mirror of
https://github.com/gnosygnu/xowa.git
synced 2026-03-02 03:49:30 +00:00
Embeddable: Create core dbs in proper subdirectory
This commit is contained in:
gnosygnu
@@ -13,3 +13,45 @@ 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.analyzers; import gplx.*; import gplx.gflucene.*;
|
||||
import gplx.gflucene.core.*;
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
public class Gflucene_analyzer_mgr_ {
|
||||
public static Analyzer New_analyzer(String key) {
|
||||
if (String_.Eq(key, "standard")) return new org.apache.lucene.analysis.standard.StandardAnalyzer();
|
||||
else if (String_.Eq(key, "ar")) return new org.apache.lucene.analysis.ar.ArabicAnalyzer();
|
||||
else if (String_.Eq(key, "bg")) return new org.apache.lucene.analysis.bg.BulgarianAnalyzer();
|
||||
// else if (String_.Eq(key, "br")) return new org.apache.lucene.analysis.br.BrazilianAnalyzer();
|
||||
else if (String_.Eq(key, "ca")) return new org.apache.lucene.analysis.ca.CatalanAnalyzer();
|
||||
else if (String_.Eq(key, "cjk")) return new org.apache.lucene.analysis.cjk.CJKAnalyzer();
|
||||
else if (String_.Eq(key, "ckb")) return new org.apache.lucene.analysis.ckb.SoraniAnalyzer();
|
||||
else if (String_.Eq(key, "cz")) return new org.apache.lucene.analysis.cz.CzechAnalyzer();
|
||||
else if (String_.Eq(key, "da")) return new org.apache.lucene.analysis.da.DanishAnalyzer();
|
||||
else if (String_.Eq(key, "de")) return new org.apache.lucene.analysis.de.GermanAnalyzer();
|
||||
else if (String_.Eq(key, "el")) return new org.apache.lucene.analysis.el.GreekAnalyzer();
|
||||
else if (String_.Eq(key, "en")) return new org.apache.lucene.analysis.en.EnglishAnalyzer();
|
||||
else if (String_.Eq(key, "es")) return new org.apache.lucene.analysis.es.SpanishAnalyzer();
|
||||
else if (String_.Eq(key, "eu")) return new org.apache.lucene.analysis.eu.BasqueAnalyzer();
|
||||
else if (String_.Eq(key, "fa")) return new org.apache.lucene.analysis.fa.PersianAnalyzer();
|
||||
else if (String_.Eq(key, "fi")) return new org.apache.lucene.analysis.fi.FinnishAnalyzer();
|
||||
else if (String_.Eq(key, "fr")) return new org.apache.lucene.analysis.fr.FrenchAnalyzer();
|
||||
else if (String_.Eq(key, "ga")) return new org.apache.lucene.analysis.ga.IrishAnalyzer();
|
||||
else if (String_.Eq(key, "gl")) return new org.apache.lucene.analysis.gl.GalicianAnalyzer();
|
||||
else if (String_.Eq(key, "hi")) return new org.apache.lucene.analysis.hi.HindiAnalyzer();
|
||||
else if (String_.Eq(key, "hu")) return new org.apache.lucene.analysis.hu.HungarianAnalyzer();
|
||||
else if (String_.Eq(key, "hy")) return new org.apache.lucene.analysis.hy.ArmenianAnalyzer();
|
||||
else if (String_.Eq(key, "id")) return new org.apache.lucene.analysis.id.IndonesianAnalyzer();
|
||||
else if (String_.Eq(key, "it")) return new org.apache.lucene.analysis.it.ItalianAnalyzer();
|
||||
else if (String_.Eq(key, "lt")) return new org.apache.lucene.analysis.lt.LithuanianAnalyzer();
|
||||
else if (String_.Eq(key, "lv")) return new org.apache.lucene.analysis.lv.LatvianAnalyzer();
|
||||
else if (String_.Eq(key, "nl")) return new org.apache.lucene.analysis.nl.DutchAnalyzer();
|
||||
else if (String_.Eq(key, "no")) return new org.apache.lucene.analysis.no.NorwegianAnalyzer();
|
||||
else if (String_.Eq(key, "pt")) return new org.apache.lucene.analysis.pt.PortugueseAnalyzer();
|
||||
else if (String_.Eq(key, "ro")) return new org.apache.lucene.analysis.ro.RomanianAnalyzer();
|
||||
else if (String_.Eq(key, "ru")) return new org.apache.lucene.analysis.ru.RussianAnalyzer();
|
||||
else if (String_.Eq(key, "sv")) return new org.apache.lucene.analysis.sv.SwedishAnalyzer();
