> |
| </ul> |
| <a name="progress"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>progress</h4> |
| <pre>private final org.apache.hadoop.util.Progressable <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.81">progress</a></pre> |
| </li> |
| </ul> |
| <a name="extensionFormat"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>extensionFormat</h4> |
| <pre>private final <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.82">extensionFormat</a></pre> |
| </li> |
| </ul> |
| <a name="maxSegmentSize"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>maxSegmentSize</h4> |
| <pre>private final long <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.83">maxSegmentSize</a></pre> |
| </li> |
| </ul> |
| <a name="segmentsCreated"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>segmentsCreated</h4> |
| <pre>private long <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.84">segmentsCreated</a></pre> |
| </li> |
| </ul> |
| <a name="segmentsAttempted"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>segmentsAttempted</h4> |
| <pre>private long <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.84">segmentsAttempted</a></pre> |
| </li> |
| </ul> |
| <a name="bytesWritten"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>bytesWritten</h4> |
| <pre>private long <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.84">bytesWritten</a></pre> |
| </li> |
| </ul> |
| <a name="byteStream"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>byteStream</h4> |
| <pre>private <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.CountingOutputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCFileWriter.CountingOutputStream</a> <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.85">byteStream</a></pre> |
| </li> |
| </ul> |
| <a name="dataStream"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>dataStream</h4> |
| <pre>private <a href="https://docs.oracle.com/javase/8/docs/api/java/io/DataOutputStream.html?is-external=true" title="class or interface in java.io">DataOutputStream</a> <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.86">dataStream</a></pre> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ========= CONSTRUCTOR DETAIL ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="constructor.detail"> |
| <!-- --> |
| </a> |
| <h3>Constructor Detail</h3> |
| <a name="WARCFileWriter-org.apache.hadoop.conf.Configuration-org.apache.hadoop.io.compress.CompressionCodec-org.apache.hadoop.fs.Path-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>WARCFileWriter</h4> |
| <pre>public <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.99">WARCFileWriter</a>(org.apache.hadoop.conf.Configuration conf, |
| org.apache.hadoop.io.compress.CompressionCodec codec, |
| org.apache.hadoop.fs.Path workOutputPath) |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Creates a WARC file, and opens it for writing. If a file with the same name already |
| exists, an attempt number in the filename is incremented until we find a file that |
| doesn't already exist.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>conf</code> - The Hadoop configuration.</dd> |
| <dd><code>codec</code> - If null, the file is uncompressed. If non-null, this compression codec |
| will be used. The codec's default file extension is appended to the filename.</dd> |
| <dd><code>workOutputPath</code> - The directory and filename prefix to which the data should be |
| written. We append a segment number and filename extensions to it.</dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="WARCFileWriter-org.apache.hadoop.conf.Configuration-org.apache.hadoop.io.compress.CompressionCodec-org.apache.hadoop.fs.Path-org.apache.hadoop.util.Progressable-"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>WARCFileWriter</h4> |
| <pre>public <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.116">WARCFileWriter</a>(org.apache.hadoop.conf.Configuration conf, |
| org.apache.hadoop.io.compress.CompressionCodec codec, |
| org.apache.hadoop.fs.Path workOutputPath, |
| org.apache.hadoop.util.Progressable progress) |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Creates a WARC file, and opens it for writing. If a file with the same name already |
| exists, it is *overwritten*. Note that this is different behaviour from the other |
| constructor. Yes, this sucks. It will probably change in a future version.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>conf</code> - The Hadoop configuration.</dd> |
| <dd><code>codec</code> - If null, the file is uncompressed. If non-null, this compression codec |
| will be used. The codec's default file extension is appended to the filename.</dd> |
| <dd><code>workOutputPath</code> - The directory and filename prefix to which the data should be |
| written. We append a segment number and filename extensions to it.</dd> |
| <dd><code>progress</code> - An object used by the mapred API for tracking a task's progress.</dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd> |
| </dl> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ============ METHOD DETAIL ========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.detail"> |
| <!-- --> |
| </a> |
| <h3>Method Detail</h3> |
| <a name="getGzipCodec-org.apache.hadoop.conf.Configuration-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>getGzipCodec</h4> |
| <pre>public static org.apache.hadoop.io.compress.CompressionCodec <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.134">getGzipCodec</a>(org.apache.hadoop.conf.Configuration conf)</pre> |
| <div class="block">Instantiates a Hadoop codec for compressing and decompressing Gzip files. This is the |
| most common compression applied to WARC files.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>conf</code> - The Hadoop configuration.</dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="createSegment--"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>createSegment</h4> |
| <pre>private void <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.155">createSegment</a>() |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Creates an output segment file and sets up the output streams to point at it. |
| If the file already exists, retries with a different filename. This is a bit nasty -- |
| after all, <code>FileOutputFormat</code>'s work directory concept is supposed to prevent |
| filename clashes -- but it looks like Amazon Elastic MapReduce prevents use of per-task |
| work directories if the output of a job is on S3. |
| |
| TODO: Investigate this and find a better solution.</div> |
| <dl> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="write-org.apache.hadoop.hbase.test.util.warc.WARCRecord-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>write</h4> |
| <pre>public void <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.193">write</a>(<a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCRecord</a> record) |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Appends a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCRecord</code></a> to the file, in WARC/1.0 format.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>record</code> - The record to be written.</dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="write-org.apache.hadoop.hbase.test.util.warc.WARCWritable-"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>write</h4> |
| <pre>public void <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.205">write</a>(<a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCWritable.html" title="class in org.apache.hadoop.hbase.test.util.warc">WARCWritable</a> record) |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Appends a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCRecord.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCRecord</code></a> wrapped in a <a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCWritable.html" title="class in org.apache.hadoop.hbase.test.util.warc"><code>WARCWritable</code></a> to the file.</div> |
| <dl> |
| <dt><span class="paramLabel">Parameters:</span></dt> |
| <dd><code>record</code> - The wrapper around the record to be written.</dd> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="close--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>close</h4> |
| <pre>public void <a href="../../../../../../../src-html/org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html#line.214">close</a>() |
| throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></pre> |
| <div class="block">Flushes any buffered data and closes the file.</div> |
| <dl> |
| <dt><span class="throwsLabel">Throws:</span></dt> |
| <dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></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="class-use/WARCFileWriter.html">Use</a></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/hadoop/hbase/test/util/warc/WARCFileReader.CountingInputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../../../../org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.CountingOutputStream.html" title="class in org.apache.hadoop.hbase.test.util.warc"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../../../../index.html?org/apache/hadoop/hbase/test/util/warc/WARCFileWriter.html" target="_top">Frames</a></li> |
| <li><a href="WARCFileWriter.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><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 ======= --> |
| <p class="legalCopy"><small>Copyright © 2007–2021 <a href="https://www.apache.org/">The Apache Software Foundation</a>. All rights reserved.</small></p> |
| </body> |
| </html> |