refactoring, adding engine and documents representers

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

@@ -2,10 +2,10 @@ package com.search.lucene;
 
 import java.io.IOException;
 
-import com.search.lucene.file.filters.TextFileFilter;
-import com.search.lucene.indexers.TextFileIndexer;
-import com.search.lucene.searchers.TextFileSearcher;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.file.filters.implementations.TextFileFilter;
+import com.search.lucene.indexers.implementations.TextFileIndexer;
+import com.search.lucene.searchers.implementations.TextFileSearcher;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.queryparser.classic.ParseException;
 import org.apache.lucene.search.ScoreDoc;
@@ -31,10 +31,10 @@ public class Lucene {
     }
 
     private static void createIndex() throws IOException {
-        indexer = new TextFileIndexer(indexDir);
+        indexer = new TextFileIndexer(indexDir, new TextFileFilter());
         int numIndexed;
         long startTime = System.currentTimeMillis();
-        numIndexed = indexer.createIndex(dataDir, new TextFileFilter());
+        numIndexed = indexer.createIndex(dataDir);
         long endTime = System.currentTimeMillis();
         indexer.close();
         System.out.println(numIndexed+" File indexed, time taken: "
@@ -52,7 +52,7 @@ public class Lucene {
         for(ScoreDoc scoreDoc : hits.scoreDocs) {
             Document doc = textFileSearcher.getDocument(scoreDoc);
             System.out.println("File: "
-                    + doc.get(LuceneConstants.FILE_PATH));
+                    + doc.get(Constants.FILE_PATH));
         }
     }
 }

src/main/java/com/search/lucene/documents/representers/abstractions/IDocumentRepresenter.java

+package com.search.lucene.documents.representers.abstractions;
+
+import org.apache.lucene.document.Document;
+
+public interface IDocumentRepresenter<T> {
+    T Represent(Document indexedDocument);
+}

src/main/java/com/search/lucene/documents/representers/implementations/CSVDocumentStringRepresenter.java

+package com.search.lucene.documents.representers.implementations;
+
+import com.search.lucene.documents.representers.abstractions.IDocumentRepresenter;
+import org.apache.lucene.document.Document;
+
+public class CSVDocumentStringRepresenter implements IDocumentRepresenter<String> {
+    @Override
+    public String Represent(Document indexedDocument) {
+        return null;
+    }
+}

src/main/java/com/search/lucene/documents/representers/implementations/PDFDocumentStringRepresenter.java

+package com.search.lucene.documents.representers.implementations;
+
+import com.search.lucene.documents.representers.abstractions.IDocumentRepresenter;
+import org.apache.lucene.document.Document;
+
+public class PDFDocumentStringRepresenter implements IDocumentRepresenter<String> {
+    @Override
+    public String Represent(Document indexedDocument) {
+        return null;
+    }
+}

src/main/java/com/search/lucene/documents/representers/implementations/TextDocumentStringRepresenter.java

+package com.search.lucene.documents.representers.implementations;
+
+import com.search.lucene.documents.representers.abstractions.IDocumentRepresenter;
+import org.apache.lucene.document.Document;
+
+public class TextDocumentStringRepresenter implements IDocumentRepresenter<String> {
+    @Override
+    public String Represent(Document indexedDocument) {
+        return null;
+    }
+}

src/main/java/com/search/lucene/engine/abstractions/ISearchEngine.java

+package com.search.lucene.engine.abstractions;
+
+import org.apache.lucene.document.Document;
+import org.apache.lucene.queryparser.classic.ParseException;
+
+import java.io.IOException;
+import java.util.ArrayList;
+
+public interface ISearchEngine {
+    void createIndexForDirectory(String directoryPath) throws IOException;
+    ArrayList<Document> search(String searchQuery) throws IOException, ParseException;
+}

src/main/java/com/search/lucene/engine/implementations/LuceneEngine.java

+package com.search.lucene.engine.implementations;
+
+import com.search.lucene.engine.abstractions.ISearchEngine;
+import com.search.lucene.indexers.abstractions.IFileIndexer;
+import com.search.lucene.searchers.abstractions.ISearcher;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.queryparser.classic.ParseException;
+
+import java.io.IOException;
+import java.util.ArrayList;
+
+public class LuceneEngine implements ISearchEngine {
+    private final ArrayList<IFileIndexer> indexers;
+    private final ArrayList<ISearcher> searchers;
+
+    public LuceneEngine(ArrayList<IFileIndexer> indexers, ArrayList<ISearcher> searchers) {
+        this.indexers = indexers;
+        this.searchers = searchers;
+    }
+
+    @Override
+    public void createIndexForDirectory(String directoryPath) throws IOException {
+        for (var indexer : indexers){
+           indexer.createIndex(directoryPath);
+        }
+    }
+
+    @Override
+    public ArrayList<Document> search(String searchQuery) throws IOException, ParseException {
+        return null;
+    }
+}

src/main/java/com/search/lucene/file/filters/CSVFileFilter.java → src/main/java/com/search/lucene/file/filters/implementations/CSVFileFilter.java

