diff --git a/dictionary-reader/pom.xml b/dictionary-reader/pom.xml
new file mode 100644
index 0000000..1a7895f
--- /dev/null
+++ b/dictionary-reader/pom.xml
@@ -0,0 +1,22 @@
+
+
+
+ morpholgy
+ org.apache.lucene.morpholgy
+ 0.7-SNAPSHOT
+
+ 4.0.0
+ org.apache.lucene.morpholgy
+ dictionary-reader
+ dictionary-reader
+ 0.7-SNAPSHOT
+ http://maven.apache.org
+
+
+
+ org.apache.lucene.morpholgy
+ morph
+ 0.7-SNAPSHOT
+
+
+
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/DictonaryReader.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/DictonaryReader.java
similarity index 89%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/DictonaryReader.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/DictonaryReader.java
index d0b8350..3b63266 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/DictonaryReader.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/DictonaryReader.java
@@ -14,9 +14,8 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
-import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
import java.io.BufferedReader;
import java.io.FileInputStream;
@@ -72,7 +71,7 @@ public class DictonaryReader {
List models = wordsFlexias.get(Integer.valueOf(wd[1]));
FlexiaModel flexiaModel = models.get(0);
if (models.size() > 0 && !ingnoredForm.contains(flexiaModel.getCode())) {
- WordCard card = new WordCard(cleanString(flexiaModel.create(wordBase)), cleanString(wordBase), flexiaModel.getSuffix());
+ WordCard card = new WordCard(flexiaModel.create(wordBase), wordBase, flexiaModel.getSuffix());
for (FlexiaModel fm : models) {
card.addFlexia(fm);
}
@@ -81,9 +80,6 @@ public class DictonaryReader {
}
}
- private String cleanString(String s) {
- return s.replace((char) (34 + RussianSuffixDecoderEncoder.RUSSIAN_SMALL_LETTER_OFFSET), (char) (6 + RussianSuffixDecoderEncoder.RUSSIAN_SMALL_LETTER_OFFSET));
- }
private void sckipBlock(BufferedReader reader) throws IOException {
String s = reader.readLine();
@@ -123,7 +119,7 @@ public class DictonaryReader {
System.out.println(line);
// flexiaModelArrayList.add(new FlexiaModel(fl[1], cleanString(fl[0].toLowerCase()), cleanString(fl[2].toLowerCase())));
}
- if (fl.length == 2) flexiaModelArrayList.add(new FlexiaModel(fl[1], cleanString(fl[0].toLowerCase()), ""));
+ if (fl.length == 2) flexiaModelArrayList.add(new FlexiaModel(fl[1], fl[0].toLowerCase(), ""));
}
}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/FlexiaModel.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FlexiaModel.java
similarity index 92%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/FlexiaModel.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FlexiaModel.java
index 3ae24e1..72b83d7 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/FlexiaModel.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FlexiaModel.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
/**
* Represent inofrmation of how word form created form it imutible part.