|
||||
else if (String_.Eq(key, "th")) return new org.apache.lucene.analysis.th.ThaiAnalyzer();
|
||||
else if (String_.Eq(key, "tr")) return new org.apache.lucene.analysis.tr.TurkishAnalyzer();
|
||||
else throw Err_.new_unhandled_default(key);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,23 @@ 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.core; import gplx.*; import gplx.gflucene.*;
|
||||
public class Gflucene_analyzer_data {
|
||||
public final String key;
|
||||
public Gflucene_analyzer_data(String key) {
|
||||
this.key = key;
|
||||
}
|
||||
public static Gflucene_analyzer_data New_data_from_locale(String locale) {
|
||||
String key = null;
|
||||
if (String_.Eq(locale, "en")) key = "standard"; // NOTE: en exists but use standard for now
|
||||
else if (String_.EqAny(locale
|
||||
, "ar", "bg", "ca", "ckb", "cz", "da", "de", "el", "es", "eu", "fa", "fi", "fr", "ga", "gl", "hi"
|
||||
, "hu", "hy", "id", "it", "lt", "lv", "nl", "no", "pt", "ro", "ru", "sv", "th", "tr")
|
||||
) key = locale;
|
||||
else if (String_.EqAny(locale
|
||||
, "zh", "ja", "ko")
|
||||
) key = "cjk";
|
||||
else key = "standard";
|
||||
return new Gflucene_analyzer_data(key);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,19 @@ 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.core; import gplx.*; import gplx.gflucene.*;
|
||||
public class Gflucene_doc_data {
|
||||
public String title;
|
||||
public String body;
|
||||
public int ns_id;
|
||||
public int page_id;
|
||||
public byte[] page_full_db;
|
||||
public int score;
|
||||
public float lucene_score = 0;
|
||||
public Gflucene_doc_data(int page_id, int score, String title, String body) {
|
||||
this.page_id = page_id;
|
||||
this.score = score;
|
||||
this.title = title;
|
||||
this.body = body;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,15 @@ 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.core; import gplx.*; import gplx.gflucene.*;
|
||||
import gplx.gflucene.analyzers.*;
|
||||
public class Gflucene_index_data {
|
||||
public final Gflucene_analyzer_data analyzer_data;
|
||||
public final String index_dir;
|
||||
|
||||
public final float max_merged_segments = 1500; // "limits" maximum file size
|
||||
public Gflucene_index_data(Gflucene_analyzer_data analyzer_data, String index_dir) {
|
||||
this.analyzer_data = analyzer_data;
|
||||
this.index_dir = index_dir;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,12 @@ 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.highlighters; import gplx.*; import gplx.gflucene.*;
|
||||
public class Gflucene_highlighter_item {
|
||||
public int num;
|
||||
public String text;
|
||||
public Gflucene_highlighter_item(int num, String text) {
|
||||
this.num = num;
|
||||
this.text = text;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,91 @@ 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.highlighters; import gplx.*; import gplx.gflucene.*;
|
||||
import gplx.gflucene.core.*;
|
||||
import gplx.gflucene.analyzers.*;
|
||||
import gplx.gflucene.searchers.*;
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Paths;
|
||||
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.standard.StandardAnalyzer;
|
||||
import org.apache.lucene.document.Document;
|
||||
import org.apache.lucene.index.DirectoryReader;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.lucene.queryparser.classic.ParseException;
|
||||
import org.apache.lucene.queryparser.classic.QueryParser;
|
||||
import org.apache.lucene.search.IndexSearcher;
|
||||
import org.apache.lucene.search.Query;
|
||||
import org.apache.lucene.search.TopDocs;