-package com.search.lucene.file.filters;
+package com.search.lucene.file.filters.implementations;
 
 import com.search.lucene.file.filters.abstractions.IFileFilter;
 

src/main/java/com/search/lucene/file/filters/PDFFileFilter.java → src/main/java/com/search/lucene/file/filters/implementations/PDFFileFilter.java

-package com.search.lucene.file.filters;
+package com.search.lucene.file.filters.implementations;
 
 import com.search.lucene.file.filters.abstractions.IFileFilter;
 

src/main/java/com/search/lucene/file/filters/TextFileFilter.java → src/main/java/com/search/lucene/file/filters/implementations/TextFileFilter.java

-package com.search.lucene.file.filters;
+package com.search.lucene.file.filters.implementations;
 
 import com.search.lucene.file.filters.abstractions.IFileFilter;
 

src/main/java/com/search/lucene/indexers/abstractions/IFileIndexer.java

@@ -4,5 +4,5 @@ import java.io.FileFilter;
 import java.io.IOException;
 
 public interface IFileIndexer {
-    int createIndex(String dataDirectoryPath, FileFilter filter) throws IOException;
+    int createIndex(String dataDirectoryPath) throws IOException;
 }

src/main/java/com/search/lucene/indexers/CSVFileIndexer.java → src/main/java/com/search/lucene/indexers/implementations/CSVFileIndexer.java

-package com.search.lucene.indexers;
+package com.search.lucene.indexers.implementations;
 
 import com.opencsv.CSVReader;
+import com.search.lucene.file.filters.abstractions.IFileFilter;
 import com.search.lucene.indexers.abstractions.IFileIndexer;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
@@ -23,8 +24,10 @@ import java.util.ArrayList;
 
 public class CSVFileIndexer implements IFileIndexer {
     private final IndexWriter writer;
+    private final IFileFilter filter;
 
-    public CSVFileIndexer(String indexDirectoryPath) throws IOException {
+    public CSVFileIndexer(String indexDirectoryPath, IFileFilter filter) throws IOException {
+        this.filter = filter;
         //this directory will contain the indexes
         Directory indexDirectory =
                 FSDirectory.open(Paths.get(indexDirectoryPath));
@@ -53,11 +56,11 @@ public class CSVFileIndexer implements IFileIndexer {
             for (int i = 0; i < nextRecord.length; i++) {
                 Document document = new Document();
 
-                document.add(new TextField(LuceneConstants.COLUMN, columns[i], Field.Store.YES));
-                document.add(new TextField(LuceneConstants.VALUE, nextRecord[i], Field.Store.YES));
-                document.add(new TextField(LuceneConstants.LINE, Integer.toString(line), Field.Store.YES));
-                document.add(new StringField(LuceneConstants.FILE_PATH, file.getCanonicalPath(), Field.Store.YES));
-                document.add(new StringField(LuceneConstants.FILE_NAME, file.getName(), Field.Store.YES));
+                document.add(new TextField(Constants.COLUMN, columns[i], Field.Store.YES));
+                document.add(new TextField(Constants.VALUE, nextRecord[i], Field.Store.YES));
+                document.add(new TextField(Constants.ROW, Integer.toString(line), Field.Store.YES));
+                document.add(new StringField(Constants.FILE_PATH, file.getCanonicalPath(), Field.Store.YES));
+                document.add(new StringField(Constants.FILE_NAME, file.getName(), Field.Store.YES));
                 documents.add(document);
                 System.out.print(nextRecord[i] + "\t");
             }
@@ -76,7 +79,7 @@ public class CSVFileIndexer implements IFileIndexer {
     }
 
     @Override
-    public int createIndex(String dataDirectoryPath, FileFilter filter)
+    public int createIndex(String dataDirectoryPath)
             throws IOException {
         File[] files = new File(dataDirectoryPath).listFiles();
 

src/main/java/com/search/lucene/indexers/PDFFileIndexer.java → src/main/java/com/search/lucene/indexers/implementations/PDFFileIndexer.java