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/FrequentyReader.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FrequentyReader.java
similarity index 93%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/FrequentyReader.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FrequentyReader.java
index 2d712bc..8537adb 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/FrequentyReader.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/FrequentyReader.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
import java.io.BufferedReader;
import java.io.FileInputStream;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/GrammaReader.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/GrammaReader.java
similarity index 94%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/GrammaReader.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/GrammaReader.java
index f249c71..aac0609 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/GrammaReader.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/GrammaReader.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
import java.io.BufferedReader;
import java.io.FileInputStream;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/IgnoredFormReader.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/IgnoredFormReader.java
similarity index 93%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/IgnoredFormReader.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/IgnoredFormReader.java
index 28100b5..6a140d4 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/IgnoredFormReader.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/IgnoredFormReader.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
import java.io.BufferedReader;
import java.io.FileInputStream;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/StatiticsCollector.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/StatiticsCollector.java
similarity index 87%
rename from src/main/java/org/apache/lucene/russian/morphology/StatiticsCollector.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/StatiticsCollector.java
index 9f533e0..b6ef5f8 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/StatiticsCollector.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/StatiticsCollector.java
@@ -14,15 +14,12 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morpholgy.dictionary;
-import org.apache.lucene.russian.morphology.dictonary.FlexiaModel;
-import org.apache.lucene.russian.morphology.dictonary.GrammaReader;
-import org.apache.lucene.russian.morphology.dictonary.WordCard;
-import org.apache.lucene.russian.morphology.dictonary.WordProccessor;
-import org.apache.lucene.russian.morphology.informations.Heuristic;
-import org.apache.lucene.russian.morphology.informations.Morph;
+import org.apache.lucene.morphology.Heuristic;
+import org.apache.lucene.morphology.LetterDecoderEncoder;
+import org.apache.lucene.morphology.Morph;
import java.io.IOException;
import java.util.*;
@@ -33,6 +30,7 @@ public class StatiticsCollector implements WordProccessor {
private Map, Integer> ruleInverIndex = new HashMap, Integer>();
private List> rules = new ArrayList>();
private GrammaReader grammaReader;
+ private LetterDecoderEncoder decoderEncoder;
public StatiticsCollector(GrammaReader grammaReader) {
@@ -40,6 +38,7 @@ public class StatiticsCollector implements WordProccessor {
}
public void proccess(WordCard wordCard) throws IOException {
+ wordCard = cleanWordCard(wordCard);
String normalStringMorph = wordCard.getWordsFroms().get(0).getCode();
String word = wordCard.getBase() + wordCard.getCanonicalSuffix();
if (word.contains("-")) return;
@@ -56,6 +55,10 @@ public class StatiticsCollector implements WordProccessor {
}
}
+ private WordCard cleanWordCard(WordCard wordCard) {
+ return wordCard;
+ }
+
public void saveHeuristic() throws IOException {
@@ -98,7 +101,7 @@ public class StatiticsCollector implements WordProccessor {
for (String key : inversIndex.keySet()) {
Set currentSet = inversIndex.get(key);
if (!currentSet.equals(prevSet)) {
- ints[count] = RussianSuffixDecoderEncoder.encodeToArray(key);
+ ints[count] = decoderEncoder.encodeToArray(key);
rulesId[count] = (short) ruleInverIndex.get(currentSet).intValue();
count++;
prevSet = currentSet;
@@ -136,5 +139,9 @@ public class StatiticsCollector implements WordProccessor {
return length;
}
+ private String cleanString(String s) {
+ return decoderEncoder.cleanString(s);
+ //return s.replace((char) (34 + RussianSuffixDecoderEncoder.RUSSIAN_SMALL_LETTER_OFFSET), (char) (6 + RussianSuffixDecoderEncoder.RUSSIAN_SMALL_LETTER_OFFSET));
+ }
}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/WordCard.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordCard.java
similarity index 76%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/WordCard.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordCard.java
