Hello,
I'm reading the code for Bloom Filter to see if arXiv:2012.00472
could be an improvement.
I'm not sure if I'm missing something or it's our test-bloom generate_filter
doesn't really support testing for multiple inputs.
If I understand correctly, we should either:
* allocate more entry for inputs; or
* abort if argc != 3
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 46e97b04eb..1026facc59 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -68,12 +68,14 @@ int cmd__bloom(int argc, const char **argv)
if (!strcmp(argv[1], "generate_filter")) {
struct bloom_filter filter;
int i = 2;
- filter.len = (settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
- filter.data = xcalloc(filter.len, sizeof(unsigned char));
if (argc - 1 < i)
usage(bloom_usage);
+ filter.len = (settings.bits_per_entry * (argc - 2) + BITS_PER_WORD - 1)
+ / BITS_PER_WORD;
+ filter.data = xcalloc(filter.len, sizeof(unsigned char));
+
while (argv[i]) {
add_string_to_filter(argv[i], &filter);
i++;
diff --git a/t/t0095-bloom.sh b/t/t0095-bloom.sh
index 7e4ab1795f..6d83927c86 100755
--- a/t/t0095-bloom.sh
+++ b/t/t0095-bloom.sh
@@ -67,6 +67,17 @@ test_expect_success 'compute bloom key for test string 2' '
test_cmp expect actual
'
+test_expect_success 'compute bloom key for multiple string' '
+ cat >expect <<-\EOF &&
+ Hashes:0xb270de9b|0x1bb6f26e|0x84fd0641|0xee431a14|0x57892de7|0xc0cf41ba|0x2a15558d|
+ Hashes:0x20ab385b|0xf5237fe2|0xc99bc769|0x9e140ef0|0x728c5677|0x47049dfe|0x1b7ce585|
+ Filter_Length:3
+ Filter_Data:45|ba|ac|
+ EOF
+ test-tool bloom generate_filter "Hello world!" file.txt >actual &&
+ test_cmp expect actual
+'
+
test_expect_success 'get bloom filters for commit with no changes' '
git init &&
git commit --allow-empty -m "c0" &&
--
Danh
