As of 3.1, Snowball stemming is done with SnowballFilter,
* LowerCaseFilter is used prior to StopFilter, and ElisionFilter and
* Snowball stopwords are used by default.
@@ -177,7 +178,7 @@ public final class FrenchAnalyzer extends StopwordAnalyzerBase {
* {@link StandardFilter}, {@link ElisionFilter},
* {@link LowerCaseFilter}, {@link StopFilter},
* {@link KeywordMarkerFilter} if a stem exclusion set is
- * provided, and {@link SnowballFilter}
+ * provided, and {@link FrenchLightStemFilter}
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
@@ -190,7 +191,11 @@ public final class FrenchAnalyzer extends StopwordAnalyzerBase {
result = new StopFilter(matchVersion, result, stopwords);
if(!excltable.isEmpty())
result = new KeywordMarkerFilter(result, excltable);
- result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
+ if (matchVersion.onOrAfter(Version.LUCENE_36)) {
+ result = new FrenchLightStemFilter(result);
+ } else {
+ result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
+ }
return new TokenStreamComponents(source, result);
} else {
final Tokenizer source = new StandardTokenizer(matchVersion, reader);
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemFilter.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemFilter.java
new file mode 100644
index 00000000000..2d9b28fd2de
--- /dev/null
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemFilter.java
@@ -0,0 +1,58 @@
+package org.apache.lucene.analysis.gl;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
+
+/**
+ * A {@link TokenFilter} that applies {@link GalicianMinimalStemmer} to stem
+ * Galician words.
+ *
+ * To prevent terms from being stemmed use an instance of
+ * {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
+ * the {@link KeywordAttribute} before this {@link TokenStream}.
+ *
+ */
+public final class GalicianMinimalStemFilter extends TokenFilter {
+ private final GalicianMinimalStemmer stemmer = new GalicianMinimalStemmer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
+
+ public GalicianMinimalStemFilter(TokenStream input) {
+ super(input);
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (input.incrementToken()) {
+ if (!keywordAttr.isKeyword()) {
+ final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
+ termAtt.setLength(newlen);
+ }
+ return true;
+ } else {
+ return false;
+ }
+ }
+}
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemmer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemmer.java
new file mode 100644
index 00000000000..54964900602
--- /dev/null
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianMinimalStemmer.java
@@ -0,0 +1,38 @@
+package org.apache.lucene.analysis.gl;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.analysis.pt.RSLPStemmerBase;
+
+/**
+ * Minimal Stemmer for Galician
+ *
+ * This follows the "RSLP-S" algorithm, but modified for Galician.
+ * Hence this stemmer only applies the plural reduction step of:
+ * "Regras do lematizador para o galego"
+ * @see RSLPStemmerBase
+ */
+public class GalicianMinimalStemmer extends RSLPStemmerBase {
+
+ private static final Step pluralStep =
+ parse(GalicianMinimalStemmer.class, "galician.rslp").get("Plural");
+
+ public int stem(char s[], int len) {
+ return pluralStep.apply(s, len);
+ }
+}
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
index ba326623b84..0d3d72ee645 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
@@ -22,6 +22,7 @@ import java.io.Reader;
import java.util.Set;
import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.TokenStream;
@@ -34,6 +35,13 @@ import org.apache.lucene.util.Version;
/**
* Analyzer for Hindi.
+ *
+ *
+ *
You must specify the required {@link Version}
+ * compatibility when creating HindiAnalyzer:
+ *
+ * - As of 3.6, StandardTokenizer is used for tokenization
+ *
*/
public final class HindiAnalyzer extends StopwordAnalyzerBase {
private final Set stemExclusionSet;
@@ -110,7 +118,7 @@ public final class HindiAnalyzer extends StopwordAnalyzerBase {
* used to tokenize all the text in the provided {@link Reader}.
*
* @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
- * built from a {@link IndicTokenizer} filtered with
+ * built from a {@link StandardTokenizer} filtered with
* {@link LowerCaseFilter}, {@link IndicNormalizationFilter},
* {@link HindiNormalizationFilter}, {@link KeywordMarkerFilter}
* if a stem exclusion set is provided, {@link HindiStemFilter}, and
@@ -119,7 +127,12 @@ public final class HindiAnalyzer extends StopwordAnalyzerBase {
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
- final Tokenizer source = new IndicTokenizer(matchVersion, reader);
+ final Tokenizer source;
+ if (matchVersion.onOrAfter(Version.LUCENE_36)) {
+ source = new StandardTokenizer(matchVersion, reader);
+ } else {
+ source = new IndicTokenizer(matchVersion, reader);
+ }
TokenStream result = new LowerCaseFilter(matchVersion, source);
if (!stemExclusionSet.isEmpty())
result = new KeywordMarkerFilter(result, stemExclusionSet);
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java
index 2e4c6e43e3f..e6ae4e7c212 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java
@@ -20,12 +20,15 @@ package org.apache.lucene.analysis.in;
import java.io.Reader;
import org.apache.lucene.analysis.util.CharTokenizer;
+import org.apache.lucene.analysis.standard.StandardTokenizer; // javadocs
import org.apache.lucene.util.AttributeSource;
import org.apache.lucene.util.Version;
/**
* Simple Tokenizer for text in Indian Languages.
+ * @deprecated (3.6) Use {@link StandardTokenizer} instead.
*/
+@Deprecated
public final class IndicTokenizer extends CharTokenizer {
public IndicTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
index 4e9011624fc..5e94049f595 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
@@ -46,6 +46,7 @@ import org.tartarus.snowball.ext.ItalianStemmer;
* You must specify the required {@link Version}
* compatibility when creating ItalianAnalyzer:
*
+ * - As of 3.6, ItalianLightStemFilter is used for less aggressive stemming.
*
- As of 3.2, ElisionFilter with a set of Italian
* contractions is used by default.
*
@@ -132,7 +133,7 @@ public final class ItalianAnalyzer extends StopwordAnalyzerBase {
* built from an {@link StandardTokenizer} filtered with
* {@link StandardFilter}, {@link ElisionFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , {@link KeywordMarkerFilter} if a stem exclusion set is
- * provided and {@link SnowballFilter}.
+ * provided and {@link ItalianLightStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
@@ -146,7 +147,11 @@ public final class ItalianAnalyzer extends StopwordAnalyzerBase {
result = new StopFilter(matchVersion, result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new KeywordMarkerFilter(result, stemExclusionSet);
- result = new SnowballFilter(result, new ItalianStemmer());
+ if (matchVersion.onOrAfter(Version.LUCENE_36)) {
+ result = new ItalianLightStemFilter(result);
+ } else {
+ result = new SnowballFilter(result, new ItalianStemmer());
+ }
return new TokenStreamComponents(source, result);
}
}
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
index 853f423d795..fd20bf93647 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
@@ -39,6 +39,13 @@ import org.tartarus.snowball.ext.PortugueseStemmer;
/**
* {@link Analyzer} for Portuguese.
+ *
+ *
+ *
You must specify the required {@link Version}
+ * compatibility when creating PortugueseAnalyzer:
+ *
+ * - As of 3.6, PortugueseLightStemFilter is used for less aggressive stemming.
+ *
*/
public final class PortugueseAnalyzer extends StopwordAnalyzerBase {
private final Set stemExclusionSet;
@@ -115,7 +122,7 @@ public final class PortugueseAnalyzer extends StopwordAnalyzerBase {
* built from an {@link StandardTokenizer} filtered with
* {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , {@link KeywordMarkerFilter} if a stem exclusion set is
- * provided and {@link SnowballFilter}.
+ * provided and {@link PortugueseLightStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
@@ -126,7 +133,11 @@ public final class PortugueseAnalyzer extends StopwordAnalyzerBase {
result = new StopFilter(matchVersion, result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new KeywordMarkerFilter(result, stemExclusionSet);
- result = new SnowballFilter(result, new PortugueseStemmer());
+ if (matchVersion.onOrAfter(Version.LUCENE_36)) {
+ result = new PortugueseLightStemFilter(result);
+ } else {
+ result = new SnowballFilter(result, new PortugueseStemmer());
+ }
return new TokenStreamComponents(source, result);
}
}
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemmer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemmer.java
index 01342ce9a11..441d236aa7d 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemmer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemmer.java
@@ -24,7 +24,7 @@ package org.apache.lucene.analysis.pt;
* A study on the Use of Stemming for Monolingual Ad-Hoc Portuguese
* Information Retrieval (Orengo, et al)
* which is just the plural reduction step of the RSLP
- * algorithm from A Stemming Algorithmm for the Portuguese Language,
+ * algorithm from A Stemming Algorithm for the Portuguese Language,
* Orengo et al.
* @see RSLPStemmerBase
*/
diff --git a/modules/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java b/modules/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
index 979339ff9da..ca2e39d92eb 100644
--- a/modules/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
+++ b/modules/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
@@ -16,7 +16,9 @@ package org.apache.lucene.analysis.th;
* limitations under the License.
*/
+import java.io.IOException;
import java.io.Reader;
+import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
@@ -24,22 +26,75 @@ import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
-import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
/**
* {@link Analyzer} for Thai language. It uses {@link java.text.BreakIterator} to break words.
- *
- * NOTE: This class uses the same {@link Version}
- * dependent settings as {@link StandardAnalyzer}.
