From 13232282128d34a81b5a48d1b98bc62b9c5e48ce Mon Sep 17 00:00:00 2001
From: Alexander Kuznetsov <alexander.a.kuznetsov@gmail.com>
Date: Sat, 21 Mar 2015 01:28:06 +0300
Subject: [PATCH] Fixing issue 
 https://code.google.com/p/russianmorphology/issues/detail?id=12

---
 .../lucene/morphology/AnalyzersTest.java      | 20 +++++++++++++++++++
 .../lucene/morphology/MorphologyImpl.java     |  9 ++++++++-
 .../analyzer/MorphologyAnalyzer.java          |  5 ++---
 3 files changed, 30 insertions(+), 4 deletions(-)

diff --git a/dictionary-reader/src/test/java/org/apache/lucene/morphology/AnalyzersTest.java b/dictionary-reader/src/test/java/org/apache/lucene/morphology/AnalyzersTest.java
index 7cd5bd0..f8f182c 100644
--- a/dictionary-reader/src/test/java/org/apache/lucene/morphology/AnalyzersTest.java
+++ b/dictionary-reader/src/test/java/org/apache/lucene/morphology/AnalyzersTest.java
@@ -18,9 +18,13 @@ package org.apache.lucene.morphology;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.morphology.analyzer.MorphologyAnalyzer;
+import org.apache.lucene.morphology.analyzer.MorphologyFilter;
 import org.apache.lucene.morphology.english.EnglishAnalyzer;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.morphology.english.EnglishLuceneMorphology;
 import org.apache.lucene.morphology.russian.RussianAnalyzer;
+import org.apache.lucene.morphology.russian.RussianLuceneMorphology;
 import org.junit.Test;
 
 import java.io.*;
@@ -50,6 +54,22 @@ public class AnalyzersTest {
         testAnalayzer(morphlogyAnalyzer, answerPath, testPath);
     }
 
+    @Test
+    public void emptyStringTest() throws IOException {
+        LuceneMorphology russianLuceneMorphology = new RussianLuceneMorphology();
+        LuceneMorphology englishLuceneMorphology = new EnglishLuceneMorphology();
+
+        MorphologyAnalyzer russianAnalyzer = new MorphologyAnalyzer(russianLuceneMorphology);
+        InputStreamReader reader = new InputStreamReader(new ByteArrayInputStream("тест пм тест".getBytes()), "UTF-8");
+        TokenStream stream = russianAnalyzer.tokenStream(null, reader);
+        MorphologyFilter englishFilter = new MorphologyFilter(stream, englishLuceneMorphology);
+
+        englishFilter.reset();
+        while (englishFilter.incrementToken()) {
+            System.out.println(englishFilter.toString());
+        }
+    }
+
     @Test
     public void shouldProvideCorrectIndentForWordWithMelitaForm() throws IOException {
         Analyzer morphlogyAnalyzer = new RussianAnalyzer();
diff --git a/morph/src/main/java/org/apache/lucene/morphology/MorphologyImpl.java b/morph/src/main/java/org/apache/lucene/morphology/MorphologyImpl.java
index b1e7580..9a12d2b 100644
--- a/morph/src/main/java/org/apache/lucene/morphology/MorphologyImpl.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/MorphologyImpl.java
@@ -50,8 +50,15 @@ public class MorphologyImpl implements Morphology {
         ArrayList<String> result = new ArrayList<String>();
         int[] ints = decoderEncoder.encodeToArray(revertWord(s));
         int ruleId = findRuleId(ints);
+        boolean notSeenEmptyString = true;
         for (Heuristic h : rules[rulesId[ruleId]]) {
-            result.add(h.transformWord(s).toString());
+            String e = h.transformWord(s).toString();
+            if (e.length() > 0) {
+                result.add(e);
+            } else if (notSeenEmptyString) {
+                result.add(s);
+                notSeenEmptyString = false;
+            }
         }
         return result;
     }
diff --git a/morph/src/main/java/org/apache/lucene/morphology/analyzer/MorphologyAnalyzer.java b/morph/src/main/java/org/apache/lucene/morphology/analyzer/MorphologyAnalyzer.java
index 6b59a64..0e9bec1 100644
--- a/morph/src/main/java/org/apache/lucene/morphology/analyzer/MorphologyAnalyzer.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/analyzer/MorphologyAnalyzer.java
@@ -19,8 +19,6 @@ package org.apache.lucene.morphology.analyzer;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.TokenFilter;
 import org.apache.lucene.analysis.core.LowerCaseFilter;
-import org.apache.lucene.analysis.core.WhitespaceTokenizer;
-import org.apache.lucene.analysis.payloads.DelimitedPayloadTokenFilter;
 import org.apache.lucene.analysis.payloads.PayloadEncoder;
 import org.apache.lucene.analysis.payloads.PayloadHelper;
 import org.apache.lucene.analysis.standard.StandardFilter;
@@ -28,7 +26,6 @@ import org.apache.lucene.analysis.standard.StandardTokenizer;
 import org.apache.lucene.morphology.LetterDecoderEncoder;
 import org.apache.lucene.morphology.LuceneMorphology;
 import org.apache.lucene.util.BytesRef;
-import org.apache.lucene.util.Version;
 
 import java.io.IOException;
 import java.io.InputStream;
@@ -84,4 +81,6 @@ public class MorphologyAnalyzer extends Analyzer {
             }
         };
     }
+
+
 }