Project setup

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml

.idea/compiler.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="CompilerConfiguration">
+    <annotationProcessing>
+      <profile name="Maven default annotation processors profile" enabled="true">
+        <sourceOutputDir name="target/generated-sources/annotations" />
+        <sourceTestOutputDir name="target/generated-test-sources/test-annotations" />
+        <outputRelativeToContentRoot value="true" />
+        <module name="lucene" />
+      </profile>
+    </annotationProcessing>
+  </component>
+</project>
\ No newline at end of file

.idea/encodings.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding">
+    <file url="file://$PROJECT_DIR$/src/main/java" charset="UTF-8" />
+    <file url="file://$PROJECT_DIR$/src/main/resources" charset="UTF-8" />
+  </component>
+</project>
\ No newline at end of file

.idea/jarRepositories.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="RemoteRepositoriesConfiguration">
+    <remote-repository>
+      <option name="id" value="central" />
+      <option name="name" value="Central Repository" />
+      <option name="url" value="https://repo.maven.apache.org/maven2" />
+    </remote-repository>
+    <remote-repository>
+      <option name="id" value="central" />
+      <option name="name" value="Maven Central repository" />
+      <option name="url" value="https://repo1.maven.org/maven2" />
+    </remote-repository>
+    <remote-repository>
+      <option name="id" value="jboss.community" />
+      <option name="name" value="JBoss Community repository" />
+      <option name="url" value="https://repository.jboss.org/nexus/content/repositories/public/" />
+    </remote-repository>
+  </component>
+</project>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ExternalStorageConfigurationManager" enabled="true" />
+  <component name="MavenProjectsManager">
+    <option name="originalFiles">
+      <list>
+        <option value="$PROJECT_DIR$/pom.xml" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_21" default="true" project-jdk-name="21" project-jdk-type="JavaSDK" />
+</project>
\ No newline at end of file

data/1.txt

+s1,Movie,Dick Johnson Is Dead,Kirsten Johnson,,United States,25-Sep-21,2020,PG-13,90 min,Documentaries,"As her father nears the end of his life, filmmaker Kirsten Johnson stages his death in inventive and comical ways to help them both face the inevitable."
\ No newline at end of file

data/2.txt

+s2,TV Show,Blood & Water,,"Ama Qamata, Khosi Ngema, Gail Mabalane, Thabang Molaba, Dillon Windvogel, Natasha Thahane, Arno Greeff, Xolile Tshabalala, Getmore Sithole, Cindy Mahlangu, Ryle De Morny, Greteli Fincham, Sello Maake Ka-Ncube, Odwa Gwanya, Mekaila Mathys, Sandi Schultz, Duane Williams, Shamilla Miller, Patrick Mofokeng",South Africa,24-Sep-21,2021,TV-MA,2 Seasons,"International TV Shows, TV Dramas, TV Mysteries","After crossing paths at a party, a Cape Town teen sets out to prove whether a private-school swimming star is her sister who was abducted at birth."
\ No newline at end of file

data/3.txt

+s3,TV Show,Ganglands,Julien Leclercq,"Sami Bouajila, Tracy Gotoas, Samuel Jouy, Nabiha Akkari, Sofia Lesaffre, Salim Kechiouche, Noureddine Farihi, Geert Van Rampelberg, Bakary Diombera",,24-Sep-21,2021,TV-MA,1 Season,"Crime TV Shows, International TV Shows, TV Action & Adventure","To protect his family from a powerful drug lord, skilled thief Mehdi and his expert team of robbers are pulled into a violent and deadly turf war."
\ No newline at end of file

data/4.txt

+s4,TV Show,Jailbirds New Orleans,,,,24-Sep-21,2021,TV-MA,1 Season,"Docuseries, Reality TV","Feuds, flirtations and toilet talk go down among the incarcerated women at the Orleans Justice Center in New Orleans on this gritty reality series."
\ No newline at end of file

data/5.txt

+s5,TV Show,Kota Factory,,"Mayur More, Jitendra Kumar, Ranjan Raj, Alam Khan, Ahsaas Channa, Revathi Pillai, Urvi Singh, Arun Kumar",India,24-Sep-21,2021,TV-MA,2 Seasons,"International TV Shows, Romantic TV Shows, TV Comedies","In a city of coaching centers known to train India’s finest collegiate minds, an earnest but unexceptional student and his friends navigate campus life."
\ No newline at end of file