-package com.search.lucene.indexers;
+package com.search.lucene.indexers.implementations;
 
+import com.search.lucene.file.filters.abstractions.IFileFilter;
 import com.search.lucene.indexers.abstractions.IFileIndexer;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.TextField;
@@ -17,18 +18,18 @@ import org.apache.pdfbox.text.PDFTextStripper;
 
 import java.io.File;
 import java.io.FileFilter;
-import java.io.FileReader;
 import java.io.IOException;
 import java.nio.file.Paths;
 
 public class PDFFileIndexer implements IFileIndexer {
     private final IndexWriter writer;
+    private final IFileFilter filter;
 
-    public PDFFileIndexer(String indexDirectoryPath) throws IOException {
+    public PDFFileIndexer(String indexDirectoryPath, IFileFilter fileFilter) throws IOException {
         //this directory will contain the indexes
         Directory indexDirectory =
                 FSDirectory.open(Paths.get(indexDirectoryPath));
-
+        this.filter = fileFilter;
         //create the indexer
         writer = new IndexWriter(indexDirectory, new IndexWriterConfig(new StandardAnalyzer()));
     }
@@ -42,9 +43,9 @@ public class PDFFileIndexer implements IFileIndexer {
         PDDocument pdDocument = PDDocument.load(file);
         String content = new PDFTextStripper().getText(pdDocument);
         Document document = new Document();
-        document.add(new TextField(LuceneConstants.CONTENTS, content, Field.Store.YES));
-        document.add(new StringField(LuceneConstants.FILE_PATH, file.getCanonicalPath(), Field.Store.YES));
-        document.add(new StringField(LuceneConstants.FILE_NAME, file.getName(), Field.Store.YES));
+        document.add(new TextField(Constants.CONTENTS, content, Field.Store.YES));
+        document.add(new StringField(Constants.FILE_PATH, file.getCanonicalPath(), Field.Store.YES));
+        document.add(new StringField(Constants.FILE_NAME, file.getName(), Field.Store.YES));
         writer.addDocument(document);
         pdDocument.close();
 
@@ -58,7 +59,7 @@ public class PDFFileIndexer implements IFileIndexer {
     }
 
     @Override
-    public int createIndex(String dataDirectoryPath, FileFilter filter)
+    public int createIndex(String dataDirectoryPath)
             throws IOException {
         File[] files = new File(dataDirectoryPath).listFiles();
 

src/main/java/com/search/lucene/indexers/TextFileIndexer.java → src/main/java/com/search/lucene/indexers/implementations/TextFileIndexer.java

-package com.search.lucene.indexers;
+package com.search.lucene.indexers.implementations;
 
 import java.io.File;
 import java.io.FileFilter;
@@ -6,8 +6,9 @@ import java.io.FileReader;
 import java.io.IOException;
 import java.nio.file.Paths;
 
+import com.search.lucene.file.filters.abstractions.IFileFilter;
 import com.search.lucene.indexers.abstractions.IFileIndexer;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.TextField;
@@ -19,8 +20,10 @@ import org.apache.lucene.store.FSDirectory;
 
 public class TextFileIndexer implements IFileIndexer {
     private final IndexWriter writer;
+    private final IFileFilter filter;
 
-    public TextFileIndexer(String indexDirectoryPath) throws IOException {
+    public TextFileIndexer(String indexDirectoryPath, IFileFilter filter) throws IOException {
+        this.filter = filter;
         //this directory will contain the indexes
         Directory indexDirectory =
                 FSDirectory.open(Paths.get(indexDirectoryPath));
@@ -36,12 +39,12 @@ public class TextFileIndexer implements IFileIndexer {
     private Document getDocument(File file) throws IOException {
         Document document = new Document();
 
-        TextField contentField = new TextField(LuceneConstants.CONTENTS, new FileReader(file));
+        TextField contentField = new TextField(Constants.CONTENTS, new FileReader(file));
 
-        TextField fileNameField = new TextField(LuceneConstants.FILE_NAME,
+        TextField fileNameField = new TextField(Constants.FILE_NAME,
                 file.getName(),TextField.Store.YES);
 
-        TextField filePathField = new TextField(LuceneConstants.FILE_PATH,
+        TextField filePathField = new TextField(Constants.FILE_PATH,
                 file.getCanonicalPath(),TextField.Store.YES);
 
         document.add(contentField);
@@ -58,7 +61,7 @@ public class TextFileIndexer implements IFileIndexer {
     }
 
