groupdocs-parser · usman-aziz · Sep 10, 2018 · Sep 10, 2018
diff --git a/Examples/Data/Source/sample.sqlite b/Examples/Data/Source/sample.sqlite
diff --git a/Examples/pom.xml b/Examples/pom.xml
@@ -42,7 +42,12 @@
 		<dependency>
 			<groupId>com.groupdocs</groupId>
 			<artifactId>groupdocs-parser</artifactId>
-			<version>18.7</version>
+			<version>18.9</version>
+		</dependency>
+		<dependency>
+			<groupId>org.xerial</groupId>
+			<artifactId>sqlite-jdbc</artifactId>
+			<version>3.23.1</version>
 		</dependency>
 	</dependencies>
 	<repositories>

diff --git a/Examples/src/main/java/com/groupdocs/parser/examples/Common.java b/Examples/src/main/java/com/groupdocs/parser/examples/Common.java
@@ -96,4 +96,15 @@ public static void useDynabicMeteredAccount() {
 
 	}
 
+	// gets connection string
+	public static String getConnectionString(String inputFileName) {
+		try {
+			String connectionString = "jdbc:sqlite:" + STORAGE_PATH + "/" + inputFileName;
+			return connectionString;
+		} catch (Exception e) {
+			e.printStackTrace();
+			return e.getMessage();
+		}
+	}
+
 }
diff --git a/Examples/src/main/java/com/groupdocs/parser/examples/Containers.java b/Examples/src/main/java/com/groupdocs/parser/examples/Containers.java
@@ -1,10 +1,12 @@
 package com.groupdocs.parser.examples;
 
+import java.io.BufferedReader;
 import java.io.InputStream;
 
 import com.groupdocs.parser.CellsMediaTypeDetector;
 import com.groupdocs.parser.Container;
 import com.groupdocs.parser.ContainerEnumerator;
+import com.groupdocs.parser.DbContainer;
 import com.groupdocs.parser.EmailConnectionInfo;
 import com.groupdocs.parser.EmailContainer;
 import com.groupdocs.parser.EmailTextExtractor;
@@ -22,7 +24,7 @@ public class Containers {
 	// ExStart:SourceOSTDocumentFilePath
 	private final static String OST_FILE_PATH = "sample.ost";
 	private final static String ZIP_FILE_PATH = "sample.zip";
-
+	private final static String DB_FILE_PATH = "sample.sqlite";
 	// ExEnd:SourceOSTZIPDocumentFilePath
 	/**
 	 * Creates containers
@@ -347,4 +349,52 @@ public static void retrieveAllEntitiesInZIPArchiveByName() {
 			exp.printStackTrace();
 		}
 	}
+
+	/**
+	 * Reads text from database
+	 * 
+	 */
+	public static void extractTextFromDatabase() {
+		try {
+			// ExStart:extractTextFromDatabase_18.9
+			String connectionString = Common.getConnectionString(DB_FILE_PATH);
+			DbContainer container = new DbContainer(java.sql.DriverManager.getConnection(connectionString));
+			try  {
+				// Iterate over entities
+				for (Container.Entity entity : container.getEntities()) {
+					// Print a table name
+					System.out.println(entity.getName());
+					// Print a media type
+					System.out.println(entity.getMediaType());
+					// Create a stream reader for CSV document: OpenStream
+					// method converts a table to the CSV file and returns it as
+					// Stream
+					java.io.InputStreamReader reader = new java.io.InputStreamReader(entity.openStream());
+					try {
+						BufferedReader br = new BufferedReader(reader);
+
+						// Read a line
+						String line = br.readLine();
+						// Loop to the end of the file
+						while (line != null) {
+							// Print a line from the document
+							System.out.println(line);
+							// Read the next line
+							line = br.readLine();
+						}
+					} finally {
+						reader.close();
+					}
+
+				}
+			} finally {
+				container.dispose();
+			}
+			// ExEnd:extractTextFromDatabase_18.9
+		} catch (Exception exp) {
+			System.out.println("Exception: " + exp.getMessage());
+			exp.printStackTrace();
+		}
+	}
+
 }
diff --git a/Examples/src/main/java/com/groupdocs/parser/examples/MainClass.java b/Examples/src/main/java/com/groupdocs/parser/examples/MainClass.java
@@ -15,6 +15,7 @@
 import com.groupdocs.parser.examples.TextFormatters.Markdown;
 import com.groupdocs.parser.examples.TextFormatters.PlainText;
 import com.groupdocs.parser.examples.Tools.EncodingDetector;
+import com.groupdocs.parser.examples.Tools.Indexer;
 import com.groupdocs.parser.examples.Tools.Loggers;
 import com.groupdocs.parser.examples.Tools.MediaTypeDetectors;
 
@@ -92,6 +93,7 @@ public static void main(String[] args) throws Throwable {
 		//// Working with PDF documents
 		// PDFDocuments.extractTextAsWhole();
 		// PDFDocuments.extractTextByLines();
+		//PDFDocuments.extractDataFromPDFForms();
 
