From c61932d99dd6167ccf232293df7269019f5cfb83 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Sat, 9 Jan 2021 06:20:06 +0100
Subject: [PATCH] Implement trivial custom analyzer
---
src/main/java/org/RI/P2/Indexer.java | 38 +++++++++++++++++++---------
1 file changed, 26 insertions(+), 12 deletions(-)
diff --git a/src/main/java/org/RI/P2/Indexer.java b/src/main/java/org/RI/P2/Indexer.java
index ac28ef4..b6fc78a 100644
--- a/src/main/java/org/RI/P2/Indexer.java
+++ b/src/main/java/org/RI/P2/Indexer.java
@@ -7,8 +7,12 @@ import java.io.Reader;
import java.nio.file.Paths;
import java.text.ParseException;
import java.util.HashMap;
+import java.util.List;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
+import org.apache.lucene.analysis.en.EnglishAnalyzer;
+import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
@@ -17,20 +21,29 @@ import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.json.simple.JSONArray;
+import org.json.simple.JSONObject;
import org.json.simple.JSONValue;
public class Indexer {
IndexWriter index;
String folderPath;
- Map<String, Analyzer> analyzerPerField;
+ PerFieldAnalyzerWrapper customAnalyzer;
Indexer(String folderPath) throws IOException, ParseException {
this.folderPath = folderPath;
- analyzerPerField = new HashMap<>();
- createIndex(folderPath);
+ customAnalyzer = createAnalyzer();
}
- public JSONArray parseJSONFile(String filePath) throws IOException, ParseException {
+ PerFieldAnalyzerWrapper createAnalyzer() {
+ Map<String, Analyzer> analyzerPerField = new HashMap<>();
+ analyzerPerField.put("title", new EnglishAnalyzer());
+ analyzerPerField.put("abstract", new EnglishAnalyzer());
+ PerFieldAnalyzerWrapper customAnalyzer = new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(),
+ analyzerPerField);
+ return customAnalyzer;
+ }
+
+ JSONArray parseJSONFile(String filePath) throws IOException, ParseException {
InputStream jsonFile = getClass().getResourceAsStream(filePath);
Reader readerJson = new InputStreamReader(jsonFile);
Object fileObjects = JSONValue.parse(readerJson);
@@ -38,25 +51,26 @@ public class Indexer {
return arrayObjects;
}
- public void openIndex() throws IOException {
+ void openIndex() throws IOException {
Directory dir = FSDirectory.open(Paths.get(folderPath));
- Analyzer analyzer = new StandardAnalyzer();
- IndexWriterConfig config = new IndexWriterConfig(analyzer);
+ IndexWriterConfig config = new IndexWriterConfig(customAnalyzer);
config.setOpenMode(OpenMode.CREATE_OR_APPEND);
index = new IndexWriter(dir, config);
}
- public void addDocuments(JSONArray jsonObjects) throws IOException {
- Document doc = new Document();
- index.addDocument(doc);
+ void addDocuments(JSONArray jsonObjects) throws IOException {
+ for (JSONObject object : (List<JSONObject>) jsonObjects) {
+ Document doc = new Document();
+ index.addDocument(doc);
+ }
}
- public void commitChanges() throws IOException {
+ void commitChanges() throws IOException {
index.commit();
index.close();
}
- public void createIndex(String folderPath) throws IOException, ParseException {
+ void createIndex() throws IOException, ParseException {
JSONArray jsonObjects = parseJSONFile(folderPath);
openIndex();
addDocuments(jsonObjects);