index 881595a..4132479 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/WordCard.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordCard.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
import java.util.ArrayList;
import java.util.List;
@@ -53,4 +53,20 @@ public class WordCard {
public List getWordsFroms() {
return wordsFroms;
}
+
+ public void setCanonicalFrom(String canonicalFrom) {
+ this.canonicalFrom = canonicalFrom;
+ }
+
+ public void setBase(String base) {
+ this.base = base;
+ }
+
+ public void setCanonicalSuffix(String canonicalSuffix) {
+ this.canonicalSuffix = canonicalSuffix;
+ }
+
+ public void setWordsFroms(List wordsFroms) {
+ this.wordsFroms = wordsFroms;
+ }
}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/dictonary/WordProccessor.java b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordProccessor.java
similarity index 93%
rename from src/main/java/org/apache/lucene/russian/morphology/dictonary/WordProccessor.java
rename to dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordProccessor.java
index 37e769a..b0dc69d 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/dictonary/WordProccessor.java
+++ b/dictionary-reader/src/main/java/org/apache/lucene/morpholgy/dictionary/WordProccessor.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.dictonary;
+package org.apache.lucene.morpholgy.dictionary;
import java.io.IOException;
diff --git a/morph/pom.xml b/morph/pom.xml
new file mode 100644
index 0000000..0b2f5bb
--- /dev/null
+++ b/morph/pom.xml
@@ -0,0 +1,23 @@
+
+
+
+ morpholgy
+ org.apache.lucene.morpholgy
+ 0.7-SNAPSHOT
+
+ 4.0.0
+ org.apache.lucene.morpholgy
+ morph
+ morph
+ 0.7-SNAPSHOT
+ http://maven.apache.org
+
+
+
+ junit
+ junit
+ 3.8.1
+ test
+
+
+
diff --git a/src/main/java/org/apache/lucene/russian/morphology/informations/Heuristic.java b/morph/src/main/java/org/apache/lucene/morphology/Heuristic.java
similarity index 95%
rename from src/main/java/org/apache/lucene/russian/morphology/informations/Heuristic.java
rename to morph/src/main/java/org/apache/lucene/morphology/Heuristic.java
index 10a9e80..7b00e93 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/informations/Heuristic.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/Heuristic.java
@@ -13,7 +13,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.informations;
+package org.apache.lucene.morphology;
import java.io.Serializable;
diff --git a/morph/src/main/java/org/apache/lucene/morphology/LetterDecoderEncoder.java b/morph/src/main/java/org/apache/lucene/morphology/LetterDecoderEncoder.java
new file mode 100644
index 0000000..0637a98
--- /dev/null
+++ b/morph/src/main/java/org/apache/lucene/morphology/LetterDecoderEncoder.java
@@ -0,0 +1,31 @@
+/**
+ * Copyright 2009 Alexander Kuznetsov
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.morphology;
+
+
+public interface LetterDecoderEncoder {
+ public Integer encode(String string);
+
+ public int[] encodeToArray(String s);
+
+ public String decodeArray(int[] array);
+
+ public String decode(Integer suffixN);
+
+ public boolean checkCharacter(char c);
+
+ public String cleanString(String s);
+}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/informations/LuceneMorph.java b/morph/src/main/java/org/apache/lucene/morphology/LuceneMorph.java
similarity index 64%
rename from src/main/java/org/apache/lucene/russian/morphology/informations/LuceneMorph.java
rename to morph/src/main/java/org/apache/lucene/morphology/LuceneMorph.java
index f2d0677..067d536 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/informations/LuceneMorph.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/LuceneMorph.java
@@ -1,14 +1,29 @@
-package org.apache.lucene.russian.morphology.informations;
+/**
+ * Copyright 2009 Alexander Kuznetsov
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.morphology;
-import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
-import java.io.IOException;
import java.io.BufferedReader;
+import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
-public class LuceneMorph extends Morph{
+public class LuceneMorph extends Morph {
+ LetterDecoderEncoder decoderEncoder;
public LuceneMorph(String fileName) throws IOException {
super(fileName);
@@ -17,7 +32,7 @@ public class LuceneMorph extends Morph{
@Override
public List getMorhInfo(String s) {
ArrayList result = new ArrayList();
- int[] ints = RussianSuffixDecoderEncoder.encodeToArray(revertWord(s));
+ int[] ints = decoderEncoder.encodeToArray(revertWord(s));
int ruleId = findRuleId(ints);
for (Heuristic h : rules[rulesId[ruleId]]) {
result.add(h.transofrmWord(s));
@@ -43,14 +58,14 @@ public class LuceneMorph extends Morph{
}
- private Heuristic[] modeifyHeuristic(Heuristic[] heuristics){
+ private Heuristic[] modeifyHeuristic(Heuristic[] heuristics) {
ArrayList result = new ArrayList();
- for(Heuristic heuristic:heuristics){
+ for (Heuristic heuristic : heuristics) {
boolean isAdded = true;
- for(Heuristic ch:result){
+ for (Heuristic ch : result) {