+ *
+ *
+ *
You must specify the required {@link Version}
+ * compatibility when creating ThaiAnalyzer:
+ *
+ * - As of 3.6, a set of Thai stopwords is used by default
+ *
*/
-public final class ThaiAnalyzer extends Analyzer {
- private final Version matchVersion;
+public final class ThaiAnalyzer extends StopwordAnalyzerBase {
+
+ /** File containing default Thai stopwords. */
+ public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
+ /**
+ * The comment character in the stopwords file.
+ * All lines prefixed with this will be ignored.
+ */
+ private static final String STOPWORDS_COMMENT = "#";
+
+ /**
+ * Returns an unmodifiable instance of the default stop words set.
+ * @return default stop words set.
+ */
+ public static Set getDefaultStopSet(){
+ return DefaultSetHolder.DEFAULT_STOP_SET;
+ }
+
+ /**
+ * Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class
+ * accesses the static final set the first time.;
+ */
+ private static class DefaultSetHolder {
+ static final Set DEFAULT_STOP_SET;
+ static {
+ try {
+ DEFAULT_STOP_SET = loadStopwordSet(false, ThaiAnalyzer.class,
+ DEFAULT_STOPWORD_FILE, STOPWORDS_COMMENT);
+ } catch (IOException ex) {
+ // default set should always be present as it is part of the
+ // distribution (JAR)
+ throw new RuntimeException("Unable to load default stopword set");
+ }
+ }
+ }
+
+ /**
+ * Builds an analyzer with the default stop words.
+ *
+ * @param matchVersion lucene compatibility version
+ */
public ThaiAnalyzer(Version matchVersion) {
- this.matchVersion = matchVersion;
+ this(matchVersion, matchVersion.onOrAfter(Version.LUCENE_36) ? DefaultSetHolder.DEFAULT_STOP_SET : StopAnalyzer.ENGLISH_STOP_WORDS_SET);
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ *
+ * @param matchVersion lucene compatibility version
+ * @param stopwords a stopword set
+ */
+ public ThaiAnalyzer(Version matchVersion, Set stopwords) {
+ super(matchVersion, stopwords);
}
/**
@@ -61,6 +116,6 @@ public final class ThaiAnalyzer extends Analyzer {
result = new LowerCaseFilter(matchVersion, result);
result = new ThaiWordFilter(matchVersion, result);
return new TokenStreamComponents(source, new StopFilter(matchVersion,
- result, StopAnalyzer.ENGLISH_STOP_WORDS_SET));
+ result, stopwords));
}
}
diff --git a/modules/analysis/common/src/resources/org/apache/lucene/analysis/th/stopwords.txt b/modules/analysis/common/src/resources/org/apache/lucene/analysis/th/stopwords.txt
new file mode 100644
index 00000000000..07f0fabe692
--- /dev/null
+++ b/modules/analysis/common/src/resources/org/apache/lucene/analysis/th/stopwords.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
index 307194b27d9..d2b26cf7c9c 100644
--- a/modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
@@ -41,6 +41,13 @@ public class TestCatalanAnalyzer extends BaseTokenStreamTestCase {
assertAnalyzesTo(a, "un", new String[] { });
}
+ /** test use of elisionfilter */
+ public void testContractions() throws IOException {
+ Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT);
+ assertAnalyzesTo(a, "Diccionari de l'Institut d'Estudis Catalans",
+ new String[] { "diccion", "inst", "estud", "catalan" });
+ }
+
/** test use of exclusion set */
public void testExclude() throws IOException {
Set exclusionSet = new HashSet();
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilter.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilter.java
new file mode 100644
index 00000000000..4bdeaacc890
--- /dev/null
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilter.java
@@ -0,0 +1,68 @@
+package org.apache.lucene.analysis.de;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+import java.io.Reader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+
+/**
+ * Tests {@link GermanNormalizationFilter}
+ */
+public class TestGermanNormalizationFilter extends BaseTokenStreamTestCase {
+ private Analyzer analyzer = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String field, Reader reader) {
+ final Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ final TokenStream stream = new GermanNormalizationFilter(tokenizer);
+ return new TokenStreamComponents(tokenizer, stream);
+ }
+ };
+
+ /**
+ * Tests that a/o/u + e is equivalent to the umlaut form
+ */
+ public void testBasicExamples() throws IOException {
+ checkOneTerm(analyzer, "Schaltflächen", "Schaltflachen");
+ checkOneTerm(analyzer, "Schaltflaechen", "Schaltflachen");
+ }
+
+ /**
+ * Tests the specific heuristic that ue is not folded after a vowel or q.
+ */
+ public void testUHeuristic() throws IOException {
+ checkOneTerm(analyzer, "dauer", "dauer");
+ }
+
+ /**
+ * Tests german specific folding of sharp-s
+ */
+ public void testSpecialFolding() throws IOException {
+ checkOneTerm(analyzer, "weißbier", "weissbier");
+ }
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+ }
+}
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java
index 07fc7ad47f9..c395246b685 100644
--- a/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java
@@ -56,7 +56,7 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
assertAnalyzesTo(
fa,
"mot \"entreguillemet\"",
- new String[] { "mot", "entreguillemet" });
+ new String[] { "mot", "entreguilemet" });
// let's do some french specific tests now
@@ -66,7 +66,7 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
assertAnalyzesTo(
fa,
"Jean-François",
- new String[] { "jean", "françois" });
+ new String[] { "jean", "francoi" });
// 2. stopwords
assertAnalyzesTo(
@@ -81,16 +81,16 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
new String[] {
"lanc",
"chism",
- "habit",
+ "habitabl",
"chist",
- "élément",
+ "element",
"captif" });
// some verbs
assertAnalyzesTo(
fa,
"finissions souffrirent rugissante",
- new String[] { "fin", "souffr", "rug" });
+ new String[] { "finision", "soufrirent", "rugisant" });
// some everything else
// aujourd'hui stays one term which is OK
@@ -101,16 +101,16 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
"c3po",
"aujourd'hui",
"oeuf",
- "ïâöûàä",
- "anticonstitutionnel",
- "jav" });
+ "ïaöuaä",
+ "anticonstitutionel",
+ "java" });
// some more everything else
// here 1940-1945 stays as one term, 1940:1945 not ?
assertAnalyzesTo(
fa,
"33Bis 1940-1945 1940:1945 (---i+++)*",
- new String[] { "33bis", "1940", "1945", "1940", "1945", "i" });
+ new String[] { "33bi", "1940", "1945", "1940", "1945", "i" });
}
@@ -217,9 +217,9 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
new String[] {
"lanc",
"chism",
- "habit",
+ "habitabl",
"chist",
- "élément",
+ "element",
"captif" });
}
@@ -238,7 +238,7 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
public void testElision() throws Exception {
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT);
- assertAnalyzesTo(fa, "voir l'embrouille", new String[] { "voir", "embrouill" });
+ assertAnalyzesTo(fa, "voir l'embrouille", new String[] { "voir", "embrouil" });
}
/**
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilter.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilter.java
new file mode 100644
index 00000000000..f8be16e4edb
--- /dev/null
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilter.java
@@ -0,0 +1,55 @@
+package org.apache.lucene.analysis.gl;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.Reader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.Tokenizer;
+
+/**
+ * Simple tests for {@link GalicianMinimalStemmer}
+ */
+public class TestGalicianMinimalStemFilter extends BaseTokenStreamTestCase {
+ Analyzer a = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer, new GalicianMinimalStemFilter(tokenizer));
+ }
+ };
+
+ public void testPlural() throws Exception {
+ checkOneTerm(a, "elefantes", "elefante");
+ checkOneTerm(a, "elefante", "elefante");
+ checkOneTerm(a, "kalóres", "kalór");
+ checkOneTerm(a, "kalór", "kalór");
+ }
+
+ public void testExceptions() throws Exception {
+ checkOneTerm(a, "mas", "mas");
+ checkOneTerm(a, "barcelonês", "barcelonês");
+ }
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+ }
+}
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java
index 83d7a863b35..56f64f19074 100644
--- a/modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java
@@ -36,8 +36,8 @@ public class TestItalianAnalyzer extends BaseTokenStreamTestCase {
public void testBasics() throws IOException {
Analyzer a = new ItalianAnalyzer(TEST_VERSION_CURRENT);
// stemming
- checkOneTermReuse(a, "abbandonata", "abbandon");
- checkOneTermReuse(a, "abbandonati", "abbandon");
+ checkOneTermReuse(a, "abbandonata", "abbandonat");
