fileconcatenator-pge/000755 036164 000024 00000000000 11617101420 015601 5ustar00rvermastaff000000 000000 fileconcatenator-pge/.classpath000644 036164 000024 00000001273 11617055321 017577 0ustar00rvermastaff000000 000000 <?xml version="1.0" encoding="UTF-8"?>
<classpath>
	<classpathentry kind="src" output="target/classes" path="src/main/java"/>
	<classpathentry excluding="**" kind="src" output="target/classes" path="src/main/resources"/>
	<classpathentry kind="src" output="target/test-classes" path="src/test/java"/>
	<classpathentry excluding="**" kind="src" output="target/test-classes" path="src/test/resources"/>
	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/J2SE-1.5"/>
	<classpathentry kind="con" path="org.maven.ide.eclipse.MAVEN2_CLASSPATH_CONTAINER"/>
	<classpathentry kind="output" path="target/classes"/>
</classpath>
fileconcatenator-pge/.project000644 036164 000024 00000001047 11617055320 017261 0ustar00rvermastaff000000 000000 <?xml version="1.0" encoding="UTF-8"?>
<projectDescription>
	<name>fileconcatenator-pge</name>
	<comment></comment>
	<projects>
	</projects>
	<buildSpec>
		<buildCommand>
			<name>org.eclipse.jdt.core.javabuilder</name>
			<arguments>
			</arguments>
		</buildCommand>
		<buildCommand>
			<name>org.maven.ide.eclipse.maven2Builder</name>
			<arguments>
			</arguments>
		</buildCommand>
	</buildSpec>
	<natures>
		<nature>org.eclipse.jdt.core.javanature</nature>
		<nature>org.maven.ide.eclipse.maven2Nature</nature>
	</natures>
</projectDescription>
fileconcatenator-pge/.settings/000755 036164 000024 00000000000 11617101425 017524 5ustar00rvermastaff000000 000000 fileconcatenator-pge/pom.xml000644 036164 000024 00000001662 11617101305 017125 0ustar00rvermastaff000000 000000 <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.apache.oodt.pge</groupId>
  <artifactId>fileconcatenator-pge</artifactId>
  <version>1.0</version>
  <name>FileConcatenatorPGE</name>
  <description>Example file-concatenator project for learning about CAS-PGE</description>
  <build>
    <plugins>
      <plugin>
        <artifactId>maven-compiler-plugin</artifactId>
        <configuration>
          <source>1.5</source>
          <target>1.5</target>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <dependencies>
  	<dependency>
  		<groupId>org.apache.oodt</groupId>
  		<artifactId>cas-pge</artifactId>
  		<version>0.3</version>
  		<scope>compile</scope>
  	</dependency>
  </dependencies>
</project>
fileconcatenator-pge/src/000755 036164 000024 00000000000 11617054756 016413 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/000755 036164 000024 00000000000 11617054756 017337 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/test/000755 036164 000024 00000000000 11617054756 017372 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/test/java/000755 036164 000024 00000000000 11617054756 020313 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/test/resources/000755 036164 000024 00000000000 11617054756 021404 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/000755 036164 000024 00000000000 11617054756 020260 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/000755 036164 000024 00000000000 11617054756 021351 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/config/000755 036164 000024 00000000000 11617054756 022616 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/extractors/000755 036164 000024 00000000000 11617054756 023547 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/files/000755 036164 000024 00000000000 11617054756 022453 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/files/concatenatingInputFile1.txt000644 036164 000024 00000001633 11617054756 027735 0ustar00rvermastaff000000 000000 Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce quis nunc
quam, vel laoreet libero. Pellentesque sit amet mauris ligula. Etiam sed
metus vel elit feugiat accumsan at ac nisi. Cras a turpis scelerisque
augue semper mollis. Proin rutrum sollicitudin est at scelerisque.
Aenean ligula eros, luctus consequat gravida et, gravida in ligula. Nunc
venenatis tellus in urna placerat accumsan. Ut vehicula adipiscing
faucibus. Lorem ipsum dolor sit amet, consectetur adipiscing elit.
Phasellus id diam sed nulla venenatis laoreet at nec elit. Suspendisse
et mauris nec tortor vehicula aliquet. Cras ornare dignissim vestibulum.
Vestibulum aliquet magna nec diam gravida gravida. Duis semper, erat in
ultrices convallis, lorem enim laoreet magna, eget sagittis ligula nunc
eu quam. Nunc ac tempus orci. Pellentesque semper eleifend suscipit. Nam
est nisi, scelerisque sodales bibendum eget, porttitor fringilla metus. fileconcatenator-pge/src/main/resources/files/concatenatingInputFile2.txt000644 036164 000024 00000001453 11617054756 027736 0ustar00rvermastaff000000 000000 

