Skip to content

R
reverse-web-link-graph
Commit 0fd7533d authored by Ali Saeed's avatar Ali Saeed
Browse files
Options

Reverse web link graph

parents
Hide whitespace changes
Inline Side-by-side
Showing with 286 additions and 0 deletions
.idea/.gitignore 0 → 100644
View file @ 0fd7533d
# Default ignored files
/shelf/
/workspace.xml
.idea/artifacts/ReverseWebLinkGraph_jar.xml 0 → 100644
View file @ 0fd7533d
<component name="ArtifactManager">
<artifact type="jar" name="ReverseWebLinkGraph:jar">
<output-path>$PROJECT_DIR$/out/artifacts/ReverseWebLinkGraph_jar</output-path>
<root id="archive" name="ReverseWebLinkGraph.jar">
<element id="module-output" name="ReverseWebLinkGraph" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/jakarta/activation/jakarta.activation-api/1.2.1/jakarta.activation-api-1.2.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-daemon/commons-daemon/1.0.13/commons-daemon-1.0.13.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/tukaani/xz/1.0/xz-1.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/mortbay/jetty/jetty/6.1.26/jetty-6.1.26.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-yarn-client/3.3.1/hadoop-yarn-client-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/curator/curator-client/2.6.0/curator-client-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/jersey-json/1.9/jersey-json-1.9.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/directory/api/api-asn1-api/1.0.0-M20/api-asn1-api-1.0.0-M20.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/guava/guava/11.0.2/guava-11.0.2.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/net/java/dev/jets3t/jets3t/0.9.0/jets3t-0.9.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/io/netty/netty/3.10.6.Final/netty-3.10.6.Final.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/thirdparty/hadoop-shaded-protobuf_3_7/1.1.1/hadoop-shaded-protobuf_3_7-1.1.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/ant/ant/1.6.5/ant-1.6.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/contribs/jersey-guice/1.19/jersey-guice-1.19.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/log4j/log4j/1.2.17/log4j-1.2.17.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/zookeeper/zookeeper/3.4.6/zookeeper-3.4.6.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/inject/extensions/guice-servlet/4.0/guice-servlet-4.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/commons/commons-math/2.1/commons-math-2.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/squareup/okio/okio/1.6.0/okio-1.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-cli/commons-cli/1.2/commons-cli-1.2.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/slf4j/slf4j-log4j12/1.7.5/slf4j-log4j12-1.7.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/javax/servlet/servlet-api/2.5/servlet-api-2.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-util-ajax/9.4.40.v20210413/jetty-util-ajax-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/protobuf/protobuf-java/2.5.0/protobuf-java-2.5.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-annotations/2.6.0/hadoop-annotations-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-el/commons-el/1.0/commons-el-1.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/codehaus/jackson/jackson-jaxrs/1.8.3/jackson-jaxrs-1.8.3.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/fusesource/leveldbjni/leveldbjni-all/1.8/leveldbjni-all-1.8.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/xml/bind/jaxb-impl/2.2.3-1/jaxb-impl-2.2.3-1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/squareup/okhttp/okhttp/2.7.5/okhttp-2.7.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/jersey-client/1.19/jersey-client-1.19.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/javax/xml/bind/jaxb-api/2.2.11/jaxb-api-2.2.11.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-yarn-api/3.3.1/hadoop-yarn-api-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/websocket/websocket-api/9.4.40.v20210413/websocket-api-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/codehaus/jettison/jettison/1.1/jettison-1.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-auth/2.6.0/hadoop-auth-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-hdfs-client/3.3.1/hadoop-hdfs-client-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/javax/servlet/jsp/jsp-api/2.1/jsp-api-2.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/directory/server/apacheds-i18n/2.0.0-M15/apacheds-i18n-2.0.0-M15.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/codehaus/jackson/jackson-mapper-asl/1.9.13/jackson-mapper-asl-1.9.13.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-mapreduce-client-core/3.3.1/hadoop-mapreduce-client-core-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-lang/commons-lang/2.6/commons-lang-2.6.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-server/9.4.40.v20210413/jetty-server-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/xerial/snappy/snappy-java/1.0.4.1/snappy-java-1.0.4.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/code/gson/gson/2.2.4/gson-2.2.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/websocket/websocket-client/9.4.40.v20210413/websocket-client-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-logging/commons-logging/1.1.3/commons-logging-1.1.3.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/httpcomponents/httpcore/4.1.2/httpcore-4.1.2.