Merge branch 'develop' of https://github.com/sleuthkit/autopsy into 3788-intercase-correlation

.gitignore

@@ -12,6 +12,7 @@
 /Core/build/
 /Core/dist/
 /Core/nbproject/*
+/Core/test/qa-functional/data/*
 !/Core/nbproject/project.xml
 !/Core/nbproject/project.properties
 

Core/build.xml

@@ -40,6 +40,11 @@
             <fileset dir="${thirdparty.dir}/Volatility"/>
         </copy>
         
+        <!--Copy Tesseract OCR to release-->
+        <copy todir="${basedir}/release/Tesseract-OCR" >
+            <fileset dir="${thirdparty.dir}/Tesseract-OCR"/>
+        </copy>
+            
         <!--Copy other jars-->
         <copy file="${thirdparty.dir}/rejistry/Rejistry-1.0-SNAPSHOT.jar" todir="${ext.dir}" />
         <copy file="${thirdparty.dir}/sevenzip/sevenzipjbinding.jar" todir="${ext.dir}" />
@@ -84,14 +89,15 @@
 
     <target name="getTestDataFiles">
         <mkdir dir="${basedir}/test/qa-functional/data"/>
-	<get src="https://drive.google.com/uc?id=1dLYGctuvRQMmnzfXPppTM_9gB49eLc_g" dest="${test-input}/embedded.vhd" skipexisting="true"/>
+	      <get src="https://drive.google.com/uc?id=1dLYGctuvRQMmnzfXPppTM_9gB49eLc_g" dest="${test-input}/embedded.vhd" skipexisting="true"/>
         <get src="https://drive.google.com/uc?id=1JACMDyH4y54ypGzFWl82ZzMQf3qbrioP" dest="${test-input}/encryption_detection_bitlocker_test.vhd" skipexisting="true"/>
         <get src="https://drive.google.com/uc?id=0BxdBkzm5VKGNT0dGY0dqcHVsU3M" dest="${test-input}/filter_test1.img" skipexisting="true"/>	    
         <get src="https://drive.google.com/uc?id=1bghoSm7z7nhmGIxlllyY1MMlbLntxm7n" dest="${test-input}/local_files_test.zip" skipexisting="true"/>
         <get src="https://drive.google.com/uc?id=1BrSiUQ1fzxFS9vIaK4mYKX6qIVp9kRWT" dest="${test-input}/password_detection_test.img" skipexisting="true"/>
+        <get src="https://drive.google.com/uc?id=1HD8s4rculgHV1qZT5g80Kg7j4m1qccrN" dest="${test-input}/veracrypt_detection_test.vhd" skipexisting="true"/>
     </target>
 
-    <target name="get-deps" depends="init-ivy,getTSKJars,get-thirdparty-dependencies,get-InternalPythonModules, download-binlist, getTestDataFiles">
+    <target name="get-deps" depends="init-ivy,getTSKJars,get-thirdparty-dependencies,get-InternalPythonModules, download-binlist,getTestDataFiles">
         <mkdir dir="${ext.dir}"/>
         <copy file="${thirdparty.dir}/LICENSE-2.0.txt" todir="${ext.dir}" />
         

Core/src/org/sleuthkit/autopsy/modules/embeddedfileextractor/SevenZipExtractor.java

@@ -218,7 +218,7 @@ class SevenZipExtractor {
      */
     private ArchiveFormat get7ZipOptions(AbstractFile archiveFile) {
         // try to get the file type from the BB
-        String detectedFormat = null;
+        String detectedFormat;
         detectedFormat = archiveFile.getMIMEType();
 
         if (detectedFormat == null) {
@@ -434,11 +434,11 @@ class SevenZipExtractor {
                     result = item.extractSlow(unpackStream, password);
                 }
                 if (result != ExtractOperationResult.OK) {
-                    logger.log(Level.WARNING, "Extraction of : " + localAbsPath + " encountered error " + result); //NON-NLS
+                    logger.log(Level.WARNING, "Extraction of : {0} encountered error {1}", new Object[]{localAbsPath, result}); //NON-NLS
                     return null;
                 }
 
-            } catch (Exception e) {
+            } catch (SevenZipException e) {
                 //could be something unexpected with this file, move on
                 logger.log(Level.WARNING, "Could not extract file from archive: " + localAbsPath, e); //NON-NLS
             } finally {
@@ -492,7 +492,7 @@ class SevenZipExtractor {
         final ProgressHandle progress = ProgressHandle.createHandle(Bundle.EmbeddedFileExtractorIngestModule_ArchiveExtractor_moduleName());
         //recursion depth check for zip bomb
         final long archiveId = archiveFile.getId();
-        SevenZipExtractor.ArchiveDepthCountTree.Archive parentAr = null;
+        SevenZipExtractor.ArchiveDepthCountTree.Archive parentAr;
         try {
             blackboard = Case.getCurrentCaseThrows().getServices().getBlackboard();
         } catch (NoCurrentCaseException ex) {
@@ -717,7 +717,7 @@ class SevenZipExtractor {
             String encryptionType = fullEncryption ? ENCRYPTION_FULL : ENCRYPTION_FILE_LEVEL;
             try {
                 BlackboardArtifact artifact = archiveFile.newArtifact(BlackboardArtifact.ARTIFACT_TYPE.TSK_ENCRYPTION_DETECTED);
-                artifact.addAttribute(new BlackboardAttribute(BlackboardAttribute.ATTRIBUTE_TYPE.TSK_NAME, EmbeddedFileExtractorModuleFactory.getModuleName(), encryptionType));
+                artifact.addAttribute(new BlackboardAttribute(BlackboardAttribute.ATTRIBUTE_TYPE.TSK_COMMENT, EmbeddedFileExtractorModuleFactory.getModuleName(), encryptionType));
 
                 try {
                     // index the artifact for keyword search

Core/test/qa-functional/src/org/sleuthkit/autopsy/ingest/EmbeddedFileTest.java

@@ -62,7 +62,7 @@ public class EmbeddedFileTest extends NbTestCase {
 
     @Override
     public void setUp() {
-        CaseUtils.createCase(CASE_DIRECTORY_PATH, CASE_NAME);
+        CaseUtils.createCase(CASE_NAME);
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
         
@@ -92,7 +92,6 @@ public class EmbeddedFileTest extends NbTestCase {
     @Override
     public void tearDown() {
         CaseUtils.closeCase();
-        CaseUtils.deleteCaseDir(CASE_DIRECTORY_PATH);
     }
     
     public void testEncryption() {

Core/test/qa-functional/src/org/sleuthkit/autopsy/ingest/IngestFileFiltersTest.java

