You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@accumulo.apache.org by bu...@apache.org on 2014/03/10 16:53:45 UTC
[1/3] git commit: ACCUMULO-2017 Wikisearch should use Guava instead
of Google Collections.
Repository: accumulo-wikisearch
Updated Branches:
refs/heads/1.4.5-SNAPSHOT e15859054 -> 1e4a40bcc
ACCUMULO-2017 Wikisearch should use Guava instead of Google Collections.
replaces Google Collections with Google Guava because that's what Hadoop 2 uses internally and they conflict.
Project: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/repo
Commit: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/commit/e84d8d7a
Tree: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/tree/e84d8d7a
Diff: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/diff/e84d8d7a
Branch: refs/heads/1.4.5-SNAPSHOT
Commit: e84d8d7a798a5b8098d01a2e02a17b8d20c918f8
Parents: e158590
Author: Sean Busbey <bu...@clouderagovt.com>
Authored: Wed Dec 11 00:27:16 2013 -0600
Committer: Sean Busbey <bu...@cloudera.com>
Committed: Mon Mar 10 10:08:22 2014 -0500
----------------------------------------------------------------------
README | 2 +-
README.parallel | 2 +-
ingest/pom.xml | 7 ++++---
pom.xml | 8 ++++----
query/pom.xml | 7 ++++---
5 files changed, 14 insertions(+), 12 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/e84d8d7a/README
----------------------------------------------------------------------
diff --git a/README b/README
index 041490f..869f5e7 100644
--- a/README
+++ b/README
@@ -55,7 +55,7 @@
kryo*.jar
minlog*.jar
commons-jexl*.jar
- google-collections*.jar
+ guava*.jar
8. Copy the $JBOSS_HOME/server/default/deploy/wikisearch-query*.jar to $ACCUMULO_HOME/lib/ext.
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/e84d8d7a/README.parallel
----------------------------------------------------------------------
diff --git a/README.parallel b/README.parallel
index 477556b..399f0f3 100644
--- a/README.parallel
+++ b/README.parallel
@@ -52,7 +52,7 @@
kryo*.jar
minlog*.jar
commons-jexl*.jar
- google-collections*.jar
+ guava*.jar
8. Copy the $JBOSS_HOME/server/default/deploy/wikisearch-query*.jar to $ACCUMULO_HOME/lib/ext.
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/e84d8d7a/ingest/pom.xml
----------------------------------------------------------------------
diff --git a/ingest/pom.xml b/ingest/pom.xml
index 31d7110..c4e0336 100644
--- a/ingest/pom.xml
+++ b/ingest/pom.xml
@@ -49,8 +49,8 @@
<artifactId>commons-lang</artifactId>
</dependency>
<dependency>
- <groupId>com.google.collections</groupId>
- <artifactId>google-collections</artifactId>
+ <groupId>com.google.guava</groupId>
+ <artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
@@ -103,7 +103,8 @@
<configuration>
<outputDirectory>lib</outputDirectory>
<!-- just grab the non-provided runtime dependencies -->
- <includeArtifactIds>commons-lang,google-collections,lucene-core,lucene-analyzers,lucene-wikipedia,protobuf-java,accumulo-core,hadoop-core,libthrift,cloudtrace,zookeeper,commons-codec</includeArtifactIds>
+ <!-- XXX we include guava at the same version as hadoop 2 provides so that we have it on hadoop 1 -->
+ <includeArtifactIds>commons-lang,guava,lucene-core,lucene-analyzers,lucene-wikipedia,protobuf-java,accumulo-core,hadoop-core,libthrift,cloudtrace,zookeeper,commons-codec</includeArtifactIds>
<excludeTransitive>false</excludeTransitive>
</configuration>
</execution>
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/e84d8d7a/pom.xml
----------------------------------------------------------------------
diff --git a/pom.xml b/pom.xml
index 1ea9a2a..44996e9 100644
--- a/pom.xml
+++ b/pom.xml
@@ -164,7 +164,7 @@
<version.lucene-analyzers>3.0.2</version.lucene-analyzers>
<version.lucene-wikipedia>3.0.2</version.lucene-wikipedia>
<version.protobuf>2.3.0</version.protobuf>
- <version.googlecollections>1.0</version.googlecollections>
+ <version.guava>11.0.2</version.guava>
<version.libthrift>0.6.1</version.libthrift>
