Merge pull request #3760 from eugene7646/ocr_via_tika_3760

OCR via tika (3760)

Core/build.xml

@@ -39,6 +39,11 @@
         <copy todir="${basedir}/release/Volatility" >
             <fileset dir="${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}" />

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">
-              <EmptySpace max="-2" attributes="0"/>
+          <Group type="102" attributes="0">
               <Group type="103" groupAlignment="0" attributes="0">
-                  <Component id="ingestSettingsLabel" alignment="0" min="-2" max="-2" attributes="0"/>
-                  <Group type="102" attributes="0">
-                      <EmptySpace min="10" pref="10" max="-2" attributes="0"/>
+                  <Group type="102" alignment="0" 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="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

@@ -40,7 +40,7 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
     private final Map<String, StringExtract.StringExtractUnicodeTable.SCRIPT> scripts = new HashMap<>();
     private ActionListener updateLanguagesAction;
     private List<SCRIPT> toUpdate;
-
+    
     KeywordSearchGlobalLanguageSettingsPanel() {
         initComponents();
         customizeComponents();
@@ -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)))
-                    .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)))
+                            .addComponent(enableUTF8Checkbox)
+                            .addComponent(enableOcrCheckbox))))
                 .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

@@ -38,7 +38,9 @@ class KeywordSearchSettings {
     static final String PROPERTIES_NSRL = NbBundle.getMessage(KeywordSearchSettings.class, "KeywordSearchSettings.propertiesNSRL.text", MODULE_NAME);
     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 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;
@@ -127,7 +129,27 @@ class KeywordSearchSettings {
         stringExtractOptions.put(key, val);
         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;
 
@@ -53,6 +59,10 @@ class TikaTextExtractor extends ContentTextExtractor {
     private final ExecutorService tikaParseExecutor = Executors.newSingleThreadExecutor();
 
     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())
@@ -79,6 +89,30 @@ class TikaTextExtractor extends ContentTextExtractor {
         officeParserConfig.setUseSAXPptxExtractor(true);
         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));
@@ -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 @@
+

thirdparty/Tesseract-OCR/tessdata/tessconfigs/segdemo

@@ -0,0 +1,10 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+wordrec_display_splits          0
+wordrec_display_all_words       1
+wordrec_display_all_blobs       1
+wordrec_display_segmentations   2
+classify_debug_level		1
+stopper_debug_level 1