@@ -72,8 +72,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
     
     public void testBasicDir() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testBasicDir");
+        CaseUtils.createCase("testBasicDir");
-        CaseUtils.createCase(casePath, "testBasicDir");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -115,8 +114,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
     
     public void testExtAndDirWithOneRule() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testExtAndDirWithOneRule");
+        CaseUtils.createCase("testExtAndDirWithOneRule");
-        CaseUtils.createCase(casePath, "testExtAndDirWithOneRule");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -151,8 +149,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
 
     public void testExtAndDirWithTwoRules() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testExtAndDirWithTwoRules");
+        CaseUtils.createCase("testExtAndDirWithTwoRules");
-        CaseUtils.createCase(casePath, "testExtAndDirWithTwoRules");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -196,8 +193,7 @@ public class IngestFileFiltersTest extends NbTestCase {
    }
    
     public void testFullFileNameRule() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testFullFileNameRule");
+        CaseUtils.createCase("testFullFileNameRule");
-        CaseUtils.createCase(casePath, "testFullFileNameRule");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -232,8 +228,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
 
     public void testCarvingWithExtRuleAndUnallocSpace() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testCarvingWithExtRuleAndUnallocSpace");
+        CaseUtils.createCase("testCarvingWithExtRuleAndUnallocSpace");
-        CaseUtils.createCase(casePath, "testCarvingWithExtRuleAndUnallocSpace");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -281,8 +276,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
   
     public void testCarvingNoUnallocatedSpace() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testCarvingNoUnallocatedSpace");
+        CaseUtils.createCase("testCarvingNoUnallocatedSpace");
-        CaseUtils.createCase(casePath, "testCarvingNoUnallocatedSpace");
         ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, IMAGE_PATH);
 
@@ -315,8 +309,7 @@ public class IngestFileFiltersTest extends NbTestCase {
     }
 
     public void testEmbeddedModule() {
-        Path casePath = Paths.get(System.getProperty("java.io.tmpdir"), "testEmbeddedModule");
+        CaseUtils.createCase("testEmbeddedModule");
-        CaseUtils.createCase(casePath, "testEmbeddedModule");
         LocalFilesDSProcessor dataSourceProcessor = new LocalFilesDSProcessor();
         IngestUtils.addDataSource(dataSourceProcessor, ZIPFILE_PATH);
         

Core/test/qa-functional/src/org/sleuthkit/autopsy/modules/encryptiondetection/EncryptionDetectionTest.java

@@ -44,6 +44,7 @@ import org.sleuthkit.datamodel.BlackboardAttribute;
 import org.sleuthkit.datamodel.Image;
 import org.sleuthkit.datamodel.TskCoreException;
 import org.sleuthkit.datamodel.TskData;
+import org.sleuthkit.datamodel.Content;
 import org.sleuthkit.datamodel.Volume;
 import org.sleuthkit.datamodel.VolumeSystem;
 
@@ -58,6 +59,12 @@ public class EncryptionDetectionTest extends NbTestCase {
     private final Path BITLOCKER_IMAGE_PATH = Paths.get(this.getDataDir().toString(), "encryption_detection_bitlocker_test.vhd");
     private final Path PASSWORD_IMAGE_PATH = Paths.get(this.getDataDir().toString(), "password_detection_test.img");
 
+    private static final String PASSWORD_DETECTION_CASE_NAME = "PasswordDetectionTest";
+    private static final String VERACRYPT_DETECTION_CASE_NAME = "VeraCryptDetectionTest";
+
+    private final Path PASSWORD_DETECTION_IMAGE_PATH = Paths.get(this.getDataDir().toString(), "password_detection_test.img");
+    private final Path VERACRYPT_DETECTION_IMAGE_PATH = Paths.get(this.getDataDir().toString(), "veracrypt_detection_test.vhd");
+  
     public static Test suite() {
         NbModuleSuite.Configuration conf = NbModuleSuite.createConfiguration(EncryptionDetectionTest.class).
                 clusters(".*").
@@ -79,7 +86,7 @@ public class EncryptionDetectionTest extends NbTestCase {
      */
     public void testBitlockerEncryption() {
         try {
-            CaseUtils.createCase(BITLOCKER_CASE_DIRECTORY_PATH, BITLOCKER_CASE_NAME);
+            CaseUtils.createCase(BITLOCKER_CASE_NAME);
             ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
             IngestUtils.addDataSource(dataSourceProcessor, BITLOCKER_IMAGE_PATH);
             Case openCase = Case.getCurrentCaseThrows();
@@ -150,21 +157,22 @@ public class EncryptionDetectionTest extends NbTestCase {
      */
     public void testPasswordProtection() {
         try {
-            CaseUtils.createCase(PASSWORD_CASE_DIRECTORY_PATH, PASSWORD_CASE_NAME);
+            CaseUtils.createCase(PASSWORD_DETECTION_CASE_NAME);
+
             ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
-            IngestUtils.addDataSource(dataSourceProcessor, PASSWORD_IMAGE_PATH);
+            List<String> errorMessages = IngestUtils.addDataSource(dataSourceProcessor, PASSWORD_DETECTION_IMAGE_PATH);
+            String joinedErrors = String.join(System.lineSeparator(), errorMessages);
+            assertEquals(joinedErrors, 0, errorMessages.size());
+
             Case openCase = Case.getCurrentCaseThrows();    
 
             /*
              * Create ingest job settings.
              */
-            IngestModuleFactory ingestModuleFactory = new EncryptionDetectionModuleFactory();
+
-            IngestModuleIngestJobSettings settings = ingestModuleFactory.getDefaultIngestJobSettings();
+            ArrayList<IngestModuleTemplate> templates = new ArrayList<>();
-            IngestModuleTemplate template = new IngestModuleTemplate(ingestModuleFactory, settings);
+            templates.add(IngestUtils.getIngestModuleTemplate(new EncryptionDetectionModuleFactory()));
-            template.setEnabled(true);
+            IngestJobSettings ingestJobSettings = new IngestJobSettings(PASSWORD_DETECTION_CASE_NAME, IngestType.FILES_ONLY, templates);
-            List<IngestModuleTemplate> templates = new ArrayList<>();
-            templates.add(template);
-            IngestJobSettings ingestJobSettings = new IngestJobSettings(EncryptionDetectionTest.class.getCanonicalName(), IngestType.FILES_ONLY, templates);
             IngestUtils.runIngestJob(openCase.getDataSources(), ingestJobSettings);
 