+ checkOneTermReuse(a, "abbandonati", "abbandonat");
// stopword
assertAnalyzesTo(a, "dallo", new String[] {});
}
@@ -49,7 +49,7 @@ public class TestItalianAnalyzer extends BaseTokenStreamTestCase {
Analyzer a = new ItalianAnalyzer(TEST_VERSION_CURRENT,
ItalianAnalyzer.getDefaultStopSet(), exclusionSet);
checkOneTermReuse(a, "abbandonata", "abbandonata");
- checkOneTermReuse(a, "abbandonati", "abbandon");
+ checkOneTermReuse(a, "abbandonati", "abbandonat");
}
/** blast some random strings through the analyzer */
@@ -61,7 +61,7 @@ public class TestItalianAnalyzer extends BaseTokenStreamTestCase {
public void testContractions() throws IOException {
Analyzer a = new ItalianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "dell'Italia", new String[] { "ital" });
- assertAnalyzesTo(a, "l'Italiano", new String[] { "ital" });
+ assertAnalyzesTo(a, "l'Italiano", new String[] { "italian" });
}
/** test that we don't enable this before 3.2*/
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java
index 9453cb21656..a0e263fd8f3 100644
--- a/modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java
@@ -35,8 +35,8 @@ public class TestPortugueseAnalyzer extends BaseTokenStreamTestCase {
public void testBasics() throws IOException {
Analyzer a = new PortugueseAnalyzer(TEST_VERSION_CURRENT);
// stemming
- checkOneTermReuse(a, "quilométricas", "quilométr");
- checkOneTermReuse(a, "quilométricos", "quilométr");
+ checkOneTermReuse(a, "quilométricas", "quilometric");
+ checkOneTermReuse(a, "quilométricos", "quilometric");
// stopword
assertAnalyzesTo(a, "não", new String[] {});
}
@@ -48,7 +48,7 @@ public class TestPortugueseAnalyzer extends BaseTokenStreamTestCase {
Analyzer a = new PortugueseAnalyzer(TEST_VERSION_CURRENT,
PortugueseAnalyzer.getDefaultStopSet(), exclusionSet);
checkOneTermReuse(a, "quilométricas", "quilométricas");
- checkOneTermReuse(a, "quilométricos", "quilométr");
+ checkOneTermReuse(a, "quilométricos", "quilometric");
}
/** blast some random strings through the analyzer */
diff --git a/modules/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java b/modules/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java
index 185749cc7fd..7ab69c13682 100644
--- a/modules/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java
+++ b/modules/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java
@@ -21,7 +21,9 @@ import java.io.StringReader;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.tokenattributes.FlagsAttribute;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
/**
@@ -40,14 +42,29 @@ public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
* testcase for offsets
*/
public void testOffsets() throws Exception {
- assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องแสดงว่างานดี",
+ assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET), "การที่ได้ต้องแสดงว่างานดี",
new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
new int[] { 0, 3, 6, 9, 13, 17, 20, 23 },
new int[] { 3, 6, 9, 13, 17, 20, 23, 25 });
}
+ public void testStopWords() throws Exception {
+ assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องแสดงว่างานดี",
+ new String[] { "แสดง", "งาน", "ดี" },
+ new int[] { 13, 20, 23 },
+ new int[] { 17, 23, 25 },
+ new int[] { 5, 2, 1 });
+ }
+
+ public void testBackwardsStopWords() throws Exception {
+ assertAnalyzesTo(new ThaiAnalyzer(Version.LUCENE_35), "การที่ได้ต้องแสดงว่างานดี",
+ new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
+ new int[] { 0, 3, 6, 9, 13, 17, 20, 23 },
+ new int[] { 3, 6, 9, 13, 17, 20, 23, 25 });
+ }
+
public void testTokenType() throws Exception {
- assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องแสดงว่างานดี ๑๒๓",
+ assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET), "การที่ได้ต้องแสดงว่างานดี ๑๒๓",
new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี", "๑๒๓" },
new String[] { "", "",
"", "",
@@ -96,8 +113,9 @@ public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
/*
* Test that position increments are adjusted correctly for stopwords.
*/
+ // note this test uses stopfilter's stopset
public void testPositionIncrements() throws Exception {
- final ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT);
+ final ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
assertAnalyzesTo(analyzer, "การที่ได้ต้อง the แสดงว่างานดี",
new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
new int[] { 0, 3, 6, 9, 18, 22, 25, 28 },
@@ -113,7 +131,7 @@ public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
}
public void testReusableTokenStream() throws Exception {
- ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT);
+ ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET);
assertAnalyzesToReuse(analyzer, "", new String[] {});
assertAnalyzesToReuse(
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 0baec610661..c648859e8c7 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -479,6 +479,9 @@ New Features
CommonGramsQueryFilterFactory can optionally read stopwords in Snowball
format (specify format="snowball"). (Robert Muir)
+* SOLR-3105: ElisionFilterFactory optionally allows the parameter
+ ignoreCase (default=false). (Robert Muir)
+
Optimizations
----------------------
* SOLR-1931: Speedup for LukeRequestHandler and admin/schema browser. New parameter
@@ -592,6 +595,9 @@ Other Changes
* SOLR-3059: Example XSL stylesheet for indexing query result XML (janhoy)
+* SOLR-3097, SOLR-3105: Add analysis configurations for different languages to
+ the example. (Christian Moen, Robert Muir)
+
Build
----------------------
* SOLR-2487: Add build target to package war without slf4j jars (janhoy)
diff --git a/solr/build.xml b/solr/build.xml
index bbcf4673329..f57db038d40 100644
--- a/solr/build.xml
+++ b/solr/build.xml
@@ -625,4 +625,98 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/solr/core/src/java/org/apache/solr/analysis/ElisionFilterFactory.java b/solr/core/src/java/org/apache/solr/analysis/ElisionFilterFactory.java
index e1a536cd616..953af62ba6b 100644
--- a/solr/core/src/java/org/apache/solr/analysis/ElisionFilterFactory.java
+++ b/solr/core/src/java/org/apache/solr/analysis/ElisionFilterFactory.java
@@ -34,7 +34,8 @@ import org.apache.lucene.analysis.TokenStream;
* <analyzer>
* <tokenizer class="solr.StandardTokenizerFactory"/>
* <filter class="solr.LowerCaseFilterFactory"/>
- * <filter class="solr.ElisionFilterFactory" articles="stopwordarticles.txt"/>
+ * <filter class="solr.ElisionFilterFactory"
+ * articles="stopwordarticles.txt" ignoreCase="true"/>
* </analyzer>
* </fieldType>
*
@@ -45,10 +46,11 @@ public class ElisionFilterFactory extends BaseTokenFilterFactory implements Reso
public void inform(ResourceLoader loader) {
String articlesFile = args.get("articles");
+ boolean ignoreCase = getBoolean("ignoreCase", false);
if (articlesFile != null) {
try {
- articles = getWordSet(loader, articlesFile, false);
+ articles = getWordSet(loader, articlesFile, ignoreCase);
} catch (IOException e) {
throw new RuntimeException(e);
}
diff --git a/solr/core/src/java/org/apache/solr/analysis/GalicianMinimalStemFilterFactory.java b/solr/core/src/java/org/apache/solr/analysis/GalicianMinimalStemFilterFactory.java
new file mode 100644
index 00000000000..ffe731ddccc
--- /dev/null
+++ b/solr/core/src/java/org/apache/solr/analysis/GalicianMinimalStemFilterFactory.java
@@ -0,0 +1,39 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.gl.GalicianMinimalStemFilter;
+
+/**
+ * Factory for {@link GalicianMinimalStemFilter}.
+ *
+ * <fieldType name="text_glplural" class="solr.TextField" positionIncrementGap="100">
+ * <analyzer>
+ * <tokenizer class="solr.StandardTokenizerFactory"/>
+ * <filter class="solr.LowerCaseFilterFactory"/>
+ * <filter class="solr.GalicianMinimalStemFilterFactory"/>
+ * </analyzer>
+ * </fieldType>
+ *
+ */
+public class GalicianMinimalStemFilterFactory extends BaseTokenFilterFactory {
+ public TokenStream create(TokenStream input) {
+ return new GalicianMinimalStemFilter(input);
+ }
+}
diff --git a/solr/core/src/java/org/apache/solr/analysis/GermanNormalizationFilterFactory.java b/solr/core/src/java/org/apache/solr/analysis/GermanNormalizationFilterFactory.java
new file mode 100644
index 00000000000..8c19498aace
--- /dev/null
+++ b/solr/core/src/java/org/apache/solr/analysis/GermanNormalizationFilterFactory.java
@@ -0,0 +1,39 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.de.GermanNormalizationFilter;
+
+/**
+ * Factory for {@link GermanNormalizationFilter}.
