Develop Reference

Bulk Load to HBase: ERROR : java.lang.ClassCastException: org.apache.hadoop.io.FloatWritable cannot be cast to org.apache.hadoop.hbase.Cell

In Java I've to import with MapReduce some data from a tsv file (ca 21*10^6 of rows) into an HBase table.
Every row is:
XYZ|XZS   YSY|SDS|XDA|JKX|SDS   0.XXXXXXXXX
The HTable has 5 column family : A,B,C,D,E
The first couple of everyline of the file is my HBase rowkey.
The second group of five are 5 column qualifier:
YSY|SDS|XDA|JKX|SDS  -> for column family A
YSY|SDS|XDA|JKX    -> for column family B
YSY|SDS|XDA      -> for column family C
YSY|SDS        -> for column family D
YSY          -> for column family E
The last is the value to insert inside a cell.
I've also to aggregate with a sum Σ all values with the same qualifier (1 or 2 or 3 or 4 or 5) (this will be part of my Reducer).
This is my driver:
public class Driver {
private static final String COLUMN_FAMILY_1 = "A";
private static final String COLUMN_FAMILY_2 = "B";
private static final String COLUMN_FAMILY_3 = "C";
private static final String COLUMN_FAMILY_4 = "D";
private static final String COLUMN_FAMILY_5 = "E";
private static final String TABLENAME = "abe:data";
private static final String DATA_SEPARATOR = "\t";
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration configuration = HBaseConfiguration.create();
//Configuration Settings about hbase table
configuration.set("hbase.table.name", TABLENAME);
configuration.set("colomn_family_1", COLUMN_FAMILY_1);
configuration.set("colomn_family_2", COLUMN_FAMILY_2);
configuration.set("colomn_family_3", COLUMN_FAMILY_3);
configuration.set("colomn_family_4", COLUMN_FAMILY_4);
configuration.set("colomn_family_5", COLUMN_FAMILY_5);
configuration.set("data_separator", DATA_SEPARATOR);
if (args.length!= 2){
System.out.println("Usage: ");
System.out.println("-\t args[0] -> HDFS input path");
System.err.println("-\r args[1] -> HDFS output path ");
System.exit(1);
}
String inputPath = args[0];
String outputPath = args[1];
Path inputHdfsPath = new Path(inputPath);
Path outputHdfsPath = new Path(outputPath);
Job job = null;
try {
job = Job.getInstance(configuration);
} catch (IOException e) {
System.out.println("\n\t--->Exception: Error trying getinstance of job.<---\n");
e.printStackTrace();
}
job.setJobName("Bulk Loading HBase Table: "+ "\""+ TABLENAME+"\" with aggregation.");
job.setJarByClass(Driver.class);
//MAPPER
job.setInputFormatClass(TextInputFormat.class);
job.setMapperClass(MappingClass.class);
job.setMapOutputKeyClass(ImmutableBytesWritable.class);
job.setMapOutputValueClass(FloatWritable.class);
try {
FileInputFormat.addInputPath(job, inputHdfsPath);
} catch (IllegalArgumentException | IOException e) {
System.out.println("Error setting inputPath in FileInputFormat");
e.printStackTrace();
}
try {
FileSystem.get(configuration).delete(outputHdfsPath, true);
} catch (IllegalArgumentException | IOException e) {
System.out.println("");
e.printStackTrace();
}
//Setting output FileSystem.Path to save HFile to bulkImport
FileOutputFormat.setOutputPath(job, outputHdfsPath);
FileSystem hdfs;
//Deleting output folder if exists
try {
hdfs = FileSystem.get(configuration);
if(hdfs.exists(outputHdfsPath)){
hdfs.delete(outputHdfsPath, true); //Delete existing Directory
}
} catch (IllegalArgumentException | IOException e) {
e.printStackTrace();
}
//Variables to access to HBase
Connection hbCon = ConnectionFactory.createConnection(configuration);
Table hTable = hbCon.getTable(TableName.valueOf(TABLENAME));
RegionLocator regionLocator = hbCon.getRegionLocator(TableName.valueOf(TABLENAME));
Admin admin = hbCon.getAdmin();
HFileOutputFormat2.configureIncrementalLoad(job, hTable, regionLocator);
// Wait for HFiles creations
boolean result = job.waitForCompletion(true);
LoadIncrementalHFiles loadFfiles = null;
try {
loadFfiles = new LoadIncrementalHFiles(configuration);
} catch (Exception e) {
System.out.println("Error configuring LoadIncrementalHFiles.");
e.printStackTrace();
}
if (result){
loadFfiles.doBulkLoad(outputHdfsPath, admin, hTable, regionLocator);
System.out.println("Bulk Import Completed.");
}
else {
System.out.println("Error in completing job. No bulkimport.");
}
}
}
My Mapper is:
public class MappingClass extends Mapper<LongWritable,Text,ImmutableBytesWritable,FloatWritable>{
private String separator;
#Override
protected void setup(Context context) throws IOException, InterruptedException {
