This is an automated email from the ASF dual-hosted git repository. jmark99 pushed a commit to branch 2.1 in repository https://gitbox.apache.org/repos/asf/accumulo-examples.git
The following commit(s) were added to refs/heads/2.1 by this push: new 3b8088a Update SampleExample and documentation (#116) 3b8088a is described below commit 3b8088a64187d6f19a28bb357a7c105b1aaf754a Author: Mark Owens <jmar...@apache.org> AuthorDate: Fri Jan 27 10:37:19 2023 -0500 Update SampleExample and documentation (#116) * Added BatchWriter flush command to SampleExample.java to ensure updated sample data is output when executing SampleExample via the runex command * Updated Sample.md documentation to correctly display changes with the update to Accumulo 2.1 * Updated Shard.md documentation to correctly display changes with the update to Accumulo 2.1 --- docs/sample.md | 2 +- docs/shard.md | 42 ++++++++++------------ .../accumulo/examples/sample/SampleExample.java | 1 + 3 files changed, 20 insertions(+), 25 deletions(-) diff --git a/docs/sample.md b/docs/sample.md index 33c9e81..9990907 100644 --- a/docs/sample.md +++ b/docs/sample.md @@ -79,7 +79,7 @@ failure and fixing the problem with a compaction. root@instance examples.sampex> compact -t examples.sampex --sf-no-sample 2015-09-09 12:23:07,242 [shell.Shell] INFO : Compaction of table sampex started for given range root@instance examples.sampex> scan --sample - 2317 doc:content [] milk, eggs, bread, parmigiano-reggiano + 2317 doc:content [] milk, eggs, bread, parmigiano-reggiano, butter 2317 doc:url [] file://groceries/9.txt 3900 doc:content [] EC2 ate my homework 3900 doc:uril [] file://final_project.txt diff --git a/docs/shard.md b/docs/shard.md index d779c6f..05beea3 100644 --- a/docs/shard.md +++ b/docs/shard.md @@ -30,36 +30,29 @@ To run these example programs, create two tables like below. username@instance> createtable examples.shard username@instance examples.shard> createtable examples.doc2term -After creating the tables, index some files. The following command indexes all of the java files in the Accumulo source code. +After creating the tables, index some files. The following command indexes all the java files in the Accumulo source code. $ find /path/to/accumulo/core -name "*.java" | xargs ./bin/runex shard.Index -t examples.shard --partitions 30 The following command queries the index to find all files containing 'foo' and 'bar'. $ ./bin/runex shard.Query -t examples.shard foo bar - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/replication/ReplicationTargetTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/admin/NewTableConfigurationTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/HostRegexTableLoadBalancerTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/data/KeyExtentTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/BaseHostRegexTableLoadBalancerTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/iterators/user/WholeRowIteratorTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/iterators/user/WholeColumnFamilyIteratorTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/iteratorsImpl/IteratorConfigUtilTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/data/KeyBuilderTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/HostRegexTableLoadBalancerReconfigurationTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/security/ColumnVisibilityTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/conf/IterConfigUtilTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/summary/SummaryCollectionTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/clientImpl/TableOperationsHelperTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/clientImpl/mapreduce/BatchInputSplitTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/HostRegexTableLoadBalancerReconfigurationTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/HostRegexTableLoadBalancerTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/IteratorSettingTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/mapred/RangeInputSplitTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/data/KeyExtentTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/security/VisibilityEvaluatorTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/iterators/user/TransformingIteratorTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/spi/balancer/BaseHostRegexTableLoadBalancerTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/admin/NewTableConfigurationTest.java /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/conf/HadoopCredentialProviderTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/mapreduce/AccumuloInputFormatTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/replication/ReplicationSchemaTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/client/mapreduce/RangeInputSplitTest.java - /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/security/VisibilityEvaluatorTest.java - + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/clientImpl/TableOperationsHelperTest.java + /path/to/accumulo/core/src/test/java/org/apache/accumulo/core/iterators/user/WholeColumnFamilyIteratorTest.java In order to run ContinuousQuery, we need to run Reverse.java to populate the `examples.doc2term` table. @@ -69,13 +62,14 @@ Below ContinuousQuery is run using 5 terms. So it selects 5 random terms from ea randomly selects one set of 5 terms and queries. It prints the number of matching documents and the time in seconds. $ ./bin/runex shard.ContinuousQuery --shardTable examples.shard --doc2Term examples.doc2term --terms 5 - [public, core, class, binarycomparable, b] 2 0.081 - [wordtodelete, unindexdocument, doctablename, putdelete, insert] 1 0.041 - [import, columnvisibilityinterpreterfactory, illegalstateexception, cv, columnvisibility] 1 0.049 - [getpackage, testversion, util, version, 55] 1 0.048 - [for, static, println, public, the] 55 0.211 - [sleeptime, wrappingiterator, options, long, utilwaitthread] 1 0.057 - [string, public, long, 0, wait] 12 0.132 + [string, protected, sizeopt, cache, build] 1 0.084 + [public, these, exception, to, as] 25 0.267 + [by, encodeprevendrow, 0, work, as] 4 0.056 + [except, to, a, limitations, one] 969 0.197 + [copy, as, asf, version, is] 969 0.341 + [core, class, may, regarding, without] 862 0.437 + [max_data_to_print, default_visibility_cache_size, use, accumulo_export_info, fate] 1 0.066 + [Index.java]: ../src/main/java/org/apache/accumulo/examples/shard/Index.java [Query.java]: ../src/main/java/org/apache/accumulo/examples/shard/Query.java diff --git a/src/main/java/org/apache/accumulo/examples/sample/SampleExample.java b/src/main/java/org/apache/accumulo/examples/sample/SampleExample.java index 2e27811..6b5e3c8 100644 --- a/src/main/java/org/apache/accumulo/examples/sample/SampleExample.java +++ b/src/main/java/org/apache/accumulo/examples/sample/SampleExample.java @@ -111,6 +111,7 @@ public class SampleExample { // update a document in the sample data bw.addMutation(createMutation("2317", "milk, eggs, bread, parmigiano-reggiano, butter", "file://groceries/9/txt")); + bw.flush(); System.out.println( "Scanning sample after updating content for docId 2317 (should see content change in sample data) : ");