Apache Nutch is an extensible and scalable web crawler
NUTCH-2887 Migrate to JUnit 5 Jupiter (#862)
Lewis John McGibbneye2b60fc000ab
diff --git a/.github/workflows/master-build.yml b/.github/workflows/master-build.ymlindex 60e97a734..4654a82cd 100644--- a/.github/workflows/master-build.yml+++ b/.github/workflows/master-build.yml@@ -65,6 +65,7 @@ jobs:java: ['11']os: [ubuntu-latest, macos-latest]runs-on: ${{ matrix.os }}+ timeout-minutes: 30steps:- uses: actions/[email protected]- name: Set up JDK ${{ matrix.java }}diff --git a/build.xml b/build.xmlindex b24222ff2..c4b0b0d66 100644--- a/build.xml+++ b/build.xml@@ -485,12 +485,12 @@<copy file="${test.src.dir}/crawl-tests.xml" todir="${test.build.classes}"/><copy file="${test.src.dir}/domain-urlfilter.txt" todir="${test.build.classes}"/><copy file="${test.src.dir}/filter-all.txt" todir="${test.build.classes}"/>-<junitlauncher printSummary="true" haltOnFailure="true" failureProperty="tests.failed"><classpath refid="test.classpath"/>- <testclasses outputDir="${test.build.dir}" unless="testcase" includeEngines="junit-vintage">- <listener type="${test.junit.output.format}" sendSysOut="true" sendSysErr="true"/>- <fork dir="${basedir}">+ <testclasses outputDir="${test.build.dir}" unless="testcase">+ <listener type="legacy-plain" sendSysOut="true" sendSysErr="true"/>+ <listener type="legacy-xml" sendSysOut="true" sendSysErr="true"/>+ <fork><jvmarg value="-Xmx1000m"/><sysproperty key="test.build.data" value="${test.build.data}"/><sysproperty key="test.src.dir" value="${test.src.dir}"/>@@ -502,9 +502,10 @@<exclude name="**/${test.exclude}.class"/></fileset></testclasses>- <testclasses outputDir="${test.build.dir}" if="testcase" includeEngines="junit-vintage">- <listener type="${test.junit.output.format}" sendSysOut="true" sendSysErr="true"/>- <fork dir="${basedir}">+ <testclasses outputDir="${test.build.dir}" if="testcase">+ <listener type="legacy-plain" sendSysOut="true" sendSysErr="true"/>+ <listener type="legacy-xml" sendSysOut="true" sendSysErr="true"/>+ <fork><jvmarg value="-Xmx1000m"/><sysproperty key="test.build.data" value="${test.build.data}"/><sysproperty key="test.src.dir" value="${test.src.dir}"/>@@ -516,7 +517,6 @@</fileset></testclasses></junitlauncher>-<fail if="tests.failed">Tests failed!</fail></target>diff --git a/default.properties b/default.propertiesindex 4a79aad3f..6008563bc 100644--- a/default.properties+++ b/default.properties@@ -38,7 +38,6 @@ test.build.lib.dir = ${test.build.dir}/libtest.build.data = ${test.build.dir}/datatest.build.classes = ${test.build.dir}/classestest.build.javadoc = ${test.build.dir}/docs/api-test.junit.output.format = legacy-plain# Proxy Host and Port to use for building JavaDocjavadoc.proxy.host=-J-DproxyHost=diff --git a/ivy/ivy.xml b/ivy/ivy.xmlindex cf32e0bc0..a822f9c54 100644--- a/ivy/ivy.xml+++ b/ivy/ivy.xml@@ -118,12 +118,12 @@<exclude org="org.gnu.inet" module="libidn" /><!-- LGPL 2.1 --></dependency>- <!-- Keep the JUnit 4 dependency for test compilation and runtime support. Remove once migration is complete -->- <dependency org="junit" name="junit" rev="4.13.2" conf="test->default" />- <!-- JUnit 5 Platform Launcher (required for <junitlauncher> task) -->+ <dependency org="org.hamcrest" name="hamcrest" rev="3.0" conf="test->default"/>+ <!-- Required for <junitlauncher> task --><dependency org="org.junit.platform" name="junit-platform-launcher" rev="1.13.4" conf="test->default"/>- <!-- JUnit Vintage Engine (to run existing JUnit 4 tests). Remove once migration is complete -->- <dependency org="org.junit.vintage" name="junit-vintage-engine" rev="5.13.4" conf="test->default"/>+ <!-- Required for JUnit 5 (Jupiter) test execution -->+ <dependency org="org.junit.jupiter" name="junit-jupiter-engine" rev="5.13.4" conf="test->default"/>+ <dependency org="org.junit.jupiter" name="junit-jupiter-api" rev="5.13.4" conf="test->default"/><dependency org="org.apache.mrunit" name="mrunit" rev="1.1.0" conf="test->default"><artifact name="mrunit" ns0:classifier="hadoop2" /><exclude org="log4j" module="log4j" />diff --git a/src/plugin/build-plugin.xml b/src/plugin/build-plugin.xmlindex 5dabc3a7c..a4f737eda 100755--- a/src/plugin/build-plugin.xml+++ b/src/plugin/build-plugin.xml@@ -80,6 +80,7 @@</fileset><!-- global test dependencies --><fileset dir="${nutch.root}/build/test/lib">+ <include name="apiguardian*.jar" /><include name="hamcrest*.jar" /><include name="junit*.jar" /><include name="opentest4j*.jar" />@@ -208,28 +209,13 @@<!-- ================================================================== --><target name="test" depends="compile-test, deploy" if="test.available"><echo message="Testing plugin: ${name}"/>-- <!--junit printsummary="yes" haltonfailure="no" fork="yes"- errorProperty="tests.failed" failureProperty="tests.failed">- <sysproperty key="test.data" value="${build.test}/data"/>- <sysproperty key="test.input" value="${root}/data"/>- <sysproperty key="javax.xml.parsers.DocumentBuilderFactory" value="com.sun.org.apache.xerces.internal.jaxp.DocumentBuilderFactoryImpl"/>- <classpath refid="test.classpath"/>- <formatter type="${test.junit.output.format}" />- <batchtest todir="${build.test}" unless="testcase">- <fileset dir="${src.test}"- includes="**/Test*.java" excludes="**/${test.exclude}.java" />- </batchtest>- <batchtest todir="${build.test}" if="testcase">- <fileset dir="${src.test}" includes="**/${testcase}.java"/>- </batchtest>- </junit-->-<junitlauncher printSummary="true" haltOnFailure="true" failureProperty="tests.failed"><classpath refid="test.classpath"/><testclasses outputDir="${build.test}" unless="testcase">- <listener type="${test.junit.output.format}" sendSysOut="true" sendSysErr="true"/>- <fork dir="${basedir}">+ <listener type="legacy-plain" sendSysOut="true" sendSysErr="true"/>+ <listener type="legacy-xml" sendSysOut="true" sendSysErr="true"/>+ <fork forkMode="perTestClass">+ <jvmarg value="-Xmx1000m"/><sysproperty key="test.data" value="${build.test}/data"/><sysproperty key="test.input" value="${root}/data"/><sysproperty key="javax.xml.parsers.DocumentBuilderFactory" value="com.sun.org.apache.xerces.internal.jaxp.DocumentBuilderFactoryImpl"/>@@ -240,18 +226,19 @@</fileset></testclasses><testclasses outputDir="${build.test}" if="testcase">- <listener type="${test.junit.output.format}" sendSysOut="true" sendSysErr="true"/>- <fork dir="${basedir}">+ <listener type="legacy-plain" sendSysOut="true" sendSysErr="true"/>+ <listener type="legacy-xml" sendSysOut="true" sendSysErr="true"/>+ <fork forkMode="perTestClass">+ <jvmarg value="-Xmx1000m"/><sysproperty key="test.data" value="${build.test}/data"/><sysproperty key="test.input" value="${root}/data"/><sysproperty key="javax.xml.parsers.DocumentBuilderFactory" value="com.sun.org.apache.xerces.internal.jaxp.DocumentBuilderFactoryImpl"/></fork>- <fileset dir="${build.test}">+ <fileset dir="${basedir}"><include name="**/${testcase}.class"/></fileset></testclasses></junitlauncher>-<fail if="tests.failed">Tests failed!</fail></target>diff --git a/src/plugin/creativecommons/src/test/org/creativecommons/nutch/TestCCParseFilter.java b/src/plugin/creativecommons/src/test/org/creativecommons/nutch/TestCCParseFilter.javaindex de189683b..68f4a78d4 100644--- a/src/plugin/creativecommons/src/test/org/creativecommons/nutch/TestCCParseFilter.java+++ b/src/plugin/creativecommons/src/test/org/creativecommons/nutch/TestCCParseFilter.java@@ -22,17 +22,18 @@ import org.apache.nutch.parse.ParseUtil;import org.apache.nutch.protocol.Content;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import java.io.*;-public class TestCCParseFilter {+import static org.junit.jupiter.api.Assertions.assertEquals;++class TestCCParseFilter {private static final File testDir = new File(System.getProperty("test.input"));@Test- public void testPages() throws Exception {+ void testPages() throws Exception {pageTest(new File(testDir, "anchor.html"), "http://foo.com/","http://creativecommons.org/licenses/by-nc-sa/1.0", "a", null);// Tika returns <a> whereas parse-html returns <rel>@@ -65,8 +66,8 @@ public class TestCCParseFilter {Parse parse = new ParseUtil(conf).parse(content).get(content.getUrl());Metadata metadata = parse.getData().getParseMeta();- Assert.assertEquals(license, metadata.get("License-Url"));- Assert.assertEquals(location, metadata.get("License-Location"));- Assert.assertEquals(type, metadata.get("Work-Type"));+ assertEquals(license, metadata.get("License-Url"));+ assertEquals(location, metadata.get("License-Location"));+ assertEquals(type, metadata.get("Work-Type"));}}diff --git a/src/plugin/feed/src/test/org/apache/nutch/parse/feed/TestFeedParser.java b/src/plugin/feed/src/test/org/apache/nutch/parse/feed/TestFeedParser.javaindex 915ee54af..1ea629172 100644--- a/src/plugin/feed/src/test/org/apache/nutch/parse/feed/TestFeedParser.java+++ b/src/plugin/feed/src/test/org/apache/nutch/parse/feed/TestFeedParser.java@@ -19,8 +19,7 @@ package org.apache.nutch.parse.feed;import java.util.Iterator;import java.util.Map;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.io.Text;@@ -35,6 +34,8 @@ import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.protocol.ProtocolNotFound;import org.apache.nutch.util.NutchConfiguration;+import static org.junit.jupiter.api.Assertions.*;+/**** @author mattmann@@ -86,7 +87,7 @@ public class TestFeedParser {parseResult = new ParseUtil(conf).parseByExtensionId("feed", content);- Assert.assertEquals(3, parseResult.size());+ assertEquals(3, parseResult.size());boolean hasLink1 = false, hasLink2 = false, hasLink3 = false;@@ -102,12 +103,12 @@ public class TestFeedParser {hasLink3 = true;}- Assert.assertNotNull(entry.getValue());- Assert.assertNotNull(entry.getValue().getData());+ assertNotNull(entry.getValue());+ assertNotNull(entry.getValue().getData());}if (!hasLink1 || !hasLink2 || !hasLink3) {- Assert.fail("Outlinks read from sample rss file are not correct!");+ fail("Outlinks read from sample rss file are not correct!");}}diff --git a/src/plugin/headings/src/test/org/apache/nutch/parse/headings/TestHeadingsParseFilter.java b/src/plugin/headings/src/test/org/apache/nutch/parse/headings/TestHeadingsParseFilter.javaindex 0795a9a05..697e83858 100644--- a/src/plugin/headings/src/test/org/apache/nutch/parse/headings/TestHeadingsParseFilter.java+++ b/src/plugin/headings/src/test/org/apache/nutch/parse/headings/TestHeadingsParseFilter.java@@ -26,12 +26,13 @@ import org.apache.nutch.util.NutchConfiguration;import java.io.ByteArrayInputStream;import java.io.IOException;+import org.junit.jupiter.api.Test;import org.w3c.dom.DocumentFragment;import org.xml.sax.InputSource;import org.xml.sax.SAXException;import org.cyberneko.html.parsers.DOMFragmentParser;-import org.junit.Assert;-import org.junit.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;public class TestHeadingsParseFilter {private static Configuration conf = NutchConfiguration.create();@@ -59,9 +60,8 @@ public class TestHeadingsParseFilter {parseResult = filter.filter(content, parseResult, metaTags, node);- Assert.assertEquals(- "The h1 tag must include the content of the inner span node",- "header with span element",- parseResult.get(content.getUrl()).getData().getParseMeta().get("h1"));+ assertEquals("header with span element",+ parseResult.get(content.getUrl()).getData().getParseMeta().get("h1"),+ "The h1 tag must include the content of the inner span node");}}diff --git a/src/plugin/index-anchor/src/test/org/apache/nutch/indexer/anchor/TestAnchorIndexingFilter.java b/src/plugin/index-anchor/src/test/org/apache/nutch/indexer/anchor/TestAnchorIndexingFilter.javaindex 08a42f30b..0974b11f4 100644--- a/src/plugin/index-anchor/src/test/org/apache/nutch/indexer/anchor/TestAnchorIndexingFilter.java+++ b/src/plugin/index-anchor/src/test/org/apache/nutch/indexer/anchor/TestAnchorIndexingFilter.java@@ -25,8 +25,9 @@ import org.apache.nutch.indexer.NutchDocument;import org.apache.nutch.parse.ParseData;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit test case which tests 1. that anchor text is obtained 2. that anchor@@ -43,7 +44,7 @@ public class TestAnchorIndexingFilter {conf.setBoolean("anchorIndexingFilter.deduplicate", true);AnchorIndexingFilter filter = new AnchorIndexingFilter();filter.setConf(conf);- Assert.assertNotNull(filter);+ assertNotNull(filter);NutchDocument doc = new NutchDocument();ParseImpl parse = new ParseImpl("foo bar", new ParseData());Inlinks inlinks = new Inlinks();@@ -55,13 +56,12 @@ public class TestAnchorIndexingFilter {new CrawlDatum(), inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertTrue("test if there is an anchor at all", doc.getFieldNames()- .contains("anchor"));- Assert.assertEquals("test dedup, we expect 2", 2, doc.getField("anchor")- .getValues().size());+ assertNotNull(doc);+ assertTrue(doc.getFieldNames().contains("anchor"), "test if there is an anchor at all");+ assertEquals(2, doc.getField("anchor").getValues().size(),+ "test dedup, we expect 2");}}diff --git a/src/plugin/index-arbitrary/src/test/org/apache/nutch/indexer/arbitrary/TestArbitraryIndexingFilter.java b/src/plugin/index-arbitrary/src/test/org/apache/nutch/indexer/arbitrary/TestArbitraryIndexingFilter.javaindex f11b43fa0..413495074 100644--- a/src/plugin/index-arbitrary/src/test/org/apache/nutch/indexer/arbitrary/TestArbitraryIndexingFilter.java+++ b/src/plugin/index-arbitrary/src/test/org/apache/nutch/indexer/arbitrary/TestArbitraryIndexingFilter.java@@ -24,9 +24,10 @@ import org.apache.nutch.crawl.Inlinks;import org.apache.nutch.indexer.NutchDocument;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** Tests that the index-arbitrary filter can add a new field with an arbitrary@@ -49,7 +50,7 @@ public class TestArbitraryIndexingFilter {ArbitraryIndexingFilter filter;NutchDocument doc;- @Before+ @BeforeEachpublic void setUp() throws Exception {parse = new ParseImpl();url = new Text("http://nutch.apache.org/index.html");@@ -73,7 +74,7 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.methodName.0","getText");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testAddingNewField",filter);+ assertNotNull(filter, "No filter exists for testAddingNewField");filter.setConf(conf);doc = new NutchDocument();@@ -82,14 +83,13 @@ public class TestArbitraryIndexingFilter {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("test if doc is not empty", doc.getFieldNames()- .isEmpty());- Assert.assertTrue("test if doc has new field with arbitrary value", doc.getField("foo")- .getValues().contains("Arbitrary text to add - bar"));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(), "test if doc is not empty");+ assertTrue(doc.getField("foo").getValues().contains("Arbitrary text to add - bar"),+ "test if doc has new field with arbitrary value");}/**@@ -113,42 +113,41 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.methodArgs.1","-1,3.14");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testSupplementExistingField", filter);+ assertNotNull(filter, "No filter exists for testSupplementExistingField");filter.setConf(conf);doc = new NutchDocument();- Assert.assertNotNull("doc doesn't exist", doc);+ assertNotNull(doc, "doc doesn't exist");doc.add("description","irrational");- Assert.assertFalse("doc is empty", doc.getFieldNames().isEmpty());+ assertFalse(doc.getFieldNames().isEmpty(), "doc is empty");- Assert.assertEquals("field description does not have exactly one value", 1,- doc.getField("description").getValues().size());+ assertEquals(1, doc.getField("description").getValues().size(),+ "field description does not have exactly one value");- Assert.assertTrue("field description does not have initial value 'irrational'",- doc.getField("description").getValues().contains("irrational"));+ assertTrue(doc.getField("description").getValues().contains("irrational"),+ "field description does not have initial value 'irrational'");try {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertTrue("doc doesn't have new field with arbitrary value",- doc.getField("foo").getValues()- .contains("Arbitrary text to add - bar"));+ assertTrue(doc.getField("foo").getValues().contains("Arbitrary text to add - bar"),+ "doc doesn't have new field with arbitrary value");- Assert.assertEquals("field description does not have 2 values", 2,- doc.getField("description").getValues().size());+ assertEquals(2, doc.getField("description").getValues().size(),+ "field description does not have 2 values");- Assert.assertTrue("field description original value gone", doc.getField("description")- .getValues().contains("irrational"));+ assertTrue(doc.getField("description").getValues().contains("irrational"),+ "field description original value gone");- Assert.assertTrue("field description missing new value", doc.getField("description")- .getValues().contains("-3.14"));+ assertTrue(doc.getField("description").getValues().contains("-3.14"),+ "field description missing new value");}@@ -176,47 +175,47 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.overwrite.2","true");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testOverwritingExistingField",filter);+ assertNotNull(filter, "No filter exists for testOverwritingExistingField");filter.setConf(conf);- Assert.assertNotNull("conf does not exist",conf);+ assertNotNull(conf, "conf does not exist");doc = new NutchDocument();- Assert.assertNotNull("doc does not exist",doc);+ assertNotNull(doc, "doc does not exist");doc.add("description","irrational");doc.add("philosopher","Socrates");- Assert.assertEquals("field description does not have exactly one value", 1, doc.getField("description")- .getValues().size());+ assertEquals(1, doc.getField("description").getValues().size(),+ "field description does not have exactly one value");- Assert.assertEquals("field philosopher does not have exactly one value", 1, doc.getField("philosopher")- .getValues().size());+ assertEquals(1, doc.getField("philosopher").getValues().size(),+ "field philosopher does not have exactly one value");- Assert.assertTrue("field description does not have initial value 'irrational'", doc.getField("description")- .getValues().contains("irrational"));+ assertTrue(doc.getField("description").getValues().contains("irrational"),+ "field description does not have initial value 'irrational'");- Assert.assertTrue("field philosopher does not have initial value 'Socrates'", doc.getField("philosopher")- .getValues().contains("Socrates"));+ assertTrue(doc.getField("philosopher").getValues().contains("Socrates"),+ "field philosopher does not have initial value 'Socrates'");try {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace(System.out);- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);+ assertNotNull(doc);- Assert.assertEquals("field philosopher no longer has only one value", 1, doc.getField("philosopher")- .getValues().size());+ assertEquals(1, doc.getField("philosopher").getValues().size(),+ "field philosopher no longer has only one value");- Assert.assertFalse("field philosopher's original value 'Socrates' NOT overwritten", doc.getField("philosopher")- .getValues().contains("Socrates"));+ assertFalse(doc.getField("philosopher").getValues().contains("Socrates"),+ "field philosopher's original value 'Socrates' NOT overwritten");- Assert.assertTrue("field philosopher does not have new value 'Popeye'", doc.getField("philosopher")- .getValues().contains("Popeye"));+ assertTrue(doc.getField("philosopher").getValues().contains("Popeye"),+ "field philosopher does not have new value 'Popeye'");}/**@@ -247,34 +246,34 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.overwrite.2","true");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testProcessingFieldAfterException",filter);+ assertNotNull(filter, "No filter exists for testProcessingFieldAfterException");filter.setConf(conf);- Assert.assertNotNull("conf does not exist",conf);+ assertNotNull(conf, "conf does not exist");doc = new NutchDocument();- Assert.assertNotNull("doc does not exist",doc);+ assertNotNull(doc, "doc does not exist");try {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace(System.out);- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);+ assertNotNull(doc);- Assert.assertTrue("field foo does not have 'first added value'", doc.getField("foo")- .getValues().contains("first added value"));+ assertTrue(doc.getField("foo").getValues().contains("first added value"),+ "field foo does not have 'first added value'");- Assert.assertNull("field mangled has a value", doc.getField("mangled"));+ assertNull(doc.getField("mangled"), "field mangled has a value");- Assert.assertFalse("Value 'first added value' has leaked into field philospoher", doc.getField("philosopher")- .getValues().contains("first added value"));+ assertFalse(doc.getField("philosopher").getValues().contains("first added value"),+ "Value 'first added value' has leaked into field philospoher");- Assert.assertTrue("field philosopher does not have new value 'last added value'", doc.getField("philosopher")- .getValues().contains("last added value"));+ assertTrue(doc.getField("philosopher").getValues().contains("last added value"),+ "field philosopher does not have new value 'last added value'");}@@ -296,28 +295,28 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.overwrite.0","true");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testAddingCalculatedNewField",filter);+ assertNotNull(filter, "No filter exists for testAddingCalculatedNewField");filter.setConf(conf);doc = new NutchDocument();Double boostVal = Double.valueOf("1.0");doc.add("popularityBoost", boostVal);- Assert.assertFalse("doc is empty", doc.getFieldNames().isEmpty());- Assert.assertTrue("test if doc has new field with arbitrary value", doc.getField("popularityBoost")- .getValues().contains(boostVal));+ assertFalse(doc.getFieldNames().isEmpty(), "doc is empty");+ assertTrue(doc.getField("popularityBoost").getValues().contains(boostVal),+ "test if doc has new field with arbitrary value");try {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("doc is empty", doc.getFieldNames().isEmpty());- Assert.assertTrue("test if unfetched doc has nonzero value in popularityBoost", doc.getField("popularityBoost")- .getValues().contains(1.0));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(), "doc is empty");+ assertTrue(doc.getField("popularityBoost").getValues().contains(1.0),+ "test if unfetched doc has nonzero value in popularityBoost");inlinks.add(new Inlink("https://www.TeamSauropod.com/BullyForBrontosaurus","dinosaur"));inlinks.add(new Inlink("https://github.com/apache","source code"));@@ -329,11 +328,11 @@ public class TestArbitraryIndexingFilter {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertTrue("test if successfully fetched doc has expected value in popularityBoost", doc.getField("popularityBoost")- .getValues().contains(2.0));+ assertTrue(doc.getField("popularityBoost").getValues().contains(2.0),+ "test if successfully fetched doc has expected value in popularityBoost");}/**@@ -372,7 +371,7 @@ public class TestArbitraryIndexingFilter {conf.set("index.arbitrary.all.fields.access.3","false");filter = new ArbitraryIndexingFilter();- Assert.assertNotNull("No filter exists for testAddingNewField",filter);+ assertNotNull(filter, "No filter exists for testAddingNewField");filter.setConf(conf);doc = new NutchDocument();@@ -381,19 +380,18 @@ public class TestArbitraryIndexingFilter {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("test if doc is not empty", doc.getFieldNames()- .isEmpty());- Assert.assertTrue("test if doc still has new field with arbitrary value running with new indexer", doc.getField("foo")- .getValues().contains("Original Echo class added 'bar'"));- Assert.assertTrue("test if updated POJO created new field with arbitrary value", doc.getField("bogusSite")- .getValues().contains("https://www.updatedNutchPluginJunitTest.com"));- Assert.assertTrue("test updated POJO set new value in existing field", doc.getField("description")- .getValues().contains("-3.14"));- Assert.assertTrue("test POJO with both constructor styles supports old calls", doc.getField("summary")- .getValues().contains("1025.0"));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(), "test if doc is not empty");+ assertTrue( doc.getField("foo").getValues().contains("Original Echo class added 'bar'"),+ "test if doc still has new field with arbitrary value running with new indexer");+ assertTrue(doc.getField("bogusSite").getValues().contains("https://www.updatedNutchPluginJunitTest.com"),+ "test if updated POJO created new field with arbitrary value");+ assertTrue(doc.getField("description").getValues().contains("-3.14"),+ "test updated POJO set new value in existing field");+ assertTrue(doc.getField("summary").getValues().contains("1025.0"),+ "test POJO with both constructor styles supports old calls");}}diff --git a/src/plugin/index-basic/src/test/org/apache/nutch/indexer/basic/TestBasicIndexingFilter.java b/src/plugin/index-basic/src/test/org/apache/nutch/indexer/basic/TestBasicIndexingFilter.javaindex 3684c9907..2157f2880 100644--- a/src/plugin/index-basic/src/test/org/apache/nutch/indexer/basic/TestBasicIndexingFilter.java+++ b/src/plugin/index-basic/src/test/org/apache/nutch/indexer/basic/TestBasicIndexingFilter.java@@ -27,11 +27,12 @@ import org.apache.nutch.parse.ParseData;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import java.util.Date;+import static org.junit.jupiter.api.Assertions.*;+/*** JUnit test case which tests 1. that basic searchable fields are added to a* document 2. that domain is added as per {@code indexer.add.domain} in@@ -54,7 +55,7 @@ public class TestBasicIndexingFilter {BasicIndexingFilter filter = new BasicIndexingFilter();filter.setConf(conf);- Assert.assertNotNull(filter);+ assertNotNull(filter);NutchDocument doc = new NutchDocument();@@ -77,22 +78,21 @@ public class TestBasicIndexingFilter {crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertEquals("test title, expect \"The Foo Pa\"", "The Foo Pa", doc- .getField("title").getValues().get(0));- Assert.assertEquals("test domain, expect \"apache.org\"", "apache.org", doc- .getField("domain").getValues().get(0));- Assert.assertEquals("test host, expect \"nutch.apache.org\"",- "nutch.apache.org", doc.getField("host").getValues().get(0));- Assert.assertEquals(- "test url, expect \"http://nutch.apache.org/index.html\"",- "http://nutch.apache.org/index.html", doc.getField("url").getValues()- .get(0));- Assert.assertEquals("test content", "this is a sample foo",- doc.getField("content").getValues().get(0));- Assert.assertEquals("test fetch time", new Date(100L),- doc.getField("tstamp").getValues().get(0));+ assertNotNull(doc);+ assertEquals("The Foo Pa", doc.getField("title").getValues().get(0),+ "test title, expect \"The Foo Pa\"");+ assertEquals("apache.org", doc.getField("domain").getValues().get(0),+ "test domain, expect \"apache.org\"");+ assertEquals("nutch.apache.org", doc.getField("host").getValues().get(0),+ "test host, expect \"nutch.apache.org\"");+ assertEquals("http://nutch.apache.org/index.html",+ doc.getField("url").getValues().get(0),+ "test url, expect \"http://nutch.apache.org/index.html\"");+ assertEquals(doc.getField("content").getValues().get(0),+ "this is a sample foo", "test content");+ assertEquals(new Date(100L), doc.getField("tstamp").getValues().get(0),+ "test fetch time");}}diff --git a/src/plugin/index-jexl-filter/src/test/org/apache/nutch/indexer/jexl/TestJexlIndexingFilter.java b/src/plugin/index-jexl-filter/src/test/org/apache/nutch/indexer/jexl/TestJexlIndexingFilter.javaindex f3cc65568..e8ad16340 100644--- a/src/plugin/index-jexl-filter/src/test/org/apache/nutch/indexer/jexl/TestJexlIndexingFilter.java+++ b/src/plugin/index-jexl-filter/src/test/org/apache/nutch/indexer/jexl/TestJexlIndexingFilter.java@@ -27,14 +27,19 @@ import org.apache.nutch.parse.ParseData;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Rule;-import org.junit.Test;-import org.junit.rules.ExpectedException;+import org.junit.jupiter.api.Test;++import java.lang.invoke.MethodHandles;++import static org.junit.jupiter.api.Assertions.*;++import org.slf4j.Logger;+import org.slf4j.LoggerFactory;public class TestJexlIndexingFilter {- @Rule- public ExpectedException thrown = ExpectedException.none();++ private static final Logger LOG = LoggerFactory+ .getLogger(MethodHandles.lookup().lookupClass());@Testpublic void testAllowMatchingDocument() throws Exception {@@ -43,7 +48,7 @@ public class TestJexlIndexingFilter {JexlIndexingFilter filter = new JexlIndexingFilter();filter.setConf(conf);- Assert.assertNotNull(filter);+ assertNotNull(filter);NutchDocument doc = new NutchDocument();@@ -66,8 +71,8 @@ public class TestJexlIndexingFilter {NutchDocument result = filter.filter(doc, parse,new Text("http://nutch.apache.org/index.html"), crawlDatum, inlinks);- Assert.assertNotNull(result);- Assert.assertEquals(doc, result);+ assertNotNull(result);+ assertEquals(doc, result);}@Test@@ -77,7 +82,7 @@ public class TestJexlIndexingFilter {JexlIndexingFilter filter = new JexlIndexingFilter();filter.setConf(conf);- Assert.assertNotNull(filter);+ assertNotNull(filter);NutchDocument doc = new NutchDocument();@@ -100,16 +105,21 @@ public class TestJexlIndexingFilter {NutchDocument result = filter.filter(doc, parse,new Text("http://nutch.apache.org/index.html"), crawlDatum, inlinks);- Assert.assertNull(result);+ assertNull(result);}@Testpublic void testMissingConfiguration() throws Exception {Configuration conf = NutchConfiguration.create();-JexlIndexingFilter filter = new JexlIndexingFilter();- thrown.expect(RuntimeException.class);- filter.setConf(conf);+ Exception exception = assertThrows(RuntimeException.class, () -> {+ filter.setConf(conf);+ });+ String expectedMessage = "The property index.jexl.filter must have a " ++ "value when index-jexl-filter is used. You can use 'true' or 'false' " ++ "to index all/none";+ String actualMessage = exception.getMessage();+ assertTrue(actualMessage.contains(expectedMessage));}@Test@@ -118,7 +128,11 @@ public class TestJexlIndexingFilter {conf.set("index.jexl.filter", "doc.lang=<>:='en'");JexlIndexingFilter filter = new JexlIndexingFilter();- thrown.expect(RuntimeException.class);- filter.setConf(conf);+ Exception exception = assertThrows(RuntimeException.class, () -> {+ filter.setConf(conf);+ });+ String expectedMessage = "Failed parsing JEXL from index.jexl.filter";+ String actualMessage = exception.getMessage();+ assertTrue(actualMessage.contains(expectedMessage));}}diff --git a/src/plugin/index-links/src/test/org/apache/nutch/indexer/links/TestLinksIndexingFilter.java b/src/plugin/index-links/src/test/org/apache/nutch/indexer/links/TestLinksIndexingFilter.javaindex 0f8b660b7..a36207973 100644--- a/src/plugin/index-links/src/test/org/apache/nutch/indexer/links/TestLinksIndexingFilter.java+++ b/src/plugin/index-links/src/test/org/apache/nutch/indexer/links/TestLinksIndexingFilter.java@@ -31,19 +31,20 @@ import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import java.net.URL;+import static org.junit.jupiter.api.Assertions.assertEquals;+public class TestLinksIndexingFilter {Configuration conf = NutchConfiguration.create();LinksIndexingFilter filter = new LinksIndexingFilter();Metadata metadata = new Metadata();- @Before+ @BeforeEachpublic void setUp() throws Exception {metadata.add(Response.CONTENT_TYPE, "text/html");}@@ -79,10 +80,10 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", outlinks, metadata)),new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());- Assert.assertEquals(1, doc.getField("outlinks").getValues().size());+ assertEquals(1, doc.getField("outlinks").getValues().size());- Assert.assertEquals("Filter outlinks, allow only those from a different host",- outlinks[0].getToUrl(), doc.getFieldValue("outlinks"));+ assertEquals(outlinks[0].getToUrl(), doc.getFieldValue("outlinks"),+ "Filter outlinks, allow only those from a different host");}@Test@@ -98,10 +99,10 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", new Outlink[0], metadata)),new Text("http://www.example.com/"), new CrawlDatum(), inlinks);- Assert.assertEquals(1, doc.getField("inlinks").getValues().size());+ assertEquals(1, doc.getField("inlinks").getValues().size());- Assert.assertEquals("Filter inlinks, allow only those from a different host",- "http://www.test.com", doc.getFieldValue("inlinks"));+ assertEquals("http://www.test.com", doc.getFieldValue("inlinks"),+ "Filter inlinks, allow only those from a different host");}@Test@@ -114,8 +115,8 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", outlinks, metadata)),new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());- Assert.assertEquals("All outlinks must be indexed even those from the same host",- outlinks.length, doc.getField("outlinks").getValues().size());+ assertEquals(outlinks.length, doc.getField("outlinks").getValues().size(),+ "All outlinks must be indexed even those from the same host");}@Test@@ -131,8 +132,8 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", new Outlink[0], metadata)),new Text("http://www.example.com/"), new CrawlDatum(), inlinks);- Assert.assertEquals("All inlinks must be indexed even those from the same host",- inlinks.size(), doc.getField("inlinks").getValues().size());+ assertEquals(inlinks.size(), doc.getField("inlinks").getValues().size(),+ "All inlinks must be indexed even those from the same host");}@Test@@ -156,16 +157,16 @@ public class TestLinksIndexingFilter {NutchField docOutlinks = doc.getField("outlinks");- Assert.assertEquals("Only the host portion of the outlink URL must be indexed",- new URL("http://www.test.com").getHost(),- docOutlinks.getValues().get(0));+ assertEquals(new URL("http://www.test.com").getHost(),+ docOutlinks.getValues().get(0),+ "Only the host portion of the outlink URL must be indexed");- Assert.assertEquals(- "The inlinks coming from the same host must count only once", 1,- doc.getField("inlinks").getValues().size());+ assertEquals(1, doc.getField("inlinks").getValues().size(),+ "The inlinks coming from the same host must count only once");- Assert.assertEquals("Only the host portion of the inlinks URL must be indexed",- new URL("http://www.test.com").getHost(), doc.getFieldValue("inlinks"));+ assertEquals(new URL("http://www.test.com").getHost(),+ doc.getFieldValue("inlinks"),+ "Only the host portion of the inlinks URL must be indexed");}@Test@@ -182,12 +183,11 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", outlinks, metadata)),new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());- Assert.assertEquals(1, doc.getField("outlinks").getValues().size());+ assertEquals(1, doc.getField("outlinks").getValues().size());- Assert.assertEquals(- "Index only the host portion of the outlinks after filtering",- new URL("http://www.test.com").getHost(),- doc.getFieldValue("outlinks"));+ assertEquals(new URL("http://www.test.com").getHost(),+ doc.getFieldValue("outlinks"),+ "Index only the host portion of the outlinks after filtering");}@Test@@ -206,12 +206,11 @@ public class TestLinksIndexingFilter {new ParseData(new ParseStatus(), "title", new Outlink[0], metadata)),new Text("http://www.example.com/"), new CrawlDatum(), inlinks);- Assert.assertEquals(1, doc.getField("inlinks").getValues().size());+ assertEquals(1, doc.getField("inlinks").getValues().size());- Assert.assertEquals(- "Index only the host portion of the inlinks after filtering",- new URL("http://www.test.com").getHost(),- doc.getFieldValue("inlinks"));+ assertEquals(new URL("http://www.test.com").getHost(),+ doc.getFieldValue("inlinks"),+ "Index only the host portion of the inlinks after filtering");}}diff --git a/src/plugin/index-more/src/test/org/apache/nutch/indexer/more/TestMoreIndexingFilter.java b/src/plugin/index-more/src/test/org/apache/nutch/indexer/more/TestMoreIndexingFilter.javaindex 5a22cf6de..4ff496c5a 100644--- a/src/plugin/index-more/src/test/org/apache/nutch/indexer/more/TestMoreIndexingFilter.java+++ b/src/plugin/index-more/src/test/org/apache/nutch/indexer/more/TestMoreIndexingFilter.java@@ -32,8 +32,9 @@ import org.apache.nutch.parse.ParseData;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;public class TestMoreIndexingFilter {@@ -59,7 +60,7 @@ public class TestMoreIndexingFilter {conf.setBoolean("moreIndexingFilter.indexMimeTypeParts", false);MoreIndexingFilter filter = new MoreIndexingFilter();filter.setConf(conf);- Assert.assertNotNull(filter);+ assertNotNull(filter);NutchDocument doc = new NutchDocument();ParseImpl parse = new ParseImpl("foo bar", new ParseData());@@ -68,12 +69,12 @@ public class TestMoreIndexingFilter {new CrawlDatum(), new Inlinks());} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertTrue(doc.getFieldNames().contains("type"));- Assert.assertEquals(1, doc.getField("type").getValues().size());- Assert.assertEquals("text/html", doc.getFieldValue("type"));+ assertNotNull(doc);+ assertTrue(doc.getFieldNames().contains("type"));+ assertEquals(1, doc.getField("type").getValues().size());+ assertEquals("text/html", doc.getFieldValue("type"));}@Test@@ -92,21 +93,21 @@ public class TestMoreIndexingFilter {NutchDocument doc = new NutchDocument();doc = filter.filter(doc, parseImpl, url, new CrawlDatum(), new Inlinks());- Assert.assertEquals("content-disposition not detected", "filename.ext",- doc.getFieldValue("title"));+ assertEquals("filename.ext", doc.getFieldValue("title"),+ "content-disposition not detected");/* NUTCH-1140: do not add second title to avoid a multi-valued title field */doc = new NutchDocument();doc.add("title", "title");doc = filter.filter(doc, parseImpl, url, new CrawlDatum(), new Inlinks());- Assert.assertEquals("do not add second title by content-disposition",- "title", doc.getFieldValue("title"));+ assertEquals("title", doc.getFieldValue("title"),+ "do not add second title by content-disposition");}private void assertParts(String[] parts, int count, String... expected) {- Assert.assertEquals(count, parts.length);+ assertEquals(count, parts.length);for (int i = 0; i < expected.length; i++) {- Assert.assertEquals(expected[i], parts[i]);+ assertEquals(expected[i], parts[i]);}}@@ -120,8 +121,8 @@ public class TestMoreIndexingFilter {"text", new ParseData(new ParseStatus(), "title", new Outlink[0],metadata)), new Text("http://www.example.com/"), new CrawlDatum(),new Inlinks());- Assert.assertEquals("mime type not detected", expected,- doc.getFieldValue("type"));+ assertEquals(expected, doc.getFieldValue("type"),+ "mime type not detected");}@Test@@ -148,8 +149,8 @@ public class TestMoreIndexingFilter {doc = filter.filter(doc, parseImpl, url, fetchDatum, new Inlinks());- Assert.assertEquals("last fetch date not extracted",- new Date(dateEpocheSeconds * 1000), doc.getFieldValue("date"));+ assertEquals(new Date(dateEpocheSeconds * 1000),+ doc.getFieldValue("date"), "last fetch date not extracted");// set last-modified time (7 days before fetch time)Date lastModifiedDate = new Date(@@ -158,7 +159,7 @@ public class TestMoreIndexingFilter {parseImpl.getData().getParseMeta().set(Metadata.LAST_MODIFIED, lastModifiedDateStr);doc = filter.filter(doc, parseImpl, url, fetchDatum, new Inlinks());- Assert.assertEquals("last-modified date not extracted", lastModifiedDate,- doc.getFieldValue("lastModified"));+ assertEquals(lastModifiedDate, doc.getFieldValue("lastModified"),+ "last-modified date not extracted");}}diff --git a/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java b/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.javaindex fcd8cb5c8..0e48cee0e 100644--- a/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java+++ b/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java@@ -29,8 +29,9 @@ import org.apache.nutch.protocol.Content;import org.apache.nutch.protocol.Protocol;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit tests for the <code>index-replace</code> plugin.