edkuksa/russianmorphology
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding reading morphology fromresource

Browse Source 
git-svn-id: https://russianmorphology.googlecode.com/svn/trunk@54 d817d54c-26ab-11de-abc9-2f7d1455ff7a
This commit is contained in:
alexander.a.kuznetsov 2009-10-04 19:49:57 +00:00
parent 2cba2dd37e
commit a6970bda31
3 changed files with 28 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
morph/src/main/java/org/apache/lucene/morphology/LuceneMorph.java
View File

@ -18,6 +18,7 @@ package org.apache.lucene.morphology;
import java.io.BufferedReader; import java.io.BufferedReader;
import java.io.IOException; import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.List; import java.util.List;
@ -28,6 +29,10 @@ public class LuceneMorph extends Morph {
super(fileName, decoderEncoder); super(fileName, decoderEncoder);
} }
public LuceneMorph(InputStream inputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
super(inputStream, decoderEncoder);
}
@Override @Override
public List<String> getMorhInfo(String s) { public List<String> getMorhInfo(String s) {
ArrayList<String> result = new ArrayList<String>(); ArrayList<String> result = new ArrayList<String>();

17
morph/src/main/java/org/apache/lucene/morphology/Morph.java
View File

@ -16,10 +16,7 @@
package org.apache.lucene.morphology; package org.apache.lucene.morphology;
import java.io.BufferedReader; import java.io.*;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.List; import java.util.List;
@ -37,6 +34,11 @@ public class Morph {
this.decoderEncoder = decoderEncoder; this.decoderEncoder = decoderEncoder;
} }
public Morph(InputStream inputStream, LetterDecoderEncoder decoderEncoder) throws IOException {
readFromInputStream(inputStream);
this.decoderEncoder = decoderEncoder;
}
public Morph(int[][] separators, short[] rulesId, Heuristic[][] rules, String[] grammaInfo) { public Morph(int[][] separators, short[] rulesId, Heuristic[][] rules, String[] grammaInfo) {
this.separators = separators; this.separators = separators;
this.rulesId = rulesId; this.rulesId = rulesId;
@ -130,7 +132,12 @@ public class Morph {
} }
public void readFromFile(String fileName) throws IOException { public void readFromFile(String fileName) throws IOException {
BufferedReader bufferedReader = new BufferedReader(new FileReader(fileName)); FileInputStream inputStream = new FileInputStream(fileName);
readFromInputStream(inputStream);
}
private void readFromInputStream(InputStream inputStream) throws IOException {
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
String s = bufferedReader.readLine(); String s = bufferedReader.readLine();
Integer amount = Integer.valueOf(s); Integer amount = Integer.valueOf(s);

7
morph/src/main/java/org/apache/lucene/morphology/analayzer/MorphlogyAnalayzer.java
View File

@ -21,10 +21,11 @@ import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardFilter; import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.morphology.LuceneMorph;
import org.apache.lucene.morphology.LetterDecoderEncoder; import org.apache.lucene.morphology.LetterDecoderEncoder;
import org.apache.lucene.morphology.LuceneMorph;
import java.io.IOException; import java.io.IOException;
import java.io.InputStream;
import java.io.Reader; import java.io.Reader;
public class MorphlogyAnalayzer extends Analyzer { public class MorphlogyAnalayzer extends Analyzer {
@ -34,6 +35,10 @@ public class MorphlogyAnalayzer extends Analyzer {
luceneMorph = new LuceneMorph("sep.txt", letterDecoderEncoder); luceneMorph = new LuceneMorph("sep.txt", letterDecoderEncoder);
} }
public MorphlogyAnalayzer(InputStream inputStream, LetterDecoderEncoder letterDecoderEncoder) throws IOException {
luceneMorph = new LuceneMorph(inputStream, letterDecoderEncoder);
}
public TokenStream tokenStream(String fieldName, Reader reader) { public TokenStream tokenStream(String fieldName, Reader reader) {
TokenStream result = new StandardTokenizer(reader); TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result); result = new StandardFilter(result);