+ *
+ * <fieldType name="text_denorm" class="solr.TextField" positionIncrementGap="100">
+ * <analyzer>
+ * <tokenizer class="solr.StandardTokenizerFactory"/>
+ * <filter class="solr.LowerCaseFilterFactory"/>
+ * <filter class="solr.GermanNormalizationFilterFactory"/>
+ * </analyzer>
+ * </fieldType>
+ */
+public class GermanNormalizationFilterFactory extends BaseTokenFilterFactory {
+
+ public TokenStream create(TokenStream input) {
+ return new GermanNormalizationFilter(input);
+ }
+}
diff --git a/solr/core/src/test/org/apache/solr/analysis/TestElisionFilterFactory.java b/solr/core/src/test/org/apache/solr/analysis/TestElisionFilterFactory.java
index ebac6788300..150886de174 100644
--- a/solr/core/src/test/org/apache/solr/analysis/TestElisionFilterFactory.java
+++ b/solr/core/src/test/org/apache/solr/analysis/TestElisionFilterFactory.java
@@ -64,4 +64,22 @@ public class TestElisionFilterFactory extends BaseTokenTestCase {
assertTokenStreamContents(stream, new String[] { "avion" });
}
+ /**
+ * Test setting ignoreCase=true
+ */
+ public void testCaseInsensitive() throws Exception {
+ Reader reader = new StringReader("L'avion");
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ ElisionFilterFactory factory = new ElisionFilterFactory();
+ factory.init(DEFAULT_VERSION_PARAM);
+ ResourceLoader loader = new SolrResourceLoader(null, null);
+ Map args = new HashMap();
+ args.put("articles", "frenchArticles.txt");
+ args.put("ignoreCase", "true");
+ factory.init(args);
+ factory.inform(loader);
+ TokenStream stream = factory.create(tokenizer);
+ assertTokenStreamContents(stream, new String[] { "avion" });
+ }
+
}
diff --git a/solr/core/src/test/org/apache/solr/analysis/TestGalicianMinimalStemFilterFactory.java b/solr/core/src/test/org/apache/solr/analysis/TestGalicianMinimalStemFilterFactory.java
new file mode 100644
index 00000000000..ea3e32b7900
--- /dev/null
+++ b/solr/core/src/test/org/apache/solr/analysis/TestGalicianMinimalStemFilterFactory.java
@@ -0,0 +1,36 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.Reader;
+import java.io.StringReader;
+
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.TokenStream;
+
+/**
+ * Simple tests to ensure the Galician plural stem factory is working.
+ */
+public class TestGalicianMinimalStemFilterFactory extends BaseTokenTestCase {
+ public void testStemming() throws Exception {
+ Reader reader = new StringReader("elefantes");
+ GalicianMinimalStemFilterFactory factory = new GalicianMinimalStemFilterFactory();
+ TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ assertTokenStreamContents(stream, new String[] { "elefante" });
+ }
+}
diff --git a/solr/core/src/test/org/apache/solr/analysis/TestGermanNormalizationFilterFactory.java b/solr/core/src/test/org/apache/solr/analysis/TestGermanNormalizationFilterFactory.java
new file mode 100644
index 00000000000..8f4a3e6f45e
--- /dev/null
+++ b/solr/core/src/test/org/apache/solr/analysis/TestGermanNormalizationFilterFactory.java
@@ -0,0 +1,36 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.Reader;
+import java.io.StringReader;
+
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.TokenStream;
+
+/**
+ * Simple tests to ensure the German normalization factory is working.
+ */
+public class TestGermanNormalizationFilterFactory extends BaseTokenTestCase {
+ public void testStemming() throws Exception {
+ Reader reader = new StringReader("weißbier");
+ GermanNormalizationFilterFactory factory = new GermanNormalizationFilterFactory();
+ TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ assertTokenStreamContents(stream, new String[] { "weissbier" });
+ }
+}
diff --git a/solr/example/solr/conf/lang/contractions_ca.txt b/solr/example/solr/conf/lang/contractions_ca.txt
new file mode 100644
index 00000000000..307a85f913d
--- /dev/null
+++ b/solr/example/solr/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
diff --git a/solr/example/solr/conf/lang/contractions_fr.txt b/solr/example/solr/conf/lang/contractions_fr.txt
new file mode 100644
index 00000000000..722db588333
--- /dev/null
+++ b/solr/example/solr/conf/lang/contractions_fr.txt
@@ -0,0 +1,9 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
diff --git a/solr/example/solr/conf/lang/contractions_it.txt b/solr/example/solr/conf/lang/contractions_it.txt
new file mode 100644
index 00000000000..cac04095372
--- /dev/null
+++ b/solr/example/solr/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l
+all
+dall
+dell
+nell
+sull
+coll
+pell
+gl
+agl
+dagl
+degl
+negl
+sugl
+un
+m
+t
+s
+v
+d
diff --git a/solr/example/solr/conf/lang/stemdict_nl.txt b/solr/example/solr/conf/lang/stemdict_nl.txt
new file mode 100644
index 00000000000..441072971d3
--- /dev/null
+++ b/solr/example/solr/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets fiets
+bromfiets bromfiets
+ei eier
+kind kinder
diff --git a/solr/example/solr/conf/lang/stoptags_ja.txt b/solr/example/solr/conf/lang/stoptags_ja.txt
new file mode 100644
index 00000000000..6f5cb8c3cf1
--- /dev/null
+++ b/solr/example/solr/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for KuromojiPartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below. Note that comments are
+# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+# noun: unclassified nouns
+#名詞
+#
+# noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+# noun-proper: Proper nouns where the sub-classification is undefined
+#名詞-固有名詞
+#
+# noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+# noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+# noun-proper-person-misc: names that cannot be divided into surname and
+# given name; foreign names; names where the surname or given name is unknown.
+# e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+# noun-proper-person-surname: Mainly Japanese surnames.
+# e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+# noun-proper-person-given_name: Mainly Japanese given names.
+# e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+# noun-proper-organization: Names representing organizations.
+# e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+# noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+# noun-proper-place-misc: Place names excluding countries.
+# e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+# noun-proper-place-country: Country names.
+# e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+# noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+# noun-pronoun-misc: miscellaneous pronouns:
+# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+# noun-pronoun-contraction: Spoken language contraction made by combining a
+# pronoun and the particle 'wa'.
+# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
+#名詞-代名詞-縮約
+#
+# noun-adverbial: Temporal nouns such as names of days or months that behave
+# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+# e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+# noun-verbal: Nouns that take arguments with case and can appear followed by
+# 'suru' and related verbs (する, できる, なさる, くださる)
+# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+# e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+# e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+# noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
+# attach to the base form of inflectional words, words that cannot be classified
+# into any of the other categories below. This category includes indefinite nouns.
+# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
+# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
+# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+# わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+# noun-affix-adverbial: noun affixes that that can behave as adverbs.
+# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
+# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
+# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
+# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
+# 儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
+# with the stem よう(だ) ("you(da)").
+# e.g. よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#
+# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+# connection form な (aux "da").
+# e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+# noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
+# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
+# form of inflectional words.
+# e.g. そう
+#名詞-特殊-助動詞語幹
+#
+# noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
+# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+# any of the other categories below. In general, this category is more inclusive than
+# 接尾語 ("suffix") and is usually the last element in a compound noun.
+# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+# noun-suffix-person: Suffixes that form nouns and attach to person names more often
+# than other nouns.
+# e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+# noun-suffix-place: Suffixes that form nouns and attach to place names more often
+# than other nouns.
+# e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
+# can appear before スル ("suru").
+# e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
+# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
+# conjunctive form of inflectional words.
+# e.g. そう
+#名詞-接尾-助動詞語幹
+#
+# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
+# form of inflectional words and appear before the copula だ ("da").
+# e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
+# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
+# to numbers.
+# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+# e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
+# together.
+# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
+# semantically verb-like.
+# e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
+# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
+# is いわく ("iwaku").
+#名詞-引用文字列
+#
+# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+# behave like an adjective.
+# e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+# prefix: unclassified prefixes
+#接頭詞
+#
+# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
+# excluding numerical expressions.
+# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+# in conjunctive form followed by なる/なさる/くださる.
+# e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+# prefix-adjectival: Prefixes that attach to adjectives.
+# e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+# prefix-numerical: Prefixes that attach to numerical expressions.
+# e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+# verb: unclassified verbs
+#動詞
+#
+# verb-main:
+#動詞-自立
+#
+# verb-auxiliary:
+#動詞-非自立
+#
+# verb-suffix:
+#動詞-接尾
+#
+#####
+# adjective: unclassified adjectives
+#形容詞
+#
+# adjective-main:
+#形容詞-自立
+#
+# adjective-auxiliary:
+#形容詞-非自立
+#
+# adjective-suffix:
+#形容詞-接尾
+#
+#####
+# adverb: unclassified adverbs
+#副詞
+#
+# adverb-misc: Words that can be segmented into one unit and where adnominal
+# modification is not possible.
+# e.g. あいかわらず, 多分
+#副詞-一般
+#
+# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
+# な, する, だ, etc.
+# e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+# adnominal: Words that only have noun-modifying forms.
+# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
+# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
+# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+# conjunction: Conjunctions that can occur independently.
+# e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+# particle: unclassified particles.
+助詞
+#
+# particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+# particle-case-misc: Case particles.
+# e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+# particle-case-quote: the "to" that appears after nouns, a person’s speech,
+# quotation marks, expressions of decisions from a meeting, reasons, judgements,
+# conjectures, etc.
+# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+# particle-case-compound: Compounds of particles and verbs that mainly behave
+# like case particles.
+# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
+# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
+# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
+# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
+# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+# particle-conjunctive:
+# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
+# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
+# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+# particle-dependency:
+# e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+# particle-adverbial:
+# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
+# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
+# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+# particle-interjective: particles with interjective grammatical roles.
+# e.g. (松島) や
+助詞-間投助詞
+#
+# particle-coordinate:
+# e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+# particle-final:
+# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
+# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
+# adverbial, conjunctive, or sentence final. For example:
+# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+# 「(祈りが届いたせい) か (, 試験に合格した.)」
+# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+# e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+# particle-adnominalizer: The "no" that attaches to nouns and modifies
+# non-inflectional words.
+助詞-連体化
+#
+# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
+# that are giongo, giseigo, or gitaigo.
