This is an automated email from the ASF dual-hosted git repository.
lewismc pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/nutch.git
The following commit(s) were added to refs/heads/master by this push:
new b91fae5 NUTCH-2857 Upgrade from JDK1.8 --> JDK11 (#573)
b91fae5 is described below
commit b91fae53e7de1d4c240ba91c951024441f2ea01f
Author: Lewis John McGibbney <[email protected]>
AuthorDate: Sun Mar 21 08:30:41 2021 -0700
NUTCH-2857 Upgrade from JDK1.8 --> JDK11 (#573)
* NUTCH-2857 Upgrade from JDK1.8 --> JDK11
---
.github/workflows/master-build.yml | 2 +-
default.properties | 4 ++--
ivy/mvn.template | 4 ++--
.../org/apache/nutch/indexer/IndexWriterParams.java | 6 +++---
src/java/org/apache/nutch/metadata/MetaWrapper.java | 2 +-
src/java/org/apache/nutch/net/URLNormalizers.java | 4 ++--
src/java/org/apache/nutch/parse/ParserChecker.java | 18 +++++++++---------
.../org/apache/nutch/segment/SegmentMergeFilter.java | 2 +-
.../org/apache/nutch/segment/SegmentMergeFilters.java | 4 ++--
.../net/urlnormalizer/regex/RegexURLNormalizer.java | 2 +-
10 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/.github/workflows/master-build.yml
b/.github/workflows/master-build.yml
index 7e74840..e3ed11c 100644
--- a/.github/workflows/master-build.yml
+++ b/.github/workflows/master-build.yml
@@ -29,7 +29,7 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
- java: [ '1.8' ]
+ java: [ '11' ]
steps:
- uses: actions/checkout@v2
diff --git a/default.properties b/default.properties
index f250904..cf82c84 100644
--- a/default.properties
+++ b/default.properties
@@ -43,7 +43,7 @@ test.junit.output.format = plain
# Proxy Host and Port to use for building JavaDoc
javadoc.proxy.host=-J-DproxyHost=
javadoc.proxy.port=-J-DproxyPort=
-javadoc.link.java=https://docs.oracle.com/javase/8/docs/api/
+javadoc.link.java=https://docs.oracle.com/en/java/javase/11/docs/api/
javadoc.link.hadoop=https://hadoop.apache.org/docs/r3.1.3/api/
#javadoc.link.lucene.core=https://lucene.apache.org/core/8_4_1/core/
#javadoc.link.lucene.analyzers-common=https://lucene.apache.org/core/8_4_1/analyzers-common/
@@ -57,7 +57,7 @@ bin.dist.version.dir=${dist.dir}/${final.name}-bin
javac.debug=on
javac.optimize=on
javac.deprecation=on
-javac.version=1.8
+javac.version=11
runtime.dir=./runtime
runtime.deploy=${runtime.dir}/deploy
diff --git a/ivy/mvn.template b/ivy/mvn.template
index edfb550..b38b37f 100644
--- a/ivy/mvn.template
+++ b/ivy/mvn.template
@@ -130,8 +130,8 @@
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.1</version>
<configuration>
- <source>1.8</source>
- <target>1.8</target>
+ <source>11</source>
+ <target>11</target>
</configuration>
</plugin>
</plugins>
diff --git a/src/java/org/apache/nutch/indexer/IndexWriterParams.java
b/src/java/org/apache/nutch/indexer/IndexWriterParams.java
index e7b3152..52cc4f9 100644
--- a/src/java/org/apache/nutch/indexer/IndexWriterParams.java
+++ b/src/java/org/apache/nutch/indexer/IndexWriterParams.java
@@ -24,10 +24,10 @@ import java.util.Map;
public class IndexWriterParams extends HashMap<String, String> {
/**
- * Constructs a new <tt>HashMap</tt> with the same mappings as the
- * specified <tt>Map</tt>. The <tt>HashMap</tt> is created with
+ * Constructs a new <code>HashMap</code> with the same mappings as the
+ * specified <code>Map</code>. The <code>HashMap</code> is created with
* default load factor (0.75) and an initial capacity sufficient to
- * hold the mappings in the specified <tt>Map</tt>.
