Skip detecting content renames for large files

There are two code paths for detecting renames: one on tree diffs
(using DiffFormatter#scan) and the other on single file diffs (using
DiffFormatter#format). The latter skips binary and large files
for rename detection - check [1], but the former doesn't.

This change skips content rename detection for the tree diffs case for
large files. This is essential to avoid expensive computations while
reading the file, especially for callers who don't want to pay that
cost. Content renames are those which involve files with slightly
modified content. Exact renames will still be identified.

The default threshold for file sizes is reused from
PackConfig.DEFAULT_BIG_FILE_THRESHOLD: 50 MB.

[1] https://git.eclipse.org/r/plugins/gitiles/jgit/jgit/+/232876421d067a1242e8afcaa33b9171342fee3e/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java#386

Change-Id: Idbc2c29bd381c6e387185204638f76fda47df41e
Signed-off-by: Youssef Elghareeb <ghareeb@google.com>

1 files changed, 48 insertions, 0 deletions

diff --git a/org.eclipse.jgit.test/tst/org/eclipse/jgit/diff/RenameDetectorTest.java b/org.eclipse.jgit.test/tst/org/eclipse/jgit/diff/RenameDetectorTest.java
index 6203feda48..2ea3cd7ebe 100644
--- a/org.eclipse.jgit.test/tst/org/eclipse/jgit/diff/RenameDetectorTest.java
+++ b/org.eclipse.jgit.test/tst/org/eclipse/jgit/diff/RenameDetectorTest.java
@@ -543,6 +543,43 @@ public class RenameDetectorTest extends RepositoryTestCase {
 	}
 
 	@Test
+	public void testExactRename_LargeFile() throws Exception {
+		ObjectId aId = blob("blah\nblah\nfoo"); // size = 14
+
+		DiffEntry a = DiffEntry.add(PATH_A, aId);
+		DiffEntry b = DiffEntry.delete(PATH_Q, aId);
+
+		rd.add(a);
+		rd.add(b);
+
+		// Exact renames are identified for large files
+		rd.setBigFileThreshold(10);
+		List<DiffEntry> entries = rd.compute();
+		assertEquals(1, entries.size());
+		assertRename(b, a, 100, entries.get(0));
+	}
+
+	@Test
+	public void testInexactRename_LargeFile() throws Exception {
+		ObjectId aId = blob("blah\nblah\nfoo"); // size = 14
+		ObjectId bId = blob("bla\nblah\nfoo"); // size = 13
+
+		DiffEntry a = DiffEntry.add(PATH_A, aId);
+		DiffEntry b = DiffEntry.delete(PATH_Q, bId);
+
+		rd.add(a);
+		rd.add(b);
+
+		rd.setBigFileThreshold(10);
+
+		// Inexact renames are not detected for large files
+		List<DiffEntry> entries = rd.compute();
+		assertEquals(2, entries.size());
+		assertAdd(PATH_A, aId, FileMode.REGULAR_FILE, entries.get(0));
+		assertDelete(PATH_Q, bId, FileMode.REGULAR_FILE, entries.get(1));
+	}
+
+	@Test
 	public void testSetRenameScore_IllegalArgs() throws Exception {
 		try {
 			rd.setRenameScore(-1);
@@ -634,4 +671,15 @@ public class RenameDetectorTest extends RepositoryTestCase {
 		assertEquals(AbbreviatedObjectId.fromObjectId(newId), add.newId);
 		assertEquals(newMode, add.newMode);
 	}
+
+	private static void assertDelete(String oldName, ObjectId oldId,
+			FileMode oldMode, DiffEntry delete) {
+		assertEquals(DiffEntry.DEV_NULL, delete.newPath);
+		assertEquals(DiffEntry.A_ZERO, delete.newId);
+		assertEquals(FileMode.MISSING, delete.newMode);
+		assertEquals(ChangeType.DELETE, delete.changeType);
+		assertEquals(oldName, delete.oldPath);
+		assertEquals(AbbreviatedObjectId.fromObjectId(oldId), delete.oldId);
+		assertEquals(oldMode, delete.oldMode);
+	}
 }