 		//// Working with OneNote documents
 		// OneNoteDocuments.extractTextAsWhole();
@@ -144,20 +146,30 @@ public static void main(String[] args) throws Throwable {
 		// MediaTypeDetectors.detectMediaTypeByContent();
 		// MediaTypeDetectors.detectMediaTypeByExtension();
 		// MediaTypeDetectors.IsMediaTypeSupportedByDetector();
-
+
+		// This feature allows providing a password for protected documents on-demand
+		//ExStart:requestPasswordForProtectedDocument_usage_18.9
+		// Indexer indexer = new Indexer();
+		// indexer.process(new java.io.File(Common.STORAGE_PATH.toString()));
+		//ExEnd:requestPasswordForProtectedDocument_usage_18.9
+
 		//// Containers
 		// Containers.createEmailConnectionInfo();
 		// Containers.enumerateAllEntitiesOfGroupOfContainers();
 		// Containers.extractMessagesFromOST();
 		// Containers.getListOfEmailsFromEWS();
 		// Containers.retrieveAnEmailFromEWS();
+		//Containers.extractTextFromDatabase();
 
 		//// Structured handlers
 		// StructuredHandlers.Headers hd = new Headers();
-		// hd.extractHeader(new java.io.FileInputStream(Common.mapSourceFilePath("sample.docx")));
-
-		// StructuredHandlers.Hyperlinks hl = new StructuredHandlers.Hyperlinks();
-		// hl.extract(new java.io.FileInputStream(Common.mapSourceFilePath("sample.docx")));
+		// hd.extractHeader(new
+		//// java.io.FileInputStream(Common.mapSourceFilePath("sample.docx")));
+
+		// StructuredHandlers.Hyperlinks hl = new
+		// StructuredHandlers.Hyperlinks();
+		// hl.extract(new
+		// java.io.FileInputStream(Common.mapSourceFilePath("sample.docx")));
 
 		System.out.println("Operation Completed...");
 	}

diff --git a/Examples/src/main/java/com/groupdocs/parser/examples/TextExtractors/PDFDocuments.java b/Examples/src/main/java/com/groupdocs/parser/examples/TextExtractors/PDFDocuments.java
@@ -54,4 +54,33 @@ public static void extractTextByLines() {
 		}
 	}
 
+	/**
+	 * Extracts data from PDF forms.
+	 * 
+	 */
+	public static void extractDataFromPDFForms() {
+		try {
+			// ExStart:extractDataFromPDFForms_18.9
+			// Create a text extractor for PDF documents
+			PdfTextExtractor extractor = new PdfTextExtractor(Common.mapSourceFilePath(FILE_PATH));
+			try {
+				// Extract forms data
+				java.util.Dictionary<String, String> fields = extractor.getFormData();
+				// Iterate over fields
+				java.util.Enumeration<String> e = fields.keys();
+				while (e.hasMoreElements()) {
+					String key = e.nextElement();
+					// Print field name and value
+					System.out.println(String.format("%s: %s", key, fields.get(key)));
+				}
+			} finally {
+				extractor.dispose();
+			}
+			// ExEnd:extractDataFromPDFForms_18.9
+		} catch (Exception exp) {
+			System.out.println("Exception: " + exp.getMessage());
+			exp.printStackTrace();
+		}
+	}
+
 }
diff --git a/...les/src/main/java/com/groupdocs/parser/examples/TextExtractors/PresentationDocuments.java b/...les/src/main/java/com/groupdocs/parser/examples/TextExtractors/PresentationDocuments.java
@@ -1,8 +1,11 @@
 package com.groupdocs.parser.examples.TextExtractors;
 
 import com.groupdocs.parser.MarkdownDocumentFormatter;
+import com.groupdocs.parser.Rectangle;
 import com.groupdocs.parser.SlidesFormattedTextExtractor;
 import com.groupdocs.parser.SlidesTextExtractor;
+import com.groupdocs.parser.TextArea;
+import com.groupdocs.parser.TextAreaSearchOptions;
 import com.groupdocs.parser.examples.Common;
 
 public class PresentationDocuments {
@@ -76,5 +79,37 @@ public static void extractFormattedText() {
 			exp.printStackTrace();
 		}
 	}
+
+	/**
+	 *  Extracts a text area from a presentation document.
+	 * 
+	 */
+	public static void extractTextAreaFromPresentationDocument() {
+		try {
+			// ExStart:ExtractTextAreaFromPresentationDocument_18.9
+			// Create a text extractor for presentations
+			try (SlidesTextExtractor  extractor = new SlidesTextExtractor (
+					Common.mapOutputFilePath(FILE_PATH))) {
+				// Create search options
+				TextAreaSearchOptions searchOptions = new TextAreaSearchOptions();
+				// Set a regular expression to search 'Published: XXXX.XX.XX' text
+				searchOptions.setExpression("\\s?Published\\:\\s?[0-9]{4}\\.[0-9]{2}\\.[0-9]{2}");
+				// Limit the search with a rectangle
+				searchOptions.setRectangle(new Rectangle(10, 10, 300, 150));
+
+				// Get text areas
+				java.util.List<TextArea> texts = extractor.getDocumentContent().getTextAreas(0, searchOptions);
+
+				for (TextArea area : texts) {
+				    // Print a text
+				    System.out.println(area.getText());
+				}
+			}
+			// ExEnd:ExtractTextAreaFromPresentationDocument_18.9
+		} catch (Exception exp) {
+			System.out.println("Exception: " + exp.getMessage());
+			exp.printStackTrace();
+		}
+	}
 