+# e.g. に, と
+助詞-副詞化
+#
+# particle-special: A particle that does not fit into one of the above classifications.
+# This includes particles that are used in Tanka, Haiku, and other poetry.
+# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+# auxiliary-verb:
+助動詞
+#
+#####
+# interjection: Greetings and other exclamations.
+# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
+# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+# symbol: unclassified Symbols.
+記号
+#
+# symbol-misc: A general symbol not in one of the categories below.
+# e.g. [○◎@$〒→+]
+記号-一般
+#
+# symbol-comma: Commas
+# e.g. [,、]
+記号-読点
+#
+# symbol-period: Periods and full stops.
+# e.g. [.．。]
+記号-句点
+#
+# symbol-space: Full-width whitespace.
+記号-空白
+#
+# symbol-open_bracket:
+# e.g. [({‘“『【]
+記号-括弧開
+#
+# symbol-close_bracket:
+# e.g. [)}’”』」】]
+記号-括弧閉
+#
+# symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+# other: unclassified other
+#その他
+#
+# other-interjection: Words that are hard to classify as noun-suffixes or
+# sentence-final particles.
+# e.g. (だ)ァ
+その他-間投
+#
+#####
+# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+# e.g. あの, うんと, えと
+フィラー
+#
+#####
+# non-verbal: non-verbal sound.
+非言語音
+#
+#####
+# fragment:
+#語断片
+#
+#####
+# unknown: unknown part of speech.
+#未知語
+#
+##### End of file
\ No newline at end of file
diff --git a/solr/example/solr/conf/lang/stopwords_ar.txt b/solr/example/solr/conf/lang/stopwords_ar.txt
new file mode 100644
index 00000000000..21897849280
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_ar.txt
@@ -0,0 +1,123 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
diff --git a/solr/example/solr/conf/lang/stopwords_bg.txt b/solr/example/solr/conf/lang/stopwords_bg.txt
new file mode 100644
index 00000000000..1ae4ba2ae38
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
diff --git a/solr/example/solr/conf/lang/stopwords_ca.txt b/solr/example/solr/conf/lang/stopwords_ca.txt
new file mode 100644
index 00000000000..3da65deafe1
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son
+són
+sons
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
diff --git a/solr/example/solr/conf/lang/stopwords_cz.txt b/solr/example/solr/conf/lang/stopwords_cz.txt
new file mode 100644
index 00000000000..53c6097dac7
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
diff --git a/solr/example/solr/conf/lang/stopwords_da.txt b/solr/example/solr/conf/lang/stopwords_da.txt
new file mode 100644
index 00000000000..a3ff5fe122c
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_da.txt
@@ -0,0 +1,108 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og | and
+i | in
+jeg | I
+det | that (dem. pronoun)/it (pers. pronoun)
+at | that (in front of a sentence)/to (with infinitive)
+en | a/an
+den | it (pers. pronoun)/that (dem. pronoun)
+til | to/at/for/until/against/by/of/into, more
+er | present tense of "to be"
+som | who, as
+på | on/upon/in/on/at/to/after/of/with/for, on
+de | they
+med | with/by/in, along
+han | he
+af | of/by/from/off/for/in/with/on, off
+for | at/for/to/from/by/of/ago, in front/before, because
+ikke | not
+der | who/which, there/those
+var | past tense of "to be"
+mig | me/myself
+sig | oneself/himself/herself/itself/themselves
+men | but
+et | a/an/one, one (number), someone/somebody/one
+har | present tense of "to have"
+om | round/about/for/in/a, about/around/down, if
+vi | we
+min | my
+havde | past tense of "to have"
+ham | him
+hun | she
+nu | now
+over | over/above/across/by/beyond/past/on/about, over/past
+da | then, when/as/since
+fra | from/off/since, off, since
+du | you
+ud | out
+sin | his/her/its/one's
+dem | them
+os | us/ourselves
+op | up
+man | you/one
+hans | his
+hvor | where
+eller | or
+hvad | what
+skal | must/shall etc.
+selv | myself/youself/herself/ourselves etc., even
+her | here
+alle | all/everyone/everybody etc.
+vil | will (verb)
+blev | past tense of "to stay/to remain/to get/to become"
+kunne | could
+ind | in
+når | when
+være | present tense of "to be"
+dog | however/yet/after all
+noget | something
+ville | would
+jo | you know/you see (adv), yes
+deres | their/theirs
+efter | after/behind/according to/for/by/from, later/afterwards
+ned | down
+skulle | should
+denne | this
+end | than
+dette | this
+mit | my/mine
+også | also
+under | under/beneath/below/during, below/underneath
+have | have
+dig | you
+anden | other
+hende | her
+mine | my
+alt | everything
+meget | much/very, plenty of
+sit | his, her, its, one's
+sine | his, her, its, one's
+vor | our
+mod | against
+disse | these
+hvis | if
+din | your/yours
+nogle | some
+hos | by/at
+blive | be/become
+mange | many
+ad | by/through
+bliver | present tense of "to be/to become"
+hendes | her/hers
+været | be
+thi | for (conj)
+jer | you
+sådan | such, like this/like that
diff --git a/solr/example/solr/conf/lang/stopwords_de.txt b/solr/example/solr/conf/lang/stopwords_de.txt
new file mode 100644
index 00000000000..f7703841887
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_de.txt
@@ -0,0 +1,292 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber | but
+
+alle | all
+allem
+allen
+aller
+alles
+
+als | than, as
+also | so
+am | an + dem
+an | at
+
+ander | other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch | also
+auf | on
+aus | out of
+bei | by
+bin | am
+bis | until
+bist | art
+da | there
+damit | with it
+dann | then
+
+der | the
+den
+des
+dem
+die
+das
+
+daß | that
+
+derselbe | the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu | to that
+
+dein | thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn | because
+
+derer | of those
+dessen | of him
+
+dich | thee
+dir | to thee
+du | thou
+
+dies | this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch | (several meanings)
+dort | (over) there
+
+
+durch | through
+
+ein | a
+eine
+einem
+einen
+einer
+eines
+
+einig | some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal | once
+
+er | he
+ihn | him
+ihm | to him
+
+es | it
+etwas | something
+
+euer | your
+eure
+eurem
+euren
+eurer
+eures
+
+für | for
+gegen | towards
+gewesen | p.p. of sein
+hab | have
+habe | have
+haben | have
+hat | has
+hatte | had
+hatten | had
+hier | here
+hin | there
+hinter | behind
+
+ich | I
+mich | me
+mir | to me
+
+
+ihr | you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch | to you
+
+im | in + dem
+in | in
+indem | while
+ins | in + das
+ist | is
+
+jede | each, every
+jedem
+jeden
+jeder
+jedes
+
+jene | that
+jenem
+jenen
+jener
+jenes
+
+jetzt | now
+kann | can
+
+kein | no
+keine
+keinem
+keinen
+keiner
+keines
+
+können | can
+könnte | could
+machen | do
+man | one
+
+manche | some, many a
+manchem
+manchen
+mancher
+manches
+
+mein | my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit | with
+muss | must
+musste | had to
+nach | to(wards)
+nicht | not
+nichts | nothing
+noch | still, yet
+nun | now
+nur | only
+ob | whether
+oder | or
+ohne | without
+sehr | very
+
+sein | his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst | self
+sich | herself
+
+sie | they, she
+ihnen | to them
+
+sind | are
+so | so
+
+solche | such
+solchem
+solchen
+solcher
+solches
+
+soll | shall
+sollte | should
+sondern | but
+sonst | else
+über | over
+um | about, around
+und | and
+
+uns | us
+unse
+unsem
+unsen
+unser
+unses
+
+unter | under
+viel | much
+vom | von + dem
+von | from
+vor | before
+während | while
+war | was
+waren | were
+warst | wast
+was | what
+weg | away, off
+weil | because
+weiter | further
+
+welche | which
+welchem
+welchen
+welcher
+welches
+
+wenn | when
+werde | will
+werden | will
+wie | how
+wieder | again
+will | want
+wir | we
+wird | will
+wirst | willst
+wo | where
+wollen | want
+wollte | wanted
+würde | would
+würden | would
+zu | to
+zum | zu + dem
+zur | zu + der
+zwar | indeed
+zwischen | between
+
diff --git a/solr/example/solr/conf/lang/stopwords_el.txt b/solr/example/solr/conf/lang/stopwords_el.txt
new file mode 100644
index 00000000000..1a08d318326
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_el.txt
@@ -0,0 +1,76 @@
+# Lucene Greek Stopwords list
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
diff --git a/solr/example/solr/conf/stopwords_en.txt b/solr/example/solr/conf/lang/stopwords_en.txt
similarity index 100%
rename from solr/example/solr/conf/stopwords_en.txt
rename to solr/example/solr/conf/lang/stopwords_en.txt
diff --git a/solr/example/solr/conf/lang/stopwords_es.txt b/solr/example/solr/conf/lang/stopwords_es.txt
new file mode 100644
index 00000000000..2db14760075
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_es.txt
@@ -0,0 +1,354 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | from, of
+la | the, her
+que | who, that
+el | the
+en | in
+y | and
+a | to
+los | the, them
+del | de + el
+se | himself, from him etc
+las | the, them
+por | for, by, etc
+un | a
+para | for
+con | with
+no | no
+una | a
+su | his, her
+al | a + el
+ | es from SER
+lo | him
+como | how
+más | more
+pero | pero
+sus | su plural
+le | to him, her
+ya | already
+o | or
+ | fue from SER
+este | this
+ | ha from HABER
+sí | himself etc
+porque | because
+esta | this
+ | son from SER
+entre | between
+ | está from ESTAR
+cuando | when
+muy | very
+sin | without
+sobre | on
+ | ser from SER
+ | tiene from TENER
+también | also
+me | me
+hasta | until
+hay | there is/are
+donde | where
+ | han from HABER
+quien | whom, that
+ | están from ESTAR
+ | estado from ESTAR
+desde | from
+todo | all
+nos | us
+durante | during
+ | estados from ESTAR
+todos | all
+uno | a
+les | to them
+ni | nor
+contra | against
+otros | other
+ | fueron from SER
+ese | that
+eso | that
+ | había from HABER
+ante | before
+ellos | they
+e | and (variant of y)
+esto | this
+mí | me
+antes | before
+algunos | some
+qué | what?
