working on new model

git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@46 d817d54c-26ab-11de-abc9-2f7d1455ff7a

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

@@ -17,7 +17,10 @@ package org.apache.lucene.russian.morphology;
 
 import org.apache.lucene.russian.morphology.informations.Morph;
 
+import java.io.BufferedReader;
 import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
 
 /**
  * Created by IntelliJ IDEA.
@@ -31,6 +34,12 @@ public class Test {
     public static void main(String[] args) throws IOException, ClassNotFoundException {
         //
         Morph splitter = new Morph("sep.txt");
+        InputStream stream = Test.class.getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/russian-text.txt");
+        BufferedReader stream1 = new BufferedReader(new InputStreamReader(stream));
+        String s = stream1.readLine().trim().toLowerCase();
+        for (String w : s.split(" ")) {
+            System.out.println(splitter.getMorhInfo(w));
+        }
         System.gc();
         System.out.println("Ready");
         System.in.read();

src/main/java/org/apache/lucene/russian/morphology/informations/Heuristic.java

@@ -24,6 +24,26 @@ public class Heuristic implements Serializable {
         this.normalFormMorphInfo = normalFormMorphInfo;
     }
 
+    public String transofrmWord(String w) {
+        return w.substring(0, w.length() - actualSuffixLengh) + actualNormalSuffix;
+    }
+
+    public byte getActualSuffixLengh() {
+        return actualSuffixLengh;
+    }
+
+    public String getActualNormalSuffix() {
+        return actualNormalSuffix;
+    }
+
+    public short getFormMorphInfo() {
+        return formMorphInfo;
+    }
+
+    public short getNormalFormMorphInfo() {
+        return normalFormMorphInfo;
+    }
+
     @Override
     public boolean equals(Object o) {
         if (this == o) return true;

src/main/java/org/apache/lucene/russian/morphology/informations/Morph.java

@@ -1,9 +1,13 @@
 package org.apache.lucene.russian.morphology.informations;
 
+import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
+
 import java.io.BufferedReader;
 import java.io.FileReader;
 import java.io.FileWriter;
 import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
 
 
 public class Morph {
@@ -24,6 +28,50 @@ public class Morph {
         this.grammaInfo = grammaInfo;
     }
 
+    public List<String> getMorhInfo(String s) {
+        ArrayList<String> result = new ArrayList<String>();
+        int[] ints = RussianSuffixDecoderEncoder.encodeToArray(revertWord(s));
+        int ruleId = findRuleId(ints);
+        for (Heuristic h : rules[rulesId[ruleId]]) {
+            System.out.println(h);
+            result.add(h.transofrmWord(s));
+        }
+        return result;
+    }
+
+    private int findRuleId(int[] ints) {
+        int low = 0;
+        int high = separators.length - 1;
+        int mid = 0;
+        while (low <= high) {
+            mid = (low + high) >>> 1;
+            int[] midVal = separators[mid];
+
+            int comResult = compareToInts(ints, midVal);
+            if (comResult > 0)
+                low = mid + 1;
+            else if (comResult < 0)
+                high = mid - 1;
+            else
+                break;
+        }
+        if (compareToInts(ints, separators[mid]) >= 0) {
+            return mid;
+        } else {
+            return mid + 1;
+        }
+
+    }
+
+    private int compareToInts(int[] i1, int[] i2) {
+        int minLength = Math.min(i1.length, i2.length);
+        for (int i = 0; i < minLength; i++) {
+            int i3 = i1[i] < i2[i] ? -1 : (i1[i] == i2[i] ? 0 : 1);
+            if (i3 != 0) return i3;
+        }
+        return i2.length - i1.length;
+    }
+
     public void writeToFile(String fileName) throws IOException {
         FileWriter writer = new FileWriter(fileName);
         writer.write(separators.length + "\n");
@@ -87,4 +135,12 @@ public class Morph {
         }
         bufferedReader.close();
     }
+
+    private String revertWord(String s) {
+        String result = "";
+        for (int i = 1; i <= s.length(); i++) {
+            result += s.charAt(s.length() - i);
+        }
+        return result;
+    }
 }

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

@@ -15,15 +15,31 @@
  */
 package org.apache.lucene.russian.morphology;
 
+import org.apache.lucene.russian.morphology.informations.Morph;
 import org.junit.Test;
 
+import java.io.BufferedReader;
 import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
 
 
 public class SpeedTest {
 
     @Test
     public void getTestOfSpeed() throws IOException {
+        Morph splitter = new Morph("sep.txt");
+        InputStream stream = Test.class.getResourceAsStream("/org/apache/lucene/russian/morphology/analayzer/russian-text.txt");
+        BufferedReader stream1 = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
+        String s = stream1.readLine().trim().toLowerCase();
+        for (String w : s.split(" ")) {
+            try {
+                System.out.println(w);
+                System.out.println(splitter.getMorhInfo(w));
+            } catch (WrongCharaterException e) {
+
+            }
+        }
 //        Long startTime = System.currentTimeMillis();
 //        RussianMorphlogyAnalayzer morphlogyAnalayzer = new RussianMorphlogyAnalayzer();
 //        System.out.println("To build analayzer take " + (System.currentTimeMillis() - startTime) + " ms.");