Configuration configuration = context.getConfiguration();
separator = configuration.get("data_separator");
}
#Override
public void map(LongWritable key,Text line,Context context){
String[] values = line.toString().split(separator);
String rowkey = values[0];
String[] allQualifiers = values[1].split("\\|");
String percentage = values[2];
System.out.println(percentage);
String toQ1 = new String(allQualifiers[0]+"|"+allQualifiers[1]+"|"+allQualifiers[2]+"|"+allQualifiers[3]+"|"+allQualifiers[4]);
String toQ2= new String(allQualifiers[0]+"|"+allQualifiers[1]+"|"+allQualifiers[2]+"|"+allQualifiers[3]);
String toQ3 = new String(allQualifiers[0]+"|"+allQualifiers[1]+"|"+allQualifiers[2]);
String toQ4 = new String(allQualifiers[0]+"|"+allQualifiers[1]);
String toQ5 = new String(allQualifiers[0]);
ImmutableBytesWritable ibw = new ImmutableBytesWritable();
FloatWritable valueOut = new FloatWritable(Float.parseFloat(percentage));
ibw.set(Bytes.toBytes(new String(rowkey+"_"+toQ1)));
try {
context.write(ibw, valueOut);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
ibw.set(Bytes.toBytes(new String(rowkey+"_"+toQ2)));
try {
context.write(ibw, valueOut);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
ibw.set(Bytes.toBytes(new String(rowkey+"_"+toQ3)));
try {
context.write(ibw, valueOut);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
ibw.set(Bytes.toBytes(new String(rowkey+"_"+toQ4)));
try {
context.write(ibw, valueOut);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
ibw.set(Bytes.toBytes(new String(rowkey+"_"+toQ5)));
try {
context.write(ibw, valueOut);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
}
}
This is my Reducer:
public class ReducingClass extends Reducer<ImmutableBytesWritable, FloatWritable, ImmutableBytesWritable, KeyValue> {
private String columnFamily_1;
private String columnFamily_2;
private String columnFamily_3;
private String columnFamily_4;
private String columnFamily_5;
private float sum;
#Override
protected void setup(Context context) throws IOException, InterruptedException {
Configuration configuration = context.getConfiguration();
columnFamily_1 = configuration.get("colomn_family_1");
columnFamily_2 = configuration.get("colomn_family_2");
columnFamily_3 = configuration.get("colomn_family_3");
columnFamily_4 = configuration.get("colomn_family_4");
columnFamily_5 = configuration.get("colomn_family_5");
}
#Override
public void reduce(ImmutableBytesWritable key, Iterable<FloatWritable> values, Context context){
String[] rk_cq = key.toString().split("_");
String rowkey = rk_cq[0];
String cq = rk_cq[1];
String colFamily = this.getFamily(cq);
sum = 0;
for(FloatWritable fw : values)
sum += fw.get();
ImmutableBytesWritable ibw = new ImmutableBytesWritable(rowkey.getBytes());
KeyValue kv = new KeyValue(rowkey.getBytes(), colFamily.getBytes(), cq.getBytes(), Float.toString(sum).getBytes());;
try {
context.write(ibw, kv);
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
}
private String getFamily(String cq){
String cf = new String();
switch (cq.split("\\|").length) {
case 1:
cf = columnFamily_1;
break;
case 2:
cf = columnFamily_2;
break;
case 3:
cf = columnFamily_3;
break;
case 4:
cf = columnFamily_4;
break;
case 5:
cf = columnFamily_5;
break;
default:
break;
}
return cf;
}
}
Now The Error:
17/05/08 20:04:22 INFO mapreduce.Job: map 100% reduce 29%
17/05/08 20:04:22 INFO mapreduce.Job: Task Id : attempt_1485334922305_5537_r_000000_2, Status : FAILED
Error: java.lang.ClassCastException: org.apache.hadoop.io.FloatWritable cannot be cast to org.apache.hadoop.hbase.Cell
 at org.apache.hadoop.hbase.mapreduce.HFileOutputFormat2$1.write(HFileOutputFormat2.java:167)
 at org.apache.hadoop.mapred.ReduceTask$NewTrackingRecordWriter.write(ReduceTask.java:558)
 at org.apache.hadoop.mapreduce.task.TaskInputOutputContextImpl.write(TaskInputOutputContextImpl.java:89)
 at org.apache.hadoop.mapreduce.lib.reduce.WrappedReducer$Context.write(WrappedReducer.java:105)
 at org.apache.hadoop.mapreduce.Reducer.reduce(Reducer.java:150)
 at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:171)
 at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:627)
 at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:389)
 at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:168)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:422)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
 at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:162)
Thanks for any help.

