From c94d3de87240ea9451c0d8cba24399dfa9a2d311 Mon Sep 17 00:00:00 2001
From: millmanorama <millmanorama@gmail.com>
Date: Wed, 14 Dec 2016 17:17:45 +0100
Subject: [PATCH] move encoding options to StringsTextExtractor

---
 .../autopsy/keywordsearch/FileTextExtractor.java |  8 --------
 ...KeywordSearchGlobalLanguageSettingsPanel.java | 12 ++++++------
 .../KeywordSearchJobSettingsPanel.java           |  4 ++--
 .../keywordsearch/KeywordSearchSettings.java     |  9 ++++-----
 .../keywordsearch/StringsTextExtractor.java      | 16 +++++++++++-----
 5 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileTextExtractor.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileTextExtractor.java
index bec832f8df..2103ebb5a4 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileTextExtractor.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileTextExtractor.java
@@ -28,14 +28,6 @@ import org.sleuthkit.datamodel.AbstractFile;
  */
 abstract class FileTextExtractor<AppendixProvider> extends TextExtractor<AppendixProvider, AbstractFile> {
 
-    /**
-     * Common options that can be used by some extractors
-     */
-    enum ExtractOptions {
-
-        EXTRACT_UTF16, ///< extract UTF16 text, possible values Boolean.TRUE.toString(), Boolean.FALSE.toString()
-        EXTRACT_UTF8, ///< extract UTF8 text, possible values Boolean.TRUE.toString(), Boolean.FALSE.toString()
-    };
 
     static final List<String> BLOB_MIME_TYPES
             = Arrays.asList(
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.java
index c1f1e2a5a7..9e58235318 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchGlobalLanguageSettingsPanel.java
@@ -103,12 +103,12 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
 
     private void reloadScriptsCheckBoxes() {
         boolean utf16
-                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
+                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
 
         enableUTF16Checkbox.setSelected(utf16);
 
         boolean utf8
-                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
+                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
         enableUTF8Checkbox.setSelected(utf8);
 
         final List<SCRIPT> serviceScripts = KeywordSearchSettings.getStringExtractScripts();
@@ -127,12 +127,12 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
         reloadScriptsCheckBoxes();
 
         boolean utf16
-                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
+                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
 
         enableUTF16Checkbox.setSelected(utf16);
 
         boolean utf8
-                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
+                = Boolean.parseBoolean(KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
         enableUTF8Checkbox.setSelected(utf8);
         final boolean extractEnabled = utf16 || utf8;
 
@@ -257,9 +257,9 @@ class KeywordSearchGlobalLanguageSettingsPanel extends javax.swing.JPanel implem
 
     @Override
     public void store() {
-        KeywordSearchSettings.setStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString(),
+        KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString(),
                 Boolean.toString(enableUTF8Checkbox.isSelected()));
-        KeywordSearchSettings.setStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(),
+        KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(),
                 Boolean.toString(enableUTF16Checkbox.isSelected()));
 
         if (toUpdate != null) {
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchJobSettingsPanel.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchJobSettingsPanel.java
index 123878e92f..5515b10115 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchJobSettingsPanel.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchJobSettingsPanel.java
@@ -101,8 +101,8 @@ public final class KeywordSearchJobSettingsPanel extends IngestModuleIngestJobSe
     }
 