 }
diff --git a/...ples/src/main/java/com/groupdocs/parser/examples/TextExtractors/SpreadsheetDocuments.java b/...ples/src/main/java/com/groupdocs/parser/examples/TextExtractors/SpreadsheetDocuments.java
@@ -4,6 +4,9 @@
 import com.groupdocs.parser.CellsSheetInfo;
 import com.groupdocs.parser.CellsTextExtractor;
 import com.groupdocs.parser.MarkdownDocumentFormatter;
+import com.groupdocs.parser.Rectangle;
+import com.groupdocs.parser.TextArea;
+import com.groupdocs.parser.TextAreaSearchOptions;
 import com.groupdocs.parser.examples.Common;
 
 public class SpreadsheetDocuments {
@@ -155,4 +158,35 @@ public static void extractSelectedColumnsByRows() {
 			exp.printStackTrace();
 		}
 	}
+	/**
+	 * Extracts a text area from a spreadsheet document.
+	 * 
+	 */
+	public static void extractTextAreaFromSpreadsheetDocument() {
+		try {
+			// ExStart:extractTextAreaFromSpreadsheetDocument_18.9
+			// Create a text extractor for spreadsheets
+			try (CellsTextExtractor extractor = new CellsTextExtractor(Common.mapSourceFilePath(FILE_PATH))) {
+				// Create search options
+				TextAreaSearchOptions searchOptions = new TextAreaSearchOptions();
+				// Set a regular expression to search 'Invoice # XXX' text
+				searchOptions.setExpression("\\s?INVOICE\\s?#\\s?[0-9]+");
+				// Limit the search with a rectangle
+				searchOptions.setRectangle(new Rectangle(10, 10, 300, 150));
+
+				// Get text areas
+				java.util.List<TextArea> texts = extractor.getDocumentContent().getTextAreas(0, searchOptions);
+
+				// Iterate over a list
+				for (TextArea area : texts) {
+				    // Print a text
+				    System.out.println(area.getText());
+				}
+			}
+			// ExEnd:extractTextAreaFromSpreadsheetDocument_18.9
+		} catch (Exception exp) {
+			System.out.println("Exception: " + exp.getMessage());
+			exp.printStackTrace();
+		}
+	}
 }
diff --git a/Examples/src/main/java/com/groupdocs/parser/examples/TextExtractors/TextDocuments.java b/Examples/src/main/java/com/groupdocs/parser/examples/TextExtractors/TextDocuments.java
@@ -1,6 +1,9 @@
 package com.groupdocs.parser.examples.TextExtractors;
 
 import com.groupdocs.parser.MarkdownDocumentFormatter;
+import com.groupdocs.parser.Rectangle;
+import com.groupdocs.parser.TextArea;
+import com.groupdocs.parser.TextAreaSearchOptions;
 import com.groupdocs.parser.WordsFormattedTextExtractor;
 import com.groupdocs.parser.WordsTextExtractor;
 import com.groupdocs.parser.examples.Common;
@@ -76,4 +79,36 @@ public static void extractFormattedText() {
 			exp.printStackTrace();
 		}
 	}
+
+	/**
+	 * Extracts a text area from a text document.
+	 * 
+	 */
+	public static void extractTextAreaFromTextDocument() {
+		try {
+			// ExStart:extractTextAreaFromTextDocument_18.9
+			// Create a text extractor
+			try (WordsTextExtractor extractor = new WordsTextExtractor(Common.mapSourceFilePath(FILE_PATH))) {
+				// Create search options
+				TextAreaSearchOptions searchOptions = new TextAreaSearchOptions();
+				// Set a regular expression to search 'Invoice # XXX' text
+				searchOptions.setExpression("\\s?INVOICE\\s?#\\s?[0-9]+");
+				// Limit the search with a rectangle
+				searchOptions.setRectangle(new Rectangle(10, 10, 300, 150));
+
+				// Get text areas
+				java.util.List<TextArea> texts = extractor.getDocumentContent().getTextAreas(0, searchOptions);
+
+				// Iterate over a list
+				for (TextArea area : texts) {
+					// Print a text
+					System.out.println(area.getText());
+				}
+			}
+			// ExEnd:extractTextAreaFromTextDocument_18.9
+		} catch (Exception exp) {
+			System.out.println("Exception: " + exp.getMessage());
+			exp.printStackTrace();
+		}
+	}
 }