working on analayzer and test

git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@9 d817d54c-26ab-11de-abc9-2f7d1455ff7a

src/main/java/org/apache/lucene/russian/morphology/analayzer/ArrayEvristics.java

@@ -25,7 +25,7 @@ public class ArrayEvristics {
     }
 
     public void readFromResource() throws IOException {
-        InputStream stream = this.getClass().getResourceAsStream("/russianSuffixesEvristics.txt");
+        InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/russianSuffixesEvristics.txt");
         BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream));
         readFromBufferedRreader(bufferedReader);
     }

src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzer.java

@@ -0,0 +1,19 @@
+package org.apache.lucene.russian.morphology.analayzer;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.TokenStream;
+
+import java.io.Reader;
+import java.io.IOException;
+
+public class RussianMorphlogyAnalayzer  extends Analyzer {
+    private ArrayEvristics arrayEvristics;
+
+    public RussianMorphlogyAnalayzer() throws IOException {
+        arrayEvristics = new ArrayEvristics();
+    }
+
+    public TokenStream tokenStream(String fieldName, Reader reader) {
+        return null;  //To change body of implemented methods use File | Settings | File Templates.
+    }
+}

src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyFilter.java

@@ -18,12 +18,13 @@ public class RussianMorphlogyFilter extends TokenFilter {
     public Token next(final Token reusableToken) throws IOException {
         Token nextToken = input.next(reusableToken);
         if(nextToken == null || nextToken.term().length() == 0) return nextToken;
-        Character testC = nextToken.term().charAt(0);
+        String word = nextToken.term().toLowerCase();
+        Character testC = word.charAt(0);
         if (Character.UnicodeBlock.of(testC) != Character.UnicodeBlock.CYRILLIC){
             return  nextToken;
         }
         Token current = (Token) nextToken.clone();
-        return createToken(arrayEvristics.getCanonicalForm(nextToken.term()), current, reusableToken);
+        return createToken(arrayEvristics.getCanonicalForm(word), current, reusableToken);
     }
 
     protected Token createToken(String synonym, Token current, final Token reusableToken) {

src/test/java/org/apache/lucene/russian/morphology/RussianSuffixDecoderEncoderTest.java

@@ -15,7 +15,7 @@ public class RussianSuffixDecoderEncoderTest {
 
     @Test
     public void testShouldCorretDecodeEncode() throws IOException {
-       InputStream stream = this.getClass().getResourceAsStream("/decoder-test-data.txt");
+       InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/decoder-test-data.txt");
        BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream));
        String s = bufferedReader.readLine();
         while(s != null){

src/test/java/org/apache/lucene/russian/morphology/analayzer/ArrayEvristicsTest.java

@@ -0,0 +1,12 @@
+package org.apache.lucene.russian.morphology.analayzer;
+
+import org.junit.Test;
+
+
+public class ArrayEvristicsTest {
+
+    @Test
+    public void testShouldDefineCorretCononicalWordForm(){
+
+    }
+}