             /*
@@ -201,8 +209,8 @@ public class EncryptionDetectionTest extends NbTestCase {
                      */
                     if (file.isFile() && !file.getType().equals(TskData.TSK_DB_FILES_TYPE_ENUM.SLACK)) {
                         /*
-                         * Determine which assertions to use for the file based on
+                         * Determine which assertions to use for the file based
-                         * its name.
+                         * on its name.
                          */
                         boolean fileProtected = file.getName().split("\\.")[0].endsWith("-protected");
                         List<BlackboardArtifact> artifactsList = file.getAllArtifacts();
@@ -234,4 +242,67 @@ public class EncryptionDetectionTest extends NbTestCase {
             Assert.fail(ex);
         }
     }
+
+    /**
+     * Test the Encryption Detection module's detection of veracrypt encrypted
+     * container files and partitions.
+     *
+     * Test passes if the following are true.
+     *
+     * 1. A partition was detected without a file system by checking for the
+     * error. 2. Only 1 data source exsists in the case, to ensure a stale case
+     * did not get used. 3. One volume has a TSK_ENCRYPTION_SUSPECTED artifact
+     * associated with it. 4. A single file named veracrpytContainerFile exists.
+     * 5. The file named veracrpytContainerFile has a TSK_ENCRYPTION_SUSPECTED
+     * artifact associated with it.
+     */
+    public void testVeraCryptSupport() {
+        try {
+            CaseUtils.createCase(VERACRYPT_DETECTION_CASE_NAME);
+            ImageDSProcessor dataSourceProcessor = new ImageDSProcessor();
+            List<String> errorMessages = IngestUtils.addDataSource(dataSourceProcessor, VERACRYPT_DETECTION_IMAGE_PATH);
+            String joinedErrors;
+            if (errorMessages.isEmpty()) {
+                joinedErrors = "Encrypted partition did not cause error, it was expected to";
+            } else {
+                joinedErrors = String.join(System.lineSeparator(), errorMessages);
+            }
+            //there will be 1 expected error regarding the encrypted partition not having a file system
+            assertEquals(joinedErrors, 1, errorMessages.size());
+
+            Case openCase = Case.getCurrentCaseThrows();
+            ArrayList<IngestModuleTemplate> templates = new ArrayList<>();
+            templates.add(IngestUtils.getIngestModuleTemplate(new EncryptionDetectionModuleFactory()));
+            //image includes an encrypted container file with size greater than 5 mb so default settings detect it
+            IngestJobSettings ingestJobSettings = new IngestJobSettings(VERACRYPT_DETECTION_CASE_NAME, IngestType.ALL_MODULES, templates);
+
+            assertEquals("Expected only one data source to exist in the Case", 1, openCase.getDataSources().size());
+            IngestUtils.runIngestJob(openCase.getDataSources(), ingestJobSettings);
+
+            //check that one of the partitions has an encrypted volume
+            int numberOfEncryptedVolumes = 0;
+            for (Content datasource : openCase.getDataSources()) { //data source
+                for (Content volumeSystem : datasource.getChildren()) { //volume system 
+                    for (Content volume : volumeSystem.getChildren()) { //volumes
+                        numberOfEncryptedVolumes += volume.getArtifacts(BlackboardArtifact.ARTIFACT_TYPE.TSK_ENCRYPTION_SUSPECTED).size();
+                    }
+                }
+            }
+            assertEquals("One volume should exist with an encryption suspsected artifact", 1, numberOfEncryptedVolumes);
+
+            //ensure the encrypyted container file was also detected correctly
+            FileManager fileManager = openCase.getServices().getFileManager();
+            List<AbstractFile> results = fileManager.findFiles("veracryptContainerFile");
+            assertEquals("Expected 1 file named veracryptContainerFile to exist in test image", 1, results.size());
+            int numberOfEncryptedContainers = 0;
+            for (AbstractFile file : results) {
+                numberOfEncryptedContainers += file.getArtifacts(BlackboardArtifact.ARTIFACT_TYPE.TSK_ENCRYPTION_SUSPECTED).size();
+            }
+            assertEquals("Encrypted Container file should have one encyption suspected artifact", 1, numberOfEncryptedContainers);
+        } catch (NoCurrentCaseException | TskCoreException ex) {
+            Exceptions.printStackTrace(ex);
+            Assert.fail(ex);
+        }
+    }
+
 }

Core/test/qa-functional/src/org/sleuthkit/autopsy/testutils/CaseUtils.java

@@ -18,8 +18,10 @@
  */
 package org.sleuthkit.autopsy.testutils;
 
+import java.io.File;
 import java.io.IOException;
 import java.nio.file.Path;
+import java.nio.file.Paths;
 import static junit.framework.Assert.assertFalse;
 import static junit.framework.Assert.assertTrue;
 import org.apache.commons.io.FileUtils;
@@ -30,44 +32,43 @@ import org.sleuthkit.autopsy.casemodule.CaseActionException;
 import org.sleuthkit.autopsy.casemodule.CaseDetails;
 
 /**
- * Common case utility methods.
+ * Class with common methods for testing related to the creation and elimination
+ * of cases.
  */
 public final class CaseUtils {
 
     /**
-     * CaseUtils constructor. Since this class is not meant to allow for
+     * Create a case case directory and case for the given case name.
-     * instantiation, this constructor is 'private'.
-     */
-    private CaseUtils() {
-    }
-
-    /**
-     * Create a new case. If the case already exists at the specified path, the
-     * existing case will be removed prior to creation of the new case.
      *
-     * @param caseDirectoryPath The path to the case data.
+     * @param caseName the name for the case and case directory to have
-     * @param caseDisplayName   The display name for the case.
      */
-    public static void createCase(Path caseDirectoryPath, String caseDisplayName) {
+    public static void createCase(String caseName) {
-        //Make sure the test is starting with a clean state. So delete the test directory, if it exists.
+        //Make sure the case is starting with a clean state. So delete the case directory, if it exists.
-        deleteCaseDir(caseDirectoryPath);
+        Path caseDirectoryPath = Paths.get(System.getProperty("java.io.tmpdir"), caseName);
-        assertFalse("Unable to delete existing test directory", caseDirectoryPath.toFile().exists());
+        File caseDir = new File(caseDirectoryPath.toString());
-
+        try {
+            deleteCaseDir(caseDir);
+        } catch (IOException ex) {
+            Exceptions.printStackTrace(ex);
+            Assert.fail(ex);
+        }
+        assertFalse("Unable to delete existing test directory", caseDir.exists());
         // Create the test directory
-        caseDirectoryPath.toFile().mkdirs();
+        caseDir.mkdirs();
-        assertTrue("Unable to create test directory", caseDirectoryPath.toFile().exists());
+        assertTrue("Unable to create test directory", caseDir.exists());
 
         try {
-            Case.createAsCurrentCase(Case.CaseType.SINGLE_USER_CASE, caseDirectoryPath.toString(), new CaseDetails(caseDisplayName));
+            Case.createAsCurrentCase(Case.CaseType.SINGLE_USER_CASE, caseDirectoryPath.toString(), new CaseDetails(caseName));
         } catch (CaseActionException ex) {
             Exceptions.printStackTrace(ex);
             Assert.fail(ex);
         }
-        assertTrue(caseDirectoryPath.toFile().exists());
+
+        assertTrue(caseDir.exists());
     }
 
     /**
-     * Close the currently opened case.
+     * Close the current case, fails test if case was unable to be closed.
      */
     public static void closeCase() {
         try {
@@ -85,20 +86,25 @@ public final class CaseUtils {
     }
 
     /**
-     * Delete a case at the specified path.
+     * Delete the case directory if it exists, thows exception if unable to
+     * delete case dir to allow the user to determine failure with.
      *
-     * @param caseDirectoryPath The path to the case to be removed.
+     * @param caseDirectory the case directory to delete
+     *
+     * @throws IOException thrown if there was an problem deleting the case
+     *                     directory
      */
-    public static void deleteCaseDir(Path caseDirectoryPath) {
+    public static void deleteCaseDir(File caseDirectory) throws IOException {
-        if (!caseDirectoryPath.toFile().exists()) {
+        if (!caseDirectory.exists()) {
             return;
         }
-        try {
+        FileUtils.deleteDirectory(caseDirectory);
-            FileUtils.deleteDirectory(caseDirectoryPath.toFile());
+    }
-        } catch (IOException ex) {
+
-            //We just want to make sure the case directory doesn't exist when the test starts. It shouldn't cause failure if the case directory couldn't be deleted after a test finished.            
+    /**
-            System.out.println("INFO: Unable to delete case directory: " + caseDirectoryPath.toString());
+     * Private constructor to prevent utility class instantiation.
-        }
+     */
+    private CaseUtils() {
     }    
     
