From 1c5bc6971e28c581b17b812cbbd1f09e39f0bb63 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Sat, 13 Jan 2024 04:26:13 +0000 Subject: diffcore-delta: avoid ignoring final 'line' of file hash_chars() would hash lines to integers, and store them in a spanhash, but cut lines at 64 characters. Thus, whenever it reached 64 characters or a newline, it would create a new spanhash. The problem is, the final part of the file might not end 64 characters after the previous 'line' and might not end with a newline. This could, for example, cause an 85-byte file with 12 lines and only the first character in the file differing to appear merely 23% similar rather than the expected 97%. Ensure the last line is included, and add a testcase that would have caught this problem. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- diffcore-delta.c | 4 ++++ t/t4001-diff-rename.sh | 24 ++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/diffcore-delta.c b/diffcore-delta.c index 18d8f766d7..0b45f64400 100644 --- a/diffcore-delta.c +++ b/diffcore-delta.c @@ -159,6 +159,10 @@ static struct spanhash_top *hash_chars(struct repository *r, n = 0; accum1 = accum2 = 0; } + if (n > 0) { + hashval = (accum1 + accum2 * 0x61) % HASHBASE; + hash = add_spanhash(hash, hashval, n); + } QSORT(hash->data, (size_t)1ul << hash->alloc_log2, spanhash_cmp); return hash; } diff --git a/t/t4001-diff-rename.sh b/t/t4001-diff-rename.sh index 3dc9047044..c0d88e5e0d 100755 --- a/t/t4001-diff-rename.sh +++ b/t/t4001-diff-rename.sh @@ -286,4 +286,28 @@ test_expect_success 'basename similarity vs best similarity' ' test_cmp expected actual ' +test_expect_success 'last line matters too' ' + { + test_write_lines a 0 1 2 3 4 5 6 7 8 9 && + printf "git ignores final up to 63 characters if not newline terminated" + } >no-final-lf && + git add no-final-lf && + git commit -m "original version of file with no final newline" && + + # Change ONLY the first character of the whole file + { + test_write_lines b 0 1 2 3 4 5 6 7 8 9 && + printf "git ignores final up to 63 characters if not newline terminated" + } >no-final-lf && + git add no-final-lf && + git mv no-final-lf still-absent-final-lf && + git commit -a -m "rename no-final-lf -> still-absent-final-lf" && + git diff-tree -r -M --name-status HEAD^ HEAD >actual && + sed -e "s/^R[0-9]* /R /" actual >actual.munged && + cat >expected <<-\EOF && + R no-final-lf still-absent-final-lf + EOF + test_cmp expected actual.munged +' + test_done -- cgit 1.2.3-korg