Merge branch 'master' of https://github.com/JonCook/tutorials

lucene/src/main/java/com/baeldung/lucene/InMemoryLuceneIndex.java

@@ -0,0 +1,128 @@
+package com.baeldung.lucene;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.document.SortedDocValuesField;
+import org.apache.lucene.document.TextField;
+import org.apache.lucene.index.DirectoryReader;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.index.Term;
+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.ScoreDoc;
+import org.apache.lucene.search.Sort;
+import org.apache.lucene.search.TopDocs;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.util.BytesRef;
+
+public class InMemoryLuceneIndex {
+
+    private Directory memoryIndex;
+    private Analyzer analyzer;
+
+    public InMemoryLuceneIndex(Directory memoryIndex, Analyzer analyzer) {
+        super();
+        this.memoryIndex = memoryIndex;
+        this.analyzer = analyzer;
+    }
+
+    /**
+     * 
+     * @param title
+     * @param body
+     */
+    public void indexDocument(String title, String body) {
+
+        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
+        try {
+            IndexWriter writter = new IndexWriter(memoryIndex, indexWriterConfig);
+            Document document = new Document();
+
+            document.add(new TextField("title", title, Field.Store.YES));
+            document.add(new TextField("body", body, Field.Store.YES));
+            document.add(new SortedDocValuesField("title", new BytesRef(title)));
+
+            writter.addDocument(document);
+            writter.close();
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+    }
+
+    public List<Document> searchIndex(String inField, String queryString) {
+        try {
+            Query query = new QueryParser(inField, analyzer).parse(queryString);
+
+            IndexReader indexReader = DirectoryReader.open(memoryIndex);
+            IndexSearcher searcher = new IndexSearcher(indexReader);
+            TopDocs topDocs = searcher.search(query, 10);
+            List<Document> documents = new ArrayList<>();
+            for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
+                documents.add(searcher.doc(scoreDoc.doc));
+            }
+
+            return documents;
+        } catch (IOException | ParseException e) {
+            e.printStackTrace();
+        }
+        return null;
+
+    }
+
+    public void deleteDocument(Term term) {
+        try {
+            IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
+            IndexWriter writter = new IndexWriter(memoryIndex, indexWriterConfig);
+            writter.deleteDocuments(term);
+            writter.close();
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+    }
+
+    public List<Document> searchIndex(Query query) {
+        try {
+            IndexReader indexReader = DirectoryReader.open(memoryIndex);
+            IndexSearcher searcher = new IndexSearcher(indexReader);
+            TopDocs topDocs = searcher.search(query, 10);
+            List<Document> documents = new ArrayList<>();
+            for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
+                documents.add(searcher.doc(scoreDoc.doc));
+            }
+
+            return documents;
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+        return null;
+
+    }
+
+    public List<Document> searchIndex(Query query, Sort sort) {
+        try {
+            IndexReader indexReader = DirectoryReader.open(memoryIndex);
+            IndexSearcher searcher = new IndexSearcher(indexReader);
+            TopDocs topDocs = searcher.search(query, 10, sort);
+            List<Document> documents = new ArrayList<>();
+            for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
+                documents.add(searcher.doc(scoreDoc.doc));
+            }
+
+            return documents;
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+        return null;
+
+    }
+
+}

lucene/src/main/java/com/baeldung/lucene/LuceneFileSearch.java

@@ -0,0 +1,80 @@
+package com.baeldung.lucene;
+
+import java.io.File;
+import java.io.FileReader;
+import java.io.IOException;
+import java.net.URISyntaxException;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.document.StringField;
+import org.apache.lucene.document.TextField;
+import org.apache.lucene.index.DirectoryReader;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriterConfig;
+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.ScoreDoc;
+import org.apache.lucene.search.TopDocs;
+import org.apache.lucene.store.Directory;
+
+public class LuceneFileSearch {
+
+    private Directory indexDirectory;
+    private StandardAnalyzer analyzer;
+
+    public LuceneFileSearch(Directory fsDirectory, StandardAnalyzer analyzer) {
+        super();
+        this.indexDirectory = fsDirectory;
+        this.analyzer = analyzer;
+    }
+
+    public void addFileToIndex(String filepath) throws IOException, URISyntaxException {
+
+        Path path = Paths.get(getClass().getClassLoader().getResource(filepath).toURI());
+        File file = path.toFile();
+        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
+        IndexWriter indexWriter = new IndexWriter(indexDirectory, indexWriterConfig);
+        Document document = new Document();
+
+        FileReader fileReader = new FileReader(file);
+        document.add(new TextField("contents", fileReader));
+        document.add(new StringField("path", file.getPath(), Field.Store.YES));
+        document.add(new StringField("filename", file.getName(), Field.Store.YES));
+
+        indexWriter.addDocument(document);
+
+        indexWriter.close();
+    }
+
+    public List<Document> searchFiles(String inField, String queryString) {
+        try {
+            Query query = new QueryParser(inField, analyzer).parse(queryString);
+
+            IndexReader indexReader = DirectoryReader.open(indexDirectory);
+            IndexSearcher searcher = new IndexSearcher(indexReader);
+            TopDocs topDocs = searcher.search(query, 10);
+            List<Document> documents = new ArrayList<>();
+            for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
+                documents.add(searcher.doc(scoreDoc.doc));
+            }
+
+            return documents;
+        } catch (IOException | ParseException e) {
+            e.printStackTrace();
+        }
+        return null;
+
+    }
+
+}
+
+

lucene/src/main/java/com/baeldung/lucene/MyCustomAnalyzer.java

@@ -0,0 +1,26 @@
+package com.baeldung.lucene;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.LowerCaseFilter;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.en.PorterStemFilter;
+import org.apache.lucene.analysis.miscellaneous.CapitalizationFilter;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.analysis.standard.StandardFilter;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+
+public class MyCustomAnalyzer extends Analyzer{
+
+    @Override
+    protected TokenStreamComponents createComponents(String fieldName) {
+        final StandardTokenizer src = new StandardTokenizer();
+        TokenStream result = new StandardFilter(src);
+        result = new LowerCaseFilter(result);
+        result = new StopFilter(result,  StandardAnalyzer.STOP_WORDS_SET);
+        result = new PorterStemFilter(result);
+        result = new CapitalizationFilter(result);
+        return new TokenStreamComponents(src, result);
+    }
+
+}

lucene/src/main/resources/logback.xml

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configuration>
+    <appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
+        <encoder>
+            <pattern>%d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n
+            </pattern>
+        </encoder>
+    </appender>
+
+    <root level="INFO">
+        <appender-ref ref="STDOUT" />
+    </root>
+</configuration>