 }

Core/test/qa-functional/src/org/sleuthkit/autopsy/testutils/IngestUtils.java

@@ -19,6 +19,7 @@
 package org.sleuthkit.autopsy.testutils;
 
 import java.nio.file.Path;
+import java.util.ArrayList;
 import java.util.List;
 import static junit.framework.Assert.assertEquals;
 import org.openide.util.Exceptions;
@@ -26,13 +27,14 @@ import org.python.icu.impl.Assert;
 import org.sleuthkit.autopsy.datasourceprocessors.AutoIngestDataSourceProcessor;
 import org.sleuthkit.autopsy.ingest.IngestJobSettings;
 import org.sleuthkit.autopsy.ingest.IngestModuleError;
-import org.sleuthkit.autopsy.ingest.IngestModuleFactoryAdapter;
+import org.sleuthkit.autopsy.ingest.IngestModuleFactory;
 import org.sleuthkit.autopsy.ingest.IngestModuleIngestJobSettings;
 import org.sleuthkit.autopsy.ingest.IngestModuleTemplate;
 import org.sleuthkit.datamodel.Content;
 
 /**
- * Common image utility methods.
+ * Class with common methods for testing related to adding and ingesting
+ * datasources.
  */
 public final class IngestUtils {
 
@@ -44,39 +46,48 @@ public final class IngestUtils {
     }
 
     /**
-     * Add a data source for the data source processor.
+     * Add the specified datasource to the case current case and processes it.
+     * Causes failure if it was unable to add and process the datasource.
      *
-     * @param dataSourceProcessor The data source processor.
+     * @param dataSourceProcessor the datasource processer to use to process the
-     * @param dataSourcePath      The path to the data source to be added.
+     *                            datasource
+     * @param dataSourcePath      the path to the datasource which is being
+     *                            added
+     *
+     * @return errorMessages a list of all error messages as strings which
+     *         encountered while processing the data source
      */
-    public static void addDataSource(AutoIngestDataSourceProcessor dataSourceProcessor, Path dataSourcePath) {
+    public static List<String> addDataSource(AutoIngestDataSourceProcessor dataSourceProcessor, Path dataSourcePath) {
+        List<String> errorMessages = new ArrayList<>();
         try {
+            if (!dataSourcePath.toFile().exists()) {
+                Assert.fail("Data source not found: " + dataSourcePath.toString());
+            }
             DataSourceProcessorRunner.ProcessorCallback callBack = DataSourceProcessorRunner.runDataSourceProcessor(dataSourceProcessor, dataSourcePath);
-            /*
+            errorMessages = callBack.getErrorMessages();
-             * Ignore the callback error messages. Sometimes it's perfectly
-             * valid for it to not be able to detect a file system, which is one
-             * of the errors that can be returned.
-             */
         } catch (AutoIngestDataSourceProcessor.AutoIngestDataSourceProcessorException | InterruptedException ex) {
             Exceptions.printStackTrace(ex);
             Assert.fail(ex);
         }
+        return errorMessages;
     }
 
     /**
-     * Run an ingest job.
+     * Run ingest on the specified datasources with the specified ingest job
+     * settings. Causes failure if there are any errors or other problems while
+     * running ingest.
      *
-     * @param dataSourceList    The list of data sources to process.
+     * @param datasources       - the datasources to run ingest on
-     * @param ingestJobSettings The ingest job settings to use for ingest.
+     * @param ingestJobSettings - the ingest job settings to use for ingest
      */
-    public static void runIngestJob(List<Content> dataSourceList, IngestJobSettings ingestJobSettings) {
+    public static void runIngestJob(List<Content> datasources, IngestJobSettings ingestJobSettings) {
         try {
-            List<IngestModuleError> ingestModuleErrorsList = IngestJobRunner.runIngestJob(dataSourceList, ingestJobSettings);
+            List<IngestModuleError> errs = IngestJobRunner.runIngestJob(datasources, ingestJobSettings);
-            for (IngestModuleError err : ingestModuleErrorsList) {
+            StringBuilder joinedErrors = new StringBuilder("");
-                System.out.println(String.format("Error: %s: %s.", err.getModuleDisplayName(), err.toString()));
+            errs.forEach((err) -> {
-            }
+                joinedErrors.append(String.format("Error: %s: %s.", err.getModuleDisplayName(), err.toString())).append(System.lineSeparator());
-            String errorMessage = String.format("The ingest job runner produced %d error messages.", ingestModuleErrorsList.size());
+            });
-            assertEquals(errorMessage, 0, ingestModuleErrorsList.size());
+            assertEquals(joinedErrors.toString(), 0, errs.size());
         } catch (InterruptedException ex) {
             Exceptions.printStackTrace(ex);
             Assert.fail(ex);
@@ -84,17 +95,18 @@ public final class IngestUtils {
     }
 
     /**
-     * Build a new ingest module template based on the given factory.
+     * Get the ingest module template for the the specified factories default
+     * ingest job settings.
      *
-     * @param factory The ingest module factory.
+     * @param factory the factory to get the ingest job settings from
      *
-     * @return The ingest module template.
+     * @return template - the IngestModuleTemplate created with the factory and
+     *         it's default settings.
      */
-    public static IngestModuleTemplate getIngestModuleTemplate(IngestModuleFactoryAdapter factory) {
+    public static IngestModuleTemplate getIngestModuleTemplate(IngestModuleFactory factory) {
         IngestModuleIngestJobSettings settings = factory.getDefaultIngestJobSettings();
         IngestModuleTemplate template = new IngestModuleTemplate(factory, settings);
         template.setEnabled(true);
         return template;
     }
-
 }

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties

@@ -218,6 +218,7 @@ KeywordSearchJobSettingsPanel.languagesLabel.text=Scripts enabled for string ext
 KeywordSearchGlobalLanguageSettingsPanel.enableUTF8Checkbox.text=Enable UTF8 text extraction
 KeywordSearchGlobalLanguageSettingsPanel.ingestSettingsLabel.text=Ingest settings for string extraction from unknown file types (changes effective on next ingest):
 KeywordSearchGlobalLanguageSettingsPanel.enableUTF16Checkbox.text=Enable UTF16LE and UTF16BE string extraction
+KeywordSearchGlobalLanguageSettingsPanel.enableOcrCheckbox.text=Enable Optical Character Recognition (OCR)
 KeywordSearchGlobalLanguageSettingsPanel.languagesLabel.text=Enabled scripts (languages):
 KeywordSearchGlobalSearchSettingsPanel.timeRadioButton1.toolTipText=20 mins. (fastest ingest time)
 KeywordSearchGlobalSearchSettingsPanel.timeRadioButton1.text=20 minutes (slowest feedback, fastest ingest)
@@ -309,3 +310,4 @@ ExtractedContentPanel.pageOfLabel.text=of
 ExtractedContentPanel.pageTotalLabel.text=-
 ExtractedContentPanel.pageButtonsLabel.text=Page
 ExtractedContentPanel.pagesLabel.text=Page:
+