+ * hold the mappings in the specified <code>Map</code>.
*
* @param m the map whose mappings are to be placed in this map
* @throws NullPointerException if the specified map is null
diff --git a/src/java/org/apache/nutch/metadata/MetaWrapper.java
b/src/java/org/apache/nutch/metadata/MetaWrapper.java
index a58253c..2547734 100644
--- a/src/java/org/apache/nutch/metadata/MetaWrapper.java
+++ b/src/java/org/apache/nutch/metadata/MetaWrapper.java
@@ -26,7 +26,7 @@ import org.apache.nutch.crawl.NutchWritable;
/**
* This is a simple decorator that adds metadata to any Writable-s that can be
- * serialized by <tt>NutchWritable</tt>. This is useful when data needs to be
+ * serialized by {@link NutchWritable}. This is useful when data needs to be
* temporarily enriched during processing, but this temporary metadata doesn't
* need to be permanently stored after the job is done.
*
diff --git a/src/java/org/apache/nutch/net/URLNormalizers.java
b/src/java/org/apache/nutch/net/URLNormalizers.java
index 4ec904d..bf947f7 100644
--- a/src/java/org/apache/nutch/net/URLNormalizers.java
+++ b/src/java/org/apache/nutch/net/URLNormalizers.java
@@ -42,7 +42,7 @@ import org.apache.nutch.util.ObjectCache;
* This class uses a "chained filter" pattern to run defined normalizers.
* Different lists of normalizers may be defined for different "scopes", or
* contexts where they are used (note however that they need to be activated
- * first through <tt>plugin.include</tt> property).
+ * first through <code>plugin.include</code> property).
*
* <p>
* There is one global scope defined by default, which consists of all active
@@ -82,7 +82,7 @@ import org.apache.nutch.util.ObjectCache;
* executed at the beginning. By default this loop is executed just once - if
* you want to ensure that all possible combinations have been applied you may
* want to run this loop up to the number of activated normalizers. This loop
- * count can be configured through <tt>urlnormalizer.loop.count</tt> property.
+ * count can be configured through <code>urlnormalizer.loop.count</code>
property.
* As soon as the url is unchanged the loop will stop and return the result.
* </p>
*
diff --git a/src/java/org/apache/nutch/parse/ParserChecker.java
b/src/java/org/apache/nutch/parse/ParserChecker.java
index 97dcd39..7b0e76a 100644
--- a/src/java/org/apache/nutch/parse/ParserChecker.java
+++ b/src/java/org/apache/nutch/parse/ParserChecker.java
@@ -43,22 +43,22 @@ import org.slf4j.LoggerFactory;
* to aid debugging. The tool enables us to retrieve the following data from
any
* url:
* <ol>
- * <li><tt>contentType</tt>: The URL {@link org.apache.nutch.protocol.Content}
+ * <li><code>contentType</code>: The URL {@link
org.apache.nutch.protocol.Content}
* type.</li>
- * <li><tt>signature</tt>: Digest is used to identify pages (like unique ID)
and
+ * <li><code>signature</code>: Digest is used to identify pages (like unique
ID) and
* is used to remove duplicates during the dedup procedure. It is calculated
* using {@link org.apache.nutch.crawl.MD5Signature} or
* {@link org.apache.nutch.crawl.TextProfileSignature}.</li>
- * <li><tt>Version</tt>: From {@link org.apache.nutch.parse.ParseData}.</li>
- * <li><tt>Status</tt>: From {@link org.apache.nutch.parse.ParseData}.</li>
- * <li><tt>Title</tt>: of the URL</li>
- * <li><tt>Outlinks</tt>: associated with the URL</li>
- * <li><tt>Content Metadata</tt>: such as <i>X-AspNet-Version</i>, <i>Date</i>,
+ * <li><code>Version</code>: From {@link