I fixed it. In the driver i forgot:
job.setReducerClass(ReducingClass.class);

File Structured Error [duplicate]

This question already has an answer here:
StreamCorruptedException: invalid type code: AC
(1 answer)
Closed 5 years ago.
sorry to bother you, once again I need help on the Java language , more precisely on the file structured as the title .
The error in question is that after you have stored more than once , I read reports an error (of course putting in append mode) , and does so even if I do all in the main program ...
My program consists of three classes in three files:
Alluno.java:
import java.io.Serializable;
class Alunno implements Serializable {
private String nome, cognome, data_nascita, indirizzo, residenza, telefono;
public Alunno() {
nome = ""; cognome = ""; data_nascita = ""; indirizzo = ""; residenza = ""; telefono = "";
}
public void setNome(String nome) {
this.nome = nome;
}
void setCognome(String cognome) {
this.cognome = cognome;
}
void setData_Nascita(String data_nascita) {
this.data_nascita = data_nascita;
}
void setIndirizzo(String indirizzo) {
this.indirizzo = indirizzo;
}
void setResidenza(String residenza) {
this.residenza = residenza;
}
void setTelefono(String telefono) {
this.telefono = telefono;
}
}
File.java:
import java.io.*;
class File {
private int dim;
public Alunno nuovoAlunno() throws IOException {
BufferedReader t = new BufferedReader(new InputStreamReader(System.in));
Alunno a = new Alunno();
System.out.println("***Inserimento nuovo alunno***");
System.out.format("Nome: ");
a.setNome(t.readLine());
System.out.format("Cognome: ");
a.setCognome(t.readLine());
System.out.format("Data di nascita: ");
a.setData_Nascita(t.readLine());
System.out.format("Indirizzo: ");
a.setIndirizzo(t.readLine());
System.out.format("Residenza: ");
a.setResidenza(t.readLine());
System.out.format("Telefono: ");
a.setTelefono(t.readLine());
return a;
}
public void sciviFile(Alunno a) {
try {
FileOutputStream f = new FileOutputStream("istituto.dat", true);
ObjectOutputStream fOUT = new ObjectOutputStream(f);
fOUT.writeObject(a);
fOUT.flush();
fOUT.close();
} catch (Exception e) {
System.out.println("Eccezione scrittura: " + e.getMessage());
}
}
public void leggiFile() {
Alunno a;
try {
FileInputStream f = new FileInputStream("istituto.dat");
ObjectInputStream fIN = new ObjectInputStream(f);
while (true) {
try {
a = (Alunno) fIN.readObject();
dim++;
System.out.println("Dimensione file: " + dim);
} catch (EOFException e) {
break;
}
}
f.close();
} catch (Exception e) {
System.out.println("Eccezione lettura: " + e.getMessage());
}
}
}
IstitutoScolastico.java:
import java.io.*;
public class IstitutoScolastico {
public static void main(String[] args) throws IOException {
File f = new File();
//f.sciviFile(f.nuovoAlunno());
f.leggiFile();
}
}
OUTPUT:
Dimensione file: 1
Eccezione lettura: invalid type code: AC
I do not read more than one object if I put in append mode, where did I go wrong?
Ah, anyway sorry for the grammatical errors, but I'm Italian and I helped with google translate!

