From a914e4b76e0e3981af00d11da182957a18c47e7f Mon Sep 17 00:00:00 2001
From: Ethan Roseman <eroseman@basistech.com>
Date: Thu, 21 Nov 2019 10:42:17 +0900
Subject: [PATCH] Further refactoring

---
 .../autopsy/textextractors/TextExtractor.java | 11 --------
 .../textextractors/TextExtractorFactory.java  |  1 +
 .../textextractors/TextFileExtractor.java     | 27 +++++++++++++------
 .../KeywordSearchIngestModule.java            |  6 ++---
 4 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractor.java b/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractor.java
index 294e6b41af..5e9d99e065 100644
--- a/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractor.java
+++ b/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractor.java
@@ -18,21 +18,10 @@
  */
 package org.sleuthkit.autopsy.textextractors;
 
-import com.ethteck.decodetect.core.Decodetect;
-import com.ethteck.decodetect.core.DecodetectResult;
-import java.io.BufferedInputStream;
-import java.io.IOException;
-import java.io.InputStream;
 import java.io.Reader;
-import java.nio.charset.Charset;
-import java.nio.charset.CharsetDecoder;
-import java.nio.charset.CharsetEncoder;
 import java.util.Collections;
-import java.util.List;
 import java.util.Map;
 import org.openide.util.Lookup;
-import org.sleuthkit.datamodel.Content;
-import org.sleuthkit.datamodel.ReadContentInputStream;
 
 /**
  * Extracts the text out of Content instances and exposes them as a Reader.
diff --git a/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractorFactory.java b/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractorFactory.java
index 2c8316ba60..ff0ba51dd1 100755
--- a/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractorFactory.java
+++ b/Core/src/org/sleuthkit/autopsy/textextractors/TextExtractorFactory.java
@@ -89,6 +89,7 @@ public class TextExtractorFactory {
      */
     private static List<TextExtractor> getFileExtractors(AbstractFile content, Lookup context) {
         List<TextExtractor> fileExtractors = Arrays.asList(
+                new TextFileExtractor(content),
                 new HtmlTextExtractor(content),
                 new SqliteTextExtractor(content),
                 new TikaTextExtractor(content));
diff --git a/Core/src/org/sleuthkit/autopsy/textextractors/TextFileExtractor.java b/Core/src/org/sleuthkit/autopsy/textextractors/TextFileExtractor.java
index af24f94165..b0e77eb9ba 100644
--- a/Core/src/org/sleuthkit/autopsy/textextractors/TextFileExtractor.java
+++ b/Core/src/org/sleuthkit/autopsy/textextractors/TextFileExtractor.java
@@ -35,9 +35,9 @@ import org.sleuthkit.datamodel.Content;
 import org.sleuthkit.datamodel.ReadContentInputStream;
 
 /**
- * Extract text from .txt files
+ * Extract text from text files
  */
-public final class TextFileExtractor {
+public final class TextFileExtractor implements TextExtractor {
     public static Charset UNKNOWN_CHARSET = new Charset("unknown", null) {
         @Override
         public boolean contains(Charset cs) {
@@ -55,18 +55,29 @@ public final class TextFileExtractor {
         }
     };
 
-    public Reader getReader(AbstractFile source) throws TextFileExtractorException {
-        Charset encoding = getEncoding(source);
+    private final AbstractFile file;
+
+    public TextFileExtractor(AbstractFile file) {
+        this.file = file;
+    }
+
+    public Reader getReader() {
+        Charset encoding = getEncoding(file);
         if (encoding == UNKNOWN_CHARSET) {
             encoding = StandardCharsets.UTF_8;
         }
-        return getReader(source, encoding);
+        return getReader(encoding);
     }
 
-    public Reader getReader(AbstractFile source, Charset encoding) throws TextFileExtractorException {
-        return new InputStreamReader(new BufferedInputStream(new ReadContentInputStream(source)), encoding);
+    public Reader getReader(Charset encoding) {
+        return new InputStreamReader(new BufferedInputStream(new ReadContentInputStream(file)), encoding);
     }
-    
+
+    @Override
+    public boolean isSupported() {
+        return file.getMIMEType().equals("text/plain");
+    }
+
     public class TextFileExtractorException extends Exception {
         public TextFileExtractorException(String msg, Throwable ex) {
             super(msg, ex);
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
index 50788306a2..67e6d5076c 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
@@ -682,8 +682,8 @@ public final class KeywordSearchIngestModule implements FileIngestModule {
          */
         private boolean indexTextFile(AbstractFile aFile) {
             try {
-                TextFileExtractor textFileExtractor = new TextFileExtractor();
-                Reader textReader = textFileExtractor.getReader(aFile);
+                TextFileExtractor textFileExtractor = new TextFileExtractor(aFile);
+                Reader textReader = textFileExtractor.getReader();
                 if (textReader == null) {
                     logger.log(Level.INFO, "Unable to extract with TextFileExtractor, Reader was null for file: {0}", aFile.getName());
                 } else if (Ingester.getDefault().indexText(textReader, aFile.getId(), aFile.getName(), aFile, context)) {
@@ -692,8 +692,6 @@ public final class KeywordSearchIngestModule implements FileIngestModule {
                 }
             } catch (IngesterException ex) {
                 logger.log(Level.WARNING, "Unable to index " + aFile.getName(), ex);
-            } catch (TextFileExtractorException ex) {
-                logger.log(Level.INFO, "Could not extract text with TextFileExtractor", ex);
             }
             return false;
         }