ciranda.utils
Class CirandaUtils

java.lang.Object
  ciranda.utils.CirandaUtils

public class CirandaUtils

extends java.lang.Object

Author:

vitor Utilities for the ciranda package

Nested Class Summary

static class

CirandaUtils.unigramFE

Constructor Summary

CirandaUtils()

Method Summary

static Instance	addingInstances(Instance target, Instance source) Adds one instance to another.
static Instance	extract1g2g3g4g5g(java.lang.String str, boolean uni, boolean bi, boolean tri, boolean four, boolean five)
static MutableInstance	extractBigrams(java.lang.String str) Extracts all Bigrams from String TBD
static MutableInstance	extractFivegrams(java.lang.String str) Extracts all Fivegrams from String
static MutableInstance	extractFourgrams(java.lang.String str) Extracts all Fourgrams from String
static MutableInstance	extractTrigrams(java.lang.String str) Extracts all Trigrams from String TBD
static MutableInstance	extractUnigrams(java.lang.String str) Extracts all unigrams from String TBD
static java.lang.String	getBody(java.lang.String str) returns only lines of msgs between tags.
static boolean	hasBodyTag(java.lang.String str)
static void	main(java.lang.String[] args)
static java.lang.String	removeFWDparts(java.lang.String str)
static java.lang.String	removeQuotes(java.lang.String str) Removes quotes from an email message TBD: needs to use the trained classifiers TBD
static MutableInstance	renameFeatures(MutableInstance src, java.lang.String prefix)

Methods inherited from class java.lang.Object

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

Constructor Detail

CirandaUtils

public CirandaUtils()

Method Detail

addingInstances

public static Instance addingInstances(Instance target,
                                       Instance source)

Adds one instance to another. addingInstances(destination, source);

getBody

public static java.lang.String getBody(java.lang.String str)

returns only lines of msgs between tags. remove non-body parts.

hasBodyTag

public static boolean hasBodyTag(java.lang.String str)

removeQuotes

public static java.lang.String removeQuotes(java.lang.String str)

Removes quotes from an email message TBD: needs to use the trained classifiers TBD

extractUnigrams

public static MutableInstance extractUnigrams(java.lang.String str)

Extracts all unigrams from String TBD

extractBigrams

public static MutableInstance extractBigrams(java.lang.String str)

Extracts all Bigrams from String TBD

extractTrigrams

public static MutableInstance extractTrigrams(java.lang.String str)

Extracts all Trigrams from String TBD

extractFourgrams

public static MutableInstance extractFourgrams(java.lang.String str)

Extracts all Fourgrams from String

extractFivegrams

public static MutableInstance extractFivegrams(java.lang.String str)

Extracts all Fivegrams from String

renameFeatures

public static MutableInstance renameFeatures(MutableInstance src,
                                             java.lang.String prefix)

removeFWDparts

public static java.lang.String removeFWDparts(java.lang.String str)

extract1g2g3g4g5g

public static Instance extract1g2g3g4g5g(java.lang.String str,
                                         boolean uni,
                                         boolean bi,
                                         boolean tri,
                                         boolean four,
                                         boolean five)

main

public static void main(java.lang.String[] args)