@@ -65,15 +66,15 @@ public class TestIndexReplace {BasicIndexingFilter basicIndexer = new BasicIndexingFilter();basicIndexer.setConf(conf);- Assert.assertNotNull(basicIndexer);+ assertNotNull(basicIndexer);MetadataIndexer metaIndexer = new MetadataIndexer();metaIndexer.setConf(conf);- Assert.assertNotNull(basicIndexer);+ assertNotNull(basicIndexer);ReplaceIndexer replaceIndexer = new ReplaceIndexer();replaceIndexer.setConf(conf);- Assert.assertNotNull(replaceIndexer);+ assertNotNull(replaceIndexer);try {String urlString = "file:" + sampleDir + fileSeparator + fileName;@@ -91,7 +92,7 @@ public class TestIndexReplace {doc = replaceIndexer.filter(doc, parse, text, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.toString());+ fail(e.toString());}return doc;@@ -121,14 +122,14 @@ public class TestIndexReplace {try {rp.setConf(conf);} catch (RuntimeException ohno) {- Assert.fail("Unable to parse a valid index.replace.regexp property! "+ fail("Unable to parse a valid index.replace.regexp property! "+ ohno.getMessage());}Configuration parsedConf = rp.getConf();// Does the getter equal the setter? Too easy!- Assert.assertEquals(indexReplaceProperty,+ assertEquals(indexReplaceProperty,parsedConf.get(INDEX_REPLACE_PROPERTY));}@@ -160,11 +161,10 @@ public class TestIndexReplace {// Run the document through the parser and index filters.NutchDocument doc = parseAndFilterFile(sampleFile, conf);- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}/**@@ -199,11 +199,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Assert that our metatags have not changed.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}@@ -234,11 +233,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Assert that our metatags have changed.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}@@ -271,11 +269,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Assert that our metatags have not changed.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}@@ -310,11 +307,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Assert that our metatags have changed.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}@@ -349,11 +345,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Assert that description has changed and the others have not changed.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));- Assert- .assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));- Assert.assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));+ assertEquals(expectedKeywords, doc.getFieldValue("metatag.keywords"));+ assertEquals(expectedAuthor, doc.getFieldValue("metatag.author"));}/**@@ -386,7 +381,7 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Check that the value produced by the last replacement has worked.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));}@@ -417,7 +412,7 @@ public class TestIndexReplace {// Check that the value produced by the case-insensitive replacement has// worked.- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));}@@ -446,10 +441,10 @@ public class TestIndexReplace {NutchDocument doc = parseAndFilterFile(sampleFile, conf);// Check that the input field has not been modified- Assert.assertEquals(expectedDescription,+ assertEquals(expectedDescription,doc.getFieldValue("metatag.description"));// Check that the output field has created- Assert.assertEquals(expectedTargetDescription,+ assertEquals(expectedTargetDescription,doc.getFieldValue("new"));}}diff --git a/src/plugin/index-static/src/test/org/apache/nutch/indexer/staticfield/TestStaticFieldIndexerTest.java b/src/plugin/index-static/src/test/org/apache/nutch/indexer/staticfield/TestStaticFieldIndexerTest.javaindex 42cd46dea..6d190b387 100644--- a/src/plugin/index-static/src/test/org/apache/nutch/indexer/staticfield/TestStaticFieldIndexerTest.java+++ b/src/plugin/index-static/src/test/org/apache/nutch/indexer/staticfield/TestStaticFieldIndexerTest.java@@ -23,9 +23,10 @@ import org.apache.nutch.crawl.Inlinks;import org.apache.nutch.indexer.NutchDocument;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit test case which tests 1. that static data fields are added to a@@ -46,7 +47,7 @@ public class TestStaticFieldIndexerTest {Text url;StaticFieldIndexer filter;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();parse = new ParseImpl();@@ -64,7 +65,7 @@ public class TestStaticFieldIndexerTest {@Testpublic void testEmptyIndexStatic() throws Exception {- Assert.assertNotNull(filter);+ assertNotNull(filter);filter.setConf(conf);NutchDocument doc = new NutchDocument();@@ -73,12 +74,12 @@ public class TestStaticFieldIndexerTest {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertTrue("tests if no field is set for empty index.static", doc- .getFieldNames().isEmpty());+ assertNotNull(doc);+ assertTrue(doc.getFieldNames().isEmpty(),+ "tests if no field is set for empty index.static");}/**@@ -91,7 +92,7 @@ public class TestStaticFieldIndexerTest {conf.set("index.static","field1:val1, field2 : val2 val3 , field3, field4 :val4 , ");- Assert.assertNotNull(filter);+ assertNotNull(filter);filter.setConf(conf);NutchDocument doc = new NutchDocument();@@ -100,20 +101,20 @@ public class TestStaticFieldIndexerTest {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("test if doc is not empty", doc.getFieldNames()- .isEmpty());- Assert.assertEquals("test if doc has 3 fields", 3, doc.getFieldNames()- .size());- Assert.assertTrue("test if doc has field1", doc.getField("field1")- .getValues().contains("val1"));- Assert.assertTrue("test if doc has field2", doc.getField("field2")- .getValues().contains("val2"));- Assert.assertTrue("test if doc has field4", doc.getField("field4")- .getValues().contains("val4"));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(),+ "test if doc is not empty");+ assertEquals(3, doc.getFieldNames().size(),+ "test if doc has 3 fields");+ assertTrue(doc.getField("field1").getValues().contains("val1"),+ "test if doc has field1");+ assertTrue(doc.getField("field2").getValues().contains("val2"),+ "test if doc has field2");+ assertTrue(doc.getField("field4").getValues().contains("val4"),+ "test if doc has field4");}/**@@ -129,7 +130,7 @@ public class TestStaticFieldIndexerTest {conf.set("index.static.valuesep", "|");conf.set("index.static","field1=val1>field2 = val2|val3 >field3>field4 =val4 > ");- Assert.assertNotNull(filter);+ assertNotNull(filter);filter.setConf(conf);NutchDocument doc = new NutchDocument();@@ -138,20 +139,20 @@ public class TestStaticFieldIndexerTest {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("test if doc is not empty", doc.getFieldNames()- .isEmpty());- Assert.assertEquals("test if doc has 3 fields", 3, doc.getFieldNames()- .size());- Assert.assertTrue("test if doc has field1", doc.getField("field1")- .getValues().contains("val1"));- Assert.assertTrue("test if doc has field2", doc.getField("field2")- .getValues().contains("val2"));- Assert.assertTrue("test if doc has field4", doc.getField("field4")- .getValues().contains("val4"));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(),+ "test if doc is not empty");+ assertEquals(3, doc.getFieldNames().size(),+ "test if doc has 3 fields");+ assertTrue(doc.getField("field1").getValues().contains("val1"),+ "test if doc has field1");+ assertTrue(doc.getField("field2").getValues().contains("val2"),+ "test if doc has field2");+ assertTrue(doc.getField("field4").getValues().contains("val4"),+ "test if doc has field4");}/**@@ -167,7 +168,7 @@ public class TestStaticFieldIndexerTest {conf.set("index.static.valuesep", "***");conf.set("index.static", "field1\t\tval1\n\n" + "field2\t\tval2***val3\n\n"+ "field3\n\n" + "field4\t\tval4\n\n\n\n");- Assert.assertNotNull(filter);+ assertNotNull(filter);filter.setConf(conf);NutchDocument doc = new NutchDocument();@@ -176,19 +177,19 @@ public class TestStaticFieldIndexerTest {filter.filter(doc, parse, url, crawlDatum, inlinks);} catch (Exception e) {e.printStackTrace();- Assert.fail(e.getMessage());+ fail(e.getMessage());}- Assert.assertNotNull(doc);- Assert.assertFalse("test if doc is not empty", doc.getFieldNames()- .isEmpty());- Assert.assertEquals("test if doc has 3 fields", 3, doc.getFieldNames()- .size());- Assert.assertTrue("test if doc has field1", doc.getField("field1")- .getValues().contains("val1"));- Assert.assertTrue("test if doc has field2", doc.getField("field2")- .getValues().contains("val2"));- Assert.assertTrue("test if doc has field4", doc.getField("field4")- .getValues().contains("val4"));+ assertNotNull(doc);+ assertFalse(doc.getFieldNames().isEmpty(),+ "test if doc is not empty");+ assertEquals(3, doc.getFieldNames().size(),+ "test if doc has 3 fields");+ assertTrue(doc.getField("field1").getValues().contains("val1"),+ "test if doc has field1");+ assertTrue(doc.getField("field2").getValues().contains("val2"),+ "test if doc has field2");+ assertTrue(doc.getField("field4").getValues().contains("val4"),+ "test if doc has field4");}}diff --git a/src/plugin/indexer-csv/src/test/org/apache/nutch/indexwriter/csv/TestCSVIndexWriter.java b/src/plugin/indexer-csv/src/test/org/apache/nutch/indexwriter/csv/TestCSVIndexWriter.javaindex 5714cc235..bb9f21229 100644--- a/src/plugin/indexer-csv/src/test/org/apache/nutch/indexwriter/csv/TestCSVIndexWriter.java+++ b/src/plugin/indexer-csv/src/test/org/apache/nutch/indexwriter/csv/TestCSVIndexWriter.java@@ -16,9 +16,6 @@*/package org.apache.nutch.indexwriter.csv;-import static org.junit.Assert.assertEquals;-import static org.junit.Assert.assertTrue;-import java.io.ByteArrayOutputStream;import java.io.IOException;import java.io.UnsupportedEncodingException;@@ -32,10 +29,13 @@ import org.apache.hadoop.fs.FileSystem;import org.apache.nutch.indexer.IndexWriterParams;import org.apache.nutch.indexer.NutchDocument;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;+/*** Test CSVIndexWriter. Focus is on CSV-specific potential issues, mainly quoting and escaping.*/@@ -126,8 +126,8 @@ public class TestCSVIndexWriter {"Apache Nutch is an open source web-search software project. ..." };String csv = getCSV(new String[0], fields);for (int i = 0; i < fields.length; i += 2) {- assertTrue("Testing field " + i + " (" + fields[i] + ")",- csv.contains(fields[i + 1]));+ assertTrue(csv.contains(fields[i + 1]),+ "Testing field " + i + " (" + fields[i] + ")");}}@@ -136,8 +136,8 @@ public class TestCSVIndexWriter {String[] params = { CSVConstants.CSV_FIELDS, "test,test2" };String[] fields = { "test", "a,b", "test2", "c,d" };String csv = getCSV(params, fields);- assertEquals("If field contains a fields separator, it must be quoted",- "\"a,b\",\"c,d\"", csv.trim());+ assertEquals("\"a,b\",\"c,d\"", csv.trim(),+ "If field contains a fields separator, it must be quoted");}@Test@@ -145,8 +145,8 @@ public class TestCSVIndexWriter {String[] params = { CSVConstants.CSV_FIELDS, "test" };String[] fields = { "test", "a\nb" };String csv = getCSV(params, fields);- assertEquals("If field contains a fields separator, it must be quoted",- "\"a\nb\"", csv.trim());+ assertEquals("\"a\nb\"", csv.trim(),+ "If field contains a fields separator, it must be quoted");}@Test@@ -154,8 +154,8 @@ public class TestCSVIndexWriter {String[] params = { CSVConstants.CSV_FIELDS, "test" };String[] fields = { "test", "a,b:\"quote\",c" };String csv = getCSV(params, fields);- assertEquals("Quotes inside a quoted field must be escaped",- "\"a,b:\"\"quote\"\",c\"", csv.trim());+ assertEquals("\"a,b:\"\"quote\"\",c\"", csv.trim(),+ "Quotes inside a quoted field must be escaped");}@Test@@ -163,8 +163,8 @@ public class TestCSVIndexWriter {String[] params = { CSVConstants.CSV_FIELDS, "test" };String[] fields = { "test", "\"quote\"" };String csv = getCSV(params, fields);- assertEquals("Leading quotes inside a quoted field must be escaped",- "\"\"\"quote\"\"\"", csv.trim());+ assertEquals("\"\"\"quote\"\"\"", csv.trim(),+ "Leading quotes inside a quoted field must be escaped");}@Test@@ -173,7 +173,8 @@ public class TestCSVIndexWriter {CSVConstants.CSV_MAXFIELDLENGTH, "8" };String[] fields = { "test", "0123456789" };String csv = getCSV(params, fields);- assertEquals("Field clipped to max. length = 8", "01234567", csv.trim());+ assertEquals("01234567", csv.trim(),+ "Field clipped to max. length = 8");}@Test@@ -182,8 +183,8 @@ public class TestCSVIndexWriter {CSVConstants.CSV_MAXFIELDLENGTH, "7" };String[] fields = { "test", "1,\"2\",3,\"4\"" };String csv = getCSV(params, fields);- assertEquals("Field clipped to max. length = 7", "\"1,\"\"2\"\",3\"",- csv.trim());+ assertEquals( "\"1,\"\"2\"\",3\"", csv.trim(),+ "Field clipped to max. length = 7");}@Test@@ -193,8 +194,8 @@ public class TestCSVIndexWriter {CSVConstants.CSV_QUOTECHARACTER, "" };String[] fields = { "test", "abc", "test", "def" };String csv = getCSV(params, fields);- assertEquals("Values of multi-value fields are concatenated by |",- "abc|def", csv.trim());+ assertEquals("abc|def", csv.trim(),+ "Values of multi-value fields are concatenated by |");}@Test@@ -211,7 +212,7 @@ public class TestCSVIndexWriter {CSVConstants.CSV_CHARSET, charset };String[] fields = { "test", test };String csv = getCSV(params, fields);- assertEquals("wrong charset conversion", test, csv.trim());+ assertEquals( test, csv.trim(), "wrong charset conversion");}}@@ -225,8 +226,8 @@ public class TestCSVIndexWriter {};String[] fields = { "test", "abc", "test", "def" };String csv = getCSV(params, fields);- assertEquals("Values of multi-value fields are concatenated by ¦",- "abc\u00a6def", csv.trim());+ assertEquals("abc\u00a6def", csv.trim(),+ "Values of multi-value fields are concatenated by ¦");}@Test@@ -247,8 +248,8 @@ public class TestCSVIndexWriter {docs[1].add("3", "C");String csv = getCSV(params, docs);String[] records = csv.trim().split("\\r\\n");- assertEquals("tab-separated output", "a|b\ta\"2\"b\tc,d", records[0]);- assertEquals("tab-separated output", "A\tB\tC", records[1]);+ assertEquals("a|b\ta\"2\"b\tc,d", records[0], "tab-separated output");+ assertEquals( "A\tB\tC", records[1], "tab-separated output");}@Test@@ -259,7 +260,7 @@ public class TestCSVIndexWriter {docs[0] = new NutchDocument();docs[0].add("date", new Date(0)); // 1970-01-01String csv = getCSV(params, docs);- assertTrue("date conversion", csv.contains("1970"));+ assertTrue(csv.contains("1970"), "date conversion");}}diff --git a/src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/TestHTMLLanguageParser.java b/src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/TestHTMLLanguageParser.javaindex 97be1408e..e664e221b 100644--- a/src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/TestHTMLLanguageParser.java+++ b/src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/TestHTMLLanguageParser.java@@ -26,8 +26,10 @@ import org.apache.nutch.parse.Parse;import org.apache.nutch.parse.ParseUtil;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.fail;public class TestHTMLLanguageParser {@@ -55,12 +57,12 @@ public class TestHTMLLanguageParser {for (int t = 0; t < docs.length; t++) {Content content = getContent(docs[t]);Parse parse = parser.parse(content).get(content.getUrl());- Assert.assertEquals(metalanguages[t], (String) parse.getData()+ assertEquals(metalanguages[t], (String) parse.getData().getParseMeta().get(Metadata.LANGUAGE));}} catch (Exception e) {e.printStackTrace(System.out);- Assert.fail(e.toString());+ fail(e.toString());}}@@ -89,7 +91,7 @@ public class TestHTMLLanguageParser {{ "torp, stuga, uthyres, bed & breakfast", null } };for (int i = 0; i < 44; i++) {- Assert.assertEquals(tests[i][1],+ assertEquals(tests[i][1],HTMLLanguageParser.LanguageParser.parseLanguage(tests[i][0]));}}@@ -124,7 +126,7 @@ public class TestHTMLLanguageParser {testLine = testLine.trim();if (testLine.length() > 256) {lang = identifier.identifyLanguage(testLine);- Assert.assertEquals(tokens[1], lang);+ assertEquals(tokens[1], lang);}}testFile.close();@@ -136,7 +138,7 @@ public class TestHTMLLanguageParser {lang = identifier.identifyLanguage(content);System.out.println(lang);total += System.currentTimeMillis() - start;- Assert.assertEquals(tokens[1], lang);+ assertEquals(tokens[1], lang);}}in.close();diff --git a/src/plugin/lib-http/src/test/org/apache/nutch/protocol/http/api/TestRobotRulesParser.java b/src/plugin/lib-http/src/test/org/apache/nutch/protocol/http/api/TestRobotRulesParser.javaindex 202d2d08b..20049d2fc 100644--- a/src/plugin/lib-http/src/test/org/apache/nutch/protocol/http/api/TestRobotRulesParser.java+++ b/src/plugin/lib-http/src/test/org/apache/nutch/protocol/http/api/TestRobotRulesParser.java@@ -18,11 +18,13 @@ package org.apache.nutch.protocol.http.api;import java.util.Set;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import crawlercommons.robots.BaseRobotRules;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;+/*** JUnit test case which tests* <ol>@@ -100,10 +102,9 @@ public class TestRobotRulesParser {boolean[] results) {for (int counter = 0; counter < paths.length; counter++) {boolean res = rules.isAllowed(paths[counter]);- Assert.assertTrue(- "testing on agent (" + agent + "), and " + "path " + paths[counter]- + " got " + res + ", expected " + results[counter],- res == results[counter]);+ assertEquals(res, results[counter],+ "testing on agent (" + agent + "), and " + "path " ++ paths[counter] + " got " + res + ", expected " + results[counter]);}}@@ -137,21 +138,21 @@ public class TestRobotRulesParser {// returned by the parserrules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, Set.of(SINGLE_AGENT1.toLowerCase()));- Assert.assertTrue("testing crawl delay for agent " + SINGLE_AGENT1 + " : ",- (rules.getCrawlDelay() == 10000));+ assertTrue((rules.getCrawlDelay() == 10000),+ "testing crawl delay for agent " + SINGLE_AGENT1 + " : ");// for SINGLE_AGENT2, the crawl delay of 20 seconds, i.e. 20000 msec must be// returned by the parserrules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, Set.of(SINGLE_AGENT2.toLowerCase()));- Assert.assertTrue("testing crawl delay for agent " + SINGLE_AGENT2 + " : ",- (rules.getCrawlDelay() == 20000));+ assertTrue((rules.getCrawlDelay() == 20000),+ "testing crawl delay for agent " + SINGLE_AGENT2 + " : ");// for UNKNOWN_AGENT, the default crawl delay must be returned.rules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, Set.of(UNKNOWN_AGENT.toLowerCase()));- Assert.assertTrue("testing crawl delay for agent " + UNKNOWN_AGENT + " : ",- (rules.getCrawlDelay() == Long.MIN_VALUE));+ assertTrue((rules.getCrawlDelay() == Long.MIN_VALUE),+ "testing crawl delay for agent " + UNKNOWN_AGENT + " : ");}/**@@ -186,20 +187,20 @@ public class TestRobotRulesParser {// returned by the parserrules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, SINGLE_AGENT1);- Assert.assertTrue("testing crawl delay for agent " + SINGLE_AGENT1 + " : ",- (rules.getCrawlDelay() == 10000));+ assertTrue((rules.getCrawlDelay() == 10000),+ "testing crawl delay for agent " + SINGLE_AGENT1 + " : ");// for SINGLE_AGENT2, the crawl delay of 20 seconds, i.e. 20000 msec must be// returned by the parserrules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, SINGLE_AGENT2);- Assert.assertTrue("testing crawl delay for agent " + SINGLE_AGENT2 + " : ",- (rules.getCrawlDelay() == 20000));+ assertTrue((rules.getCrawlDelay() == 20000),+ "testing crawl delay for agent " + SINGLE_AGENT2 + " : ");// for UNKNOWN_AGENT, the default crawl delay must be returned.rules = parser.parseRules("testCrawlDelay", ROBOTS_STRING.getBytes(),CONTENT_TYPE, UNKNOWN_AGENT);- Assert.assertTrue("testing crawl delay for agent " + UNKNOWN_AGENT + " : ",- (rules.getCrawlDelay() == Long.MIN_VALUE));+ assertTrue((rules.getCrawlDelay() == Long.MIN_VALUE),+ "testing crawl delay for agent " + UNKNOWN_AGENT + " : ");}}diff --git a/src/plugin/lib-regex-filter/src/test/org/apache/nutch/urlfilter/api/RegexURLFilterBaseTest.java b/src/plugin/lib-regex-filter/src/test/org/apache/nutch/urlfilter/api/RegexURLFilterBaseTest.javaindex 080b2e587..3f20f28ef 100644--- a/src/plugin/lib-regex-filter/src/test/org/apache/nutch/urlfilter/api/RegexURLFilterBaseTest.java+++ b/src/plugin/lib-regex-filter/src/test/org/apache/nutch/urlfilter/api/RegexURLFilterBaseTest.java@@ -26,12 +26,13 @@ import java.util.List;import java.util.concurrent.TimeUnit;import org.apache.commons.lang3.time.StopWatch;-import org.junit.Assert;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.apache.nutch.net.URLFilter;+import static org.junit.jupiter.api.Assertions.*;+/*** JUnit based test of class <code>RegexURLFilterBase</code>.*@@ -53,7 +54,7 @@ public abstract class RegexURLFilterBaseTest {bench(loops, new FileReader(SAMPLES + SEPARATOR + file + ".rules"),new FileReader(SAMPLES + SEPARATOR + file + ".urls"));} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}}@@ -67,7 +68,7 @@ public abstract class RegexURLFilterBaseTest {test(filter, expected);}} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}stopWatch.stop();LOG.info("bench time {} loops {} ms", loops, stopWatch.getTime(TimeUnit.MILLISECONDS));@@ -78,7 +79,7 @@ public abstract class RegexURLFilterBaseTest {bench(loops, new FileReader(SAMPLES + SEPARATOR + rulesFile),new FileReader(SAMPLES + SEPARATOR + urlsFile));} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}}@@ -87,7 +88,7 @@ public abstract class RegexURLFilterBaseTest {test(new FileReader(SAMPLES + SEPARATOR + rulesFile),new FileReader(SAMPLES + SEPARATOR + urlsFile));} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}}@@ -96,7 +97,7 @@ public abstract class RegexURLFilterBaseTest {test(new FileReader(SAMPLES + SEPARATOR + file + ".rules"),new FileReader(SAMPLES + SEPARATOR + file + ".urls"));} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}}@@ -104,7 +105,7 @@ public abstract class RegexURLFilterBaseTest {try {test(getURLFilter(rules), readURLFile(urls));} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}}@@ -112,9 +113,9 @@ public abstract class RegexURLFilterBaseTest {for (int i = 0; i < expected.length; i++) {String result = filter.filter(expected[i].url);if (result != null) {- Assert.assertTrue(expected[i].url, expected[i].sign);+ assertTrue(expected[i].sign, expected[i].url);} else {- Assert.assertFalse(expected[i].url, expected[i].sign);+ assertFalse(expected[i].sign, expected[i].url);}}}diff --git a/src/plugin/mimetype-filter/src/test/org/apache/nutch/indexer/filter/MimeTypeIndexingFilterTest.java b/src/plugin/mimetype-filter/src/test/org/apache/nutch/indexer/filter/MimeTypeIndexingFilterTest.javaindex 28b9f401f..6f2be4cf8 100644--- a/src/plugin/mimetype-filter/src/test/org/apache/nutch/indexer/filter/MimeTypeIndexingFilterTest.java+++ b/src/plugin/mimetype-filter/src/test/org/apache/nutch/indexer/filter/MimeTypeIndexingFilterTest.java@@ -29,9 +29,10 @@ import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit based tests of class@@ -45,7 +46,7 @@ public class MimeTypeIndexingFilterTest {private String[] MIME_TYPES = { "text/html", "image/png", "application/pdf" };private ParseImpl[] parses = new ParseImpl[MIME_TYPES.length];- @Before+ @BeforeEachpublic void setUp() throws Exception {for (int i = 0; i < MIME_TYPES.length; i++) {Metadata metadata = new Metadata();@@ -61,9 +62,10 @@ public class MimeTypeIndexingFilterTest {@Testpublic void testMissingConfigFile() throws Exception {String file = conf.get(MimeTypeIndexingFilter.MIMEFILTER_REGEX_FILE, "");- Assert.assertEquals(String- .format("Property %s must not be present in the the configuration file",- MimeTypeIndexingFilter.MIMEFILTER_REGEX_FILE), "", file);+ assertEquals("", file,+ String+ .format("Property %s must not be present in the the configuration file",+ MimeTypeIndexingFilter.MIMEFILTER_REGEX_FILE));filter.setConf(conf);@@ -72,7 +74,7 @@ public class MimeTypeIndexingFilterTest {NutchDocument doc = filter.filter(new NutchDocument(), parses[i],new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());- Assert.assertNotNull("All documents must be allowed by default", doc);+ assertNotNull(doc, "All documents must be allowed by default");}}@@ -86,9 +88,9 @@ public class MimeTypeIndexingFilterTest {new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());if (MIME_TYPES[i].contains("image")) {- Assert.assertNotNull("Allow only images", doc);+ assertNotNull(doc, "Allow only images");} else {- Assert.assertNull("Block everything else", doc);+ assertNull(doc, "Block everything else");}}}@@ -103,9 +105,9 @@ public class MimeTypeIndexingFilterTest {new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());if (MIME_TYPES[i].contains("html")) {- Assert.assertNull("Block only HTML documents", doc);+ assertNull(doc, "Block only HTML documents");} else {- Assert.assertNotNull("Allow everything else", doc);+ assertNotNull(doc, "Allow everything else");}}}diff --git a/src/plugin/parse-ext/src/test/org/apache/nutch/parse/ext/TestExtParser.java b/src/plugin/parse-ext/src/test/org/apache/nutch/parse/ext/TestExtParser.javaindex 782a1529b..c8698e815 100644--- a/src/plugin/parse-ext/src/test/org/apache/nutch/parse/ext/TestExtParser.java+++ b/src/plugin/parse-ext/src/test/org/apache/nutch/parse/ext/TestExtParser.java@@ -27,15 +27,17 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import java.io.File;import java.io.FileOutputStream;import java.io.IOException;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;+/*** Unit tests for ExtParser. First creates a temp file with fixed content, then* fetch and parse it using external command 'cat' and 'md5sum' alternately for@@ -56,7 +58,7 @@ public class TestExtParser {// echo -n "nutch rocks nutch rocks nutch rocks" | md5sumprivate String expectedMD5sum = "df46711a1a48caafc98b1c3b83aa1526";- @Before+ @BeforeEachprotected void setUp() throws ProtocolException, IOException {// prepare a temp file with expectedText as its content// This system property is defined in ./src/plugin/build-plugin.xml@@ -85,7 +87,7 @@ public class TestExtParser {protocol = null;}- @After+ @AfterEachprotected void tearDown() {// clean contentcontent = null;@@ -115,14 +117,14 @@ public class TestExtParser {content.setContentType(contentType);parse = new ParseUtil(conf).parseByExtensionId("parse-ext", content).get(content.getUrl());- Assert.assertEquals(expectedText, parse.getText());+ assertEquals(expectedText, parse.getText());// check external parser that does 'md5sum'contentType = "application/vnd.nutch.example.md5sum";content.setContentType(contentType);parse = new ParseUtil(conf).parseByExtensionId("parse-ext", content).get(content.getUrl());- Assert.assertTrue(parse.getText().startsWith(expectedMD5sum));+ assertTrue(parse.getText().startsWith(expectedMD5sum));}}diff --git a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestDOMContentUtils.java b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestDOMContentUtils.javaindex d50e9052d..bcebd9804 100644--- a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestDOMContentUtils.java+++ b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestDOMContentUtils.java@@ -27,13 +27,15 @@ import java.util.ArrayList;import java.util.StringTokenizer;import org.cyberneko.html.parsers.*;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.xml.sax.*;import org.w3c.dom.*;import org.apache.html.dom.*;+import static org.junit.jupiter.api.Assertions.assertTrue;+import static org.junit.jupiter.api.Assertions.fail;+/*** Unit tests for DOMContentUtils.*/@@ -179,7 +181,7 @@ public class TestDOMContentUtils {private static Configuration conf;private static DOMContentUtils utils = null;- @Before+ @BeforeEachpublic void setup() {conf = NutchConfiguration.create();conf.setBoolean("parser.html.form.use_action", true);@@ -200,7 +202,7 @@ public class TestDOMContentUtils {node);testBaseHrefURLs[i] = new URL(testBaseHrefs[i]);} catch (Exception e) {- Assert.assertTrue("caught exception: " + e, false);+ fail("caught exception: " + e);}testDOMs[i] = node;}@@ -273,11 +275,10 @@ public class TestDOMContentUtils {StringBuffer sb = new StringBuffer();utils.getText(sb, testDOMs[i]);String text = sb.toString();- Assert.assertTrue(+ assertTrue(equalsIgnoreWhitespace(answerText[i], text),"expecting text: " + answerText[i]+ System.getProperty("line.separator")- + System.getProperty("line.separator") + "got text: " + text,- equalsIgnoreWhitespace(answerText[i], text));+ + System.getProperty("line.separator") + "got text: " + text);}}@@ -289,11 +290,10 @@ public class TestDOMContentUtils {StringBuffer sb = new StringBuffer();utils.getTitle(sb, testDOMs[i]);String text = sb.toString();- Assert.assertTrue(+ assertTrue(equalsIgnoreWhitespace(answerTitle[i], text),"expecting text: " + answerText[i]+ System.getProperty("line.separator")- + System.getProperty("line.separator") + "got text: " + text,- equalsIgnoreWhitespace(answerTitle[i], text));+ + System.getProperty("line.separator") + "got text: " + text);}}@@ -332,26 +332,25 @@ public class TestDOMContentUtils {private static final void compareOutlinks(Outlink[] o1, Outlink[] o2) {if (o1.length != o2.length) {- Assert.assertTrue(+ fail("got wrong number of outlinks (expecting " + o1.length + ", got "- + o2.length + ")" + System.getProperty("line.separator")- + "answer: " + System.getProperty("line.separator")- + outlinksString(o1) + System.getProperty("line.separator")- + "got: " + System.getProperty("line.separator")- + outlinksString(o2) + System.getProperty("line.separator"),- false);+ + o2.length + ")" + System.getProperty(+ "line.separator") + "answer: " + System.getProperty(+ "line.separator") + outlinksString(o1) + System.getProperty(+ "line.separator") + "got: " + System.getProperty(+ "line.separator") + outlinksString(o2) + System.getProperty(+ "line.separator"));}for (int i = 0; i < o1.length; i++) {if (!o1[i].equals(o2[i])) {- Assert.assertTrue(- "got wrong outlinks at position " + i- + System.getProperty("line.separator") + "answer: "- + System.getProperty("line.separator") + "'" + o1[i].getToUrl()- + "', anchor: '" + o1[i].getAnchor() + "'"- + System.getProperty("line.separator") + "got: "- + System.getProperty("line.separator") + "'" + o2[i].getToUrl()- + "', anchor: '" + o2[i].getAnchor() + "'", false);+ fail("got wrong outlinks at position " + i + System.getProperty(+ "line.separator") + "answer: " + System.getProperty(+ "line.separator") + "'" + o1[i].getToUrl() + "', anchor: '"+ + o1[i].getAnchor() + "'" + System.getProperty(+ "line.separator") + "got: " + System.getProperty(+ "line.separator") + "'" + o2[i].getToUrl() + "', anchor: '"+ + o2[i].getAnchor() + "'");}}diff --git a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestHtmlParser.java b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestHtmlParser.javaindex 6e13a69ea..47beff5a0 100644--- a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestHtmlParser.java+++ b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestHtmlParser.java@@ -27,11 +27,12 @@ import org.apache.nutch.parse.Parse;import org.apache.nutch.parse.Parser;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.