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

LUCENE-8373: Removed StandardAnalyzer.ENGLISH_STOP_WORDS_SET

This commit is contained in:
Alan Woodward 2018-06-29 16:02:48 +01:00
parent 6566b59f36
commit ad727bac43
4 changed files with 9 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/CHANGES.txt
View File

@ -50,6 +50,9 @@ API Changes
* LUCENE-8356: StandardFilter and StandardFilterFactory have been removed * LUCENE-8356: StandardFilter and StandardFilterFactory have been removed
(Alan Woodward) (Alan Woodward)
* LUCENE-8373: StandardAnalyzer.ENGLISH_STOP_WORD_SET has been removed
(Alan Woodward)
Changes in Runtime Behavior Changes in Runtime Behavior
* LUCENE-8333: Switch MoreLikeThis.setMaxDocFreqPct to use maxDoc instead of * LUCENE-8333: Switch MoreLikeThis.setMaxDocFreqPct to use maxDoc instead of

5
lucene/MIGRATE.txt
View File

@ -57,3 +57,8 @@ ALWAYS_CACHE can be replaced by a UsageTrackingQueryCachingPolicy with an approp
To retain the old behaviour, pass StandardAnalyzer.ENGLISH_STOP_WORDS_SET as an argument To retain the old behaviour, pass StandardAnalyzer.ENGLISH_STOP_WORDS_SET as an argument
to the constructor to the constructor
## StandardAnalyzer.ENGLISH_STOP_WORD_SET has been moved ##
English stop words are now defined in EnglishAnalyzer#ENGLISH_STOP_WORD_SET in the
analysis-common module

15
lucene/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java
View File

@ -28,27 +28,12 @@ import org.apache.lucene.analysis.StopwordAnalyzerBase;
import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.WordlistLoader; import org.apache.lucene.analysis.WordlistLoader;
import org.apache.lucene.analysis.en.EnglishAnalyzer;
/** /**
* Filters {@link LetterTokenizer} with {@link LowerCaseFilter} and {@link StopFilter}. * Filters {@link LetterTokenizer} with {@link LowerCaseFilter} and {@link StopFilter}.
*/ */
public final class StopAnalyzer extends StopwordAnalyzerBase { public final class StopAnalyzer extends StopwordAnalyzerBase {
/** An unmodifiable set containing some common English words that are not usually useful
for searching.*/
@Deprecated
public static final CharArraySet ENGLISH_STOP_WORDS_SET = EnglishAnalyzer.ENGLISH_STOP_WORDS_SET;
/** Builds an analyzer which removes words in
* {@link #ENGLISH_STOP_WORDS_SET}.
* @deprecated Use a constructor with a specific stop word set
*/
@Deprecated
public StopAnalyzer() {
this(ENGLISH_STOP_WORDS_SET);
}
/** Builds an analyzer with the stop words from the given set. /** Builds an analyzer with the stop words from the given set.
* @param stopWords Set of stop words */ * @param stopWords Set of stop words */
public StopAnalyzer(CharArraySet stopWords) { public StopAnalyzer(CharArraySet stopWords) {

31
lucene/core/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java
View File

@ -19,8 +19,6 @@ package org.apache.lucene.analysis.standard;
import java.io.IOException; import java.io.IOException;
import java.io.Reader; import java.io.Reader;
import java.util.Arrays;
import java.util.List;
import org.apache.lucene.analysis.CharArraySet; import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter; import org.apache.lucene.analysis.LowerCaseFilter;
@ -35,40 +33,11 @@ import org.apache.lucene.analysis.WordlistLoader;
*/ */
public final class StandardAnalyzer extends StopwordAnalyzerBase { public final class StandardAnalyzer extends StopwordAnalyzerBase {
/**
* An unmodifiable set containing some common English words that are not
* usually useful for searching.
* @deprecated Use the stop words on EnglishAnalyzer in the analysis-common module
*/
@Deprecated
public static final CharArraySet ENGLISH_STOP_WORDS_SET;
static {
final List<String> stopWords = Arrays.asList(
"a", "an", "and", "are", "as", "at", "be", "but", "by",
"for", "if", "in", "into", "is", "it",
"no", "not", "of", "on", "or", "such",
"that", "the", "their", "then", "there", "these",
"they", "this", "to", "was", "will", "with"
);
final CharArraySet stopSet = new CharArraySet(stopWords, false);
ENGLISH_STOP_WORDS_SET = CharArraySet.unmodifiableSet(stopSet);
}
/** Default maximum allowed token length */ /** Default maximum allowed token length */
public static final int DEFAULT_MAX_TOKEN_LENGTH = 255; public static final int DEFAULT_MAX_TOKEN_LENGTH = 255;
private int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH; private int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;
/**
* An unmodifiable set containing some common English words that are usually not
* useful for searching.
* @deprecated Use the stop words on EnglishAnalyzer in the analysis-common module
*/
@Deprecated
public static final CharArraySet STOP_WORDS_SET = ENGLISH_STOP_WORDS_SET;
/** Builds an analyzer with the given stop words. /** Builds an analyzer with the given stop words.
* @param stopWords stop words */ * @param stopWords stop words */
public StandardAnalyzer(CharArraySet stopWords) { public StandardAnalyzer(CharArraySet stopWords) {