+unos | a
+yo | I
+otro | other
+otras | other
+otra | other
+él | he
+tanto | so much, many
+esa | that
+estos | these
+mucho | much, many
+quienes | who
+nada | nothing
+muchos | many
+cual | who
+ | sea from SER
+poco | few
+ella | she
+estar | to be
+ | haber from HABER
+estas | these
+ | estaba from ESTAR
+ | estamos from ESTAR
+algunas | some
+algo | something
+nosotros | we
+
+ | other forms
+
+mi | me
+mis | mi plural
+tú | thou
+te | thee
+ti | thee
+tu | thy
+tus | tu plural
+ellas | they
+nosotras | we
+vosotros | you
+vosotras | you
+os | you
+mío | mine
+mía |
+míos |
+mías |
+tuyo | thine
+tuya |
+tuyos |
+tuyas |
+suyo | his, hers, theirs
+suya |
+suyos |
+suyas |
+nuestro | ours
+nuestra |
+nuestros |
+nuestras |
+vuestro | yours
+vuestra |
+vuestros |
+vuestras |
+esos | those
+esas | those
+
+ | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+ | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+ | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+ | sed also means 'thirst'
+
+ | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
diff --git a/solr/example/solr/conf/lang/stopwords_eu.txt b/solr/example/solr/conf/lang/stopwords_eu.txt
new file mode 100644
index 00000000000..25f1db93460
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
diff --git a/solr/example/solr/conf/lang/stopwords_fa.txt b/solr/example/solr/conf/lang/stopwords_fa.txt
new file mode 100644
index 00000000000..36182817b40
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_fa.txt
@@ -0,0 +1,311 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
diff --git a/solr/example/solr/conf/lang/stopwords_fi.txt b/solr/example/solr/conf/lang/stopwords_fi.txt
new file mode 100644
index 00000000000..addad798c4b
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_fi.txt
@@ -0,0 +1,95 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
+minä minun minut minua minussa minusta minuun minulla minulta minulle | I
+sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
+hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
+me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
+te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
+he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
+
+tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
+tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
+se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
+nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
+nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
+ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
+
+kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
+mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
+mitkä | (pl)
+
+joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
+jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
+
+| conjunctions
+
+että | that
+ja | and
+jos | if
+koska | because
+kuin | than
+mutta | but
+niin | so
+sekä | and
+sillä | for
+tai | or
+vaan | but
+vai | or
+vaikka | although
+
+
+| prepositions
+
+kanssa | with
+mukaan | according to
+noin | about
+poikki | across
+yli | over, across
+
+| other
+
+kun | when
+niin | so
+nyt | now
+itse | self
+
diff --git a/solr/example/solr/conf/lang/stopwords_fr.txt b/solr/example/solr/conf/lang/stopwords_fr.txt
new file mode 100644
index 00000000000..c00837ea939
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_fr.txt
@@ -0,0 +1,183 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au | a + le
+aux | a + les
+avec | with
+ce | this
+ces | these
+dans | with
+de | of
+des | de + les
+du | de + le
+elle | she
+en | `of them' etc
+et | and
+eux | them
+il | he
+je | I
+la | the
+le | the
+leur | their
+lui | him
+ma | my (fem)
+mais | but
+me | me
+même | same; as in moi-même (myself) etc
+mes | me (pl)
+moi | me
+mon | my (masc)
+ne | not
+nos | our (pl)
+notre | our
+nous | we
+on | one
+ou | where
+par | by
+pas | not
+pour | for
+qu | que before vowel
+que | that
+qui | who
+sa | his, her (fem)
+se | oneself
+ses | his (pl)
+son | his, her (masc)
+sur | on
+ta | thy (fem)
+te | thee
+tes | thy (pl)
+toi | thee
+ton | thy (masc)
+tu | thou
+un | a
+une | a
+vos | your (pl)
+votre | your
+vous | you
+
+ | single letter forms
+
+c | c'
+d | d'
+j | j'
+l | l'
+à | to, at
+m | m'
+n | n'
+s | s'
+t | t'
+y | there
+
+ | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+ | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+ | Later additions (from Jean-Christophe Deschamps)
+ceci | this
+celà | that
+cet | this
+cette | this
+ici | here
+ils | they
+les | the (pl)
+leurs | their (pl)
+quel | which
+quels | which
+quelle | which
+quelles | which
+sans | without
+soi | oneself
+
diff --git a/solr/example/solr/conf/lang/stopwords_gl.txt b/solr/example/solr/conf/lang/stopwords_gl.txt
new file mode 100644
index 00000000000..d8760b12c14
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
diff --git a/solr/example/solr/conf/lang/stopwords_hi.txt b/solr/example/solr/conf/lang/stopwords_hi.txt
new file mode 100644
index 00000000000..53874db03d2
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_hi.txt
@@ -0,0 +1,231 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह
+वहाँ
+वहीं
+वाले
+वुह
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
diff --git a/solr/example/solr/conf/lang/stopwords_hu.txt b/solr/example/solr/conf/lang/stopwords_hu.txt
new file mode 100644
index 00000000000..1a96f1db6f2
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_hu.txt
@@ -0,0 +1,209 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
diff --git a/solr/example/solr/conf/lang/stopwords_hy.txt b/solr/example/solr/conf/lang/stopwords_hy.txt
new file mode 100644
index 00000000000..60c1c50fbc8
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
diff --git a/solr/example/solr/conf/lang/stopwords_id.txt b/solr/example/solr/conf/lang/stopwords_id.txt
new file mode 100644
index 00000000000..4617f83a5c5
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
diff --git a/solr/example/solr/conf/lang/stopwords_it.txt b/solr/example/solr/conf/lang/stopwords_it.txt
new file mode 100644
index 00000000000..4cb5b0891b1
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_it.txt
@@ -0,0 +1,301 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad | a (to) before vowel
+al | a + il
+allo | a + lo
+ai | a + i
+agli | a + gli
+all | a + l'
+agl | a + gl'
+alla | a + la
+alle | a + le
+con | with
+col | con + il
+coi | con + i (forms collo, cogli etc are now very rare)
+da | from
+dal | da + il
+dallo | da + lo
+dai | da + i
+dagli | da + gli
+dall | da + l'
+dagl | da + gll'
+dalla | da + la
+dalle | da + le
+di | of
+del | di + il
+dello | di + lo
+dei | di + i
+degli | di + gli
+dell | di + l'
+degl | di + gl'
+della | di + la
+delle | di + le
+in | in
+nel | in + el
+nello | in + lo
+nei | in + i
+negli | in + gli
+nell | in + l'
+negl | in + gl'
+nella | in + la
+nelle | in + le
+su | on
+sul | su + il
+sullo | su + lo
+sui | su + i
+sugli | su + gli
+sull | su + l'
+sugl | su + gl'
+sulla | su + la
+sulle | su + le
+per | through, by
+tra | among
+contro | against
+io | I
+tu | thou
+lui | he
+lei | she
+noi | we
+voi | you
+loro | they
+mio | my
+mia |
+miei |
+mie |
+tuo |
+tua |
+tuoi | thy
+tue |
+suo |
+sua |
+suoi | his, her
+sue |
+nostro | our
+nostra |
+nostri |
+nostre |
+vostro | your
+vostra |
+vostri |
+vostre |
+mi | me
+ti | thee
+ci | us, there
+vi | you, there
+lo | him, the
+la | her, the
+li | them
+le | them, the
+gli | to him, the
+ne | from there etc
+il | the
+un | a
+uno | a
+una | a
+ma | but
+ed | and
+se | if
+perché | why, because
+anche | also
+come | how
+dov | where (as dov')
+dove | where
+che | who, that
+chi | who
+cui | whom
+non | not
+più | more
+quale | who, that
+quanto | how much
+quanti |
+quanta |
+quante |
+quello | that
+quelli |
+quella |
+quelle |
+questo | this
+questi |
+questa |
+queste |
+si | yes
+tutto | all
+tutti | all
+
+ | single letter forms:
+
+a | at
+c | as c' for ce or ci
+e | and
+i | the
+l | as l'
+o | or
+
+ | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+ | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+ | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+ | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
diff --git a/solr/example/solr/conf/lang/stopwords_ja.txt b/solr/example/solr/conf/lang/stopwords_ja.txt
new file mode 100644
index 00000000000..db850d3915f
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_ja.txt
@@ -0,0 +1,122 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# The set is made up hand-picked frequent terms from taken from segmented Japanese
+# Wikipedia. Punctuation characters and frequent kanji have mostly been left out.