*;+public class TestHtmlParser {private static final Logger LOG = LoggerFactory@@ -117,15 +118,15 @@ public class TestHtmlParser {LOG.info("title:\t{}", title);LOG.info("keywords:\t{}", keywords);LOG.info("text:\t{}", text);- Assert.assertEquals("Title not extracted properly (" + name + ")",- encodingTestKeywords, title);+ assertEquals(encodingTestKeywords, title,+ "Title not extracted properly (" + name + ")");for (String keyword : encodingTestKeywords.split(",\\s*")) {- Assert.assertTrue(keyword + " not found in text (" + name + ")",- text.contains(keyword));+ assertTrue(text.contains(keyword),+ keyword + " not found in text (" + name + ")");}- Assert.assertNotNull("No keywords extracted", keywords);- Assert.assertEquals("Keywords not extracted properly (" + name + ")",- encodingTestKeywords, keywords);+ assertNotNull(keywords, "No keywords extracted");+ assertEquals(encodingTestKeywords, keywords,+ "Keywords not extracted properly (" + name + ")");}}@@ -137,8 +138,8 @@ public class TestHtmlParser {Parse parse = parse(contentBytes);LOG.info(parse.getData().toString());Outlink[] outlinks = parse.getData().getOutlinks();- Assert.assertEquals(1, outlinks.length);- Assert.assertEquals("http://www.example.com/index.html",+ assertEquals(1, outlinks.length);+ assertEquals("http://www.example.com/index.html",outlinks[0].getToUrl());}diff --git a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestRobotsMetaProcessor.java b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestRobotsMetaProcessor.javaindex e75635090..b977b82ab 100644--- a/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestRobotsMetaProcessor.java+++ b/src/plugin/parse-html/src/test/org/apache/nutch/parse/html/TestRobotsMetaProcessor.java@@ -22,12 +22,13 @@ import java.io.ByteArrayInputStream;import java.net.URL;import org.cyberneko.html.parsers.*;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.xml.sax.*;import org.w3c.dom.*;import org.apache.html.dom.*;+import static org.junit.jupiter.api.Assertions.*;+/** Unit tests for HTMLMetaProcessor. */public class TestRobotsMetaProcessor {@@ -117,7 +118,7 @@ public class TestRobotsMetaProcessor {{ new URL("http://www.nutch.org"),new URL("http://www.nutch.org/base/") } };} catch (Exception e) {- Assert.assertTrue("couldn't make test URLs!", false);+ fail("couldn't make test URLs!");}for (int i = 0; i < tests.length; i++) {@@ -134,19 +135,18 @@ public class TestRobotsMetaProcessor {HTMLMetaTags robotsMeta = new HTMLMetaTags();HTMLMetaProcessor.getMetaTags(robotsMeta, node, currURLsAndAnswers[i][0]);- Assert.assertTrue("got index wrong on test " + i,- robotsMeta.getNoIndex() == answers[i][0]);- Assert.assertTrue("got follow wrong on test " + i,- robotsMeta.getNoFollow() == answers[i][1]);- Assert.assertTrue("got cache wrong on test " + i,- robotsMeta.getNoCache() == answers[i][2]);- Assert- .assertTrue(- "got base href wrong on test " + i + " (got "- + robotsMeta.getBaseHref() + ")",- ((robotsMeta.getBaseHref() == null) && (currURLsAndAnswers[i][1] == null))+ assertEquals(robotsMeta.getNoIndex(), answers[i][0],+ "got index wrong on test " + i);+ assertEquals(robotsMeta.getNoFollow(), answers[i][1],+ "got follow wrong on test " + i);+ assertEquals(robotsMeta.getNoCache(), answers[i][2],+ "got cache wrong on test " + i);+ assertTrue(((robotsMeta.getBaseHref() == null) &&+ (currURLsAndAnswers[i][1] == null))|| ((robotsMeta.getBaseHref() != null) && robotsMeta- .getBaseHref().equals(currURLsAndAnswers[i][1])));+ .getBaseHref().equals(currURLsAndAnswers[i][1])),+ "got base href wrong on test " + i + " (got "+ + robotsMeta.getBaseHref() + ")");}}diff --git a/src/plugin/parse-js/src/test/org/apache/nutch/parse/js/TestJSParseFilter.java b/src/plugin/parse-js/src/test/org/apache/nutch/parse/js/TestJSParseFilter.javaindex 01bee1321..b0ee51914 100644--- a/src/plugin/parse-js/src/test/org/apache/nutch/parse/js/TestJSParseFilter.java+++ b/src/plugin/parse-js/src/test/org/apache/nutch/parse/js/TestJSParseFilter.java@@ -37,8 +37,8 @@ import org.apache.nutch.protocol.Protocol;import org.apache.nutch.protocol.ProtocolException;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;@@ -66,7 +66,7 @@ public class TestJSParseFilter {private Configuration conf;- @Before+ @BeforeEachpublic void setUp() {conf = NutchConfiguration.create();conf.set("file.content.limit", "-1");diff --git a/src/plugin/parse-metatags/src/test/org/apache/nutch/parse/metatags/TestMetatagParser.java b/src/plugin/parse-metatags/src/test/org/apache/nutch/parse/metatags/TestMetatagParser.javaindex 5702c10b0..9a3eb96c0 100644--- a/src/plugin/parse-metatags/src/test/org/apache/nutch/parse/metatags/TestMetatagParser.java+++ b/src/plugin/parse-metatags/src/test/org/apache/nutch/parse/metatags/TestMetatagParser.java@@ -31,11 +31,12 @@ import org.apache.nutch.protocol.Content;import org.apache.nutch.protocol.Protocol;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.*;+public class TestMetatagParser {private String fileSeparator = System.getProperty("file.separator");@@ -59,7 +60,7 @@ public class TestMetatagParser {metadata = parse.getData().getParseMeta();} catch (Exception e) {e.printStackTrace();- Assert.fail(e.toString());+ fail(e.toString());}return metadata;}@@ -72,8 +73,8 @@ public class TestMetatagParser {// check that we get the same valuesMetadata parseMeta = parseMeta(sampleFile, conf);- Assert.assertEquals(description, parseMeta.get("metatag.description"));- Assert.assertEquals(keywords, parseMeta.get("metatag.keywords"));+ assertEquals(description, parseMeta.get("metatag.description"));+ assertEquals(keywords, parseMeta.get("metatag.keywords"));}@Test@@ -93,7 +94,7 @@ public class TestMetatagParser {}String[] expectedValues1 = { "Doug Cutting", "Michael Cafarella" };for (String val : expectedValues1) {- Assert.assertTrue(failMessage + val, valueSet.contains(val));+ assertTrue(valueSet.contains(val), failMessage + val);}valueSet.clear();@@ -103,7 +104,7 @@ public class TestMetatagParser {String[] expectedValues2 = { "robot d'indexation", "web crawler","Webcrawler" };for (String val : expectedValues2) {- Assert.assertTrue(failMessage + val, valueSet.contains(val));+ assertTrue(valueSet.contains(val), failMessage + val);}}@@ -123,9 +124,8 @@ public class TestMetatagParser {LOG.info("metatags ({}): {}", parsePlugin,Arrays.toString(parseMeta.getValues("metatag.keywords")));- Assert.assertEquals(- "Test document contains a single value of <meta name=keywords>, metatag.keywords should be also single-valued",- 1, parseMeta.getValues("metatag.keywords").length);+ assertEquals(1, parseMeta.getValues("metatag.keywords").length,+ "Test document contains a single value of <meta name=keywords>, metatag.keywords should be also single-valued");}}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestDOMContentUtils.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestDOMContentUtils.javaindex b449e1e4d..423fa870d 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestDOMContentUtils.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestDOMContentUtils.java@@ -27,11 +27,13 @@ import org.apache.nutch.metadata.Metadata;import org.apache.nutch.parse.Outlink;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.w3c.dom.DocumentFragment;+import static org.junit.jupiter.api.Assertions.assertTrue;+import static org.junit.jupiter.api.Assertions.fail;+/*** Unit tests for DOMContentUtils.*/@@ -175,7 +177,7 @@ public class TestDOMContentUtils {private static Configuration conf;private static DOMContentUtils utils = null;- @Before+ @BeforeEachpublic void setup() throws Exception {conf = NutchConfiguration.create();utils = new DOMContentUtils(conf);@@ -196,7 +198,7 @@ public class TestDOMContentUtils {parser.getParse(content, doc, root);testDOMs[i] = root;} catch (Exception e) {- Assert.assertTrue("caught exception: " + e, false);+ fail("caught exception: " + e);}}answerOutlinks = new Outlink[][] {@@ -260,11 +262,10 @@ public class TestDOMContentUtils {StringBuffer sb = new StringBuffer();utils.getText(sb, testDOMs[i]);String text = sb.toString();- Assert.assertTrue(+ assertTrue(equalsIgnoreWhitespace(answerText[i], text),"expecting text: " + answerText[i]+ System.getProperty("line.separator")- + System.getProperty("line.separator") + "got text: " + text,- equalsIgnoreWhitespace(answerText[i], text));+ + System.getProperty("line.separator") + "got text: " + text);}}@@ -276,11 +277,10 @@ public class TestDOMContentUtils {StringBuffer sb = new StringBuffer();utils.getTitle(sb, testDOMs[i]);String text = sb.toString();- Assert.assertTrue(+ assertTrue(equalsIgnoreWhitespace(answerTitle[i], text),"expecting text: " + answerText[i]+ System.getProperty("line.separator")- + System.getProperty("line.separator") + "got text: " + text,- equalsIgnoreWhitespace(answerTitle[i], text));+ + System.getProperty("line.separator") + "got text: " + text);}}@@ -319,26 +319,25 @@ public class TestDOMContentUtils {private static final void compareOutlinks(Outlink[] o1, Outlink[] o2) {if (o1.length != o2.length) {- Assert.assertTrue(- "got wrong number of outlinks (expecting " + o1.length + ", got "- + o2.length + ")" + System.getProperty("line.separator")- + "answer: " + System.getProperty("line.separator")- + outlinksString(o1) + System.getProperty("line.separator")- + "got: " + System.getProperty("line.separator")- + outlinksString(o2) + System.getProperty("line.separator"),- false);+ fail(+ "got wrong number of outlinks (expecting " + o1.length+ + ", got " + o2.length + ")" + System.getProperty(+ "line.separator") + "answer: " + System.getProperty(+ "line.separator") + outlinksString(o1) + System.getProperty(+ "line.separator") + "got: " + System.getProperty(+ "line.separator") + outlinksString(o2) + System.getProperty(+ "line.separator"));}for (int i = 0; i < o1.length; i++) {if (!o1[i].equals(o2[i])) {- Assert.assertTrue(- "got wrong outlinks at position " + i- + System.getProperty("line.separator") + "answer: "- + System.getProperty("line.separator") + "'" + o1[i].getToUrl()- + "', anchor: '" + o1[i].getAnchor() + "'"- + System.getProperty("line.separator") + "got: "- + System.getProperty("line.separator") + "'" + o2[i].getToUrl()- + "', anchor: '" + o2[i].getAnchor() + "'", false);+ fail("got wrong outlinks at position " + i + System.getProperty(+ "line.separator") + "answer: " + System.getProperty(+ "line.separator") + "'" + o1[i].getToUrl() + "', anchor: '"+ + o1[i].getAnchor() + "'" + System.getProperty(+ "line.separator") + "got: " + System.getProperty(+ "line.separator") + "'" + o2[i].getToUrl() + "', anchor: '"+ + o2[i].getAnchor() + "'");}}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestEmbeddedDocuments.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestEmbeddedDocuments.javaindex 8d5b29030..b66132e24 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestEmbeddedDocuments.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestEmbeddedDocuments.java@@ -18,9 +18,10 @@ package org.apache.nutch.parse.tika;import org.apache.nutch.parse.ParseException;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertTrue;/*** Unit tests for MSWordParser.@@ -34,7 +35,7 @@ public class TestEmbeddedDocuments extends TikaParserTest {private String expectedText = "When in the Course of human events";@Override- @Before+ @BeforeEachpublic void setUp() {super.setUp();conf.setBoolean("tika.parse.embedded", true);@@ -44,8 +45,7 @@ public class TestEmbeddedDocuments extends TikaParserTest {public void testIt() throws ProtocolException, ParseException {for (int i = 0; i < sampleFiles.length; i++) {String found = getTextContent(sampleFiles[i]);- Assert.assertTrue("text found : '" + found + "'",- found.contains(expectedText));+ assertTrue(found.contains(expectedText), "text found : '" + found + "'");}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestFeedParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestFeedParser.javaindex 94eec535e..6350984ed 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestFeedParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestFeedParser.java@@ -16,8 +16,7 @@*/package org.apache.nutch.parse.tika;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;@@ -32,6 +31,9 @@ import org.apache.nutch.protocol.ProtocolException;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.util.NutchConfiguration;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.fail;+/*** Test Suite for the RSS feeds with the {@link TikaParser}.*/@@ -79,8 +81,8 @@ public class TestFeedParser extends TikaParserTest {Outlink[] theOutlinks = theParseData.getOutlinks();- Assert.assertTrue("There aren't 2 outlinks read!",- theOutlinks.length == 2);+ assertEquals(2, theOutlinks.length,+ "There aren't 2 outlinks read!");// now check to make sure that those are the two outlinksboolean hasLink1 = false, hasLink2 = false;@@ -97,7 +99,7 @@ public class TestFeedParser extends TikaParserTest {}if (!hasLink1 || !hasLink2) {- Assert.fail("Outlinks read from sample rss file are not correct!");+ fail("Outlinks read from sample rss file are not correct!");}}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestHtmlParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestHtmlParser.javaindex e03622246..17d244447 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestHtmlParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestHtmlParser.java@@ -27,11 +27,12 @@ import org.apache.nutch.parse.Parse;import org.apache.nutch.parse.Parser;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.*;+public class TestHtmlParser {private static final Logger LOG = LoggerFactory@@ -117,15 +118,15 @@ public class TestHtmlParser {LOG.info("title:\t{}", title);LOG.info("keywords:\t{}", keywords);LOG.info("text:\t{}", text);- Assert.assertEquals("Title not extracted properly (" + name + ")",- encodingTestKeywords, title);+ assertEquals(encodingTestKeywords, title,+ "Title not extracted properly (" + name + ")");for (String keyword : encodingTestKeywords.split(",\\s*")) {- Assert.assertTrue(keyword + " not found in text (" + name + ")",- text.contains(keyword));+ assertTrue(text.contains(keyword),+ keyword + " not found in text (" + name + ")");}- Assert.assertNotNull("No keywords extracted", keywords);- Assert.assertEquals("Keywords not extracted properly (" + name + ")",- encodingTestKeywords, keywords);+ assertNotNull(keywords, "No keywords extracted");+ assertEquals(encodingTestKeywords, keywords,+ "Keywords not extracted properly (" + name + ")");}}@@ -137,8 +138,8 @@ public class TestHtmlParser {Parse parse = parse(contentBytes);LOG.info(parse.getData().toString());Outlink[] outlinks = parse.getData().getOutlinks();- Assert.assertEquals(1, outlinks.length);- Assert.assertEquals("http://www.example.com/index.html",+ assertEquals(1, outlinks.length);+ assertEquals("http://www.example.com/index.html",outlinks[0].getToUrl());}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestImageMetadata.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestImageMetadata.javaindex 0f1505d0a..6f694a59e 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestImageMetadata.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestImageMetadata.java@@ -27,8 +27,9 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;/*** Test extraction of image metadata@@ -55,8 +56,8 @@ public class TestImageMetadata extends TikaParserTest {parse = new ParseUtil(conf).parseByExtensionId("parse-tika", content).get(content.getUrl());- Assert.assertEquals("121", parse.getData().getMeta("width"));- Assert.assertEquals("48", parse.getData().getMeta("height"));+ assertEquals("121", parse.getData().getMeta("width"));+ assertEquals("48", parse.getData().getMeta("height"));}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestMSWordParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestMSWordParser.javaindex c5062f684..a8f5dc93f 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestMSWordParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestMSWordParser.java@@ -20,8 +20,10 @@ import java.io.File;import org.apache.nutch.parse.ParseException;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertFalse;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** Unit tests for MSWordParser.@@ -38,8 +40,7 @@ public class TestMSWordParser extends TikaParserTest {public void testIt() throws ProtocolException, ParseException {for (int i = 0; i < sampleFiles.length; i++) {String found = getTextContent(sampleFiles[i]);- Assert.assertTrue("text found : '" + found + "'",- found.startsWith(expectedText));+ assertTrue(found.startsWith(expectedText), "text found : '" + found + "'");}}@@ -49,8 +50,8 @@ public class TestMSWordParser extends TikaParserTest {for (int i = 0; i < filenames.length; i++) {if (filenames[i].endsWith(".doc") == false)continue;- Assert.assertTrue("can't read content of " + filenames[i],- getTextContent(filenames[i]).length() > 0);+ assertFalse(getTextContent(filenames[i]).isEmpty(),+ "can't read content of " + filenames[i]);}}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestOOParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestOOParser.javaindex 41c47e9ba..90667a64d 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestOOParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestOOParser.java@@ -21,8 +21,9 @@ import java.io.InputStreamReader;import org.apache.nutch.parse.ParseException;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertFalse;/*** Unit tests for OOParser.@@ -53,7 +54,7 @@ public class TestOOParser extends TikaParserTest {// simply test for the presence of a text - the ordering of the elements// may differ from what was expected// in the previous tests- Assert.assertTrue(text != null && text.length() > 0);+ assertFalse(text.isEmpty());System.out.println("Found " + sampleFiles[i] + ": " + text);}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestPdfParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestPdfParser.javaindex 784b55c1e..2671a4fd9 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestPdfParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestPdfParser.java@@ -18,8 +18,9 @@ package org.apache.nutch.parse.tika;import org.apache.nutch.parse.ParseException;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertTrue;/*** Unit tests for PdfParser.@@ -36,7 +37,7 @@ public class TestPdfParser extends TikaParserTest {public void testIt() throws ProtocolException, ParseException {for (int i = 0; i < sampleFiles.length; i++) {int index = getTextContent(sampleFiles[i]).indexOf(expectedText);- Assert.assertTrue(index > 0);+ assertTrue(index > 0);}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRTFParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRTFParser.javaindex de0c1c630..22147cba6 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRTFParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRTFParser.java@@ -27,8 +27,10 @@ import org.apache.nutch.protocol.Protocol;import org.apache.nutch.protocol.ProtocolException;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.tika.metadata.DublinCore;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** Unit tests for TestRTFParser.@@ -54,13 +56,13 @@ public class TestRTFParser extends TikaParserTest {parse = new ParseUtil(conf).parseByExtensionId("parse-tika", content).get(content.getUrl());String text = parse.getText();- Assert.assertTrue(text.contains("The quick brown fox jumps over the lazy dog"));+ assertTrue(text.contains("The quick brown fox jumps over the lazy dog"));String title = parse.getData().getTitle();Metadata meta = parse.getData().getParseMeta();- Assert.assertEquals("test rft document", title);- Assert.assertEquals("tests", meta.get(DublinCore.SUBJECT.getName()));+ assertEquals("test rft document", title);+ assertEquals("tests", meta.get(DublinCore.SUBJECT.getName()));}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRobotsMetaProcessor.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRobotsMetaProcessor.javaindex 7591cef2e..a9eb2adf2 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRobotsMetaProcessor.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestRobotsMetaProcessor.java@@ -25,10 +25,11 @@ import org.apache.nutch.parse.HTMLMetaTags;import org.apache.nutch.parse.Parse;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.w3c.dom.DocumentFragment;+import static org.junit.jupiter.api.Assertions.*;+/** Unit tests for HTMLMetaProcessor. */public class TestRobotsMetaProcessor {@@ -125,7 +126,7 @@ public class TestRobotsMetaProcessor {new URL("http://www.nutch.org/base/") },{ new URL("http://www.nutch.org"), null } };} catch (Exception e) {- Assert.assertTrue("couldn't make test URLs!", false);+ fail("couldn't make test URLs!");}for (int i = 0; i < tests.length; i++) {@@ -148,30 +149,27 @@ public class TestRobotsMetaProcessor {HTMLMetaTags robotsMeta = new HTMLMetaTags();HTMLMetaProcessor.getMetaTags(robotsMeta, root, currURLsAndAnswers[i][0]);- Assert.assertEquals("got noindex wrong on test " + i,- answers[i][0], robotsMeta.getNoIndex());- Assert.assertEquals("got nofollow wrong on test " + i,- answers[i][1], robotsMeta.getNoFollow());- Assert.assertEquals("got nocache wrong on test " + i,- answers[i][2], robotsMeta.getNoCache());- Assert- .assertTrue(- "got base href wrong on test " + i + " (got "- + robotsMeta.getBaseHref() + ")",+ assertEquals(answers[i][0], robotsMeta.getNoIndex(),+ "got noindex wrong on test " + i);+ assertEquals(answers[i][1], robotsMeta.getNoFollow(),+ "got nofollow wrong on test " + i);+ assertEquals(answers[i][2], robotsMeta.getNoCache(),+ "got nocache wrong on test " + i);+ assertTrue(((robotsMeta.getBaseHref() == null) && (currURLsAndAnswers[i][1] == null))|| ((robotsMeta.getBaseHref() != null) && robotsMeta- .getBaseHref().equals(currURLsAndAnswers[i][1])));+ .getBaseHref().equals(currURLsAndAnswers[i][1])),+ "got base href wrong on test " + i + " (got "+ + robotsMeta.getBaseHref() + ")");if (tests[i].contains("meta-refresh redirect")) {// test for NUTCH-2589URL metaRefreshUrl = robotsMeta.getRefreshHref();- Assert.assertNotNull("failed to get meta-refresh redirect",- metaRefreshUrl);- Assert.assertEquals("failed to get meta-refresh redirect",- "http://example.com/", metaRefreshUrl.toString());- Assert.assertEquals(- "failed to add meta-refresh redirect to parse status",- "http://example.com/", parse.getData().getStatus().getArgs()[0]);+ assertNotNull(metaRefreshUrl, "failed to get meta-refresh redirect");+ assertEquals("http://example.com/", metaRefreshUrl.toString(),+ "failed to get meta-refresh redirect");+ assertEquals("http://example.com/", parse.getData().getStatus().getArgs()[0],+ "failed to add meta-refresh redirect to parse status");}}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestXlsxParser.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestXlsxParser.javaindex 85427dbdc..1228f8fab 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestXlsxParser.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TestXlsxParser.java@@ -16,13 +16,16 @@*/package org.apache.nutch.parse.tika;-import static org.junit.Assert.*;+import static org.hamcrest.CoreMatchers.is;+import static org.hamcrest.MatcherAssert.assertThat;import java.io.IOException;import org.apache.nutch.parse.ParseException;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Test;+import org.hamcrest.CoreMatchers.*;+import org.hamcrest.MatcherAssert.*;+import org.junit.jupiter.api.Test;public class TestXlsxParser extends TikaParserTest {@@ -32,7 +35,7 @@ public class TestXlsxParser extends TikaParserTest {String expected = "test.txt This is a test for spreadsheets xlsx";// text is distributed over columns and rows, need to normalize white spacefound = found.replaceAll("\\s+", " ").trim();- assertEquals(found, expected);+ assertThat(found, is(expected));}}diff --git a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TikaParserTest.java b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TikaParserTest.javaindex 781debbae..9fd468b55 100644--- a/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TikaParserTest.java+++ b/src/plugin/parse-tika/src/test/org/apache/nutch/parse/tika/TikaParserTest.java@@ -27,7 +27,7 @@ import org.apache.nutch.protocol.Protocol;import org.apache.nutch.protocol.ProtocolException;import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Before;+import org.junit.jupiter.api.BeforeEach;/*** Base class to extend Tika parser tests from.@@ -45,7 +45,7 @@ public class TikaParserTest {protected Configuration conf;- @Before+ @BeforeEachpublic void setUp() {conf = NutchConfiguration.create();conf.set("file.content.limit", "-1");diff --git a/src/plugin/parse-zip/src/test/org/apache/nutch/parse/zip/TestZipParser.java b/src/plugin/parse-zip/src/test/org/apache/nutch/parse/zip/TestZipParser.javaindex 767099ef6..1877cf6cc 100644--- a/src/plugin/parse-zip/src/test/org/apache/nutch/parse/zip/TestZipParser.java+++ b/src/plugin/parse-zip/src/test/org/apache/nutch/parse/zip/TestZipParser.java@@ -27,8 +27,9 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertTrue;/*** Based on Unit tests for MSWordParser by John Xing@@ -63,10 +64,9 @@ public class TestZipParser {new CrawlDatum()).getContent();parse = new ParseUtil(conf).parseByExtensionId("parse-zip", content).get(content.getUrl());- Assert.assertTrue(+ assertTrue(parse.getText().startsWith(expectedText),"Extracted text does not start with <" + expectedText + ">: <"- + parse.getText() + ">",- parse.getText().startsWith(expectedText));+ + parse.getText() + ">");}}diff --git a/src/plugin/parsefilter-regex/src/test/org/apache/nutch/parsefilter/regex/TestRegexParseFilter.java b/src/plugin/parsefilter-regex/src/test/org/apache/nutch/parsefilter/regex/TestRegexParseFilter.javaindex 64fa7f666..44f6cb114 100644--- a/src/plugin/parsefilter-regex/src/test/org/apache/nutch/parsefilter/regex/TestRegexParseFilter.java+++ b/src/plugin/parsefilter-regex/src/test/org/apache/nutch/parsefilter/regex/TestRegexParseFilter.java@@ -24,14 +24,17 @@ import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseResult;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import junit.framework.TestCase;+import org.junit.jupiter.api.Test;-public class TestRegexParseFilter extends TestCase {+import static org.junit.jupiter.api.Assertions.assertEquals;++class TestRegexParseFilter {private final static String SEPARATOR = System.getProperty("file.separator");private final static String SAMPLES = System.getProperty("test.data", ".");- public void testPositiveFilter() throws Exception {+ @Test+ void testPositiveFilter() throws Exception {Configuration conf = NutchConfiguration.create();String file = SAMPLES + SEPARATOR + "regex-parsefilter.txt";@@ -52,8 +55,9 @@ public class TestRegexParseFilter extends TestCase {assertEquals("true", meta.get("first"));assertEquals("true", meta.get("second"));}-- public void testNegativeFilter() throws Exception {++ @Test+ void testNegativeFilter() throws Exception {Configuration conf = NutchConfiguration.create();String file = SAMPLES + SEPARATOR + "regex-parsefilter.txt";diff --git a/src/plugin/protocol-file/src/test/org/apache/nutch/protocol/file/TestProtocolFile.java b/src/plugin/protocol-file/src/test/org/apache/nutch/protocol/file/TestProtocolFile.javaindex ffee2ba4d..0139151fc 100644--- a/src/plugin/protocol-file/src/test/org/apache/nutch/protocol/file/TestProtocolFile.java+++ b/src/plugin/protocol-file/src/test/org/apache/nutch/protocol/file/TestProtocolFile.java@@ -29,9 +29,11 @@ import org.apache.nutch.protocol.ProtocolFactory;import org.apache.nutch.protocol.ProtocolOutput;import org.apache.nutch.protocol.ProtocolStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;/*** @author mattmann@@ -57,7 +59,7 @@ public class TestProtocolFile {private Configuration conf;- @Before+ @BeforeEachpublic void setUp() {conf = NutchConfiguration.create();}@@ -77,20 +79,20 @@ public class TestProtocolFile {*/public void setContentType(String testTextFile) throws ProtocolException {String urlString = "file:" + sampleDir + fileSeparator + testTextFile;- Assert.assertNotNull(urlString);+ assertNotNull(urlString);Protocol protocol = new ProtocolFactory(conf).getProtocol(urlString);ProtocolOutput output = protocol.getProtocolOutput(new Text(urlString),datum);- Assert.assertNotNull(output);- Assert.assertEquals("Status code: [" + output.getStatus().getCode()- + "], not equal to: [" + ProtocolStatus.SUCCESS + "]: args: ["- + output.getStatus().getArgs() + "]", ProtocolStatus.SUCCESS, output- .getStatus().getCode());- Assert.assertNotNull(output.getContent());- Assert.assertNotNull(output.getContent().getContentType());- Assert.assertEquals(expectedMimeType, output.getContent().getContentType());- Assert.assertNotNull(output.getContent().getMetadata());- Assert.assertEquals(expectedMimeType, output.getContent().getMetadata()+ assertNotNull(output);+ assertEquals(ProtocolStatus.SUCCESS, output.getStatus().getCode(),+ "Status code: [" + output.getStatus().getCode()+ + "], not equal to: [" + ProtocolStatus.SUCCESS + "]: args: ["+ + output.getStatus().getArgs() + "]");+ assertNotNull(output.getContent());+ assertNotNull(output.getContent().getContentType());+ assertEquals(expectedMimeType, output.getContent().getContentType());+ assertNotNull(output.getContent().getMetadata());+ assertEquals(expectedMimeType, output.getContent().getMetadata().get(Response.CONTENT_TYPE));}diff --git a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestBadServerResponses.java b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestBadServerResponses.javaindex 13c25587c..02e381e46 100644--- a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestBadServerResponses.java+++ b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestBadServerResponses.java@@ -16,19 +16,18 @@*/package org.apache.nutch.protocol.http;-import static org.junit.Assert.assertEquals;-import static org.junit.Assert.assertNotNull;-import static org.junit.Assert.assertTrue;--import java.lang.invoke.MethodHandles;-import java.nio.charset.StandardCharsets;-import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;import org.apache.nutch.protocol.ProtocolOutput;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import java.lang.invoke.MethodHandles;+import java.nio.charset.StandardCharsets;++import static org.hamcrest.CoreMatchers.*;+import static org.hamcrest.MatcherAssert.assertThat;+/*** Test cases for protocol-http - robustness regarding bad server responses:* malformed HTTP header lines, etc. See, NUTCH-2549.@@ -100,9 +99,10 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {launchServer("HTTP/1.1 302 Found\r\nLocation: http://example.com/\r\n"+ "Transfer-Encoding: chunked\r\n\r\nNot a valid chunk.");ProtocolOutput fetched = fetchPage("/", 302);- assertNotNull("No redirect Location.", getHeader(fetched, "Location"));- assertEquals("Wrong redirect Location.", "http://example.com/",- getHeader(fetched, "Location"));+ assertThat("No redirect Location.", getHeader(fetched, "Location"),+ notNullValue());+ assertThat("Wrong redirect Location.", getHeader(fetched, "Location"),+ is("http://example.com/"));}/**@@ -113,8 +113,9 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {String text = "This is a text containing non-ASCII characters: \u00e4\u00f6\u00fc\u00df";launchServer(text);ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Wrong text returned for response with no status line.", text,- new String(fetched.getContent().getContent(), StandardCharsets.UTF_8));+ assertThat("Wrong text returned for response with no status line.",+ new String(fetched.getContent().getContent(), StandardCharsets.UTF_8),+ is(text));server.close();text = "<!DOCTYPE html>\n<html>\n<head>\n"+ "<title>Testing no HTTP header èéâ</title>\n"@@ -123,8 +124,9 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {+ "\u00e4\u00f6\u00fc\u00df</body>\n</html";launchServer(text);fetched = fetchPage("/", 200);- assertEquals("Wrong text returned for response with no status line.", text,- new String(fetched.getContent().getContent(), StandardCharsets.UTF_8));+ assertThat("Wrong text returned for response with no status line.",+ new String(fetched.getContent().getContent(), StandardCharsets.UTF_8),+ is(text));}/**@@ -138,10 +140,10 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {+ simpleContent);ProtocolOutput fetched = fetchPage("/", 200);LOG.info("Headers: {}", getHeaders(fetched));- assertNotNull("Failed to set multi-line \"Set-Cookie\" header.",- getHeader(fetched, "Set-Cookie"));- assertTrue("Failed to set multi-line \"Set-Cookie\" header.",- getHeader(fetched, "Set-Cookie").contains("Version=1"));+ assertThat("Failed to set multi-line \"Set-Cookie\" header.",+ getHeader(fetched, "Set-Cookie"), notNullValue());+ assertThat("Failed to set multi-line \"Set-Cookie\" header.",+ getHeader(fetched, "Set-Cookie"), containsString("Version=1"));}/**@@ -188,9 +190,8 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {response.append("\r\n0\r\n\r\n");launchServer(response.toString());ProtocolOutput fetched = fetchPage("/", 200);- assertEquals(- "Chunked content not truncated according to http.content.limit", 65536,- fetched.getContent().getContent().length);+ assertThat("Chunked content not truncated according to http.content.limit",+ fetched.getContent().getContent().length, is(65536));}}diff --git a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttp.java b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttp.javaindex fb7657390..31cc50081 100644--- a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttp.java+++ b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttp.java@@ -22,7 +22,7 @@ import java.util.Map;import java.util.TreeMap;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;-import org.junit.Test;+import org.junit.jupiter.api.Test;/*** Test cases for protocol-httpdiff --git a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttpByProxy.java b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttpByProxy.javaindex 16d354818..6a694d1df 100644--- a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttpByProxy.java+++ b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestProtocolHttpByProxy.java@@ -22,13 +22,13 @@ import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;import org.apache.nutch.protocol.Content;import org.apache.nutch.protocol.ProtocolOutput;import org.apache.nutch.protocol.ProtocolStatus;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.littleshoot.proxy.HttpProxyServer;import org.littleshoot.proxy.impl.DefaultHttpProxyServer;-import static org.junit.Assert.assertNotNull;-import static org.junit.Assert.assertTrue;+import static org.junit.jupiter.api.Assertions.assertNotNull;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** Test cases for protocol-http by proxy@@ -41,7 +41,7 @@ public class TestProtocolHttpByProxy extends AbstractHttpProtocolPluginTest {public static final String TARGET_HOST = "www.baidu.com";public static final Integer TARGET_PORT = 443;- @Before+ @BeforeEachpublic void setUp() throws Exception {super.setUp();conf.set("http.proxy.host", PROXY_HOST);diff --git a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestResponse.java b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestResponse.javaindex 53b605568..1126e8e84 100644--- a/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestResponse.java+++ b/src/plugin/protocol-http/src/test/org/apache/nutch/protocol/http/TestResponse.java@@ -17,8 +17,7 @@package org.apache.nutch.protocol.http;import static java.nio.charset.StandardCharsets.UTF_8;--import static org.junit.Assert.assertEquals;+import static org.junit.jupiter.api.Assertions.assertEquals;import java.io.IOException;import java.lang.invoke.MethodHandles;@@ -31,9 +30,9 @@ import org.apache.nutch.crawl.CrawlDatum;import org.apache.nutch.net.protocols.Response;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Before;-import org.junit.Ignore;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Disabled;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.apache.hadoop.conf.Configuration;@@ -53,7 +52,7 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {}@Override- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = new Configuration();conf.addResource("nutch-default.xml");@@ -82,10 +81,9 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {HttpResponse response = getResponse(statusCode, headerName);LOG.info("Response headers:");LOG.info(response.getHeaders().get(Response.RESPONSE_HEADERS));- assertEquals(+ assertEquals(value, response.getHeader(lookupName),"No or unexpected value of header \"" + headerName- + "\" returned when retrieving header \"" + lookupName + "\"",- value, response.getHeader(lookupName));+ + "\" returned when retrieving header \"" + lookupName + "\"");}protected Map<String, byte[]> getResponses(String headerValue) {@@ -126,7 +124,7 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {// testHeader(200, "MYCUSTOMHEADER", value, "MyCustomHeader");}- @Ignore("Only for benchmarking")+ @Disabled("Only for benchmarking")@Testpublic void testMetadataBenchmark() throws MalformedURLException, ProtocolException,IOException, InterruptedException {diff --git a/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java b/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.javaindex f7277bd9e..ddc0e24e4 100644--- a/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java+++ b/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java@@ -30,7 +30,7 @@ import org.apache.commons.codec.binary.Base64;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;diff --git a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestBadServerResponses.java b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestBadServerResponses.javaindex 7c5d0f15c..bea9a1ba5 100644--- a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestBadServerResponses.java+++ b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestBadServerResponses.java@@ -16,9 +16,9 @@*/package org.apache.nutch.protocol.okhttp;-import static org.junit.Assert.assertEquals;-import static org.junit.Assert.assertNotNull;-import static org.junit.Assert.assertTrue;+import static org.hamcrest.CoreMatchers.