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/hsqldb/hsqldb/1.8.0.10/hsqldb-1.8.0.10.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-util/9.4.40.v20210413/jetty-util-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/io/netty/netty-all/4.1.61.Final/netty-all-4.1.61.Final.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/directory/server/apacheds-kerberos-codec/2.0.0-M15/apacheds-kerberos-codec-2.0.0-M15.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/httpcomponents/httpclient/4.1.2/httpclient-4.1.2.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/jamesmurty/utils/java-xmlbuilder/0.4/java-xmlbuilder-0.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-digester/commons-digester/1.8/commons-digester-1.8.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/core/jackson-core/2.10.5/jackson-core-2.10.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jdt/core/3.1.1/core-3.1.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/thoughtworks/paranamer/paranamer/2.3/paranamer-2.3.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/mortbay/jetty/jsp-2.1/6.1.14/jsp-2.1-6.1.14.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/javax/servlet/javax.servlet-api/3.1.0/javax.servlet-api-3.1.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/asm/asm/3.1/asm-3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/jakarta/xml/bind/jakarta.xml.bind-api/2.3.2/jakarta.xml.bind-api-2.3.2.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-configuration/commons-configuration/1.6/commons-configuration-1.6.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/oro/oro/2.0.8/oro-2.0.8.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/xmlenc/xmlenc/0.52/xmlenc-0.52.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/curator/curator-recipes/2.6.0/curator-recipes-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-beanutils/commons-beanutils/1.7.0/commons-beanutils-1.7.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/commons/commons-math3/3.1.1/commons-math3-3.1.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/codehaus/jackson/jackson-core-asl/1.9.13/jackson-core-asl-1.9.13.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-codec/commons-codec/1.4/commons-codec-1.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-httpclient/commons-httpclient/3.1/commons-httpclient-3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-net/commons-net/3.1/commons-net-3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/jersey-core/1.9/jersey-core-1.9.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-collections/commons-collections/3.2.1/commons-collections-3.2.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/javax/inject/javax.inject/1/javax.inject-1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-common/2.6.0/hadoop-common-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-hdfs/3.3.1/hadoop-hdfs-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/codehaus/jackson/jackson-xc/1.8.3/jackson-xc-1.8.3.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/tomcat/jasper-runtime/5.5.23/jasper-runtime-5.5.23.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/inject/guice/4.0/guice-4.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/curator/curator-framework/2.6.0/curator-framework-2.6.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/jersey-servlet/1.19/jersey-servlet-1.19.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/mortbay/jetty/jsp-api-2.1/6.1.14/jsp-api-2.1-6.1.14.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/htrace/htrace-core4/4.1.0-incubating/htrace-core4-4.1.0-incubating.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/thirdparty/hadoop-shaded-guava/1.1.1/hadoop-shaded-guava-1.1.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/commons/commons-compress/1.4.1/commons-compress-1.4.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="C:/Program Files/Java/jdk1.8.0_301/lib/tools.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-io/9.4.40.v20210413/jetty-io-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/mortbay/jetty/jetty-util/6.1.26/jetty-util-6.1.26.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/htrace/htrace-core/3.0.4/htrace-core-3.0.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/tomcat/jasper-compiler/5.5.23/jasper-compiler-5.5.23.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-yarn-common/3.3.1/hadoop-yarn-common-3.3.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/avro/avro/1.7.4/avro-1.7.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/sun/jersey/jersey-server/1.9/jersey-server-1.9.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/google/code/findbugs/jsr305/1.3.9/jsr305-1.3.9.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/jaxrs/jackson-jaxrs-json-provider/2.10.5/jackson-jaxrs-json-provider-2.10.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/jaxrs/jackson-jaxrs-base/2.10.5/jackson-jaxrs-base-2.10.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/jline/jline/3.9.0/jline-3.9.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/mortbay/jetty/servlet-api-2.5/6.1.14/servlet-api-2.5-6.1.14.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-http/9.4.40.v20210413/jetty-http-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-io/commons-io/2.4/commons-io-2.4.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/jetty-client/9.4.40.v20210413/jetty-client-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/jcraft/jsch/0.1.42/jsch-0.1.42.