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.form

@@ -16,21 +16,26 @@
   <Layout>
     <DimensionLayout dim="0">
       <Group type="103" groupAlignment="0" attributes="0">
-          <Group type="102" alignment="0" attributes="0">
+          <Group type="102" attributes="0">
-              <EmptySpace max="-2" attributes="0"/>
               <Group type="103" groupAlignment="0" attributes="0">
-                  <Component id="ingestSettingsLabel" alignment="0" min="-2" max="-2" attributes="0"/>
+                  <Group type="102" alignment="0" attributes="0">
-                  <Group type="102" attributes="0">
+                      <EmptySpace max="-2" attributes="0"/>
-                      <EmptySpace min="10" pref="10" max="-2" attributes="0"/>
+                      <Group type="103" groupAlignment="0" attributes="0">
+                          <Component id="ingestSettingsLabel" alignment="0" min="-2" max="-2" attributes="0"/>
+                          <Group type="103" alignment="0" groupAlignment="1" attributes="0">
+                              <Component id="languagesLabel" alignment="0" min="-2" max="-2" attributes="0"/>
+                              <Component id="langPanel" min="-2" max="-2" attributes="0"/>
+                          </Group>
+                      </Group>
+                  </Group>
+                  <Group type="102" alignment="0" attributes="0">
+                      <EmptySpace min="-2" pref="26" max="-2" attributes="0"/>
                       <Group type="103" groupAlignment="0" max="-2" attributes="0">
                           <Component id="enableUTF16Checkbox" min="-2" max="-2" attributes="0"/>
                           <Component id="enableUTF8Checkbox" alignment="0" min="-2" max="-2" attributes="0"/>
+                          <Component id="enableOcrCheckbox" alignment="0" min="-2" max="-2" attributes="0"/>
                       </Group>
                   </Group>
-                  <Group type="103" alignment="0" groupAlignment="1" attributes="0">
-                      <Component id="languagesLabel" alignment="0" min="-2" max="-2" attributes="0"/>
-                      <Component id="langPanel" min="-2" max="-2" attributes="0"/>
-                  </Group>
               </Group>
               <EmptySpace pref="255" max="32767" attributes="0"/>
           </Group>
@@ -42,13 +47,15 @@
               <EmptySpace max="-2" attributes="0"/>
               <Component id="ingestSettingsLabel" min="-2" max="-2" attributes="0"/>
               <EmptySpace type="unrelated" max="-2" attributes="0"/>
+              <Component id="enableOcrCheckbox" min="-2" max="-2" attributes="0"/>
+              <EmptySpace max="32767" attributes="0"/>
               <Component id="enableUTF16Checkbox" min="-2" max="-2" attributes="0"/>
               <EmptySpace max="-2" attributes="0"/>
               <Component id="enableUTF8Checkbox" min="-2" max="-2" attributes="0"/>
-              <EmptySpace type="separate" max="-2" attributes="0"/>
-              <Component id="languagesLabel" min="-2" max="-2" attributes="0"/>
               <EmptySpace type="unrelated" max="-2" attributes="0"/>
-              <Component id="langPanel" pref="397" max="32767" attributes="0"/>
+              <Component id="languagesLabel" min="-2" max="-2" attributes="0"/>
+              <EmptySpace max="-2" attributes="0"/>
+              <Component id="langPanel" min="-2" pref="380" max="-2" attributes="0"/>
               <EmptySpace max="-2" attributes="0"/>
           </Group>
       </Group>
@@ -86,7 +93,7 @@
             </DimensionLayout>
             <DimensionLayout dim="1">
               <Group type="103" groupAlignment="0" attributes="0">
-                  <EmptySpace min="0" pref="395" max="32767" attributes="0"/>
+                  <EmptySpace min="0" pref="378" max="32767" attributes="0"/>
               </Group>
             </DimensionLayout>
           </Layout>
@@ -120,5 +127,15 @@
         </Property>
       </Properties>
     </Component>
+    <Component class="javax.swing.JCheckBox" name="enableOcrCheckbox">
+      <Properties>
+        <Property name="text" type="java.lang.String" editor="org.netbeans.modules.i18n.form.FormI18nStringEditor">
+          <ResourceString bundle="org/sleuthkit/autopsy/keywordsearch/Bundle.properties" key="KeywordSearchGlobalLanguageSettingsPanel.enableOcrCheckbox.text" replaceFormat="org.openide.util.NbBundle.getMessage({sourceFileName}.class, &quot;{key}&quot;)"/>
+        </Property>
+      </Properties>
+      <Events>
+        <EventHandler event="actionPerformed" listener="java.awt.event.ActionListener" parameters="java.awt.event.ActionEvent" handler="enableOcrCheckboxActionPerformed"/>
+      </Events>
+    </Component>
   </SubComponents>
 </Form>

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.java

@@ -111,6 +111,9 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
                 = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
         enableUTF8Checkbox.setSelected(utf8);
 
+        boolean ocr = KeywordSearchSettings.getOcrOption();
+        enableOcrCheckbox.setSelected(ocr);        
+        
         final List<SCRIPT> serviceScripts = KeywordSearchSettings.getStringExtractScripts();
         final int components = checkPanel.getComponentCount();
 
@@ -141,6 +144,7 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
         activateScriptsCheckboxes(extractEnabled && ingestNotRunning);
         enableUTF16Checkbox.setEnabled(ingestNotRunning);
         enableUTF8Checkbox.setEnabled(ingestNotRunning);
+        enableOcrCheckbox.setEnabled(ingestNotRunning);
     }
 
     /**
@@ -158,6 +162,7 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
         enableUTF8Checkbox = new javax.swing.JCheckBox();
         enableUTF16Checkbox = new javax.swing.JCheckBox();
         ingestSettingsLabel = new javax.swing.JLabel();
+        enableOcrCheckbox = new javax.swing.JCheckBox();
 
         org.openide.awt.Mnemonics.setLocalizedText(languagesLabel, org.openide.util.NbBundle.getMessage(KeywordSearchGlobalLanguageSettingsPanel.class, "KeywordSearchGlobalLanguageSettingsPanel.languagesLabel.text")); // NOI18N
 
@@ -173,7 +178,7 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
         );
         checkPanelLayout.setVerticalGroup(
             checkPanelLayout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
-            .addGap(0, 395, Short.MAX_VALUE)
+            .addGap(0, 378, Short.MAX_VALUE)
         );
 
         langPanel.setViewportView(checkPanel);
@@ -194,22 +199,32 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
 
         org.openide.awt.Mnemonics.setLocalizedText(ingestSettingsLabel, org.openide.util.NbBundle.getMessage(KeywordSearchGlobalLanguageSettingsPanel.class, "KeywordSearchGlobalLanguageSettingsPanel.ingestSettingsLabel.text")); // NOI18N
 
