LUCENE-2560: add basic stress tests for analyzers

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1096178 13f79535-47bb-0310-9956-ffa450edef68

lucene/src/test-framework/org/apache/lucene/analysis/BaseTokenStreamTestCase.java

@@ -19,11 +19,15 @@ package org.apache.lucene.analysis;
 
 import java.io.StringReader;
 import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Random;
  
 import org.apache.lucene.analysis.tokenattributes.*;
 import org.apache.lucene.util.Attribute;
 import org.apache.lucene.util.AttributeImpl;
 import org.apache.lucene.util.LuceneTestCase;
+import org.apache.lucene.util._TestUtil;
 
 /** 
  * Base class for all Lucene unit tests that use TokenStreams.  
@@ -229,4 +233,39 @@ public abstract class BaseTokenStreamTestCase extends LuceneTestCase {
     assertAnalyzesToReuse(a, input, new String[]{expected});
   }
   
+  // simple utility method for blasting tokenstreams with data to make sure they don't do anything crazy
+
+  public static void checkRandomData(Random random, Analyzer a, int iterations) throws IOException {
+    checkRandomData(random, a, iterations, 20);
+  }
+
+  public static void checkRandomData(Random random, Analyzer a, int iterations, int maxWordLength) throws IOException {
+    for (int i = 0; i < iterations; i++) {
+      String text;
+      switch(_TestUtil.nextInt(random, 0, 3)) {
+        case 0: 
+          text = _TestUtil.randomSimpleString(random);
+          break;
+        case 1:
+          text = _TestUtil.randomRealisticUnicodeString(random, maxWordLength);
+          break;
+        default:
+          text = _TestUtil.randomUnicodeString(random, maxWordLength);
+      }
+      
+      TokenStream ts = a.reusableTokenStream("dummy", new StringReader(text));
+      assertTrue("has no CharTermAttribute", ts.hasAttribute(CharTermAttribute.class));
+      CharTermAttribute termAtt = ts.getAttribute(CharTermAttribute.class);
+      List<String> tokens = new ArrayList<String>();
+      ts.reset();
+      while (ts.incrementToken()) {
+        tokens.add(termAtt.toString());
+        // TODO: we could collect offsets etc here for better checking that reset() really works.
+      }
+      ts.close();
+      // verify reusing is "reproducable" and also get the normal tokenstream sanity checks
+      if (!tokens.isEmpty())
+        assertAnalyzesToReuse(a, text, tokens.toArray(new String[tokens.size()]));
+    }
+  }
 }

lucene/src/test/org/apache/lucene/analysis/TestMockAnalyzer.java

@@ -111,4 +111,8 @@ public class TestMockAnalyzer extends BaseTokenStreamTestCase {
     assertAnalyzesToReuse(analyzer, testString, new String[] { "t" });
   }
 
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new MockAnalyzer(random), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java

@@ -98,4 +98,9 @@ public class TestArabicAnalyzer extends BaseTokenStreamTestCase {
     assertAnalyzesTo(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهد" });
     assertAnalyzesToReuse(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهد" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new ArabicAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java

@@ -75,4 +75,9 @@ public class TestBulgarianAnalyzer extends BaseTokenStreamTestCase {
     Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
     assertAnalyzesTo(a, "строевете строеве", new String[] { "строй", "строеве" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new BulgarianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java

@@ -157,4 +157,8 @@ public class TestBrazilianStemmer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, input, expected);
   }
 
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new BrazilianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java

@@ -50,4 +50,9 @@ public class TestCatalanAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "llengües", "llengües");
     checkOneTermReuse(a, "llengua", "llengu");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new CatalanAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKTokenizer.java

@@ -270,4 +270,9 @@ public class TestCJKTokenizer extends BaseTokenStreamTestCase {
         newToken("test", 0, 4, CJKTokenizer.SINGLE_TOKEN_TYPE),
         newToken("あい", 4, 6, CJKTokenizer.DOUBLE_TOKEN_TYPE) });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new CJKAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java

@@ -210,6 +210,13 @@ public class TestAnalyzers extends BaseTokenStreamTestCase {
     assertTokenStreamContents(tokenizer, new String[] { "Tokenizer",
         "\ud801\udc1ctest" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new WhitespaceAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+    checkRandomData(random, new SimpleAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+    checkRandomData(random, new StopAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }
 
 final class PayloadSetter extends TokenFilter {

modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java

@@ -309,4 +309,9 @@ public class TestClassicAnalyzer extends BaseTokenStreamTestCase {
 
     dir.close();
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new ClassicAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java

