arsenetar/dupeguru
1
0
Fork 0
mirror of https://github.com/arsenetar/dupeguru.git synced 2026-01-22 14:41:39 +00:00
Code Releases Wiki Activity

Add unit tests for hash sample optimization

Browse Source 
* Instead of keeping md5 samples separate, merge them as one hash computed from the various selected chunks we picked.
* We don't need to keep a boolean to see whether or not the user chose to optimize; we can simply compare the value of the threshold, since 0 means no optimization currently active.
This commit is contained in:
glubsy
2021-06-21 22:44:05 +02:00
parent e07dfd5955
commit 277bc3fbb8
7 changed files with 152 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
core/tests/scanner_test.py
View File

@@ -56,6 +56,7 @@ def test_default_settings(fake_fileexists):
eq_(s.mix_file_kind, True)
eq_(s.word_weighting, False)
eq_(s.match_similar_words, False)
eq_(s.big_file_size_threshold, 0)
def test_simple_with_default_settings(fake_fileexists):
@@ -120,9 +121,9 @@ def test_content_scan(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.Contents
f = [no("foo"), no("bar"), no("bleh")]
f[0].md5 = f[0].md5partial = "foobar"
f[1].md5 = f[1].md5partial = "foobar"
f[2].md5 = f[2].md5partial = "bleh"
f[0].md5 = f[0].md5partial = f[0].md5samples = "foobar"
f[1].md5 = f[1].md5partial = f[1].md5samples = "foobar"
f[2].md5 = f[2].md5partial = f[1].md5samples = "bleh"
r = s.get_dupe_groups(f)
eq_(len(r), 1)
eq_(len(r[0]), 2)
@@ -141,13 +142,43 @@ def test_content_scan_compare_sizes_first(fake_fileexists):
eq_(len(s.get_dupe_groups(f)), 0)
def test_big_file_partial_hashes(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.Contents
smallsize = 1
bigsize = 100 * 1024 * 1024 # 100MB
s.big_file_size_threshold = bigsize
f = [no("bigfoo", bigsize), no("bigbar", bigsize),
no("smallfoo", smallsize), no("smallbar", smallsize)]
f[0].md5 = f[0].md5partial = f[0].md5samples = "foobar"
f[1].md5 = f[1].md5partial = f[1].md5samples = "foobar"
f[2].md5 = f[2].md5partial = "bleh"
f[3].md5 = f[3].md5partial = "bleh"
r = s.get_dupe_groups(f)
eq_(len(r), 2)
# md5partial is still the same, but the file is actually different
f[1].md5 = f[1].md5samples = "difffoobar"
# here we compare the full md5s, as the user disabled the optimization
s.big_file_size_threshold = 0
r = s.get_dupe_groups(f)
eq_(len(r), 1)
# here we should compare the md5samples, and see they are different
s.big_file_size_threshold = bigsize
r = s.get_dupe_groups(f)
eq_(len(r), 1)
def test_min_match_perc_doesnt_matter_for_content_scan(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.Contents
f = [no("foo"), no("bar"), no("bleh")]
f[0].md5 = f[0].md5partial = "foobar"
f[1].md5 = f[1].md5partial = "foobar"
f[2].md5 = f[2].md5partial = "bleh"
f[0].md5 = f[0].md5partial = f[0].md5samples = "foobar"
f[1].md5 = f[1].md5partial = f[1].md5samples = "foobar"
f[2].md5 = f[2].md5partial = f[2].md5samples = "bleh"
s.min_match_percentage = 101
r = s.get_dupe_groups(f)
eq_(len(r), 1)
@@ -162,13 +193,12 @@ def test_content_scan_doesnt_put_md5_in_words_at_the_end(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.Contents
f = [no("foo"), no("bar")]
f[0].md5 = f[
0
].md5partial = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
f[1].md5 = f[
1
].md5partial = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
f[0].md5 = f[0].md5partial = f[0].md5samples =\
"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
f[1].md5 = f[1].md5partial = f[1].md5samples =\
"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
r = s.get_dupe_groups(f)
# FIXME looks like we are missing something here?
r[0]
@@ -514,21 +544,21 @@ def test_folder_scan_exclude_subfolder_matches(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.Folders
topf1 = no("top folder 1", size=42)
topf1.md5 = topf1.md5partial = b"some_md5_1"
topf1.md5 = topf1.md5partial = topf1.md5samples = b"some_md5_1"
topf1.path = Path("/topf1")
topf2 = no("top folder 2", size=42)
topf2.md5 = topf2.md5partial = b"some_md5_1"
topf2.md5 = topf2.md5partial = topf2.md5samples = b"some_md5_1"
topf2.path = Path("/topf2")
subf1 = no("sub folder 1", size=41)
subf1.md5 = subf1.md5partial = b"some_md5_2"
subf1.md5 = subf1.md5partial = subf1.md5samples = b"some_md5_2"
subf1.path = Path("/topf1/sub")
subf2 = no("sub folder 2", size=41)
subf2.md5 = subf2.md5partial = b"some_md5_2"
subf2.md5 = subf2.md5partial = subf2.md5samples = b"some_md5_2"
subf2.path = Path("/topf2/sub")
eq_(len(s.get_dupe_groups([topf1, topf2, subf1, subf2])), 1) # only top folders
# however, if another folder matches a subfolder, keep in in the matches
otherf = no("other folder", size=41)
otherf.md5 = otherf.md5partial = b"some_md5_2"
otherf.md5 = otherf.md5partial = otherf.md5samples = b"some_md5_2"
otherf.path = Path("/otherfolder")
eq_(len(s.get_dupe_groups([topf1, topf2, subf1, subf2, otherf])), 2)
@@ -551,9 +581,9 @@ def test_dont_count_ref_files_as_discarded(fake_fileexists):
o1 = no("foo", path="p1")
o2 = no("foo", path="p2")
o3 = no("foo", path="p3")
o1.md5 = o1.md5partial = "foobar"
o2.md5 = o2.md5partial = "foobar"
o3.md5 = o3.md5partial = "foobar"
o1.md5 = o1.md5partial = o1.md5samples = "foobar"
o2.md5 = o2.md5partial = o2.md5samples = "foobar"
o3.md5 = o3.md5partial = o3.md5samples = "foobar"
o1.is_ref = True
o2.is_ref = True
eq_(len(s.get_dupe_groups([o1, o2, o3])), 1)