+#
+# There is an overlap between these stopwords and the terms removed when used in
+# combination with the KuromojiPartOfSpeechStopFilter. When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# See LUCENE-3745 for frequency lists, etc. that can be useful for making your own set.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
diff --git a/solr/example/solr/conf/lang/stopwords_lv.txt b/solr/example/solr/conf/lang/stopwords_lv.txt
new file mode 100644
index 00000000000..e21a23c06c3
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined:
+# pronouns, adverbs, interjections were removed
+#
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt
+biju
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat
+būšu
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
diff --git a/solr/example/solr/conf/lang/stopwords_nl.txt b/solr/example/solr/conf/lang/stopwords_nl.txt
new file mode 100644
index 00000000000..f4d61f5092c
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_nl.txt
@@ -0,0 +1,117 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de | the
+en | and
+van | of, from
+ik | I, the ego
+te | (1) chez, at etc, (2) to, (3) too
+dat | that, which
+die | that, those, who, which
+in | in, inside
+een | a, an, one
+hij | he
+het | the, it
+niet | not, nothing, naught
+zijn | (1) to be, being, (2) his, one's, its
+is | is
+was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op | on, upon, at, in, up, used up
+aan | on, upon, to (as dative)
+met | with, by
+als | like, such as, when
+voor | (1) before, in front of, (2) furrow
+had | had, past tense all persons sing. of 'hebben' (have)
+er | there
+maar | but, only
+om | round, about, for etc
+hem | him
+dan | then
+zou | should/would, past tense all persons sing. of 'zullen'
+of | or, whether, if
+wat | what, something, anything
+mijn | possessive and noun 'mine'
+men | people, 'one'
+dit | this
+zo | so, thus, in this way
+door | through by
+over | over, across
+ze | she, her, they, them
+zich | oneself
+bij | (1) a bee, (2) by, near, at
+ook | also, too
+tot | till, until
+je | you
+mij | me
+uit | out of, from
+der | Old Dutch form of 'van der' still found in surnames
+daar | (1) there, (2) because
+haar | (1) her, their, them, (2) hair
+naar | (1) unpleasant, unwell etc, (2) towards, (3) as
+heb | present first person sing. of 'to have'
+hoe | how, why
+heeft | present third person sing. of 'to have'
+hebben | 'to have' and various parts thereof
+deze | this
+u | you
+want | (1) for, (2) mitten, (3) rigging
+nog | yet, still
+zal | 'shall', first and third person sing. of verb 'zullen' (will)
+me | me
+zij | she, they
+nu | now
+ge | 'thou', still used in Belgium and south Netherlands
+geen | none
+omdat | because
+iets | something, somewhat
+worden | to become, grow, get
+toch | yet, still
+al | all, every, each
+waren | (1) 'were' (2) to wander, (3) wares, (3)
+veel | much, many
+meer | (1) more, (2) lake
+doen | to do, to make
+toen | then, when
+moet | noun 'spot/mote' and present form of 'to must'
+ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder | without
+kan | noun 'can' and present form of 'to be able'
+hun | their, them
+dus | so, consequently
+alles | all, everything, anything
+onder | under, beneath
+ja | yes, of course
+eens | once, one day
+hier | here
+wie | who
+werd | imperfect third person sing. of 'become'
+altijd | always
+doch | yet, but etc
+wordt | present third person sing. of 'become'
+wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen | to be able
+ons | us/our
+zelf | self
+tegen | against, towards, at
+na | after, near
+reeds | already
+wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon | could; past tense of 'to be able'
+niets | nothing
+uw | your
+iemand | somebody
+geweest | been; past participle of 'be'
+andere | other
diff --git a/solr/example/solr/conf/lang/stopwords_no.txt b/solr/example/solr/conf/lang/stopwords_no.txt
new file mode 100644
index 00000000000..e76f36e69ed
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_no.txt
@@ -0,0 +1,192 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard , Jan 2005
+
+og | and
+i | in
+jeg | I
+det | it/this/that
+at | to (w. inf.)
+en | a/an
+et | a/an
+den | it/this/that
+til | to
+er | is/am/are
+som | who/that
+på | on
+de | they / you(formal)
+med | with
+han | he
+av | of
+ikke | not
+ikkje | not *
+der | there
+så | so
+var | was/were
+meg | me
+seg | you
+men | but
+ett | one
+har | have
+om | about
+vi | we
+min | my
+mitt | my
+ha | have
+hadde | had
+hun | she
+nå | now
+over | over
+da | when/as
+ved | by/know
+fra | from
+du | you
+ut | out
+sin | your
+dem | them
+oss | us
+opp | up
+man | you/one
+kan | can
+hans | his
+hvor | where
+eller | or
+hva | what
+skal | shall/must
+selv | self (reflective)
+sjøl | self (reflective)
+her | here
+alle | all
+vil | will
+bli | become
+ble | became
+blei | became *
+blitt | have become
+kunne | could
+inn | in
+når | when
+være | be
+kom | come
+noen | some
+noe | some
+ville | would
+dere | you
+som | who/which/that
+deres | their/theirs
+kun | only/just
+ja | yes
+etter | after
+ned | down
+skulle | should
+denne | this
+for | for/because
+deg | you
+si | hers/his
+sine | hers/his
+sitt | hers/his
+mot | against
+å | to
+meget | much
+hvorfor | why
+dette | this
+disse | these/those
+uten | without
+hvordan | how
+ingen | none
+din | your
+ditt | your
+blir | become
+samme | same
+hvilken | which
+hvilke | which (plural)
+sånn | such a
+inni | inside/within
+mellom | between
+vår | our
+hver | each
+hvem | who
+vors | us/ours
+hvis | whose
+både | both
+bare | only/just
+enn | than
+fordi | as/because
+før | before
+mange | many
+også | also
+slik | just
+vært | been
+være | to be
+båe | both *
+begge | both
+siden | since
+dykk | your *
+dykkar | yours *
+dei | they *
+deira | them *
+deires | theirs *
+deim | them *
+di | your (fem.) *
+då | as/when *
+eg | I *
+ein | a/an *
+eit | a/an *
+eitt | a/an *
+elles | or *
+honom | he *
+hjå | at *
+ho | she *
+hoe | she *
+henne | her
+hennar | her/hers
+hennes | hers
+hoss | how *
+hossen | how *
+ikkje | not *
+ingi | noone *
+inkje | noone *
+korleis | how *
+korso | how *
+kva | what/which *
+kvar | where *
+kvarhelst | where *
+kven | who/whom *
+kvi | why *
+kvifor | why *
+me | we *
+medan | while *
+mi | my *
+mine | my *
+mykje | much *
+no | now *
+nokon | some (masc./neut.) *
+noka | some (fem.) *
+nokor | some *
+noko | some *
+nokre | some *
+si | his/hers *
+sia | since *
+sidan | since *
+so | so *
+somt | some *
+somme | some *
+um | about*
+upp | up *
+vere | be *
+vore | was *
+verte | become *
+vort | become *
+varte | became *
+vart | became *
+
diff --git a/solr/example/solr/conf/lang/stopwords_pt.txt b/solr/example/solr/conf/lang/stopwords_pt.txt
new file mode 100644
index 00000000000..276c1b446f2
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_pt.txt
@@ -0,0 +1,251 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | of, from
+a | the; to, at; her
+o | the; him
+que | who, that
+e | and
+do | de + o
+da | de + a
+em | in
+um | a
+para | for
+ | é from SER
+com | with
+não | not, no
+uma | a
+os | the; them
+no | em + o
+se | himself etc
+na | em + a
+por | for
+mais | more
+as | the; them
+dos | de + os
+como | as, like
+mas | but
+ | foi from SER
+ao | a + o
+ele | he
+das | de + as
+ | tem from TER
+à | a + a
+seu | his
+sua | her
+ou | or
+ | ser from SER
+quando | when
+muito | much
+ | há from HAV
+nos | em + os; us
+já | already, now
+ | está from EST
+eu | I
+também | also
+só | only, just
+pelo | per + o
+pela | per + a
+até | up to
+isso | that
+ela | he
+entre | between
+ | era from SER
+depois | after
+sem | without
+mesmo | same
+aos | a + os
+ | ter from TER
+seus | his
+quem | whom
+nas | em + as
+me | me
+esse | that
+eles | they
+ | estão from EST
+você | you
+ | tinha from TER
+ | foram from SER
+essa | that
+num | em + um
+nem | nor
+suas | her
+meu | my
+às | a + as
+minha | my
+ | têm from TER
+numa | em + uma
+pelos | per + os
+elas | they
+ | havia from HAV
+ | seja from SER
+qual | which
+ | será from SER
+nós | we
+ | tenho from TER
+lhe | to him, her
+deles | of them
+essas | those
+esses | those
+pelas | per + as
+este | this
+ | fosse from SER
+dele | of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu | thou
+te | thee