@@ -102,4 +102,9 @@ public class TestKeywordAnalyzer extends BaseTokenStreamTestCase {
     assertEquals(0, offsetAtt.startOffset());
     assertEquals(4, offsetAtt.endOffset());
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new KeywordAnalyzer(), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java

@@ -3,6 +3,7 @@ package org.apache.lucene.analysis.core;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.analysis.standard.StandardTokenizer;
 import org.apache.lucene.analysis.util.ReusableAnalyzerBase;
 
@@ -219,4 +220,9 @@ public class TestStandardAnalyzer extends BaseTokenStreamTestCase {
         new String[] { "仮", "名", "遣", "い", "カタカナ" },
         new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<HIRAGANA>", "<KATAKANA>" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new StandardAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestUAX29URLEmailTokenizer.java

@@ -418,4 +418,9 @@ public class TestUAX29URLEmailTokenizer extends BaseTokenStreamTestCase {
         new String[] { "仮", "名", "遣", "い", "カタカナ" },
         new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<HIRAGANA>", "<KATAKANA>" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechAnalyzer.java

@@ -67,4 +67,9 @@ public class TestCzechAnalyzer extends BaseTokenStreamTestCase {
     CzechAnalyzer cz = new CzechAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
     assertAnalyzesTo(cz, "hole desek", new String[] {"hole", "desk"});
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new CzechAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/da/TestDanishAnalyzer.java

@@ -50,4 +50,9 @@ public class TestDanishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "undersøgelse", "undersøgelse");
     checkOneTermReuse(a, "undersøg", "undersøg");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new DanishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanAnalyzer.java

@@ -63,4 +63,9 @@ public class TestGermanAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "Schaltflächen", "schaltflach");
     checkOneTermReuse(a, "Schaltflaechen", "schaltflaech");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new GermanAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilter.java

@@ -24,6 +24,7 @@ import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.core.WhitespaceTokenizer;
+import org.apache.lucene.analysis.hu.HungarianAnalyzer;
 import org.apache.lucene.analysis.util.ReusableAnalyzerBase;
 
 import static org.apache.lucene.analysis.util.VocabularyAssert.*;
@@ -45,4 +46,9 @@ public class TestGermanLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("delighttestdata.zip"), "delight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilter.java

@@ -57,4 +57,9 @@ public class TestGermanMinimalStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("deminimaltestdata.zip"), "deminimal.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilter.java

@@ -26,6 +26,7 @@ import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.core.KeywordTokenizer;
 import org.apache.lucene.analysis.core.LowerCaseFilter;
 import org.apache.lucene.analysis.util.ReusableAnalyzerBase;
+import org.junit.Ignore;
 
 import static org.apache.lucene.analysis.util.VocabularyAssert.*;
 
@@ -36,8 +37,6 @@ import static org.apache.lucene.analysis.util.VocabularyAssert.*;
  *
  */
 public class TestGermanStemFilter extends BaseTokenStreamTestCase {
-
-  public void testStemming() throws Exception {
   Analyzer analyzer = new ReusableAnalyzerBase() {
     @Override
     protected TokenStreamComponents createComponents(String fieldName,
@@ -48,8 +47,15 @@ public class TestGermanStemFilter extends BaseTokenStreamTestCase {
     }
   };
 
+  public void testStemming() throws Exception {  
     InputStream vocOut = getClass().getResourceAsStream("data.txt");
     assertVocabulary(analyzer, vocOut);
     vocOut.close();
   }
+  
+  /** blast some random strings through the analyzer */
+  @Ignore("bugs!")
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/el/GreekAnalyzerTest.java

@@ -87,4 +87,9 @@ public class GreekAnalyzerTest extends BaseTokenStreamTestCase {
     assertAnalyzesToReuse(a, "ΠΡΟΫΠΟΘΕΣΕΙΣ  Άψογος, ο μεστός και οι άλλοι",
         new String[] { "προυποθεσ", "αψογ", "μεστ", "αλλ" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new GreekAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishAnalyzer.java