Aenean vel nulla ut nulla tempus venenatis in eget est. Curabitur
tincidunt mattis dolor rutrum gravida. Nunc vel dui eu diam luctus
dictum non vitae leo. Morbi et velit neque. Phasellus placerat augue eu
nisi convallis adipiscing. Donec sagittis tristique tellus, ut aliquet
quam pellentesque ut. Ut tortor nibh, ultrices in bibendum vitae, mollis
a justo. Nulla fermentum, urna sed bibendum tempor, ipsum leo tincidunt
tellus, ac lacinia purus justo ut nibh. Pellentesque gravida, metus
lobortis convallis egestas, erat dui ullamcorper leo, vitae aliquet
justo nunc ac justo. Vivamus dapibus, quam in eleifend aliquet, erat
nulla molestie lectus, ut gravida nunc augue vitae nulla. Nam vulputate
arcu ut ante pharetra a dictum nunc tincidunt. Nunc tortor quam,
convallis vel lacinia ac, dignissim sed sem. 
fileconcatenator-pge/src/main/resources/extractors/concatenatingfilename.extractor.config.xml000644 036164 000024 00000001037 11617077706 034066 0ustar00rvermastaff000000 000000 <?xml version="1.0" encoding="UTF-8"?>
  <input>
    <group name="SubstringOffsetGroup">
      <vector name="ConcatenatingInputFileName">
        <element>1</element>
        <element>33</element>      
      </vector>
   </group>
    
    <group name="CommonMetadata">
        <scalar name="DataVersion">1.0</scalar>
        <scalar name="CollectionName">File Concatenator product</scalar>
        <scalar name="DataProvider">OODT-PGE</scalar>
        <scalar name="ProductType">FileConcatenatorProductType</scalar>
    </group>
    
</input>fileconcatenator-pge/src/main/resources/extractors/metlistwriter/000755 036164 000024 00000000000 11617054756 026465 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/resources/extractors/metlistwriter/metout.xml000644 036164 000024 00000000235 11617054756 030524 0ustar00rvermastaff000000 000000 <?xml version="1.0" encoding="UTF-8"?>
<metadataList>
    
    <!-- one or more of these -->
    <metadata key="JobId" value="[JobId]"/>
    
</metadataList>fileconcatenator-pge/src/main/resources/config/PGEConfig.xml000644 036164 000024 00000004375 11617077701 025105 0ustar00rvermastaff000000 000000 <?xml version="1.0" encoding="UTF-8"?>
<pgeConfig>

        <!-- How to run the PGE -->
        <exe dir="[JobDir]" shell="/bin/bash">
          <!-- cd to PGE root -->
          <cmd>cd [PGE_ROOT]/file_concatenator</cmd>
              	<cmd>cp [InputFile1] [OutputFile]</cmd>
              	<cmd>cat [InputFile2] >> [OutputFile]</cmd>
        </exe>

	    <!-- Files to ingest -->
	    <output>
        	<!-- one or more of these -->
       	 	<dir path="[JobDir]" createBeforeExe="false">
            
            	<!-- one or more of these ** regExp or name can be used-->
            	<files regExp=".*\.txt" metFileWriterClass="org.apache.oodt.pge.examples.fileconcatenator.writers.ConcactenatingFilenameExtractorWriter"  args="[PGE_ROOT]/file_concatenator/extractors/concatenatingfilename.extractor.config.xml"/>
                <files regExp=".*\.txt" metFileWriterClass="org.apache.oodt.cas.pge.writers.metlist.MetadataListPcsMetFileWriter" args="[PGE_ROOT]/file_concatenator/extractors/metlistwriter/metout.xml"/>
            </dir>
        </output>

        <!-- Custom metadata to add to output files -->
        <customMetadata>
                <!-- helpful keys -->
                <metadata key="LessThan" val="&#x3C;"/>
                <metadata key="LessThanOrEqualTo" val="[LessThan]="/>
                <metadata key="GreaterThan" val="&#x3E;"/>
                <metadata key="GreaterThanOrEqualTo" val="[GreaterThan]="/>
                <metadata key="Exclamation" val="&#33;"/>
                <metadata key="Ampersand" val="&#38;"/>
                <metadata key="NotEqualTo" val="[Ampersand]="/>
                <metadata key="LogicalAnd" val="[Ampersand][Ampersand]"/>
                <metadata key="CshPipeToStdOutAndError" val="[GreaterThan][Ampersand][Exclamation]"/>

				<metadata key="ProductionDateTime" val="[DATE.UTC]"/>
				<metadata key="JobDir" val="[PGE_ROOT]/file_concatenator/output/jobs/job-[ProductionDateTime]"/>
				<metadata key="InputFile1" val="[PGE_ROOT]/file_concatenator/files/concatenatingInputFile1.txt"/>
				<metadata key="InputFile2" val="[PGE_ROOT]/file_concatenator/files/concatenatingInputFile2.txt"/>
				<metadata key="OutputFile" val="[JobDir]/concatenatedOutputFile-[ProductionDateTime].txt"/>        
      </customMetadata>