     @Override
-    public int createIndex(String dataDirectoryPath, FileFilter filter)
+    public int createIndex(String dataDirectoryPath)
             throws IOException {
         File[] files = new File(dataDirectoryPath).listFiles();
 

src/main/java/com/search/lucene/searchers/CSVFileSearcher.java → src/main/java/com/search/lucene/searchers/implementations/CSVFileSearcher.java

-package com.search.lucene.searchers;
+package com.search.lucene.searchers.implementations;
 
 import com.search.lucene.searchers.abstractions.ISearcher;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.index.CorruptIndexException;
@@ -31,7 +31,7 @@ public class CSVFileSearcher implements ISearcher {
                 FSDirectory.open(Paths.get(indexDirectoryPath));
         IndexReader reader = DirectoryReader.open(indexDirectory);
         indexSearcher = new IndexSearcher(reader);
-        queryParser = new QueryParser(LuceneConstants.CONTENTS,
+        queryParser = new QueryParser(Constants.CONTENTS,
                 new StandardAnalyzer());
     }
 
@@ -39,7 +39,7 @@ public class CSVFileSearcher implements ISearcher {
     public TopDocs search( String searchQuery)
             throws IOException, ParseException {
         query = queryParser.parse(searchQuery);
-        return indexSearcher.search(query, LuceneConstants.MAX_SEARCH);
+        return indexSearcher.search(query, Constants.MAX_SEARCH);
     }
     @Override
     public Document getDocument(ScoreDoc scoreDoc)

src/main/java/com/search/lucene/searchers/PDFFileSearcher.java → src/main/java/com/search/lucene/searchers/implementations/PDFFileSearcher.java

-package com.search.lucene.searchers;
+package com.search.lucene.searchers.implementations;
 
 import com.search.lucene.searchers.abstractions.ISearcher;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.index.CorruptIndexException;
@@ -31,15 +31,15 @@ public class PDFFileSearcher implements ISearcher {
                 FSDirectory.open(Paths.get(indexDirectoryPath));
         IndexReader reader = DirectoryReader.open(indexDirectory);
         indexSearcher = new IndexSearcher(reader);
-        queryParser = new QueryParser(LuceneConstants.CONTENTS,
+        queryParser = new QueryParser(Constants.CONTENTS,
                 new StandardAnalyzer());
     }
 
     @Override
-    public TopDocs search( String searchQuery)
+    public TopDocs search(String searchQuery)
             throws IOException, ParseException {
         query = queryParser.parse(searchQuery);
-        return indexSearcher.search(query, LuceneConstants.MAX_SEARCH);
+        return indexSearcher.search(query, Constants.MAX_SEARCH);
     }
     @Override
     public Document getDocument(ScoreDoc scoreDoc)

src/main/java/com/search/lucene/searchers/TextFileSearcher.java → src/main/java/com/search/lucene/searchers/implementations/TextFileSearcher.java

-package com.search.lucene.searchers;
+package com.search.lucene.searchers.implementations;
 
 import java.io.IOException;
 import java.nio.file.Paths;
 
 import com.search.lucene.searchers.abstractions.ISearcher;
-import com.search.lucene.settings.LuceneConstants;
+import com.search.lucene.settings.Constants;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.index.CorruptIndexException;
@@ -31,20 +31,19 @@ public class TextFileSearcher implements ISearcher {
                 FSDirectory.open(Paths.get(indexDirectoryPath));
         IndexReader reader = DirectoryReader.open(indexDirectory);
         indexSearcher = new IndexSearcher(reader);
-        queryParser = new QueryParser(LuceneConstants.CONTENTS,
+        queryParser = new QueryParser(Constants.CONTENTS,
                 new StandardAnalyzer());
     }
 
     @Override
-    public TopDocs search( String searchQuery)
+    public TopDocs search(String searchQuery)
             throws IOException, ParseException {
         query = queryParser.parse(searchQuery);
-        return indexSearcher.search(query, LuceneConstants.MAX_SEARCH);
+        return indexSearcher.search(query, Constants.MAX_SEARCH);
     }
     @Override
     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/settings/Constants.java

 package com.search.lucene.settings;
 
 
-public class LuceneConstants {
+public class Constants {
     public static final String CONTENTS = "contents";
+    public static final String INDEXED_FROM_FILE_FORMAT = "from_format";
     public static final String FILE_NAME = "filename";
     public static final String FILE_PATH = "filepath";
     public static final String COLUMN = "column";

src/main/java/com/search/lucene/settings/IndexType.java

+package com.search.lucene.settings;
+
+public enum IndexType {
+    CSV,
+    PDF,
+    TEXT
+}