+        org.openide.awt.Mnemonics.setLocalizedText(enableOcrCheckbox, org.openide.util.NbBundle.getMessage(KeywordSearchGlobalLanguageSettingsPanel.class, "KeywordSearchGlobalLanguageSettingsPanel.enableOcrCheckbox.text")); // NOI18N
+        enableOcrCheckbox.addActionListener(new java.awt.event.ActionListener() {
+            public void actionPerformed(java.awt.event.ActionEvent evt) {
+                enableOcrCheckboxActionPerformed(evt);
+            }
+        });
+
         javax.swing.GroupLayout layout = new javax.swing.GroupLayout(this);
         this.setLayout(layout);
         layout.setHorizontalGroup(
             layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
             .addGroup(layout.createSequentialGroup()
-                .addContainerGap()
                 .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
-                    .addComponent(ingestSettingsLabel)
                     .addGroup(layout.createSequentialGroup()
-                        .addGap(10, 10, 10)
+                        .addContainerGap()
+                        .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
+                            .addComponent(ingestSettingsLabel)
+                            .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.TRAILING)
+                                .addComponent(languagesLabel, javax.swing.GroupLayout.Alignment.LEADING)
+                                .addComponent(langPanel, javax.swing.GroupLayout.PREFERRED_SIZE, javax.swing.GroupLayout.DEFAULT_SIZE, javax.swing.GroupLayout.PREFERRED_SIZE))))
+                    .addGroup(layout.createSequentialGroup()
+                        .addGap(26, 26, 26)
                         .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING, false)
                             .addComponent(enableUTF16Checkbox)
-                            .addComponent(enableUTF8Checkbox)))
+                            .addComponent(enableUTF8Checkbox)
-                    .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.TRAILING)
+                            .addComponent(enableOcrCheckbox))))
-                        .addComponent(languagesLabel, javax.swing.GroupLayout.Alignment.LEADING)
-                        .addComponent(langPanel, javax.swing.GroupLayout.PREFERRED_SIZE, javax.swing.GroupLayout.DEFAULT_SIZE, javax.swing.GroupLayout.PREFERRED_SIZE)))
                 .addContainerGap(255, Short.MAX_VALUE))
         );
         layout.setVerticalGroup(
@@ -218,13 +233,15 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
                 .addContainerGap()
                 .addComponent(ingestSettingsLabel)
                 .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.UNRELATED)
+                .addComponent(enableOcrCheckbox)
+                .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED, javax.swing.GroupLayout.DEFAULT_SIZE, Short.MAX_VALUE)
                 .addComponent(enableUTF16Checkbox)
                 .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED)
                 .addComponent(enableUTF8Checkbox)
-                .addGap(18, 18, 18)
-                .addComponent(languagesLabel)
                 .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.UNRELATED)
-                .addComponent(langPanel, javax.swing.GroupLayout.DEFAULT_SIZE, 397, Short.MAX_VALUE)
+                .addComponent(languagesLabel)
+                .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED)
+                .addComponent(langPanel, javax.swing.GroupLayout.PREFERRED_SIZE, 380, javax.swing.GroupLayout.PREFERRED_SIZE)
                 .addContainerGap())
         );
     }// </editor-fold>//GEN-END:initComponents
@@ -246,8 +263,13 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
         firePropertyChange(OptionsPanelController.PROP_CHANGED, null, null);
     }//GEN-LAST:event_enableUTF16CheckboxActionPerformed
 
+    private void enableOcrCheckboxActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_enableOcrCheckboxActionPerformed
+        firePropertyChange(OptionsPanelController.PROP_CHANGED, null, null);
+    }//GEN-LAST:event_enableOcrCheckboxActionPerformed
+
     // Variables declaration - do not modify//GEN-BEGIN:variables
     private javax.swing.JPanel checkPanel;
+    private javax.swing.JCheckBox enableOcrCheckbox;
     private javax.swing.JCheckBox enableUTF16Checkbox;
     private javax.swing.JCheckBox enableUTF8Checkbox;
     private javax.swing.JLabel ingestSettingsLabel;
@@ -261,6 +283,7 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
                 Boolean.toString(enableUTF8Checkbox.isSelected()));
         KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(),
                 Boolean.toString(enableUTF16Checkbox.isSelected()));
+        KeywordSearchSettings.setOcrOption(enableOcrCheckbox.isSelected());
 
         if (toUpdate != null) {
             KeywordSearchSettings.setStringExtractScripts(toUpdate);

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchSettings.java

@@ -39,6 +39,8 @@ class KeywordSearchSettings {
     static final String PROPERTIES_SCRIPTS = NbBundle.getMessage(KeywordSearchSettings.class, "KeywordSearchSettings.propertiesScripts.text", MODULE_NAME);
     static final String SHOW_SNIPPETS = "showSnippets"; //NON-NLS
     static final boolean DEFAULT_SHOW_SNIPPETS = true;    
+    static final String OCR_ENABLED = "ocrEnabled"; //NON-NLS
+    static final boolean OCR_ENABLED_DEFAULT = false; // NON-NLS
     private static boolean skipKnown = true;
     private static final Logger logger = Logger.getLogger(KeywordSearchSettings.class.getName());
     private static UpdateFrequency UpdateFreq = UpdateFrequency.DEFAULT;
@@ -128,6 +130,26 @@ class KeywordSearchSettings {
         ModuleSettings.setConfigSetting(PROPERTIES_OPTIONS, key, val);
     }
     
+    /**
+     * Save OCR setting to permanent storage
+     * @param enabled 
+     */
+    static void setOcrOption(boolean enabled) {
+        ModuleSettings.setConfigSetting(PROPERTIES_OPTIONS, OCR_ENABLED, (enabled ? "true" : "false")); //NON-NLS
+    }    
+
+    /**
+     * Get OCR setting from permanent storage
+     * @return 
+     */
+    static boolean getOcrOption() {
+        if (ModuleSettings.settingExists(PROPERTIES_OPTIONS, OCR_ENABLED)) {
+            return ModuleSettings.getConfigSetting(PROPERTIES_OPTIONS, OCR_ENABLED).equals("true"); //NON-NLS
+        } else {
+            return OCR_ENABLED_DEFAULT;
+        }
+    }
+    
     static void setShowSnippets(boolean showSnippets) {
         ModuleSettings.setConfigSetting(PROPERTIES_OPTIONS, SHOW_SNIPPETS, (showSnippets ? "true" : "false")); //NON-NLS
     }
@@ -219,6 +241,11 @@ class KeywordSearchSettings {
             logger.log(Level.INFO, "No configuration for UTF16 found, generating defaults..."); //NON-NLS
             KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(), Boolean.TRUE.toString());
         }
+        //setting OCR default (disabled by default)
+        if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_OPTIONS, OCR_ENABLED)) {
+            logger.log(Level.INFO, "No configuration for OCR found, generating defaults..."); //NON-NLS
+            KeywordSearchSettings.setOcrOption(OCR_ENABLED_DEFAULT);
+        }        
         //setting default Latin-1 Script
         if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_SCRIPTS, SCRIPT.LATIN_1.name())) {
             logger.log(Level.INFO, "No configuration for Scripts found, generating defaults..."); //NON-NLS

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/TikaTextExtractor.java

@@ -19,9 +19,11 @@
 package org.sleuthkit.autopsy.keywordsearch;
 
 import com.google.common.io.CharSource;
+import java.io.File;
 import java.io.IOException;
 import java.io.PushbackReader;
 import java.io.Reader;
+import java.nio.file.Paths;
 import java.util.List;
 import java.util.concurrent.ExecutorService;
 import java.util.concurrent.Executors;
@@ -38,8 +40,12 @@ import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
 import org.apache.tika.parser.ParsingReader;
 import org.apache.tika.parser.microsoft.OfficeParserConfig;
+import org.apache.tika.parser.ocr.TesseractOCRConfig;
+import org.apache.tika.parser.pdf.PDFParserConfig;
 import org.openide.util.NbBundle;
+import org.openide.modules.InstalledFileLocator;
 import org.sleuthkit.autopsy.coreutils.Logger;
+import org.sleuthkit.autopsy.coreutils.PlatformUtil;
 import org.sleuthkit.datamodel.Content;
 import org.sleuthkit.datamodel.ReadContentInputStream;
 
