ApplyCommand: use byte arrays for text patches, not strings

Instead of converting the patch bytes to strings apply the patch on
byte level, like C git does. Converting the input lines and the hunk
lines from bytes to strings and then applying the patch based on
strings may give surprising results if a patch converts a text file
from one encoding to another. Moreover, in the end we don't know which
encoding to use to write the result.

Previous code just wrote the result as UTF-8, which forcibly changed
the encoding if the original input had some other encoding (even if the
patch had the same non-UTF-8 encoding). It was also wrong if the input
was UTF-8, and the patch should have changed the encoding to something
else.

So use ByteBuffers instead of Strings. This has the additional advantage
that all these ByteBuffers can share the underlying byte arrays of the
input and of the patch, so it also reduces memory consumption.

Change-Id: I450975f2ba0e7d0bec8973e3113cc2e7aea187ee
Signed-off-by: Thomas Wolf <thomas.wolf@paranor.ch>

1 files changed, 23 insertions, 1 deletions

diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java b/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java
index 9f4b1fa493..d09da019dd 100644
--- a/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009, Google Inc.
- * Copyright (C) 2008-2009, Johannes E. Schindelin <johannes.schindelin@gmx.de> and others
+ * Copyright (C) 2008-2021, Johannes E. Schindelin <johannes.schindelin@gmx.de> and others
  *
  * This program and the accompanying materials are made available under the
  * terms of the Eclipse Distribution License v. 1.0 which is available at
@@ -16,6 +16,7 @@ import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.OutputStream;
+import java.nio.ByteBuffer;
 
 import org.eclipse.jgit.errors.BinaryBlobException;
 import org.eclipse.jgit.errors.LargeObjectException;
@@ -165,6 +166,27 @@ public class RawText extends Sequence {
 	}
 
 	/**
+	 * Get the raw text for a single line.
+	 *
+	 * @param i
+	 *            index of the line to extract. Note this is 0-based, so line
+	 *            number 1 is actually index 0.
+	 * @return the text for the line, without a trailing LF, as a
+	 *         {@link ByteBuffer} that is backed by a slice of the
+	 *         {@link #getRawContent() raw content}, with the buffer's position
+	 *         on the start of the line and the limit at the end.
+	 * @since 5.12
+	 */
+	public ByteBuffer getRawString(int i) {
+		int s = getStart(i);
+		int e = getEnd(i);
+		if (e > 0 && content[e - 1] == '\n') {
+			e--;
+		}
+		return ByteBuffer.wrap(content, s, e - s);
+	}
+
+	/**
 	 * Get the text for a region of lines.
 	 *
 	 * @param begin