*;+import static org.hamcrest.MatcherAssert.*;+import static org.junit.jupiter.api.Assertions.assertTrue;import java.io.ByteArrayOutputStream;import java.lang.invoke.MethodHandles;@@ -28,8 +28,8 @@ import java.util.zip.GZIPOutputStream;import org.apache.nutch.net.protocols.Response;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;import org.apache.nutch.protocol.ProtocolOutput;-import org.junit.Ignore;-import org.junit.Test;+import org.junit.jupiter.api.Disabled;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;@@ -79,7 +79,7 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {/*** NUTCH-2559 protocol-http cannot handle colons after the HTTP status code*/- @Ignore("Fails with okhttp 3.10.0")+ @Disabled("Fails with okhttp 3.10.0")@Testpublic void testHeaderWithColon() throws Exception {launchServer("HTTP/1.1 200: OK\r\n" + simpleContent);@@ -100,28 +100,30 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {* NUTCH-2557 protocol-http fails to follow redirections when an HTTP response* body is invalid*/- @Ignore("Fails with okhttp 3.10.0")+ @Disabled("Fails with okhttp 3.10.0")@Testpublic void testIgnoreErrorInRedirectPayload() throws Exception {launchServer("HTTP/1.1 302 Found\r\nLocation: http://example.com/\r\n"+ "Transfer-Encoding: chunked\r\n\r\nNot a valid chunk.");ProtocolOutput fetched = fetchPage("/", 302);- assertNotNull("No redirect Location.", getHeader(fetched, "Location"));- assertEquals("Wrong redirect Location.", "http://example.com/",- getHeader(fetched, "Location"));+ assertThat("No redirect Location.", getHeader(fetched, "Location"),+ notNullValue());+ assertThat("Wrong redirect Location.", getHeader(fetched, "Location"),+ is("http://example.com/"));}/*** NUTCH-2558 protocol-http cannot handle a missing HTTP status line*/- @Ignore("Fails with okhttp 3.10.0")+ @Disabled("Fails with okhttp 3.10.0")@Testpublic void testNoStatusLine() throws Exception {String text = "This is a text containing non-ASCII characters: \u00e4\u00f6\u00fc\u00df";launchServer(text);ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Wrong text returned for response with no status line.", text,- new String(fetched.getContent().getContent(), StandardCharsets.UTF_8));+ assertThat("Wrong text returned for response with no status line.",+ new String(fetched.getContent().getContent(), StandardCharsets.UTF_8),+ is(text));server.close();text = "<!DOCTYPE html>\n<html>\n<head>\n"+ "<title>Testing no HTTP header èéâ</title>\n"@@ -130,15 +132,16 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {+ "\u00e4\u00f6\u00fc\u00df</body>\n</html";launchServer(text);fetched = fetchPage("/", 200);- assertEquals("Wrong text returned for response with no status line.", text,- new String(fetched.getContent().getContent(), StandardCharsets.UTF_8));+ assertThat("Wrong text returned for response with no status line.",+ new String(fetched.getContent().getContent(), StandardCharsets.UTF_8),+ is(text));}/*** NUTCH-2560 protocol-http throws an error when an http header spans over* multiple lines*/- @Ignore("Fails with okhttp 3.10.0")+ @Disabled("Fails with okhttp 3.10.0")@Testpublic void testMultiLineHeader() throws Exception {launchServer(responseHeader@@ -146,10 +149,10 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {+ simpleContent);ProtocolOutput fetched = fetchPage("/", 200);LOG.info("Headers: {}", getHeaders(fetched));- assertNotNull("Failed to set multi-line \"Set-Cookie\" header.",- getHeader(fetched, "Set-Cookie"));- assertTrue("Failed to set multi-line \"Set-Cookie\" header.",- getHeader(fetched, "Set-Cookie").contains("Version=1"));+ assertThat("Failed to set multi-line \"Set-Cookie\" header.",+ getHeader(fetched, "Set-Cookie"), notNullValue());+ assertThat("Failed to set multi-line \"Set-Cookie\" header.",+ getHeader(fetched, "Set-Cookie"), containsString("Version=1"));}/**@@ -197,14 +200,14 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {response.append("\r\n0\r\n\r\n");launchServer(response.toString());ProtocolOutput fetched = fetchPage("/", 200);- assertEquals(- "Chunked content not truncated according to http.content.limit", 65536,- fetched.getContent().getContent().length);- assertNotNull("Content truncation not marked",- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT));- assertEquals("Content truncation not marked",- Response.TruncatedContentReason.LENGTH.toString().toLowerCase(),- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON));+ assertThat("Chunked content not truncated according to http.content.limit",+ fetched.getContent().getContent().length, is(65536));+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT),+ notNullValue());+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON),+ is(Response.TruncatedContentReason.LENGTH.toString().toLowerCase()));}/**@@ -229,14 +232,16 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {}launchServer(response.toString());ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Content not truncated according to http.content.limit",- Math.min(kB * 1024, 65536), fetched.getContent().getContent().length);+ assertThat("Content not truncated according to http.content.limit",+ fetched.getContent().getContent().length,+ is(Math.min(kB * 1024, 65536)));if (kB * 1024 > 65536) {- assertNotNull("Content truncation not marked",- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT));- assertEquals("Content truncation not marked",- Response.TruncatedContentReason.LENGTH.toString().toLowerCase(),- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON));+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT),+ notNullValue());+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON),+ is(Response.TruncatedContentReason.LENGTH.toString().toLowerCase()));}server.close(); // need to close server before next loop iteration}@@ -273,14 +278,16 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {launchServer("/", response.toByteArray());ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Content not truncated according to http.content.limit",- Math.min(kB * 1024, 65536), fetched.getContent().getContent().length);+ assertThat("Content not truncated according to http.content.limit",+ fetched.getContent().getContent().length,+ is(Math.min(kB * 1024, 65536)));if (kB * 1024 > 65536) {- assertNotNull("Content truncation not marked",- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT));- assertEquals("Content truncation not marked",- Response.TruncatedContentReason.LENGTH.toString().toLowerCase(),- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON));+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT),+ notNullValue());+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT_REASON),+ is(Response.TruncatedContentReason.LENGTH.toString().toLowerCase()));}server.close(); // need to close server before next loop iteration}@@ -299,10 +306,12 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {launchServer(responseHeader + "Content-Length: 50000\r\n\r\n" + testContent);ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Content not saved as truncated", testContent,- new String(fetched.getContent().getContent(), StandardCharsets.UTF_8));- assertNotNull("Content truncation not marked",- fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT));+ assertThat("Content not saved as truncated",+ new String(fetched.getContent().getContent(), StandardCharsets.UTF_8),+ is(testContent));+ assertThat("Content truncation not marked",+ fetched.getContent().getMetadata().get(Response.TRUNCATED_CONTENT),+ notNullValue());}@Test@@ -325,8 +334,8 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {}launchServer(response.toString());ProtocolOutput fetched = fetchPage("/", 200);- assertEquals("Content truncated although http.content.limit == -1",- (kB * 1024), fetched.getContent().getContent().length);+ assertThat("Content truncated although http.content.limit == -1",+ fetched.getContent().getContent().length, is((kB * 1024)));}/**@@ -339,9 +348,8 @@ public class TestBadServerResponses extends AbstractHttpProtocolPluginTest {String statusLineNoMessage = "HTTP/1.1 200 \r\n";launchServer(statusLineNoMessage + simpleContent);ProtocolOutput fetched = fetchPage("/", 200);- assertTrue(- "Invalid HTTP status line (see NUTCH-2763, missing whitespace between status code and message)",- getHeaders(fetched).startsWith(statusLineNoMessage));+ assertTrue(getHeaders(fetched).startsWith(statusLineNoMessage),+ "Invalid HTTP status line (see NUTCH-2763, missing whitespace between status code and message)");}}diff --git a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestIPAddressFiltering.java b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestIPAddressFiltering.javaindex dbd1b846d..850b08818 100644--- a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestIPAddressFiltering.java+++ b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestIPAddressFiltering.java@@ -17,16 +17,14 @@package org.apache.nutch.protocol.okhttp;import static java.nio.charset.StandardCharsets.UTF_8;-import static org.junit.Assert.assertFalse;-import static org.junit.Assert.assertTrue;-import static org.junit.Assert.fail;+import static org.junit.jupiter.api.Assertions.*;import java.net.InetAddress;import java.util.function.Function;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;-import org.junit.Test;+import org.junit.jupiter.api.Test;import com.google.common.net.InetAddresses;@@ -53,13 +51,13 @@ public class TestIPAddressFiltering extends AbstractHttpProtocolPluginTest {public void testCIDRcontains(String cidr, String ip) {CIDR c = new CIDR(cidr);InetAddress i = parseIP(ip);- assertTrue(i + " should be in " + c, c.contains(i));+ assertTrue(c.contains(i), i + " should be in " + c);}public void testCIDRnotContains(String cidr, String ip) {CIDR c = new CIDR(cidr);InetAddress i = parseIP(ip);- assertFalse(i + " should not be in " + c, c.contains(i));+ assertFalse(c.contains(i), i + " should not be in " + c);}/** Tests for {@link CIDR} */@@ -93,12 +91,12 @@ public class TestIPAddressFiltering extends AbstractHttpProtocolPluginTest {public void testFilter(Configuration conf, String[] included, String[] excluded) {IPFilterRules ipFilterRules = new IPFilterRules(conf);for (String address : included) {- assertTrue("Address " + address + " should be included",- ipFilterRules.accept(parseIP(address)));+ assertTrue(ipFilterRules.accept(parseIP(address)),+ "Address " + address + " should be included");}for (String address : excluded) {- assertFalse("Address " + address + " should be excluded",- ipFilterRules.accept(parseIP(address)));+ assertFalse(ipFilterRules.accept(parseIP(address)),+ "Address " + address + " should be excluded");}}@@ -141,7 +139,7 @@ public class TestIPAddressFiltering extends AbstractHttpProtocolPluginTest {default:fail("Unknown IP address type " + type);}- assertTrue(ipAddress + " is not recognized as " + type + " address", pred.apply(addr));+ assertTrue(pred.apply(addr), ipAddress + " is not recognized as " + type + " address");} catch (IllegalArgumentException e) {fail("Not a valid IP address string: " + ipAddress);}diff --git a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestProtocolOkHttp.java b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestProtocolOkHttp.javaindex e740ed288..a9b7267b3 100644--- a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestProtocolOkHttp.java+++ b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestProtocolOkHttp.java@@ -22,7 +22,7 @@ import java.util.Map;import java.util.TreeMap;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;-import org.junit.Test;+import org.junit.jupiter.api.Test;/*** Test cases for protocol-okhttpdiff --git a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestResponse.java b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestResponse.javaindex 5cff6ddbc..f0944ff4c 100644--- a/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestResponse.java+++ b/src/plugin/protocol-okhttp/src/test/org/apache/nutch/protocol/okhttp/TestResponse.java@@ -17,8 +17,7 @@package org.apache.nutch.protocol.okhttp;import static java.nio.charset.StandardCharsets.UTF_8;--import static org.junit.Assert.assertEquals;+import static org.junit.jupiter.api.Assertions.assertEquals;import java.io.IOException;import java.lang.invoke.MethodHandles;@@ -31,9 +30,9 @@ import org.apache.nutch.crawl.CrawlDatum;import org.apache.nutch.net.protocols.Response;import org.apache.nutch.protocol.AbstractHttpProtocolPluginTest;import org.apache.nutch.protocol.ProtocolException;-import org.junit.Before;-import org.junit.Ignore;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Disabled;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.apache.hadoop.conf.Configuration;@@ -53,7 +52,7 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {}@Override- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = new Configuration();conf.addResource("nutch-default.xml");@@ -82,10 +81,9 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {OkHttpResponse response = getResponse(statusCode, headerName);LOG.info("Response headers:");LOG.info(response.getHeaders().get(Response.RESPONSE_HEADERS));- assertEquals(+ assertEquals(value, response.getHeader(lookupName),"No or unexpected value of header \"" + headerName- + "\" returned when retrieving header \"" + lookupName + "\"",- value, response.getHeader(lookupName));+ + "\" returned when retrieving header \"" + lookupName + "\"");}protected Map<String, byte[]> getResponses(String headerValue) {@@ -127,7 +125,7 @@ public class TestResponse extends AbstractHttpProtocolPluginTest {// testHeader(200, "MYCUSTOMHEADER", value, "MyCustomHeader");}- @Ignore("Only for benchmarking")+ @Disabled("Only for benchmarking")@Testpublic void testMetadataBenchmark() throws MalformedURLException, ProtocolException,IOException, InterruptedException {diff --git a/src/plugin/scoring-metadata/src/test/org/apache/nutch/scoring/metadata/TestMetadataScoringFilter.java b/src/plugin/scoring-metadata/src/test/org/apache/nutch/scoring/metadata/TestMetadataScoringFilter.javaindex 011223958..e0ad7e68b 100644--- a/src/plugin/scoring-metadata/src/test/org/apache/nutch/scoring/metadata/TestMetadataScoringFilter.java+++ b/src/plugin/scoring-metadata/src/test/org/apache/nutch/scoring/metadata/TestMetadataScoringFilter.java@@ -23,11 +23,12 @@ import org.apache.nutch.parse.*;import org.apache.nutch.protocol.Content;import org.apache.nutch.scoring.ScoringFilterException;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import java.util.HashMap;+import static org.junit.jupiter.api.Assertions.assertEquals;+public class TestMetadataScoringFilter {@@ -60,8 +61,8 @@ public class TestMetadataScoringFilter {Text parent = (Text) outlink.getMetaData().get(new Text(PARENT));Text depth = (Text) outlink.getMetaData().get(new Text(DEPTH));- Assert.assertEquals(parentMD,parent.toString());- Assert.assertEquals(depthMD,depth.toString());+ assertEquals(parentMD,parent.toString());+ assertEquals(depthMD,depth.toString());}}@@ -87,8 +88,8 @@ public class TestMetadataScoringFilter {metadataScoringFilter.passScoreBeforeParsing(from,crawlDatum,content);- Assert.assertEquals(parentMD,content.getMetadata().get(PARENT));- Assert.assertEquals(depthMD,content.getMetadata().get(DEPTH));+ assertEquals(parentMD,content.getMetadata().get(PARENT));+ assertEquals(depthMD,content.getMetadata().get(DEPTH));}@Test@@ -118,7 +119,7 @@ public class TestMetadataScoringFilter {metadataScoringFilter.passScoreAfterParsing(from,content,parse);- Assert.assertEquals(parentMD,parse.getData().getMeta(PARENT));- Assert.assertEquals(depthMD,parse.getData().getMeta(DEPTH));+ assertEquals(parentMD,parse.getData().getMeta(PARENT));+ assertEquals(depthMD,parse.getData().getMeta(DEPTH));}}diff --git a/src/plugin/scoring-orphan/src/test/org/apache/nutch/scoring/orphan/TestOrphanScoringFilter.java b/src/plugin/scoring-orphan/src/test/org/apache/nutch/scoring/orphan/TestOrphanScoringFilter.javaindex f49a99607..568c6521d 100644--- a/src/plugin/scoring-orphan/src/test/org/apache/nutch/scoring/orphan/TestOrphanScoringFilter.java+++ b/src/plugin/scoring-orphan/src/test/org/apache/nutch/scoring/orphan/TestOrphanScoringFilter.java@@ -16,9 +16,6 @@*/package org.apache.nutch.scoring.orphan;-import static org.junit.Assert.assertEquals;-import static org.junit.Assert.assertTrue;-import java.util.ArrayList;import java.util.List;@@ -28,7 +25,10 @@ import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;import org.apache.nutch.scoring.ScoringFilter;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;public class TestOrphanScoringFilter {@@ -72,10 +72,9 @@ public class TestOrphanScoringFilter {filter.updateDbScore(url, null, datum, emptyListOfInlinks);int thirdOrphanTime = getTime(datum);assertEquals(thirdOrphanTime, secondOrphanTime);- assertEquals(+ assertEquals(CrawlDatum.STATUS_DB_NOTMODIFIED, datum.getStatus(),"Expected status db_notmodified but got "- + CrawlDatum.getStatusName(datum.getStatus()),- CrawlDatum.STATUS_DB_NOTMODIFIED, datum.getStatus());+ + CrawlDatum.getStatusName(datum.getStatus()));// Wait a little bittry {@@ -86,10 +85,9 @@ public class TestOrphanScoringFilter {// Act as if no more inlinks, time will not increase, status is still the// samefilter.updateDbScore(url, null, datum, emptyListOfInlinks);- assertEquals(+ assertEquals(CrawlDatum.STATUS_DB_NOTMODIFIED, datum.getStatus(),"Expected status db_notmodified but got "- + CrawlDatum.getStatusName(datum.getStatus()),- CrawlDatum.STATUS_DB_NOTMODIFIED, datum.getStatus());+ + CrawlDatum.getStatusName(datum.getStatus()));// Wait until scoring.orphan.mark.gone.aftertry {@@ -101,10 +99,9 @@ public class TestOrphanScoringFilter {filter.updateDbScore(url, null, datum, emptyListOfInlinks);int fourthOrphanTime = getTime(datum);assertEquals(fourthOrphanTime, thirdOrphanTime);- assertEquals(+ assertEquals(CrawlDatum.STATUS_DB_GONE, datum.getStatus(),"Expected status db_gone but got "- + CrawlDatum.getStatusName(datum.getStatus()),- CrawlDatum.STATUS_DB_GONE, datum.getStatus());+ + CrawlDatum.getStatusName(datum.getStatus()));// Wait until scoring.orphan.mark.orphan.aftertry {@@ -114,10 +111,9 @@ public class TestOrphanScoringFilter {// Again, but now markgoneafter has expired and record should be DB_ORPHANfilter.updateDbScore(url, null, datum, emptyListOfInlinks);- assertEquals(+ assertEquals(CrawlDatum.STATUS_DB_ORPHAN, datum.getStatus(),"Expected status db_orphan but got "- + CrawlDatum.getStatusName(datum.getStatus()),- CrawlDatum.STATUS_DB_ORPHAN, datum.getStatus());+ + CrawlDatum.getStatusName(datum.getStatus()));}protected int getTime(CrawlDatum datum) {diff --git a/src/plugin/subcollection/src/test/org/apache/nutch/collection/TestSubcollection.java b/src/plugin/subcollection/src/test/org/apache/nutch/collection/TestSubcollection.javaindex a2d277276..5b148034f 100644--- a/src/plugin/subcollection/src/test/org/apache/nutch/collection/TestSubcollection.java+++ b/src/plugin/subcollection/src/test/org/apache/nutch/collection/TestSubcollection.java@@ -21,8 +21,10 @@ import java.io.InputStream;import java.util.Collection;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNull;public class TestSubcollection {@@ -38,16 +40,15 @@ public class TestSubcollection {sc.setBlackList("jpg\nwww.apache.org/zecret/");// matches whitelist- Assert.assertEquals("http://www.apache.org/index.html",+ assertEquals("http://www.apache.org/index.html",sc.filter("http://www.apache.org/index.html"));// matches blacklist- Assert.assertEquals(null,- sc.filter("http://www.apache.org/zecret/index.html"));- Assert.assertEquals(null, sc.filter("http://www.apache.org/img/image.jpg"));+ assertNull(sc.filter("http://www.apache.org/zecret/index.html"));+ assertNull(sc.filter("http://www.apache.org/img/image.jpg"));// no match- Assert.assertEquals(null, sc.filter("http://www.google.com/"));+ assertNull(sc.filter("http://www.google.com/"));}@Test@@ -77,36 +78,36 @@ public class TestSubcollection {Collection<?> c = cm.getAll();// test that size matches- Assert.assertEquals(1, c.size());+ assertEquals(1, c.size());Subcollection collection = (Subcollection) c.toArray()[0];// test collection id- Assert.assertEquals("nutch", collection.getId());+ assertEquals("nutch", collection.getId());// test collection name- Assert.assertEquals("nutch collection", collection.getName());+ assertEquals("nutch collection", collection.getName());// test whitelist- Assert.assertEquals(2, collection.whiteList.size());+ assertEquals(2, collection.whiteList.size());String wlUrl = (String) collection.whiteList.get(0);- Assert.assertEquals("http://lucene.apache.org/nutch/", wlUrl);+ assertEquals("http://lucene.apache.org/nutch/", wlUrl);wlUrl = (String) collection.whiteList.get(1);- Assert.assertEquals("http://wiki.apache.org/nutch/", wlUrl);+ assertEquals("http://wiki.apache.org/nutch/", wlUrl);// matches whitelist- Assert.assertEquals("http://lucene.apache.org/nutch/",+ assertEquals("http://lucene.apache.org/nutch/",collection.filter("http://lucene.apache.org/nutch/"));// test blacklist- Assert.assertEquals(1, collection.blackList.size());+ assertEquals(1, collection.blackList.size());String blUrl = (String) collection.blackList.get(0);- Assert.assertEquals("http://www.xxx.yyy", blUrl);+ assertEquals("http://www.xxx.yyy", blUrl);// no match- Assert.assertEquals(null, collection.filter("http://www.google.com/"));+ assertNull(collection.filter("http://www.google.com/"));}}diff --git a/src/plugin/urlfilter-automaton/src/test/org/apache/nutch/urlfilter/automaton/TestAutomatonURLFilter.java b/src/plugin/urlfilter-automaton/src/test/org/apache/nutch/urlfilter/automaton/TestAutomatonURLFilter.javaindex bf2d6b236..143d65fdc 100644--- a/src/plugin/urlfilter-automaton/src/test/org/apache/nutch/urlfilter/automaton/TestAutomatonURLFilter.java+++ b/src/plugin/urlfilter-automaton/src/test/org/apache/nutch/urlfilter/automaton/TestAutomatonURLFilter.java@@ -23,8 +23,9 @@ import java.io.Reader;import org.apache.nutch.net.*;// Nutch importsimport org.apache.nutch.urlfilter.api.RegexURLFilterBaseTest;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.fail;/*** JUnit based test of class <code>AutomatonURLFilter</code>.@@ -38,7 +39,7 @@ public class TestAutomatonURLFilter extends RegexURLFilterBaseTest {try {return new AutomatonURLFilter(rules);} catch (IOException e) {- Assert.fail(e.toString());+ fail(e.toString());return null;}}diff --git a/src/plugin/urlfilter-domain/src/test/org/apache/nutch/urlfilter/domain/TestDomainURLFilter.java b/src/plugin/urlfilter-domain/src/test/org/apache/nutch/urlfilter/domain/TestDomainURLFilter.javaindex 7878aa198..aa829bfba 100644--- a/src/plugin/urlfilter-domain/src/test/org/apache/nutch/urlfilter/domain/TestDomainURLFilter.java+++ b/src/plugin/urlfilter-domain/src/test/org/apache/nutch/urlfilter/domain/TestDomainURLFilter.java@@ -18,8 +18,10 @@ package org.apache.nutch.urlfilter.domain;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertNotNull;+import static org.junit.jupiter.api.Assertions.assertNull;public class TestDomainURLFilter {@@ -34,16 +36,16 @@ public class TestDomainURLFilter {conf.set("urlfilter.domain.file", domainFile);DomainURLFilter domainFilter = new DomainURLFilter();domainFilter.setConf(conf);- Assert.assertNotNull(domainFilter.filter("http://lucene.apache.org"));- Assert.assertNotNull(domainFilter.filter("http://hadoop.apache.org"));- Assert.assertNotNull(domainFilter.filter("http://www.apache.org"));- Assert.assertNull(domainFilter.filter("http://www.google.com"));- Assert.assertNull(domainFilter.filter("http://mail.yahoo.com"));- Assert.assertNotNull(domainFilter.filter("http://www.foobar.net"));- Assert.assertNotNull(domainFilter.filter("http://www.foobas.net"));- Assert.assertNotNull(domainFilter.filter("http://www.yahoo.com"));- Assert.assertNotNull(domainFilter.filter("http://www.foobar.be"));- Assert.assertNull(domainFilter.filter("http://www.adobe.com"));+ assertNotNull(domainFilter.filter("http://lucene.apache.org"));+ assertNotNull(domainFilter.filter("http://hadoop.apache.org"));+ assertNotNull(domainFilter.filter("http://www.apache.org"));+ assertNull(domainFilter.filter("http://www.google.com"));+ assertNull(domainFilter.filter("http://mail.yahoo.com"));+ assertNotNull(domainFilter.filter("http://www.foobar.net"));+ assertNotNull(domainFilter.filter("http://www.foobas.net"));+ assertNotNull(domainFilter.filter("http://www.yahoo.com"));+ assertNotNull(domainFilter.filter("http://www.foobar.be"));+ assertNull(domainFilter.filter("http://www.adobe.com"));}@Test@@ -54,16 +56,16 @@ public class TestDomainURLFilter {conf.set("urlfilter.domain.file", domainFile);DomainURLFilter domainFilter = new DomainURLFilter();domainFilter.setConf(conf);- Assert.assertNotNull(domainFilter.filter("http://lucene.apache.org"));- Assert.assertNotNull(domainFilter.filter("http://hadoop.apache.org"));- Assert.assertNotNull(domainFilter.filter("http://www.apache.org"));- Assert.assertNotNull(domainFilter.filter("http://www.google.com"));- Assert.assertNotNull(domainFilter.filter("http://mail.yahoo.com"));- Assert.assertNotNull(domainFilter.filter("http://www.foobar.net"));- Assert.assertNotNull(domainFilter.filter("http://www.foobas.net"));- Assert.assertNotNull(domainFilter.filter("http://www.yahoo.com"));- Assert.assertNotNull(domainFilter.filter("http://www.foobar.be"));- Assert.assertNotNull(domainFilter.filter("http://www.adobe.com"));+ assertNotNull(domainFilter.filter("http://lucene.apache.org"));+ assertNotNull(domainFilter.filter("http://hadoop.apache.org"));+ assertNotNull(domainFilter.filter("http://www.apache.org"));+ assertNotNull(domainFilter.filter("http://www.google.com"));+ assertNotNull(domainFilter.filter("http://mail.yahoo.com"));+ assertNotNull(domainFilter.filter("http://www.foobar.net"));+ assertNotNull(domainFilter.filter("http://www.foobas.net"));+ assertNotNull(domainFilter.filter("http://www.yahoo.com"));+ assertNotNull(domainFilter.filter("http://www.foobar.be"));+ assertNotNull(domainFilter.filter("http://www.adobe.com"));}}diff --git a/src/plugin/urlfilter-domaindenylist/src/test/org/apache/nutch/urlfilter/domaindenylist/TestDomainDenylistURLFilter.java b/src/plugin/urlfilter-domaindenylist/src/test/org/apache/nutch/urlfilter/domaindenylist/TestDomainDenylistURLFilter.javaindex 0dde23437..f60315715 100644--- a/src/plugin/urlfilter-domaindenylist/src/test/org/apache/nutch/urlfilter/domaindenylist/TestDomainDenylistURLFilter.java+++ b/src/plugin/urlfilter-domaindenylist/src/test/org/apache/nutch/urlfilter/domaindenylist/TestDomainDenylistURLFilter.java@@ -16,11 +16,13 @@*/package org.apache.nutch.urlfilter.domaindenylist;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;+import static org.junit.jupiter.api.Assertions.assertNotNull;+import static org.junit.jupiter.api.Assertions.assertNull;+public class TestDomainDenylistURLFilter {private final static String SEPARATOR = System.getProperty("file.separator");@@ -34,16 +36,16 @@ public class TestDomainDenylistURLFilter {conf.set("urlfilter.domaindenylist.file", domainDenylistFile);DomainDenylistURLFilter domainDenylistFilter = new DomainDenylistURLFilter();domainDenylistFilter.setConf(conf);- Assert.assertNull(domainDenylistFilter.filter("http://lucene.apache.org"));- Assert.assertNull(domainDenylistFilter.filter("http://hadoop.apache.org"));- Assert.assertNull(domainDenylistFilter.filter("http://www.apache.org"));- Assert.assertNotNull(domainDenylistFilter.filter("http://www.google.com"));- Assert.assertNotNull(domainDenylistFilter.filter("http://mail.yahoo.com"));- Assert.assertNull(domainDenylistFilter.filter("http://www.foobar.net"));- Assert.assertNull(domainDenylistFilter.filter("http://www.foobas.net"));- Assert.assertNull(domainDenylistFilter.filter("http://www.yahoo.com"));- Assert.assertNull(domainDenylistFilter.filter("http://www.foobar.be"));- Assert.assertNotNull(domainDenylistFilter.filter("http://www.adobe.com"));+ assertNull(domainDenylistFilter.filter("http://lucene.apache.org"));+ assertNull(domainDenylistFilter.filter("http://hadoop.apache.org"));+ assertNull(domainDenylistFilter.filter("http://www.apache.org"));+ assertNotNull(domainDenylistFilter.filter("http://www.google.com"));+ assertNotNull(domainDenylistFilter.filter("http://mail.yahoo.com"));+ assertNull(domainDenylistFilter.filter("http://www.foobar.net"));+ assertNull(domainDenylistFilter.filter("http://www.foobas.net"));+ assertNull(domainDenylistFilter.filter("http://www.yahoo.com"));+ assertNull(domainDenylistFilter.filter("http://www.foobar.be"));+ assertNotNull(domainDenylistFilter.filter("http://www.adobe.com"));}}diff --git a/src/plugin/urlfilter-fast/src/test/org/apache/nutch/urlfilter/fast/TestFastURLFilter.java b/src/plugin/urlfilter-fast/src/test/org/apache/nutch/urlfilter/fast/TestFastURLFilter.javaindex 2c9ceea6f..82b13330e 100644--- a/src/plugin/urlfilter-fast/src/test/org/apache/nutch/urlfilter/fast/TestFastURLFilter.java+++ b/src/plugin/urlfilter-fast/src/test/org/apache/nutch/urlfilter/fast/TestFastURLFilter.java@@ -23,8 +23,9 @@ import java.io.StringReader;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLFilter;import org.apache.nutch.urlfilter.api.RegexURLFilterBaseTest;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;public class TestFastURLFilter extends RegexURLFilterBaseTest {@@ -33,7 +34,7 @@ public class TestFastURLFilter extends RegexURLFilterBaseTest {try {return new FastURLFilter(rules);} catch (IOException e) {- Assert.fail(e.toString());+ fail(e.toString());return null;}}@@ -65,14 +66,14 @@ public class TestFastURLFilter extends RegexURLFilterBaseTest {for (int i = 0; i < 50; i++) {url.append(i);}- Assert.assertEquals(null, filter.filter(url.toString()));+ assertNull(filter.filter(url.toString()));url = new StringBuilder("http://nutch.apache.org/path?");for (int i = 0; i < 50; i++) {url.append(i);}- Assert.assertEquals(null, filter.filter(url.toString()));+ assertNull(filter.filter(url.toString()));}@Test@@ -86,6 +87,6 @@ public class TestFastURLFilter extends RegexURLFilterBaseTest {for (int i = 0; i < 500; i++) {url.append(i);}- Assert.assertEquals(null, filter.filter(url.toString()));+ assertNull(filter.filter(url.toString()));}}diff --git a/src/plugin/urlfilter-prefix/src/test/org/apache/nutch/urlfilter/prefix/TestPrefixURLFilter.java b/src/plugin/urlfilter-prefix/src/test/org/apache/nutch/urlfilter/prefix/TestPrefixURLFilter.javaindex 0079fa7fd..ebf86d941 100644--- a/src/plugin/urlfilter-prefix/src/test/org/apache/nutch/urlfilter/prefix/TestPrefixURLFilter.java+++ b/src/plugin/urlfilter-prefix/src/test/org/apache/nutch/urlfilter/prefix/TestPrefixURLFilter.java@@ -16,13 +16,12 @@*/package org.apache.nutch.urlfilter.prefix;-import junit.framework.Test;-import junit.framework.TestCase;-import junit.framework.TestSuite;-import junit.textui.TestRunner;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import java.io.IOException;+import static org.junit.jupiter.api.Assertions.assertSame;/*** JUnit test for <code>PrefixURLFilter</code>.@@ -30,7 +29,7 @@ import java.io.IOException;* @author Talat Uyarer* @author Cihad Guzel*/-public class TestPrefixURLFilter extends TestCase {+public class TestPrefixURLFilter {private static final String prefixes ="# this is a comment\n" +"\n" +@@ -59,22 +58,15 @@ public class TestPrefixURLFilter extends TestCase {private PrefixURLFilter filter = null;- public static Test suite() {- return new TestSuite(TestPrefixURLFilter.class);- }-- public static void main(String[] args) {- TestRunner.run(suite());- }-- @Override+ @BeforeEachpublic void setUp() throws IOException {filter = new PrefixURLFilter(prefixes);}+ @Testpublic void testModeAccept() {for (int i = 0; i < urls.length; i++) {- assertTrue(urlsModeAccept[i] == filter.filter(urls[i]));+ assertSame(urlsModeAccept[i], filter.filter(urls[i]));}}}diff --git a/src/plugin/urlfilter-regex/src/test/org/apache/nutch/urlfilter/regex/TestRegexURLFilter.java b/src/plugin/urlfilter-regex/src/test/org/apache/nutch/urlfilter/regex/TestRegexURLFilter.javaindex bd0503eb4..cc79c003f 100644--- a/src/plugin/urlfilter-regex/src/test/org/apache/nutch/urlfilter/regex/TestRegexURLFilter.java+++ b/src/plugin/urlfilter-regex/src/test/org/apache/nutch/urlfilter/regex/TestRegexURLFilter.java@@ -23,8 +23,9 @@ import java.io.Reader;import org.apache.nutch.net.*;// Nutch importsimport org.apache.nutch.urlfilter.api.RegexURLFilterBaseTest;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.fail;/*** JUnit based test of class <code>RegexURLFilter</code>.@@ -38,7 +39,7 @@ public class TestRegexURLFilter extends RegexURLFilterBaseTest {try {return new RegexURLFilter(rules);} catch (IOException e) {- Assert.fail(e.toString());+ fail(e.toString());return null;}}diff --git a/src/plugin/urlfilter-suffix/src/test/org/apache/nutch/urlfilter/suffix/TestSuffixURLFilter.java b/src/plugin/urlfilter-suffix/src/test/org/apache/nutch/urlfilter/suffix/TestSuffixURLFilter.javaindex eecb2b2d7..bb9e62ae0 100644--- a/src/plugin/urlfilter-suffix/src/test/org/apache/nutch/urlfilter/suffix/TestSuffixURLFilter.java+++ b/src/plugin/urlfilter-suffix/src/test/org/apache/nutch/urlfilter/suffix/TestSuffixURLFilter.java@@ -19,9 +19,11 @@ package org.apache.nutch.urlfilter.suffix;import java.io.IOException;import java.io.StringReader;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertSame;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** JUnit test for <code>SuffixURLFilter</code>.