@@ -54,6 +60,10 @@ class TikaTextExtractor extends ContentTextExtractor {
 
     private final AutoDetectParser parser = new AutoDetectParser();
     
+    private static final String TESSERACT_DIR_NAME = "Tesseract-OCR"; //NON-NLS
+    private static final String TESSERACT_EXECUTABLE = "tesseract.exe"; //NON-NLS
+    private static final File TESSERACT_PATH = locateTesseractExecutable();
+
     private static final List<String> TIKA_SUPPORTED_TYPES
             = new Tika().getParser().getSupportedTypes(new ParseContext())
                     .stream()
@@ -80,6 +90,30 @@ class TikaTextExtractor extends ContentTextExtractor {
         officeParserConfig.setUseSAXDocxExtractor(true);
         parseContext.set(OfficeParserConfig.class, officeParserConfig);
         
+        // configure OCR if it is enabled in KWS settings and installed on the machine
+        if (TESSERACT_PATH != null && KeywordSearchSettings.getOcrOption() && PlatformUtil.isWindowsOS() == true) {
+            
+            // configure PDFParser. 
+            PDFParserConfig pdfConfig = new PDFParserConfig();
+            
+            // Extracting the inline images and letting Tesseract run on each inline image.
+            // https://wiki.apache.org/tika/PDFParser%20%28Apache%20PDFBox%29
+            // https://tika.apache.org/1.7/api/org/apache/tika/parser/pdf/PDFParserConfig.html
+            pdfConfig.setExtractInlineImages(true); 
+            // Multiple pages within a PDF file might refer to the same underlying image.
+            pdfConfig.setExtractUniqueInlineImagesOnly(true);            
+            parseContext.set(PDFParserConfig.class, pdfConfig);
+            
+            // Configure Tesseract parser to perform OCR
+            TesseractOCRConfig ocrConfig = new TesseractOCRConfig();
+            String tesseractFolder = TESSERACT_PATH.getParent();
+            ocrConfig.setTesseractPath(tesseractFolder);
+            // Tesseract expects language data packs to be in a subdirectory of tesseractFolder, in a folder called "tessdata".
+            // If they are stored somewhere else, use ocrConfig.setTessdataPath(String tessdataPath) to point to them
+            ocrConfig.setLanguage("eng");
+            parseContext.set(TesseractOCRConfig.class, ocrConfig);
+        }
+
         //Parse the file in a task, a convenient way to have a timeout...
         final Future<Reader> future = tikaParseExecutor.submit(() -> new ParsingReader(parser, stream, metadata, parseContext));
         try {
@@ -112,6 +146,29 @@ class TikaTextExtractor extends ContentTextExtractor {
         }
     }
 
+    /**
+     * Finds and returns the path to the Tesseract executable, if able.
+     *
+     * @return A File reference or null.
+     */
+    private static File locateTesseractExecutable() {
+        if (!PlatformUtil.isWindowsOS()) {
+            return null;
+        }
+
+        String executableToFindName = Paths.get(TESSERACT_DIR_NAME, TESSERACT_EXECUTABLE).toString();
+        File exeFile = InstalledFileLocator.getDefault().locate(executableToFindName, TikaTextExtractor.class.getPackage().getName(), false);
+        if (null == exeFile) {
+            return null;
+        }
+
+        if (!exeFile.canExecute()) {
+            return null;
+        }
+
+        return exeFile;
+    }
+
     /**
      * Gets a CharSource that wraps a formated representation of the given
      * Metadata.

thirdparty/Tesseract-OCR/doc/AUTHORS

@@ -0,0 +1,42 @@
+Ray Smith (lead developer) <theraysmith@gmail.com>
+Ahmad Abdulkader
+Rika Antonova
+Nicholas Beato
+Jeff Breidenbach
+Samuel Charron
+Phil Cheatle
+Simon Crouch
+David Eger
+Sheelagh Huddleston
+Dan Johnson
+Rajesh Katikam
+Thomas Kielbus
+Dar-Shyang Lee
+Zongyi (Joe) Liu
+Robert Moss
+Chris Newton
+Michael Reimer
+Marius Renn
+Raquel Romano
+Christy Russon
+Shobhit Saxena
+Mark Seaman
+Faisal Shafait
+Hiroshi Takenaka
+Ranjith Unnikrishnan
+Joern Wanke
+Ping Ping Xiu
+Andrew Ziem
+Oscar Zuniga
+
+Community Contributors:
+Zdenko Podobný (Maintainer)
+Jim Regan (Maintainer)
+James R Barlow
+Amit Dovev
+Martin Ettl
+Tom Morris
+Tobias Müller
+Egor Pugin
+Sundar M. Vaidya
+Stefan Weil

thirdparty/Tesseract-OCR/doc/COPYING

@@ -0,0 +1,21 @@
+This package contains the Tesseract Open Source OCR Engine.
+Originally developed at Hewlett Packard Laboratories Bristol and
+at Hewlett Packard Co, Greeley Colorado, all the code
+in this distribution is now licensed under the Apache License:
+
+** Licensed under the Apache License, Version 2.0 (the "License");
+** you may not use this file except in compliance with the License.
+** You may obtain a copy of the License at
+** http://www.apache.org/licenses/LICENSE-2.0
+** Unless required by applicable law or agreed to in writing, software
+** distributed under the License is distributed on an "AS IS" BASIS,
+** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+** See the License for the specific language governing permissions and
+** limitations under the License.
+
+
+Other Dependencies and Licenses:
+================================
+
+Tesseract uses Leptonica library (http://leptonica.com/) which essentially
+uses a BSD 2-clause license. (http://leptonica.com/about-the-license.html)

thirdparty/Tesseract-OCR/doc/README

@@ -0,0 +1,43 @@
+How to run UNLV tests.
+
+The scripts in this directory make it possible to duplicate the tests
+published in the Fourth Annual Test of OCR Accuracy.
+See http://www.isri.unlv.edu/downloads/AT-1995.pdf
+but first you have to get the tools and data from UNLV:
+
+Step 1: to download the images goto
+http://www.isri.unlv.edu/ISRI/OCRtk
+and get 3b.tgz, Bb.tgz, Mb.tgz and Nb.tgz.
+
+Step 2: extract the files. It doesn't really matter where
+in your filesystem you put them, but they must go under a common
+root so you have directories 3, B, M and N in, for example,
+/users/me/ISRI-OCRtk.
+
+Step 3: Reorg the files
+The lack of tif extensions on the images is inconvenient, so there
+is a script to reorganize the data to match the rest of the test
+scripts.
+cd to /users/me/ISRI-OCRtk or wherever 3, B, M and N ended up and run
+/blah/blah/tesseract-ocr/testing/reorgdata.sh 3B
+This makes directories doe3.3B, bus.3B, mag.3B and news.3B.
+You can now get rid of 3, B, M, and N unless you want to get some of the
+other scanning resolutions out of them.
+
+Step 4: Download the ISRI toolkit from:
+http://www.isri.unlv.edu/downloads/ftk-1.0.tgz
+
+Step 5: If they work for you, use the binaries directly from the bin
+directory and put them in tesseract-ocr/testing/unlv
+otherwise build the tools for yourself and put them there.
+
+Step 6: cd back to your main tesseract-ocr dir and Build tesseract.
+
+Step 7: run testing/runalltests.sh with the root data dir and testname:
+testing/runalltests.sh /users/me/ISRI-OCRtk tess2.0
+and go to the gym, have lunch etc.
+
+Step 8: There should be a file
+testing/reports/tess2.0.summary that contains the final summarized accuracy
+report and comparison with the 1995 results.
+

