svn commit: r1311765 - /lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java

[rm...@apache.org]

Author: rmuir
Date: Tue Apr 10 14:49:36 2012
New Revision: 1311765

URL: http://svn.apache.org/viewvc?rev=1311765&view=rev
Log:
LUCENE-3969: add new random test for MappingCharFilter (sometimes fails, due to same final offset bug)

Modified:
    lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java

Modified: lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java?rev=1311765&r1=1311764&r2=1311765&view=diff
==============================================================================
--- lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java (original)
+++ lucene/dev/branches/lucene3969/modules/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestMappingCharFilter.java Tue Apr 10 14:49:36 2012
@@ -19,6 +19,8 @@ package org.apache.lucene.analysis.charf
 
 import java.io.Reader;
 import java.io.StringReader;
+import java.util.HashSet;
+import java.util.Set;
 
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
@@ -27,6 +29,7 @@ import org.apache.lucene.analysis.CharSt
 import org.apache.lucene.analysis.MockTokenizer;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.util._TestUtil;
 
 public class TestMappingCharFilter extends BaseTokenStreamTestCase {
 
@@ -214,4 +217,43 @@ public class TestMappingCharFilter exten
     String text = "gzw f quaxot";
     checkAnalysisConsistency(random, analyzer, false, text);
   }
+  
+  // nocommit: this is intended to fail until we fix bugs
+  public void testRandomMaps() throws Exception {
+    for (int i = 0; i < 100; i++) {
+      final NormalizeCharMap map = randomMap();
+      Analyzer analyzer = new Analyzer() {
+        @Override
+        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+          Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+          return new TokenStreamComponents(tokenizer, tokenizer);
+        }
+
+        @Override
+        protected Reader initReader(Reader reader) {
+          return new MappingCharFilter(map, CharReader.get(reader));
+        }
+      };
+      int numRounds = RANDOM_MULTIPLIER * 100;
+      checkRandomData(random, analyzer, numRounds);
+    }
+  }
+  
+  private NormalizeCharMap randomMap() {
+    NormalizeCharMap map = new NormalizeCharMap();
+    // we can't add duplicate keys, or NormalizeCharMap gets angry
+    Set<String> keys = new HashSet<String>();
+    int num = random.nextInt(5);
+    //System.out.println("NormalizeCharMap=");
+    for (int i = 0; i < num; i++) {
+      String key = _TestUtil.randomSimpleString(random);
+      if (!keys.contains(key)) {
+        String value = _TestUtil.randomSimpleString(random);
+        map.add(key, value);
+        keys.add(key);
+        //System.out.println("mapping: '" + key + "' => '" + value + "'");
+      }
+    }
+    return map;
+  }
 }