Created
July 21, 2010 06:05
-
-
Save choenes/484135 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.tynt.xiang; | |
import static org.junit.Assert.assertEquals; | |
import org.apache.pig.data.Tuple; | |
import org.junit.Before; | |
import org.junit.Test; | |
import com.tynt.xiang.helper.Helper; | |
import com.tynt.xiang.helper.PigRunner; | |
public class ExampleTest { | |
private static final String BASE_DIR = "../scripts/example/"; | |
private static final String SCRIPT_FILE = BASE_DIR + "example.pig"; | |
private static final String OUT_FILE = "./target/pig-output"; | |
private static final String IN_FILE = "./target/test-classes/example-input.log"; | |
private PigRunner runner; | |
@Before | |
public void setUp() throws Exception { | |
Helper.delete(OUT_FILE); | |
runner = new PigRunner(); | |
} | |
@Test | |
public void testRecordCount() throws Exception { | |
runner.execute(SCRIPT_FILE, "in_file="+IN_FILE,"out_file="+OUT_FILE); | |
List<Tuple> tuples = runner.getTuples("some_pig_alias"); | |
assertEquals(41, tuples.size()); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.tynt.xiang.helper; | |
import java.io.BufferedReader; | |
import java.io.BufferedWriter; | |
import java.io.FileReader; | |
import java.io.FileWriter; | |
import java.io.IOException; | |
import java.util.ArrayList; | |
import java.util.List; | |
import java.util.Iterator; | |
import org.apache.pig.ExecType; | |
import org.apache.pig.PigServer; | |
import org.apache.pig.data.Tuple; | |
import org.apache.pig.tools.parameters.ParameterSubstitutionPreprocessor; | |
import org.apache.pig.tools.parameters.ParseException; | |
public class PigRunner { | |
private PigServer pigServer; | |
public PigServer getPigServer() { | |
return pigServer; | |
} | |
public PigRunner() throws Exception { | |
pigServer = new PigServer(ExecType.LOCAL); | |
} | |
public void execute(String scriptFile, String... params) throws Exception { | |
String substFile = preprocess(scriptFile, params); | |
pigServer.registerScript(substFile); | |
} | |
public List<Tuple> getTuples(String aliasName) throws IOException { | |
List<Tuple> list = new ArrayList<Tuple>(); | |
Iterator<Tuple> tuples = pigServer.openIterator(aliasName); | |
while(tuples.hasNext()) { | |
Tuple t = tuples.next(); | |
list.add(t); | |
} | |
return list; | |
} | |
private String preprocess(String scriptFile, String... params) | |
throws IOException, ParseException { | |
ParameterSubstitutionPreprocessor psp = new ParameterSubstitutionPreprocessor( | |
50); | |
String substFile = scriptFile + ".subst"; | |
BufferedWriter writer = new BufferedWriter(new FileWriter(substFile)); | |
try { | |
// String content = FileUtils.readFileToString(new File(script)); | |
// System.out.println(content); | |
psp.genSubstitutedFile(new BufferedReader( | |
new FileReader(scriptFile)), writer, params, null); | |
} catch (org.apache.pig.tools.parameters.ParseException pex) { | |
throw new ParseException(pex.getMessage()); | |
} | |
return substFile; | |
} | |
} |
There's three new API in trunk for pig script which has parameters
registerScript(String fileName, Map<String,String> params)
registerScript(String fileName, List paramsFiles)
registerScript(String fileName, Map<String,String> params,List paramsFiles)
You can use that to replace your preprocess when you upgrade your pig
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Run entire pig scripts from your JUnit tests just like you'll run them from the cluster/cmd line.