@@ -59,7 +61,7 @@ public class TestSuffixURLFilter {private SuffixURLFilter filter = null;- @Before+ @BeforeEachpublic void setUp() throws IOException {filter = new SuffixURLFilter(new StringReader(suffixes));}@@ -69,7 +71,7 @@ public class TestSuffixURLFilter {filter.setIgnoreCase(false);filter.setModeAccept(true);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeAccept[i] == filter.filter(urls[i]));+ assertSame(urlsModeAccept[i], filter.filter(urls[i]));}}@@ -78,7 +80,7 @@ public class TestSuffixURLFilter {filter.setIgnoreCase(false);filter.setModeAccept(false);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeReject[i] == filter.filter(urls[i]));+ assertSame(urlsModeReject[i], filter.filter(urls[i]));}}@@ -87,7 +89,7 @@ public class TestSuffixURLFilter {filter.setIgnoreCase(true);filter.setModeAccept(true);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeAcceptIgnoreCase[i] == filter.filter(urls[i]));+ assertSame(urlsModeAcceptIgnoreCase[i], filter.filter(urls[i]));}}@@ -96,7 +98,7 @@ public class TestSuffixURLFilter {filter.setIgnoreCase(true);filter.setModeAccept(false);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeRejectIgnoreCase[i] == filter.filter(urls[i]));+ assertSame(urlsModeRejectIgnoreCase[i], filter.filter(urls[i]));}}@@ -105,8 +107,7 @@ public class TestSuffixURLFilter {filter.setModeAccept(true);filter.setFilterFromPath(false);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeAcceptAndNonPathFilter[i] == filter- .filter(urls[i]));+ assertSame(urlsModeAcceptAndNonPathFilter[i], filter.filter(urls[i]));}}@@ -115,8 +116,7 @@ public class TestSuffixURLFilter {filter.setModeAccept(true);filter.setFilterFromPath(true);for (int i = 0; i < urls.length; i++) {- Assert.assertTrue(urlsModeAcceptAndPathFilter[i] == filter- .filter(urls[i]));+ assertSame(urlsModeAcceptAndPathFilter[i], filter.filter(urls[i]));}}diff --git a/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java b/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.javaindex a52285bde..d815486de 100644--- a/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java+++ b/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java@@ -16,8 +16,10 @@*/package org.apache.nutch.urlfilter.validator;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertNotNull;+import static org.junit.jupiter.api.Assertions.assertNull;/*** JUnit test case which tests 1. that valid urls are not filtered while invalid@@ -38,41 +40,37 @@ public class TestUrlValidator {@Testpublic void testFilter() {UrlValidator url_validator = new UrlValidator();- Assert.assertNotNull(url_validator);+ assertNotNull(url_validator);- Assert.assertNull("Filtering on a null object should return null",- url_validator.filter(null));- Assert.assertNull("Invalid url: example.com/file[/].html",- url_validator.filter("example.com/file[/].html"));- Assert.assertNull("Invalid url: http://www.example.com/space here.html",- url_validator.filter("http://www.example.com/space here.html"));- Assert.assertNull("Invalid url: /main.html",- url_validator.filter("/main.html"));- Assert.assertNull("Invalid url: www.example.com/main.html",- url_validator.filter("www.example.com/main.html"));- Assert.assertNull("Invalid url: ftp:www.example.com/main.html",- url_validator.filter("ftp:www.example.com/main.html"));- Assert.assertNull(- "Inalid url: http://999.000.456.32/nutch/trunk/README.txt",- url_validator.filter("http://999.000.456.32/nutch/trunk/README.txt"));- Assert.assertNull("Invalid url: http://www.example.com/ma|in\\toc.html",- url_validator.filter(" http://www.example.com/ma|in\\toc.html"));+ assertNull(url_validator.filter(null),+ "Filtering on a null object should return null");+ assertNull(url_validator.filter("example.com/file[/].html"),+ "Invalid url: example.com/file[/].html");+ assertNull(url_validator.filter("http://www.example.com/space here.html"),+ "Invalid url: http://www.example.com/space here.html");+ assertNull(url_validator.filter("/main.html"),+ "Invalid url: /main.html");+ assertNull(url_validator.filter("www.example.com/main.html"),+ "Invalid url: www.example.com/main.html");+ assertNull(url_validator.filter("ftp:www.example.com/main.html"),+ "Invalid url: ftp:www.example.com/main.html");+ assertNull(+ url_validator.filter("http://999.000.456.32/nutch/trunk/README.txt"),+ "Inalid url: http://999.000.456.32/nutch/trunk/README.txt");+ assertNull(url_validator.filter(" http://www.example.com/ma|in\\toc.html"),+ "Invalid url: http://www.example.com/ma|in\\toc.html");- Assert.assertNotNull(- "Valid url: https://issues.apache.org/jira/NUTCH-1127",- url_validator.filter("https://issues.apache.org/jira/NUTCH-1127"));- Assert- .assertNotNull(- "Valid url: http://domain.tld/function.cgi?url=http://fonzi.com/&name=Fonzi&mood=happy&coat=leather",- url_validator- .filter("http://domain.tld/function.cgi?url=http://fonzi.com/&name=Fonzi&mood=happy&coat=leather"));- Assert- .assertNotNull(- "Valid url: http://validator.w3.org/feed/check.cgi?url=http%3A%2F%2Ffeeds.feedburner.com%2Fperishablepress",- url_validator- .filter("http://validator.w3.org/feed/check.cgi?url=http%3A%2F%2Ffeeds.feedburner.com%2Fperishablepress"));- Assert.assertNotNull("Valid url: ftp://alfa.bravo.pi/foo/bar/plan.pdf",- url_validator.filter("ftp://alfa.bravo.pi/mike/check/plan.pdf"));+ assertNotNull(+ url_validator.filter("https://issues.apache.org/jira/NUTCH-1127"),+ "Valid url: https://issues.apache.org/jira/NUTCH-1127");+ assertNotNull(url_validator+ .filter("http://domain.tld/function.cgi?url=http://fonzi.com/&name=Fonzi&mood=happy&coat=leather"),+ "Valid url: http://domain.tld/function.cgi?url=http://fonzi.com/&name=Fonzi&mood=happy&coat=leather");+ assertNotNull(url_validator+ .filter("http://validator.w3.org/feed/check.cgi?url=http%3A%2F%2Ffeeds.feedburner.com%2Fperishablepress"),+ "Valid url: http://validator.w3.org/feed/check.cgi?url=http%3A%2F%2Ffeeds.feedburner.com%2Fperishablepress");+ assertNotNull(url_validator.filter("ftp://alfa.bravo.pi/mike/check/plan.pdf"),+ "Valid url: ftp://alfa.bravo.pi/foo/bar/plan.pdf");}}diff --git a/src/plugin/urlnormalizer-ajax/src/test/org/apache/nutch/net/urlnormalizer/ajax/TestAjaxURLNormalizer.java b/src/plugin/urlnormalizer-ajax/src/test/org/apache/nutch/net/urlnormalizer/ajax/TestAjaxURLNormalizer.javaindex 5a1387970..310761e37 100644--- a/src/plugin/urlnormalizer-ajax/src/test/org/apache/nutch/net/urlnormalizer/ajax/TestAjaxURLNormalizer.java+++ b/src/plugin/urlnormalizer-ajax/src/test/org/apache/nutch/net/urlnormalizer/ajax/TestAjaxURLNormalizer.java@@ -19,21 +19,22 @@ package org.apache.nutch.net.urlnormalizer.ajax;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;+import org.junit.jupiter.api.Test;-import junit.framework.TestCase;+import static org.junit.jupiter.api.Assertions.assertEquals;/** Unit tests for AjaxURLNormalizer. */-public class TestAjaxURLNormalizer extends TestCase {+public class TestAjaxURLNormalizer {private AjaxURLNormalizer normalizer;private Configuration conf;- public TestAjaxURLNormalizer(String name) {- super(name);+ public TestAjaxURLNormalizer() {normalizer = new AjaxURLNormalizer();conf = NutchConfiguration.create();normalizer.setConf(conf);}+ @Testpublic void testNormalizer() throws Exception {// check if AJAX URL's are normalized to an _escaped_frament_ formnormalizeTest("http://example.org/#!k=v", "http://example.org/?_escaped_fragment_=k=v");@@ -44,7 +45,8 @@ public class TestAjaxURLNormalizer extends TestCase {// Check with query string and multiple fragment paramsnormalizeTest("http://example.org/path.html?queryparam=queryvalue#!key1=value1&key2=value2", "http://example.org/path.html?queryparam=queryvalue&_escaped_fragment_=key1=value1%26key2=value2");}-++ @Testpublic void testNormalizerWhenIndexing() throws Exception {// check if it works the other way aroundnormalizeTest("http://example.org/?_escaped_fragment_=key=value", "http://example.org/#!key=value", URLNormalizers.SCOPE_INDEXER);@@ -53,7 +55,8 @@ public class TestAjaxURLNormalizer extends TestCase {}private void normalizeTest(String weird, String normal) throws Exception {- assertEquals(normal, normalizer.normalize(weird, URLNormalizers.SCOPE_DEFAULT));+ assertEquals(normal,+ normalizer.normalize(weird, URLNormalizers.SCOPE_DEFAULT));}private void normalizeTest(String weird, String normal, String scope) throws Exception {@@ -61,6 +64,6 @@ public class TestAjaxURLNormalizer extends TestCase {}public static void main(String[] args) throws Exception {- new TestAjaxURLNormalizer("test").testNormalizer();+ new TestAjaxURLNormalizer().testNormalizer();}}diff --git a/src/plugin/urlnormalizer-basic/src/test/org/apache/nutch/net/urlnormalizer/basic/TestBasicURLNormalizer.java b/src/plugin/urlnormalizer-basic/src/test/org/apache/nutch/net/urlnormalizer/basic/TestBasicURLNormalizer.javaindex d48e58510..a6bad41f2 100644--- a/src/plugin/urlnormalizer-basic/src/test/org/apache/nutch/net/urlnormalizer/basic/TestBasicURLNormalizer.java+++ b/src/plugin/urlnormalizer-basic/src/test/org/apache/nutch/net/urlnormalizer/basic/TestBasicURLNormalizer.java@@ -23,8 +23,10 @@ import java.net.URL;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.fail;/** Unit tests for BasicURLNormalizer. */public class TestBasicURLNormalizer {@@ -295,12 +297,12 @@ public class TestBasicURLNormalizer {private void normalizeTest(BasicURLNormalizer normalizer, String weird,String normal) throws Exception {- Assert.assertEquals("normalizing: " + weird, normal,- normalizer.normalize(weird, URLNormalizers.SCOPE_DEFAULT));+ assertEquals(normal, normalizer.normalize(weird, URLNormalizers.SCOPE_DEFAULT),+ "normalizing: " + weird);try {(new URL(normal)).toURI();} catch (MalformedURLException | URISyntaxException e) {- Assert.fail("Output of normalization fails to validate as URL or URI: "+ fail("Output of normalization fails to validate as URL or URI: "+ e.getMessage());}}@@ -318,7 +320,7 @@ public class TestBasicURLNormalizer {// ok, expectedreturn;}- Assert.fail("Expected MalformedURLException was not thrown on " + weird+ fail("Expected MalformedURLException was not thrown on " + weird+ " (normalized: " + normalized + ")");}diff --git a/src/plugin/urlnormalizer-host/src/test/org/apache/nutch/net/urlnormalizer/host/TestHostURLNormalizer.java b/src/plugin/urlnormalizer-host/src/test/org/apache/nutch/net/urlnormalizer/host/TestHostURLNormalizer.javaindex 68cb50ab5..03df349d7 100644--- a/src/plugin/urlnormalizer-host/src/test/org/apache/nutch/net/urlnormalizer/host/TestHostURLNormalizer.java+++ b/src/plugin/urlnormalizer-host/src/test/org/apache/nutch/net/urlnormalizer/host/TestHostURLNormalizer.java@@ -19,8 +19,9 @@ package org.apache.nutch.net.urlnormalizer.host;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;public class TestHostURLNormalizer {@@ -37,22 +38,22 @@ public class TestHostURLNormalizer {normalizer.setConf(conf);// Force www. sub domain when hitting link without sub domain- Assert.assertEquals("http://www.example.org/page.html",+ assertEquals("http://www.example.org/page.html",normalizer.normalize("http://example.org/page.html",URLNormalizers.SCOPE_DEFAULT));// Force no sub domain to www. URL's- Assert.assertEquals("http://example.net/path/to/something.html", normalizer+ assertEquals("http://example.net/path/to/something.html", normalizer.normalize("http://www.example.net/path/to/something.html",URLNormalizers.SCOPE_DEFAULT));// Force all sub domains to www.- Assert.assertEquals("http://example.com/?does=it&still=work", normalizer+ assertEquals("http://example.com/?does=it&still=work", normalizer.normalize("http://example.com/?does=it&still=work",URLNormalizers.SCOPE_DEFAULT));- Assert.assertEquals("http://example.com/buh", normalizer.normalize(+ assertEquals("http://example.com/buh", normalizer.normalize("http://http.www.example.com/buh", URLNormalizers.SCOPE_DEFAULT));- Assert.assertEquals("http://example.com/blaat", normalizer.normalize(+ assertEquals("http://example.com/blaat", normalizer.normalize("http://whatever.example.com/blaat", URLNormalizers.SCOPE_DEFAULT));}}diff --git a/src/plugin/urlnormalizer-pass/src/test/org/apache/nutch/net/urlnormalizer/pass/TestPassURLNormalizer.java b/src/plugin/urlnormalizer-pass/src/test/org/apache/nutch/net/urlnormalizer/pass/TestPassURLNormalizer.javaindex f470c627e..83367a14e 100644--- a/src/plugin/urlnormalizer-pass/src/test/org/apache/nutch/net/urlnormalizer/pass/TestPassURLNormalizer.java+++ b/src/plugin/urlnormalizer-pass/src/test/org/apache/nutch/net/urlnormalizer/pass/TestPassURLNormalizer.java@@ -21,8 +21,10 @@ import java.net.MalformedURLException;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.fail;public class TestPassURLNormalizer {@@ -37,9 +39,9 @@ public class TestPassURLNormalizer {try {result = normalizer.normalize(url, URLNormalizers.SCOPE_DEFAULT);} catch (MalformedURLException mue) {- Assert.fail(mue.toString());+ fail(mue.toString());}- Assert.assertEquals(url, result);+ assertEquals(url, result);}}diff --git a/src/plugin/urlnormalizer-protocol/src/test/org/apache/nutch/net/urlnormalizer/protocol/TestProtocolURLNormalizer.java b/src/plugin/urlnormalizer-protocol/src/test/org/apache/nutch/net/urlnormalizer/protocol/TestProtocolURLNormalizer.javaindex 977525073..91e1fb70b 100644--- a/src/plugin/urlnormalizer-protocol/src/test/org/apache/nutch/net/urlnormalizer/protocol/TestProtocolURLNormalizer.java+++ b/src/plugin/urlnormalizer-protocol/src/test/org/apache/nutch/net/urlnormalizer/protocol/TestProtocolURLNormalizer.java@@ -20,14 +20,17 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;-import junit.framework.TestCase;+import org.junit.jupiter.api.Test;-public class TestProtocolURLNormalizer extends TestCase {+import static org.junit.jupiter.api.Assertions.assertEquals;++class TestProtocolURLNormalizer {private final static String SEPARATOR = System.getProperty("file.separator");private final static String SAMPLES = System.getProperty("test.data", ".");- public void testProtocolURLNormalizer() throws Exception {+ @Test+ void testProtocolURLNormalizer() throws Exception {Configuration conf = NutchConfiguration.create();String protocolsFile = SAMPLES + SEPARATOR + "protocols.txt";diff --git a/src/plugin/urlnormalizer-querystring/src/test/org/apache/nutch/net/urlnormalizer/querystring/TestQuerystringURLNormalizer.java b/src/plugin/urlnormalizer-querystring/src/test/org/apache/nutch/net/urlnormalizer/querystring/TestQuerystringURLNormalizer.javaindex e9a02cd2c..0029f5c71 100644--- a/src/plugin/urlnormalizer-querystring/src/test/org/apache/nutch/net/urlnormalizer/querystring/TestQuerystringURLNormalizer.java+++ b/src/plugin/urlnormalizer-querystring/src/test/org/apache/nutch/net/urlnormalizer/querystring/TestQuerystringURLNormalizer.java@@ -20,11 +20,14 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;-import junit.framework.TestCase;+import org.junit.jupiter.api.Test;-public class TestQuerystringURLNormalizer extends TestCase {+import static org.junit.jupiter.api.Assertions.assertEquals;- public void testQuerystringURLNormalizer() throws Exception {+class TestQuerystringURLNormalizer {++ @Test+ void testQuerystringURLNormalizer() throws Exception {Configuration conf = NutchConfiguration.create();QuerystringURLNormalizer normalizer = new QuerystringURLNormalizer();diff --git a/src/plugin/urlnormalizer-regex/src/test/org/apache/nutch/net/urlnormalizer/regex/TestRegexURLNormalizer.java b/src/plugin/urlnormalizer-regex/src/test/org/apache/nutch/net/urlnormalizer/regex/TestRegexURLNormalizer.javaindex 250ad2527..ed4b99abf 100644--- a/src/plugin/urlnormalizer-regex/src/test/org/apache/nutch/net/urlnormalizer/regex/TestRegexURLNormalizer.java+++ b/src/plugin/urlnormalizer-regex/src/test/org/apache/nutch/net/urlnormalizer/regex/TestRegexURLNormalizer.java@@ -27,8 +27,7 @@ import java.io.InputStreamReader;import java.util.*;import java.util.concurrent.TimeUnit;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.apache.commons.lang3.time.StopWatch;@@ -36,6 +35,9 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.fail;+/** Unit tests for RegexUrlNormalizer. */public class TestRegexURLNormalizer {private static final Logger LOG = LoggerFactory@@ -101,7 +103,7 @@ public class TestRegexURLNormalizer {String expected = urls[i].expectedURL;LOG.info("scope: {} url: {} | normalized: {} | expected: {}", scope, url,normalized, expected);- Assert.assertEquals(urls[i].expectedURL, normalized);+ assertEquals(urls[i].expectedURL, normalized);}}@@ -116,7 +118,7 @@ public class TestRegexURLNormalizer {normalizeTest(expected, scope);}} catch (Exception e) {- Assert.fail(e.toString());+ fail(e.toString());}stopWatch.stop();LOG.info("bench time ({}) {}ms", loops,diff --git a/src/plugin/urlnormalizer-slash/src/test/org/apache/nutch/net/urlnormalizer/slash/TestSlashURLNormalizer.java b/src/plugin/urlnormalizer-slash/src/test/org/apache/nutch/net/urlnormalizer/slash/TestSlashURLNormalizer.javaindex 54af2bf12..6e2e5d115 100644--- a/src/plugin/urlnormalizer-slash/src/test/org/apache/nutch/net/urlnormalizer/slash/TestSlashURLNormalizer.java+++ b/src/plugin/urlnormalizer-slash/src/test/org/apache/nutch/net/urlnormalizer/slash/TestSlashURLNormalizer.java@@ -19,15 +19,17 @@ package org.apache.nutch.net.urlnormalizer.slash;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.net.URLNormalizers;import org.apache.nutch.util.NutchConfiguration;+import org.junit.jupiter.api.Test;-import junit.framework.TestCase;+import static org.junit.jupiter.api.Assertions.assertEquals;-public class TestSlashURLNormalizer extends TestCase {+class TestSlashURLNormalizer {private final static String SEPARATOR = System.getProperty("file.separator");private final static String SAMPLES = System.getProperty("test.data", ".");- public void testSlashURLNormalizer() throws Exception {+ @Test+ void testSlashURLNormalizer() throws Exception {Configuration conf = NutchConfiguration.create();String slashesFile = SAMPLES + SEPARATOR + "slashes.txt";@@ -36,37 +38,53 @@ public class TestSlashURLNormalizer extends TestCase {normalizer.setConf(conf);// No change- assertEquals("http://example.org/", normalizer.normalize("http://example.org/", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.net/", normalizer.normalize("http://example.net/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.org/",+ normalizer.normalize("http://example.org/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.net/",+ normalizer.normalize("http://example.net/", URLNormalizers.SCOPE_DEFAULT));// Don't touch base URL's- assertEquals("http://example.org", normalizer.normalize("http://example.org", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.net", normalizer.normalize("http://example.net", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.org/", normalizer.normalize("http://example.org/", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.net/", normalizer.normalize("http://example.net/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.org",+ normalizer.normalize("http://example.org", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.net",+ normalizer.normalize("http://example.net", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.org/",+ normalizer.normalize("http://example.org/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.net/",+ normalizer.normalize("http://example.net/", URLNormalizers.SCOPE_DEFAULT));// Change- assertEquals("http://www.example.org/page/", normalizer.normalize("http://www.example.org/page", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.org/page/",+ normalizer.normalize("http://www.example.org/page", URLNormalizers.SCOPE_DEFAULT));assertEquals("http://www.example.net/path/to/something", normalizer.normalize("http://www.example.net/path/to/something/", URLNormalizers.SCOPE_DEFAULT));// No change- assertEquals("http://example.org/buh/", normalizer.normalize("http://example.org/buh/", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.net/blaat", normalizer.normalize("http://example.net/blaat", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.org/buh/",+ normalizer.normalize("http://example.org/buh/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.net/blaat",+ normalizer.normalize("http://example.net/blaat", URLNormalizers.SCOPE_DEFAULT));// No change- assertEquals("http://example.nl/buh/", normalizer.normalize("http://example.nl/buh/", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://example.de/blaat", normalizer.normalize("http://example.de/blaat", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.nl/buh/",+ normalizer.normalize("http://example.nl/buh/", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://example.de/blaat",+ normalizer.normalize("http://example.de/blaat", URLNormalizers.SCOPE_DEFAULT));// ChangeassertEquals("http://www.example.org/page/?a=b&c=d", normalizer.normalize("http://www.example.org/page?a=b&c=d", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://www.example.net/path/to/something?a=b&c=d", normalizer.normalize("http://www.example.net/path/to/something/?a=b&c=d", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.net/path/to/something?a=b&c=d",+ normalizer.normalize("http://www.example.net/path/to/something/?a=b&c=d", URLNormalizers.SCOPE_DEFAULT));// No change- assertEquals("http://www.example.org/noise.mp3", normalizer.normalize("http://www.example.org/noise.mp3", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://www.example.org/page.html", normalizer.normalize("http://www.example.org/page.html", URLNormalizers.SCOPE_DEFAULT));- assertEquals("http://www.example.org/page.shtml", normalizer.normalize("http://www.example.org/page.shtml", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.org/noise.mp3",+ normalizer.normalize("http://www.example.org/noise.mp3", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.org/page.html",+ normalizer.normalize("http://www.example.org/page.html", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.org/page.shtml",+ normalizer.normalize("http://www.example.org/page.shtml", URLNormalizers.SCOPE_DEFAULT));// Change- assertEquals("http://www.example.org/this.is.not.an_extension/", normalizer.normalize("http://www.example.org/this.is.not.an_extension", URLNormalizers.SCOPE_DEFAULT));+ assertEquals("http://www.example.org/this.is.not.an_extension/",+ normalizer.normalize("http://www.example.org/this.is.not.an_extension", URLNormalizers.SCOPE_DEFAULT));}}diff --git a/src/test/org/apache/nutch/crawl/ContinuousCrawlTestUtil.java b/src/test/org/apache/nutch/crawl/ContinuousCrawlTestUtil.javaindex c3dab2cee..f0971c2e1 100644--- a/src/test/org/apache/nutch/crawl/ContinuousCrawlTestUtil.java+++ b/src/test/org/apache/nutch/crawl/ContinuousCrawlTestUtil.java@@ -16,15 +16,6 @@*/package org.apache.nutch.crawl;-import java.io.IOException;-import java.lang.invoke.MethodHandles;-import java.util.ArrayList;-import java.util.Arrays;-import java.util.Date;-import java.util.List;--import junit.framework.TestCase;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Reducer;@@ -33,11 +24,20 @@ import org.apache.nutch.util.TimingUtil;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import java.io.IOException;+import java.lang.invoke.MethodHandles;+import java.util.ArrayList;+import java.util.Arrays;+import java.util.Date;+import java.util.List;++import static org.junit.jupiter.api.Assertions.*;+/*** Emulate a continuous crawl for one URL.**/-public class ContinuousCrawlTestUtil extends TestCase {+public class ContinuousCrawlTestUtil {private static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());@@ -239,9 +239,9 @@ public class ContinuousCrawlTestUtil extends TestCase {values.add(fetchDatum);values.addAll(parse(fetchDatum));List<CrawlDatum> res = updateDb.update(values);- assertNotNull("null returned", res);- assertFalse("no CrawlDatum", 0 == res.size());- assertEquals("more than one CrawlDatum", 1, res.size());+ assertNotNull(res, "null returned");+ assertNotEquals(0, res.size(), "no CrawlDatum");+ assertEquals(1, res.size(), "more than one CrawlDatum");if (!check(res.get(0))) {LOG.info("previously in CrawlDb: {}", copyDbDatum);LOG.info("after shouldFetch(): {}", afterShouldFetch);diff --git a/src/test/org/apache/nutch/crawl/TODOTestCrawlDbStates.java b/src/test/org/apache/nutch/crawl/TODOTestCrawlDbStates.javaindex 09863656d..dfad39351 100644--- a/src/test/org/apache/nutch/crawl/TODOTestCrawlDbStates.java+++ b/src/test/org/apache/nutch/crawl/TODOTestCrawlDbStates.java@@ -16,22 +16,19 @@*/package org.apache.nutch.crawl;-import java.io.IOException;-import java.lang.invoke.MethodHandles;--import static org.apache.nutch.crawl.CrawlDatum.*;-import org.apache.hadoop.conf.Configuration;-import org.apache.nutch.util.TimingUtil;-import org.apache.hadoop.mapreduce.Reducer.Context;--import static org.junit.Assert.*;--import org.junit.Test;+import org.apache.nutch.util.TimingUtil;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import java.io.IOException;+import java.lang.invoke.MethodHandles;++import static org.apache.nutch.crawl.CrawlDatum.*;+import static org.junit.jupiter.api.Assertions.fail;+public class TODOTestCrawlDbStates extends TestCrawlDbStates {private static final Logger LOG = LoggerFactorydiff --git a/src/test/org/apache/nutch/crawl/TestAdaptiveFetchSchedule.java b/src/test/org/apache/nutch/crawl/TestAdaptiveFetchSchedule.javaindex f83c8d9fb..377d49ec8 100644--- a/src/test/org/apache/nutch/crawl/TestAdaptiveFetchSchedule.java+++ b/src/test/org/apache/nutch/crawl/TestAdaptiveFetchSchedule.java@@ -16,19 +16,20 @@*/package org.apache.nutch.crawl;-import junit.framework.TestCase;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.io.Text;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.hamcrest.CoreMatchers.is;+import static org.hamcrest.MatcherAssert.assertThat;/*** Test cases for AdaptiveFetchSchedule.**/-public class TestAdaptiveFetchSchedule extends TestCase {+public class TestAdaptiveFetchSchedule {private float inc_rate;private float dec_rate;@@ -36,10 +37,8 @@ public class TestAdaptiveFetchSchedule extends TestCase {private long curTime, lastModified;private int changed, interval, calculateInterval;- @Override- @Before+ @BeforeEachpublic void setUp() throws Exception {- super.setUp();conf = NutchConfiguration.create();inc_rate = conf.getFloat("db.fetch.schedule.adaptive.inc_rate", 0.2f);dec_rate = conf.getFloat("db.fetch.schedule.adaptive.dec_rate", 0.2f);@@ -106,15 +105,15 @@ public class TestAdaptiveFetchSchedule extends TestCase {private void validateFetchInterval(int changed, int getInterval) {if (changed == FetchSchedule.STATUS_UNKNOWN) {- assertEquals(getInterval, interval);+ assertThat(interval, is(getInterval));} else if (changed == FetchSchedule.STATUS_MODIFIED) {calculateInterval = (int) (interval - (interval * dec_rate));- assertEquals(getInterval, calculateInterval);+ assertThat(calculateInterval, is(getInterval));} else if (changed == FetchSchedule.STATUS_NOTMODIFIED) {calculateInterval = (int) (interval + (interval * inc_rate));- assertEquals(getInterval, calculateInterval);+ assertThat(calculateInterval, is(getInterval));}}diff --git a/src/test/org/apache/nutch/crawl/TestCrawlDbDeduplication.java b/src/test/org/apache/nutch/crawl/TestCrawlDbDeduplication.javaindex 25850a936..646749db5 100644--- a/src/test/org/apache/nutch/crawl/TestCrawlDbDeduplication.java+++ b/src/test/org/apache/nutch/crawl/TestCrawlDbDeduplication.java@@ -16,10 +16,6 @@*/package org.apache.nutch.crawl;-import java.io.File;-import java.io.IOException;-import java.lang.invoke.MethodHandles;-import org.apache.commons.io.FileUtils;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileStatus;@@ -28,13 +24,18 @@ import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.Text;import org.apache.hadoop.util.ToolRunner;import org.apache.nutch.util.NutchConfiguration;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import java.io.File;+import java.io.IOException;+import java.lang.invoke.MethodHandles;++import static org.junit.jupiter.api.Assertions.*;+public class TestCrawlDbDeduplication {private static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());@@ -45,7 +46,7 @@ public class TestCrawlDbDeduplication {Path testCrawlDb;CrawlDbReader reader;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();fs = FileSystem.get(conf);@@ -62,7 +63,7 @@ public class TestCrawlDbDeduplication {reader = new CrawlDbReader();}- @After+ @AfterEachpublic void tearDown() {try {if (fs.exists(testCrawlDb))@@ -82,7 +83,7 @@ public class TestCrawlDbDeduplication {args[1] = "-compareOrder";args[2] = "fetchTime,urlLength,score";int result = ToolRunner.run(conf, new DeduplicationJob(), args);- Assert.assertEquals("DeduplicationJob did not succeed", 0, result);+ assertEquals(0, result, "DeduplicationJob did not succeed");String url1 = "http://nutch.apache.org/";String url2 = "https://nutch.apache.org/";// url1 has been fetched earlier, so it should "survive" as "db_fetched":@@ -97,7 +98,7 @@ public class TestCrawlDbDeduplication {args[1] = "-compareOrder";args[2] = "httpsOverHttp,fetchTime,urlLength,score";int result = ToolRunner.run(conf, new DeduplicationJob(), args);- Assert.assertEquals("DeduplicationJob did not succeed", 0, result);+ assertEquals(0, result, "DeduplicationJob did not succeed");String url1 = "http://nutch.apache.org/";String url2 = "https://nutch.apache.org/";// url2 is https://, so it should "survive" as "db_fetched":@@ -107,10 +108,10 @@ public class TestCrawlDbDeduplication {private void checkStatus(String url, byte status) throws IOException {CrawlDatum datum = reader.get(testCrawlDb.toString(), url, conf);- Assert.assertNotNull("No CrawlDatum found in CrawlDb for " + url, datum);- Assert.assertEquals(- "Expected status for " + url + ": " + CrawlDatum.getStatusName(status),- status, datum.getStatus());+ assertNotNull(datum, "No CrawlDatum found in CrawlDb for " + url);+ assertEquals(+ status, datum.getStatus(),+ "Expected status for " + url + ": " + CrawlDatum.getStatusName(status));}static class TestDedupReducer extends DeduplicationJob.DedupReducer<Text> {@@ -142,22 +143,22 @@ public class TestCrawlDbDeduplication {public void testCompareURLs() {// test same protocol, same length: no decision possibleString url0 = "https://example.com/";- Assert.assertNull(getDuplicateURL("httpsOverHttp,urlLength", url0, url0));+ assertNull(getDuplicateURL("httpsOverHttp,urlLength", url0, url0));String url1 = "http://nutch.apache.org/";String url2 = "https://nutch.apache.org/";// test httpsOverHttp- Assert.assertEquals(url1, getDuplicateURL("httpsOverHttp", url1, url2));+ assertEquals(url1, getDuplicateURL("httpsOverHttp", url1, url2));// test urlLength- Assert.assertEquals(url2, getDuplicateURL("urlLength", url1, url2));+ assertEquals(url2, getDuplicateURL("urlLength", url1, url2));// test urlLength with percent-encoded URLs// "b%C3%BCcher" (unescaped "bücher") is shorter than "buecher"String url3 = "https://example.com/b%C3%BCcher";String url4 = "https://example.com/buecher";- Assert.assertEquals(url4, getDuplicateURL("urlLength", url3, url4));+ assertEquals(url4, getDuplicateURL("urlLength", url3, url4));// test NUTCH-2935: should not throw error on invalid percent-encodingString url5 = "https://example.com/%YR";String url6 = "https://example.com/%YR%YR";- Assert.assertEquals(url6, getDuplicateURL("urlLength", url5, url6));+ assertEquals(url6, getDuplicateURL("urlLength", url5, url6));}}diff --git a/src/test/org/apache/nutch/crawl/TestCrawlDbFilter.java b/src/test/org/apache/nutch/crawl/TestCrawlDbFilter.javaindex 812d4a6a8..d18b3139f 100644--- a/src/test/org/apache/nutch/crawl/TestCrawlDbFilter.java+++ b/src/test/org/apache/nutch/crawl/TestCrawlDbFilter.java@@ -16,9 +16,6 @@*/package org.apache.nutch.crawl;-import java.io.IOException;-import java.util.ArrayList;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;@@ -26,15 +23,19 @@ import org.apache.hadoop.io.SequenceFile;import org.apache.hadoop.io.SequenceFile.Reader.Option;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Job;-import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;-import org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;+import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;+import org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat;import org.apache.nutch.crawl.CrawlDBTestUtil.URLCrawlDatum;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import java.io.IOException;+import java.util.ArrayList;++import static org.junit.jupiter.api.Assertions.assertEquals;/*** CrawlDbFiltering test which tests for correct, error free url normalization@@ -50,14 +51,14 @@ public class TestCrawlDbFilter {final static Path testdir = new Path("build/test/crawldbfilter-test");FileSystem fs;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = CrawlDBTestUtil.createContext().getConfiguration();fs = FileSystem.get(conf);fs.delete(testdir, true);}- @After+ @AfterEachpublic void tearDown() {delete(testdir);}@@ -114,7 +115,7 @@ public class TestCrawlDbFilter {ArrayList<URLCrawlDatum> l = readContents(fetchlist);// verify we got right amount of records- Assert.assertEquals(2, l.size());+ assertEquals(2, l.size());}/**diff --git a/src/test/org/apache/nutch/crawl/TestCrawlDbMerger.java b/src/test/org/apache/nutch/crawl/TestCrawlDbMerger.javaindex 7fb83f601..48892e49e 100644--- a/src/test/org/apache/nutch/crawl/TestCrawlDbMerger.java+++ b/src/test/org/apache/nutch/crawl/TestCrawlDbMerger.java@@ -16,25 +16,27 @@*/package org.apache.nutch.crawl;-import java.lang.invoke.MethodHandles;-import java.util.HashMap;-import java.util.Iterator;-import java.util.TreeSet;--import org.slf4j.Logger;-import org.slf4j.LoggerFactory;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.MapFile;+import org.apache.hadoop.io.MapFile.Writer.Option;import org.apache.hadoop.io.SequenceFile;import org.apache.hadoop.io.Text;-import org.apache.hadoop.io.MapFile.Writer.Option;import org.apache.nutch.util.NutchConfiguration;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;+import org.slf4j.Logger;+import org.slf4j.LoggerFactory;++import java.lang.invoke.MethodHandles;+import java.util.HashMap;+import java.util.Iterator;+import java.util.TreeSet;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;public class TestCrawlDbMerger {private static final Logger LOG = LoggerFactory@@ -55,7 +57,7 @@ public class TestCrawlDbMerger {Path testDir;CrawlDbReader reader;- @Before+ @BeforeEachpublic void setUp() throws Exception {init1.add(url10);init1.add(url11);@@ -85,7 +87,7 @@ public class TestCrawlDbMerger {fs.mkdirs(testDir);}- @After+ @AfterEachpublic void tearDown() {try {if (fs.exists(testDir))@@ -133,8 +135,8 @@ public class TestCrawlDbMerger {System.out.println(" cd " + cd);System.out.println(" res " + res);// may not be null- Assert.assertNotNull(res);- Assert.assertTrue(cd.equals(res));+ assertNotNull(res);+ assertEquals(cd, res);}reader.close();fs.delete(testDir, true);diff --git a/src/test/org/apache/nutch/crawl/TestCrawlDbStates.java b/src/test/org/apache/nutch/crawl/TestCrawlDbStates.javaindex c6aac88f9..bae7b29fd 100644--- a/src/test/org/apache/nutch/crawl/TestCrawlDbStates.java+++ b/src/test/org/apache/nutch/crawl/TestCrawlDbStates.java@@ -16,6 +16,17 @@*/package org.apache.nutch.crawl;+import org.apache.hadoop.conf.Configuration;+import org.apache.hadoop.io.Text;+import org.apache.hadoop.mapreduce.Reducer;+import org.apache.hadoop.mapreduce.Reducer.Context;+import org.apache.hadoop.util.StringUtils;+import org.apache.nutch.scoring.ScoringFilterException;+import org.apache.nutch.scoring.ScoringFilters;+import org.junit.jupiter.api.Test;+import org.slf4j.Logger;+import org.slf4j.LoggerFactory;+import java.io.IOException;import java.lang.invoke.MethodHandles;import java.util.ArrayList;@@ -23,24 +34,8 @@ import java.util.Date;import java.util.Iterator;import java.util.List;-import org.apache.hadoop.conf.Configuration;-import org.apache.hadoop.util.StringUtils;-import static org.apache.nutch.crawl.CrawlDatum.*;--import org.apache.nutch.scoring.ScoringFilterException;-import org.apache.nutch.scoring.ScoringFilters;--import org.apache.hadoop.mapreduce.Reducer;-import org.apache.hadoop.mapreduce.Reducer.Context;-import org.apache.hadoop.io.Text;--import static org.junit.Assert.