isAdded = isAdded && !(ch.getActualNormalSuffix().equals(heuristic.getActualNormalSuffix()) && (ch.getActualSuffixLengh() == heuristic.getActualSuffixLengh()));
}
- if(isAdded){
+ if (isAdded) {
result.add(heuristic);
}
}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/informations/Morph.java b/morph/src/main/java/org/apache/lucene/morphology/Morph.java
similarity index 93%
rename from src/main/java/org/apache/lucene/russian/morphology/informations/Morph.java
rename to morph/src/main/java/org/apache/lucene/morphology/Morph.java
index 52b1a36..b40d933 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/informations/Morph.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/Morph.java
@@ -13,9 +13,8 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.informations;
+package org.apache.lucene.morphology;
-import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
import java.io.BufferedReader;
import java.io.FileReader;
@@ -30,6 +29,7 @@ public class Morph {
protected short[] rulesId;
protected Heuristic[][] rules;
protected String[] grammaInfo;
+ LetterDecoderEncoder decoderEncoder;
public Morph(String fileName) throws IOException {
@@ -61,7 +61,7 @@ public class Morph {
public List getMorhInfo(String s) {
ArrayList result = new ArrayList();
- int[] ints = RussianSuffixDecoderEncoder.encodeToArray(revertWord(s));
+ int[] ints = decoderEncoder.encodeToArray(revertWord(s));
int ruleId = findRuleId(ints);
for (Heuristic h : rules[rulesId[ruleId]]) {
result.add(h.transofrmWord(s) + "|" + grammaInfo[h.getFormMorphInfo()]);
diff --git a/src/main/java/org/apache/lucene/russian/morphology/SuffixToLongException.java b/morph/src/main/java/org/apache/lucene/morphology/SuffixToLongException.java
similarity index 91%
rename from src/main/java/org/apache/lucene/russian/morphology/SuffixToLongException.java
rename to morph/src/main/java/org/apache/lucene/morphology/SuffixToLongException.java
index 568ba05..22f7414 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/SuffixToLongException.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/SuffixToLongException.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morphology;
public class SuffixToLongException extends RuntimeException {
diff --git a/src/main/java/org/apache/lucene/russian/morphology/WrongCharaterException.java b/morph/src/main/java/org/apache/lucene/morphology/WrongCharaterException.java
similarity index 91%
rename from src/main/java/org/apache/lucene/russian/morphology/WrongCharaterException.java
rename to morph/src/main/java/org/apache/lucene/morphology/WrongCharaterException.java
index e37c690..906bc0d 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/WrongCharaterException.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/WrongCharaterException.java
@@ -14,7 +14,7 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morphology;
public class WrongCharaterException extends RuntimeException {
diff --git a/src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzer.java b/morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyAnalayzer.java
similarity index 89%
rename from src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzer.java
rename to morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyAnalayzer.java
index 18e56a2..67c12ec 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyAnalayzer.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyAnalayzer.java
@@ -14,14 +14,14 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.analayzer;
+package org.apache.lucene.morphology.analayzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
-import org.apache.lucene.russian.morphology.informations.LuceneMorph;
+import org.apache.lucene.morphology.LuceneMorph;
import java.io.IOException;
import java.io.Reader;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyFilter.java b/morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyFilter.java
similarity index 92%
rename from src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyFilter.java
rename to morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyFilter.java
index b494792..ca3a1a0 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/analayzer/RussianMorphlogyFilter.java
+++ b/morph/src/main/java/org/apache/lucene/morphology/analayzer/RussianMorphlogyFilter.java
@@ -14,16 +14,16 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology.analayzer;
+package org.apache.lucene.morphology.analayzer;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.russian.morphology.informations.LuceneMorph;
+import org.apache.lucene.morphology.LuceneMorph;
import java.io.IOException;
-import java.util.List;
import java.util.ArrayList;
+import java.util.List;
public class RussianMorphlogyFilter extends TokenFilter {
@@ -37,7 +37,7 @@ public class RussianMorphlogyFilter extends TokenFilter {
private List stack = new ArrayList();
private int index = 0;
- private Token current = null;
+ private Token current = null;
/**
* Returns the next token in the stream, or null at EOS.