thirdparty/Tesseract-OCR/tessdata/configs/ambigs.train

@@ -0,0 +1,7 @@
+tessedit_ambigs_training	1
+load_freq_dawg	0
+load_punc_dawg	0
+load_system_dawg	0
+load_number_dawg	0
+ambigs_debug_level	3
+load_fixed_length_dawgs	0

thirdparty/Tesseract-OCR/tessdata/configs/api_config

@@ -0,0 +1 @@
+tessedit_zero_rejection T

thirdparty/Tesseract-OCR/tessdata/configs/bigram

@@ -0,0 +1,5 @@
+load_bigram_dawg	True
+tessedit_enable_bigram_correction	True
+tessedit_bigram_debug	3
+save_raw_choices	True
+save_alt_choices	True

thirdparty/Tesseract-OCR/tessdata/configs/box.train

@@ -0,0 +1,14 @@
+disable_character_fragments T
+file_type                   .bl
+textord_fast_pitch_test	T
+tessedit_single_match	0
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+il1_adaption_test 1
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+textord_no_rejects T

thirdparty/Tesseract-OCR/tessdata/configs/box.train.stderr

@@ -0,0 +1,15 @@
+file_type .bl
+#tessedit_use_nn F
+textord_fast_pitch_test T
+tessedit_single_match 0
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+il1_adaption_test 1
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+#textord_repeat_extraction F
+textord_no_rejects T

thirdparty/Tesseract-OCR/tessdata/configs/digits

@@ -0,0 +1 @@
+tessedit_char_whitelist 0123456789-.

thirdparty/Tesseract-OCR/tessdata/configs/hocr

@@ -0,0 +1,3 @@
+tessedit_create_hocr 1
+tessedit_pageseg_mode 1
+hocr_font_info 0

thirdparty/Tesseract-OCR/tessdata/configs/inter

@@ -0,0 +1,2 @@
+interactive_display_mode				T
+tessedit_display_outwords		T

thirdparty/Tesseract-OCR/tessdata/configs/kannada

@@ -0,0 +1,4 @@
+textord_skewsmooth_offset 8
+textord_skewsmooth_offset2 8
+textord_merge_desc 0.5
+textord_no_rejects 1

thirdparty/Tesseract-OCR/tessdata/configs/linebox

@@ -0,0 +1,2 @@
+tessedit_resegment_from_line_boxes 1
+tessedit_make_boxes_from_boxes 1

thirdparty/Tesseract-OCR/tessdata/configs/logfile

@@ -0,0 +1 @@
+debug_file tesseract.log

thirdparty/Tesseract-OCR/tessdata/configs/makebox

@@ -0,0 +1 @@
+tessedit_create_boxfile 1

thirdparty/Tesseract-OCR/tessdata/configs/pdf

@@ -0,0 +1,2 @@
+tessedit_create_pdf 1
+tessedit_pageseg_mode 1

thirdparty/Tesseract-OCR/tessdata/configs/quiet

@@ -0,0 +1 @@
+debug_file /dev/null

thirdparty/Tesseract-OCR/tessdata/configs/rebox

@@ -0,0 +1,2 @@
+tessedit_resegment_from_boxes 1
+tessedit_make_boxes_from_boxes 1

thirdparty/Tesseract-OCR/tessdata/configs/strokewidth

@@ -0,0 +1,12 @@
+textord_show_blobs 0
+textord_debug_tabfind 3
+textord_tabfind_show_partitions 1
+textord_tabfind_show_initial_partitions 1
+textord_tabfind_show_columns 1
+textord_tabfind_show_blocks 1
+textord_tabfind_show_initialtabs 1
+textord_tabfind_show_finaltabs 1
+textord_tabfind_show_strokewidths 1
+textord_tabfind_show_vlines 0
+textord_tabfind_show_images 1
+tessedit_dump_pageseg_images 0

thirdparty/Tesseract-OCR/tessdata/configs/tsv

@@ -0,0 +1,2 @@
+tessedit_create_tsv 1
+tessedit_pageseg_mode 1

thirdparty/Tesseract-OCR/tessdata/configs/txt

@@ -0,0 +1,3 @@
+# This config file should be used with other cofig files which creates renderers.
+# usage example: tesseract eurotext.tif eurotext txt hocr pdf
+tessedit_create_txt 1

thirdparty/Tesseract-OCR/tessdata/configs/unlv

@@ -0,0 +1,2 @@
+tessedit_write_unlv 1
+tessedit_pageseg_mode 6

thirdparty/Tesseract-OCR/tessdata/eng.cube.fold

@@ -0,0 +1,12 @@
+0oO
+lI1
+cC
+kK
+pP
+sS
+uU
+vV
+wW
+xX
+yY
+zZ

thirdparty/Tesseract-OCR/tessdata/eng.cube.lm

@@ -0,0 +1,7 @@
+LeadPunc="({[`'
+TrailPunc=}:;-]!?`,.)"'
+NumLeadPunc=#({[@$
+NumTrailPunc=}):;].,%
+Operators=*+-/.:,()[]
+Digits=0123456789
+Alphas=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ

thirdparty/Tesseract-OCR/tessdata/eng.cube.params

@@ -0,0 +1,14 @@
+RecoWgt=1.0
+SizeWgt=0.2435
+OODWgt=0.0214
+NumWgt=0.036
+CharBigramsWgt=0.1567
+MaxSegPerChar=8
+BeamWidth=10
+ConvGridSize=48
+WordUnigramsWgt=0.01
+MaxWordAspectRatio=20.0000
+MinSpaceHeightRatio=0.5000
+MaxSpaceHeightRatio=0.6000
+HistWindWid=2
+MinConCompSize=0

thirdparty/Tesseract-OCR/tessdata/eng.user-patterns

@@ -0,0 +1,2 @@
+1-\d\d\d-GOOG-411
+www.\n\\\*.com

thirdparty/Tesseract-OCR/tessdata/eng.user-words

@@ -0,0 +1,5 @@
+the
+quick
+brown
+fox
+jumped

thirdparty/Tesseract-OCR/tessdata/tessconfigs/batch

@@ -0,0 +1,2 @@
+# No content needed as all defaults are correct.
+

thirdparty/Tesseract-OCR/tessdata/tessconfigs/batch.nochop

@@ -0,0 +1,2 @@
+chop_enable 0
+wordrec_enable_assoc 0

thirdparty/Tesseract-OCR/tessdata/tessconfigs/matdemo

@@ -0,0 +1,7 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger   1
+matcher_debug_flags         6
+matcher_debug_level       1

thirdparty/Tesseract-OCR/tessdata/tessconfigs/msdemo

@@ -0,0 +1,13 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger	1
+matcher_debug_flags         6
+matcher_debug_level       1
+
+wordrec_display_splits          0
+wordrec_display_all_words       1
+wordrec_display_all_blobs       1
+wordrec_display_segmentations   2
+classify_debug_level		1

thirdparty/Tesseract-OCR/tessdata/tessconfigs/nobatch

@@ -0,0 +1 @@
+