+vocês | you (plural)
+vos | you
+lhes | to them
+meus | my
+minhas
+teu | thy
+tua
+teus
+tuas
+nosso | our
+nossa
+nossos
+nossas
+
+dela | of her
+delas | of them
+
+esta | this
+estes | these
+estas | these
+aquele | that
+aquela | that
+aqueles | those
+aquelas | those
+isto | this
+aquilo | that
+
+ | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+ | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+ | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+ | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
diff --git a/solr/example/solr/conf/lang/stopwords_ro.txt b/solr/example/solr/conf/lang/stopwords_ro.txt
new file mode 100644
index 00000000000..4fdee90a5ba
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
diff --git a/solr/example/solr/conf/lang/stopwords_ru.txt b/solr/example/solr/conf/lang/stopwords_ru.txt
new file mode 100644
index 00000000000..64307693457
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_ru.txt
@@ -0,0 +1,241 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и | and
+в | in/into
+во | alternative form
+не | not
+что | what/that
+он | he
+на | on/onto
+я | i
+с | from
+со | alternative form
+как | how
+а | milder form of `no' (but)
+то | conjunction and form of `that'
+все | all
+она | she
+так | so, thus
+его | him
+но | but
+да | yes/and
+ты | thou
+к | towards, by
+у | around, chez
+же | intensifier particle
+вы | you
+за | beyond, behind
+бы | conditional/subj. particle
+по | up to, along
+только | only
+ее | her
+мне | to me
+было | it was
+вот | here is/are, particle
+от | away from
+меня | me
+еще | still, yet, more
+нет | no, there isnt/arent
+о | about
+из | out of
+ему | to him
+теперь | now
+когда | when
+даже | even
+ну | so, well
+вдруг | suddenly
+ли | interrogative particle
+если | if
+уже | already, but homonym of `narrower'
+или | or
+ни | neither
+быть | to be
+был | he was
+него | prepositional form of его
+до | up to
+вас | you accusative
+нибудь | indef. suffix preceded by hyphen
+опять | again
+уж | already, but homonym of `adder'
+вам | to you
+сказал | he said
+ведь | particle `after all'
+там | there
+потом | then
+себя | oneself
+ничего | nothing
+ей | to her
+может | usually with `быть' as `maybe'
+они | they
+тут | here
+где | where
+есть | there is/are
+надо | got to, must
+ней | prepositional form of ей
+для | for
+мы | we
+тебя | thee
+их | them, their
+чем | than
+была | she was
+сам | self
+чтоб | in order to
+без | without
+будто | as if
+человек | man, person, one
+чего | genitive form of `what'
+раз | once
+тоже | also
+себе | to oneself
+под | beneath
+жизнь | life
+будет | will be
+ж | short form of intensifer particle `же'
+тогда | then
+кто | who
+этот | this
+говорил | was saying
+того | genitive form of `that'
+потому | for that reason
+этого | genitive form of `this'
+какой | which
+совсем | altogether
+ним | prepositional form of `его', `они'
+здесь | here
+этом | prepositional form of `этот'
+один | one
+почти | almost
+мой | my
+тем | instrumental/dative plural of `тот', `то'
+чтобы | full form of `in order that'
+нее | her (acc.)
+кажется | it seems
+сейчас | now
+были | they were
+куда | where to
+зачем | why
+сказать | to say
+всех | all (acc., gen. preposn. plural)
+никогда | never
+сегодня | today
+можно | possible, one can
+при | by
+наконец | finally
+два | two
+об | alternative form of `о', about
+другой | another
+хоть | even
+после | after
+над | above
+больше | more
+тот | that one (masc.)
+через | across, in
+эти | these
+нас | us
+про | about
+всего | in all, only, of all
+них | prepositional form of `они' (they)
+какая | which, feminine
+много | lots
+разве | interrogative particle
+сказала | she said
+три | three
+эту | this, acc. fem. sing.
+моя | my, feminine
+впрочем | moreover, besides
+хорошо | good
+свою | ones own, acc. fem. sing.
+этой | oblique form of `эта', fem. `this'
+перед | in front of
+иногда | sometimes
+лучше | better
+чуть | a little
+том | preposn. form of `that one'
+нельзя | one must not
+такой | such a one
+им | to them
+более | more
+всегда | always
+конечно | of course
+всю | acc. fem. sing of `all'
+между | between
+
+
+ | b: some paradigms
+ |
+ | personal pronouns
+ |
+ | я меня мне мной [мною]
+ | ты тебя тебе тобой [тобою]
+ | он его ему им [него, нему, ним]
+ | она ее эи ею [нее, нэи, нею]
+ | оно его ему им [него, нему, ним]
+ |
+ | мы нас нам нами
+ | вы вас вам вами
+ | они их им ими [них, ним, ними]
+ |
+ | себя себе собой [собою]
+ |
+ | demonstrative pronouns: этот (this), тот (that)
+ |
+ | этот эта это эти
+ | этого эты это эти
+ | этого этой этого этих
+ | этому этой этому этим
+ | этим этой этим [этою] этими
+ | этом этой этом этих
+ |
+ | тот та то те
+ | того ту то те
+ | того той того тех
+ | тому той тому тем
+ | тем той тем [тою] теми
+ | том той том тех
+ |
+ | determinative pronouns
+ |
+ | (a) весь (all)
+ |
+ | весь вся все все
+ | всего всю все все
+ | всего всей всего всех
+ | всему всей всему всем
+ | всем всей всем [всею] всеми
+ | всем всей всем всех
+ |
+ | (b) сам (himself etc)
+ |
+ | сам сама само сами
+ | самого саму само самих
+ | самого самой самого самих
+ | самому самой самому самим
+ | самим самой самим [самою] самими
+ | самом самой самом самих
+ |
+ | stems of verbs `to be', `to have', `to do' and modal
+ |
+ | быть бы буд быв есть суть
+ | име
+ | дел
+ | мог мож мочь
+ | уме
+ | хоч хот
+ | долж
+ | можн
+ | нужн
+ | нельзя
+
diff --git a/solr/example/solr/conf/lang/stopwords_sv.txt b/solr/example/solr/conf/lang/stopwords_sv.txt
new file mode 100644
index 00000000000..22bddfd8cb3
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_sv.txt
@@ -0,0 +1,131 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ | så = so, but also seed. These are indicated clearly below.
+
+och | and
+det | it, this/that
+att | to (with infinitive)
+i | in, at
+en | a
+jag | I
+hon | she
+som | who, that
+han | he
+på | on
+den | it, this/that
+med | with
+var | where, each
+sig | him(self) etc
+för | for
+så | so (also: seed)
+till | to
+är | is
+men | but
+ett | a
+om | if; around, about
+hade | had
+de | they, these/those
+av | of
+icke | not, no
+mig | me
+du | you
+henne | her
+då | then, when
+sin | his
+nu | now
+har | have
+inte | inte någon = no one
+hans | his
+honom | him
+skulle | 'sake'
+hennes | her
+där | there
+min | my
+man | one (pronoun)
+ej | nor
+vid | at, by, on (also: vast)
+kunde | could
+något | some etc
+från | from, off
+ut | out
+när | when
+efter | after, behind
+upp | up
+vi | we
+dem | them
+vara | be
+vad | what
+över | over
+än | than
+dig | you
+kan | can
+sina | his
+här | here
+ha | have
+mot | towards
+alla | all
+under | under (also: wonder)
+någon | some etc
+eller | or (else)
+allt | all
+mycket | much
+sedan | since
+ju | why
+denna | this/that
+själv | myself, yourself etc
+detta | this/that
+åt | to
+utan | without
+varit | was
+hur | how
+ingen | no
+mitt | my
+ni | you
+bli | to be, become
+blev | from bli
+oss | us
+din | thy
+dessa | these/those
+några | some etc
+deras | their
+blir | from bli
+mina | my
+samma | (the) same
+vilken | who, that
+er | you, your
+sådan | such a
+vår | our
+blivit | from bli
+dess | its
+inom | within
+mellan | between
+sådant | such a
+varför | why
+varje | each
+vilka | who, that
+ditt | thy
+vem | who
+vilket | who, that
+sitta | his
+sådana | such a
+vart | each
+dina | thy
+vars | whose
+vårt | our
+våra | our
+ert | your
+era | your
+vilkas | whose
+
diff --git a/solr/example/solr/conf/lang/stopwords_th.txt b/solr/example/solr/conf/lang/stopwords_th.txt
new file mode 100644
index 00000000000..07f0fabe692
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
diff --git a/solr/example/solr/conf/lang/stopwords_tr.txt b/solr/example/solr/conf/lang/stopwords_tr.txt
new file mode 100644
index 00000000000..84d9408d4ea
--- /dev/null
+++ b/solr/example/solr/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
diff --git a/solr/example/solr/conf/schema.xml b/solr/example/solr/conf/schema.xml
index 5e140c0750c..0508bc89efb 100755
--- a/solr/example/solr/conf/schema.xml
+++ b/solr/example/solr/conf/schema.xml
@@ -219,7 +219,7 @@
@@ -234,7 +234,7 @@
-->
@@ -250,7 +250,7 @@
@@ -287,7 +287,7 @@
-->
@@ -300,7 +300,7 @@
@@ -316,7 +316,7 @@
-
+
@@ -454,6 +454,323 @@
-->
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+