org.tartarus.snowball
Class SnowballProgram

java.lang.Object
  org.tartarus.snowball.SnowballProgram

Direct Known Subclasses:

ArmenianStemmer, BasqueStemmer, CatalanStemmer, DanishStemmer, DutchStemmer, EnglishStemmer, FinnishStemmer, FrenchStemmer, German2Stemmer, GermanStemmer, HungarianStemmer, IrishStemmer, ItalianStemmer, KpStemmer, LovinsStemmer, NorwegianStemmer, PorterStemmer, PortugueseStemmer, RomanianStemmer, RussianStemmer, SpanishStemmer, SwedishStemmer, TurkishStemmer

public abstract class SnowballProgram
extends Object

This is the rev 502 of the Snowball SVN trunk, but modified: made abstract and introduced abstract method stem to avoid expensive reflection in filter class. refactored StringBuffers to StringBuilder uses char[] as buffer instead of StringBuffer/StringBuilder eq_s,eq_s_b,insert,replace_s take CharSequence like eq_v and eq_v_b reflection calls (Lovins, etc) use EMPTY_ARGS/EMPTY_PARAMS

Field Summary

protected int	bra
protected int	cursor
protected int	ket
protected int	limit
protected int	limit_backward

Constructor Summary

protected

SnowballProgram()

Method Summary

protected StringBuilder	assign_to(StringBuilder s)
protected void	copy_from(SnowballProgram other)
protected boolean	eq_s_b(int s_size, CharSequence s)
protected boolean	eq_s_b(int s_size, String s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected boolean	eq_s(int s_size, CharSequence s)
protected boolean	eq_s(int s_size, String s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected boolean	eq_v_b(CharSequence s)
protected boolean	eq_v_b(StringBuilder s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected boolean	eq_v(CharSequence s)
protected boolean	eq_v(StringBuilder s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected int	find_among_b(Among[] v, int v_size)
protected int	find_among(Among[] v, int v_size)
String	getCurrent() Get the current string.
char[]	getCurrentBuffer() Get the current buffer containing the stem.
int	getCurrentBufferLength() Get the valid length of the character array in getCurrentBuffer().
protected boolean	in_grouping_b(char[] s, int min, int max)
protected boolean	in_grouping(char[] s, int min, int max)
protected boolean	in_range_b(int min, int max)
protected boolean	in_range(int min, int max)
protected void	insert(int c_bra, int c_ket, CharSequence s)
protected void	insert(int c_bra, int c_ket, String s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected void	insert(int c_bra, int c_ket, StringBuilder s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected boolean	out_grouping_b(char[] s, int min, int max)
protected boolean	out_grouping(char[] s, int min, int max)
protected boolean	out_range_b(int min, int max)
protected boolean	out_range(int min, int max)
protected int	replace_s(int c_bra, int c_ket, CharSequence s)
protected int	replace_s(int c_bra, int c_ket, String s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
void	setCurrent(char[] text, int length) Set the current string.
void	setCurrent(String value) Set the current string.
protected void	slice_check()
protected void	slice_del()
protected void	slice_from(CharSequence s)
protected void	slice_from(String s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected void	slice_from(StringBuilder s) Deprecated. for binary back compat. Will be removed in Lucene 4.0
protected StringBuilder	slice_to(StringBuilder s)
abstract boolean	stem()

Methods inherited from class java.lang.Object

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

Field Detail

cursor

protected int cursor

limit

protected int limit

limit_backward

protected int limit_backward

bra

protected int bra

ket

protected int ket

Constructor Detail

SnowballProgram

protected SnowballProgram()

Method Detail

stem

public abstract boolean stem()

setCurrent

public void setCurrent(String value)

Set the current string.

getCurrent

public String getCurrent()

Get the current string.

setCurrent

public void setCurrent(char[] text,
                       int length)

Set the current string.

Parameters:

text - character array containing input

length - valid length of text.

getCurrentBuffer

public char[] getCurrentBuffer()

Get the current buffer containing the stem.

NOTE: this may be a reference to a different character array than the one originally provided with setCurrent, in the exceptional case that stemming produced a longer intermediate or result string.

It is necessary to use getCurrentBufferLength() to determine the valid length of the returned buffer. For example, many words are stemmed simply by subtracting from the length to remove suffixes.

See Also:

getCurrentBufferLength()

getCurrentBufferLength

public int getCurrentBufferLength()

Get the valid length of the character array in getCurrentBuffer().

Returns:

valid length of the array.

copy_from

protected void copy_from(SnowballProgram other)

in_grouping

protected boolean in_grouping(char[] s,
                              int min,
                              int max)

in_grouping_b

protected boolean in_grouping_b(char[] s,
                                int min,
                                int max)

out_grouping

protected boolean out_grouping(char[] s,
                               int min,
                               int max)

out_grouping_b

protected boolean out_grouping_b(char[] s,
                                 int min,
                                 int max)

in_range

protected boolean in_range(int min,
                           int max)

in_range_b

protected boolean in_range_b(int min,
                             int max)

out_range

protected boolean out_range(int min,
                            int max)

out_range_b

protected boolean out_range_b(int min,
                              int max)

eq_s

protected boolean eq_s(int s_size,
                       CharSequence s)

eq_s

@Deprecated
protected boolean eq_s(int s_size,
                                  String s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

eq_s_b

protected boolean eq_s_b(int s_size,
                         CharSequence s)

eq_s_b

@Deprecated
protected boolean eq_s_b(int s_size,
                                    String s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

eq_v

protected boolean eq_v(CharSequence s)

eq_v

@Deprecated
protected boolean eq_v(StringBuilder s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

eq_v_b

protected boolean eq_v_b(CharSequence s)

eq_v_b

@Deprecated
protected boolean eq_v_b(StringBuilder s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

find_among

protected int find_among(Among[] v,
                         int v_size)

find_among_b

protected int find_among_b(Among[] v,
                           int v_size)

replace_s

protected int replace_s(int c_bra,
                        int c_ket,
                        CharSequence s)

replace_s

@Deprecated
protected int replace_s(int c_bra,
                                   int c_ket,
                                   String s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

slice_check

protected void slice_check()

slice_from

protected void slice_from(CharSequence s)

slice_from

@Deprecated
protected void slice_from(String s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

slice_from

@Deprecated
protected void slice_from(StringBuilder s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

slice_del

protected void slice_del()

insert

protected void insert(int c_bra,
                      int c_ket,
                      CharSequence s)

insert

@Deprecated
protected void insert(int c_bra,
                                 int c_ket,
                                 String s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

insert

@Deprecated
protected void insert(int c_bra,
                                 int c_ket,
                                 StringBuilder s)

Deprecated. for binary back compat. Will be removed in Lucene 4.0

slice_to

protected StringBuilder slice_to(StringBuilder s)

assign_to

protected StringBuilder assign_to(StringBuilder s)