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/module/jackson-module-jaxb-annotations/2.10.5/jackson-module-jaxb-annotations-2.10.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/slf4j/slf4j-api/1.7.5/slf4j-api-1.7.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/aopalliance/aopalliance/1.0/aopalliance-1.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/core/jackson-annotations/2.10.5/jackson-annotations-2.10.5.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/hadoop/hadoop-core/1.2.1/hadoop-core-1.2.1.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/eclipse/jetty/websocket/websocket-common/9.4.40.v20210413/websocket-common-9.4.40.v20210413.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/commons-beanutils/commons-beanutils-core/1.8.0/commons-beanutils-core-1.8.0.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/org/apache/directory/api/api-util/1.0.0-M20/api-util-1.0.0-M20.jar" path-in-jar="/" />
<element id="extracted-dir" path="$MAVEN_REPOSITORY$/com/fasterxml/jackson/core/jackson-databind/2.10.5.1/jackson-databind-2.10.5.1.jar" path-in-jar="/" />
</root>
</artifact>
</component>
\ No newline at end of file
.idea/compiler.xml 0 → 100644
View file @ 0fd7533d
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="CompilerConfiguration">
<annotationProcessing>
<profile name="Maven default annotation processors profile" enabled="true">
<sourceOutputDir name="target/generated-sources/annotations" />
<sourceTestOutputDir name="target/generated-test-sources/test-annotations" />
<outputRelativeToContentRoot value="true" />
<module name="ReverseWebLinkGraph" />
</profile>
</annotationProcessing>
</component>
</project>
\ No newline at end of file
.idea/encodings.xml 0 → 100644
View file @ 0fd7533d
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Encoding">
<file url="file://$PROJECT_DIR$/src/main/java" charset="UTF-8" />
<file url="file://$PROJECT_DIR$/src/main/resources" charset="UTF-8" />
</component>
</project>
\ No newline at end of file
.idea/jarRepositories.xml 0 → 100644
View file @ 0fd7533d
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="RemoteRepositoriesConfiguration">
<remote-repository>
<option name="id" value="central" />
<option name="name" value="Central Repository" />
<option name="url" value="https://repo.maven.apache.org/maven2" />
</remote-repository>
<remote-repository>
<option name="id" value="central" />
<option name="name" value="Maven Central repository" />
<option name="url" value="https://repo1.maven.org/maven2" />
</remote-repository>
<remote-repository>
<option name="id" value="jboss.community" />
<option name="name" value="JBoss Community repository" />
<option name="url" value="https://repository.jboss.org/nexus/content/repositories/public/" />
</remote-repository>
</component>
</project>
\ No newline at end of file
.idea/misc.xml 0 → 100644
View file @ 0fd7533d
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ExternalStorageConfigurationManager" enabled="true" />
<component name="MavenProjectsManager">
<option name="originalFiles">
<list>
<option value="$PROJECT_DIR$/pom.xml" />
</list>
</option>
</component>
<component name="ProjectRootManager" version="2" languageLevel="JDK_1_8" default="true" project-jdk-name="1.8" project-jdk-type="JavaSDK">
<output url="file://$PROJECT_DIR$/out" />
</component>
</project>
\ No newline at end of file
input.txt 0 → 100644
View file @ 0fd7533d
page1, page2
page2, page3
page2, page4
page3, page4
page4, page1
page4, page2
\ No newline at end of file
pom.xml 0 → 100644
View file @ 0fd7533d
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>org.example</groupId>
<artifactId>ReverseWebLinkGraph</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.2.1</version>
</dependency>
</dependencies>
</project>
\ No newline at end of file
src/main/java/org/example/ReverseWebLinkGraph.java 0 → 100644
View file @ 0fd7533d
package org.example;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class ReverseWebLinkGraph {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] files = new GenericOptionsParser(conf, args).getRemainingArgs();
Path input = new Path(files[0]);
Path output = new Path(files[1]);
Job job = new Job(conf, "reverseweblinkgraph");
job.setJarByClass(ReverseWebLinkGraph.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, input);
FileOutputFormat.setOutputPath(job, output);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static class Map extends Mapper<LongWritable, Text, Text, Text> {
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] pages = line.split(",");
if (pages.length == 2) {
String sourcePage = pages[0].trim();
String targetPage = pages[1].trim();
context.write(new Text(targetPage), new Text(sourcePage));
}
}
}
public static class Reduce extends Reducer<Text, Text, Text, Text> {
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
List<String> sources = new ArrayList<>();
for (Text value : values) {
sources.add(value.toString());
}
String sourceList = String.join(", ", sources);
context.write(key, new Text(sourceList));
}
}
}
\ No newline at end of file
src/main/resources/META-INF/MANIFEST.MF 0 → 100644
View file @ 0fd7533d
Manifest-Version: 1.0
Main-Class: org.example.ReverseWebLinkGraph
target/classes/META-INF/MANIFEST.MF 0 → 100644
View file @ 0fd7533d
Manifest-Version: 1.0
Main-Class: org.example.ReverseWebLinkGraph
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment

HIAST - GitLab