The problem is that ObjectOutputStream writes a header to the file in it's constructor.
Since you call the constructor for each Alunno you append, you write a new header to the file too.
However ObjectInputStream expects only one header(at the start of the file).
If you don't want to change much in your code, you should create a new ObjectInputStream for each Alunno you read, change the code in your File class:
public void leggiFile() {
Alunno a;
try {
FileInputStream f = new FileInputStream("istituto.dat");
try {
while (true) {
// the header is read in the constructor
ObjectInputStream fIN = new ObjectInputStream(f);
a = (Alunno) fIN.readObject();
dim++;
System.out.println("Dimensione file: " + dim);
}
} catch (EOFException e) { }
f.close();
} catch (Exception e) {
System.out.println("Eccezione lettura: " + e.getMessage());
}
}
A alternative would be to skip 2(?) shorts (4(?) bytes) from the FileInputStream, but if the definition of the header should change (although this seems unlikely), you might have to change your code.
Another alternative would be to read all the Alunnos that are already in the file and then write all Alunnos (including the new one) to the File starting at the beginning of the file. But this may not be as fast as you wish.
For detailed information you can read http://docs.oracle.com/javase/7/docs/platform/serialization/spec/output.html and http://docs.oracle.com/javase/7/docs/platform/serialization/spec/input.html
One last tip: If you use Java SE 7 (or higher) consider using try-with-resources for your streams.

Creating a new MS Access file in Java using Jackcess

I have referred selected answer to this question: Java: Create MSAccess Database File (.mdb 0r .accdb) using Java.
I have MS Office 2010 in my machine. I am trying to create access database file (*.mdb / *.accdb). But, still the file is not getting created itself throwing following exception:
Exception in thread "main" java.io.FileNotFoundException: given file does not exist: C:\Users\473886\Desktop\employeedb1.mdb
at com.healthmarketscience.jackcess.impl.DatabaseImpl.open(DatabaseImpl.java:360)
at com.healthmarketscience.jackcess.DatabaseBuilder.open(DatabaseBuilder.java:170)
at mdb.MDBWriter.createDatabase(MDBWriter.java:93)
at mdb.MDBWriter.startDatabaseProcess(MDBWriter.java:107)
at mdb.MDBWriter.main(MDBWriter.java:120)
I have used the same code available in the answer with one modification that I have used file dialog that will ask me where I want to save the database file:
public class MDBWriter {
public static String saveFile(Frame f, String title, String defDir, String fileType) {
FileDialog fd = new FileDialog(f, title, FileDialog.SAVE);
fd.setFile(fileType);
fd.setDirectory(defDir);
fd.setLocation(50, 50);
fd.show();
return (fd.getDirectory() + "\\" + fd.getFile());
}
private static Database createDatabase(String databaseName) throws IOException {
// return Database.create(new File(databaseName));
File file = new File(databaseName);
return new DatabaseBuilder(file)
.setFileFormat(Database.FileFormat.V2010)
.open();
}
private static TableBuilder createTable(String tableName) {
return new TableBuilder(tableName);
}
public static void addColumn(Database database, TableBuilder tableName, String columnName, Types sqlType) throws SQLException, IOException {
tableName.addColumn(new ColumnBuilder(columnName).setSQLType(Types.INTEGER).toColumn()).toTable(database);
}
public static void startDatabaseProcess() throws IOException, SQLException {
String fileName = saveFile(new Frame(), "Save...", ".\\", "*.mdb");
String databaseName = "D:\\employeedb1.accdb"; // Creating an MS Access database
Database database = createDatabase(fileName);
String tableName = "Employee"; // Creating table
Table table = createTable(tableName)
.addColumn(new ColumnBuilder("Emp_Id").setSQLType(Types.INTEGER).toColumn())
.addColumn(new ColumnBuilder("Emp_Name").setSQLType(Types.VARCHAR).toColumn())
.addColumn(new ColumnBuilder("Emp_Employer").setSQLType(Types.VARCHAR).toColumn())
.toTable(database);
table.addRow(122875, "Sarath Kumar Sivan","Infosys Limited.");//Inserting values into the table
}
public static void main(String[] args) throws IOException, SQLException {
startDatabaseProcess();
}
}
Please suggest some solution.

