Archives/gnosygnu_xowa
1
0
Fork 0
mirror of https://github.com/gnosygnu/xowa.git synced 2026-03-02 03:49:30 +00:00
Code Issues Projects Releases Wiki Activity

Full-text search: Add analyzers for non-English languages

Browse Source
This commit is contained in:
gnosygnu
2017-03-13 10:05:21 -04:00
parent 77de7215ce
commit 3b6cc45084
10 changed files with 181 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
gplx.gflucene/src/gplx/gflucene/searchers/Gflucene_searcher_mgr.java Normal file
View File

@@ -0,0 +1,81 @@
/*
XOWA: the XOWA Offline Wiki Application
Copyright (C) 2012-2017 gnosygnu@gmail.com
XOWA is licensed under the terms of the General Public License (GPL) Version 3,
or alternatively under the terms of the Apache License Version 2.0.
You may use XOWA according to either of these licenses as is most appropriate
for your project on a case-by-case basis.
The terms of each license can be found in the source code repository:
GPLv3 License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-GPLv3.txt
Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
*/
package gplx.gflucene.searchers; import gplx.*; import gplx.gflucene.*;
import gplx.gflucene.core.*;
import gplx.gflucene.analyzers.*;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import gplx.gflucene.indexers.*;
public class Gflucene_searcher_mgr {
private Analyzer analyzer;
private Directory index;
public Gflucene_searcher_mgr() {
}
public void Init(Gflucene_index_data idx_data) {
// create analyzer
this.analyzer = Gflucene_analyzer_mgr_.New_analyzer(idx_data.analyzer_data.key);
// get index
Path path = Paths.get(idx_data.index_dir);
try {
this.index = FSDirectory.open(path);
} catch (IOException e) {
throw Err_.new_exc(e, "lucene_index", "failed to init searcher", "dir", idx_data.index_dir);
}
}
public void Exec(List_adp list, Gflucene_searcher_qry data) {
try {
IndexReader reader = DirectoryReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
Query query = new QueryParser("body", analyzer).parse(data.query);
// TopDocs docs = searcher.search(query, reader.maxDoc());
TopDocs docs = searcher.search(query, data.match_max);
ScoreDoc[] hits = docs.scoreDocs;
for(int i = 0; i < hits.length; i++) {
int docId = hits[i].doc;
Document d = searcher.doc(docId);
Gflucene_doc_data doc = new Gflucene_doc_data(Integer.parseInt(d.get("page_id")), Integer.parseInt(d.get("page_score")), d.get("title"), "");
doc.lucene_score = hits[i].score;
list.Add(doc);
}
reader.close();
} catch (Exception e) {
throw Err_.new_exc(e, "lucene_index", "failed to exec seearch", "query", data.query);
}
}
public void Term() {
}
}

24
gplx.gflucene/src/gplx/gflucene/searchers/Gflucene_searcher_qry.java Normal file
View File

@@ -0,0 +1,24 @@
/*
XOWA: the XOWA Offline Wiki Application
Copyright (C) 2012-2017 gnosygnu@gmail.com
XOWA is licensed under the terms of the General Public License (GPL) Version 3,
or alternatively under the terms of the Apache License Version 2.0.
You may use XOWA according to either of these licenses as is most appropriate
for your project on a case-by-case basis.
The terms of each license can be found in the source code repository:
GPLv3 License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-GPLv3.txt
Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
*/
package gplx.gflucene.searchers; import gplx.*; import gplx.gflucene.*;
public class Gflucene_searcher_qry {
public String query;
public int match_max;
public Gflucene_searcher_qry(String query, int match_max) {
this.query = query;
this.match_max = match_max;
}
}