*;--import org.junit.Test;--import org.slf4j.Logger;-import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.fail;/*** Test transitions of {@link CrawlDatum} states during an update ofdiff --git a/src/test/org/apache/nutch/crawl/TestGenerator.java b/src/test/org/apache/nutch/crawl/TestGenerator.javaindex 1003e40c5..cf4fa4955 100644--- a/src/test/org/apache/nutch/crawl/TestGenerator.java+++ b/src/test/org/apache/nutch/crawl/TestGenerator.java@@ -16,22 +16,24 @@*/package org.apache.nutch.crawl;-import java.io.IOException;-import java.util.ArrayList;-import java.util.Collections;-import java.util.Comparator;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.SequenceFile;-import org.apache.hadoop.io.Text;import org.apache.hadoop.io.SequenceFile.Reader.Option;+import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDBTestUtil.URLCrawlDatum;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import java.io.IOException;+import java.util.ArrayList;+import java.util.Collections;+import java.util.Comparator;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNull;/*** Basic generator test. 1. Insert entries in crawldb 2. Generates entries to@@ -51,14 +53,14 @@ public class TestGenerator {final static Path testdir = new Path("build/test/generator-test");- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = CrawlDBTestUtil.createContext().getConfiguration();fs = FileSystem.get(conf);fs.delete(testdir, true);}- @After+ @AfterEachpublic void tearDown() {delete(testdir);}@@ -99,11 +101,11 @@ public class TestGenerator {Collections.sort(l, new ScoreComparator());// verify we got right amount of records- Assert.assertEquals(NUM_RESULTS, l.size());+ assertEquals(NUM_RESULTS, l.size());// verify we have the highest scoring urls- Assert.assertEquals("http://aaa/100", (l.get(0).url.toString()));- Assert.assertEquals("http://aaa/099", (l.get(1).url.toString()));+ assertEquals("http://aaa/100", (l.get(0).url.toString()));+ assertEquals("http://aaa/099", (l.get(1).url.toString()));}private String pad(int i) {@@ -159,8 +161,8 @@ public class TestGenerator {// verify we got right amount of recordsint expectedFetchListSize = Math.min(maxPerHost, list.size());- Assert.assertEquals("Failed to apply generate.max.count by host",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by host");maxPerHost = 2;myConfiguration = new Configuration(conf);@@ -175,8 +177,8 @@ public class TestGenerator {// verify we got right amount of recordsexpectedFetchListSize = Math.min(maxPerHost, list.size());- Assert.assertEquals("Failed to apply generate.max.count by host",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by host");maxPerHost = 3;myConfiguration = new Configuration(conf);@@ -191,8 +193,8 @@ public class TestGenerator {// verify we got right amount of recordsexpectedFetchListSize = Math.min(maxPerHost, list.size());- Assert.assertEquals("Failed to apply generate.max.count by host",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by host");}/**@@ -227,8 +229,8 @@ public class TestGenerator {// verify we got right amount of recordsint expectedFetchListSize = Math.min(maxPerDomain, list.size());- Assert.assertEquals("Failed to apply generate.max.count by domain",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by domain");maxPerDomain = 2;myConfiguration = new Configuration(myConfiguration);@@ -243,8 +245,8 @@ public class TestGenerator {// verify we got right amount of recordsexpectedFetchListSize = Math.min(maxPerDomain, list.size());- Assert.assertEquals("Failed to apply generate.max.count by domain",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by domain");maxPerDomain = 3;myConfiguration = new Configuration(myConfiguration);@@ -259,8 +261,8 @@ public class TestGenerator {// verify we got right amount of recordsexpectedFetchListSize = Math.min(maxPerDomain, list.size());- Assert.assertEquals("Failed to apply generate.max.count by domain",- expectedFetchListSize, fetchList.size());+ assertEquals(expectedFetchListSize, fetchList.size(),+ "Failed to apply generate.max.count by domain");}/**@@ -286,7 +288,7 @@ public class TestGenerator {Path generatedSegment = generateFetchlist(Integer.MAX_VALUE,myConfiguration, true);- Assert.assertNull("should be null (0 entries)", generatedSegment);+ assertNull(generatedSegment, "should be null (0 entries)");generatedSegment = generateFetchlist(Integer.MAX_VALUE, myConfiguration,false);@@ -297,7 +299,7 @@ public class TestGenerator {ArrayList<URLCrawlDatum> fetchList = readContents(fetchlistPath);// verify nothing got filtered- Assert.assertEquals(list.size(), fetchList.size());+ assertEquals(list.size(), fetchList.size());}@@ -333,8 +335,8 @@ public class TestGenerator {ArrayList<URLCrawlDatum> fetchList = readContents(fetchlistPath);- Assert.assertEquals("Size of fetch list does not fit",- numValidURLs, fetchList.size());+ assertEquals(numValidURLs, fetchList.size(),+ "Size of fetch list does not fit");myConfiguration.set(Generator.GENERATOR_COUNT_MODE,Generator.GENERATOR_COUNT_VALUE_DOMAIN);@@ -347,8 +349,8 @@ public class TestGenerator {fetchList = readContents(fetchlistPath);- Assert.assertEquals("Size of fetch list does not fit",- numValidURLs, fetchList.size());+ assertEquals(numValidURLs, fetchList.size(),+ "Size of fetch list does not fit");}/**diff --git a/src/test/org/apache/nutch/crawl/TestInjector.java b/src/test/org/apache/nutch/crawl/TestInjector.javaindex c6db4ba77..74ccc44d0 100644--- a/src/test/org/apache/nutch/crawl/TestInjector.java+++ b/src/test/org/apache/nutch/crawl/TestInjector.java@@ -16,23 +16,21 @@*/package org.apache.nutch.crawl;-import java.io.IOException;-import java.util.ArrayList;-import java.util.Collections;-import java.util.HashMap;-import java.util.List;-import java.util.Map;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.SequenceFile;-import org.apache.hadoop.io.Text;import org.apache.hadoop.io.SequenceFile.Reader.Option;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.apache.hadoop.io.Text;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import java.io.IOException;+import java.util.*;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** Basic injector test: 1. Creates a text file with urls 2. Injects them into@@ -48,7 +46,7 @@ public class TestInjector {Path crawldbPath;Path urlPath;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = CrawlDBTestUtil.createContext().getConfiguration();urlPath = new Path(testdir, "urls");@@ -60,7 +58,7 @@ public class TestInjector {fs.delete(crawldbPath, true);}- @After+ @AfterEachpublic void tearDown() throws IOException {fs.delete(testdir, true);}@@ -88,10 +86,10 @@ public class TestInjector {Collections.sort(read);Collections.sort(urls);- Assert.assertEquals(urls.size(), read.size());+ assertEquals(urls.size(), read.size());- Assert.assertTrue(read.containsAll(urls));- Assert.assertTrue(urls.containsAll(read));+ assertTrue(read.containsAll(urls));+ assertTrue(urls.containsAll(read));// inject more urlsArrayList<String> urls2 = new ArrayList<String>();@@ -114,10 +112,10 @@ public class TestInjector {Collections.sort(urls);// We should have 100 less records because we've overwritten- Assert.assertEquals(urls.size() - 100, read.size());+ assertEquals(urls.size() - 100, read.size());- Assert.assertTrue(read.containsAll(urls));- Assert.assertTrue(urls.containsAll(read));+ assertTrue(read.containsAll(urls));+ assertTrue(urls.containsAll(read));// Check if we correctly preserved MDMap<String, CrawlDatum> records = readCrawldbRecords();@@ -129,11 +127,11 @@ public class TestInjector {for (String url : urls) {if (url.indexOf("http://zzz") == 0) {// Check for fetch interval- Assert.assertTrue(records.get(url).getFetchInterval() == 171717);+ assertEquals(171717, records.get(url).getFetchInterval());// Check for default score- Assert.assertTrue(records.get(url).getScore() != 1.0);+ assertTrue(records.get(url).getScore() != 1.0);// Check for MD key=value- Assert.assertEquals(writableValue,+ assertEquals(writableValue,records.get(url).getMetaData().get(writableKey));}}diff --git a/src/test/org/apache/nutch/crawl/TestLinkDbMerger.java b/src/test/org/apache/nutch/crawl/TestLinkDbMerger.javaindex 8e634c5b9..837090909 100644--- a/src/test/org/apache/nutch/crawl/TestLinkDbMerger.java+++ b/src/test/org/apache/nutch/crawl/TestLinkDbMerger.java@@ -16,27 +16,29 @@*/package org.apache.nutch.crawl;-import java.lang.invoke.MethodHandles;-import java.util.ArrayList;-import java.util.HashMap;-import java.util.Iterator;-import java.util.TreeMap;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.MapFile;+import org.apache.hadoop.io.MapFile.Writer.Option;import org.apache.hadoop.io.SequenceFile;import org.apache.hadoop.io.Text;-import org.apache.hadoop.io.MapFile.Writer.Option;import org.apache.nutch.util.NutchConfiguration;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import java.lang.invoke.MethodHandles;+import java.util.ArrayList;+import java.util.HashMap;+import java.util.Iterator;+import java.util.TreeMap;++import static org.junit.jupiter.api.Assertions.assertNotNull;+import static org.junit.jupiter.api.Assertions.assertTrue;+public class TestLinkDbMerger {private static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());@@ -68,7 +70,7 @@ public class TestLinkDbMerger {FileSystem fs;LinkDbReader reader;- @Before+ @BeforeEachpublic void setUp() throws Exception {init1.put(url10, urls10);init1.put(url11, urls11);@@ -85,7 +87,7 @@ public class TestLinkDbMerger {fs.mkdirs(testDir);}- @After+ @AfterEachpublic void tearDown() {try {if (fs.exists(testDir))@@ -120,7 +122,7 @@ public class TestLinkDbMerger {String[] vals = expected.get(url);Inlinks inlinks = reader.getInlinks(new Text(url));// may not be null- Assert.assertNotNull(inlinks);+ assertNotNull(inlinks);ArrayList<String> links = new ArrayList<String>();Iterator<?> it2 = inlinks.iterator();while (it2.hasNext()) {@@ -129,7 +131,7 @@ public class TestLinkDbMerger {}for (int i = 0; i < vals.length; i++) {LOG.debug(" -> {}", vals[i]);- Assert.assertTrue(links.contains(vals[i]));+ assertTrue(links.contains(vals[i]));}}reader.close();diff --git a/src/test/org/apache/nutch/crawl/TestSignatureFactory.java b/src/test/org/apache/nutch/crawl/TestSignatureFactory.javaindex db82d7acb..986fcf47d 100644--- a/src/test/org/apache/nutch/crawl/TestSignatureFactory.java+++ b/src/test/org/apache/nutch/crawl/TestSignatureFactory.java@@ -18,8 +18,10 @@ package org.apache.nutch.crawl;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;public class TestSignatureFactory {@@ -28,8 +30,8 @@ public class TestSignatureFactory {Configuration conf = NutchConfiguration.create();Signature signature1 = SignatureFactory.getSignature(conf);Signature signature2 = SignatureFactory.getSignature(conf);- Assert.assertNotNull(signature1);- Assert.assertNotNull(signature2);- Assert.assertEquals(signature1, signature2);+ assertNotNull(signature1);+ assertNotNull(signature2);+ assertEquals(signature1, signature2);}}diff --git a/src/test/org/apache/nutch/crawl/TestTextProfileSignature.java b/src/test/org/apache/nutch/crawl/TestTextProfileSignature.javaindex adf4b5e57..1d415b42f 100644--- a/src/test/org/apache/nutch/crawl/TestTextProfileSignature.java+++ b/src/test/org/apache/nutch/crawl/TestTextProfileSignature.java@@ -16,10 +16,6 @@*/package org.apache.nutch.crawl;-import java.util.Arrays;-import java.util.Collections;-import java.util.List;-import org.apache.hadoop.conf.Configuration;import org.apache.nutch.metadata.Metadata;import org.apache.nutch.parse.Outlink;@@ -29,8 +25,14 @@ import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;import org.apache.nutch.util.StringUtil;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import java.util.Arrays;+import java.util.Collections;+import java.util.List;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;public class TestTextProfileSignature {@@ -44,14 +46,14 @@ public class TestTextProfileSignature {new Outlink[0], new Metadata());byte[] signature1 = textProf.calculate(new Content(),new ParseImpl(text, pd));- Assert.assertNotNull(signature1);+ assertNotNull(signature1);List<String> words = Arrays.asList(text.split("\\s"));Collections.shuffle(words);String text2 = String.join(" ", words);byte[] signature2 = textProf.calculate(new Content(),new ParseImpl(text2, pd));- Assert.assertNotNull(signature2);- Assert.assertEquals(StringUtil.toHexString(signature1),+ assertNotNull(signature2);+ assertEquals(StringUtil.toHexString(signature1),StringUtil.toHexString(signature2));}}diff --git a/src/test/org/apache/nutch/fetcher/TestFetcher.java b/src/test/org/apache/nutch/fetcher/TestFetcher.javaindex 19e4104b2..f25cab545 100644--- a/src/test/org/apache/nutch/fetcher/TestFetcher.java+++ b/src/test/org/apache/nutch/fetcher/TestFetcher.java@@ -16,10 +16,6 @@*/package org.apache.nutch.fetcher;-import java.io.IOException;-import java.util.ArrayList;-import java.util.Collections;-import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;@@ -32,11 +28,17 @@ import org.apache.nutch.metadata.Metadata;import org.apache.nutch.metadata.Nutch;import org.apache.nutch.parse.ParseData;import org.apache.nutch.protocol.Content;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;import org.eclipse.jetty.server.Server;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import java.io.IOException;+import java.util.ArrayList;+import java.util.Collections;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;/*** Basic fetcher test 1. generate seedlist 2. inject 3. generate 3. fetch 4.@@ -53,7 +55,7 @@ public class TestFetcher {Path urlPath;Server server;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = CrawlDBTestUtil.createContext().getConfiguration();fs = FileSystem.get(conf);@@ -67,7 +69,7 @@ public class TestFetcher {server.start();}- @After+ @AfterEachpublic void tearDown() throws Exception {server.stop();for (int i = 0; i < 5; i++) {@@ -116,7 +118,7 @@ public class TestFetcher {// verify politeness, time taken should be more than (num_of_pages +1)*delayint minimumTime = (int) ((urls.size() + 1) * 1000 * conf.getFloat("fetcher.server.delay", 5));- Assert.assertTrue(time > minimumTime);+ assertTrue(time > minimumTime);// verify contentPath content = new Path(new Path(generatedSegment[0], Content.DIR_NAME),@@ -142,11 +144,11 @@ public class TestFetcher {Collections.sort(handledurls);// verify that enough pages were handled- Assert.assertEquals(urls.size(), handledurls.size());+ assertEquals(urls.size(), handledurls.size());// verify that correct pages were handled- Assert.assertTrue(handledurls.containsAll(urls));- Assert.assertTrue(urls.containsAll(handledurls));+ assertTrue(handledurls.containsAll(urls));+ assertTrue(urls.containsAll(handledurls));handledurls.clear();@@ -174,10 +176,10 @@ public class TestFetcher {Collections.sort(handledurls);- Assert.assertEquals(urls.size(), handledurls.size());+ assertEquals(urls.size(), handledurls.size());- Assert.assertTrue(handledurls.containsAll(urls));- Assert.assertTrue(urls.containsAll(handledurls));+ assertTrue(handledurls.containsAll(urls));+ assertTrue(urls.containsAll(handledurls));}private void addUrl(ArrayList<String> urls, String page) {@@ -201,7 +203,7 @@ public class TestFetcher {} catch (Exception e) {}- Assert.assertTrue(failedNoAgentName);+ assertTrue(failedNoAgentName);}}diff --git a/src/test/org/apache/nutch/indexer/TestIndexerMapReduce.java b/src/test/org/apache/nutch/indexer/TestIndexerMapReduce.javaindex 95a5b4115..c275b1941 100644--- a/src/test/org/apache/nutch/indexer/TestIndexerMapReduce.java+++ b/src/test/org/apache/nutch/indexer/TestIndexerMapReduce.java@@ -16,9 +16,10 @@*/package org.apache.nutch.indexer;-import java.lang.invoke.MethodHandles;-import org.apache.commons.codec.binary.Base64;+import org.apache.hadoop.conf.Configuration;+import org.apache.hadoop.io.Text;+import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mrunit.mapreduce.ReduceDriver;import org.apache.hadoop.mrunit.types.Pair;import org.apache.hadoop.util.StringUtils;@@ -32,22 +33,19 @@ import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.parse.ParseText;import org.apache.nutch.protocol.Content;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;-import org.apache.hadoop.io.Text;-import org.apache.hadoop.mapreduce.Reducer;--import static org.junit.Assert.*;-import java.io.IOException;+import java.lang.invoke.MethodHandles;import java.nio.charset.Charset;import java.nio.charset.StandardCharsets;import java.util.ArrayList;import java.util.List;-import org.apache.hadoop.conf.Configuration;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;/** Test {@link IndexerMapReduce} */public class TestIndexerMapReduce {@@ -128,7 +126,7 @@ public class TestIndexerMapReduce {NutchDocument doc = runIndexer(crawlDatumDbFetched,crawlDatumFetchSuccess, parseText, parseData, content);- assertNotNull("No NutchDocument indexed", doc);+ assertNotNull(doc, "No NutchDocument indexed");String binaryContentBase64 = (String) doc.getField("binaryContent").getValues().get(0);@@ -136,9 +134,8 @@ public class TestIndexerMapReduce {String binaryContent = new String(Base64.decodeBase64(binaryContentBase64), charset);LOG.info("binary content (decoded): {}", binaryContent);- assertEquals(- "Binary content (" + charset + ") not correctly saved as base64",- htmlDoc, binaryContent);+ assertEquals(htmlDoc, binaryContent,+ "Binary content (" + charset + ") not correctly saved as base64");}}diff --git a/src/test/org/apache/nutch/indexer/TestIndexingFilters.java b/src/test/org/apache/nutch/indexer/TestIndexingFilters.javaindex 4d5849fdc..f4a1b2cf7 100644--- a/src/test/org/apache/nutch/indexer/TestIndexingFilters.java+++ b/src/test/org/apache/nutch/indexer/TestIndexingFilters.java@@ -26,8 +26,10 @@ import org.apache.nutch.parse.ParseData;import org.apache.nutch.parse.ParseImpl;import org.apache.nutch.parse.ParseStatus;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNull;public class TestIndexingFilters {@@ -67,7 +69,7 @@ public class TestIndexingFilters {new Metadata())), new Text("http://www.example.com/"),new CrawlDatum(), new Inlinks());- Assert.assertNull(doc);+ assertNull(doc);}/**@@ -103,7 +105,7 @@ public class TestIndexingFilters {NutchDocument fdoc2 = filters2.filter(new NutchDocument(), new ParseImpl("text", new ParseData(new ParseStatus(), "title", new Outlink[0], md)),new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());- Assert.assertEquals(fdoc1.getFieldNames().size(), fdoc2.getFieldNames()+ assertEquals(fdoc1.getFieldNames().size(), fdoc2.getFieldNames().size());}diff --git a/src/test/org/apache/nutch/metadata/TestMetadata.java b/src/test/org/apache/nutch/metadata/TestMetadata.javaindex 0804e3e35..9c7791c72 100644--- a/src/test/org/apache/nutch/metadata/TestMetadata.java+++ b/src/test/org/apache/nutch/metadata/TestMetadata.java@@ -23,8 +23,9 @@ import java.io.DataOutputStream;import java.io.IOException;import java.util.Properties;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit based tests of class {@link org.apache.nutch.metadata.Metadata}.@@ -48,14 +49,14 @@ public class TestMetadata {met.add(CONTENTTYPE, "text/bogus2");met = writeRead(met);- Assert.assertNotNull(met);- Assert.assertEquals(met.size(), 1);+ assertNotNull(met);+ assertEquals(1, met.size());boolean hasBogus = false, hasBogus2 = false;String[] values = met.getValues(CONTENTTYPE);- Assert.assertNotNull(values);- Assert.assertEquals(values.length, 2);+ assertNotNull(values);+ assertEquals(2, values.length);for (int i = 0; i < values.length; i++) {if (values[i].equals("text/bogus")) {@@ -67,7 +68,7 @@ public class TestMetadata {}}- Assert.assertTrue(hasBogus && hasBogus2);+ assertTrue(hasBogus && hasBogus2);}/** Test for the <code>add(String, String)</code> method. */@@ -77,27 +78,27 @@ public class TestMetadata {Metadata meta = new Metadata();values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(0, values.length);+ assertEquals(0, values.length);meta.add(CONTENTTYPE, "value1");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1", values[0]);meta.add(CONTENTTYPE, "value2");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(2, values.length);- Assert.assertEquals("value1", values[0]);- Assert.assertEquals("value2", values[1]);+ assertEquals(2, values.length);+ assertEquals("value1", values[0]);+ assertEquals("value2", values[1]);// NOTE : For now, the same value can be added many times.// Should it be changed?meta.add(CONTENTTYPE, "value1");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(3, values.length);- Assert.assertEquals("value1", values[0]);- Assert.assertEquals("value2", values[1]);- Assert.assertEquals("value1", values[2]);+ assertEquals(3, values.length);+ assertEquals("value1", values[0]);+ assertEquals("value2", values[1]);+ assertEquals("value1", values[2]);}/** Test for the <code>set(String, String)</code> method. */@@ -107,24 +108,24 @@ public class TestMetadata {Metadata meta = new Metadata();values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(0, values.length);+ assertEquals(0, values.length);meta.set(CONTENTTYPE, "value1");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1", values[0]);meta.set(CONTENTTYPE, "value2");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(1, values.length);- Assert.assertEquals("value2", values[0]);+ assertEquals(1, values.length);+ assertEquals("value2", values[0]);meta.set(CONTENTTYPE, "new value 1");meta.add("contenttype", "new value 2");values = meta.getValues(CONTENTTYPE);- Assert.assertEquals(2, values.length);- Assert.assertEquals("new value 1", values[0]);- Assert.assertEquals("new value 2", values[1]);+ assertEquals(2, values.length);+ assertEquals("new value 1", values[0]);+ assertEquals("new value 2", values[1]);}/** Test for <code>setAll(Properties)</code> method. */@@ -135,46 +136,46 @@ public class TestMetadata {Properties props = new Properties();meta.setAll(props);- Assert.assertEquals(0, meta.size());+ assertEquals(0, meta.size());props.setProperty("name-one", "value1.1");meta.setAll(props);- Assert.assertEquals(1, meta.size());+ assertEquals(1, meta.size());values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1.1", values[0]);props.setProperty("name-two", "value2.1");meta.setAll(props);- Assert.assertEquals(2, meta.size());+ assertEquals(2, meta.size());values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1.1", values[0]);values = meta.getValues("name-two");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value2.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value2.1", values[0]);}/** Test for <code>get(String)</code> method. */@Testpublic void testGet() {Metadata meta = new Metadata();- Assert.assertNull(meta.get("a-name"));+ assertNull(meta.get("a-name"));meta.add("a-name", "value-1");- Assert.assertEquals("value-1", meta.get("a-name"));+ assertEquals("value-1", meta.get("a-name"));meta.add("a-name", "value-2");- Assert.assertEquals("value-1", meta.get("a-name"));+ assertEquals("value-1", meta.get("a-name"));}/** Test for <code>isMultiValued()</code> method. */@Testpublic void testIsMultiValued() {Metadata meta = new Metadata();- Assert.assertFalse(meta.isMultiValued("key"));+ assertFalse(meta.isMultiValued("key"));meta.add("key", "value1");- Assert.assertFalse(meta.isMultiValued("key"));+ assertFalse(meta.isMultiValued("key"));meta.add("key", "value2");- Assert.assertTrue(meta.isMultiValued("key"));+ assertTrue(meta.isMultiValued("key"));}/** Test for <code>names</code> method. */@@ -183,15 +184,15 @@ public class TestMetadata {String[] names = null;Metadata meta = new Metadata();names = meta.names();- Assert.assertEquals(0, names.length);+ assertEquals(0, names.length);meta.add("name-one", "value");names = meta.names();- Assert.assertEquals(1, names.length);- Assert.assertEquals("name-one", names[0]);+ assertEquals(1, names.length);+ assertEquals("name-one", names[0]);meta.add("name-two", "value");names = meta.names();- Assert.assertEquals(2, names.length);+ assertEquals(2, names.length);}/** Test for <code>remove(String)</code> method. */@@ -199,21 +200,21 @@ public class TestMetadata {public void testRemove() {Metadata meta = new Metadata();meta.remove("name-one");- Assert.assertEquals(0, meta.size());+ assertEquals(0, meta.size());meta.add("name-one", "value-1.1");meta.add("name-one", "value-1.2");meta.add("name-two", "value-2.2");- Assert.assertEquals(2, meta.size());- Assert.assertNotNull(meta.get("name-one"));- Assert.assertNotNull(meta.get("name-two"));+ assertEquals(2, meta.size());+ assertNotNull(meta.get("name-one"));+ assertNotNull(meta.get("name-two"));meta.remove("name-one");- Assert.assertEquals(1, meta.size());- Assert.assertNull(meta.get("name-one"));- Assert.assertNotNull(meta.get("name-two"));+ assertEquals(1, meta.size());+ assertNull(meta.get("name-one"));+ assertNotNull(meta.get("name-two"));meta.remove("name-two");- Assert.assertEquals(0, meta.size());- Assert.assertNull(meta.get("name-one"));- Assert.assertNull(meta.get("name-two"));+ assertEquals(0, meta.size());+ assertNull(meta.get("name-one"));+ assertNull(meta.get("name-two"));}/** Test for <code>equals(Object)</code> method. */@@ -221,25 +222,25 @@ public class TestMetadata {public void testObject() {Metadata meta1 = new Metadata();Metadata meta2 = new Metadata();- Assert.assertFalse(meta1.equals(null));- Assert.assertFalse(meta1.equals("String"));- Assert.assertTrue(meta1.equals(meta2));+ assertNotNull(meta1);+ assertNotEquals("String", meta1);+ assertEquals(meta1, meta2);meta1.add("name-one", "value-1.1");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-one", "value-1.1");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-one", "value-1.2");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-one", "value-1.2");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-two", "value-2.1");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-two", "value-2.1");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-two", "value-2.2");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-two", "value-2.x");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);}/** Test for <code>Writable</code> implementation. */@@ -248,21 +249,21 @@ public class TestMetadata {Metadata result = null;Metadata meta = new Metadata();result = writeRead(meta);- Assert.assertEquals(0, result.size());+ assertEquals(0, result.size());meta.add("name-one", "value-1.1");result = writeRead(meta);- Assert.assertEquals(1, result.size());- Assert.assertEquals(1, result.getValues("name-one").length);- Assert.assertEquals("value-1.1", result.get("name-one"));+ assertEquals(1, result.size());+ assertEquals(1, result.getValues("name-one").length);+ assertEquals("value-1.1", result.get("name-one"));meta.add("name-two", "value-2.1");meta.add("name-two", "value-2.2");result = writeRead(meta);- Assert.assertEquals(2, result.size());- Assert.assertEquals(1, result.getValues("name-one").length);- Assert.assertEquals("value-1.1", result.getValues("name-one")[0]);- Assert.assertEquals(2, result.getValues("name-two").length);- Assert.assertEquals("value-2.1", result.getValues("name-two")[0]);- Assert.assertEquals("value-2.2", result.getValues("name-two")[1]);+ assertEquals(2, result.size());+ assertEquals(1, result.getValues("name-one").length);+ assertEquals("value-1.1", result.getValues("name-one")[0]);+ assertEquals(2, result.getValues("name-two").length);+ assertEquals("value-2.1", result.getValues("name-two")[0]);+ assertEquals("value-2.2", result.getValues("name-two")[1]);}private Metadata writeRead(Metadata meta) {@@ -273,7 +274,7 @@ public class TestMetadata {readed.readFields(new DataInputStream(new ByteArrayInputStream(out.toByteArray())));} catch (IOException ioe) {- Assert.fail(ioe.toString());+ fail(ioe.toString());}return readed;}diff --git a/src/test/org/apache/nutch/metadata/TestSpellCheckedMetadata.java b/src/test/org/apache/nutch/metadata/TestSpellCheckedMetadata.javaindex 9041736ae..b33d51447 100644--- a/src/test/org/apache/nutch/metadata/TestSpellCheckedMetadata.java+++ b/src/test/org/apache/nutch/metadata/TestSpellCheckedMetadata.java@@ -24,8 +24,9 @@ import java.io.IOException;import java.util.HashMap;import java.util.Properties;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** JUnit based tests of class@@ -41,17 +42,17 @@ public class TestSpellCheckedMetadata {/** Test for the <code>getNormalizedName(String)</code> method. */@Testpublic void testGetNormalizedName() {- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("Content-Type"));- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("ContentType"));- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("Content-type"));- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("contenttype"));- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("contentype"));- Assert.assertEquals("Content-Type",+ assertEquals("Content-Type",SpellCheckedMetadata.getNormalizedName("contntype"));}@@ -62,27 +63,27 @@ public class TestSpellCheckedMetadata {SpellCheckedMetadata meta = new SpellCheckedMetadata();values = meta.getValues("contentype");- Assert.assertEquals(0, values.length);+ assertEquals(0, values.length);meta.add("contentype", "value1");values = meta.getValues("contentype");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1", values[0]);meta.add("Content-Type", "value2");values = meta.getValues("contentype");- Assert.assertEquals(2, values.length);- Assert.assertEquals("value1", values[0]);- Assert.assertEquals("value2", values[1]);+ assertEquals(2, values.length);+ assertEquals("value1", values[0]);+ assertEquals("value2", values[1]);// NOTE : For now, the same value can be added many times.// Should it be changed?meta.add("ContentType", "value1");values = meta.getValues("Content-Type");- Assert.assertEquals(3, values.length);- Assert.assertEquals("value1", values[0]);- Assert.assertEquals("value2", values[1]);- Assert.assertEquals("value1", values[2]);+ assertEquals(3, values.length);+ assertEquals("value1", values[0]);+ assertEquals("value2", values[1]);+ assertEquals("value1", values[2]);}/** Test for the <code>set(String, String)</code> method. */@@ -92,24 +93,24 @@ public class TestSpellCheckedMetadata {SpellCheckedMetadata meta = new SpellCheckedMetadata();values = meta.getValues("contentype");- Assert.assertEquals(0, values.length);+ assertEquals(0, values.length);meta.set("contentype", "value1");values = meta.getValues("contentype");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1", values[0]);meta.set("Content-Type", "value2");values = meta.getValues("contentype");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value2", values[0]);+ assertEquals(1, values.length);+ assertEquals("value2", values[0]);meta.set("contenttype", "new value 1");meta.add("contenttype", "new value 2");values = meta.getValues("contentype");- Assert.assertEquals(2, values.length);- Assert.assertEquals("new value 1", values[0]);- Assert.assertEquals("new value 2", values[1]);+ assertEquals(2, values.length);+ assertEquals("new value 1", values[0]);+ assertEquals("new value 2", values[1]);}/** Test for the <code>set(String, String)</code> method. */@@ -119,24 +120,24 @@ public class TestSpellCheckedMetadata {SpellCheckedMetadata meta = new SpellCheckedMetadata();values = meta.getValues("name-one");- Assert.assertEquals(0, values.length);+ assertEquals(0, values.length);meta.set("name-one", "value1");values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1", values[0]);meta.set("naMe-OnE", "value2");values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value2", values[0]);+ assertEquals(1, values.length);+ assertEquals("value2", values[0]);meta.set("nAme-One", "new value 1");meta.add("NamE-oNe", "new value 2");values = meta.getValues("namE-OnE");- Assert.assertEquals(2, values.length);- Assert.assertEquals("new value 1", values[0]);- Assert.assertEquals("new value 2", values[1]);+ assertEquals(2, values.length);+ assertEquals("new value 1", values[0]);+ assertEquals("new value 2", values[1]);}/** Test for <code>setAll(Properties)</code> method. */@@ -147,60 +148,60 @@ public class TestSpellCheckedMetadata {Properties props = new Properties();meta.setAll(props);- Assert.assertEquals(0, meta.size());+ assertEquals(0, meta.size());props.setProperty("name-one", "value1.1");meta.setAll(props);- Assert.assertEquals(1, meta.size());+ assertEquals(1, meta.size());values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1.1", values[0]);props.setProperty("name-two", "value2.1");meta.setAll(props);- Assert.assertEquals(2, meta.size());+ assertEquals(2, meta.size());values = meta.getValues("name-one");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value1.