@@ -52,4 +52,9 @@ public class TestEnglishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "books", "books");
     checkOneTermReuse(a, "book", "book");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new EnglishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilter.java

@@ -51,4 +51,9 @@ public class TestEnglishMinimalStemFilter extends BaseTokenStreamTestCase {
     checkOneTerm(analyzer, "congress", "congress");
     checkOneTerm(analyzer, "serious", "serious");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilter.java

@@ -37,11 +37,6 @@ import static org.apache.lucene.analysis.util.VocabularyAssert.*;
  * Test the PorterStemFilter with Martin Porter's test data.
  */
 public class TestPorterStemFilter extends BaseTokenStreamTestCase {
-  /**
-   * Run the stemmer against all strings in voc.txt
-   * The output should be the same as the string in output.txt
-   */
-  public void testPorterStemFilter() throws Exception {
   Analyzer a = new ReusableAnalyzerBase() {
     @Override
     protected TokenStreamComponents createComponents(String fieldName,
@@ -51,6 +46,11 @@ public class TestPorterStemFilter extends BaseTokenStreamTestCase {
     }
   };
   
+  /**
+   * Run the stemmer against all strings in voc.txt
+   * The output should be the same as the string in output.txt
+   */
+  public void testPorterStemFilter() throws Exception {
     assertVocabulary(a, getDataFile("porterTestData.zip"), "voc.txt", "output.txt");
   }
   
@@ -61,4 +61,9 @@ public class TestPorterStemFilter extends BaseTokenStreamTestCase {
     TokenStream filter = new PorterStemFilter(new KeywordMarkerFilter(tokenizer, set));   
     assertTokenStreamContents(filter, new String[] {"yourselves", "your"});
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishAnalyzer.java

@@ -50,4 +50,9 @@ public class TestSpanishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "chicana", "chican");
     checkOneTermReuse(a, "chicano", "chicano");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new SpanishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishLightStemFilter.java

@@ -45,4 +45,9 @@ public class TestSpanishLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("eslighttestdata.zip"), "eslight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/eu/TestBasqueAnalyzer.java

@@ -50,4 +50,9 @@ public class TestBasqueAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "zaldiak", "zaldiak");
     checkOneTermReuse(a, "mendiari", "mendi");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new BasqueAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianAnalyzer.java

@@ -219,4 +219,9 @@ public class TestPersianAnalyzer extends BaseTokenStreamTestCase {
     assertAnalyzesTo(a, "The quick brown fox.", new String[] { "quick",
         "brown", "fox" });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new PersianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java

@@ -50,4 +50,9 @@ public class TestFinnishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "edeltäjiinsä", "edeltäj");
     checkOneTermReuse(a, "edeltäjistään", "edeltäjistään");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new FinnishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilter.java

@@ -45,4 +45,9 @@ public class TestFinnishLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("filighttestdata.zip"), "filight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java

@@ -260,4 +260,9 @@ public class TestFrenchAnalyzer extends BaseTokenStreamTestCase {
     FrenchAnalyzer a = new FrenchAnalyzer(Version.LUCENE_31);
     assertAnalyzesTo(a, "Votre", new String[] { });
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new FrenchAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilter.java

@@ -159,4 +159,9 @@ public class TestFrenchLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("frlighttestdata.zip"), "frlight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilter.java

@@ -59,4 +59,9 @@ public class TestFrenchMinimalStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("frminimaltestdata.zip"), "frminimal.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestGalicianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "correspondente", "correspondente");
     checkOneTermReuse(a, "corresponderá", "correspond");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new GalicianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java

@@ -47,4 +47,9 @@ public class TestHindiAnalyzer extends BaseTokenStreamTestCase {
         HindiAnalyzer.getDefaultStopSet(), exclusionSet);
     checkOneTermReuse(a, "हिंदी", "हिंदी");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new HindiAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestHungarianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "babakocsi", "babakocsi");
     checkOneTermReuse(a, "babakocsijáért", "babakocs");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new HungarianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/hy/TestArmenianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestArmenianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "արծիվներ", "արծիվներ");
     checkOneTermReuse(a, "արծիվ", "արծ");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new ArmenianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestIndonesianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "peledakan", "peledakan");
     checkOneTermReuse(a, "pembunuhan", "bunuh");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new IndonesianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestItalianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "abbandonata", "abbandonata");
     checkOneTermReuse(a, "abbandonati", "abbandon");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new ItalianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilter.java