If you want to create a new database, you need to call DatabaseBuilder.create(), not open() (which opens an existing database).

No way to create [an Access database] from [Java] code !
Nonsense. The following works on any platform with Java and Jackcess...
import com.healthmarketscience.jackcess.*;
import java.io.File;
public class bar {
public static void main(String[] args) {
try {
DatabaseBuilder.create(Database.FileFormat.V2010, new File("/home/gord/jTest.accdb"));
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("Done!");
}
}
..and the following code works in Java on Windows without Jackcess (but requires the Access Database Engine)...
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;
public class CreateAccdb {
public static void main(String[] args) {
String databaseName = "C:\\__tmp\\employeedb1.accdb";
String tempScriptName = System.getenv("TEMP") + "\\$$CreateAccdbScript.vbs";
try {
BufferedWriter out = new BufferedWriter(new FileWriter(tempScriptName));
out.write("Set cat = CreateObject(\"ADOX.Catalog\")");
out.newLine();
out.write("cat.Create \"Provider=Microsoft.ACE.OLEDB.12.0;Data Source=" + databaseName + ";\"");
out.close();
} catch (IOException e) {
e.printStackTrace();
}
String cmd = "cscript " + tempScriptName;
try {
Process p = Runtime.getRuntime().exec(cmd);
p.waitFor();
BufferedReader rdr =
new BufferedReader(new InputStreamReader(p.getErrorStream()));
int errorLines = 0;
String line = rdr.readLine();
while (line != null) {
errorLines++;
System.out.println(line); // display error line(s), if any
line = rdr.readLine();
}
if (errorLines == 0) {
System.out.println("The operation completed successfully.");
}
} catch(Exception e) {
e.printStackTrace();
}
try {
Files.deleteIfExists(Paths.get(tempScriptName));
} catch(Exception e) {
e.printStackTrace();
}
}
}

According to the answer available here. The only solution is to copy an existing empty mdb, connect to this and create tables etc. No way to create a mdb from code !

how to enhance this java class that reads xls file using POI and JXL?

I am currently using POI to read excel file and it is working great except it can't read xls files with older format (BIFF5/ office 95) to resolve this I am catching OldExcelFormatException and in this case call a function that will read the xls file using jxl. What I want to achieve is to write the same code but without catching the exception. Here is the current working code:
public void translate() throws IOException, CmpException
{
ArrayList<String> row = null;
try
{
// create a new org.apache.poi.poifs.filesystem.Filesystem
POIFSFileSystem poifs = new POIFSFileSystem(fin);
w = new HSSFWorkbook(poifs);
}
catch (OldExcelFormatException e) // OldExcelFormatException
{
w = null;
System.out.println("OldExcelFormatException");
translateBIFF5();
}
catch (Exception e) // Any Exception
{
w = null;
}
if (w != null)
{
// read the excel file using POI
}
}
private void translateBIFF5() throws IOException, CmpException
{
ArrayList<String> row = null;
try
{
jxl_w = Workbook.getWorkbook(excelFile);
}
catch (Exception e) // Any Exception
{
jxl_w = null;
}
if (jxl_w != null)
{
// read the excel file using jxl
}
}

Never mind guys. I found the solution by myself. The trick is to see the workbook name: For excel 95/97, the workbook name is 'Book' while for the new format the workbook name is 'WorkBook'. So here is the piece of coding I have been searching for:
POIFSFileSystem poifs = new POIFSFileSystem(fin);
DirectoryNode directory = poifs.getRoot();
Iterator<Entry> i = directory.getEntries();
while (i.hasNext())
{
Entry e = i.next();
String bookName = e.getName();
if (bookName.equals("Book"))
{
System.out.println("This is an old format");
}
else
{
System.out.println("This is a new format");
}
}

using dbpedia spotlight in java or scala

Does anyone know where to find a little how to on using dbpedia spotlight in java or scala? Or could anyone explain how it's done? I can't find any information on this...