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value1.1", values[0]);values = meta.getValues("name-two");- Assert.assertEquals(1, values.length);- Assert.assertEquals("value2.1", values[0]);+ assertEquals(1, values.length);+ assertEquals("value2.1", values[0]);}/** Test for <code>get(String)</code> method. */@Testpublic void testGet() {SpellCheckedMetadata meta = new SpellCheckedMetadata();- Assert.assertNull(meta.get("a-name"));+ assertNull(meta.get("a-name"));meta.add("a-name", "value-1");- Assert.assertEquals("value-1", meta.get("a-name"));+ assertEquals("value-1", meta.get("a-name"));meta.add("a-name", "value-2");- Assert.assertEquals("value-1", meta.get("a-name"));+ assertEquals("value-1", meta.get("a-name"));}/** Test for <code>get(String)</code> method. */@Testpublic void testGetCaseInsensitive() {SpellCheckedMetadata meta = new SpellCheckedMetadata();- Assert.assertNull(meta.get("a-name"));+ assertNull(meta.get("a-name"));meta.add("a-name", "value-1");- Assert.assertEquals("value-1", meta.get("a-name"));+ assertEquals("value-1", meta.get("a-name"));- Assert.assertNotNull(meta.get("a-NamE"));- Assert.assertEquals("value-1", meta.get("a-NamE"));+ assertNotNull(meta.get("a-NamE"));+ assertEquals("value-1", meta.get("a-NamE"));}/** Test for <code>isMultiValued()</code> method. */@Testpublic void testIsMultiValued() {SpellCheckedMetadata meta = new SpellCheckedMetadata();- Assert.assertFalse(meta.isMultiValued("key"));+ assertFalse(meta.isMultiValued("key"));meta.add("key", "value1");- Assert.assertFalse(meta.isMultiValued("key"));+ assertFalse(meta.isMultiValued("key"));meta.add("key", "value2");- Assert.assertTrue(meta.isMultiValued("key"));+ assertTrue(meta.isMultiValued("key"));}/** Test for <code>names</code> method. */@@ -209,15 +210,15 @@ public class TestSpellCheckedMetadata {String[] names = null;SpellCheckedMetadata meta = new SpellCheckedMetadata();names = meta.names();- Assert.assertEquals(0, names.length);+ assertEquals(0, names.length);meta.add("name-one", "value");names = meta.names();- Assert.assertEquals(1, names.length);- Assert.assertEquals("name-one", names[0]);+ assertEquals(1, names.length);+ assertEquals("name-one", names[0]);meta.add("name-two", "value");names = meta.names();- Assert.assertEquals(2, names.length);+ assertEquals(2, names.length);}/** Test for <code>remove(String)</code> method. */@@ -225,21 +226,21 @@ public class TestSpellCheckedMetadata {public void testRemove() {SpellCheckedMetadata meta = new SpellCheckedMetadata();meta.remove("name-one");- Assert.assertEquals(0, meta.size());+ assertEquals(0, meta.size());meta.add("name-one", "value-1.1");meta.add("name-one", "value-1.2");meta.add("name-two", "value-2.2");- Assert.assertEquals(2, meta.size());- Assert.assertNotNull(meta.get("name-one"));- Assert.assertNotNull(meta.get("name-two"));+ assertEquals(2, meta.size());+ assertNotNull(meta.get("name-one"));+ assertNotNull(meta.get("name-two"));meta.remove("name-one");- Assert.assertEquals(1, meta.size());- Assert.assertNull(meta.get("name-one"));- Assert.assertNotNull(meta.get("name-two"));+ assertEquals(1, meta.size());+ assertNull(meta.get("name-one"));+ assertNotNull(meta.get("name-two"));meta.remove("name-two");- Assert.assertEquals(0, meta.size());- Assert.assertNull(meta.get("name-one"));- Assert.assertNull(meta.get("name-two"));+ assertEquals(0, meta.size());+ assertNull(meta.get("name-one"));+ assertNull(meta.get("name-two"));}/** Test for <code>equals(Object)</code> method. */@@ -247,25 +248,25 @@ public class TestSpellCheckedMetadata {public void testObject() {SpellCheckedMetadata meta1 = new SpellCheckedMetadata();SpellCheckedMetadata meta2 = new SpellCheckedMetadata();- Assert.assertFalse(meta1.equals(null));- Assert.assertFalse(meta1.equals("String"));- Assert.assertTrue(meta1.equals(meta2));+ assertNotEquals(null, meta1);+ assertNotEquals("String", meta1);+ assertEquals(meta1, meta2);meta1.add("name-one", "value-1.1");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-one", "value-1.1");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-one", "value-1.2");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-one", "value-1.2");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-two", "value-2.1");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-two", "value-2.1");- Assert.assertTrue(meta1.equals(meta2));+ assertEquals(meta1, meta2);meta1.add("name-two", "value-2.2");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);meta2.add("name-two", "value-2.x");- Assert.assertFalse(meta1.equals(meta2));+ assertNotEquals(meta1, meta2);}/** Test for <code>Writable</code> implementation. */@@ -274,23 +275,23 @@ public class TestSpellCheckedMetadata {SpellCheckedMetadata result = null;SpellCheckedMetadata meta = new SpellCheckedMetadata();result = writeRead(meta);- Assert.assertEquals(0, result.size());+ assertEquals(0, result.size());meta.add("name-one", "value-1.1");result = writeRead(meta);meta.add("Contenttype", "text/html");- Assert.assertEquals(1, result.size());- Assert.assertEquals(1, result.getValues("name-one").length);- Assert.assertEquals("value-1.1", result.get("name-one"));+ assertEquals(1, result.size());+ assertEquals(1, result.getValues("name-one").length);+ assertEquals("value-1.1", result.get("name-one"));meta.add("name-two", "value-2.1");meta.add("name-two", "value-2.2");result = writeRead(meta);- Assert.assertEquals(3, result.size());- Assert.assertEquals(1, result.getValues("name-one").length);- Assert.assertEquals("value-1.1", result.getValues("name-one")[0]);- Assert.assertEquals(2, result.getValues("name-two").length);- Assert.assertEquals("value-2.1", result.getValues("name-two")[0]);- Assert.assertEquals("value-2.2", result.getValues("name-two")[1]);- Assert.assertEquals("text/html", result.get(Metadata.CONTENT_TYPE));+ assertEquals(3, result.size());+ assertEquals(1, result.getValues("name-one").length);+ assertEquals("value-1.1", result.getValues("name-one")[0]);+ assertEquals(2, result.getValues("name-two").length);+ assertEquals("value-2.1", result.getValues("name-two")[0]);+ assertEquals("value-2.2", result.getValues("name-two")[1]);+ assertEquals("text/html", result.get(Metadata.CONTENT_TYPE));}/** Test for <code>Writable</code> implementation. */@@ -302,30 +303,30 @@ public class TestSpellCheckedMetadata {CaseSensitiveSpellCheckedMetadata meta = new CaseSensitiveSpellCheckedMetadata();result = writeRead(meta);- Assert.assertEquals(0, result.size());+ assertEquals(0, result.size());meta.add("name-One", "value-1.1");// Check that the original case is kept for old Metadata class- Assert.assertEquals(0, result.getValues("naMe-one").length);+ assertEquals(0, result.getValues("naMe-one").length);// Check that the values written by old instances can be// read by new instances of SpellCheckedMetadataresult = writeRead(meta);- Assert.assertEquals(1, result.size());- Assert.assertEquals(1, result.getValues("naMe-one").length);- Assert.assertEquals("value-1.1", result.get("nAme-oNe"));+ assertEquals(1, result.size());+ assertEquals(1, result.getValues("naMe-one").length);+ assertEquals("value-1.1", result.get("nAme-oNe"));meta.add("Contenttype", "text/html");meta.add("name-Two", "value-2.1");meta.add("namE-two", "value-2.2");result = writeRead(meta);- Assert.assertEquals(3, result.size());- Assert.assertEquals(1, result.getValues("name-onE").length);- Assert.assertEquals("value-1.1", result.getValues("namE-one")[0]);- Assert.assertEquals(2, result.getValues("name-two").length);- Assert.assertEquals("value-2.1", result.getValues("nAme-tWo")[0]);- Assert.assertEquals("value-2.2", result.getValues("namE-Two")[1]);- Assert.assertEquals("text/html", result.get(Metadata.CONTENT_TYPE));+ assertEquals(3, result.size());+ assertEquals(1, result.getValues("name-onE").length);+ assertEquals("value-1.1", result.getValues("namE-one")[0]);+ assertEquals(2, result.getValues("name-two").length);+ assertEquals("value-2.1", result.getValues("nAme-tWo")[0]);+ assertEquals("value-2.2", result.getValues("namE-Two")[1]);+ assertEquals("text/html", result.get(Metadata.CONTENT_TYPE));}/**@@ -363,7 +364,7 @@ public class TestSpellCheckedMetadata {readed.readFields(new DataInputStream(new ByteArrayInputStream(out.toByteArray())));} catch (IOException ioe) {- Assert.fail(ioe.toString());+ fail(ioe.toString());}return readed;}diff --git a/src/test/org/apache/nutch/net/TestURLFilters.java b/src/test/org/apache/nutch/net/TestURLFilters.javaindex c43941a94..00c9b1489 100644--- a/src/test/org/apache/nutch/net/TestURLFilters.java+++ b/src/test/org/apache/nutch/net/TestURLFilters.java@@ -18,7 +18,7 @@ package org.apache.nutch.net;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Test;+import org.junit.jupiter.api.Test;public class TestURLFilters {diff --git a/src/test/org/apache/nutch/net/TestURLNormalizers.java b/src/test/org/apache/nutch/net/TestURLNormalizers.javaindex 6fdbb9d88..3427109d1 100644--- a/src/test/org/apache/nutch/net/TestURLNormalizers.java+++ b/src/test/org/apache/nutch/net/TestURLNormalizers.java@@ -20,8 +20,9 @@ import java.net.MalformedURLException;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;public class TestURLNormalizers {@@ -35,12 +36,12 @@ public class TestURLNormalizers {URLNormalizers normalizers = new URLNormalizers(conf,URLNormalizers.SCOPE_DEFAULT);- Assert.assertNotNull(normalizers);+ assertNotNull(normalizers);try {normalizers.normalize("http://www.example.com/",URLNormalizers.SCOPE_DEFAULT);} catch (MalformedURLException mue) {- Assert.fail(mue.toString());+ fail(mue.toString());}// NUTCH-1011 - Get rid of superfluous slashes@@ -48,10 +49,10 @@ public class TestURLNormalizers {String normalizedSlashes = normalizers.normalize("http://www.example.com//path/to//somewhere.html",URLNormalizers.SCOPE_DEFAULT);- Assert.assertEquals(normalizedSlashes,- "http://www.example.com/path/to/somewhere.html");+ assertEquals("http://www.example.com/path/to/somewhere.html",+ normalizedSlashes);} catch (MalformedURLException mue) {- Assert.fail(mue.toString());+ fail(mue.toString());}// HostNormalizer NUTCH-1319@@ -59,10 +60,10 @@ public class TestURLNormalizers {String normalizedHost = normalizers.normalize("http://www.example.org//path/to//somewhere.html",URLNormalizers.SCOPE_DEFAULT);- Assert.assertEquals(normalizedHost,- "http://www.example.org/path/to/somewhere.html");+ assertEquals("http://www.example.org/path/to/somewhere.html",+ normalizedHost);} catch (MalformedURLException mue) {- Assert.fail(mue.toString());+ fail(mue.toString());}// check the order@@ -76,8 +77,7 @@ public class TestURLNormalizers {pos2 = i;}if (pos1 != -1 && pos2 != -1) {- Assert.assertTrue("RegexURLNormalizer before BasicURLNormalizer",- pos1 < pos2);+ assertTrue(pos1 < pos2, "RegexURLNormalizer before BasicURLNormalizer");}}}diff --git a/src/test/org/apache/nutch/net/protocols/TestHttpDateFormat.java b/src/test/org/apache/nutch/net/protocols/TestHttpDateFormat.javaindex 94f30c3e6..818d35b30 100644--- a/src/test/org/apache/nutch/net/protocols/TestHttpDateFormat.java+++ b/src/test/org/apache/nutch/net/protocols/TestHttpDateFormat.java@@ -19,8 +19,13 @@ package org.apache.nutch.net.protocols;import java.text.ParseException;import java.util.Date;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;+import static org.junit.jupiter.api.Assertions.assertThrows;+import static org.junit.jupiter.api.Assertions.assertTrue;+import static org.junit.jupiter.api.Assertions.assertEquals;++import static org.hamcrest.CoreMatchers.is;+import static org.hamcrest.MatcherAssert.assertThat;public class TestHttpDateFormat {@@ -38,18 +43,25 @@ public class TestHttpDateFormat {@Testpublic void testHttpDateFormat() throws ParseException {- Assert.assertEquals(dateMillis, HttpDateFormat.toLong(dateString));- Assert.assertEquals(dateString, HttpDateFormat.toString(dateMillis));- Assert.assertEquals(new Date(dateMillis), HttpDateFormat.toDate(dateString));+ assertThat(HttpDateFormat.toLong(dateString), is(dateMillis));+ assertThat(HttpDateFormat.toString(dateMillis), is(dateString));+ assertThat(HttpDateFormat.toDate(dateString), is(new Date(dateMillis)));String ds2 = "Sun, 6 Nov 1994 08:49:37 GMT";- Assert.assertEquals(dateMillis, HttpDateFormat.toLong(ds2));+ assertThat(HttpDateFormat.toLong(ds2), is(dateMillis));}- @Test(expected = ParseException.class)+ @Testpublic void testHttpDateFormatException() throws ParseException {String ds = "this is not a valid date";- HttpDateFormat.toLong(ds);+ Exception exception = assertThrows(ParseException.class, () -> {+ HttpDateFormat.toLong(ds);+ });+ String expectedMessage =+ "Text 'this is not a valid date' could not be parsed at index 0";+ String actualMessage = exception.getMessage();+ assertTrue(actualMessage.contains(expectedMessage));+}/**@@ -60,6 +72,6 @@ public class TestHttpDateFormat {public void testHttpDateFormatTimeZone() throws ParseException {String dateStringPDT = "Mon, 21 Oct 2019 03:18:16 PDT";HttpDateFormat.toLong(dateStringPDT); // must not affect internal time zone- Assert.assertEquals(dateString, HttpDateFormat.toString(dateMillis));+ assertEquals(dateString, HttpDateFormat.toString(dateMillis));}}diff --git a/src/test/org/apache/nutch/parse/TestOutlinkExtractor.java b/src/test/org/apache/nutch/parse/TestOutlinkExtractor.javaindex 218e4fc46..4b4c4e9dd 100644--- a/src/test/org/apache/nutch/parse/TestOutlinkExtractor.java+++ b/src/test/org/apache/nutch/parse/TestOutlinkExtractor.java@@ -18,8 +18,9 @@ package org.apache.nutch.parse;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** TestCase to check regExp extraction of URLs.@@ -37,12 +38,12 @@ public class TestOutlinkExtractor {Outlink[] outlinks = null;outlinks = OutlinkExtractor.getOutlinks(null, conf);- Assert.assertNotNull(outlinks);- Assert.assertEquals(0, outlinks.length);+ assertNotNull(outlinks);+ assertEquals(0, outlinks.length);outlinks = OutlinkExtractor.getOutlinks("", conf);- Assert.assertNotNull(outlinks);- Assert.assertEquals(0, outlinks.length);+ assertNotNull(outlinks);+ assertEquals(0, outlinks.length);}@Test@@ -54,13 +55,13 @@ public class TestOutlinkExtractor {+ "A longer URL could be http://www.sybit.com/solutions/portals.html",conf);- Assert.assertTrue("Url not found!", outlinks.length == 3);- Assert.assertEquals("Wrong URL", "http://www.nutch.org/index.html",- outlinks[0].getToUrl());- Assert.assertEquals("Wrong URL", "http://www.google.de",- outlinks[1].getToUrl());- Assert.assertEquals("Wrong URL",- "http://www.sybit.com/solutions/portals.html", outlinks[2].getToUrl());+ assertEquals(3, outlinks.length, "Url not found!");+ assertEquals("http://www.nutch.org/index.html",+ outlinks[0].getToUrl(), "Wrong URL");+ assertEquals( "http://www.google.de",+ outlinks[1].getToUrl(), "Wrong URL");+ assertEquals("http://www.sybit.com/solutions/portals.html",+ outlinks[2].getToUrl(), "Wrong URL");}@Test@@ -72,13 +73,13 @@ public class TestOutlinkExtractor {+ "A longer URL could be http://www.sybit.com/solutions/portals.html","http://www.sybit.de", conf);- Assert.assertTrue("Url not found!", outlinks.length == 3);- Assert.assertEquals("Wrong URL", "http://www.nutch.org/index.html",- outlinks[0].getToUrl());- Assert.assertEquals("Wrong URL", "http://www.google.de",- outlinks[1].getToUrl());- Assert.assertEquals("Wrong URL",- "http://www.sybit.com/solutions/portals.html", outlinks[2].getToUrl());+ assertEquals(3, outlinks.length, "Url not found!");+ assertEquals("http://www.nutch.org/index.html",+ outlinks[0].getToUrl(), "Wrong URL");+ assertEquals("http://www.google.de", outlinks[1].getToUrl(),+ "Wrong URL");+ assertEquals("http://www.sybit.com/solutions/portals.html",+ outlinks[2].getToUrl(), "Wrong URL");}@Test@@ -87,10 +88,10 @@ public class TestOutlinkExtractor {"Test with ftp://www.nutch.org is it found? "+ "What about www.google.com at ftp://www.google.de", conf);- Assert.assertTrue("Url not found!", outlinks.length > 1);- Assert.assertEquals("Wrong URL", "ftp://www.nutch.org",- outlinks[0].getToUrl());- Assert.assertEquals("Wrong URL", "ftp://www.google.de",- outlinks[1].getToUrl());+ assertTrue(outlinks.length > 1, "Url not found!");+ assertEquals( "ftp://www.nutch.org", outlinks[0].getToUrl(),+ "Wrong URL");+ assertEquals( "ftp://www.google.de", outlinks[1].getToUrl(),+ "Wrong URL");}}diff --git a/src/test/org/apache/nutch/parse/TestOutlinks.java b/src/test/org/apache/nutch/parse/TestOutlinks.javaindex 78c051e51..e0e46a200 100644--- a/src/test/org/apache/nutch/parse/TestOutlinks.java+++ b/src/test/org/apache/nutch/parse/TestOutlinks.java@@ -16,12 +16,12 @@*/package org.apache.nutch.parse;-import org.junit.Test;+import org.junit.jupiter.api.Test;import java.util.HashSet;import java.util.Set;-import static org.junit.Assert.*;+import static org.junit.jupiter.api.Assertions.assertEquals;public class TestOutlinks {@@ -33,7 +33,7 @@ public class TestOutlinks {set.add(o);set.add(o);- assertEquals("Adding the same Outlink twice", 1, set.size());+ assertEquals(1, set.size(), "Adding the same Outlink twice");}@Test@@ -43,11 +43,11 @@ public class TestOutlinks {Outlink o = new Outlink("http://www.example.com", "Example");Outlink o1 = new Outlink("http://www.example.com", "Example");- assertTrue("The two Outlink objects are the same", o.equals(o1));+ assertEquals(o, o1, "The two Outlink objects are the same");set.add(o);set.add(o1);- assertEquals("The set should contain only 1 Outlink", 1, set.size());+ assertEquals(1, set.size(), "The set should contain only 1 Outlink");}}diff --git a/src/test/org/apache/nutch/parse/TestParseData.java b/src/test/org/apache/nutch/parse/TestParseData.javaindex 0dbbf78cd..c4f12cc3c 100644--- a/src/test/org/apache/nutch/parse/TestParseData.java+++ b/src/test/org/apache/nutch/parse/TestParseData.java@@ -18,8 +18,9 @@ package org.apache.nutch.parse;import org.apache.nutch.util.WritableTestUtils;import org.apache.nutch.metadata.Metadata;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;/** Unit tests for ParseData. */@@ -52,6 +53,6 @@ public class TestParseData {ParseData original = new ParseData(ParseStatus.STATUS_SUCCESS,"Max Outlinks Title", outlinks, new Metadata());ParseData data = (ParseData) WritableTestUtils.writeRead(original, null);- Assert.assertEquals(outlinks.length, data.getOutlinks().length);+ assertEquals(outlinks.length, data.getOutlinks().length);}}diff --git a/src/test/org/apache/nutch/parse/TestParseSegment.java b/src/test/org/apache/nutch/parse/TestParseSegment.javaindex dd7f4f920..d989c7a0b 100644--- a/src/test/org/apache/nutch/parse/TestParseSegment.java+++ b/src/test/org/apache/nutch/parse/TestParseSegment.java@@ -16,15 +16,14 @@*/package org.apache.nutch.parse;-import static junit.framework.TestCase.assertFalse;-import static junit.framework.TestCase.assertTrue;-import java.nio.charset.StandardCharsets;import org.apache.nutch.metadata.Metadata;import org.apache.nutch.net.protocols.Response;import org.apache.nutch.protocol.Content;-import org.junit.Test;+import org.junit.jupiter.api.Test;+import static org.junit.jupiter.api.Assertions.assertFalse;+import static org.junit.jupiter.api.Assertions.assertTrue;public class TestParseSegment {private static byte[] BYTES = "the quick brown fox".getBytes(StandardCharsets.UTF_8);diff --git a/src/test/org/apache/nutch/parse/TestParseText.java b/src/test/org/apache/nutch/parse/TestParseText.javaindex 387363299..56418a1fc 100644--- a/src/test/org/apache/nutch/parse/TestParseText.java+++ b/src/test/org/apache/nutch/parse/TestParseText.java@@ -17,7 +17,7 @@package org.apache.nutch.parse;import org.apache.nutch.util.WritableTestUtils;-import org.junit.Test;+import org.junit.jupiter.api.Test;/** Unit tests for ParseText. */diff --git a/src/test/org/apache/nutch/parse/TestParserFactory.java b/src/test/org/apache/nutch/parse/TestParserFactory.javaindex c996ef76a..228b41972 100644--- a/src/test/org/apache/nutch/parse/TestParserFactory.java+++ b/src/test/org/apache/nutch/parse/TestParserFactory.java@@ -20,9 +20,11 @@ package org.apache.nutch.parse;import org.apache.nutch.plugin.Extension;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.Test;+import org.junit.jupiter.api.BeforeEach;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;/*** Unit test for new parse plugin selection.@@ -36,7 +38,7 @@ public class TestParserFactory {private ParserFactory parserFactory;/** Inits the Test Case with the test parse-plugin file */- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();conf.set("plugin.includes", ".*");@@ -49,55 +51,54 @@ public class TestParserFactory {@Testpublic void testGetExtensions() throws Exception {Extension ext = parserFactory.getExtensions("text/html").get(0);- Assert.assertEquals("parse-tika", ext.getDescriptor().getPluginId());+ assertEquals("parse-tika", ext.getDescriptor().getPluginId());ext = parserFactory.getExtensions("text/html; charset=ISO-8859-1").get(0);- Assert.assertEquals("parse-tika", ext.getDescriptor().getPluginId());+ assertEquals("parse-tika", ext.getDescriptor().getPluginId());ext = parserFactory.getExtensions("foo/bar").get(0);- Assert.assertEquals("parse-tika", ext.getDescriptor().getPluginId());+ assertEquals("parse-tika", ext.getDescriptor().getPluginId());}/** Unit test to check <code>getParsers</code> method */@Testpublic void testGetParsers() throws Exception {Parser[] parsers = parserFactory.getParsers("text/html", "http://foo.com");- Assert.assertNotNull(parsers);- Assert.assertEquals(1, parsers.length);- Assert.assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0]+ assertNotNull(parsers);+ assertEquals(1, parsers.length);+ assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0].getClass().getName());parsers = parserFactory.getParsers("text/html; charset=ISO-8859-1","http://foo.com");- Assert.assertNotNull(parsers);- Assert.assertEquals(1, parsers.length);- Assert.assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0]+ assertNotNull(parsers);+ assertEquals(1, parsers.length);+ assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0].getClass().getName());parsers = parserFactory.getParsers("application/x-javascript","http://foo.com");- Assert.assertNotNull(parsers);- Assert.assertEquals(1, parsers.length);- Assert.assertEquals("org.apache.nutch.parse.js.JSParseFilter", parsers[0]+ assertNotNull(parsers);+ assertEquals(1, parsers.length);+ assertEquals("org.apache.nutch.parse.js.JSParseFilter", parsers[0].getClass().getName());parsers = parserFactory.getParsers("text/plain", "http://foo.com");- Assert.assertNotNull(parsers);- Assert.assertEquals(1, parsers.length);- Assert.assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0]+ assertNotNull(parsers);+ assertEquals(1, parsers.length);+ assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0].getClass().getName());Parser parser1 = parserFactory.getParsers("text/plain", "http://foo.com")[0];Parser parser2 = parserFactory.getParsers("*", "http://foo.com")[0];- Assert.assertEquals("Different instances!", parser1.hashCode(),- parser2.hashCode());+ assertEquals(parser1.hashCode(), parser2.hashCode(), "Different instances!");// test and make sure that the rss parser is loaded even though its// plugin.xml// doesn't claim to support text/rss, only application/rss+xmlparsers = parserFactory.getParsers("text/rss", "http://foo.com");- Assert.assertNotNull(parsers);- Assert.assertEquals(1, parsers.length);- Assert.assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0]+ assertNotNull(parsers);+ assertEquals(1, parsers.length);+ assertEquals("org.apache.nutch.parse.tika.TikaParser", parsers[0].getClass().getName());}diff --git a/src/test/org/apache/nutch/plugin/TestPluginSystem.java b/src/test/org/apache/nutch/plugin/TestPluginSystem.javaindex 7c1362aa5..049c49adf 100644--- a/src/test/org/apache/nutch/plugin/TestPluginSystem.java+++ b/src/test/org/apache/nutch/plugin/TestPluginSystem.java@@ -28,10 +28,12 @@ import java.util.Properties;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.mapreduce.Job;import org.apache.nutch.util.NutchConfiguration;-import org.junit.After;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;++import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/*** Unit tests for the plugin system@@ -43,7 +45,7 @@ public class TestPluginSystem {private Configuration conf;private PluginRepository repository;- @Before+ @BeforeEachpublic void setUp() throws Exception {this.conf = NutchConfiguration.create();conf.set("plugin.includes", ".*");@@ -54,12 +56,7 @@ public class TestPluginSystem {this.repository = PluginRepository.get(conf);}- /*- * (non-Javadoc)- *- * @see junit.framework.TestCase#tearDown()- */- @After+ @AfterEachpublic void tearDown() throws Exception {for (int i = 0; i < fFolders.size(); i++) {File folder = fFolders.get(i);@@ -77,7 +74,7 @@ public class TestPluginSystem {if (!file.exists()) {file.mkdir();}- Assert.assertTrue(file.exists());+ assertTrue(file.exists());}/**@@ -86,14 +83,14 @@ public class TestPluginSystem {public void testLoadPlugins() {PluginDescriptor[] descriptors = repository.getPluginDescriptors();int k = descriptors.length;- Assert.assertTrue(fPluginCount <= k);+ assertTrue(fPluginCount <= k);for (int i = 0; i < descriptors.length; i++) {PluginDescriptor descriptor = descriptors[i];if (!descriptor.getPluginId().startsWith("getPluginFolder()")) {continue;}- Assert.assertEquals(1, descriptor.getExportedLibUrls().length);- Assert.assertEquals(1, descriptor.getNotExportedLibUrls().length);+ assertEquals(1, descriptor.getExportedLibUrls().length);+ assertEquals(1, descriptor.getNotExportedLibUrls().length);}}@@ -104,7 +101,7 @@ public class TestPluginSystem {Job job = Job.getInstance(config);config = job.getConfiguration();PluginRepository repo1 = PluginRepository.get(config);- Assert.assertTrue(repo == repo1);+ assertSame(repo, repo1);// now construct a config without UUIDconfig = new Configuration();config.addResource("nutch-default.xml");@@ -113,7 +110,7 @@ public class TestPluginSystem {job = Job.getInstance(config);config = job.getConfiguration();repo1 = PluginRepository.get(config);- Assert.assertTrue(repo1 != repo);+ assertNotSame(repo1, repo);}/**@@ -123,14 +120,14 @@ public class TestPluginSystem {public void testGetExtensionAndAttributes() {String xpId = " sdsdsd";ExtensionPoint extensionPoint = repository.getExtensionPoint(xpId);- Assert.assertEquals(extensionPoint, null);+ assertNull(extensionPoint);Extension[] extension1 = repository.getExtensionPoint(getGetExtensionId()).getExtensions();- Assert.assertEquals(extension1.length, fPluginCount);+ assertEquals(extension1.length, fPluginCount);for (int i = 0; i < extension1.length; i++) {Extension extension2 = extension1[i];String string = extension2.getAttribute(getGetConfigElementName());- Assert.assertEquals(string, getParameterValue());+ assertEquals(string, getParameterValue());}}@@ -141,15 +138,15 @@ public class TestPluginSystem {public void testGetExtensionInstances() throws PluginRuntimeException {Extension[] extensions = repository.getExtensionPoint(getGetExtensionId()).getExtensions();- Assert.assertEquals(extensions.length, fPluginCount);+ assertEquals(extensions.length, fPluginCount);for (int i = 0; i < extensions.length; i++) {Extension extension = extensions[i];Object object = extension.getExtensionInstance();if (!(object instanceof HelloWorldExtension))- Assert.fail(" object is not a instance of HelloWorldExtension");+ fail(" object is not a instance of HelloWorldExtension");((ITestExtension) object).testGetExtension("Bla ");String string = ((ITestExtension) object).testGetExtension("Hello");- Assert.assertEquals("Hello World", string);+ assertEquals("Hello World", string);}}@@ -162,7 +159,7 @@ public class TestPluginSystem {PluginDescriptor[] descriptors = repository.getPluginDescriptors();for (int i = 0; i < descriptors.length; i++) {PluginDescriptor descriptor = descriptors[i];- Assert.assertNotNull(descriptor.getClassLoader());+ assertNotNull(descriptor.getClassLoader());}}@@ -178,9 +175,9 @@ public class TestPluginSystem {continue;}String value = descriptor.getResourceString("key", Locale.UK);- Assert.assertEquals("value", value);+ assertEquals("value", value);value = descriptor.getResourceString("key", Locale.TRADITIONAL_CHINESE);- Assert.assertEquals("value", value);+ assertEquals("value", value);}}@@ -191,7 +188,7 @@ public class TestPluginSystem {private String getPluginFolder() {String[] strings = conf.getStrings("plugin.folders");if (strings == null || strings.length == 0)- Assert.fail("no plugin directory setuped..");+ fail("no plugin directory setuped..");String name = strings[0];return new PluginManifestParser(conf, this.repository)diff --git a/src/test/org/apache/nutch/protocol/AbstractHttpProtocolPluginTest.java b/src/test/org/apache/nutch/protocol/AbstractHttpProtocolPluginTest.javaindex be26d9147..17b87ebe2 100644--- a/src/test/org/apache/nutch/protocol/AbstractHttpProtocolPluginTest.java+++ b/src/test/org/apache/nutch/protocol/AbstractHttpProtocolPluginTest.java@@ -41,8 +41,8 @@ import org.apache.hadoop.io.Text;import org.apache.nutch.crawl.CrawlDatum;import org.apache.nutch.metadata.Nutch;import org.apache.nutch.net.protocols.Response;-import org.junit.After;-import org.junit.Before;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeEach;import org.slf4j.Logger;import org.slf4j.LoggerFactory;@@ -94,7 +94,7 @@ public abstract class AbstractHttpProtocolPluginTest {protected abstract String getPluginClassName();- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = new Configuration();conf.addResource("nutch-default.xml");@@ -110,7 +110,7 @@ public abstract class AbstractHttpProtocolPluginTest {http.setConf(conf);}- @After+ @AfterEachpublic void tearDown() throws Exception {if (server != null) {server.close();diff --git a/src/test/org/apache/nutch/protocol/TestContent.java b/src/test/org/apache/nutch/protocol/TestContent.javaindex e6a2a0e85..fa5c7d17d 100644--- a/src/test/org/apache/nutch/protocol/TestContent.java+++ b/src/test/org/apache/nutch/protocol/TestContent.java@@ -22,8 +22,12 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;import org.apache.nutch.util.WritableTestUtils;import org.apache.tika.mime.MimeTypes;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import java.nio.charset.StandardCharsets;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertNotNull;/** Unit tests for Content. */@@ -46,9 +50,9 @@ public class TestContent {metaData, conf);WritableTestUtils.testWritable(r);- Assert.assertEquals("text/html", r.getMetadata().get("Content-Type"));- Assert.assertEquals("text/html", r.getMetadata().get("content-type"));- Assert.assertEquals("text/html", r.getMetadata().get("CONTENTYPE"));+ assertEquals("text/html", r.getMetadata().get("Content-Type"));+ assertEquals("text/html", r.getMetadata().get("content-type"));+ assertEquals("text/html", r.getMetadata().get("CONTENTYPE"));}/** Unit tests for getContentType(String, String, byte[]) method. */@@ -58,36 +62,36 @@ public class TestContent {Metadata p = new Metadata();c = new Content("http://www.foo.com/", "http://www.foo.com/",- "".getBytes("UTF8"), "text/html; charset=UTF-8", p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "".getBytes(StandardCharsets.UTF_8), "text/html; charset=UTF-8", p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/foo.html", "http://www.foo.com/",- "".getBytes("UTF8"), "", p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "".getBytes(StandardCharsets.UTF_8), "", p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/foo.html", "http://www.foo.com/",- "".getBytes("UTF8"), null, p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "".getBytes(StandardCharsets.UTF_8), null, p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/", "http://www.foo.com/",- "<html></html>".getBytes("UTF8"), "", p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "<html></html>".getBytes(StandardCharsets.UTF_8), "", p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/foo.html", "http://www.foo.com/",- "<html></html>".getBytes("UTF8"), "text/plain", p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "<html></html>".getBytes(StandardCharsets.UTF_8), "text/plain", p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/foo.png", "http://www.foo.com/",- "<html></html>".getBytes("UTF8"), "text/plain", p, conf);- Assert.assertEquals("text/html", c.getContentType());+ "<html></html>".getBytes(StandardCharsets.UTF_8), "text/plain", p, conf);+ assertEquals("text/html", c.getContentType());c = new Content("http://www.foo.com/", "http://www.foo.com/",- "".getBytes("UTF8"), "", p, conf);- Assert.assertEquals(MimeTypes.OCTET_STREAM, c.getContentType());+ "".getBytes(StandardCharsets.UTF_8), "", p, conf);+ assertEquals(MimeTypes.OCTET_STREAM, c.getContentType());c = new Content("http://www.foo.com/", "http://www.foo.com/",- "".getBytes("UTF8"), null, p, conf);- Assert.assertNotNull(c.getContentType());+ "".getBytes(StandardCharsets.UTF_8), null, p, conf);+ assertNotNull(c.getContentType());}}diff --git a/src/test/org/apache/nutch/protocol/TestProtocolFactory.java b/src/test/org/apache/nutch/protocol/TestProtocolFactory.javaindex 2266b084e..b6639f304 100644--- a/src/test/org/apache/nutch/protocol/TestProtocolFactory.java+++ b/src/test/org/apache/nutch/protocol/TestProtocolFactory.java@@ -18,16 +18,17 @@ package org.apache.nutch.protocol;import org.apache.hadoop.conf.Configuration;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;public class TestProtocolFactory {Configuration conf;ProtocolFactory factory;- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();conf.set("plugin.includes", ".*");@@ -41,11 +42,11 @@ public class TestProtocolFactory {// non existing protocoltry {factory.getProtocol("xyzxyz://somehost");- Assert.fail("Must throw ProtocolNotFound");+ fail("Must throw ProtocolNotFound");} catch (ProtocolNotFound e) {// all is ok} catch (Exception ex) {- Assert.fail("Must not throw any other exception");+ fail("Must not throw any other exception");}Protocol httpProtocol = null;@@ -53,26 +54,26 @@ public class TestProtocolFactory {// existing protocoltry {httpProtocol = factory.getProtocol("http://somehost");- Assert.assertNotNull(httpProtocol);+ assertNotNull(httpProtocol);} catch (Exception ex) {- Assert.fail("Must not throw any other exception");+ fail("Must not throw any other exception");}// test same object instancetry {- Assert.assertTrue(httpProtocol == factory.getProtocol("http://somehost"));+ assertSame(httpProtocol, factory.getProtocol("http://somehost"));} catch (ProtocolNotFound e) {- Assert.fail("Must not throw any exception");+ fail("Must not throw any exception");}}@Testpublic void testContains() {- Assert.assertTrue(factory.contains("http", "http"));- Assert.assertTrue(factory.contains("http", "http,ftp"));- Assert.assertTrue(factory.contains("http", " http , ftp"));- Assert.assertTrue(factory.contains("smb", "ftp,smb,http"));- Assert.assertFalse(factory.contains("smb", "smbb"));+ assertTrue(factory.contains("http", "http"));+ assertTrue(factory.contains("http", "http,ftp"));+ assertTrue(factory.contains("http", " http , ftp"));+ assertTrue(factory.contains("smb", "ftp,smb,http"));+ assertFalse(factory.contains("smb", "smbb"));}}diff --git a/src/test/org/apache/nutch/segment/TestSegmentMerger.java b/src/test/org/apache/nutch/segment/TestSegmentMerger.javaindex e70518873..0df88a2de 100644--- a/src/test/org/apache/nutch/segment/TestSegmentMerger.java+++ b/src/test/org/apache/nutch/segment/TestSegmentMerger.java@@ -29,12 +29,14 @@ import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat;import org.apache.nutch.parse.ParseText;import org.apache.nutch.util.NutchConfiguration;-import org.junit.After;-import org.junit.Assert;-import org.junit.Assume;-import org.junit.Before;-import org.junit.BeforeClass;-import org.junit.Test;+import org.junit.jupiter.api.AfterEach;+import org.junit.jupiter.api.BeforeAll;+import org.junit.jupiter.api.Test;+import org.junit.jupiter.api.BeforeEach;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;+import static org.junit.jupiter.api.Assumptions.assumeTrue;public class TestSegmentMerger {Configuration conf;@@ -45,12 +47,12 @@ public class TestSegmentMerger {Path out;int countSeg1, countSeg2;- @BeforeClass+ @BeforeAllpublic static void checkConditions() throws Exception {- Assume.assumeTrue(Boolean.getBoolean("test.include.slow"));+ assumeTrue(Boolean.getBoolean("test.include.slow"));}- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();fs = FileSystem.get(conf);@@ -98,7 +100,7 @@ public class TestSegmentMerger {System.err.println(" - done: " + countSeg2 + " records.");}- @After+ @AfterEachpublic void tearDown() throws Exception {fs.delete(testDir, true);}@@ -110,7 +112,7 @@ public class TestSegmentMerger {// verify outputFileStatus[] stats = fs.listStatus(out);// there should be just one path- Assert.assertEquals(1, stats.length);+ assertEquals(1, stats.length);Path outSeg = stats[0].getPath();Text k = new Text();ParseText v = new ParseText();@@ -123,16 +125,16 @@ public class TestSegmentMerger {String vs = v.getText();if (ks.startsWith("seg1-")) {cnt1++;- Assert.assertTrue(vs.startsWith("seg1 "));+ assertTrue(vs.startsWith("seg1 "));} else if (ks.startsWith("seg2-")) {cnt2++;- Assert.assertTrue(vs.startsWith("seg2 "));+ assertTrue(vs.startsWith("seg2 "));}}r.close();}- Assert.assertEquals(countSeg1, cnt1);- Assert.assertEquals(countSeg2, cnt2);+ assertEquals(countSeg1, cnt1);+ assertEquals(countSeg2, cnt2);}}diff --git a/src/test/org/apache/nutch/segment/TestSegmentMergerCrawlDatums.java b/src/test/org/apache/nutch/segment/TestSegmentMergerCrawlDatums.javaindex 8cc4744a2..cd0db1e50 100644--- a/src/test/org/apache/nutch/segment/TestSegmentMergerCrawlDatums.java+++ b/src/test/org/apache/nutch/segment/TestSegmentMergerCrawlDatums.java@@ -31,14 +31,15 @@ import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat;import org.apache.nutch.crawl.CrawlDatum;import org.apache.nutch.util.NutchConfiguration;-import org.junit.Assert;-import org.junit.Assume;-import org.junit.Before;-import org.junit.BeforeClass;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.BeforeAll;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;+import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assumptions.assumeTrue;+/*** New SegmentMerger unit test focusing on several crappy issues with the* segment merger. The general problem is disappearing records and incorrect@@ -63,12 +64,12 @@ public class TestSegmentMergerCrawlDatums {private static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());- @BeforeClass+ @BeforeAllpublic static void checkConditions() throws Exception {- Assume.assumeTrue(Boolean.getBoolean("test.include.slow"));+ assumeTrue(Boolean.getBoolean("test.include.slow"));}- @Before+ @BeforeEachpublic void setUp() throws Exception {conf = NutchConfiguration.create();fs = FileSystem.get(conf);@@ -80,7 +81,7 @@ public class TestSegmentMergerCrawlDatums {*/@Testpublic void testSingleRandomSequence() throws Exception {- Assert.assertEquals(+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS),Byte.valueOf(executeSequence(CrawlDatum.STATUS_FETCH_GONE,CrawlDatum.STATUS_FETCH_SUCCESS, 256, false)));@@ -118,7 +119,7 @@ public class TestSegmentMergerCrawlDatums {segment3, segment4, segment5, segment6, segment7, segment8 });Byte status = Byte.valueOf(status = checkMergedSegment(testDir, mergedSegment));- Assert.assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);}/**@@ -139,12 +140,11 @@ public class TestSegmentMergerCrawlDatums {byte resultStatus = executeSequence(randomStatus, expectedStatus, rounds,withRedirects);- Assert.assertEquals(+ assertEquals(expectedStatus, resultStatus,"Expected status = " + CrawlDatum.getStatusName(expectedStatus)+ ", but got " + CrawlDatum.getStatusName(resultStatus)+ " when merging " + rounds + " segments"- + (withRedirects ? " with redirects" : ""), expectedStatus,- resultStatus);+ + (withRedirects ? " with redirects" : ""));}}@@ -153,7 +153,7 @@ public class TestSegmentMergerCrawlDatums {*/@Testpublic void testRandomTestSequenceWithRedirects() throws Exception {- Assert.assertEquals(+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS),Byte.valueOf(executeSequence(CrawlDatum.STATUS_FETCH_GONE,CrawlDatum.STATUS_FETCH_SUCCESS, 128, true)));@@ -181,7 +181,7 @@ public class TestSegmentMergerCrawlDatums {segment3 });Byte status = Byte.valueOf(status = checkMergedSegment(testDir, mergedSegment));- Assert.assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);}/**@@ -201,7 +201,7 @@ public class TestSegmentMergerCrawlDatums {Path mergedSegment = merge(testDir, new Path[] { segment });Byte status = Byte.valueOf(status = checkMergedSegment(testDir, mergedSegment));- Assert.assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);}/**@@ -223,7 +223,7 @@ public class TestSegmentMergerCrawlDatums {Path mergedSegment = merge(testDir, new Path[] { segment1, segment2 });Byte status = Byte.valueOf(status = checkMergedSegment(testDir, mergedSegment));- Assert.assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);+ assertEquals(Byte.valueOf(CrawlDatum.STATUS_FETCH_SUCCESS), status);}/**@@ -349,7 +349,7 @@ public class TestSegmentMergerCrawlDatums {merger.merge(out, segments, false, false, -1);FileStatus[] stats = fs.listStatus(out);- Assert.assertEquals(1, stats.length);+ assertEquals(1, stats.length);return stats[0].getPath();}diff --git a/src/test/org/apache/nutch/service/TestNutchServer.java b/src/test/org/apache/nutch/service/TestNutchServer.javaindex 811285faf..11397a9b1 100644--- a/src/test/org/apache/nutch/service/TestNutchServer.java+++ b/src/test/org/apache/nutch/service/TestNutchServer.java@@ -20,7 +20,7 @@ import java.lang.invoke.MethodHandles;import javax.ws.rs.core.Response;import org.apache.cxf.jaxrs.client.WebClient;-import org.junit.Test;+import org.junit.jupiter.api.Test;import org.slf4j.Logger;import org.slf4j.LoggerFactory;diff --git a/src/test/org/apache/nutch/tools/TestCommonCrawlDataDumper.java b/src/test/org/apache/nutch/tools/TestCommonCrawlDataDumper.javaindex 547007aea..fee72b65a 100644--- a/src/test/org/apache/nutch/tools/TestCommonCrawlDataDumper.java+++ b/src/test/org/apache/nutch/tools/TestCommonCrawlDataDumper.java@@ -16,15 +16,15 @@*/package org.apache.nutch.tools;-import static org.junit.Assert.assertTrue;-import java.io.File;import java.nio.file.Files;import java.util.Collection;import org.apache.commons.io.FileUtils;import org.apache.commons.io.filefilter.FileFilterUtils;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertTrue;/***@@ -100,8 +100,8 @@ public class TestCommonCrawlDataDumper {FileFilterUtils.directoryFileFilter());for (String expectedFileName : crawledFiles) {- assertTrue("Missed file " + expectedFileName + " in dump",- hasFile(expectedFileName, tempFiles));+ assertTrue(hasFile(expectedFileName, tempFiles),+ "Missed file " + expectedFileName + " in dump");}}diff --git a/src/test/org/apache/nutch/util/DumpFileUtilTest.java b/src/test/org/apache/nutch/util/DumpFileUtilTest.javaindex 249d9783f..546ea7e6b 100644--- a/src/test/org/apache/nutch/util/DumpFileUtilTest.java+++ b/src/test/org/apache/nutch/util/DumpFileUtilTest.java@@ -16,9 +16,11 @@*/package org.apache.nutch.util;-import org.junit.Test;+import org.junit.jupiter.api.Test;-import static org.junit.Assert.