<version.zookeeper>3.3.1</version.zookeeper>
<version.minlog>1.2</version.minlog>
@@ -203,9 +203,9 @@
<version>${version.accumulo}</version>
</dependency>
<dependency>
- <groupId>com.google.collections</groupId>
- <artifactId>google-collections</artifactId>
- <version>${version.googlecollections}</version>
+ <groupId>com.google.guava</groupId>
+ <artifactId>guava</artifactId>
+ <version>${version.guava}</version>
</dependency>
<dependency>
<groupId>com.googlecode</groupId>
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/e84d8d7a/query/pom.xml
----------------------------------------------------------------------
diff --git a/query/pom.xml b/query/pom.xml
index 8c6e6d3..d2f75ea 100644
--- a/query/pom.xml
+++ b/query/pom.xml
@@ -62,8 +62,8 @@
<artifactId>commons-jexl</artifactId>
</dependency>
<dependency>
- <groupId>com.google.collections</groupId>
- <artifactId>google-collections</artifactId>
+ <groupId>com.google.guava</groupId>
+ <artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>com.googlecode</groupId>
@@ -106,7 +106,8 @@
<configuration>
<outputDirectory>lib</outputDirectory>
<!-- just grab the non-provided runtime dependencies -->
- <includeArtifactIds>commons-lang,commons-codec,protobuf-java,libthrift,zookeeper,hadoop-core,commons-jexl,google-collections,kryo,asm,minlog,reflectasm,wikisearch-ingest,accumulo-core,cloudtrace</includeArtifactIds>
+ <!-- XXX we include guava at the same version as hadoop 2 provides so that we have it on hadoop 1 -->
+ <includeArtifactIds>commons-lang,commons-codec,protobuf-java,libthrift,zookeeper,hadoop-core,commons-jexl,guava,kryo,asm,minlog,reflectasm,wikisearch-ingest,accumulo-core,cloudtrace</includeArtifactIds>
<excludeTransitive>true</excludeTransitive>
</configuration>
</execution>
[3/3] git commit: ACCUMULO-2019 Fix packaging and deployment
instructions for wikisearch query interface.
Posted by bu...@apache.org.
ACCUMULO-2019 Fix packaging and deployment instructions for wikisearch query interface.
* update directions for project move to contrib
* update $ACCUMULO_HOME/lib/ext needs based on what ships with current Accumulo installation.
* update the dependencies included in the query dist tarball for the hadoop 2 profile.
Project: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/repo
Commit: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/commit/1e4a40bc
Tree: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/tree/1e4a40bc
Diff: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/diff/1e4a40bc
Branch: refs/heads/1.4.5-SNAPSHOT
Commit: 1e4a40bcc6cd11100def006f26037dbe0cd14e71
Parents: bcf16ab
Author: Sean Busbey <bu...@clouderagovt.com>
Authored: Fri Dec 13 14:30:59 2013 -0600
Committer: Sean Busbey <bu...@cloudera.com>
Committed: Mon Mar 10 10:16:15 2014 -0500
----------------------------------------------------------------------
README | 6 ++----
query/pom.xml | 23 +++++++++++++++++++++++
2 files changed, 25 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/1e4a40bc/README
----------------------------------------------------------------------
diff --git a/README b/README
index 869f5e7..ad28cdc 100644
--- a/README
+++ b/README
@@ -38,11 +38,11 @@
1. Copy the query/src/main/resources/META-INF/ejb-jar.xml.example file to
query/src/main/resources/META-INF/ejb-jar.xml. Modify to the file to contain the same
information that you put into the wikipedia.xml file from the Ingest step above.
- 2. Re-build the query distribution by running 'mvn package assembly:single' in the top-level directory.
+ 2. Re-build the query distribution by running 'mvn package assembly:single' in the query module's directory.
3. Untar the resulting file in the $JBOSS_HOME/server/default directory.
$ cd $JBOSS_HOME/server/default
- $ tar -xzf $ACCUMULO_HOME/src/examples/wikisearch/query/target/wikisearch-query*.tar.gz
+ $ tar -xzf /some/path/to/wikisearch/query/target/wikisearch-query*.tar.gz
This will place the dependent jars in the lib directory and the EJB jar into the deploy directory.