     private void displayEncodings() {
-        String utf8 = KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString());
-        String utf16 = KeywordSearchSettings.getStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString());
+        String utf8 = KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString());
+        String utf16 = KeywordSearchSettings.getStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString());
         ArrayList<String> encodingsList = new ArrayList<>();
         if (utf8 == null || Boolean.parseBoolean(utf8)) {
             encodingsList.add("UTF8");
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchSettings.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchSettings.java
index cd5702722b..0550978442 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchSettings.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchSettings.java
@@ -23,7 +23,6 @@ import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 import java.util.logging.Level;
-
 import org.openide.util.NbBundle;
 import org.sleuthkit.autopsy.coreutils.Logger;
 import org.sleuthkit.autopsy.coreutils.ModuleSettings;
@@ -211,14 +210,14 @@ class KeywordSearchSettings {
             KeywordSearchSettings.setUpdateFrequency(UpdateFrequency.DEFAULT);
         }
         //setting default Extract UTF8
-        if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_OPTIONS, FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString())) {
+        if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_OPTIONS, StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString())) {
             logger.log(Level.INFO, "No configuration for UTF8 found, generating default..."); //NON-NLS
-            KeywordSearchSettings.setStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString(), Boolean.TRUE.toString());
+            KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF8.toString(), Boolean.TRUE.toString());
         }
         //setting default Extract UTF16
-        if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_OPTIONS, FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString())) {
+        if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_OPTIONS, StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString())) {
             logger.log(Level.INFO, "No configuration for UTF16 found, generating defaults..."); //NON-NLS
-            KeywordSearchSettings.setStringExtractOption(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(), Boolean.TRUE.toString());
+            KeywordSearchSettings.setStringExtractOption(StringsTextExtractor.ExtractOptions.EXTRACT_UTF16.toString(), Boolean.TRUE.toString());
         }
         //setting default Latin-1 Script
         if (!ModuleSettings.settingExists(KeywordSearchSettings.PROPERTIES_SCRIPTS, SCRIPT.LATIN_1.name())) {
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/StringsTextExtractor.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/StringsTextExtractor.java
index 165bcd7591..8bf8d21910 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/StringsTextExtractor.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/StringsTextExtractor.java
@@ -38,8 +38,14 @@ import org.sleuthkit.datamodel.TskException;
  * Solr.
  */
 class StringsTextExtractor extends FileTextExtractor<Void> {
+    /**
+     * Common options that can be used by some extractors
+     */
+    enum ExtractOptions {
 
-    private static final long MAX_STRING_CHUNK_SIZE = 1 * 1024 * 1024L;
+        EXTRACT_UTF16, ///< extract UTF16 text, possible values Boolean.TRUE.toString(), Boolean.FALSE.toString()
+        EXTRACT_UTF8, ///< extract UTF8 text, possible values Boolean.TRUE.toString(), Boolean.FALSE.toString()
+    };
     private final List<SCRIPT> extractScripts = new ArrayList<>();
     private Map<String, String> extractOptions = new HashMap<>();
 
@@ -92,8 +98,8 @@ class StringsTextExtractor extends FileTextExtractor<Void> {
 
     @Override
     boolean noExtractionOptionsAreEnabled() {
-        boolean extractUTF8 = Boolean.parseBoolean(extractOptions.get(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
-        boolean extractUTF16 = Boolean.parseBoolean(extractOptions.get(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
+        boolean extractUTF8 = Boolean.parseBoolean(extractOptions.get(ExtractOptions.EXTRACT_UTF8.toString()));
+        boolean extractUTF16 = Boolean.parseBoolean(extractOptions.get(ExtractOptions.EXTRACT_UTF16.toString()));
 
         return extractUTF8 == false && extractUTF16 == false;
     }
@@ -118,8 +124,8 @@ class StringsTextExtractor extends FileTextExtractor<Void> {
      */
     @Override
     InputStream getInputStream(AbstractFile sourceFile) {
-        boolean extractUTF8 = Boolean.parseBoolean(extractOptions.get(FileTextExtractor.ExtractOptions.EXTRACT_UTF8.toString()));
-        boolean extractUTF16 = Boolean.parseBoolean(extractOptions.get(FileTextExtractor.ExtractOptions.EXTRACT_UTF16.toString()));
+        boolean extractUTF8 = Boolean.parseBoolean(extractOptions.get(ExtractOptions.EXTRACT_UTF8.toString()));
+        boolean extractUTF16 = Boolean.parseBoolean(extractOptions.get(ExtractOptions.EXTRACT_UTF16.toString()));
 
         //check which extract stream to use
         InputStream stringStream = extractScripts.size() == 1 && extractScripts.get(0).equals(SCRIPT.LATIN_1)