data/6.txt

+s6,TV Show,Midnight Mass,Mike Flanagan,"Kate Siegel, Zach Gilford, Hamish Linklater, Henry Thomas, Kristin Lehman, Samantha Sloyan, Igby Rigney, Rahul Kohli, Annarah Cymone, Annabeth Gish, Alex Essoe, Rahul Abburi, Matt Biedel, Michael Trucco, Crystal Balint, Louis Oliver",,24-Sep-21,2021,TV-MA,1 Season,"TV Dramas, TV Horror, TV Mysteries","The arrival of a charismatic young priest brings glorious miracles, ominous mysteries and renewed religious fervor to a dying town desperate to believe."
\ No newline at end of file

data/7.txt

+s7,Movie,My Little Pony: A New Generation,"Robert Cullen, José Luis Ucha","Vanessa Hudgens, Kimiko Glenn, James Marsden, Sofia Carson, Liza Koshy, Ken Jeong, Elizabeth Perkins, Jane Krakowski, Michael McKean, Phil LaMarr",,24-Sep-21,2021,PG,91 min,Children & Family Movies,"Equestria's divided. But a bright-eyed hero believes Earth Ponies, Pegasi and Unicorns should be pals — and, hoof to heart, she’s determined to prove it."
\ No newline at end of file

data/8.txt

+s8,Movie,Sankofa,Haile Gerima,"Kofi Ghanaba, Oyafunmike Ogunlano, Alexandra Duah, Nick Medley, Mutabaruka, Afemo Omilami, Reggie Carter, Mzuri","United States, Ghana, Burkina Faso, United Kingdom, Germany, Ethiopia",24-Sep-21,1993,TV-MA,125 min,"Dramas, Independent Movies, International Movies","On a photo shoot in Ghana, an American model slips back in time, becomes enslaved on a plantation and bears witness to the agony of her ancestral past."
\ No newline at end of file

pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>com.search</groupId>
+    <artifactId>lucene</artifactId>
+    <version>1.0-SNAPSHOT</version>
+    <packaging>jar</packaging>
+    <properties>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+        <maven.compiler.source>17</maven.compiler.source>
+        <maven.compiler.target>17</maven.compiler.target>
+        <exec.mainClass>com.search.lucene.Lucene</exec.mainClass>
+    </properties>
+    <dependencies>
+        <dependency>
+            <groupId>org.apache.lucene</groupId>          
+            <artifactId>lucene-core</artifactId>
+            <version>9.10.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.lucene</groupId>
+            <artifactId>lucene-queryparser</artifactId>
+            <version>9.10.0</version>
+        </dependency>
+    </dependencies>
+</project>
\ No newline at end of file

src/main/java/com/search/lucene/Indexer.java

+package com.search.lucene;
+
+import java.io.File;
+import java.io.FileFilter;
+import java.io.FileReader;
+import java.io.IOException;
+import java.nio.file.Paths;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.TextField;
+import org.apache.lucene.index.CorruptIndexException;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.FSDirectory;
+
+public class Indexer {
+
+    private IndexWriter writer;
+
+    public Indexer(String indexDirectoryPath) throws IOException {
+        //this directory will contain the indexes
+        Directory indexDirectory =
+                FSDirectory.open(Paths.get(indexDirectoryPath));
+
+        //create the indexer
+        writer = new IndexWriter(indexDirectory, new IndexWriterConfig(new StandardAnalyzer()));
+    }
+
+    public void close() throws CorruptIndexException, IOException {
+        writer.close();
+    }
+
+    private Document getDocument(File file) throws IOException {
+        Document document = new Document();
+
+        TextField contentField = new TextField(LuceneConstants.CONTENTS, new FileReader(file));
+        TextField fileNameField = new TextField(LuceneConstants.FILE_NAME,
+                file.getName(),TextField.Store.YES);
+        TextField filePathField = new TextField(LuceneConstants.FILE_PATH,
+                file.getCanonicalPath(),TextField.Store.YES);
+
+        document.add(contentField);
+        document.add(fileNameField);
+        document.add(filePathField);
+
+        return document;
+    }
+
+    private void indexFile(File file) throws IOException {
+        System.out.println("Indexing "+file.getCanonicalPath());
+        Document document = getDocument(file);
+        writer.addDocument(document);
+    }
+
+    public int createIndex(String dataDirPath, FileFilter filter)
+            throws IOException {
+        File[] files = new File(dataDirPath).listFiles();
+
+        for (File file : files) {
+            if(!file.isDirectory()
+                    && !file.isHidden()
+                    && file.exists()
+                    && file.canRead()
+                    && filter.accept(file)
+            ){
+                indexFile(file);
+            }
+        }
+        return writer.numRamDocs();
+    }
+}
\ No newline at end of file

