adding name and middel name to russian morphology

git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@53 d817d54c-26ab-11de-abc9-2f7d1455ff7a

dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/StatiticsCollector.java

@@ -68,7 +68,7 @@ public class StatiticsCollector implements WordProccessor {
     }
 
 
-    public void saveHeuristic() throws IOException {
+    public void saveHeuristic(String fileName) throws IOException {
 
         Map<Integer, Integer> dist = new TreeMap<Integer, Integer>();
         Set<Heuristic> prevSet = null;
@@ -116,7 +116,7 @@ public class StatiticsCollector implements WordProccessor {
             }
         }
         Morph morph = new Morph(ints, rulesId, heuristics, grammaReader.getGrammaInfoAsArray());
-        morph.writeToFile("sep.txt");
+        morph.writeToFile(fileName);
     }
 
     private String revertWord(String s) {

russian/src/main/java/org/apache/lucene/morphology/russian/HeuristicBuilder.java

@@ -16,20 +16,21 @@
 
 package org.apache.lucene.morphology.russian;
 
-import org.apache.lucene.morpholgy.dictionary.*;
+import org.apache.lucene.morpholgy.dictionary.DictonaryReader;
+import org.apache.lucene.morpholgy.dictionary.GrammaReader;
+import org.apache.lucene.morpholgy.dictionary.StatiticsCollector;
 
 import java.io.IOException;
-import java.util.Set;
+import java.util.HashSet;
 
 
 public class HeuristicBuilder {
     public static void main(String[] args) throws IOException {
-        IgnoredFormReader formReader = new IgnoredFormReader("data/igoredFrom.txt");
-        Set<String> form = formReader.getIngnoredFroms();
+        //IgnoredFormReader formReader = new IgnoredFormReader("data/igoredFrom.txt");
+        //Set<String> form = formReader.getIngnoredFroms();
 
-        FrequentyReader frequentyReader = new FrequentyReader("data/lemma.num");
         GrammaReader grammaInfo = new GrammaReader("dictonary/Dicts/Morph/rgramtab.tab");
-        DictonaryReader dictonaryReader = new DictonaryReader("dictonary/Dicts/SrcMorph/RusSrc/morphs.mrd", form);
+        DictonaryReader dictonaryReader = new DictonaryReader("dictonary/Dicts/SrcMorph/RusSrc/morphs.mrd", new HashSet<String>());
 
         RussianLetterDecoderEncoder decoderEncoder = new RussianLetterDecoderEncoder();
         StatiticsCollector statiticsCollector = new StatiticsCollector(grammaInfo, decoderEncoder);

russian/src/main/java/org/apache/lucene/morphology/russian/Test.java

@@ -16,13 +16,11 @@
 package org.apache.lucene.morphology.russian;
 
 
-import org.apache.lucene.morphology.Heuristic;
 import org.apache.lucene.morphology.Morph;
 
+import java.io.BufferedReader;
+import java.io.FileReader;
 import java.io.IOException;
-import java.util.Arrays;
-import java.util.TreeMap;
-import java.util.TreeSet;
 
 /**
  * Created by IntelliJ IDEA.
@@ -35,27 +33,16 @@ public class Test {
 
     public static void main(String[] args) throws IOException, ClassNotFoundException {
         //
-        Morph splitter = new Morph("sep.txt",new RussianLetterDecoderEncoder());
-        TreeSet<Short> shorts = new TreeSet<Short>();
-        int count = 0;
-        TreeMap<Integer, Integer> rulesStat = new TreeMap<Integer, Integer>();
-        for (Heuristic[] heuristics : splitter.getRules()) {
-            Integer d = rulesStat.get(heuristics.length);
-            rulesStat.put(heuristics.length, 1 + (d == null ? 0 : d));
-            boolean flag = true;
-            short actualSuffixLenght = heuristics[0].getActualSuffixLengh();
-            String normalSuffix = heuristics[0].getActualNormalSuffix();
-            for (Heuristic heuristic : heuristics) {
-                flag = flag && (heuristic.getActualSuffixLengh() == actualSuffixLenght)
-                        && normalSuffix.equals(heuristic.getActualNormalSuffix());
+        Morph splitter = new Morph("russian/src/main/resources/org/apache/lucene/morphology/russian/morph.info", new RussianLetterDecoderEncoder());
+        FileReader fileReader = new FileReader("russian/src/main/resources/for.test.txt");
+        BufferedReader bufferedReader = new BufferedReader(fileReader);
+        String s = bufferedReader.readLine();
+        while (s != null) {
+            System.out.println(splitter.getMorhInfo(s));
+            s = bufferedReader.readLine();
         }
-            if (!flag) {
-                System.out.println(Arrays.asList(heuristics));
-                count++;
-            }
-        }
-        System.out.println(count);
-        System.out.println(rulesStat);
+
+        fileReader.close();
         System.gc();
         System.in.read();
     }

russian/src/main/resources/for.test.txt

@@ -0,0 +1,22 @@
+тест
+тестов
+вина
+вино
+еду
+ехать
+ананасов
+бухой
+сухой
+дураков
+пушка
+пушок
+пушек
+козлов
+жуков
+красив
+красивая
+тосклив
+наилучший
+лучший
+наипрекрасный
+на

russian/src/test/resources/org/apache/lucene/morphology/russian/decoder-test-data-for-array.txt

@@ -0,0 +1,13 @@
+тест тест
+ёж еж
+естера естера
+что-то что-то
+а а
+яяяяяя яяяяяя
+яяяя яяяя
+аа аа
+аааааа аааааа
+аааааааааааа аааааааааааа
+аааааааааааааааааа аааааааааааааааааа
+ааааааааааааааааа ааааааааааааааааа
+йфячыцувс йфячыцувс

russian/src/test/resources/org/apache/lucene/morphology/russian/decoder-test-data.txt

@@ -0,0 +1,8 @@
+тест тест
+ёж еж
+естера естера
+что-то что-то
+а а
+яяяяяя яяяяяя
+яяяя яяяя
+аа аа

russian/src/test/resources/org/apache/lucene/morphology/russian/russian-morphology-test.txt

@@ -0,0 +1,9 @@
+шел идти
+турестических турестический
+отзывы отзыв
+победы победа
+поэтическая поэтический
+произошло произойти
+test test
+ананасов ананас
+встовашего встовать