org.apache.nutch.parse.ParseData}.</li>
+ * <li><code>Status</code>: From {@link org.apache.nutch.parse.ParseData}.</li>
+ * <li><code>Title</code>: of the URL</li>
+ * <li><code>Outlinks</code>: associated with the URL</li>
+ * <li><code>Content Metadata</code>: such as <i>X-AspNet-Version</i>,
<i>Date</i>,
* <i>Content-length</i>, <i>servedBy</i>, <i>Content-Type</i>,
* <i>Cache-Control</i>, etc.</li>
- * <li><tt>Parse Metadata</tt>: such as <i>CharEncodingForConversion</i>,
+ * <li><code>Parse Metadata</code>: such as <i>CharEncodingForConversion</i>,
* <i>OriginalCharEncoding</i>, <i>language</i>, etc.</li>
- * <li><tt>ParseText</tt>: The page parse text which varies in length
depdnecing
+ * <li><code>ParseText</code>: The page parse text which varies in length
depdnecing
* on <code>content.length</code> configuration.</li>
* </ol>
*
diff --git a/src/java/org/apache/nutch/segment/SegmentMergeFilter.java
b/src/java/org/apache/nutch/segment/SegmentMergeFilter.java
index 0e1d579..c0c72c7 100644
--- a/src/java/org/apache/nutch/segment/SegmentMergeFilter.java
+++ b/src/java/org/apache/nutch/segment/SegmentMergeFilter.java
@@ -45,7 +45,7 @@ public interface SegmentMergeFilter {
* @param parseData directory and data produced by the parse phase
* @param parseText directory and data produced by the parse phase
* @param linked all LINKED values from the latest segment
- * @return <tt>true</tt> values for this <tt>key</tt> (URL) should be merged
+ * @return <code>true</code> values for this <code>key</code> (URL) should
be merged
* into the new segment.
*/
public boolean filter(Text key, CrawlDatum generateData,
diff --git a/src/java/org/apache/nutch/segment/SegmentMergeFilters.java
b/src/java/org/apache/nutch/segment/SegmentMergeFilters.java
index 81cf323..8126221 100644
--- a/src/java/org/apache/nutch/segment/SegmentMergeFilters.java
+++ b/src/java/org/apache/nutch/segment/SegmentMergeFilters.java
@@ -36,7 +36,7 @@ import org.apache.nutch.protocol.Content;
/**
* This class wraps all {@link SegmentMergeFilter} extensions in a single
object
* so it is easier to operate on them. If any of extensions returns
- * <tt>false</tt> this one will return <tt>false</tt> as well.
+ * <code>false</code> this one will return <code>false</code> as well.
*
*/
public class SegmentMergeFilters {
@@ -71,7 +71,7 @@ public class SegmentMergeFilters {
* @param parseData directory and data produced by the parse phase
* @param parseText directory and data produced by the parse phase
* @param linked all LINKED values from the latest segment
- * @return <tt>true</tt> values for this <tt>key</tt> (URL) should be merged
+ * @return <code>true</code> values for this <code>key</code> (URL) should
be merged
* into the new segment.
*/
public boolean filter(Text key, CrawlDatum generateData,
diff --git
a/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java
b/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java
index 7ccc423..885944e 100644
---
a/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java
+++
b/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java
@@ -52,7 +52,7 @@ import org.xml.sax.InputSource;
* which is useful for stripping session IDs from URLs.
*
* <p>
- * This class uses the <tt>urlnormalizer.regex.file</tt> property. It should be
+ * This class uses the <code>urlnormalizer.regex.file</code> property. It
should be
* set to the file name of an xml file which should contain the patterns and
* substitutions to be done on encountered URLs.
* </p>
