org.dice_research.topicmodeling.io

Class CSVDocumentImporter

java.lang.Object

org.dice_research.topicmodeling.preprocessing.docsupplier.AbstractDocumentSupplier

org.dice_research.topicmodeling.io.CSVDocumentImporter

All Implemented Interfaces:

org.dice_research.topicmodeling.preprocessing.docsupplier.DocumentSupplier

public class CSVDocumentImporter
extends org.dice_research.topicmodeling.preprocessing.docsupplier.AbstractDocumentSupplier

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CSVDocumentImporter.CSVDocumentColumnBinding

Field Summary

Fields

Modifier and Type	Field and Description
protected HashMap<Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty>,Integer>	columnAssignment
private static org.slf4j.Logger	logger
protected int	maxColumnId
protected au.com.bytecode.opencsv.CSVReader	reader

Fields inherited from class org.dice_research.topicmodeling.preprocessing.docsupplier.AbstractDocumentSupplier

nextDocumentId

Constructor Summary

Constructors

Constructor and Description
CSVDocumentImporter()

Method Summary

Modifier and Type	Method and Description
void	addPropertyToRead(Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty> propertyClass, int columnId)
void	addPropertyToRead(CSVDocumentImporter.CSVDocumentColumnBinding binding)
void	closeCsvFile()
org.dice_research.topicmodeling.utils.doc.Document	getNextDocument()
void	openCsvFile(File csvFile)
void	openCsvFile(File csvFile, char separator)
void	openCsvFile(File csvFile, char separator, char quotechar)
void	openCsvFile(File csvFile, char separator, char quotechar, boolean strictQuotes)
void	openCsvFile(File csvFile, char separator, char quotechar, char escape)
void	openCsvFile(File csvFile, char separator, char quotechar, char escape, int line)
void	openCsvFile(File csvFile, char separator, char quotechar, char escape, int line, boolean strictQuotes)
void	openCsvFile(File csvFile, char separator, char quotechar, int line)

Methods inherited from class org.dice_research.topicmodeling.preprocessing.docsupplier.AbstractDocumentSupplier

getNextDocumentId, setDocumentStartId

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.dice_research.topicmodeling.preprocessing.docsupplier.DocumentSupplier

convertToStream

Field Detail

logger

private static final org.slf4j.Logger logger

reader

protected au.com.bytecode.opencsv.CSVReader reader

columnAssignment

protected HashMap<Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty>,Integer> columnAssignment

maxColumnId

protected int maxColumnId

Constructor Detail

CSVDocumentImporter

public CSVDocumentImporter()

Method Detail

openCsvFile

public void openCsvFile(File csvFile)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar,
                        boolean strictQuotes)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

strictQuotes - - sets if characters outside the quotes are ignored

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar,
                        char escape)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

escape - - the character to use for escaping a separator or quote

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar,
                        char escape,
                        int line)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

escape - - the character to use for escaping a separator or quote

line - - the line number to skip for start reading

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar,
                        int line)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

line - - the line number to skip for start reading

Throws:

FileNotFoundException

openCsvFile

public void openCsvFile(File csvFile,
                        char separator,
                        char quotechar,
                        char escape,
                        int line,
                        boolean strictQuotes)
                 throws FileNotFoundException

Parameters:

csvFile - - name and path of the CSV file

separator - - the delimiter to use for separating entries

quotechar - - the character to use for quoted elements

escape - - the character to use for escaping a separator or quote

line - - the line number to skip for start reading

strictQuotes - - sets if characters outside the quotes are ignored

Throws:

FileNotFoundException

getNextDocument

public org.dice_research.topicmodeling.utils.doc.Document getNextDocument()

addPropertyToRead

public void addPropertyToRead(Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty> propertyClass,
                              int columnId)

addPropertyToRead

public void addPropertyToRead(CSVDocumentImporter.CSVDocumentColumnBinding binding)

closeCsvFile

public void closeCsvFile()