Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

improve doc for default constructor; make stop word list public but final 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@151013 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Daniel Naber 2004-10-17 11:41:41 +00:00
parent 8fd3b8498b
commit a8d98638a0
5 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
View File

@ -73,14 +73,14 @@ import java.util.Set;
* will not be indexed at all) and an external list of exclusions (word that will * will not be indexed at all) and an external list of exclusions (word that will
* not be stemmed, but indexed). * not be stemmed, but indexed).
* *
* @author João Kramer * @author Jo<EFBFBD>o Kramer
*/ */
public final class BrazilianAnalyzer extends Analyzer { public final class BrazilianAnalyzer extends Analyzer {
/** /**
* List of typical german stopwords. * List of typical german stopwords.
*/ */
private String[] BRAZILIAN_STOP_WORDS = { public final static String[] BRAZILIAN_STOP_WORDS = {
"a","ainda","alem","ambas","ambos","antes", "a","ainda","alem","ambas","ambos","antes",
"ao","aonde","aos","apos","aquele","aqueles", "ao","aonde","aos","apos","aquele","aqueles",
"as","assim","com","como","contra","contudo", "as","assim","com","como","contra","contudo",
@ -112,7 +112,7 @@ public final class BrazilianAnalyzer extends Analyzer {
private Set excltable = new HashSet(); private Set excltable = new HashSet();
/** /**
* Builds an analyzer. * Builds an analyzer with the default stop words ({@link #BRAZILIAN_STOP_WORDS}).
*/ */
public BrazilianAnalyzer() { public BrazilianAnalyzer() {
stoptable = StopFilter.makeStopSet( BRAZILIAN_STOP_WORDS ); stoptable = StopFilter.makeStopSet( BRAZILIAN_STOP_WORDS );

6
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java
View File

@ -76,7 +76,7 @@ public class CJKAnalyzer extends Analyzer {
* An array containing some common English words that are not usually * An array containing some common English words that are not usually
* useful for searching. and some double-byte interpunctions..... * useful for searching. and some double-byte interpunctions.....
*/ */
private static String[] stopWords = { public final static String[] STOP_WORDS = {
"a", "and", "are", "as", "at", "be", "a", "and", "are", "as", "at", "be",
"but", "by", "for", "if", "in", "but", "by", "for", "if", "in",
"into", "is", "it", "no", "not", "into", "is", "it", "no", "not",
@ -97,10 +97,10 @@ public class CJKAnalyzer extends Analyzer {
//~ Constructors ----------------------------------------------------------- //~ Constructors -----------------------------------------------------------
/** /**
* Builds an analyzer which removes words in STOP_WORDS. * Builds an analyzer which removes words in {@link #STOP_WORDS}.
*/ */
public CJKAnalyzer() { public CJKAnalyzer() {
stopTable = StopFilter.makeStopSet(stopWords); stopTable = StopFilter.makeStopSet(STOP_WORDS);
} }
/** /**

6
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
View File

@ -80,7 +80,7 @@ public final class CzechAnalyzer extends Analyzer {
/** /**
* List of typical stopwords. * List of typical stopwords.
*/ */
private static String[] STOP_WORDS = { public final static String[] CZECH_STOP_WORDS = {
"a","s","k","o","i","u","v","z","dnes","cz","t\u00edmto","bude\u0161","budem", "a","s","k","o","i","u","v","z","dnes","cz","t\u00edmto","bude\u0161","budem",
"byli","jse\u0161","m\u016fj","sv\u00fdm","ta","tomto","tohle","tuto","tyto", "byli","jse\u0161","m\u016fj","sv\u00fdm","ta","tomto","tohle","tuto","tyto",
"jej","zda","pro\u010d","m\u00e1te","tato","kam","tohoto","kdo","kte\u0159\u00ed", "jej","zda","pro\u010d","m\u00e1te","tato","kam","tohoto","kdo","kte\u0159\u00ed",
@ -107,10 +107,10 @@ public final class CzechAnalyzer extends Analyzer {
private Set stoptable; private Set stoptable;
/** /**
* Builds an analyzer. * Builds an analyzer with the default stop words ({@link #CZECH_STOP_WORDS}).
*/ */
public CzechAnalyzer() { public CzechAnalyzer() {
stoptable = StopFilter.makeStopSet( STOP_WORDS ); stoptable = StopFilter.makeStopSet( CZECH_STOP_WORDS );
} }
/** /**

4
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
View File

@ -84,7 +84,7 @@ public final class FrenchAnalyzer extends Analyzer {
/** /**
* Extended list of typical french stopwords. * Extended list of typical french stopwords.
*/ */
private String[] FRENCH_STOP_WORDS = { public final static String[] FRENCH_STOP_WORDS = {
"a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi", "a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi",
"autre", "autres", "aux", "auxquelles", "auxquels", "avait", "avant", "avec", "avoir", "autre", "autres", "aux", "auxquelles", "auxquels", "avait", "avant", "avec", "avoir",
"c", "car", "ce", "ceci", "cela", "celle", "celles", "celui", "cependant", "certain", "c", "car", "ce", "ceci", "cela", "celle", "celles", "celui", "cependant", "certain",
@ -119,7 +119,7 @@ public final class FrenchAnalyzer extends Analyzer {
private Set excltable = new HashSet(); private Set excltable = new HashSet();
/** /**
* Builds an analyzer. * Builds an analyzer with the default stop words ({@link #FRENCH_STOP_WORDS}).
*/ */
public FrenchAnalyzer() { public FrenchAnalyzer() {
stoptable = StopFilter.makeStopSet(FRENCH_STOP_WORDS); stoptable = StopFilter.makeStopSet(FRENCH_STOP_WORDS);

4
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java
View File

@ -45,7 +45,7 @@ public class DutchAnalyzer extends Analyzer {
/** /**
* List of typical Dutch stopwords. * List of typical Dutch stopwords.
*/ */
private String[] DUTCH_STOP_WORDS = public final static String[] DUTCH_STOP_WORDS =
{ {
"de", "en", "van", "ik", "te", "dat", "die", "in", "een", "de", "en", "van", "ik", "te", "dat", "die", "in", "een",
"hij", "het", "niet", "zijn", "is", "was", "op", "aan", "met", "als", "voor", "had", "hij", "het", "niet", "zijn", "is", "was", "op", "aan", "met", "als", "voor", "had",
@ -74,7 +74,7 @@ public class DutchAnalyzer extends Analyzer {
/** /**
* Builds an analyzer. * Builds an analyzer with the default stop words ({@link #DUTCH_STOP_WORDS}).
*/ */
public DutchAnalyzer() { public DutchAnalyzer() {
stoptable = StopFilter.makeStopSet(DUTCH_STOP_WORDS); stoptable = StopFilter.makeStopSet(DUTCH_STOP_WORDS);