The DBpedia Spotlight wiki pages would be a good place to start.
And I believe the installation page has listed the most popular ways (using a jar, or set up a web service) to use the application.
It includes instructions on using the Java/Scala API with your own installation, or calling the Web Service.
There are some additional data needed to be downloaded to run your own server for full service, good time to make a coffee for yourself.

you need download dbpedia spotlight (jar file) after that u can use next two classes ( author pablomendes ) i only make some change .
public class db extends AnnotationClient {
//private final static String API_URL = "http://jodaiber.dyndns.org:2222/";
private static String API_URL = "http://spotlight.dbpedia.org:80/";
private static double CONFIDENCE = 0.0;
private static int SUPPORT = 0;
private static String powered_by ="non";
private static String spotter ="CoOccurrenceBasedSelector";//"LingPipeSpotter"=Annotate all spots
//AtLeastOneNounSelector"=No verbs and adjs.
//"CoOccurrenceBasedSelector" =No 'common words'
//"NESpotter"=Only Per.,Org.,Loc.
private static String disambiguator ="Default";//Default ;Occurrences=Occurrence-centric;Document=Document-centric
private static String showScores ="yes";
#SuppressWarnings("static-access")
public void configiration(double CONFIDENCE,int SUPPORT,
String powered_by,String spotter,String disambiguator,String showScores){
this.CONFIDENCE=CONFIDENCE;
this.SUPPORT=SUPPORT;
this.powered_by=powered_by;
this.spotter=spotter;
this.disambiguator=disambiguator;
this.showScores=showScores;
}
public List<DBpediaResource> extract(Text text) throws AnnotationException {
LOG.info("Querying API.");
String spotlightResponse;
try {
String Query=API_URL + "rest/annotate/?" +
"confidence=" + CONFIDENCE
+ "&support=" + SUPPORT
+ "&spotter=" + spotter
+ "&disambiguator=" + disambiguator
+ "&showScores=" + showScores
+ "&powered_by=" + powered_by
+ "&text=" + URLEncoder.encode(text.text(), "utf-8");
LOG.info(Query);
GetMethod getMethod = new GetMethod(Query);
getMethod.addRequestHeader(new Header("Accept", "application/json"));
spotlightResponse = request(getMethod);
} catch (UnsupportedEncodingException e) {
throw new AnnotationException("Could not encode text.", e);
}
assert spotlightResponse != null;
JSONObject resultJSON = null;
JSONArray entities = null;
try {
resultJSON = new JSONObject(spotlightResponse);
entities = resultJSON.getJSONArray("Resources");
} catch (JSONException e) {
//throw new AnnotationException("Received invalid response from DBpedia Spotlight API.");
}
LinkedList<DBpediaResource> resources = new LinkedList<DBpediaResource>();
if(entities!=null)
for(int i = 0; i < entities.length(); i++) {
try {
JSONObject entity = entities.getJSONObject(i);
resources.add(
new DBpediaResource(entity.getString("#URI"),
Integer.parseInt(entity.getString("#support"))));
} catch (JSONException e) {
LOG.error("JSON exception "+e);
}
}
return resources;
}
}
second class
/**
* #author pablomendes
*/
public abstract class AnnotationClient {
public Logger LOG = Logger.getLogger(this.getClass());
private List<String> RES = new ArrayList<String>();
// Create an instance of HttpClient.
private static HttpClient client = new HttpClient();
public List<String> getResu(){
return RES;
}
public String request(HttpMethod method) throws AnnotationException {
String response = null;
// Provide custom retry handler is necessary
method.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
new DefaultHttpMethodRetryHandler(3, false));
try {
// Execute the method.
int statusCode = client.executeMethod(method);
if (statusCode != HttpStatus.SC_OK) {
LOG.error("Method failed: " + method.getStatusLine());
}
// Read the response body.
byte[] responseBody = method.getResponseBody(); //TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
