Maven pom.xml for a nutch project, that do an overlay on the nutch source zip file.

README

This is the project structure :
├── pom.xml
└── src
    ├── filters
    │   └── filter.properties
    └── main
        └── resources
            ├── conf
            │   ├── gora.properties
            │   ├── nutch-site.xml
            │   └── regex-urlfilter.txt
            ├── default.properties
            ├── ivy
            │   └── ivy.xml
            └── urls
                └── seed.txt

Nutch - pom.xml

<?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/maven-v4_0_0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<packaging>pom</packaging>

	<!-- =========== -->
	<!-- = General = -->
	<!-- =========== -->
	<groupId>com.logisima.search</groupId>
	<artifactId>crawler</artifactId>
	<version>1.0-SNAPSHOT</version>
	<name>Web crawler based on nutch</name>
	
	<!-- ============== -->
	<!-- = Developers = -->
	<!-- ============== -->
	<developers>
		<developer>
            <id>bsimard</id>
            <name>Benoît Simard</name>
            <email>[email protected]</email>
        </developer>
    </developers>

    <!-- ============== -->
    <!-- = Properties = -->
    <!-- ============== -->
    <properties>
        <nutch.version>2.2.1</nutch.version>
        <nutch.download>http://mir2.ovh.net/ftp.apache.org/dist/nutch/${nutch.version}/apache-nutch-${nutch.version}-src.tar.gz</nutch.download>
    </properties>

    <!-- ================ -->
    <!-- = Dependencies = -->
    <!-- ================ -->
    <dependencies>
    </dependencies>

    <!-- ========= -->
    <!-- = Build = -->
    <!-- ========= -->
    <build>      
        <pluginManagement>
            <plugins>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-resources-plugin</artifactId>
                    <version>2.6</version>
                </plugin>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-antrun-plugin</artifactId>
                    <version>1.6</version>
                </plugin>
            </plugins>
        </pluginManagement>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-resources-plugin</artifactId>
                <executions>
                    <execution>
                        <id>copy-resources</id>
                        <phase>compile</phase>
                        <goals>
                            <goal>copy-resources</goal>
                        </goals>
                        <configuration>
                            <outputDirectory>${project.build.directory}/apache-nutch-${nutch.version}</outputDirectory>
                            <filters>
                                <filter>src/filters/filter.properties</filter>
                            </filters>
                            <resources>          
                                <resource>
                                    <directory>src/main/resources</directory>
                                    <filtering>true</filtering>
                                </resource>
                            </resources>              
                        </configuration>            
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-antrun-plugin</artifactId>
                <!-- Adding this so we can invoke javac in ant build's file-->
                <dependencies>
                    <dependency>
                        <groupId>com.sun</groupId>
                        <artifactId>tools</artifactId>
                        <version>1.6</version>
                        <scope>system</scope>
                        <systemPath>${java.home}/../lib/tools.jar</systemPath>
                    </dependency>
                </dependencies>
                <executions>
                    <execution>
                        <id>dependency</id>
                        <phase>validate</phase>
                        <goals>
                            <goal>run</goal>
                        </goals>
                        <configuration>
                            <tasks>
                                <echo message="Downloading nutch src archive at ${nutch.download}" />
                                <get src="${nutch.download}" dest="${project.build.directory}"/>
                                <echo message="Untar nutch archive apache-nutch-${nutch.version}-src.tar.gz"/>
                                <gunzip src="${project.build.directory}/apache-nutch-${nutch.version}-src.tar.gz"/>
                                <untar src="${project.build.directory}/apache-nutch-${nutch.version}-src.tar" dest="${project.build.directory}"/>
                            </tasks>
                        </configuration>
                    </execution>
                    <execution>
                        <id>compile</id>
                        <phase>compile</phase>
                        <goals>
                            <goal>run</goal>
                        </goals>
                        <configuration>
                            <tasks>
                                <echo message="Compile nutch" />
                                <ant antfile="${project.build.directory}/apache-nutch-${nutch.version}/build.xml" target="runtime"  dir="${project.build.directory}/apache-nutch-${nutch.version}">
                                    <property name="final.name" value="${project.artifactId}"/>
                                </ant>
                                <move file="${project.build.directory}/apache-nutch-${nutch.version}/urls" todir="${project.build.directory}/apache-nutch-${nutch.version}/runtime/local/" />
                            </tasks>
                        </configuration>
                    </execution>
                    <execution>
                        <id>package</id>
                        <phase>package</phase>
                        <goals>
                            <goal>run</goal>
                        </goals>
                        <configuration>
                            <tasks>
                                <echo message="Packaging" />
                                <delete dir="${project.build.directory}/apache-nutch-${nutch.version}/runtime/local/test"/>
                                <zip destfile="${project.build.directory}/${project.artifactId}.zip" basedir="${project.build.directory}/apache-nutch-${nutch.version}/runtime/local/"/>
                            </tasks>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>