|
||||
import org.apache.lucene.search.highlight.Formatter;
|
||||
import org.apache.lucene.search.highlight.Fragmenter;
|
||||
import org.apache.lucene.search.highlight.Highlighter;
|
||||
import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
|
||||
import org.apache.lucene.search.highlight.QueryScorer;
|
||||
import org.apache.lucene.search.highlight.SimpleFragmenter;
|
||||
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
|
||||
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
|
||||
import org.apache.lucene.search.highlight.TextFragment;
|
||||
import org.apache.lucene.search.highlight.TokenSources;
|
||||
import org.apache.lucene.store.FSDirectory;
|
||||
public class Gflucene_highlighter_mgr {
|
||||
private Analyzer analyzer;
|
||||
|
||||
public Gflucene_highlighter_mgr() {
|
||||
}
|
||||
|
||||
public void Init(Gflucene_index_data idx_data) {
|
||||
this.analyzer = Gflucene_analyzer_mgr_.New_analyzer(idx_data.analyzer_data.key);
|
||||
}
|
||||
public Gflucene_highlighter_item[] Exec(Gflucene_searcher_qry qry_data, Gflucene_doc_data doc_data) {
|
||||
// create query
|
||||
QueryParser parser = new QueryParser("body", analyzer);
|
||||
Query query = null;
|
||||
try {
|
||||
query = parser.parse(qry_data.query);
|
||||
} catch (ParseException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to parse", "query", qry_data.query);
|
||||
}
|
||||
|
||||
// create highlighter
|
||||
SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter("<span class='snip_highlight'>", "</span>");
|
||||
QueryScorer scorer = new QueryScorer(query);
|
||||
scorer.setExpandMultiTermQuery(false);
|
||||
Highlighter highlighter = new Highlighter(htmlFormatter, scorer);
|
||||
SimpleFragmenter fragmenter = new SimpleFragmenter(100);
|
||||
highlighter.setTextFragmenter(fragmenter);
|
||||
|
||||
// get token stream
|
||||
String text = doc_data.body;
|
||||
TokenStream tokenStream = null;
|
||||
try {
|
||||
tokenStream = analyzer.tokenStream("body", text);
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to get stream", "query", qry_data.query);
|
||||
}
|
||||
|
||||
// get fragments from stream
|
||||
TextFragment[] frags;
|
||||
try {
|
||||
// frags = highlighter.getBestTextFragments(tokenStream, text, false, 1000);
|
||||
frags = highlighter.getBestTextFragments(tokenStream, text, true, 10);
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to get best", "query", qry_data.query);
|
||||
} catch (InvalidTokenOffsetsException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to get best", "query", qry_data.query);
|
||||
}
|
||||
|
||||
// convert fragments to highlighter items
|
||||
int frags_len = frags.length;
|
||||
Gflucene_highlighter_item[] array = new Gflucene_highlighter_item[frags_len];
|
||||
for (int i = 0; i < frags_len; i++) {
|
||||
String frag = frags[i].toString();
|
||||
array[i] = new Gflucene_highlighter_item(i, frag);
|
||||
}
|
||||
return array;
|
||||
}
|
||||
public void Term() {
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,37 @@ 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.indexers; import gplx.*; import gplx.gflucene.*;
|
||||
public class Gflucene_idx_opt {
|
||||
public Gflucene_idx_opt(int uid, String key, String name) {
|
||||
this.uid = uid;
|
||||
this.key = key;
|
||||
this.name = name;
|
||||
}
|
||||
public int Uid() {return uid;} private final int uid;
|
||||
public String Key() {return key;} private final String key;
|
||||
public String Name() {return name;} private final String name;
|
||||
|
||||
public static final int
|
||||
Uid_docs = 0 // basic inverted word index; number of words is always 1 per doc