*;+import static org.hamcrest.CoreMatchers.is;+import static org.hamcrest.CoreMatchers.nullValue;+import static org.hamcrest.MatcherAssert.assertThat;public class DumpFileUtilTest {@@ -28,7 +30,7 @@ public class DumpFileUtilTest {String result = DumpFileUtil.getUrlMD5(testUrl);- assertEquals("991e599262e04ea2ec76b6c5aed499a7", result);+ assertThat(result, is("991e599262e04ea2ec76b6c5aed499a7"));}@Test@@ -37,12 +39,12 @@ public class DumpFileUtilTest {String basePath = "/tmp";String fullDir = DumpFileUtil.createTwoLevelsDirectory(basePath, DumpFileUtil.getUrlMD5(testUrl));- assertEquals("/tmp/96/ea", fullDir);+ assertThat(fullDir, is("/tmp/96/ea"));String basePath2 = "/this/path/is/not/existed/just/for/testing";String fullDir2 = DumpFileUtil.createTwoLevelsDirectory(basePath2, DumpFileUtil.getUrlMD5(testUrl));- assertNull(fullDir2);+ assertThat(fullDir2, nullValue());}@Test@@ -52,16 +54,17 @@ public class DumpFileUtilTest {String extension = "html";String fullDir = DumpFileUtil.createFileName(DumpFileUtil.getUrlMD5(testUrl), baseName, extension);- assertEquals("991e599262e04ea2ec76b6c5aed499a7_test.html", fullDir);+ assertThat(fullDir, is("991e599262e04ea2ec76b6c5aed499a7_test.html"));String tooLongBaseName = "testtesttesttesttesttesttesttesttesttesttesttesttesttesttesttesttesttest";String fullDir2 = DumpFileUtil.createFileName(DumpFileUtil.getUrlMD5(testUrl), tooLongBaseName, extension);- assertEquals("991e599262e04ea2ec76b6c5aed499a7_testtesttesttesttesttesttesttest.html", fullDir2);+ assertThat(fullDir2,+ is("991e599262e04ea2ec76b6c5aed499a7_testtesttesttesttesttesttesttest.html"));String tooLongExtension = "testtesttesttesttesttesttesttesttesttesttesttesttesttesttesttesttesttest";String fullDir3 = DumpFileUtil.createFileName(DumpFileUtil.getUrlMD5(testUrl), baseName, tooLongExtension);- assertEquals("991e599262e04ea2ec76b6c5aed499a7_test.testt", fullDir3);+ assertThat(fullDir3, is("991e599262e04ea2ec76b6c5aed499a7_test.testt"));}}diff --git a/src/test/org/apache/nutch/util/TestEncodingDetector.java b/src/test/org/apache/nutch/util/TestEncodingDetector.javaindex 8697a62f0..153b026b0 100644--- a/src/test/org/apache/nutch/util/TestEncodingDetector.java+++ b/src/test/org/apache/nutch/util/TestEncodingDetector.java@@ -22,8 +22,9 @@ import org.apache.hadoop.conf.Configuration;import org.apache.nutch.metadata.Metadata;import org.apache.nutch.net.protocols.Response;import org.apache.nutch.protocol.Content;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;public class TestEncodingDetector {private static Configuration conf = NutchConfiguration.create();@@ -54,7 +55,7 @@ public class TestEncodingDetector {detector.autoDetectClues(content, true);encoding = detector.guessEncoding(content, "windows-1252");// no information is available, so it should return default encoding- Assert.assertEquals("windows-1252", encoding.toLowerCase());+ assertEquals("windows-1252", encoding.toLowerCase());metadata.clear();metadata.set(Response.CONTENT_TYPE, "text/plain; charset=UTF-16");@@ -63,7 +64,7 @@ public class TestEncodingDetector {detector = new EncodingDetector(conf);detector.autoDetectClues(content, true);encoding = detector.guessEncoding(content, "windows-1252");- Assert.assertEquals("utf-16", encoding.toLowerCase());+ assertEquals("utf-16", encoding.toLowerCase());metadata.clear();content = new Content("http://www.example.com", "http://www.example.com/",@@ -72,7 +73,7 @@ public class TestEncodingDetector {detector.autoDetectClues(content, true);detector.addClue("windows-1254", "sniffed");encoding = detector.guessEncoding(content, "windows-1252");- Assert.assertEquals("windows-1254", encoding.toLowerCase());+ assertEquals("windows-1254", encoding.toLowerCase());// enable autodetectionconf.setInt(EncodingDetector.MIN_CONFIDENCE_KEY, 50);@@ -84,7 +85,7 @@ public class TestEncodingDetector {detector.autoDetectClues(content, true);detector.addClue("utf-32", "sniffed");encoding = detector.guessEncoding(content, "windows-1252");- Assert.assertEquals("utf-8", encoding.toLowerCase());+ assertEquals("utf-8", encoding.toLowerCase());}}diff --git a/src/test/org/apache/nutch/util/TestGZIPUtils.java b/src/test/org/apache/nutch/util/TestGZIPUtils.javaindex fcda06c12..fb405c5ad 100644--- a/src/test/org/apache/nutch/util/TestGZIPUtils.java+++ b/src/test/org/apache/nutch/util/TestGZIPUtils.java@@ -18,8 +18,9 @@ package org.apache.nutch.util;import java.io.IOException;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/** Unit tests for GZIPUtils methods. */public class TestGZIPUtils {@@ -154,37 +155,37 @@ public class TestGZIPUtils {public void testZipUnzip(byte[] origBytes) {byte[] compressedBytes = GZIPUtils.zip(origBytes);- Assert.assertTrue("compressed array is not smaller!",- compressedBytes.length < origBytes.length);+ assertTrue(compressedBytes.length < origBytes.length,+ "compressed array is not smaller!");byte[] uncompressedBytes = null;try {uncompressedBytes = GZIPUtils.unzip(compressedBytes);} catch (IOException e) {e.printStackTrace();- Assert.assertTrue("caught exception '" + e + "' during unzip()", false);+ fail("caught exception '" + e + "' during unzip()");}- Assert.assertTrue("uncompressedBytes is wrong size",- uncompressedBytes.length == origBytes.length);+ assertEquals(uncompressedBytes.length, origBytes.length,+ "uncompressedBytes is wrong size");for (int i = 0; i < origBytes.length; i++)if (origBytes[i] != uncompressedBytes[i])- Assert.assertTrue("uncompressedBytes does not match origBytes", false);+ fail("uncompressedBytes does not match origBytes");}public void testZipUnzipBestEffort(byte[] origBytes) {byte[] compressedBytes = GZIPUtils.zip(origBytes);- Assert.assertTrue("compressed array is not smaller!",- compressedBytes.length < origBytes.length);+ assertTrue(compressedBytes.length < origBytes.length,+ "compressed array is not smaller!");byte[] uncompressedBytes = GZIPUtils.unzipBestEffort(compressedBytes);- Assert.assertTrue("uncompressedBytes is wrong size",- uncompressedBytes.length == origBytes.length);+ assertEquals(uncompressedBytes.length, origBytes.length,+ "uncompressedBytes is wrong size");for (int i = 0; i < origBytes.length; i++)if (origBytes[i] != uncompressedBytes[i])- Assert.assertTrue("uncompressedBytes does not match origBytes", false);+ fail("uncompressedBytes does not match origBytes");}public void testTruncation(byte[] origBytes) {@@ -210,9 +211,8 @@ public class TestGZIPUtils {for (int j = 0; j < trunc.length; j++)if (trunc[j] != origBytes[j])- Assert.assertTrue("truncated/uncompressed array differs at pos "- + j + " (compressed data had been truncated to len " + i + ")",- false);+ fail("truncated/uncompressed array differs at pos " + j+ + " (compressed data had been truncated to len " + i + ")");}}}@@ -220,20 +220,19 @@ public class TestGZIPUtils {public void testLimit(byte[] origBytes) {byte[] compressedBytes = GZIPUtils.zip(origBytes);- Assert.assertTrue("compressed array is not smaller!",- compressedBytes.length < origBytes.length);+ assertTrue(compressedBytes.length < origBytes.length,+ "compressed array is not smaller!");for (int i = 0; i < origBytes.length; i++) {byte[] uncompressedBytes = GZIPUtils.unzipBestEffort(compressedBytes, i);- Assert.assertTrue("uncompressedBytes is wrong size",- uncompressedBytes.length == i);+ assertEquals(uncompressedBytes.length, i,+ "uncompressedBytes is wrong size");for (int j = 0; j < i; j++)if (origBytes[j] != uncompressedBytes[j])- Assert- .assertTrue("uncompressedBytes does not match origBytes", false);+ fail("uncompressedBytes does not match origBytes");}}diff --git a/src/test/org/apache/nutch/util/TestMimeUtil.java b/src/test/org/apache/nutch/util/TestMimeUtil.javaindex 6ebe76669..c9b09226a 100644--- a/src/test/org/apache/nutch/util/TestMimeUtil.java+++ b/src/test/org/apache/nutch/util/TestMimeUtil.java@@ -24,9 +24,10 @@ import org.apache.hadoop.conf.Configuration;import com.google.common.io.Files;-import junit.framework.TestCase;+import org.junit.jupiter.api.Test;+import static org.junit.jupiter.api.Assertions.assertEquals;-public class TestMimeUtil extends TestCase {+public class TestMimeUtil {public static String urlPrefix = "http://localhost/";@@ -96,15 +97,17 @@ public class TestMimeUtil extends TestCase {}/** use HTTP Content-Type, URL pattern, and MIME magic */+ @Testpublic void testWithMimeMagic() {for (String[] testPage : textBasedFormats) {String mimeType = getMimeType(urlPrefix,testPage[3].getBytes(defaultCharset), testPage[2], true);- assertEquals("", testPage[0], mimeType);+ assertEquals(testPage[0], mimeType);}}/** use only HTTP Content-Type (if given) and URL pattern */+ @Testpublic void testWithoutMimeMagic() {for (String[] testPage : textBasedFormats) {if (testPage.length > 4 && "requires-mime-magic".equals(testPage[4])) {@@ -112,26 +115,28 @@ public class TestMimeUtil extends TestCase {}String mimeType = getMimeType(urlPrefix + testPage[1],testPage[3].getBytes(defaultCharset), testPage[2], false);- assertEquals("", testPage[0], mimeType);+ assertEquals(testPage[0], mimeType);}}/** use only MIME magic (detection from content bytes) */+ @Testpublic void testOnlyMimeMagic() {for (String[] testPage : textBasedFormats) {String mimeType = getMimeType(urlPrefix,testPage[3].getBytes(defaultCharset), "", true);- assertEquals("", testPage[0], mimeType);+ assertEquals(testPage[0], mimeType);}}/** test binary file formats (real files) */+ @Testpublic void testBinaryFiles() throws IOException {for (String[] testPage : binaryFiles) {File dataFile = new File(sampleDir, testPage[1]);String mimeType = getMimeType(urlPrefix + testPage[1], dataFile,testPage[2], false);- assertEquals("", testPage[0], mimeType);+ assertEquals(testPage[0], mimeType);}}diff --git a/src/test/org/apache/nutch/util/TestNodeWalker.java b/src/test/org/apache/nutch/util/TestNodeWalker.javaindex 066bf1aad..892adaa1b 100644--- a/src/test/org/apache/nutch/util/TestNodeWalker.java+++ b/src/test/org/apache/nutch/util/TestNodeWalker.java@@ -19,12 +19,14 @@ package org.apache.nutch.util;import java.io.ByteArrayInputStream;import org.apache.xerces.parsers.DOMParser;-import org.junit.Assert;-import org.junit.Before;-import org.junit.Test;+import org.junit.jupiter.api.BeforeEach;+import org.junit.jupiter.api.Test;import org.w3c.dom.Node;import org.xml.sax.InputSource;+import static org.junit.jupiter.api.Assertions.assertFalse;+import static org.junit.jupiter.api.Assertions.assertTrue;+/** Unit tests for NodeWalker methods. */public class TestNodeWalker {@@ -40,7 +42,7 @@ public class TestNodeWalker {private final static String[] ULCONTENT = new String[4];- @Before+ @BeforeEachpublic void setUp() throws Exception {ULCONTENT[0] = "crawl several billion pages per month";ULCONTENT[1] = "maintain an index of these pages";@@ -74,8 +76,8 @@ public class TestNodeWalker {sb.append(text);}}- Assert.assertTrue("UL Content can NOT be found in the node",- findSomeUlContent(sb.toString()));+ assertTrue(findSomeUlContent(sb.toString()),+ "UL Content can NOT be found in the node");StringBuffer sbSkip = new StringBuffer();NodeWalker walkerSkip = new NodeWalker(parser.getDocument());@@ -92,8 +94,8 @@ public class TestNodeWalker {sbSkip.append(text);}}- Assert.assertFalse("UL Content can be found in the node",- findSomeUlContent(sbSkip.toString()));+ assertFalse(findSomeUlContent(sbSkip.toString()),+ "UL Content can be found in the node");}public boolean findSomeUlContent(String str) {diff --git a/src/test/org/apache/nutch/util/TestPrefixStringMatcher.java b/src/test/org/apache/nutch/util/TestPrefixStringMatcher.javaindex f86070dd0..82fca11b2 100644--- a/src/test/org/apache/nutch/util/TestPrefixStringMatcher.java+++ b/src/test/org/apache/nutch/util/TestPrefixStringMatcher.java@@ -16,8 +16,10 @@*/package org.apache.nutch.util;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;+import static org.junit.jupiter.api.Assertions.assertTrue;/** Unit tests for PrefixStringMatcher. */public class TestPrefixStringMatcher {@@ -90,18 +92,16 @@ public class TestPrefixStringMatcher {numInputsTested++;- Assert.assertTrue("'" + input + "' should " + (matches ? "" : "not ")- + "match!", matches == prematcher.matches(input));+ assertEquals(matches, prematcher.matches(input),+ "'" + input + "' should " + (matches ? "" : "not ") + "match!");if (matches) {- Assert.assertTrue(shortestMatch == prematcher.shortestMatch(input)- .length());- Assert.assertTrue(input.substring(0, shortestMatch).equals(- prematcher.shortestMatch(input)));-- Assert.assertTrue(longestMatch == prematcher.longestMatch(input)- .length());- Assert.assertTrue(input.substring(0, longestMatch).equals(- prematcher.longestMatch(input)));+ assertEquals(shortestMatch, prematcher.shortestMatch(input).length());+ assertEquals(input.substring(0, shortestMatch),+ prematcher.shortestMatch(input));++ assertEquals(longestMatch, prematcher.longestMatch(input).length());+ assertEquals(input.substring(0, longestMatch),+ prematcher.longestMatch(input));}}diff --git a/src/test/org/apache/nutch/util/TestStringUtil.java b/src/test/org/apache/nutch/util/TestStringUtil.javaindex 9b8291211..b42c45e91 100644--- a/src/test/org/apache/nutch/util/TestStringUtil.java+++ b/src/test/org/apache/nutch/util/TestStringUtil.java@@ -18,8 +18,9 @@ package org.apache.nutch.util;import java.util.regex.Pattern;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/** Unit tests for StringUtil methods. */public class TestStringUtil {@@ -28,16 +29,16 @@ public class TestStringUtil {String s = "my string";String ps = StringUtil.rightPad(s, 0);- Assert.assertTrue(s.equals(ps));+ assertEquals(s, ps);ps = StringUtil.rightPad(s, 9);- Assert.assertTrue(s.equals(ps));+ assertEquals(s, ps);ps = StringUtil.rightPad(s, 10);- Assert.assertTrue((s + " ").equals(ps));+ assertEquals((s + " "), ps);ps = StringUtil.rightPad(s, 15);- Assert.assertTrue((s + " ").equals(ps));+ assertEquals((s + " "), ps);}@Test@@ -45,38 +46,38 @@ public class TestStringUtil {String s = "my string";String ps = StringUtil.leftPad(s, 0);- Assert.assertTrue(s.equals(ps));+ assertEquals(s, ps);ps = StringUtil.leftPad(s, 9);- Assert.assertTrue(s.equals(ps));+ assertEquals(s, ps);ps = StringUtil.leftPad(s, 10);- Assert.assertTrue((" " + s).equals(ps));+ assertEquals((" " + s), ps);ps = StringUtil.leftPad(s, 15);- Assert.assertTrue((" " + s).equals(ps));+ assertEquals((" " + s), ps);}@Testpublic void testMaskPasswords() {String secret = "password";String masked = StringUtil.mask(secret);- Assert.assertNotEquals(secret, masked);- Assert.assertEquals(secret.length(), masked.length());+ assertNotEquals(secret, masked);+ assertEquals(secret.length(), masked.length());char mask = 'X';masked = StringUtil.mask(secret, mask);- Assert.assertNotEquals(secret, masked);- Assert.assertEquals(secret.length(), masked.length());- masked.chars().forEach((c) -> Assert.assertEquals(mask, c));+ assertNotEquals(secret, masked);+ assertEquals(secret.length(), masked.length());+ masked.chars().forEach((c) -> assertEquals(mask, c));String strWithSecret = "amqp://username:[email protected]:5672/virtualHost";Pattern maskPasswordPattern = Pattern.compile("^amqp://[^:]+:([^@]+)@");masked = StringUtil.mask(strWithSecret, maskPasswordPattern, mask);- Assert.assertNotEquals(strWithSecret, masked);- Assert.assertEquals(strWithSecret.length(), masked.length());- Assert.assertFalse(masked.contains(secret));- Assert.assertTrue(masked.contains(StringUtil.mask(secret, mask)));+ assertNotEquals(strWithSecret, masked);+ assertEquals(strWithSecret.length(), masked.length());+ assertFalse(masked.contains(secret));+ assertTrue(masked.contains(StringUtil.mask(secret, mask)));}}diff --git a/src/test/org/apache/nutch/util/TestSuffixStringMatcher.java b/src/test/org/apache/nutch/util/TestSuffixStringMatcher.javaindex 104907cc5..6396afd98 100644--- a/src/test/org/apache/nutch/util/TestSuffixStringMatcher.java+++ b/src/test/org/apache/nutch/util/TestSuffixStringMatcher.java@@ -16,8 +16,9 @@*/package org.apache.nutch.util;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;/** Unit tests for SuffixStringMatcher. */public class TestSuffixStringMatcher {@@ -90,18 +91,16 @@ public class TestSuffixStringMatcher {numInputsTested++;- Assert.assertTrue("'" + input + "' should " + (matches ? "" : "not ")- + "match!", matches == sufmatcher.matches(input));+ assertEquals(matches, sufmatcher.matches(input),+ "'" + input + "' should " + (matches ? "" : "not ") + "match!");if (matches) {- Assert.assertTrue(shortestMatch == sufmatcher.shortestMatch(input)- .length());- Assert.assertTrue(input.substring(input.length() - shortestMatch)- .equals(sufmatcher.shortestMatch(input)));-- Assert.assertTrue(longestMatch == sufmatcher.longestMatch(input)- .length());- Assert.assertTrue(input.substring(input.length() - longestMatch)- .equals(sufmatcher.longestMatch(input)));+ assertEquals(shortestMatch, sufmatcher.shortestMatch(input).length());+ assertEquals(input.substring(input.length() - shortestMatch),+ sufmatcher.shortestMatch(input));++ assertEquals(longestMatch, sufmatcher.longestMatch(input).length());+ assertEquals(input.substring(input.length() - longestMatch),+ sufmatcher.longestMatch(input));}}}diff --git a/src/test/org/apache/nutch/util/TestTableUtil.java b/src/test/org/apache/nutch/util/TestTableUtil.javaindex d31acdb13..2a9e5df3b 100644--- a/src/test/org/apache/nutch/util/TestTableUtil.java+++ b/src/test/org/apache/nutch/util/TestTableUtil.java@@ -16,8 +16,9 @@*/package org.apache.nutch.util;-import org.junit.Test;-import static org.junit.Assert.*;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.assertEquals;public class TestTableUtil {diff --git a/src/test/org/apache/nutch/util/TestURLUtil.java b/src/test/org/apache/nutch/util/TestURLUtil.javaindex f8a0a8876..59e486d69 100644--- a/src/test/org/apache/nutch/util/TestURLUtil.java+++ b/src/test/org/apache/nutch/util/TestURLUtil.java@@ -18,8 +18,9 @@ package org.apache.nutch.util;import java.net.URL;-import org.junit.Assert;-import org.junit.Test;+import org.junit.jupiter.api.Test;++import static org.junit.jupiter.api.Assertions.*;/** Test class for URLUtil */public class TestURLUtil {@@ -30,60 +31,60 @@ public class TestURLUtil {URL url = null;url = new URL("http://lucene.apache.org/nutch");- Assert.assertEquals("apache.org", URLUtil.getDomainName(url));+ assertEquals("apache.org", URLUtil.getDomainName(url));// hostname with trailing doturl = new URL("https://lucene.apache.org./nutch");- Assert.assertEquals("apache.org", URLUtil.getDomainName(url));+ assertEquals("apache.org", URLUtil.getDomainName(url));url = new URL("http://en.wikipedia.org/wiki/Java_coffee");- Assert.assertEquals("wikipedia.org", URLUtil.getDomainName(url));+ assertEquals("wikipedia.org", URLUtil.getDomainName(url));url = new URL("http://140.211.11.130/foundation/contributing.html");- Assert.assertEquals("140.211.11.130", URLUtil.getDomainName(url));+ assertEquals("140.211.11.130", URLUtil.getDomainName(url));url = new URL("http://www.example.co.uk:8080/index.html");- Assert.assertEquals("example.co.uk", URLUtil.getDomainName(url));+ assertEquals("example.co.uk", URLUtil.getDomainName(url));url = new URL("http://com");- Assert.assertEquals("com", URLUtil.getDomainName(url));+ assertEquals("com", URLUtil.getDomainName(url));url = new URL("http://www.example.co.uk.com");- Assert.assertEquals("uk.com", URLUtil.getDomainName(url));+ assertEquals("uk.com", URLUtil.getDomainName(url));// "nn" is not a public suffixurl = new URL("http://example.com.nn");- Assert.assertEquals("example.com.nn", URLUtil.getDomainName(url));+ assertEquals("example.com.nn", URLUtil.getDomainName(url));url = new URL("http://");- Assert.assertEquals("", URLUtil.getDomainName(url));+ assertEquals("", URLUtil.getDomainName(url));/** "xyz" is an ICANN suffix since 2014, see* https://www.iana.org/domains/root/db/xyz.html*/url = new URL("http://www.edu.tr.xyz");- Assert.assertEquals("tr.xyz", URLUtil.getDomainName(url));+ assertEquals("tr.xyz", URLUtil.getDomainName(url));url = new URL("http://www.example.c.se");- Assert.assertEquals("example.c.se", URLUtil.getDomainName(url));+ assertEquals("example.c.se", URLUtil.getDomainName(url));// plc.co.im is listed as a domain suffixurl = new URL("http://www.example.plc.co.im");- Assert.assertEquals("example.plc.co.im", URLUtil.getDomainName(url));+ assertEquals("example.plc.co.im", URLUtil.getDomainName(url));// 2000.hu is listed as a domain suffixurl = new URL("http://www.example.2000.hu");- Assert.assertEquals("example.2000.hu", URLUtil.getDomainName(url));+ assertEquals("example.2000.hu", URLUtil.getDomainName(url));// test non-asciiurl = new URL("http://www.example.商業.tw");- Assert.assertEquals("example.商業.tw", URLUtil.getDomainName(url));+ assertEquals("example.商業.tw", URLUtil.getDomainName(url));// test URL without host/authorityurl = new URL("file:/path/index.html");- Assert.assertNotNull(URLUtil.getDomainName(url));- Assert.assertEquals("", URLUtil.getDomainName(url));+ assertNotNull(URLUtil.getDomainName(url));+ assertEquals("", URLUtil.getDomainName(url));}@Test@@ -91,58 +92,58 @@ public class TestURLUtil {URL url = null;url = new URL("http://lucene.apache.org/nutch");- Assert.assertEquals("org", URLUtil.getDomainSuffix(url));+ assertEquals("org", URLUtil.getDomainSuffix(url));// hostname with trailing doturl = new URL("https://lucene.apache.org./nutch");- Assert.assertEquals("org", URLUtil.getDomainSuffix(url));+ assertEquals("org", URLUtil.getDomainSuffix(url));url = new URL("http://140.211.11.130/foundation/contributing.html");- Assert.assertNull(URLUtil.getDomainSuffix(url));+ assertNull(URLUtil.getDomainSuffix(url));url = new URL("http://www.example.co.uk:8080/index.html");- Assert.assertEquals("co.uk", URLUtil.getDomainSuffix(url));+ assertEquals("co.uk", URLUtil.getDomainSuffix(url));url = new URL("http://com");- Assert.assertEquals("com", URLUtil.getDomainSuffix(url));+ assertEquals("com", URLUtil.getDomainSuffix(url));url = new URL("http://www.example.co.uk.com");- Assert.assertEquals("com", URLUtil.getDomainSuffix(url));+ assertEquals("com", URLUtil.getDomainSuffix(url));// "nn" is not a public suffixurl = new URL("http://example.com.nn");- Assert.assertNull(URLUtil.getDomainSuffix(url));+ assertNull(URLUtil.getDomainSuffix(url));url = new URL("http://");- Assert.assertNull(URLUtil.getDomainSuffix(url));+ assertNull(URLUtil.getDomainSuffix(url));/** "xyz" is an ICANN suffix since 2014, see* https://www.iana.org/domains/root/db/xyz.html*/url = new URL("http://www.edu.tr.xyz");- Assert.assertEquals("xyz", URLUtil.getDomainSuffix(url));+ assertEquals("xyz", URLUtil.getDomainSuffix(url));url = new URL("http://subdomain.example.edu.tr");- Assert.assertEquals("edu.tr", URLUtil.getDomainSuffix(url));+ assertEquals("edu.tr", URLUtil.getDomainSuffix(url));url = new URL("http://subdomain.example.presse.fr");- Assert.assertEquals("fr", URLUtil.getDomainSuffix(url));+ assertEquals("fr", URLUtil.getDomainSuffix(url));url = new URL("http://subdomain.example.presse.tr");- Assert.assertEquals("tr", URLUtil.getDomainSuffix(url));+ assertEquals("tr", URLUtil.getDomainSuffix(url));// plc.co.im is listed as a domain suffixurl = new URL("http://www.example.plc.co.im");- Assert.assertEquals("plc.co.im", URLUtil.getDomainSuffix(url));+ assertEquals("plc.co.im", URLUtil.getDomainSuffix(url));// 2000.hu is listed as a domain suffixurl = new URL("http://www.example.2000.hu");- Assert.assertEquals("2000.hu", URLUtil.getDomainSuffix(url));+ assertEquals("2000.hu", URLUtil.getDomainSuffix(url));// test non-asciiurl = new URL("http://www.example.商業.tw");- Assert.assertEquals("xn--czrw28b.tw", URLUtil.getDomainSuffix(url));+ assertEquals("xn--czrw28b.tw", URLUtil.getDomainSuffix(url));}@Test@@ -150,27 +151,27 @@ public class TestURLUtil {URL url = null;url = new URL("http://lucene.apache.org/nutch");- Assert.assertEquals("org", URLUtil.getTopLevelDomainName(url));+ assertEquals("org", URLUtil.getTopLevelDomainName(url));// hostname with trailing doturl = new URL("https://lucene.apache.org./nutch");- Assert.assertEquals("org", URLUtil.getTopLevelDomainName(url));+ assertEquals("org", URLUtil.getTopLevelDomainName(url));url = new URL("http://140.211.11.130/foundation/contributing.html");- Assert.assertNull(URLUtil.getTopLevelDomainName(url));+ assertNull(URLUtil.getTopLevelDomainName(url));url = new URL("http://www.example.co.uk:8080/index.html");- Assert.assertEquals("uk", URLUtil.getTopLevelDomainName(url));+ assertEquals("uk", URLUtil.getTopLevelDomainName(url));// "nn" is not a public suffixurl = new URL("http://example.com.nn");- Assert.assertNull(URLUtil.getTopLevelDomainName(url));+ assertNull(URLUtil.getTopLevelDomainName(url));url = new URL("http://");- Assert.assertNull(URLUtil.getTopLevelDomainName(url));+ assertNull(URLUtil.getTopLevelDomainName(url));url = new URL("http://nic.삼성/");- Assert.assertEquals("xn--cg4bki", URLUtil.getTopLevelDomainName(url));+ assertEquals("xn--cg4bki", URLUtil.getTopLevelDomainName(url));}@Test@@ -180,28 +181,28 @@ public class TestURLUtil {url = new URL("http://subdomain.example.edu.tr");segments = URLUtil.getHostSegments(url);- Assert.assertEquals("subdomain", segments[0]);- Assert.assertEquals("example", segments[1]);- Assert.assertEquals("edu", segments[2]);- Assert.assertEquals("tr", segments[3]);+ assertEquals("subdomain", segments[0]);+ assertEquals("example", segments[1]);+ assertEquals("edu", segments[2]);+ assertEquals("tr", segments[3]);url = new URL("http://");segments = URLUtil.getHostSegments(url);- Assert.assertEquals(1, segments.length);- Assert.assertEquals("", segments[0]);+ assertEquals(1, segments.length);+ assertEquals("", segments[0]);url = new URL("http://140.211.11.130/foundation/contributing.html");segments = URLUtil.getHostSegments(url);- Assert.assertEquals(1, segments.length);- Assert.assertEquals("140.211.11.130", segments[0]);+ assertEquals(1, segments.length);+ assertEquals("140.211.11.130", segments[0]);// test non-asciiurl = new URL("http://www.example.商業.tw");segments = URLUtil.getHostSegments(url);- Assert.assertEquals("www", segments[0]);- Assert.assertEquals("example", segments[1]);- Assert.assertEquals("商業", segments[2]);- Assert.assertEquals("tw", segments[3]);+ assertEquals("www", segments[0]);+ assertEquals("example", segments[1]);+ assertEquals("商業", segments[2]);+ assertEquals("tw", segments[3]);}@@ -218,40 +219,40 @@ public class TestURLUtil {// 1) different domain them keep dest, temp or perm// a.com -> b.com*- Assert.assertEquals(bDotCom, URLUtil.chooseRepr(aDotCom, bDotCom, true));- Assert.assertEquals(bDotCom, URLUtil.chooseRepr(aDotCom, bDotCom, false));+ assertEquals(bDotCom, URLUtil.chooseRepr(aDotCom, bDotCom, true));+ assertEquals(bDotCom, URLUtil.chooseRepr(aDotCom, bDotCom, false));// 2) permanent and root, keep src// *a.com -> a.com?y=1 || *a.com -> a.com/xyz/index.html- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aQStr, false));- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aPath, false));+ assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aQStr, false));+ assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aPath, false));// 3) permanent and not root and dest root, keep dest// a.com/xyz/index.html -> a.com*- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aPath, aDotCom, false));+ assertEquals(aDotCom, URLUtil.chooseRepr(aPath, aDotCom, false));// 4) permanent and neither root keep dest// a.com/xyz/index.html -> a.com/abc/page.html*- Assert.assertEquals(aPath2, URLUtil.chooseRepr(aPath, aPath2, false));+ assertEquals(aPath2, URLUtil.chooseRepr(aPath, aPath2, false));// 5) temp and root and dest not root keep src// *a.com -> a.com/xyz/index.html- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aPath, true));+ assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aPath, true));// 6) temp and not root and dest root keep dest// a.com/xyz/index.html -> a.com*- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aPath, aDotCom, true));+ assertEquals(aDotCom, URLUtil.chooseRepr(aPath, aDotCom, true));// 7) temp and neither root, keep shortest, if hosts equal by path else by// hosts// a.com/xyz/index.html -> a.com/abc/page.html*// *www.a.com/xyz/index.html -> www.news.a.com/xyz/index.html- Assert.assertEquals(aPath2, URLUtil.chooseRepr(aPath, aPath2, true));- Assert.assertEquals(aPath, URLUtil.chooseRepr(aPath, aPath3, true));+ assertEquals(aPath2, URLUtil.chooseRepr(aPath, aPath2, true));+ assertEquals(aPath, URLUtil.chooseRepr(aPath, aPath3, true));// 8) temp and both root keep shortest sub domain// *www.a.com -> www.news.a.com- Assert.assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aSubDotCom, true));+ assertEquals(aDotCom, URLUtil.chooseRepr(aDotCom, aSubDotCom, true));}// from RFC3986 section 5.4.1@@ -274,31 +275,29 @@ public class TestURLUtil {public void testResolveURL() throws Exception {// test NUTCH-436URL u436 = new URL("http://a/b/c/d;p?q#f");- Assert.assertEquals("http://a/b/c/d;p?q#f", u436.toString());+ assertEquals("http://a/b/c/d;p?q#f", u436.toString());URL abs = URLUtil.resolveURL(u436, "?y");- Assert.assertEquals("http://a/b/c/d;p?y", abs.toString());+ assertEquals("http://a/b/c/d;p?y", abs.toString());// test NUTCH-566URL u566 = new URL("http://www.fleurie.org/entreprise.asp");abs = URLUtil.resolveURL(u566, "?id_entrep=111");- Assert.assertEquals("http://www.fleurie.org/entreprise.asp?id_entrep=111",+ assertEquals("http://www.fleurie.org/entreprise.asp?id_entrep=111",abs.toString());URL base = new URL(baseString);- Assert.assertEquals("base url parsing", baseString, base.toString());+ assertEquals(baseString, base.toString(), "base url parsing");for (int i = 0; i < targets.length; i++) {URL u = URLUtil.resolveURL(base, targets[i][0]);- Assert.assertEquals(targets[i][1], targets[i][1], u.toString());+ assertEquals(targets[i][1], targets[i][1], u.toString());}}@Testpublic void testToUNICODE() throws Exception {- Assert.assertEquals("http://www.çevir.com",+ assertEquals("http://www.çevir.com",URLUtil.toUNICODE("http://www.xn--evir-zoa.com"));- Assert.assertEquals("http://uni-tübingen.de/",+ assertEquals("http://uni-tübingen.de/",URLUtil.toUNICODE("http://xn--uni-tbingen-xhb.de/"));- Assert- .assertEquals(- "http://www.medizin.uni-tübingen.de:8080/search.php?q=abc#p1",+ assertEquals("http://www.medizin.uni-tübingen.de:8080/search.php?q=abc#p1",URLUtil.toUNICODE("http://www.medizin.xn--uni-tbingen-xhb.de:8080/search.php?q=abc#p1"));@@ -306,13 +305,11 @@ public class TestURLUtil {@Testpublic void testToASCII() throws Exception {- Assert.assertEquals("http://www.xn--evir-zoa.com",+ assertEquals("http://www.xn--evir-zoa.com",URLUtil.toASCII("http://www.çevir.com"));- Assert.assertEquals("http://xn--uni-tbingen-xhb.de/",+ assertEquals("http://xn--uni-tbingen-xhb.de/",URLUtil.toASCII("http://uni-tübingen.de/"));- Assert- .assertEquals(- "http://www.medizin.xn--uni-tbingen-xhb.de:8080/search.php?q=abc#p1",+ assertEquals("http://www.medizin.xn--uni-tbingen-xhb.de:8080/search.php?q=abc#p1",URLUtil.toASCII("http://www.medizin.uni-tübingen.de:8080/search.php?q=abc#p1"));}@@ -320,9 +317,9 @@ public class TestURLUtil {@Testpublic void testFileProtocol() throws Exception {// keep one single slash NUTCH-1483- Assert.assertEquals("file:/path/file.html",+ assertEquals("file:/path/file.html",URLUtil.toASCII("file:/path/file.html"));- Assert.assertEquals("file:/path/file.html",+ assertEquals("file:/path/file.html",URLUtil.toUNICODE("file:/path/file.html"));}diff --git a/src/test/org/apache/nutch/util/WritableTestUtils.java b/src/test/org/apache/nutch/util/WritableTestUtils.javaindex 3da2226d1..d4429dbf3 100644--- a/src/test/org/apache/nutch/util/WritableTestUtils.java+++ b/src/test/org/apache/nutch/util/WritableTestUtils.java@@ -18,7 +18,8 @@ package org.apache.nutch.util;import org.apache.hadoop.io.*;import org.apache.hadoop.conf.*;-import org.junit.Assert;++import static org.junit.jupiter.api.Assertions.assertEquals;public class WritableTestUtils {@@ -30,7 +31,7 @@ public class WritableTestUtils {/** Utility method for testing writables. */public static void testWritable(Writable before, Configuration conf)throws Exception {- Assert.assertEquals(before, writeRead(before, conf));+ assertEquals(before, writeRead(before, conf));}/** Utility method for testing writables. */