// Deal with the response.
// Use caution: ensure correct character encoding and is not binary data
response = new String(responseBody);
} catch (HttpException e) {
LOG.error("Fatal protocol violation: " + e.getMessage());
throw new AnnotationException("Protocol error executing HTTP request.",e);
} catch (IOException e) {
LOG.error("Fatal transport error: " + e.getMessage());
LOG.error(method.getQueryString());
throw new AnnotationException("Transport error executing HTTP request.",e);
} finally {
// Release the connection.
method.releaseConnection();
}
return response;
}
protected static String readFileAsString(String filePath) throws java.io.IOException{
return readFileAsString(new File(filePath));
}
protected static String readFileAsString(File file) throws IOException {
byte[] buffer = new byte[(int) file.length()];
#SuppressWarnings("resource")
BufferedInputStream f = new BufferedInputStream(new FileInputStream(file));
f.read(buffer);
return new String(buffer);
}
static abstract class LineParser {
public abstract String parse(String s) throws ParseException;
static class ManualDatasetLineParser extends LineParser {
public String parse(String s) throws ParseException {
return s.trim();
}
}
static class OccTSVLineParser extends LineParser {
public String parse(String s) throws ParseException {
String result = s;
try {
result = s.trim().split("\t")[3];
} catch (ArrayIndexOutOfBoundsException e) {
throw new ParseException(e.getMessage(), 3);
}
return result;
}
}
}
public void saveExtractedEntitiesSet(String Question, LineParser parser, int restartFrom) throws Exception {
String text = Question;
int i=0;
//int correct =0 ; int error = 0;int sum = 0;
for (String snippet: text.split("\n")) {
String s = parser.parse(snippet);
if (s!= null && !s.equals("")) {
i++;
if (i<restartFrom) continue;
List<DBpediaResource> entities = new ArrayList<DBpediaResource>();
try {
entities = extract(new Text(snippet.replaceAll("\\s+"," ")));
System.out.println(entities.get(0).getFullUri());
} catch (AnnotationException e) {
// error++;
LOG.error(e);
e.printStackTrace();
}
for (DBpediaResource e: entities) {
RES.add(e.uri());
}
}
}
}
public abstract List<DBpediaResource> extract(Text text) throws AnnotationException;
public void evaluate(String Question) throws Exception {
evaluateManual(Question,0);
}
public void evaluateManual(String Question, int restartFrom) throws Exception {
saveExtractedEntitiesSet(Question,new LineParser.ManualDatasetLineParser(), restartFrom);
}
}
main()
public static void main(String[] args) throws Exception {
String Question ="Is the Amazon river longer than the Nile River?";
db c = new db ();
c.configiration(0.0, 0, "non", "CoOccurrenceBasedSelector", "Default", "yes");
System.out.println("resource : "+c.getResu());
}

I just add one little fix for your answer.
Your code is running, if you add the evaluate method call:
public static void main(String[] args) throws Exception {
String question = "Is the Amazon river longer than the Nile River?";
db c = new db ();
c.configiration(0.0, 0, "non", "CoOccurrenceBasedSelector", "Default", "yes");
c.evaluate(question);
System.out.println("resource : "+c.getResu());
}
Lamine

In the request method of the second class (AnnotationClient) in Adel's answer, the author Pablo Mendes hasn't finished
TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
which is an annoying warning that needs to be removed by replacing
byte[] responseBody = method.getResponseBody(); //TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
// Deal with the response.
// Use caution: ensure correct character encoding and is not binary data
response = new String(responseBody);
with
Reader in = new InputStreamReader(method.getResponseBodyAsStream(), "UTF-8");
StringWriter writer = new StringWriter();
org.apache.commons.io.IOUtils.copy(in, writer);
response = writer.toString();