This is an automated email from the ASF dual-hosted git repository. snagel pushed a commit to branch 2.x in repository https://gitbox.apache.org/repos/asf/nutch.git
commit 63b58e8889297ca4afcff2de4c8b1f86d657dbf2 Author: Kiyonari Harigae <laks...@cloudysunny14.org> AuthorDate: Mon Apr 17 13:52:42 2017 +0900 NUTCH-2374 Upgrade Nutch 2.X to Gora 0.7 --- ivy/ivy.xml | 16 ++++++++-------- src/java/org/apache/nutch/crawl/WebTableReader.java | 4 ++-- src/java/org/apache/nutch/host/HostDbUpdateJob.java | 2 +- src/java/org/apache/nutch/storage/StorageUtils.java | 2 +- .../org/apache/nutch/util/domain/DomainStatistics.java | 2 +- 5 files changed, 13 insertions(+), 13 deletions(-) diff --git a/ivy/ivy.xml b/ivy/ivy.xml index 9f43252..84954a2 100644 --- a/ivy/ivy.xml +++ b/ivy/ivy.xml @@ -102,7 +102,7 @@ <!-- N.B. To use Gora SNAPSHOT's merely replace the 'ref' value with the SNAPSHOT version and add changing="true" alongside the dependency declaration. An example has been provided for the gora-core dependency as below --> - <dependency org="org.apache.gora" name="gora-core" rev="0.6.1" conf="*->default"/> + <dependency org="org.apache.gora" name="gora-core" rev="0.7" conf="*->default"/> <!-- Uncomment this to use SQL as Gora backend. It should be noted that the gora-sql 0.1.1-incubating artifact is NOT compatable with gora-core 0.3. Users should @@ -116,29 +116,29 @@ --> <!-- Uncomment this to use HBase as Gora backend. --> <!-- - <dependency org="org.apache.gora" name="gora-hbase" rev="0.6.1" conf="*->default" /> + <dependency org="org.apache.gora" name="gora-hbase" rev="0.7" conf="*->default" /> --> <!-- Uncomment this to use Accumulo as Gora backend. --> <!-- - <dependency org="org.apache.gora" name="gora-accumulo" rev="0.6.1" conf="*->default" /> + <dependency org="org.apache.gora" name="gora-accumulo" rev="0.7" conf="*->default" /> --> <!-- Uncomment this to use Cassandra as Gora backend. --> <!-- - <dependency org="org.apache.gora" name="gora-cassandra" rev="0.6.1" conf="*->default" /> + <dependency org="org.apache.gora" name="gora-cassandra" rev="0.7" conf="*->default" /> --> <!-- Uncomment this to use MongoDB as Gora backend. --> <!-- - <dependency org="org.apache.gora" name="gora-mongodb" rev="0.6.1" conf="*->default" /> + <dependency org="org.apache.gora" name="gora-mongodb" rev="0.7" conf="*->default" /> --> <!-- Uncomment this to use Solr as Gora backend. --> <!-- - <dependency org="org.apache.gora" name="gora-solr" rev="0.6.1" conf="*->default" /> + <dependency org="org.apache.gora" name="gora-solr" rev="0.7" conf="*->default" /> --> <!-- The gora-compiler is used within the 'ant generate-gora-src' target to compile the Gora .avsc files within ./src/gora --> - <dependency org="org.apache.gora" name="gora-compiler-cli" rev="0.6.1" conf="*->default"/> - <dependency org="org.apache.gora" name="gora-compiler" rev="0.6.1" conf="*->default"/> + <dependency org="org.apache.gora" name="gora-compiler-cli" rev="0.7" conf="*->default"/> + <dependency org="org.apache.gora" name="gora-compiler" rev="0.7" conf="*->default"/> <!-- web app dependencies --> diff --git a/src/java/org/apache/nutch/crawl/WebTableReader.java b/src/java/org/apache/nutch/crawl/WebTableReader.java index b0b8b3f..5985dd6 100644 --- a/src/java/org/apache/nutch/crawl/WebTableReader.java +++ b/src/java/org/apache/nutch/crawl/WebTableReader.java @@ -332,7 +332,7 @@ public class WebTableReader extends NutchTool implements Tool { WebPage._ALL_FIELDS.length); query.setFields(fields); - GoraMapper.initMapperJob(job, query, store, Text.class, Text.class, + GoraMapper.initMapperJob(job, query, Text.class, Text.class, WebTableRegexMapper.class, null, true); FileOutputFormat.setOutputPath(job, outFolder); @@ -562,7 +562,7 @@ public class WebTableReader extends NutchTool implements Tool { WebPage._ALL_FIELDS.length); query.setFields(fields); - GoraMapper.initMapperJob(currentJob, query, store, Text.class, + GoraMapper.initMapperJob(currentJob, query, Text.class, LongWritable.class, WebTableStatMapper.class, null, true); currentJob.setCombinerClass(WebTableStatCombiner.class); diff --git a/src/java/org/apache/nutch/host/HostDbUpdateJob.java b/src/java/org/apache/nutch/host/HostDbUpdateJob.java index 0bfec40..1f95cc4 100644 --- a/src/java/org/apache/nutch/host/HostDbUpdateJob.java +++ b/src/java/org/apache/nutch/host/HostDbUpdateJob.java @@ -105,7 +105,7 @@ public class HostDbUpdateJob implements Tool { query.setFields(StorageUtils.toStringArray(FIELDS)); // Note: pages without // these fields are // skipped - GoraMapper.initMapperJob(job, query, pageStore, Text.class, WebPage.class, + GoraMapper.initMapperJob(job, query, Text.class, WebPage.class, HostDbUpdateJob.Mapper.class, null, true); // === Reduce === diff --git a/src/java/org/apache/nutch/storage/StorageUtils.java b/src/java/org/apache/nutch/storage/StorageUtils.java index e82a3c5..d600e57 100644 --- a/src/java/org/apache/nutch/storage/StorageUtils.java +++ b/src/java/org/apache/nutch/storage/StorageUtils.java @@ -139,7 +139,7 @@ public class StorageUtils { if (filter != null) { query.setFilter(filter); } - GoraMapper.initMapperJob(job, query, store, outKeyClass, outValueClass, + GoraMapper.initMapperJob(job, query, outKeyClass, outValueClass, mapperClass, partitionerClass, reuseObjects); GoraOutputFormat.setOutput(job, store, true); } diff --git a/src/java/org/apache/nutch/util/domain/DomainStatistics.java b/src/java/org/apache/nutch/util/domain/DomainStatistics.java index 179634b..7563d9f 100644 --- a/src/java/org/apache/nutch/util/domain/DomainStatistics.java +++ b/src/java/org/apache/nutch/util/domain/DomainStatistics.java @@ -110,7 +110,7 @@ public class DomainStatistics extends Configured implements Tool { Query<String, WebPage> query = store.newQuery(); query.setFields(WebPage._ALL_FIELDS); - GoraMapper.initMapperJob(job, query, store, Text.class, LongWritable.class, + GoraMapper.initMapperJob(job, query, Text.class, LongWritable.class, DomainStatisticsMapper.class, null, true); FileOutputFormat.setOutputPath(job, new Path(outputDir)); -- To stop receiving notification emails like this one, please contact "commits@nutch.apache.org" <commits@nutch.apache.org>.