From 267bfc5ff2dad1940f792388913a4b87bc34f5b7 Mon Sep 17 00:00:00 2001 From: Arun Murthy Date: Thu, 11 Oct 2012 17:22:27 +0000 Subject: [PATCH] Merge -c 1397182 from trunk to branch-2 to fix MAPREDUCE-4616. Improve javadoc for MultipleOutputs. Contributed by Tony Burton. git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2@1397183 13f79535-47bb-0310-9956-ffa450edef68 --- hadoop-mapreduce-project/CHANGES.txt | 3 + .../lib/output/LazyOutputFormat.java | 5 +- .../mapreduce/lib/output/MultipleOutputs.java | 62 +++++++++++++++++++ 3 files changed, 69 insertions(+), 1 deletion(-) diff --git a/hadoop-mapreduce-project/CHANGES.txt b/hadoop-mapreduce-project/CHANGES.txt index 0275b847fa2..9f520ff3a45 100644 --- a/hadoop-mapreduce-project/CHANGES.txt +++ b/hadoop-mapreduce-project/CHANGES.txt @@ -14,6 +14,9 @@ Release 2.0.3-alpha - Unreleased MAPREDUCE-3678. The Map tasks logs should have the value of input split it processed. (harsh) + MAPREDUCE-4616. Improve javadoc for MultipleOutputs. (Tony Burton via + acmurthy) + OPTIMIZATIONS BUG FIXES diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java index 2619e207358..c6c49fa6f5a 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java @@ -32,7 +32,10 @@ import org.apache.hadoop.mapreduce.TaskAttemptContext; import org.apache.hadoop.util.ReflectionUtils; /** - * A Convenience class that creates output lazily. + * A Convenience class that creates output lazily. + * Use in conjuction with org.apache.hadoop.mapreduce.lib.output.MultipleOutputs to recreate the + * behaviour of org.apache.hadoop.mapred.lib.MultipleTextOutputFormat (etc) of the old Hadoop API. + * See {@link MultipleOutputs} documentation for more information. */ @InterfaceAudience.Public @InterfaceStability.Stable diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java index 0db94e0475d..7974b78fb89 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java @@ -20,7 +20,10 @@ package org.apache.hadoop.mapreduce.lib.output; import org.apache.hadoop.classification.InterfaceAudience; import org.apache.hadoop.classification.InterfaceStability; import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.*; +import org.apache.hadoop.mapreduce.Reducer.Context; +import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs; import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl; import org.apache.hadoop.util.ReflectionUtils; @@ -37,6 +40,7 @@ import java.util.*; * Each additional output, or named output, may be configured with its own * OutputFormat, with its own key class and with its own value * class. + *

* *

* Case two: to write data to different files provided by user @@ -107,6 +111,64 @@ import java.util.*; * * } * + * + *

+ * When used in conjuction with org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat, + * MultipleOutputs can mimic the behaviour of MultipleTextOutputFormat and MultipleSequenceFileOutputFormat + * from the old Hadoop API - ie, output can be written from the Reducer to more than one location. + *

+ * + *

+ * Use MultipleOutputs.write(KEYOUT key, VALUEOUT value, String baseOutputPath) to write key and + * value to a path specified by baseOutputPath, with no need to specify a named output: + *

+ * + * 
+ * private MultipleOutputs out;
+ * 
+ * public void setup(Context context) {
+ *   out = new MultipleOutputs(context);
+ *   ...
+ * }
+ * 
+ * public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
+ * for (Text t : values) {
+ *   out.write(key, t, generateFileName(<parameter list...>));
+ *   }
+ * }
+ * 
+ * protected void cleanup(Context context) throws IOException, InterruptedException {
+ *   out.close();
+ * }
+ *
+ * + *

+ * Use your own code in generateFileName() to create a custom path to your results. + * '/' characters in baseOutputPath will be translated into directory levels in your file system. + * Also, append your custom-generated path with "part" or similar, otherwise your output will be -00000, -00001 etc. + * No call to context.write() is necessary. See example generateFileName() code below. + *

+ * + * 
+ * private String generateFileName(Text k) {
+ *   // expect Text k in format "Surname|Forename"
+ *   String[] kStr = k.toString().split("\\|");
+ *   
+ *   String sName = kStr[0];
+ *   String fName = kStr[1];
+ *
+ *   // example for k = Smith|John
+ *   // output written to /user/hadoop/path/to/output/Smith/John-r-00000 (etc)
+ *   return sName + "/" + fName;
+ * }
+ *
+ * + *

+ * Using MultipleOutputs in this way will still create zero-sized default output, eg part-00000. + * To prevent this use LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class); + * instead of job.setOutputFormatClass(TextOutputFormat.class); in your Hadoop job configuration. + *

+ * */ @InterfaceAudience.Public @InterfaceStability.Stable