diff --git a/src/test/resources/org/apache/lucene/russian/morphology/analayzer/russian-text.txt b/morph/src/main/java/org/apache/lucene/morphology/analayzer/russian-text.txt
similarity index 100%
rename from src/test/resources/org/apache/lucene/russian/morphology/analayzer/russian-text.txt
rename to morph/src/main/java/org/apache/lucene/morphology/analayzer/russian-text.txt
diff --git a/src/test/resources/org/apache/lucene/russian/morphology/analayzer/suffix-heuristic-test-data.txt b/morph/src/main/java/org/apache/lucene/morphology/analayzer/suffix-heuristic-test-data.txt
similarity index 100%
rename from src/test/resources/org/apache/lucene/russian/morphology/analayzer/suffix-heuristic-test-data.txt
rename to morph/src/main/java/org/apache/lucene/morphology/analayzer/suffix-heuristic-test-data.txt
diff --git a/src/test/resources/org/apache/lucene/russian/morphology/analayzer/token-of-russian-text.txt b/morph/src/main/java/org/apache/lucene/morphology/analayzer/token-of-russian-text.txt
similarity index 100%
rename from src/test/resources/org/apache/lucene/russian/morphology/analayzer/token-of-russian-text.txt
rename to morph/src/main/java/org/apache/lucene/morphology/analayzer/token-of-russian-text.txt
diff --git a/pom.xml b/pom.xml
index b961528..97fbb1c 100644
--- a/pom.xml
+++ b/pom.xml
@@ -1,16 +1,19 @@
-
+
+
4.0.0
- org.apache.lucene
- russian-morpholgy
- jar
+ org.apache.lucene.morpholgy
+ morpholgy
+ pom
0.7-SNAPSHOT
- russian-morpholgy
+ morpholgy
http://maven.apache.org
- scm:svn:http://russianmorphology.googlecode.com/svn/tags/russian-morpholgy-0.6
- scm:svn:https://russianmorphology.googlecode.com/svn/tags/russian-morpholgy-0.6
+ scm:svn:http://russianmorphology.googlecode.com/svn/tags/russian-morpholgy-0.7
+ scm:svn:https://russianmorphology.googlecode.com/svn/tags/russian-morpholgy-0.7
+
@@ -108,10 +111,10 @@
**/*.txt
+ **/pom.xml
**/src/**
- **/pom.xml
@@ -127,4 +130,9 @@
-
+
+ morph
+ dictionary-reader
+ russian
+
+
\ No newline at end of file
diff --git a/russian/pom.xml b/russian/pom.xml
new file mode 100644
index 0000000..ceade52
--- /dev/null
+++ b/russian/pom.xml
@@ -0,0 +1,31 @@
+
+
+
+ morpholgy
+ org.apache.lucene.morpholgy
+ 0.7-SNAPSHOT
+
+ 4.0.0
+ org.apache.lucene.morpholgy
+ russian
+ russian
+ 0.7-SNAPSHOT
+ http://maven.apache.org
+
+
+
+ org.apache.lucene.morpholgy
+ dictionary-reader
+ 0.7-SNAPSHOT
+
+
+
+ junit
+ junit
+ 4.4
+ test
+
+
+
+
\ No newline at end of file
diff --git a/src/main/java/org/apache/lucene/russian/morphology/HeuristicBuilder.java b/russian/src/main/java/org/apache/lucene/morphology/russian/HeuristicBuilder.java
similarity index 78%
rename from src/main/java/org/apache/lucene/russian/morphology/HeuristicBuilder.java
rename to russian/src/main/java/org/apache/lucene/morphology/russian/HeuristicBuilder.java
index cb32470..f38a335 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/HeuristicBuilder.java
+++ b/russian/src/main/java/org/apache/lucene/morphology/russian/HeuristicBuilder.java
@@ -14,12 +14,9 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morphology.russian;
-import org.apache.lucene.russian.morphology.dictonary.DictonaryReader;
-import org.apache.lucene.russian.morphology.dictonary.FrequentyReader;