|
||||
, Uid_docs_and_freqs = 1 // freqs needed for number of words per doc
|
||||
, Uid_docs_and_freqs_and_positions = 2 // positions needed for proximity queries
|
||||
, Uid_docs_and_freqs_and_positions_and_offsets = 3 // offsets needed for highlighter
|
||||
;
|
||||
|
||||
private static final Hash_adp parse_hash = Hash_adp_.New();
|
||||
public static final Gflucene_idx_opt
|
||||
Docs = New(Uid_docs, "d", "Documents")
|
||||
, Docs_and_freqs = New(Uid_docs_and_freqs, "df", "Documents / Frequencies")
|
||||
, Docs_and_freqs_and_positions = New(Uid_docs_and_freqs_and_positions, "dfp", "Documents / Frequencies / Positions")
|
||||
, Docs_and_freqs_and_positions_and_offsets = New(Uid_docs_and_freqs_and_positions_and_offsets, "dfpo", "Documents / Frequencies / Positions / Offsets")
|
||||
;
|
||||
private static Gflucene_idx_opt New(int uid, String key, String name) {
|
||||
Gflucene_idx_opt rv = new Gflucene_idx_opt(uid, key, name);
|
||||
parse_hash.Add(key, rv);
|
||||
return rv;
|
||||
}
|
||||
public static Gflucene_idx_opt Parse(String key) {
|
||||
return (Gflucene_idx_opt)parse_hash.Get_by_or_fail(key);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,112 @@ 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.indexers; import gplx.*; import gplx.gflucene.*;
|
||||
import gplx.gflucene.core.*;
|
||||
import java.io.IOException;
|
||||
import org.lukhnos.portmobile.file.Path;
|
||||
import org.lukhnos.portmobile.file.Paths;
|
||||
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.standard.StandardAnalyzer;
|
||||
import org.apache.lucene.document.*;
|
||||
import org.apache.lucene.index.IndexOptions;
|
||||
import org.apache.lucene.index.IndexWriter;
|
||||
import org.apache.lucene.index.IndexWriterConfig;
|
||||
import org.apache.lucene.index.TieredMergePolicy;
|
||||
import org.apache.lucene.store.Directory;
|
||||
import org.apache.lucene.store.FSDirectory;
|
||||
|
||||
import gplx.gflucene.analyzers.*;;
|
||||
public class Gflucene_indexer_mgr {
|
||||
private Analyzer analyzer;
|
||||
private IndexWriterConfig config;
|
||||
private Directory index;
|
||||
private IndexWriter wtr;
|
||||
private FieldType body_fld_type;
|
||||
|
||||
public Gflucene_indexer_mgr() {
|
||||
}
|
||||
|
||||
public void Init(Gflucene_index_data idx_data, String idx_opt) {
|
||||
// create analyzer
|
||||
this.analyzer = Gflucene_analyzer_mgr_.New_analyzer(idx_data.analyzer_data.key);
|
||||
this.config = new IndexWriterConfig(analyzer);
|
||||
|
||||
// limit max size by setting merge policy
|
||||
TieredMergePolicy merge_policy = new TieredMergePolicy();
|
||||
merge_policy.setMaxMergedSegmentMB(idx_data.max_merged_segments);
|
||||
config.setMergePolicy(merge_policy);
|
||||
|
||||
// create 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 open lucene index", "path", path);
|
||||
}
|
||||
|
||||
// create writer
|
||||
try {
|
||||
wtr = new IndexWriter(index, config);
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to create writer");
|
||||
}
|
||||
|
||||
// create field for body
|
||||
this.body_fld_type = new FieldType();
|
||||
IndexOptions index_options = To_index_options(idx_opt);
|
||||
body_fld_type.setIndexOptions(index_options);
|
||||
body_fld_type.setTokenized(true);
|
||||
body_fld_type.setStored(false);
|
||||
// body_fld.setStoreTermVectors(true);
|
||||
// body_fld.setStoreTermVectorOffsets(true);
|
||||
}
|
||||
public void Exec(Gflucene_doc_data doc_data) {
|
||||
Document doc = new Document();
|
||||
|
||||
doc.add(new StoredField("page_id", doc_data.page_id));
|
||||
doc.add(new NumericDocValuesField("page_score", doc_data.score));