4. Next, copy the wikisearch*.war file in the query-war/target directory to $JBOSS_HOME/server/default/deploy.
@@ -51,11 +51,9 @@
setauths -u <user> -s all,enwiki,eswiki,frwiki,fawiki
7. Copy the following jars to the $ACCUMULO_HOME/lib/ext directory from the $JBOSS_HOME/server/default/lib directory:
- commons-lang*.jar
kryo*.jar
minlog*.jar
commons-jexl*.jar
- guava*.jar
8. Copy the $JBOSS_HOME/server/default/deploy/wikisearch-query*.jar to $ACCUMULO_HOME/lib/ext.
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/1e4a40bc/query/pom.xml
----------------------------------------------------------------------
diff --git a/query/pom.xml b/query/pom.xml
index d2f75ea..eb932f9 100644
--- a/query/pom.xml
+++ b/query/pom.xml
@@ -175,6 +175,29 @@
<artifactId>hadoop-client</artifactId>
</dependency>
</dependencies>
+ <build>
+ <plugins>
+ <plugin>
+ <groupId>org.apache.maven.plugins</groupId>
+ <artifactId>maven-dependency-plugin</artifactId>
+ <executions>
+ <execution>
+ <id>copy-dependencies</id>
+ <phase>process-resources</phase>
+ <goals>
+ <goal>copy-dependencies</goal>
+ </goals>
+ <configuration>
+ <outputDirectory>lib</outputDirectory>
+ <!-- just grab the non-provided runtime dependencies -->
+ <includeArtifactIds>commons-lang,commons-codec,protobuf-java,libthrift,zookeeper,hadoop-client,hadoop-common,hadoop-hdfs,commons-jexl,guava,kryo,asm,minlog,reflectasm,wikisearch-ingest,accumulo-core,cloudtrace</includeArtifactIds>
+ <excludeTransitive>false</excludeTransitive>
+ </configuration>
+ </execution>
+ </executions>
+ </plugin>
+ </plugins>
+ </build>
</profile>
</profiles>
[2/3] git commit: ACCUMULO-2018 Wikisearch Parallel Ingest script
should use parallel configuration file.
Posted by bu...@apache.org.
ACCUMULO-2018 Wikisearch Parallel Ingest script should use parallel configuration file.
make sure parallel ingester uses parallel config, per README.parallel
Project: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/repo
Commit: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/commit/bcf16abe
Tree: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/tree/bcf16abe
Diff: http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/diff/bcf16abe
Branch: refs/heads/1.4.5-SNAPSHOT
Commit: bcf16abe896e6ebb93a0e935473ec7a2afcc8ec2
Parents: e84d8d7
Author: Sean Busbey <bu...@clouderagovt.com>
Authored: Wed Dec 11 02:18:37 2013 -0600
Committer: Sean Busbey <bu...@cloudera.com>
Committed: Mon Mar 10 10:09:02 2014 -0500
----------------------------------------------------------------------
ingest/bin/ingest_parallel.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/accumulo-wikisearch/blob/bcf16abe/ingest/bin/ingest_parallel.sh
----------------------------------------------------------------------
diff --git a/ingest/bin/ingest_parallel.sh b/ingest/bin/ingest_parallel.sh
index 8c63ac0..62e79db 100755
--- a/ingest/bin/ingest_parallel.sh
+++ b/ingest/bin/ingest_parallel.sh
@@ -39,7 +39,7 @@ LIBJARS=`echo $CLASSPATH | sed 's/^://' | sed 's/:/,/g'`
# Map/Reduce job
#
JAR=$SCRIPT_DIR/../lib/wikisearch-ingest-1.4.5-SNAPSHOT.jar
-CONF=$SCRIPT_DIR/../conf/wikipedia.xml
+CONF=$SCRIPT_DIR/../conf/wikipedia_parallel.xml
HDFS_DATA_DIR=$1
export HADOOP_CLASSPATH=$CLASSPATH
echo "hadoop jar $JAR org.apache.accumulo.examples.wikisearch.ingest.WikipediaPartitionedIngester -libjars $LIBJARS -conf $CONF -Dwikipedia.input=${HDFS_DATA_DIR}"