-import org.apache.lucene.russian.morphology.dictonary.GrammaReader;
-import org.apache.lucene.russian.morphology.dictonary.IgnoredFormReader;
+import org.apache.lucene.morpholgy.dictionary.*;
import java.io.IOException;
import java.util.Set;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/RussianSuffixDecoderEncoder.java b/russian/src/main/java/org/apache/lucene/morphology/russian/RussianSuffixDecoderEncoder.java
similarity index 82%
rename from src/main/java/org/apache/lucene/russian/morphology/RussianSuffixDecoderEncoder.java
rename to russian/src/main/java/org/apache/lucene/morphology/russian/RussianSuffixDecoderEncoder.java
index 90388db..6c0240d 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/RussianSuffixDecoderEncoder.java
+++ b/russian/src/main/java/org/apache/lucene/morphology/russian/RussianSuffixDecoderEncoder.java
@@ -14,7 +14,11 @@
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morphology.russian;
+
+import org.apache.lucene.morphology.LetterDecoderEncoder;
+import org.apache.lucene.morphology.SuffixToLongException;
+import org.apache.lucene.morphology.WrongCharaterException;
import java.util.ArrayList;
@@ -24,7 +28,7 @@ import java.util.ArrayList;
* Assumed that suffix contains only small russian letters and dash.
* Also assumed that letter � and � coinsed.
*/
-public class RussianSuffixDecoderEncoder {
+public class RussianSuffixDecoderEncoder implements LetterDecoderEncoder {
public static final int RUSSIAN_SMALL_LETTER_OFFSET = 1071;
static public int SUFFIX_LENGTH = 6;
public static final int EE_CHAR = 34;
@@ -32,7 +36,7 @@ public class RussianSuffixDecoderEncoder {
public static final int DASH_CHAR = 45;
public static final int DASH_CODE = 33;
- static public Integer encode(String string) {
+ public Integer encode(String string) {
if (string.length() > 6) throw new SuffixToLongException("Suffix length should not be greater then " + 12);
int result = 0;
for (int i = 0; i < string.length(); i++) {
@@ -51,7 +55,7 @@ public class RussianSuffixDecoderEncoder {
return result;
}
- static public int[] encodeToArray(String s) {
+ public int[] encodeToArray(String s) {
ArrayList integers = new ArrayList();
while (s.length() > 6) {
integers.add(encode(s.substring(0, 6)));
@@ -67,7 +71,7 @@ public class RussianSuffixDecoderEncoder {
return ints;
}
- static public String decodeArray(int[] array) {
+ public String decodeArray(int[] array) {
String result = "";
for (int i : array) {
result += decode(i);
@@ -76,7 +80,7 @@ public class RussianSuffixDecoderEncoder {
}
- static public String decode(Integer suffixN) {
+ public String decode(Integer suffixN) {
String result = "";
while (suffixN > 33) {
int c = suffixN % 34 + RUSSIAN_SMALL_LETTER_OFFSET;
@@ -94,11 +98,15 @@ public class RussianSuffixDecoderEncoder {
return result;
}
- static public boolean checkCharacter(char c) {
+ public boolean checkCharacter(char c) {
int code = 0 + c;
if (code == 45) return true;
code -= RUSSIAN_SMALL_LETTER_OFFSET;
if (code > 0 && code < 33) return true;
return false;
}
+
+ public String cleanString(String s) {
+ return s;
+ }
}
diff --git a/src/main/java/org/apache/lucene/russian/morphology/Test.java b/russian/src/main/java/org/apache/lucene/morphology/russian/Test.java
similarity index 89%
rename from src/main/java/org/apache/lucene/russian/morphology/Test.java