</pgeConfig>
fileconcatenator-pge/src/main/java/org/000755 036164 000024 00000000000 11617054756 021047 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/org/apache/000755 036164 000024 00000000000 11617054756 022270 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/org/apache/oodt/000755 036164 000024 00000000000 11617054756 023235 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/org/apache/oodt/pge/000755 036164 000024 00000000000 11617054756 024010 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/org/apache/oodt/pge/examples/000755 036164 000024 00000000000 11617054756 025626 5ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/java/org/apache/oodt/pge/examples/fileconcatenator/000755 036164 000024 00000000000 11617054756 031146 5ustar00rvermastaff000000 000000 src/main/java/org/apache/oodt/pge/examples/fileconcatenator/FileConcatenatorPGETask.java000644 036164 000024 00000002420 11617054756 036327 0ustar00rvermastaff000000 000000 fileconcatenator-pgepackage org.apache.oodt.pge.examples.fileconcatenator;

import org.apache.oodt.cas.pge.PGETaskInstance;
import org.apache.oodt.cas.pge.metadata.PgeTaskMetadataKeys;

public class FileConcatenatorPGETask extends PGETaskInstance {
	  
	/* PGE task statuses */
	  public static final String STAGING_INPUT = "STAGING INPUT";
	  
	  public static final String CONF_FILE_BUILD = "BUILDING CONFIG FILE";
	  
	  public static final String RUNNING_PGE = "PGE EXEC";
	  
	  public static final String CRAWLING = "CRAWLING";

	  /* (non-Javadoc)
	   * @see org.apache.oodt.cas.pge.PGETaskInstance#updateStatus(java.lang.String)
	   */
	  @Override
	  protected void updateStatus(String status) {
	     String proteoStatus = this.convertStatus(status);
	     super.updateStatus(proteoStatus);
	  }

	  private String convertStatus(String casPgeStatus) {
	    if (casPgeStatus.equals(PgeTaskMetadataKeys.CONF_FILE_BUILD)) {
	        return CONF_FILE_BUILD;
	    } else if (casPgeStatus.equals(PgeTaskMetadataKeys.STAGING_INPUT)) {
	        return STAGING_INPUT;
	    } else if (casPgeStatus.equals(PgeTaskMetadataKeys.CRAWLING)) {
	        return CRAWLING;
	    } else if (casPgeStatus.equals(PgeTaskMetadataKeys.RUNNING_PGE)) {
	        return RUNNING_PGE;
	    } else
	        return casPgeStatus;
	}
	  
}
fileconcatenator-pge/src/main/java/org/apache/oodt/pge/examples/fileconcatenator/writers/000755 036164 000024 00000000000 11617054756 032645 5ustar00rvermastaff000000 000000 org/apache/oodt/pge/examples/fileconcatenator/writers/ConcactenatingFilenameExtractorWriter.java000600 036164 000024 00000002125 11617077213 043064 0ustar00rvermastaff000000 000000 fileconcatenator-pge/src/main/javapackage org.apache.oodt.pge.examples.fileconcatenator.writers;

import java.io.File;
import java.util.logging.Logger;

import org.apache.oodt.cas.metadata.Metadata;
import org.apache.oodt.cas.metadata.extractors.FilenameTokenMetExtractor;
import org.apache.oodt.cas.pge.writers.PcsMetFileWriter;

public class ConcactenatingFilenameExtractorWriter extends PcsMetFileWriter {

	private static final Logger LOG = Logger.getLogger(ConcactenatingFilenameExtractorWriter.class
		      .getName());	
	
	@Override
	protected Metadata getSciPgeSpecificMetadata(File sciPgeCreatedDataFile,
			Metadata inputMetadata, Object... customArgs) throws Exception {

		Metadata met = new Metadata();
		met.addMetadata(inputMetadata);
		met.addMetadata("ProductType", "GenericFile");
		
	    String metConfFilePath = String.valueOf(customArgs[0]);
	    LOG.info("metConfFilePath = ["+metConfFilePath+"]");
	    FilenameTokenMetExtractor extractor = new FilenameTokenMetExtractor();
	    extractor.setConfigFile(metConfFilePath);
	    met.addMetadata(extractor.extractMetadata(sciPgeCreatedDataFile));
	    
		return met;
	}

}
fileconcatenator-pge/.settings/org.eclipse.jdt.core.prefs000644 036164 000024 00000000414 11617055320 024507 0ustar00rvermastaff000000 000000 #Fri Aug 05 14:04:16 PDT 2011
eclipse.preferences.version=1
org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.5
org.eclipse.jdt.core.compiler.compliance=1.5
org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning
org.eclipse.jdt.core.compiler.source=1.5
fileconcatenator-pge/.settings/org.maven.ide.eclipse.prefs000644 036164 000024 00000000406 11617055300 024644 0ustar00rvermastaff000000 000000 #Fri Aug 05 14:04:00 PDT 2011
activeProfiles=
eclipse.preferences.version=1
fullBuildGoals=process-test-resources
includeModules=false
resolveWorkspaceProjects=true
resourceFilterGoals=process-resources resources\:testResources
skipCompilerPlugin=true
version=1