src/main/java/com/search/lucene/Lucene.java

+package com.search.lucene;
+
+import java.io.IOException;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.queryparser.classic.ParseException;
+import org.apache.lucene.search.ScoreDoc;
+import org.apache.lucene.search.TopDocs;
+
+public class Lucene {
+
+    private static final String indexDir = "index";
+    private static final String dataDir = "data";
+    private static Indexer indexer;
+    private static Searcher searcher;
+
+    public static void main(String[] args) {
+        try {
+            createIndex();
+            search("Kota");
+        } catch (IOException e) {
+            e.printStackTrace();
+        } catch (ParseException e) {
+            e.printStackTrace();
+        }
+    }
+
+    private static void createIndex() throws IOException {
+        indexer = new Indexer(indexDir);
+        int numIndexed;
+        long startTime = System.currentTimeMillis();
+        numIndexed = indexer.createIndex(dataDir, new TextFileFilter());
+        long endTime = System.currentTimeMillis();
+        indexer.close();
+        System.out.println(numIndexed+" File indexed, time taken: "
+                +(endTime-startTime)+" ms");
+    }
+
+    private static void search(String searchQuery) throws IOException, ParseException {
+        searcher = new Searcher(indexDir);
+        long startTime = System.currentTimeMillis();
+        TopDocs hits = searcher.search(searchQuery);
+        long endTime = System.currentTimeMillis();
+
+        System.out.println(hits.totalHits +
+                " documents found. Time :" + (endTime - startTime));
+        for(ScoreDoc scoreDoc : hits.scoreDocs) {
+            Document doc = searcher.getDocument(scoreDoc);
+            System.out.println("File: "
+                    + doc.get(LuceneConstants.FILE_PATH));
+        }
+    }
+}

src/main/java/com/search/lucene/LuceneConstants.java

+package com.search.lucene;
+
+
+public class LuceneConstants {
+    public static final String CONTENTS = "contents";
+    public static final String FILE_NAME = "filename";
+    public static final String FILE_PATH = "filepath";
+    public static final int MAX_SEARCH = 10;
+}
+

src/main/java/com/search/lucene/Searcher.java

+package com.search.lucene;
+
+import java.io.IOException;
+import java.nio.file.Paths;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.index.CorruptIndexException;
+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.ScoreDoc;
+import org.apache.lucene.search.TopDocs;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.FSDirectory;
+
+public class Searcher {
+
+    IndexSearcher indexSearcher;
+    QueryParser queryParser;
+    Query query;
+
+    public Searcher(String indexDirectoryPath)
+            throws IOException {
+        Directory indexDirectory =
+                FSDirectory.open(Paths.get(indexDirectoryPath));
+        IndexReader reader = DirectoryReader.open(indexDirectory);
+        indexSearcher = new IndexSearcher(reader);
+        queryParser = new QueryParser(LuceneConstants.CONTENTS,
+                new StandardAnalyzer());
+    }
+
+    public TopDocs search( String searchQuery)
+            throws IOException, ParseException {
+        query = queryParser.parse(searchQuery);
+        return indexSearcher.search(query, LuceneConstants.MAX_SEARCH);
+    }
+
+    public Document getDocument(ScoreDoc scoreDoc)
+            throws CorruptIndexException, IOException {
+        return indexSearcher.doc(scoreDoc.doc);
+    }
+
+}
\ No newline at end of file

src/main/java/com/search/lucene/TextFileFilter.java

+package com.search.lucene;
+
+import java.io.File;
+import java.io.FileFilter;
+
+public class TextFileFilter implements FileFilter {
+
+    @Override
+    public boolean accept(File pathname) {
+        return pathname.getName().toLowerCase().endsWith(".txt");
+    }
+}
\ No newline at end of file

target/maven-archiver/pom.properties

+#Generated by Maven
+#Sun Mar 17 00:54:55 AST 2024
+groupId=com.search
+artifactId=lucene
+version=1.0-SNAPSHOT

target/maven-status/maven-compiler-plugin/compile/default-compile/createdFiles.lst

+com\search\lucene\Lucene.class

target/maven-status/maven-compiler-plugin/compile/default-compile/inputFiles.lst

+D:\hiast\5th\IR\1\lucene\src\main\java\com\search\lucene\Lucene.java