@@ -45,4 +45,9 @@ public class TestItalianLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("itlighttestdata.zip"), "itlight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestLatvianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "tirgiem", "tirgiem");
     checkOneTermReuse(a, "tirgus", "tirg");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new LatvianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/nl/TestDutchStemmer.java

@@ -185,4 +185,9 @@ public class TestDutchStemmer extends BaseTokenStreamTestCase {
     checkOneTerm(new DutchAnalyzer(TEST_VERSION_CURRENT), input, expected); 
   }
   
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new DutchAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
+  
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/no/TestNorwegianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestNorwegianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "havnedistriktene", "havnedistriktene");
     checkOneTermReuse(a, "havnedistrikter", "havnedistrikt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new NorwegianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java

@@ -50,4 +50,9 @@ public class TestPortugueseAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "quilométricas", "quilométricas");
     checkOneTermReuse(a, "quilométricos", "quilométr");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new PortugueseAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseLightStemFilter.java

@@ -92,4 +92,9 @@ public class TestPortugueseLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("ptlighttestdata.zip"), "ptlight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseMinimalStemFilter.java

@@ -66,4 +66,9 @@ public class TestPortugueseMinimalStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("ptminimaltestdata.zip"), "ptminimal.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseStemFilter.java

@@ -66,4 +66,9 @@ public class TestPortugueseStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("ptrslptestdata.zip"), "ptrslp.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/ro/TestRomanianAnalyzer.java

@@ -50,4 +50,9 @@ public class TestRomanianAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "absenţa", "absenţa");
     checkOneTermReuse(a, "absenţi", "absenţ");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new RomanianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java

@@ -64,4 +64,9 @@ public class TestRussianAnalyzer extends BaseTokenStreamTestCase {
           new String[] { "вмест", "сил", "электромагнитн", "энерг", "имел", "представление" });
      
     }
+    
+    /** blast some random strings through the analyzer */
+    public void testRandomStrings() throws Exception {
+      checkRandomData(random, new RussianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+    }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianLightStemFilter.java

@@ -45,4 +45,9 @@ public class TestRussianLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("rulighttestdata.zip"), "rulight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/sv/TestSwedishAnalyzer.java

@@ -23,6 +23,7 @@ import java.util.Set;
 
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.hu.HungarianAnalyzer;
 
 public class TestSwedishAnalyzer extends BaseTokenStreamTestCase {
   /** This test fails with NPE when the 
@@ -50,4 +51,9 @@ public class TestSwedishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "jaktkarlarne", "jaktkarlarne");
     checkOneTermReuse(a, "jaktkarlens", "jaktkarl");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new SwedishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/sv/TestSwedishLightStemFilter.java

@@ -45,4 +45,9 @@ public class TestSwedishLightStemFilter extends BaseTokenStreamTestCase {
   public void testVocabulary() throws IOException {
     assertVocabulary(analyzer, getDataFile("svlighttestdata.zip"), "svlight.txt");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java

@@ -143,4 +143,9 @@ public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
             "บริษัทชื่อ XY&Z - คุยกับ xyz@demo.com",
             new String[] { "บริษัท", "ชื่อ", "xy&z", "คุย", "กับ", "xyz@demo.com" });
   }
+	
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new ThaiAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/common/src/test/org/apache/lucene/analysis/tr/TestTurkishAnalyzer.java

@@ -50,4 +50,9 @@ public class TestTurkishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "ağacı", "ağacı");
     checkOneTermReuse(a, "ağaç", "ağaç");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new TurkishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/smartcn/src/test/org/apache/lucene/analysis/cn/smart/TestSmartChineseAnalyzer.java

@@ -195,4 +195,9 @@ public class TestSmartChineseAnalyzer extends BaseTokenStreamTestCase {
     while (stream.incrementToken()) {
     }
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new SmartChineseAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }

modules/analysis/stempel/src/test/org/apache/lucene/analysis/pl/TestPolishAnalyzer.java

@@ -50,4 +50,9 @@ public class TestPolishAnalyzer extends BaseTokenStreamTestCase {
     checkOneTermReuse(a, "studenta", "studenta");
     checkOneTermReuse(a, "studenci", "student");
   }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, new PolishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
+  }
 }