5078-HTML-viewer-not-correctly-interpreting-Unicode

Determine encoding of html file and display html file using encoding.

Core/ivy.xml

@@ -44,6 +44,7 @@
         <dependency conf="core->default" org="org.apache.opennlp" name="opennlp-tools" rev="1.9.1"/>
         
         <dependency org="org.sejda.webp-imageio" name="webp-imageio-sejda" rev="0.1.0"/>
+        <dependency org="net.sourceforge.jchardet" name="jchardet" rev="1.0"/>
         
         <dependency conf="core->default" org="commons-validator" name="commons-validator" rev="1.6"/>
         <dependency conf="core->default" org="net.htmlparser.jericho" name="jericho-html" rev="3.3"/>

Core/nbproject/project.properties

@@ -35,6 +35,7 @@ file.reference.java-libpst-0.8.1.jar=release\\modules\\ext\\java-libpst-0.8.1.ja
 file.reference.javax.activation-1.2.0.jar=release\\modules\\ext\\javax.activation-1.2.0.jar
 file.reference.javax.annotation-api-1.3.2.jar=release\\modules\\ext\\javax.annotation-api-1.3.2.jar
 file.reference.jbig2-imageio-3.0.2.jar=release\\modules\\ext\\jbig2-imageio-3.0.2.jar
+file.reference.jchardet-1.0.jar=release/modules/ext/jchardet-1.0.jar
 file.reference.jcl-over-slf4j-1.7.25.jar=release\\modules\\ext\\jcl-over-slf4j-1.7.25.jar
 file.reference.jdom-2.0.5-contrib.jar=release/modules/ext/jdom-2.0.5-contrib.jar
 file.reference.jdom-2.0.5.jar=release/modules/ext/jdom-2.0.5.jar

Core/nbproject/project.xml

@@ -517,6 +517,14 @@
                 <runtime-relative-path>ext/google-http-client-1.29.0.jar</runtime-relative-path>
                 <binary-origin>release/modules/ext/google-http-client-1.29.0.jar</binary-origin>
             </class-path-extension>
+            <class-path-extension>
+                <runtime-relative-path>ext/sleuthkit-postgresql-4.7.0.jar</runtime-relative-path>
+                <binary-origin>release/modules/ext/sleuthkit-postgresql-4.7.0.jar</binary-origin>
+            </class-path-extension>
+            <class-path-extension>
+                <runtime-relative-path>ext/jchardet-1.0.jar</runtime-relative-path>
+                <binary-origin>release/modules/ext/jchardet-1.0.jar</binary-origin>
+            </class-path-extension>
             <class-path-extension>
                 <runtime-relative-path>ext/bcpkix-jdk15on-1.60.jar</runtime-relative-path>
                 <binary-origin>release\modules\ext\bcpkix-jdk15on-1.60.jar</binary-origin>
@@ -605,10 +613,6 @@
                 <runtime-relative-path>ext/jbig2-imageio-3.0.2.jar</runtime-relative-path>
                 <binary-origin>release\modules\ext\jbig2-imageio-3.0.2.jar</binary-origin>
             </class-path-extension>
-            <class-path-extension>
-                <runtime-relative-path>ext/sleuthkit-postgresql-4.7.0.jar</runtime-relative-path>
-                <binary-origin>release/modules/ext/sleuthkit-postgresql-4.7.0.jar</binary-origin>
-            </class-path-extension>
             <class-path-extension>
                 <runtime-relative-path>ext/apache-mime4j-dom-0.8.2.jar</runtime-relative-path>
                 <binary-origin>release\modules\ext\apache-mime4j-dom-0.8.2.jar</binary-origin>

Core/src/org/sleuthkit/autopsy/contentviewers/HtmlViewer.java

@@ -20,9 +20,11 @@ package org.sleuthkit.autopsy.contentviewers;
 
 import java.awt.Component;
 import java.awt.Cursor;
+import java.io.UnsupportedEncodingException;
 import java.util.Arrays;
 import java.util.List;
 import java.util.logging.Level;
+import org.mozilla.universalchardet.UniversalDetector;
 import org.openide.util.NbBundle;
 import org.openide.windows.WindowManager;
 import org.sleuthkit.autopsy.coreutils.Logger;
@@ -65,14 +67,37 @@ final class HtmlViewer extends javax.swing.JPanel implements FileTypeViewer {
             int fileSize = (int) abstractFile.getSize();
             byte[] buffer = new byte[fileSize];
             abstractFile.read(buffer, 0, fileSize);
-            return new String(buffer);
+            String encoding = determineEncoding(buffer);
-        } catch (TskCoreException ex) {
+            if (encoding != null) {
+                return new String(buffer, encoding);
+            } else {
+                return new String(buffer);
+            }
+        } catch (TskCoreException | UnsupportedEncodingException ex) {
             logger.log(Level.SEVERE, String.format("Unable to read from file '%s' (id=%d).",
                     abstractFile.getName(), abstractFile.getId()), ex);
             return String.format("<p>%s</p>", Bundle.HtmlViewer_file_error());
         }
     }
 
+    /**
+     * This method will try and determine the encoding of the html file based on its contents
+     * 
+     * @param buffer byte array of the html file to check
+     * 
+     * @return encoding type, null if encoding could not be determined
+     */
+    private String determineEncoding(byte[] buffer) {
+        UniversalDetector detector = new UniversalDetector(null);
+
+        detector.handleData(buffer, 0, buffer.length - 1);
+        detector.dataEnd();
+
+        String encoding = detector.getDetectedCharset();
+        detector.reset();
+        return encoding;
+    }
+
     /**
      * This method is called from within the constructor to initialize the form.
      * WARNING: Do NOT modify this code. The content of this method is always