eu.fbk.dkm.pikes.resources.mpqa

Class CorpusPreprocessor

java.lang.Object

eu.fbk.dkm.pikes.resources.mpqa.CorpusPreprocessor

public class CorpusPreprocessor
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
static String	DEFAULT_ANNOTATION_HTML
static String	DEFAULT_ANNOTATION_TSV
static String	DEFAULT_NAMESPACE

Constructor Summary

Constructors

Constructor and Description
CorpusPreprocessor()

Method Summary

Modifier and Type	Method and Description
static boolean	isDelim(char c)
static boolean	isWord(char c)
static void	main(String[] args)
static void	preprocess(File inputPath, File outputPath, File fileList, String namespace, String checkOneDoc)

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_NAMESPACE

public static final String DEFAULT_NAMESPACE

See Also:

Constant Field Values

DEFAULT_ANNOTATION_TSV

public static final String DEFAULT_ANNOTATION_TSV

See Also:

Constant Field Values

DEFAULT_ANNOTATION_HTML

public static final String DEFAULT_ANNOTATION_HTML

See Also:

Constant Field Values

Constructor Detail

CorpusPreprocessor

public CorpusPreprocessor()

Method Detail

main

public static void main(String[] args)
                 throws IOException,
                        XMLStreamException

Throws:

IOException

XMLStreamException

preprocess

public static final void preprocess(@Nullable
                                    File inputPath,
                                    @Nullable
                                    File outputPath,
                                    File fileList,
                                    String namespace,
                                    @Nullable
                                    String checkOneDoc)
                             throws IOException

Throws:

IOException

isWord

public static boolean isWord(char c)

isDelim

public static boolean isDelim(char c)