#9 & #10 support for .rtf and .doc files

pom.xml

@@ -51,6 +51,11 @@
 			<artifactId>poi-ooxml</artifactId>
 			<version>3.13</version>
 		</dependency>
+		<dependency>
+			<groupId>org.apache.poi</groupId>
+			<artifactId>poi-scratchpad</artifactId>
+			<version>3.13</version>
+		</dependency>
 		<dependency>
 			<groupId>org.apache.commons</groupId>
 			<artifactId>commons-lang3</artifactId>

src/main/java/com/cv/parser/CVparserMain.java

@@ -133,11 +133,11 @@ protected void createContents() {
 	pdf.main();
 	superList.addAll(pdf.getContents());
 
-	MSExtractor ms = new MSExtractor(filesInPublicDir);
+	MSExtractor ms = new MSExtractor();
 	ms.main();
 	superList.addAll(ms.getContents());
 
-	TXTExtractor txt = new TXTExtractor(filesInPublicDir);
+	TXTExtractor txt = new TXTExtractor();
 	txt.main();
 	superList.addAll(txt.getContents());
 

src/main/java/com/cv/parser/FileExtension.java

@@ -7,7 +7,7 @@ public FileExtension() {
     }
 
     public enum Ext {
-	PDF, DOC, DOCX, TXT
+	PDF, DOC, DOCX, TXT, RTF
     }
 
     public String get(Ext ext) {
@@ -20,6 +20,8 @@ public String get(Ext ext) {
 	    return ".docx";
 	case TXT:
 	    return ".txt";
+	case RTF:
+	    return ".rtf";
 	}
 	return null;
     }

src/main/java/com/cv/parser/extract/MSExtractor.java

@@ -2,11 +2,14 @@
 
 import java.io.File;
 import java.io.FileInputStream;
+import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
 
 import org.apache.commons.lang3.ArrayUtils;
+import org.apache.poi.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.extractor.WordExtractor;
 import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
 import org.apache.poi.xwpf.usermodel.XWPFDocument;
 import org.slf4j.Logger;
@@ -17,45 +20,38 @@
 import com.cv.parser.FileFinderByExt;
 
 /**
- * Supports MS Word 2004+.
+ * Supports MS Word 2004+ file extension .doc and .docx.
  * 
  * @author RAYMARTHINKPAD
  *
  */
 public class MSExtractor implements IExtractor {
     Logger logger = LoggerFactory.getLogger(MSExtractor.class);
 
-    FileExtension fe = new FileExtension();
-    FileFinderByExt find = new FileFinderByExt();
+    private FileExtension fileExtension = new FileExtension();
+    private FileFinderByExt fileFinderByExt = new FileFinderByExt();
 
-    File[] msDocs;
-    List<String> contents = new ArrayList<String>();
-
-    File[] filesInPublicDir;
-
-    public MSExtractor(File[] filesInPublicDir) {
-	this.filesInPublicDir = filesInPublicDir;
-    }
+    private File[] docxFiles;
+    private File[] docFiles;
+    private List<String> contents = new ArrayList<String>();
 
     public void main() {
 	setFiles();
 	extractFiles();
     }
 
     public void setFiles() {
-	File[] doc = find.finder(fe.get(Ext.DOC));
-	File[] docx = find.finder(fe.get(Ext.DOCX));
-	if (doc.length != 0 && docx.length != 0) {
-	    this.msDocs = ArrayUtils.addAll(doc, docx);
-	} else if (doc.length != 0) {
-	    this.msDocs = doc;
-	} else if (docx.length != 0) {
-	    this.msDocs = docx;
-	}
+	this.docxFiles = fileFinderByExt.finder(fileExtension.get(Ext.DOCX));
+	this.docFiles = fileFinderByExt.finder(fileExtension.get(Ext.DOC));
     }
 
     public void extractFiles() {
-	for (File file : msDocs) {
+	extractDocxFiles();
+	extractDocFiles();
+    }
+
+    public void extractDocxFiles() {
+	for (File file : docxFiles) {
 	    FileInputStream fs = null;
 	    XWPFDocument msDoc = null;
 	    XWPFWordExtractor we = null;
@@ -77,7 +73,22 @@ public void extractFiles() {
 	    }
 	}
     }
-
+
+    public void extractDocFiles() {
+	for (File file : docFiles) {
+	    HWPFDocument hwpfdoc;
+	    WordExtractor extractor;
+	    try {
+		hwpfdoc = new HWPFDocument(new FileInputStream(file));
+		extractor = new WordExtractor(hwpfdoc);
+		this.contents.add(extractor.getText());
+		extractor.close();
+	    } catch (IOException e) {
+		logger.info(e.getMessage());
+	    }
+	}
+    }
+
     public List<String> getContents() {
 	return contents;
     }

src/main/java/com/cv/parser/extract/RTFExtractor.java

@@ -0,0 +1,52 @@
+package com.cv.parser.extract;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import javax.swing.text.BadLocationException;
+import javax.swing.text.Document;
+import javax.swing.text.rtf.RTFEditorKit;
+
+import com.cv.parser.FileExtension;
+import com.cv.parser.FileExtension.Ext;
+import com.cv.parser.FileFinderByExt;
+
+public class RTFExtractor implements IExtractor {
+
+    private File[] files;
+    private List<String> contents = new ArrayList<>();
+
+    private FileExtension fileExtension = new FileExtension();
+    private FileFinderByExt fileFinderByExt = new FileFinderByExt();
+
+    @Override
+    public void main() {
+	setFiles();
+	extractFiles();
+    }
+
+    @Override
+    public void setFiles() {
+	this.files = fileFinderByExt.finder(fileExtension.get(Ext.RTF));
+    }
+
+    @Override
+    public void extractFiles() {
+	for (File file : files) {
+	    FileInputStream stream;
+	    try {
+		stream = new FileInputStream(file);
+		RTFEditorKit kit = new RTFEditorKit();
+		Document doc = kit.createDefaultDocument();
+		kit.read(stream, doc, 0);
+		String plainText = doc.getText(0, doc.getLength());
+		this.contents.add(plainText);
+	    } catch (IOException | BadLocationException e) {
+		e.printStackTrace();
+	    }
+	}
+    }
+}

src/main/java/com/cv/parser/extract/TXTExtractor.java

@@ -20,14 +20,8 @@ public class TXTExtractor implements IExtractor {
     private FileExtension fe = new FileExtension();
     private FileFinderByExt find = new FileFinderByExt();
 
-    File[] txtFiles;
-    List<String> contents = new ArrayList<String>();
-
-    File[] filesInPublicDir;
-
-    public TXTExtractor(File[] filesInPublicDir) {
-	this.filesInPublicDir = filesInPublicDir;
-    }
+    private File[] txtFiles;
+    private List<String> contents = new ArrayList<String>();
 
     public void main() {
 	setFiles();