rename to russian/src/main/java/org/apache/lucene/morphology/russian/Test.java
index ff63cb4..ad972a3 100644
--- a/src/main/java/org/apache/lucene/russian/morphology/Test.java
+++ b/russian/src/main/java/org/apache/lucene/morphology/russian/Test.java
@@ -13,10 +13,11 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.lucene.russian.morphology;
+package org.apache.lucene.morphology.russian;
-import org.apache.lucene.russian.morphology.informations.Heuristic;
-import org.apache.lucene.russian.morphology.informations.Morph;
+
+import org.apache.lucene.morphology.Heuristic;
+import org.apache.lucene.morphology.Morph;
import java.io.IOException;
import java.util.Arrays;
diff --git a/src/main/java/org/apache/lucene/russian/morphology/analayzer/SuffixHeuristic.java b/src/main/java/org/apache/lucene/russian/morphology/analayzer/SuffixHeuristic.java
deleted file mode 100644
index c9905be..0000000
--- a/src/main/java/org/apache/lucene/russian/morphology/analayzer/SuffixHeuristic.java
+++ /dev/null
@@ -1,87 +0,0 @@
-/**
- * Copyright 2009 Alexander Kuznetsov
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-package org.apache.lucene.russian.morphology.analayzer;
-
-import org.apache.lucene.russian.morphology.RussianSuffixDecoderEncoder;
-
-import java.io.*;
-import java.util.Arrays;
-
-
-public class SuffixHeuristic {
- private long[] keys;
- private long[] values;
-
- public void readFromFile(String fileName) throws IOException {
- BufferedReader reader = new BufferedReader(new FileReader(fileName));
- readFromBufferedRreader(reader);
- }
-
-
- public SuffixHeuristic() throws IOException {
- readFromResource();
- }
-
- public SuffixHeuristic(String fileName) throws IOException {
- readFromFile(fileName);
- }
-
- public void readFromResource() throws IOException {
- InputStream stream = this.getClass().getResourceAsStream("/org/apache/lucene/russian/morphology/russianSuffixesHeuristic.txt");
- BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(stream));
- readFromBufferedRreader(bufferedReader);
- }
-
- private void readFromBufferedRreader(BufferedReader reader) throws IOException {
- int size = Integer.valueOf(reader.readLine());
- keys = new long[size];
- values = new long[size];
- for (int i = 0; i < size; i++) {
- String[] s = reader.readLine().split(" ");
- keys[i] = Long.valueOf(s[0]);
- values[i] = Long.valueOf(s[1]);
- }
- }
-
- public String getCanonicalForm(String form) {
- int startSymbol = form.length() > RussianSuffixDecoderEncoder.SUFFIX_LENGTH ? form.length() - RussianSuffixDecoderEncoder.SUFFIX_LENGTH : 0;
- String suffixS = form.substring(startSymbol);
-
- if (!chechSuffix(suffixS)) return form;
-
- Integer suffix = RussianSuffixDecoderEncoder.encode(suffixS);
-
- int index = Arrays.binarySearch(keys, suffix);
- if (index < -1) {
- System.out.println(" " + form);
- return form;
- } else {
- String nSuffix = RussianSuffixDecoderEncoder.decode((int) values[index]);
- return startSymbol > 0 ? form.substring(0, startSymbol) + nSuffix : nSuffix;
- }
- }
-
-
- private boolean chechSuffix(String suffix) {
- for (int i = 0; i < suffix.length(); i++) {
- if (!RussianSuffixDecoderEncoder.checkCharacter(suffix.charAt(i))) return false;
- }
- return true;
- }
-
-
-}