|
||||
|
||||
// float score = ((float)doc_data.score / 1000000);
|
||||
// float score = doc_data.score;
|
||||
|
||||
TextField title_field = new TextField("title", doc_data.title, Field.Store.YES);
|
||||
// title_field.setBoost(score * 1024);
|
||||
// title_field.setBoost(score);
|
||||
doc.add(title_field);
|
||||
|
||||
Field body_field = new Field("body", doc_data.body, body_fld_type);
|
||||
// body_field.setBoost(score);
|
||||
doc.add(body_field);
|
||||
|
||||
try {
|
||||
wtr.addDocument(doc);
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to add document", "title", doc_data.title);
|
||||
}
|
||||
}
|
||||
public void Term() {
|
||||
try {
|
||||
wtr.close();
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to close writer");
|
||||
}
|
||||
try {
|
||||
index.close();
|
||||
} catch (IOException e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to close writer");
|
||||
}
|
||||
}
|
||||
|
||||
private static IndexOptions To_index_options(String key) {
|
||||
Gflucene_idx_opt opt = Gflucene_idx_opt.Parse(key);
|
||||
switch (opt.Uid()) {
|
||||
case Gflucene_idx_opt.Uid_docs: return IndexOptions.DOCS;
|
||||
case Gflucene_idx_opt.Uid_docs_and_freqs: return IndexOptions.DOCS_AND_FREQS;
|
||||
case Gflucene_idx_opt.Uid_docs_and_freqs_and_positions: return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
|
||||
case Gflucene_idx_opt.Uid_docs_and_freqs_and_positions_and_offsets: return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
|
||||
default: throw Err_.new_unhandled_default(opt.Uid());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,86 @@ 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 org.lukhnos.portmobile.file.Path;
|
||||
import org.lukhnos.portmobile.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.queries.CustomScoreQuery;
|
||||
import org.apache.lucene.queries.function.FunctionQuery;
|
||||
import org.apache.lucene.queries.function.valuesource.LongFieldSource;
|
||||
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
|
||||
import org.apache.lucene.queryparser.classic.QueryParser;
|
||||
import org.apache.lucene.search.BooleanClause;
|
||||
import org.apache.lucene.search.BooleanQuery;
|
||||
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(Ordered_hash 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);
|
||||
|
||||
// creates query that boosts by page_score; not sure if this is needed, but 1st release of fts uses this
|
||||
Query multi_query = MultiFieldQueryParser.parse(data.query, new String[] {"body"}, new BooleanClause.Occur []{BooleanClause.Occur.SHOULD}, analyzer);
|
||||
FunctionQuery boost_query = new FunctionQuery(new LongFieldSource("page_score"));
|
||||
CustomScoreQuery query = new CustomScoreQuery(multi_query, boost_query);
|
||||
|
||||
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"), "");
|
||||
String docTitle = d.get("title");
|
||||
Gflucene_doc_data doc = (Gflucene_doc_data)list.Get_by(docTitle);
|
||||
if (doc == null) {
|
||||
int doc_id = Integer.parseInt(d.get("page_id"));
|
||||
doc = new Gflucene_doc_data(doc_id, 0, docTitle, "");
|
||||
doc.lucene_score = hits[i].score;
|
||||
list.Add(doc_id, doc);
|
||||
}
|
||||
// Tfds.Write(doc.lucene_score, doc.title);
|
||||
}
|
||||
|
||||
reader.close();
|
||||
} catch (Exception e) {
|
||||
throw Err_.new_exc(e, "lucene_index", "failed to exec seearch", "query", data.query);
|
||||
}
|
||||
}
|
||||
public void Term() {
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,3 +13,12 @@ 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;
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user