From 48da203239a1cd181aa5b56004ff1d2e12f74567 Mon Sep 17 00:00:00 2001
From: apriestman <apriestman@basistech.com>
Date: Thu, 5 Nov 2020 14:14:21 -0500
Subject: [PATCH] Stop hashing if EOF is found.
Keep track of how many bytes are written to the EncodedFileOutputStream.
---
.../datamodel/EncodedFileOutputStream.java | 20 +++++++++++++++++--
.../org/sleuthkit/datamodel/HashUtility.java | 7 ++++++-
2 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/bindings/java/src/org/sleuthkit/datamodel/EncodedFileOutputStream.java b/bindings/java/src/org/sleuthkit/datamodel/EncodedFileOutputStream.java
index f181b936f..7c0183e1d 100644
--- a/bindings/java/src/org/sleuthkit/datamodel/EncodedFileOutputStream.java
+++ b/bindings/java/src/org/sleuthkit/datamodel/EncodedFileOutputStream.java
@@ -30,7 +30,8 @@
*/
public class EncodedFileOutputStream extends BufferedOutputStream {
- private TskData.EncodingType type;
+ private final TskData.EncodingType type;
+ private long encodedDataLength;
/**
* Create an encoded output stream using the specified encoding.
@@ -43,6 +44,7 @@ public class EncodedFileOutputStream extends BufferedOutputStream {
public EncodedFileOutputStream(OutputStream out, TskData.EncodingType type) throws IOException {
super(out);
this.type = type;
+ encodedDataLength = 0;
writeHeader();
}
@@ -65,11 +67,13 @@ public EncodedFileOutputStream(OutputStream out, int size, TskData.EncodingType
private void writeHeader() throws IOException {
// We get the encoded header here so it will be in plaintext after encoding
write(EncodedFileUtil.getEncodedHeader(type), 0, EncodedFileUtil.getHeaderLength());
+ encodedDataLength -= EncodedFileUtil.getHeaderLength();
}
@Override
public void write(int b) throws IOException {
super.write((int) EncodedFileUtil.encodeByte((byte) b, type));
+ encodedDataLength++;
}
@Override
@@ -83,5 +87,17 @@ public void write(byte[] b,
}
super.write(encodedData, off, len);
+ encodedDataLength += len;
}
-}
+
+ /**
+ * Get the number of bytes written to the file, excluding header bytes.
+ * This is needed for storing the original length of the file in the
+ * tsk_files table in cases where we don't know the size in advance.
+ *
+ * @return the number of bytes written to the stream, excluding the header.
+ */
+ public long getBytesWritten() {
+ return encodedDataLength;
+ }
+}
\ No newline at end of file
diff --git a/bindings/java/src/org/sleuthkit/datamodel/HashUtility.java b/bindings/java/src/org/sleuthkit/datamodel/HashUtility.java
index d8618b0ee..4ce6e192e 100644
--- a/bindings/java/src/org/sleuthkit/datamodel/HashUtility.java
+++ b/bindings/java/src/org/sleuthkit/datamodel/HashUtility.java
@@ -68,6 +68,11 @@ static public List<HashResult> calculateHashes(Content content, Collection<HashT
} catch (TskCoreException ex) {
throw new TskCoreException("Error reading data at address " + i * BUFFER_SIZE + " from content with ID: " + content.getId(), ex);
}
+
+ // Check for EOF
+ if (read == -1) {
+ break;
+ }
// Only update with the read bytes.
if (read == BUFFER_SIZE) {
@@ -228,4 +233,4 @@ static public String calculateMd5Hash(Content content) throws IOException {
throw new IOException(ex);
}
}
-}
+}
\ No newline at end of file
--
GitLab